Data processing method and device for multi-parameter health monitoring sensor

Abstract

The invention relates to a data processing method and device for a multi-parameter health monitoring sensor, and the method comprises the following steps: carrying out the continuous recording of a target user, and obtaining a multi-channel monitoring data flow; carrying out heartbeat profile description on the multi-channel monitoring data stream based on a heartbeat feature reconstructor to obtain heart activity parameters; carrying out heartbeat rule analysis on the target user based on the heart activity parameters to obtain heart working characteristics; performing heart state evaluation on the heart working characteristics to obtain heart operation data; and if the heart running data is not within the preset heart running range, performing dynamic health tracking on the target user based on the heart running data to obtain a heart health report, thereby solving the problem that the traditional heart health monitoring means mainly depends on regular physical examination and static electrocardiogram detection, and the monitoring accuracy is high. Dynamic changes and individual differences of heart activities are difficult to capture, so that potential heart risks cannot be early warned and intervened in time.

Description

Technical Field

[0001] The present invention relates to the technical field of health monitoring sensors, and in particular to a data processing method and device for a multi-parameter health monitoring sensor. Background Art

[0002] Traditional heart health monitoring methods mainly rely on regular physical examinations and static electrocardiogram tests, which are difficult to capture the dynamic changes and individual differences in heart activity, and thus cannot timely warn and intervene in potential heart risks. At the same time, most existing portable heart monitoring devices only focus on a single parameter, such as heart rate, and lack the acquisition and analysis of comprehensive, multi-dimensional information on heart activity, making it difficult to provide personalized and accurate health guidance. This makes the need for continuous, dynamic, and multi-parameter monitoring of heart health increasingly urgent, in order to achieve early warning, early diagnosis, and early intervention, thereby effectively reducing the morbidity and mortality of cardiovascular diseases.

[0003] However, there are still many challenges to achieve truly dynamic, multi-parameter heart health monitoring. First, how to effectively extract and integrate key features related to heart health from multi-channel monitoring data streams and construct an accurate heartbeat profile remains a technical challenge. Secondly, how to convert the extracted heart activity parameters into understandable and quantifiable health indicators and establish an association model with disease risk requires in-depth medical research and data analysis. In addition, how to present complex monitoring data and analysis results in a user-friendly manner and provide personalized health management recommendations are also important aspects that need attention.

[0004] Therefore, developing a data processing method for multi-parameter health monitoring sensors that can effectively process multi-channel monitoring data streams and achieve heartbeat contour depiction, heart state assessment, and dynamic health tracking is of great significance for improving the prevention and treatment of cardiovascular diseases. This requires the integration of multidisciplinary knowledge and technologies such as sensor technology, signal processing technology, medical knowledge, and artificial intelligence algorithms, in order to break through the bottleneck of existing technologies and ultimately achieve comprehensive, accurate, and dynamic monitoring and management of heart health. Summary of the invention

[0005] The main purpose of the present invention is to provide a data processing method and device for a multi-parameter health monitoring sensor, which solves the technical problem that traditional heart health monitoring methods mainly rely on regular physical examinations and static electrocardiogram tests, which are difficult to capture the dynamic changes and individual differences in heart activity, and thus cannot timely warn and intervene in potential heart risks.

[0006] To achieve the above object, the present invention provides a data processing method for a multi-parameter health monitoring sensor, comprising the following steps: The target user is continuously recorded through the preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream; Based on the heartbeat feature reconstructor, the heartbeat contour is depicted on the multi-channel monitoring data stream to obtain heart activity parameters; Analyze the heartbeat pattern of the target user based on the heart activity parameters to obtain heart working characteristics; Performing a heart state assessment on the heart working characteristics to obtain heart operation data; If the heart operation data is not within a preset heart operation range, dynamic health tracking is performed on the target user based on the heart operation data to obtain a heart health report.

[0007] The present invention also provides a data processing device for a multi-parameter health monitoring sensor, comprising: A recording module is used to continuously record the target user through a preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream; A depiction module, used for depicting the heartbeat contour of the multi-channel monitoring data stream based on a heartbeat feature reconstructor to obtain heart activity parameters; An analysis module, configured to analyze the heartbeat pattern of the target user based on the heart activity parameters to obtain heart working characteristics; An evaluation module, used for evaluating the cardiac state of the cardiac operating characteristics to obtain cardiac operation data; The tracking module is used to perform dynamic health tracking on the target user based on the heart operation data to obtain a heart health report if the heart operation data is not within a preset heart operation range.

[0008] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0009] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0010] The data processing method of the multi-parameter health monitoring sensor provided by the present invention comprises the following steps: continuously recording the target user through a preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream; based on a heartbeat feature reconstructor, the heartbeat contour of the multi-channel monitoring data stream is depicted to obtain heart activity parameters; based on the heart activity parameters, the heartbeat regularity of the target user is analyzed to obtain heart working characteristics; the heart state of the heart working characteristics is evaluated to obtain heart operation data; if the heart operation data is not within the preset heart operation range, the target user is dynamically tracked based on the heart operation data to obtain a heart health report, which solves the problem that traditional heart health monitoring methods mainly rely on regular physical examinations and static electrocardiogram tests, and it is difficult to capture the dynamic changes and individual differences of heart activity, so that it is impossible to timely warn and intervene in potential heart risks, and realize dynamic health tracking of users based on heart operation data, and finally form a heart health report. This makes it possible to track individual heart health changes for a long time, facilitates timely adjustment of treatment plans or lifestyle recommendations, thereby effectively preventing the occurrence of cardiovascular events, and also provides a strong technical effect of supporting patient self-management. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a schematic diagram of the steps of a data processing method for a multi-parameter health monitoring sensor in one embodiment of the present invention; Figure 2 is a structural block diagram of a data processing device for a multi-parameter health monitoring sensor in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0012] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0013] 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.

[0014] like Figure 1 As shown, Figure 1 It is a schematic diagram of the steps of a data processing method for a multi-parameter health monitoring sensor in one embodiment of the present invention; In one embodiment of the present invention, a data processing method for a multi-parameter health monitoring sensor is provided, comprising the following steps: Step S1, continuously record the target user through a preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream.

[0015] Specifically, in the process of realizing the above-mentioned "continuously recording the target user through the preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream", we have deeply explored how to use advanced sensing technology and data acquisition methods to comprehensively and continuously monitor the user's physiological state. This process not only relies on high-precision sensor equipment, but also requires an efficient data processing system to ensure the accuracy and integrity of the data. Specifically, the multi-parameter health monitoring sensor can simultaneously record multiple physiological parameters, such as electrocardiogram (ECG), blood pressure, blood oxygen saturation (SpO2), respiratory rate, and body temperature, thereby providing rich basic data for subsequent cardiac activity analysis. First, in order to ensure the reliability and accuracy of the data, the preset multi-parameter health monitoring sensor is usually designed with high sensitivity and high resolution. These sensors can capture multiple physiological signals of the target user in real time and convert these signals into digital data streams. For example, in a marathon runner who runs frequently, the sensor can continuously record the changes in heart rate, blood pressure fluctuations, and changes in blood oxygen saturation during exercise. These data can not only reflect the athlete's physical response during high-intensity training, but also help coaches and doctors assess their heart health. The sensor transmits these raw data to the central processing unit in the form of multiple channels to form a multi-channel monitoring data stream. Next, in order to ensure the stability and consistency of the data stream, the sensor device is usually equipped with a built-in calibration mechanism and adaptive algorithm. These mechanisms can automatically adjust the sensitivity and response time of the sensor under different environmental conditions to ensure the accuracy of data collection. For example, when a user suddenly enters a strenuous exercise from a static state, the sensor needs to quickly adapt to this change to avoid data loss or distortion. In addition, the sensor also has anti-interference ability and can maintain stable performance in a complex electromagnetic environment, which is particularly important for long-term continuous monitoring. In practical applications, suppose an elderly person with a history of heart disease wears such a multi-parameter health monitoring device. The device can continuously record various physiological parameters in his daily life and upload these data to the cloud platform in real time. In this way, doctors can access the elderly's health data at any time and discover potential risk factors in time. For example, if the platform detects that the elderly frequently have short-term arrhythmias or signs of myocardial ischemia over a period of time, it can automatically notify medical staff and recommend further examinations. This continuous recording method not only improves the early detection rate of heart disease, but also provides strong support for personalized health management. To further improve the quality of data, sensor devices will also combine intelligent algorithms for preliminary data processing and screening. These algorithms can identify outliers and filter them to reduce the impact of noise on data analysis. For example, some algorithms can establish a normal range model based on historical data. When new data exceeds this range, the system will issue an alarm to alert users or medical staff to pay attention.In addition, the sensor can also be customized according to the specific needs of the user, such as adjusting the sampling frequency or selecting a specific combination of monitoring parameters to meet the needs of different application scenarios. In short, the process of continuously recording the target user through the preset multi-parameter health monitoring sensor can not only obtain high-quality multi-channel monitoring data streams, but also lay a solid foundation for subsequent cardiac activity analysis. The application of this method not only improves the accuracy of heart disease diagnosis, but also provides a scientific basis for personalized health management. Whether for professional athletes or ordinary users, this continuous monitoring method can escort their health and provide all-round support and protection.

[0016] Step S2, based on the heartbeat feature reconstructor, the heartbeat contour is depicted on the multi-channel monitoring data stream to obtain heart activity parameters.

