Health data monitoring method for cardiovascular disease high-risk group based on Internet of Things

Abstract

The invention relates to the technical field of health monitoring, in particular to a cardiovascular disease high-risk group health data monitoring method based on the Internet of Things, which comprises the following steps: acquiring health equipment state and activity records, analyzing health state trend, extracting abnormal fluctuation frequency and duration, collecting node environment parameters and signal quality, screening nodes meeting conditions, and determining the health data of cardiovascular disease high-risk groups. According to the invention, through continuous acquisition and time sequence analysis of the multi-source health data, dynamic mastering of multi-dimensional physiological indexes is realized, and the health monitoring recovery path and the synchronization node configuration table are obtained. Abnormal fluctuation screens and focuses key risk parameters according to frequency and duration, monitoring nodes complete adaptive adjustment according to signal and environment matching, monitoring paths are optimized according to signal delay and fluctuation characteristics, information transmission synchronization accuracy is guaranteed, the data utilization rate and decision-making precision are improved, and the real-time performance and continuity of cardiovascular risk monitoring are enhanced.

Description

Technical Field

[0001] This invention relates to the field of health monitoring technology, and in particular to a method for monitoring health data of high-risk groups for cardiovascular diseases based on the Internet of Things. Background Technology

[0002] The field of health monitoring technology mainly involves the long-term dynamic collection and recording of daily physiological information of high-risk groups for cardiovascular diseases. Through continuous monitoring of multi-source health data such as blood pressure, heart rate, blood oxygen, body temperature, and exercise volume, it aims to comprehensively understand the patient's cardiac and vascular function. This technology encompasses core aspects such as data perception, data acquisition, remote transmission, information storage, and analysis, and aims to provide continuous health information support for medical institutions and patients, forming an important component of the medical and health monitoring system. Traditional methods for monitoring health data of high-risk groups for cardiovascular diseases rely on single medical testing devices such as blood pressure monitors, electrocardiographs, and pulse oximeters obtained during regular hospital checkups or outpatient visits to accumulate limited individual physiological data. Alternatively, data can be accumulated through patients' self-recording of blood pressure and heart rate values. These methods primarily depend on manual testing and single-point collection, failing to achieve multi-dimensional, multi-time-period continuous dynamic monitoring.

[0003] Current technologies primarily rely on regular hospital testing and patient self-monitoring. Data acquisition is limited by time and location, making it difficult to form a continuous monitoring chain. Physiological parameters only reflect the static state at a specific point in time, lacking long-term observation of health trends. Manual recording methods are easily affected by individual operational differences, leading to data distortion or omissions. Single-device measurement methods cannot take into account multiple indicators, limiting the monitoring range. The results cannot reflect the correlation characteristics between multiple systems in the body. Low data update frequency makes it difficult to detect abnormal changes in a timely manner. Sudden risk events are often overlooked during testing intervals. Isolated information leads to a lack of support for subsequent analysis and intervention. Overall, health monitoring presents a passive response mode, which cannot meet the needs for dynamic, comprehensive, and precise management of high-risk groups for cardiovascular diseases. Summary of the Invention

[0004] To address the technical problems existing in the prior art, embodiments of the present invention provide a method for monitoring health data of high-risk groups of cardiovascular disease based on the Internet of Things, comprising the following steps: To achieve the above objectives, the present invention adopts the following technical solution: a method for monitoring health data of high-risk groups for cardiovascular diseases based on the Internet of Things, comprising the following steps: S1: Acquire the operating status of multi-source health sensing devices and the patient's daily activity records, combine the initial distribution characteristics of health indicators, analyze the temporal balance of health status, and generate a health status trend chart. S2: Call the health status trend chart, extract the abnormal fluctuation frequency and duration of each health indicator, sort by fluctuation frequency and exclude periods with duration below the set threshold, and generate a priority monitoring sequence. S3: Call the priority monitoring sequence, collect the operating environment parameters and signal quality assessment values ​​of the candidate monitoring nodes, compare and screen the nodes that meet the requirements, and map them through the logical correlation between the nodes and health indicators to obtain the node health correlation matching group; S4: Based on the node health association matching group, compare the current health status with the target health status, determine the direction of deviation, adjust the working mode of the monitoring node in the current monitoring cycle according to the direction of deviation, and generate a cardiology health monitoring list.