[0017] Specifically, when implementing the process of "depicting the heartbeat contour of the multi-channel monitoring data stream based on the heartbeat feature reconstructor to obtain the heart activity parameters" mentioned above, we deeply explore how to accurately extract and analyze the key information of the heart's electrical activity through advanced algorithms and technical means. This step is immediately after the multi-parameter health monitoring sensor continuously records the heart's electrical activity of the target user. When the sensor collects a large amount of raw physiological signals, these data need to be processed to reveal the heart activity patterns hidden therein. The heartbeat feature reconstructor is an indispensable core component in this process. It uses complex mathematical models and machine learning algorithms to parse the information in the multi-channel monitoring data stream. First, the reconstructor identifies and separates the key event points in each heartbeat cycle, such as the characteristic waveforms on the electrocardiogram such as the P wave, QRS complex wave and T wave, which correspond to the changes in the electrical activity of the heart at different stages. Next, through the precise positioning and quantitative analysis of these feature points, the reconstructor can reconstruct the contour of each heartbeat cycle, that is, the heartbeat contour depiction. This depiction is not just a simple time series graph of the ECG signal, but more importantly, it can capture subtle changes within each heartbeat cycle, including but not limited to important indicators such as heart rate variability, stability of RR intervals, and ST segment deviation. These heart activity parameters are crucial for evaluating the working state of the heart. For example, in daily life, when a user wearing a multi-parameter health monitoring device exercises, his heart rate will change significantly. As the intensity of exercise increases, the heartbeat speeds up, and the heart needs to pump blood more frequently to meet the needs of the body. At this time, the heartbeat feature reconstructor can keenly detect these changes and accurately depict the outline of each heartbeat, even in the case of fast or irregular heartbeats. It can maintain high accuracy. For example, if the user has a short-term arrhythmia, such as premature beats or atrial fibrillation, the reconstructor can not only identify the abnormal heartbeat pattern, but also calculate related activity parameters, such as the frequency and duration of premature beats and the impact on the overall heart rate. These parameters provide a solid foundation for subsequent heartbeat regularity analysis, helping doctors or health managers better understand the performance of the heart under specific conditions. In addition, to ensure the accuracy of the heartbeat contour, the heartbeat feature reconstructor also considers data input from other channels, such as the user's breathing rate, body movement, and other factors that may affect heart activity. By comprehensively analyzing these multi-source information, the reconstructor can maintain its performance in a more complex and dynamic environment. Ultimately, the multi-channel monitoring data stream processed by the reconstructor is converted into a series of meaningful heart activity parameters, which are not only an intuitive reflection of the heart's working characteristics, but also lay the foundation for further heart status assessment and the formulation of personalized health management plans.In short, the heartbeat feature reconstructor serves as a bridge between raw data and clinical significance, allowing us to extract valuable information from the complex electrical activity of the heart, thus providing strong support for the maintenance of cardiovascular health.

[0018] Step S3, analyzing the heartbeat pattern of the target user based on the heart activity parameters to obtain heart working characteristics.

[0019] Specifically, when implementing the process of "analyzing the heartbeat pattern of the target user based on the heart activity parameters to obtain the heart working characteristics" mentioned above, we continue to explore in depth along the data processing chain constructed by the multi-parameter health monitoring sensor and the heartbeat feature reconstructor. When the heartbeat feature reconstructor successfully extracts detailed heart activity parameters from the multi-channel monitoring data stream, the next key step is to use these parameters to perform in-depth heartbeat pattern analysis. This analysis is not only aimed at revealing the operation mode of the heart in different time periods, but also aims to identify abnormal patterns that may indicate potential cardiovascular problems. The core of heartbeat pattern analysis is to evaluate the relationship between heart activity parameters and their changing trends over time through a series of algorithms and technical means. For example, heart rate variability (HRV) is one of the important indicators for measuring heart adaptability, which reflects the ability of the autonomic nervous system to control the heart. By carefully analyzing the fluctuations of the RR interval, we can understand the speed and efficiency of the heart's response to changes in the internal and external environment. In addition, there are parameters such as QRS complex width and ST segment deviation, which together form the basis for describing the heart's working characteristics. These parameters can reflect the state of the heart's electrical conduction system and the working conditions of myocardial cells, thereby providing a basis for a deeper assessment of heart health. To ensure the accuracy of the analysis results, multiple factors are considered during the heartbeat pattern analysis process. Take a user wearing a multi-parameter health monitoring device as an example. In daily life, the user's physiological state will be affected by multiple factors, such as exercise, mood swings, or sleep quality. When a user starts a morning run, his heart rate may rise rapidly, and then gradually return to normal after the run. In this process, the heartbeat pattern analysis tool can capture the rate of heart rate acceleration and deceleration, as well as the time required to return to the base heart rate. If a user experiences a brief arrhythmia at a specific moment, such as a premature beat, the analysis tool can not only detect the occurrence of this event, but also further quantify its frequency, duration, and impact on the overall heart rate. Through such analysis, we can have a more comprehensive understanding of the heart's performance in response to external stimuli, and judge whether there is potential dysfunction in the heart. In addition to the analysis of parameters within a single heartbeat cycle, heartbeat pattern analysis also focuses on the overall trend of heart activity in a long time series. For example, long-term tracking of a user's heart rate variability can help doctors find problems such as sympathetic overactivity caused by chronic stress or weakened parasympathetic function. At the same time, for certain special groups, such as athletes or the elderly, heartbeat pattern analysis can also customize personalized health monitoring plans according to their specific needs.For example, for a well-trained marathon runner, the analysis tool can monitor the response of his heart during high-intensity training and evaluate whether the heart can effectively cope with the challenges brought by strenuous exercise; for an elderly person with a history of heart disease, it can focus on monitoring the stability of the heart at rest and with slight activity, and promptly warn of possible risks. In short, through in-depth analysis of cardiac activity parameters, we can not only obtain detailed information about the working characteristics of the heart, but also provide users with valuable health guidance. Heartbeat pattern analysis, as an important link between cardiac activity parameters and the final heart health report, enables us to detect signs of cardiac abnormalities at an early stage, so as to take preventive measures or adjust treatment plans, providing strong scientific support for the maintenance of cardiovascular health. The application of this method not only improves the accuracy of heart disease diagnosis, but also lays a solid foundation for personalized health management.

[0020] Step S4, performing a heart state assessment on the heart working characteristics to obtain heart operation data.

[0021] Specifically, in the key step of "carrying out a cardiac state assessment on the cardiac working characteristics to obtain cardiac operation data" mentioned above, we further explored how to convert the cardiac working characteristics obtained from the heartbeat pattern analysis into clinically significant cardiac operation data. This process is not only a quantitative description of cardiac health status, but also an important basis for providing users with personalized health management advice. By integrating various cardiac activity parameters and heartbeat pattern information obtained in the previous steps, the cardiac state assessment aims to build a comprehensive and dynamic cardiac health portrait, thereby supporting doctors to make more accurate diagnostic decisions and helping users better understand the working status of their own hearts. When the heartbeat pattern analysis is completed and a series of cardiac working characteristics are generated, these characteristics will be input into a specially designed state assessment algorithm. The algorithm will conduct a detailed assessment of each characteristic based on pre-set medical standards and reference values. For example, heart rate variability (HRV) is an important indicator for measuring the cardiac autonomic nervous regulation function. A lower HRV may indicate an increased cardiovascular risk; while a higher HRV is usually associated with good cardiac fitness and health status. Through the comprehensive evaluation of HRV and other cardiac activity parameters such as RR interval stability and QRS complex width changes, specific conclusions about the cardiac electrical conduction system and myocardial cell function can be drawn. In addition, the evaluation algorithm will pay special attention to parameters such as ST segment deviation that can reflect myocardial ischemia to identify potential heart attack risks. In order to ensure the reliability and accuracy of the evaluation results, the cardiac state assessment not only relies on data at a single time point, but also considers the overall trend of cardiac activity in a long time series. Taking users wearing multi-parameter health monitoring devices as an example, in daily life, the user's physiological state fluctuates with time and activity level. Suppose a user who runs frequently suddenly experiences a short arrhythmia or abnormal acceleration of heart rate during a certain exercise. Although this event may be temporary, if it occurs frequently, it may indicate a potential problem. Therefore, the cardiac state assessment tool records the frequency, duration and impact of such events on the overall heart rate, and combines them with the user's historical health data for comparative analysis. In this way, not only the instantaneous impact of acute events can be captured, but also long-standing chronic problems can be revealed, such as sympathetic overactivity or parasympathetic weakening caused by chronic stress. For example, for a well-trained marathon runner, a heart status assessment can help monitor the performance of his heart during high-intensity training, ensuring that the heart can maintain efficient operation under extreme conditions and quickly restore normal function during the recovery period. For an elderly person with a history of heart disease, the assessment tool can focus on tracking the stability of the heart at rest and with light activity, and promptly warn of possible risks, such as early detection of arrhythmias or myocardial ischemia, so that preventive measures can be taken or treatment plans adjusted.Through such an assessment, users can obtain a detailed heart health report, which not only contains current heart operation data, but also provides predictions and suggestions for future heart health. In short, heart status assessment, as a key link connecting heart working characteristics with the final health report, allows us to fully understand the working status of the heart from multiple dimensions. Through in-depth analysis and comprehensive evaluation of heart activity parameters, it can not only provide more accurate diagnostic information, but also lay a solid foundation for personalized health management. The application of this method not only improves the accuracy of heart disease diagnosis, but also provides strong support for the prevention and management of cardiovascular diseases, helping users to better maintain their own heart health.

[0022] Step S5: If the heart operation data is not within the preset heart operation range, dynamic health tracking is performed on the target user based on the heart operation data to obtain a heart health report.

[0023] Specifically, in the process of "if the heart operation data is not within the preset heart operation range, the target user is dynamically tracked based on the heart operation data to obtain a heart health report" mentioned above, we have explored in depth how to use advanced data analysis and early warning mechanisms to respond to abnormal heart operation in a timely manner. When the monitoring system detects that the heart operation data exceeds the preset safety range, it means that there may be potential cardiovascular risks or abnormalities. At this time, the system will immediately start the dynamic health tracking program to ensure that the user's current heart condition can be quickly and accurately assessed and a detailed heart health report can be generated. Specifically, once the heart operation data deviates from the normal reference value, the system will first conduct a comprehensive analysis of these abnormal data. For example, if the heart rate variability is significantly reduced or the ventricular contraction force is abnormally increased, this may be a manifestation of excessive stress on the heart. The system will perform multi-dimensional health status prediction analysis based on these heart operation data, and reveal the changing trend of health status through time series trend analysis. For a marathon runner who runs frequently, if the platform detects abnormal heart operation data during high-intensity training, such as a high heart rate and slow recovery, this may indicate the risk of overtraining. The system records these changes and further analyzes their long-term impact. Next, in order to assess potential health risks, the system conducts a dynamic risk assessment of the trend of health status changes. Dynamic risk assessment not only quantifies cardiac health risk parameters, but also reveals risk distribution characteristics, including high-risk areas, low-risk areas, and dynamic risk transfer paths. For example, if a user frequently experiences short-term arrhythmia or signs of myocardial ischemia over a period of time, the system will automatically mark it as a high-risk event and notify medical personnel to recommend further examination. Through a detailed analysis of the distribution characteristics of cardiac health risks, we can better understand the response mechanism of the heart under different conditions and provide a basis for personalized health management. Based on the above-mentioned cardiac health risk distribution characteristics, the system automatically generates a set of personalized health intervention recommendations, prioritizes them, and determines the priority of dynamic health intervention. For example, for elderly people with a history of heart disease, the system may emphasize the importance of regular monitoring and propose specific preventive measures, such as appropriately increasing aerobic exercise, reducing high-fat food intake, and taking medications on time. Subsequently, the system will evaluate the effectiveness of health intervention measures through multi-parameter performance simulation analysis, and adjust the optimized health intervention plan based on feedback to ensure that the intervention measures are always in the best state. Finally, the system will monitor the health status of the target user in real time, obtain dynamic health monitoring data, and generate health monitoring feature sequences through multi-scale association analysis. Based on these feature sequences, the system will generate a detailed heart health report, including heart function scores and risk level assessment results. This report not only summarizes the user's current heart working status, but also provides directions and suggestions for future health management, helping users take necessary preventive measures in a timely manner to maintain their own heart health.For example, in daily life, when a user wearing a multi-parameter health monitoring device exercises, his heart rate will change significantly. If the monitoring system finds that the heart operation data exceeds the preset range, such as abnormal conditions such as premature beats or atrial fibrillation, the system can not only identify abnormal heartbeat patterns, but also calculate related activity parameters, such as the frequency and duration of premature beats and the impact on the overall heart rate. This information provides a solid foundation for subsequent dynamic health tracking, helping doctors or health managers to better understand the performance of the heart under specific conditions, so as to take timely intervention measures to ensure the health and safety of users.

[0024] In a specific embodiment, the multi-parameter health monitoring sensor includes an electrocardiogram sensor, an acoustic sensor, and a pulse wave sensor. The target user is continuously recorded by the preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream, including: The target user's cardiac electrical activity is collected and continuously recorded by using a preset electrocardiogram sensor and an acoustic sensor to obtain a first set of original physiological signals, and the target user's blood vessels are continuously monitored and collected by using a pulse wave sensor to obtain a second set of original physiological signals; Based on the empirical mode decomposition algorithm, the first original physiological signal set and the second original physiological signal are respectively decomposed at multiple scales to obtain an intrinsic mode function group; wherein the intrinsic mode function group includes an electrocardiogram waveform component, a cardiac sound spectrum component and a pressure fluctuation component; Continuously processing the intrinsic mode function group to obtain a continuous signal sequence; Feature extraction is performed on the continuous signal sequence to obtain a multi-channel monitoring data stream; wherein the multi-channel monitoring data stream includes heartbeat waveform data, heart sound data and vascular pressure data.

[0025] Specifically, in the process of realizing the above-mentioned "continuously recording the target user through the preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream", we have deeply explored how to use multiple sensors and advanced signal processing technologies to comprehensively and continuously monitor the user's physiological state. This process not only relies on high-precision ECG sensors, acoustic sensors and pulse wave sensors, but also needs to combine empirical mode decomposition (EMD) algorithms and other advanced signal processing methods to ensure the accuracy and integrity of the data. First, in order to obtain high-quality original physiological signals, the preset ECG sensors and acoustic sensors are used to collect and continuously record the target user's cardiac electrical activity from multiple sources to obtain the first set of original physiological signals. At the same time, the target user's blood vessels are continuously monitored and collected through the pulse wave sensor to obtain the second original physiological signal. These sensors can capture the user's cardiac electrical activity, heart sounds, and vascular pressure changes in real time. For example, in a marathon runner who runs frequently, the ECG sensor can continuously record the changes in his heart rate during exercise, the acoustic sensor can capture the sound characteristics of the heart, and the pulse wave sensor can monitor blood oxygen saturation and blood pressure fluctuations. These data can not only reflect the physical response of athletes during high-intensity training, but also help coaches and doctors assess their heart health. Next, in order to further analyze these original physiological signals, the empirical mode decomposition (EMD) algorithm was used to perform multi-scale decomposition on the first original physiological signal set and the second original physiological signal to obtain an intrinsic mode function group. EMD is an adaptive data analysis method that can decompose complex signals into multiple intrinsic mode functions (IMFs), each of which represents a different frequency component of the signal. By applying the EMD algorithm to the first original physiological signal set, an intrinsic mode function group including the ECG waveform component and the heart sound spectrum component can be obtained; similarly, by applying the EMD algorithm to the second original physiological signal, an intrinsic mode function group of the pressure fluctuation component can be obtained. These IMFs not only reflect the dynamic changes of the signal at different time scales, but also provide a basis for subsequent signal processing. Then, in order to convert these intrinsic mode function groups into continuous signal sequences that can be used for further analysis, continuous processing was performed. Specifically, by recombining the individual IMFs, a smooth and continuous time series is formed. This processing method can not only eliminate the noise interference in the original signal, but also retain the main characteristics of the signal. For example, in the above example of marathon runners, the ECG waveform components and heart sound spectrum components obtained after EMD decomposition can be recombined to generate continuous ECG signals and heart sound signals, which can more clearly show the working state of the athlete's heart during exercise. On this basis, in order to extract valuable feature information from the continuous signal sequence, feature extraction operations are performed.Feature extraction is a key step in signal processing, which aims to filter out the most representative features from a large amount of raw data for subsequent analysis. In this process, by performing frequency domain analysis, time domain analysis, and nonlinear dynamics analysis on continuous signal sequences, multi-channel monitoring data streams such as heartbeat waveform data, heart sound data, and vascular pressure data can be obtained. For example, heartbeat waveform data can reflect the QRS complex characteristics, P wave characteristics, and T wave characteristics in the electrocardiogram; heart sound data contains important information such as the first heart sound (S1) and the second heart sound (S2); and vascular pressure data shows the changes in the pulse waveform. These data not only describe the specific performance of the heart in each heartbeat, but also provide an important basis for subsequent heart activity analysis. For example, in daily life, when an elderly person with a history of heart disease wears a multi-parameter health monitoring device, the device can continuously record various physiological parameters in his daily life and upload these data to the cloud platform in real time. In this way, doctors can access the health data of the elderly at any time and discover potential risk factors in a timely manner. For example, if the platform detects that an elderly person frequently experiences short-term arrhythmia or signs of myocardial ischemia over a period of time, it can automatically notify medical personnel and recommend further examination. This continuous recording method not only improves the early detection rate of heart disease, but also provides strong support for personalized health management. In addition, suppose a marathon runner uses this multi-parameter health monitoring device during preparation for the competition. The device can record its electrocardiogram, heart sound, and pulse wave data in real time, and perform multi-scale decomposition of these data through the EMD algorithm to obtain an intrinsic mode function group. Subsequently, by continuously processing and feature extracting these IMFs, multi-channel monitoring data streams such as heartbeat waveform data, heart sound data, and vascular pressure data are generated. These data not only help coaches understand the physical condition of the runners, but also help doctors assess their heart health status. For example, if the platform detects that the runner has abnormal heart rate fluctuations or heart sound changes during high-intensity training, it can remind the coach to adjust the training plan to avoid heart damage caused by overtraining. In short, the process of continuously recording the target user through the preset multi-parameter health monitoring sensor can not only obtain high-quality multi-channel monitoring data streams, but also lay a solid foundation for subsequent heart activity analysis. The application of this method not only improves the accuracy of heart disease diagnosis, but also provides a scientific basis for personalized health management. Whether for professional athletes or ordinary users, this continuous monitoring method can escort their health and provide all-round support and protection. By combining multiple sensors and advanced signal processing technology, we can better understand the working state of the heart under different conditions and provide strong scientific support for the maintenance of cardiovascular health. In this way, even in the face of complex heart problems, solutions can be found through detailed data analysis, thereby improving the overall health management effect.

[0026] In a specific embodiment, the heartbeat feature reconstructor is used to depict the heartbeat contour of the multi-channel monitoring data stream to obtain the heart activity parameter, including: Based on wavelet packet transform, the multi-channel monitoring data stream is decomposed in time and frequency domain to obtain a multi-scale feature sequence set, and nonlinear feature extraction is performed on the multi-scale feature sequence set to obtain heartbeat waveform features; wherein the heartbeat waveform features include QRS complex features, P wave features and T wave features; Performing instantaneous frequency analysis on the heartbeat waveform features to obtain heartbeat frequency domain features, and performing adaptive threshold segmentation on the heartbeat frequency domain features to obtain a heartbeat rhythm sequence; Extracting dynamic features from the heartbeat rhythm sequence to obtain cardiac dynamic features, and performing nonlinear functional calculation on the cardiac dynamic features to obtain cardiac function parameters; wherein the cardiac function parameters include ventricular contraction strength, atrial filling degree and cardiac pumping intensity; Performing nonlinear dynamic analysis on the target user based on cardiac function parameters to obtain a cardiac working state sequence, and performing entropy value calculation based on the cardiac working state sequence to obtain cardiac rhythm parameters; Based on the heart rhythm parameters, the heartbeat contour is depicted to obtain a heartbeat state trajectory diagram, and based on the heartbeat state trajectory diagram, the heart activity is calculated to obtain heart activity parameters; wherein the heart activity parameters include ventricular contraction duration, cardiac diastole duration and cardiac pumping efficiency.

[0027] Specifically, in the complex process of "depicting the heartbeat contour of the multi-channel monitoring data stream based on the heartbeat feature reconstructor to obtain the heart activity parameters", we have explored in depth how to use advanced signal processing technology and nonlinear analysis methods to accurately depict the heartbeat contour and extract clinically significant heart activity parameters from it. This step not only relies on the high-quality acquisition of multi-channel monitoring data streams, but also involves a series of precise data processing and feature extraction operations, and finally generates information that can fully describe the working state of the heart. With this method, we can provide strong scientific support for the maintenance of cardiovascular health. First, in order to obtain more refined heartbeat waveform features from multi-channel monitoring data streams, the wavelet packet transform (WPT) technology is used to decompose it in the time and frequency domain. WPT is a powerful tool that can analyze signals at different time scales to capture the changes in different frequency components in heart activity. Specifically, by applying WPT to multi-channel monitoring data streams, a set of multi-scale feature sequences can be obtained. These sequences contain the manifestations of cardiac electrical activity at multiple time scales, reflecting the dynamic changes of the heart at different frequencies. For example, characteristic waveforms on the electrocardiogram, such as QRS complex, P wave and T wave, will show different shapes and intensities at different time scales. By performing nonlinear feature extraction on these multi-scale feature sequence sets, the QRS complex features, P wave features and T wave features can be more accurately identified. These characteristic waveforms are important signs of cardiac electrical activity, and they directly reflect the working conditions of the heart's electrical conduction system and myocardial cells. Next, in order to further analyze the frequency information in the heartbeat waveform features, instantaneous frequency analysis was performed. Instantaneous frequency analysis can reveal the frequency characteristics of cardiac electrical activity over time, which is crucial for evaluating the working state of the heart. By performing instantaneous frequency analysis on the heartbeat waveform features, the heartbeat frequency domain features, that is, the changes in the frequency components within each heartbeat cycle, can be obtained. Then, in order to distinguish normal heartbeat rhythms from abnormal heartbeat events, the adaptive threshold segmentation method is used to process the heartbeat frequency domain features. Adaptive threshold segmentation can dynamically adjust the threshold according to the characteristics of each user's heart activity, thereby ensuring accurate recognition of the heartbeat rhythm sequence. For a marathon runner who runs frequently, this method can help distinguish between normal high heart rates and potential arrhythmias during training, and promptly warn of possible risks. After obtaining the heartbeat rhythm sequence, dynamic feature extraction was further performed on these sequences to obtain cardiac dynamic features. Cardiac dynamic features reflect the movement pattern and functional state of the heart in different time periods, including important indicators such as ventricular contraction strength, atrial filling degree, and cardiac pumping intensity. These indicators not only describe the performance of cardiac mechanical function, but also provide a basis for the subsequent calculation of cardiac function parameters.In order to quantify the dynamic characteristics of the heart, a nonlinear function calculation method was used. Nonlinear function calculation takes into account the complexity and uncertainty in cardiac activity and can more realistically reflect the working efficiency of the heart. For example, the strength of ventricular contraction can be estimated by analyzing the amplitude and width of the QRS complex; the degree of atrial filling can be judged by the morphological changes of the P wave; and the strength of cardiac pumping can be derived from the changes in the T wave and ST segment. In this way, we can not only understand the specific performance of the heart in each heartbeat, but also comprehensively evaluate its overall function. Based on the above cardiac function parameters, nonlinear dynamic analysis was performed on the target user to obtain the cardiac working state sequence. Nonlinear dynamic analysis aims to explore the inherent laws and complex patterns in cardiac activity, especially those phenomena that are difficult to explain with traditional linear models. By calculating the entropy of the cardiac working state sequence, cardiac rhythm parameters can be obtained. Entropy calculation is a method to measure the complexity and uncertainty of a system, and is used here to evaluate the stability and regularity of the cardiac rhythm. For example, a higher entropy value may indicate a larger heart rhythm variability or an irregular heartbeat pattern, which may be an indication of poor heart health. On the contrary, a lower entropy value is usually associated with a stable heartbeat rhythm. By analyzing the heart rhythm parameters, we can better understand the response mechanism of the heart under different conditions and provide a basis for personalized health management. Finally, the heartbeat contour is depicted based on the heart rhythm parameters to generate a heartbeat state trajectory diagram. The heartbeat state trajectory diagram is a way to intuitively show the trend of changes in heart activity. It shows the behavior of the heart in each heartbeat cycle as a continuous curve. By calculating the heart activity on the heartbeat state trajectory diagram, a series of heart activity parameters can be obtained, such as ventricular contraction duration, cardiac diastole duration, and heart pumping efficiency. These parameters not only describe the specific performance of the heart in a single heartbeat cycle, but also reflect the overall working state of the heart during the entire monitoring period. For example, for an elderly person with a history of heart disease, the heartbeat state trajectory diagram can help doctors observe the stability of their heart at rest and in a state of slight activity, and promptly identify potential risk factors. If the platform detects that the elderly frequently have short-term arrhythmias or signs of myocardial ischemia over a period of time, it can automatically notify medical personnel and recommend further examinations. For example, in daily life, when a user wearing a multi-parameter health monitoring device exercises, his heart rate will change significantly. As the intensity of exercise increases, the heart rate accelerates and the heart needs to pump blood more frequently to meet the needs of the body. At this time, the multi-channel monitoring data stream processed by the above steps can not only capture the subtle changes within each heartbeat cycle, but also record how the user's heart responds to different stimuli and stress situations during daily activities.If the user has a short-term arrhythmia, such as premature beats or atrial fibrillation, the reconstructor can not only identify the abnormal heartbeat pattern, but also calculate the relevant activity parameters, such as the frequency, duration and impact of premature beats on the overall heart rate. These parameters provide a solid foundation for the subsequent analysis of heartbeat patterns, helping doctors or health managers to better understand the performance of the heart under specific conditions. In short, through the process of heartbeat contouring of multi-channel monitoring data streams, we can not only extract valuable information from the complex heart activities, but also provide strong scientific support for the maintenance of cardiovascular health. The application of this method not only improves the accuracy of heart disease diagnosis, but also lays a solid foundation for personalized health management. By combining advanced signal processing technology and nonlinear analysis methods, we can construct a detailed heart health portrait and provide users with scientific and personalized health management suggestions. This method not only improves the accuracy and breadth of heart health monitoring, but also allows us to fully understand the working status of the heart from multiple dimensions and provide strong support for the prevention and management of cardiovascular diseases.

[0028] In a specific embodiment, the heartbeat regularity analysis of the target user based on the heart activity parameter to obtain the heart working characteristics includes: Performing heart rate variability analysis on the target user based on the heart activity parameters to obtain a heart rate variability parameter sequence; Performing a detrended fluctuation analysis on the heart rate variability parameter sequence to obtain a heart rate fluctuation spectrum, and performing a recursive graph analysis on the heart rate fluctuation spectrum to obtain a heart rate recursive pattern; Performing a Poincare diagram analysis on the target user based on the heart rate recursive mode to obtain a heartbeat cycle scatter plot, and performing an ellipse fitting analysis on the heartbeat cycle scatter plot to obtain a heartbeat cycle dispersion; wherein the heartbeat cycle dispersion includes a heartbeat cycle standard deviation SD1, a heartbeat cycle standard deviation SD2, and a SD1 / SD2 ratio; Reconstructing the heartbeat cycle discreteness in phase space to obtain a heartbeat phase space trajectory, and calculating the Lyapunov exponent of the heartbeat phase space trajectory to obtain a heartbeat chaos degree feature; wherein the heartbeat chaos degree feature includes a maximum Lyapunov exponent, a Lyapunov exponent spectrum, and a Lyapunov dimension; Based on the heartbeat chaos degree characteristics, wavelet transform analysis is performed on the target user to obtain the heartbeat time scale energy distribution, and singular value decomposition is performed on the heartbeat time scale energy distribution to obtain the heartbeat principal component characteristics; The target user's heartbeat pattern is analyzed based on the heartbeat principal component characteristics to obtain heart working characteristics; wherein the heart working characteristics include changes in heartbeat rhythm, changes in heart sound patterns, and changes in blood pressure fluctuations.

[0029] Specifically, in the complex and delicate process of "analyzing the heartbeat pattern of the target user based on the heart activity parameters to obtain the heart working characteristics" mentioned above, we have deeply explored how to use advanced signal processing technology and nonlinear dynamic analysis methods to reveal subtle changes in heart activity. This process not only relies on the heart activity parameters obtained in the previous step, but also involves a series of precise data processing and feature extraction operations, and finally generates information that can fully describe the heart's working state. Through this method, we can provide strong scientific support for the maintenance of cardiovascular health. First, in order to evaluate the regulatory function of the cardiac autonomic nervous system, the heart rate variability (HRV) analysis technology is used to process the heart activity parameters of the target user. HRV is one of the important indicators to measure the adaptability and health status of the heart. It reflects the ability of the sympathetic and parasympathetic nervous systems to control the heart. By performing a detailed analysis of data such as the RR interval in the heart activity parameters, a series of heart rate variability parameter sequences can be obtained. These parameter sequences include not only statistical values ​​in the time domain, such as average heart rate, standard deviation, etc., but also components in the frequency domain, such as low frequency (LF), high frequency (HF) power and their proportions. For a regular marathon runner, HRV analysis can help understand the heart's ability to respond to different training intensities, ensuring that the heart can maintain efficient operation under extreme conditions and quickly restore normal function during the recovery period. For example, if the platform detects that a user frequently experiences short-term arrhythmias or signs of myocardial ischemia over a period of time, it can automatically notify medical personnel and recommend further examinations. Next, in order to further analyze the long-term trends and short-term fluctuations in the heart rate variability parameter sequence, Detrended Fluctuation Analysis (DFA) was performed. DFA is a method for quantifying the self-similarity of time series, which can reveal the actual patterns hidden behind seemingly random heart rate fluctuations. By applying DFA to the heart rate variability parameter sequence, the heart rate fluctuation spectrum can be obtained, which shows the fluctuation characteristics on different time scales. Then, in order to explore the repeatability and regularity in these fluctuations, the recurrence plot (RP) analysis technique is used to process the heart rate fluctuation spectrum. The recurrence plot can intuitively display the changes in the system state over time. By analyzing the point distribution in the plot, the heart rate recurrence pattern can be obtained. This pattern reflects the inherent dynamics of cardiac activity and helps identify potential abnormal or irregular behavior. For example, if the platform detects that a user frequently experiences short-term arrhythmias or signs of myocardial ischemia over a period of time, it can automatically notify medical personnel and recommend further examination. After obtaining the recursive pattern of heart rate, Poincaré Plot analysis was further performed to more accurately depict the scatter plot of the heartbeat cycle.Poincare plot is a commonly used visualization tool. It can intuitively show the relationship between heartbeat cycles by plotting adjacent heartbeat cycles into a two-dimensional scatter plot. By performing ellipse fitting analysis on the heartbeat cycle scatter plot, the heartbeat cycle dispersion can be obtained, including the heartbeat cycle standard deviation SD1, the heartbeat cycle standard deviation SD2, and the SD1 / SD2 ratio. These parameters not only describe the degree of dispersion of the heartbeat cycle, but also reflect the balance state of the cardiac autonomic nervous system. For example, a higher SD1 value may indicate a larger short-term variability, which is usually a manifestation of parasympathetic nerve activity; while a higher SD2 value is related to heart rate changes on a longer time scale, which may be the result of sympathetic nerve influence. Through the comprehensive analysis of these parameters, we can better understand the response mechanism of the heart under different conditions and provide a basis for personalized health management. In order to further explore the deep information in the heartbeat cycle dispersion, phase space reconstruction was performed to construct the heartbeat phase space trajectory. Phase space reconstruction is a method to reconstruct system dynamics from time series, which can reveal the complex structure of cardiac activity. By reconstructing the phase space of the discreteness of the heartbeat cycle, the heartbeat phase space trajectory can be obtained, which intuitively shows the movement path of the heart in multidimensional space. Then, in order to evaluate the degree of chaos in cardiac activity, the Lyapunov exponent calculation technique was used. The Lyapunov exponent is a set of indicators used to measure the sensitivity and predictability of the system. Features such as the maximum Lyapunov exponent, the Lyapunov exponent spectrum, and the Lyapunov dimension can reflect the degree of chaos in cardiac activity. For example, a higher maximum Lyapunov exponent usually means that cardiac activity has a strong unpredictability, which may be an indication of poor heart health. On the contrary, a lower maximum Lyapunov exponent is usually associated with a stable heartbeat rhythm. By analyzing the characteristics of cardiac chaos, we can better understand the complexity and uncertainty in cardiac activity and provide a scientific basis for diagnosis and treatment. Finally, in order to comprehensively consider the multi-scale information in the characteristics of cardiac chaos, wavelet transform analysis was performed to obtain the energy distribution of the heartbeat time scale. Wavelet transform is a powerful tool that can analyze signals at different time scales, thereby capturing the changes in different frequency components in cardiac activity. By applying wavelet transform to the chaotic degree characteristics of heartbeat, the time-scale energy distribution of heartbeat can be obtained, which shows the energy distribution of the heart at different time scales. Then, in order to extract the main energy components, the singular value decomposition (SVD) technology is used to process the time-scale energy distribution of heartbeat. SVD can decompose complex matrices into a set of principal components, which represent the key features of heart activity.By analyzing the heartbeat regularity of the main component features of the heartbeat, the heart working characteristics can be obtained, including important indicators such as changes in heartbeat rhythm, changes in heart sound regularity, and changes in blood pressure fluctuations. For example, for elderly people with a history of heart disease, heart working characteristics can help doctors observe the stability of their hearts at rest and in a state of slight activity, and promptly discover potential risk factors. For example, in daily life, when a user wearing a multi-parameter health monitoring device exercises, his heart rate will change significantly. As the intensity of exercise increases, the heartbeat speeds up, and the heart needs to pump blood more frequently to meet the needs of the body. At this time, the heart activity parameters processed by the above steps can not only capture the subtle changes within each heartbeat cycle, but also record how the user's heart responds to different stimuli and stress conditions during daily activities. If the user has a short-term arrhythmia, such as premature beats or atrial fibrillation, the reconstructor can not only identify the abnormal heartbeat pattern, but also calculate related activity parameters, such as the frequency and duration of premature beats and the impact on the overall heart rate. These parameters provide a solid foundation for subsequent heartbeat regularity analysis, helping doctors or health managers better understand the performance of the heart under specific conditions. In short, through the process of analyzing the heartbeat pattern of cardiac activity parameters, we can not only extract valuable information from the complex cardiac activities, but also provide strong scientific support for the maintenance of cardiovascular health. The application of this method not only improves the accuracy of heart disease diagnosis, but also lays a solid foundation for personalized health management. By combining advanced signal processing technology and nonlinear dynamic analysis methods, we can construct a detailed portrait of heart health and provide users with scientific and personalized health management suggestions. This method not only improves the accuracy and breadth of heart health monitoring, but also allows us to fully understand the working status of the heart from multiple dimensions and provide strong support for the prevention and management of cardiovascular diseases.

[0030] In a specific embodiment, the step of performing a heart state assessment on the heart operating characteristics to obtain heart operation data includes: Performing a cardiac dynamics state analysis on the target user based on the cardiac working characteristics to obtain cardiac dynamics state parameters, and performing a nonlinear coupling analysis on the cardiac dynamics state parameters to obtain cardiac dynamic coupling characteristics; Performing multi-scale time series decomposition on the cardiac dynamic coupling characteristics to obtain a cardiac cycle dynamic feature sequence, and performing frequency domain correlation analysis on the cardiac cycle dynamic feature sequence to obtain a cardiac cycle spectrum characteristic; Based on the cardiac cycle spectrum characteristics, the target user is subjected to hemodynamic analysis to obtain hemodynamic parameters, and the hemodynamic parameters are subjected to waveform pattern recognition to obtain blood flow waveform characteristics; wherein the blood flow waveform characteristics include systolic blood flow waveform, diastolic blood flow waveform and pulse pressure waveform; Performing pulse wave propagation velocity analysis on the blood flow waveform characteristics to obtain pulse propagation velocity parameters, and performing arterial elasticity analysis on the pulse propagation velocity parameters to obtain arterial elasticity characteristics; wherein the arterial elasticity characteristics include arterial compliance, arteriosclerosis index and arterial dilatation capacity; Based on the arterial elasticity characteristics, a cardiac load assessment is performed on the target user to obtain a cardiac load parameter, and a cardiac metabolism analysis is performed on the cardiac load parameter to obtain a cardiac metabolic state characteristic; wherein the cardiac metabolic state characteristic includes myocardial oxygen consumption, myocardial metabolic efficiency, and cardiac energy consumption rate; A comprehensive cardiac function evaluation is performed on the cardiac metabolic state characteristics to obtain cardiac operation data; wherein the cardiac operation data includes the degree of heartbeat disorder, myocardial contraction strength and cardiac load level.

[0031] Specifically, in the key step of "evaluating the cardiac state of the cardiac working characteristics to obtain cardiac operation data" mentioned above, we deeply explored how to use advanced nonlinear dynamic analysis, multi-scale time series decomposition, hemodynamics and other technical means to comprehensively evaluate the working state of the heart. This process not only relies on the cardiac working characteristics obtained in the previous steps, but also involves a series of precise data processing and feature extraction operations, and finally generates data that can fully describe the working state of the heart. Through this method, we can provide strong scientific support for the maintenance of cardiovascular health. First, in order to evaluate the dynamic state of the heart, the cardiac dynamic state analysis method is used to process the cardiac working characteristics of the target user. The cardiac dynamic state parameters reflect the movement pattern and functional state of the heart in different time periods, including important indicators such as ventricular contraction strength, atrial filling degree and cardiac pumping intensity. These parameters not only describe the performance of the mechanical function of the heart, but also provide a basis for subsequent nonlinear coupling analysis. For example, for a marathon runner who runs frequently, cardiac dynamic state analysis can help understand the specific performance of his heart during high-intensity training, ensure that the heart can maintain efficient operation under extreme conditions, and can also quickly restore normal function during the recovery period. By performing nonlinear coupling analysis on these cardiac dynamic state parameters, the complex interaction between the various parts of the heart, namely the cardiac dynamic coupling characteristics, can be revealed. This characteristic reflects the coordinated working of the various subsystems within the heart as a complex system, which helps to identify potential dysfunction or abnormal behavior. Next, in order to further analyze the dynamic changes in the cardiac dynamic coupling characteristics, multiscale time series decomposition (Multiscale TimeSeries Decomposition) was performed. Multiscale time series decomposition is a technique used to capture the changes of signals at different time scales, which can reveal the actual patterns hidden behind seemingly random cardiac activities. By applying multiscale time series decomposition to the cardiac dynamic coupling characteristics, a cardiac cycle dynamic feature sequence can be obtained, which shows the detailed changes of the heart in a complete cardiac cycle. Then, in order to explore the frequency information in these dynamic features, the frequency-domain correlation analysis (Frequency-Domain Correlation Analysis) technique is used to process the cardiac cycle dynamic feature sequence. Frequency-domain correlation analysis can reveal the frequency characteristics of cardiac activity changing over time, which is crucial for evaluating the working state of the heart. By analyzing the cardiac cycle spectrum characteristics, the cardiac cycle spectrum characteristics can be obtained, which not only reflects the changing trend of cardiac electrical activity, but also provides a basis for subsequent hemodynamic analysis. Based on the above-mentioned spectral characteristics of the cardiac cycle, hemodynamic analysis was performed to obtain hemodynamic parameters.Hemodynamic parameters are important indicators for measuring the heart's ability to pump blood and the response of the vascular system. They directly reflect the interaction between the heart and blood vessels. By performing waveform pattern recognition on hemodynamic parameters, blood flow waveform characteristics, such as systolic blood flow waveform, diastolic blood flow waveform and pulse pressure waveform, can be obtained. These characteristic waveforms are not only key information for describing the heart's pumping process, but also provide clues for evaluating the health of the vascular system. For example, the systolic blood flow waveform can directly reflect the blood flow during ventricular contraction; while the diastolic blood flow waveform reflects the state of blood flow in the blood vessels when the heart is relaxed. The pulse pressure waveform shows the changes in blood pressure caused by each heartbeat, which is very important for evaluating the efficiency of the heart. In order to further evaluate the health of the vascular system, the pulse wave velocity analysis (Pulse Wave Velocity Analysis) was performed on the blood flow waveform characteristics to obtain the pulse velocity parameters. Pulse wave velocity is a set of indicators used to measure the elasticity and hardness of arteries. A higher propagation velocity usually means arteriosclerosis, which is a risk factor for cardiovascular disease. By performing arterial elasticity analysis on pulse propagation velocity parameters, arterial elasticity characteristics such as arterial compliance, arterial stiffness index, and arterial dilatation capacity can be obtained. These characteristics not only describe the physical properties of the artery, but also reflect the responsiveness of the artery to the heart's pumping. For example, higher arterial compliance means that the artery can better adapt to the pressure changes caused by the heart's pumping; while a lower arterial stiffness index indicates that the artery is softer, which is conducive to maintaining good blood circulation. Finally, based on the above arterial elasticity characteristics, a cardiac load assessment was conducted on the target users to obtain cardiac load parameters. Cardiac load parameters reflect the intensity of the heart's work under different conditions, including the heart burden at rest and in active states. By performing cardiac metabolic analysis on cardiac load parameters, cardiac metabolic state characteristics such as myocardial oxygen consumption, myocardial metabolic efficiency, and cardiac energy consumption rate can be obtained. These characteristics not only describe the heart's energy demand and utilization, but also provide important information for assessing the overall health of the heart. For example, higher myocardial oxygen consumption may indicate that the heart needs more oxygen supply, which may be a manifestation of overloaded heart; while higher myocardial metabolic efficiency means that the heart can complete the same amount of work at lower energy consumption, indicating good heart function. By comprehensively evaluating the characteristics of cardiac metabolic status, heart operation data can be obtained, including important indicators such as the degree of heartbeat disorder, myocardial contraction strength and cardiac load level. These data not only summarize the current working status of the heart, but also provide a scientific basis for personalized health management. For example, in daily life, when a user wearing a multi-parameter health monitoring device exercises, his heart rate will change significantly. As the intensity of exercise increases, the heartbeat speeds up, and the heart needs to pump blood more frequently to meet the needs of the body.At this point, the cardiac working characteristics processed by the above steps can not only capture the subtle changes within each heartbeat cycle, but also record how the user's heart responds to different stimuli and stress conditions during daily activities. If the user has a short-term arrhythmia, such as premature beats or atrial fibrillation, the reconstructor can not only identify the abnormal heartbeat pattern, but also calculate the relevant activity parameters, such as the frequency and duration of premature beats and the impact on the overall heart rate. These parameters provide a solid foundation for subsequent cardiac state assessment, helping doctors or health managers to better understand the performance of the heart under specific conditions. In short, through the process of cardiac state assessment based on cardiac working characteristics, we can not only extract valuable information from the complex cardiac activities, but also provide strong scientific support for the maintenance of cardiovascular health. The application of this method not only improves the accuracy of heart disease diagnosis, but also lays a solid foundation for personalized health management. By combining advanced nonlinear dynamic analysis, multi-scale time series decomposition, and hemodynamics, we can construct a detailed portrait of cardiac health and provide users with scientific and personalized health management suggestions. This method not only improves the accuracy and breadth of heart health monitoring, but also enables us to fully understand the working status of the heart from multiple dimensions and provide strong support for the prevention and management of cardiovascular diseases.

[0032] In a specific embodiment, the cardiac load assessment of the target user based on the arterial elasticity characteristics to obtain the cardiac load parameter includes: Based on the arterial elasticity characteristics, pulse wave impedance analysis is performed on the target user to obtain vascular mechanical impedance parameters, and cardiac afterload calculation is performed on the vascular mechanical impedance parameters to obtain cardiac afterload characteristics; wherein the cardiac afterload characteristics include aortic characteristic impedance, peripheral vascular resistance and vascular rebound coefficient; Performing volume-pressure relationship analysis on the cardiac afterload characteristics to obtain ventricular filling parameters, and performing preload dynamics calculation on the ventricular filling parameters to obtain cardiac preload characteristics; Performing ventricular wall tension analysis based on the cardiac preload characteristics to obtain ventricular wall stress parameters, and performing myocardial load distribution calculation on the ventricular wall stress parameters to obtain myocardial load distribution characteristics; Performing ventricular pressure-volume loop analysis on the myocardial load distribution characteristics to obtain ventricular function parameters, and performing cardiac work efficiency calculation on the ventricular function parameters to obtain cardiac mechanical performance characteristics; Performing cardiac energy consumption analysis based on the cardiac mechanical performance characteristics to obtain cardiac energy metabolism parameters, and performing myocardial supply and demand balance calculation on the cardiac energy metabolism parameters to obtain cardiac load balance characteristics; wherein the cardiac load balance characteristics include myocardial oxygen consumption, coronary perfusion pressure and myocardial oxygen reserve; A load integration evaluation is performed on the cardiac load balance characteristics to obtain a cardiac load parameter.

[0033] Specifically, in the complex and delicate process of "evaluating the cardiac load of the target user based on the arterial elasticity characteristics to obtain the cardiac load parameters" mentioned above, we have deeply explored how to use advanced vascular mechanics analysis, ventricular dynamics calculation, and energy metabolism evaluation to comprehensively evaluate the workload of the heart. This process not only relies on the arterial elasticity characteristics obtained in the previous steps, but also involves a series of precise data processing and feature extraction operations, and finally generates data that can fully describe the cardiac load status. With this method, we can provide strong scientific support for the maintenance of cardiovascular health. First, in order to evaluate the workload of the heart under different conditions, the arterial elasticity characteristics were processed using the pulse wave impedance analysis technology. Pulse wave impedance analysis aims to quantify the mechanical properties of the vascular system. By analyzing characteristics such as arterial compliance, arteriosclerosis index, and arterial expansion capacity, vascular mechanical impedance parameters can be obtained. These parameters reflect the resistance of the vascular system to the heart pumping blood, which is crucial for understanding the afterload of the heart. For example, a higher aortic characteristic impedance means that the blood flow encounters greater resistance, which increases the difficulty of the heart pumping blood; while a higher peripheral vascular resistance indicates that the resistance of the distal vascular bed is greater, affecting the overall blood circulation. By calculating the cardiac afterload of vascular mechanical impedance parameters, the cardiac afterload characteristics can be obtained, including aortic characteristic impedance, peripheral vascular resistance and vascular rebound coefficient. These characteristics not only describe the specific burden of the heart in each heartbeat, but also provide a basis for subsequent cardiac load assessment. Next, in order to further analyze the dynamic changes in the cardiac afterload characteristics, volume-pressure relationship analysis was performed. Volume-pressure relationship analysis is a method used to evaluate the filling state of the heart, which can reveal the filling state of the heart under different conditions. By applying volume-pressure relationship analysis to the cardiac afterload characteristics, ventricular filling parameters can be obtained, which reflect the filling state of the heart during diastole. Then, in order to evaluate the cardiac preload, that is, the resistance that the heart needs to overcome before contraction, the preload dynamics calculation technology was used to process the ventricular filling parameters. The preload dynamics calculation takes into account the volume changes of the heart at different stages and its impact on the myocardial contractility, thereby obtaining the cardiac preload characteristics. These characteristics not only describe the state of the heart at the beginning of each heartbeat, but also provide a basis for evaluating the overall function of the heart. Based on the above cardiac preload characteristics, ventricular wall tension analysis was performed to obtain ventricular wall stress parameters.Ventricular wall tension analysis aims to evaluate the stress on the ventricular wall in each heartbeat, which is very important for understanding the working intensity of the myocardium. By calculating the myocardial load distribution of ventricular wall stress parameters, the myocardial load distribution characteristics can be obtained, which show the load differences of the myocardium in different parts. For example, the myocardium in certain areas may be under greater pressure, which may be caused by local vascular stenosis or abnormal cardiac structure. By analyzing the myocardial load distribution characteristics in detail, we can better understand the working mode of the heart under different conditions and provide a scientific basis for personalized health management. In order to further evaluate the functional state of the heart, ventricular pressure-volume loop analysis was performed on the myocardial load distribution characteristics. Ventricular pressure-volume loop analysis is a classic method for evaluating cardiac function. It intuitively shows the working efficiency of the heart by drawing the pressure-volume change curve of the heart in a complete cardiac cycle. By analyzing the ventricular pressure-volume loop, ventricular function parameters can be obtained, which reflect the performance of the heart at different stages. Then, in order to evaluate the cardiac work efficiency, the cardiac work efficiency calculation technology was used to process the ventricular function parameters. The calculation of cardiac work efficiency considers the relationship between the mechanical work done by the heart in each heartbeat and the energy it consumes, thereby obtaining the characteristics of cardiac mechanical efficiency. These characteristics not only describe the working efficiency of the heart, but also provide important information for evaluating the overall health of the heart. Finally, based on the above cardiac mechanical efficiency characteristics, cardiac energy consumption analysis (Cardiac EnergyConsumption Analysis) was performed to obtain cardiac energy metabolism parameters. Cardiac energy consumption analysis aims to evaluate the energy demand and utilization of the heart under different conditions, which is very important for understanding the metabolic state of the heart. By performing myocardial supply and demand balance calculations on cardiac energy metabolism parameters, cardiac load balance characteristics can be obtained, including myocardial oxygen consumption, coronary perfusion pressure, and myocardial oxygen reserve. These characteristics not only describe the energy demand and supply of the heart, but also provide a basis for evaluating the overall function of the heart. For example, higher myocardial oxygen consumption may indicate that the heart needs more oxygen supply, which may be a manifestation of overloaded heart; while higher coronary perfusion pressure means that the heart has obtained sufficient blood supply, which is conducive to maintaining good heart function. By performing load integration evaluation on cardiac load balance characteristics, cardiac load parameters can be obtained, which not only summarize the current working state of the heart, but also provide a scientific basis for personalized health management. For example, in daily life, when a user wearing a multi-parameter health monitoring device exercises, his heart rate will change significantly. As the intensity of exercise increases, the heart rate speeds up and the heart needs to pump blood more frequently to meet the body's needs.At this point, the arterial elasticity features processed by the above steps can not only capture the subtle changes within each heartbeat cycle, but also record how the user's heart responds to different stimuli and pressure conditions during daily activities. If the user has a short-term arrhythmia, such as premature beats or atrial fibrillation, the reconstructor can not only identify the abnormal heartbeat pattern, but also calculate the relevant activity parameters, such as the frequency and duration of premature beats and the impact on the overall heart rate. These parameters provide a solid foundation for subsequent cardiac load assessment, helping doctors or health managers to better understand the performance of the heart under specific conditions. In short, through the process of cardiac load assessment of arterial elasticity features, we can not only extract valuable information from the complex cardiac activities, but also provide strong scientific support for the maintenance of cardiovascular health. The application of this method not only improves the accuracy of heart disease diagnosis, but also lays a solid foundation for personalized health management. By combining advanced vascular mechanics analysis, ventricular dynamics calculation, and energy metabolism assessment, we can construct a detailed portrait of heart health and provide users with scientific and personalized health management suggestions. This method not only improves the accuracy and breadth of heart health monitoring, but also enables us to fully understand the working status of the heart from multiple dimensions and provide strong support for the prevention and management of cardiovascular diseases.

[0034] In a specific embodiment, the dynamically tracking the health of the target user based on the heart operation data to obtain a heart health report includes: Based on the heart operation data, a multi-dimensional health status prediction analysis is performed on the target user to obtain health status prediction parameters, and a time series trend analysis is performed on the health status prediction parameters to obtain a health status change trend of the target user; Performing a dynamic risk assessment on the health status change trend to obtain a heart health risk parameter, and performing a risk cluster analysis on the heart health risk parameter to obtain a heart health risk distribution feature; wherein the heart health risk distribution feature includes a high-risk area, a low-risk area, and a dynamic risk transfer path; Based on the cardiac health risk distribution characteristics, individualized health intervention suggestions are generated for the target user to obtain a health intervention suggestion set, and the health intervention suggestion set is prioritized to obtain a dynamic health intervention priority; wherein the dynamic health intervention priority includes exercise suggestion priority, diet adjustment priority and drug management priority; Performing a multi-parameter effectiveness simulation analysis on the dynamic health intervention priority to obtain health intervention effectiveness parameters, and performing feedback adjustment on the health intervention effectiveness parameters to obtain an optimized health intervention plan; Performing real-time monitoring of the health status of the target user through the optimized health intervention plan to obtain dynamic health monitoring data, and performing multi-scale correlation analysis on the dynamic health monitoring data to obtain a health monitoring feature sequence; A health assessment report is generated for the target user based on the health monitoring feature sequence to obtain a heart health report; wherein the heart health report includes a heart function score and a risk level assessment result.

[0035] Specifically, in the complex and delicate process of "dynamically tracking the health of the target user based on the heart operation data to obtain a heart health report" mentioned above, we have explored in depth how to use advanced predictive analysis, risk assessment, and individualized intervention recommendation generation and other technical means to comprehensively track and manage heart health. This process not only relies on the heart operation data obtained in the previous steps, but also involves a series of sophisticated data processing and feature extraction operations to ultimately generate a report that can fully describe the heart health status. In this way, we can provide strong scientific support for the maintenance of cardiovascular health. First, in order to evaluate the long-term health trends of the target users, the multidimensional health status prediction analysis technology is used to process the heart operation data. Multidimensional health status prediction analysis aims to comprehensively consider information from multiple dimensions such as heart activity parameters, hemodynamic parameters, and cardiac metabolic status characteristics to predict the user's future health status. By applying time series models and other machine learning algorithms to these data, health status prediction parameters can be obtained, which reflect the health changes that may occur in the user in the future. Then, in order to reveal the changing trend of health status, time series trend analysis was performed. Time series trend analysis can capture the changing patterns of health status over time, thus helping to identify potential health problems or signs of improvement. For example, for a marathon runner who runs frequently, time series trend analysis can help understand the changes in his heart function in different training cycles, ensuring that the heart can maintain efficient operation during high-intensity training and quickly restore normal function during the recovery period. A detailed analysis of the trend of changes in health status can provide a basis for subsequent risk assessment. Next, in order to further analyze the potential risks in the trend of changes in health status, a dynamic risk assessment was conducted. Dynamic risk assessment aims to quantify cardiac health risk parameters, including but not limited to myocardial oxygen consumption, coronary perfusion pressure, and myocardial oxygen reserve. Through a detailed analysis of cardiac health risk parameters, the distribution characteristics of cardiac health risks can be obtained, including high-risk areas, low-risk areas, and dynamic risk transfer paths. These characteristics not only describe the current risk level faced by users, but also reveal the transfer of risks in different time periods. For example, if the platform detects that a user frequently experiences short-term arrhythmia or signs of myocardial ischemia over a period of time, it can automatically notify medical personnel and recommend further examinations. By analyzing the distribution characteristics of heart health risks, we can better understand the heart's response mechanism under different conditions and provide a basis for personalized health management.Based on the above-mentioned characteristics of cardiac health risk distribution, personalized health intervention suggestion generation was performed to obtain a set of health intervention suggestions. Personalized health intervention suggestion generation aims to develop personalized intervention measures according to the user's specific health status, including exercise suggestion priority, diet adjustment priority, and drug management priority. By prioritizing the health intervention suggestion set, dynamic health intervention priorities can be obtained, which helps guide users to adopt the most effective health management strategies. For example, for elderly people with a history of heart disease, personalized health intervention suggestions may emphasize the importance of regular monitoring and propose specific preventive measures, such as appropriately increasing aerobic exercise, reducing high-fat food intake, and taking medication on time. Through a detailed analysis of dynamic health intervention priorities, scientific and personalized health management suggestions can be provided to users to help them better maintain their heart health. In order to evaluate the effectiveness of health intervention measures, a multiparametric efficacy simulation analysis was performed to obtain health intervention efficacy parameters. Multiparametric efficacy simulation analysis aims to simulate the effects of different intervention measures on cardiac health, so as to evaluate their actual effects. By feedback adjustment of health intervention efficacy parameters, an optimized health intervention plan can be obtained. The optimized health intervention program not only summarizes the effects of existing intervention measures, but also provides improvement directions for future health management. For example, if a certain exercise recommendation fails to achieve the expected effect, the system can readjust the recommendation content based on the new health data to ensure that the intervention measures are always in the best state. By applying the optimized health intervention program, the quality and efficiency of heart health management can be continuously improved. Finally, in order to monitor the effect of the optimized health intervention program in real time, the target users were monitored in real time (Real-Time Health Status Monitoring) to obtain dynamic health monitoring data. Dynamic health monitoring data not only reflects the user's immediate response after the implementation of intervention measures, but also provides important information for subsequent health assessment. By performing multiscale correlation analysis on dynamic health monitoring data (Multiscale Correlation Analysis), health monitoring feature sequences can be obtained, which show the changes in heart health at different time scales. Based on these health monitoring feature sequences, health assessment report generation (Health Assessment Report Generation) was performed to obtain a heart health report. The heart health report not only contains key information such as heart function score and risk level assessment results, but also provides users with a detailed heart health portrait.For example, the heart function score can intuitively show the working efficiency of the heart; and the risk level assessment result prompts the user's current risk level and helps him take necessary preventive measures in time. For example, in daily life, when a user wearing a multi-parameter health monitoring device exercises, his heart rate will change significantly. As the intensity of exercise increases, the heart rate accelerates, and the heart needs to pump blood more frequently to meet the needs of the body. At this time, the heart operation data processed by the above steps can not only capture the subtle changes within each heartbeat cycle, but also record how the user's heart responds to different stimuli and stress conditions during daily activities. If the user has a short-term arrhythmia, such as premature beats or atrial fibrillation, the reconstructor can not only identify the abnormal heartbeat pattern, but also calculate the relevant activity parameters, such as the frequency and duration of premature beats and the impact on the overall heart rate. These parameters provide a solid foundation for subsequent dynamic health tracking, helping doctors or health managers to better understand the performance of the heart under specific conditions. In short, through the process of dynamic health tracking of heart operation data, we can not only extract valuable information from the complex heart activities, but also provide strong scientific support for the maintenance of cardiovascular health. The application of this method not only improves the accuracy of heart disease diagnosis, but also lays a solid foundation for personalized health management. By combining advanced predictive analysis, risk assessment, and individualized intervention recommendation generation, we can build a detailed heart health portrait and provide users with scientific and personalized health management recommendations. This method not only improves the accuracy and breadth of heart health monitoring, but also allows us to fully understand the working status of the heart from multiple dimensions and provide strong support for the prevention and management of cardiovascular diseases.

[0036] The above describes the data processing method of the multi-parameter health monitoring sensor in the embodiment of the present invention. The following describes the data processing device of the multi-parameter health monitoring sensor in the embodiment of the present invention. Figure 2 , an embodiment of a data processing device for a multi-parameter health monitoring sensor in an embodiment of the present invention includes: The recording module 21 is used to continuously record the target user through a preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream; A depiction module 22, configured to depict the heartbeat contour of the multi-channel monitoring data stream based on a heartbeat feature reconstructor to obtain heart activity parameters; An analysis module 23, configured to analyze the heartbeat pattern of the target user based on the heart activity parameters to obtain heart working characteristics; An evaluation module 24, configured to evaluate the cardiac state of the cardiac operating characteristics to obtain cardiac operation data; The tracking module 25 is used to perform dynamic health tracking on the target user based on the heart operation data to obtain a heart health report if the heart operation data is not within a preset heart operation range.

[0037] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0038] Reference Figure 3 The present invention also provides a computer device in an embodiment, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0039] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0040] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0041] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0042] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0043] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A data processing method for a multi-parameter health monitoring sensor, characterized in that: The following steps are involved: The target user is continuously recorded through the preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream; Based on the heartbeat feature reconstructor, the heartbeat contour is depicted on the multi-channel monitoring data stream to obtain heart activity parameters; Analyze the heartbeat pattern of the target user based on the heart activity parameters to obtain heart working characteristics; Performing a heart state assessment on the heart working characteristics to obtain heart operation data; If the heart operation data is not within a preset heart operation range, dynamic health tracking is performed on the target user based on the heart operation data to obtain a heart health report.

2. The data processing method of the multi-parameter health monitoring sensor according to claim 1, characterized in that: The multi-parameter health monitoring sensor includes an electrocardiogram sensor, an acoustic sensor, and a pulse wave sensor. The preset multi-parameter health monitoring sensor is used to continuously record the target user to obtain a multi-channel monitoring data stream, including: The target user's cardiac electrical activity is collected and continuously recorded by using a preset electrocardiogram sensor and an acoustic sensor to obtain a first set of original physiological signals, and the target user's blood vessels are continuously monitored and collected by using a pulse wave sensor to obtain a second set of original physiological signals; Based on the empirical mode decomposition algorithm, the first original physiological signal set and the second original physiological signal are respectively decomposed at multiple scales to obtain an intrinsic mode function group; wherein the intrinsic mode function group includes an electrocardiogram waveform component, a cardiac sound spectrum component and a pressure fluctuation component; Continuously processing the intrinsic mode function group to obtain a continuous signal sequence; Feature extraction is performed on the continuous signal sequence to obtain a multi-channel monitoring data stream; wherein the multi-channel monitoring data stream includes heartbeat waveform data, heart sound data and vascular pressure data.

3. The data processing method of the multi-parameter health monitoring sensor according to claim 1, characterized in that: The heartbeat feature reconstructor is used to depict the heartbeat contour of the multi-channel monitoring data stream to obtain heart activity parameters, including: Based on wavelet packet transform, the multi-channel monitoring data stream is decomposed in time and frequency domain to obtain a multi-scale feature sequence set, and nonlinear feature extraction is performed on the multi-scale feature sequence set to obtain heartbeat waveform features; wherein the heartbeat waveform features include QRS complex features, P wave features and T wave features; Performing instantaneous frequency analysis on the heartbeat waveform features to obtain heartbeat frequency domain features, and performing adaptive threshold segmentation on the heartbeat frequency domain features to obtain a heartbeat rhythm sequence; Extracting dynamic features from the heartbeat rhythm sequence to obtain cardiac dynamic features, and performing nonlinear functional calculation on the cardiac dynamic features to obtain cardiac function parameters; wherein the cardiac function parameters include ventricular contraction strength, atrial filling degree and cardiac pumping intensity; Performing nonlinear dynamic analysis on the target user based on cardiac function parameters to obtain a cardiac working state sequence, and performing entropy value calculation based on the cardiac working state sequence to obtain cardiac rhythm parameters; Based on the heart rhythm parameters, the heartbeat contour is depicted to obtain a heartbeat state trajectory diagram, and based on the heartbeat state trajectory diagram, the heart activity is calculated to obtain heart activity parameters; wherein the heart activity parameters include ventricular contraction duration, cardiac diastole duration and cardiac pumping efficiency.

4. The data processing method of the multi-parameter health monitoring sensor according to claim 1, characterized in that: The performing heartbeat regularity analysis on the target user based on the heart activity parameter to obtain the heart working characteristics includes: Performing heart rate variability analysis on the target user based on the heart activity parameters to obtain a heart rate variability parameter sequence; Performing a detrended fluctuation analysis on the heart rate variability parameter sequence to obtain a heart rate fluctuation spectrum, and performing a recursive graph analysis on the heart rate fluctuation spectrum to obtain a heart rate recursive pattern; Performing a Poincare diagram analysis on the target user based on the heart rate recursive mode to obtain a heartbeat cycle scatter plot, and performing an ellipse fitting analysis on the heartbeat cycle scatter plot to obtain a heartbeat cycle dispersion; wherein the heartbeat cycle dispersion includes a heartbeat cycle standard deviation SD1, a heartbeat cycle standard deviation SD2, and a SD1 / SD2 ratio; Reconstructing the heartbeat cycle discreteness in phase space to obtain a heartbeat phase space trajectory, and calculating the Lyapunov exponent of the heartbeat phase space trajectory to obtain a heartbeat chaos degree feature; wherein the heartbeat chaos degree feature includes a maximum Lyapunov exponent, a Lyapunov exponent spectrum, and a Lyapunov dimension; Based on the heartbeat chaos degree characteristics, wavelet transform analysis is performed on the target user to obtain the heartbeat time scale energy distribution, and singular value decomposition is performed on the heartbeat time scale energy distribution to obtain the heartbeat principal component characteristics; The target user's heartbeat pattern is analyzed based on the heartbeat principal component characteristics to obtain heart working characteristics; wherein the heart working characteristics include changes in heartbeat rhythm, changes in heart sound patterns, and changes in blood pressure fluctuations.

5. The data processing method of the multi-parameter health monitoring sensor according to claim 1, characterized in that: The step of evaluating the cardiac state of the cardiac operating characteristics to obtain cardiac operation data includes: Performing a cardiac dynamics state analysis on the target user based on the cardiac working characteristics to obtain cardiac dynamics state parameters, and performing a nonlinear coupling analysis on the cardiac dynamics state parameters to obtain cardiac dynamic coupling characteristics; Performing multi-scale time series decomposition on the cardiac dynamic coupling characteristics to obtain a cardiac cycle dynamic feature sequence, and performing frequency domain correlation analysis on the cardiac cycle dynamic feature sequence to obtain a cardiac cycle spectrum characteristic; Based on the cardiac cycle spectrum characteristics, the target user is subjected to hemodynamic analysis to obtain hemodynamic parameters, and the hemodynamic parameters are subjected to waveform pattern recognition to obtain blood flow waveform characteristics; wherein the blood flow waveform characteristics include systolic blood flow waveform, diastolic blood flow waveform and pulse pressure waveform; Performing pulse wave propagation velocity analysis on the blood flow waveform characteristics to obtain pulse propagation velocity parameters, and performing arterial elasticity analysis on the pulse propagation velocity parameters to obtain arterial elasticity characteristics; wherein the arterial elasticity characteristics include arterial compliance, arteriosclerosis index and arterial dilatation capacity; Based on the arterial elasticity characteristics, a cardiac load assessment is performed on the target user to obtain a cardiac load parameter, and a cardiac metabolism analysis is performed on the cardiac load parameter to obtain a cardiac metabolic state characteristic; wherein the cardiac metabolic state characteristic includes myocardial oxygen consumption, myocardial metabolic efficiency, and cardiac energy consumption rate; A comprehensive cardiac function evaluation is performed on the cardiac metabolic state characteristics to obtain cardiac operation data; wherein the cardiac operation data includes the degree of heartbeat disorder, myocardial contraction strength and cardiac load level.

6. The data processing method of the multi-parameter health monitoring sensor according to claim 5, characterized in that: The cardiac load assessment of the target user based on the arterial elasticity characteristics to obtain cardiac load parameters includes: Based on the arterial elasticity characteristics, pulse wave impedance analysis is performed on the target user to obtain vascular mechanical impedance parameters, and cardiac afterload calculation is performed on the vascular mechanical impedance parameters to obtain cardiac afterload characteristics; wherein the cardiac afterload characteristics include aortic characteristic impedance, peripheral vascular resistance and vascular rebound coefficient; Performing volume-pressure relationship analysis on the cardiac afterload characteristics to obtain ventricular filling parameters, and performing preload dynamics calculation on the ventricular filling parameters to obtain cardiac preload characteristics; Performing ventricular wall tension analysis based on the cardiac preload characteristics to obtain ventricular wall stress parameters, and performing myocardial load distribution calculation on the ventricular wall stress parameters to obtain myocardial load distribution characteristics; Performing ventricular pressure-volume loop analysis on the myocardial load distribution characteristics to obtain ventricular function parameters, and performing cardiac work efficiency calculation on the ventricular function parameters to obtain cardiac mechanical performance characteristics; Performing cardiac energy consumption analysis based on the cardiac mechanical performance characteristics to obtain cardiac energy metabolism parameters, and performing myocardial supply and demand balance calculation on the cardiac energy metabolism parameters to obtain cardiac load balance characteristics; wherein the cardiac load balance characteristics include myocardial oxygen consumption, coronary perfusion pressure and myocardial oxygen reserve; A load integration evaluation is performed on the cardiac load balance characteristics to obtain a cardiac load parameter.

7. The data processing method of the multi-parameter health monitoring sensor according to claim 1, characterized in that: The dynamically tracking the health of the target user based on the heart operation data to obtain a heart health report includes: Based on the heart operation data, a multi-dimensional health status prediction analysis is performed on the target user to obtain health status prediction parameters, and a time series trend analysis is performed on the health status prediction parameters to obtain a health status change trend of the target user; Performing a dynamic risk assessment on the health status change trend to obtain a heart health risk parameter, and performing a risk cluster analysis on the heart health risk parameter to obtain a heart health risk distribution feature; wherein the heart health risk distribution feature includes a high-risk area, a low-risk area, and a dynamic risk transfer path; Based on the cardiac health risk distribution characteristics, individualized health intervention suggestions are generated for the target user to obtain a health intervention suggestion set, and the health intervention suggestion set is prioritized to obtain a dynamic health intervention priority; wherein the dynamic health intervention priority includes exercise suggestion priority, diet adjustment priority and drug management priority; Performing a multi-parameter effectiveness simulation analysis on the dynamic health intervention priority to obtain health intervention effectiveness parameters, and performing feedback adjustment on the health intervention effectiveness parameters to obtain an optimized health intervention plan; Performing real-time monitoring of the health status of the target user through the optimized health intervention plan to obtain dynamic health monitoring data, and performing multi-scale correlation analysis on the dynamic health monitoring data to obtain a health monitoring feature sequence; A health assessment report is generated for the target user based on the health monitoring feature sequence to obtain a heart health report; wherein the heart health report includes a heart function score and a risk level assessment result.

8. A data processing device for a multi-parameter health monitoring sensor, characterized in that: include: A recording module is used to continuously record the target user through a preset multi-parameter health monitoring sensor to obtain a multi-channel monitoring data stream; A depiction module, used for depicting the heartbeat contour of the multi-channel monitoring data stream based on a heartbeat feature reconstructor to obtain heart activity parameters; An analysis module, configured to analyze the heartbeat pattern of the target user based on the heart activity parameters to obtain heart working characteristics; An evaluation module, used for evaluating the cardiac state of the cardiac operating characteristics to obtain cardiac operation data; The tracking module is used to perform dynamic health tracking on the target user based on the heart operation data to obtain a heart health report if the heart operation data is not within a preset heart operation range.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images