[0005] As a further embodiment of the present invention, the health status trend graph includes health indicator number, time distribution feature identifier, and environmental adaptation value; the priority monitoring sequence includes fluctuation frequency parameter, duration limit value, and priority label; the node health association matching group includes logical association relationship identifier, signal quality benchmark interval, and operating environment stability judgment value; and the cardiology health monitoring list includes working mode code, health status adjustment direction, and optimization parameters within the monitoring period.

[0006] As a further aspect of the present invention, the steps of the health status trend graph are specifically as follows: S101: Acquire the operating status of multi-source health sensing devices and the patient's daily activity records, perform comparison calculations between activity volume and initial health index distribution, identify the time distribution characteristics of health status, and generate a health status distribution sequence; S102: Call the health status distribution sequence, compare it with the set balance threshold according to the time distribution characteristics, filter the time period when the continuous characteristic value is lower than the balance threshold, extract the corresponding health indicator number and time window, and obtain the time distribution balance segment index set. S103: Based on the time distribution balanced segment index set, select health indicators with balanced characteristics as key monitoring objects, mark controllable interfaces and indicators with predictable health status, and generate a health status trend chart.

[0007] As a further aspect of the present invention, the step of prioritizing the monitoring sequence specifically includes: S201: Call the health status trend chart, extract the corresponding health indicator number, abnormal fluctuation frequency and duration, identify the number to match each data item, and establish a set of health indicator operation parameters; S202: Based on the set of health indicator operating parameters, sort them in ascending order according to the frequency of abnormal fluctuations, filter the health indicator sequences with lower fluctuation frequencies, and obtain a fluctuation frequency sorting list. S203: Call the fluctuation frequency sorting list, compare the duration with the set minimum duration threshold, remove the periods with durations lower than the threshold, and generate a priority monitoring sequence.

[0008] As a further aspect of the present invention, the step of the node health association matching group specifically includes: S301: Call the priority monitoring sequence to capture the operating environment parameters and signal quality evaluation values ​​of the candidate monitoring nodes, summarize the real-time environmental parameters and signal quality values ​​of the nodes, and generate node operating status parameters; S302: Based on the node operating status parameters, and by comparing the environmental parameters, signal quality values, and required ranges, select nodes that meet the requirements to obtain a set of available nodes for health monitoring; S303: Call the set of available health monitoring nodes, map the node number to the health indicator channel according to the logical relationship between the list nodes and health indicators, calculate the node health correlation index, and obtain the node health correlation matching group.

[0009] As a further aspect of the present invention, the node operating status parameters include standardizing the mean environmental parameters and signal quality assessment values ​​of the candidate monitoring nodes to obtain a node operating score; The node health correlation index refers to the node health correlation calculated based on the correlation coefficient between the node operation score in the available node set for health monitoring and the corresponding health indicator channel. When the node health correlation index value is greater than the threshold, the node is determined to belong to the node health correlation matching group.

[0010] As a further aspect of the present invention, the steps of the cardiology health monitoring checklist are specifically as follows: S401: Based on the node health association matching group, collect the real-time status values ​​of health indicators within the current monitoring period, match the target status value corresponding to each indicator, merge the current value and the target value according to the indicator number, and generate a health status difference data group. S402: Call the health status difference data group, determine the deviation direction between the current state and the target state of each health indicator, and classify the state into exceeding the standard and insufficient according to the positive and negative values ​​of the deviation values ​​to obtain the health status deviation direction identifier set; S403: Based on the set of health status deviation direction identifiers, locate the list monitoring nodes connected to the corresponding health indicators, adjust the node working mode within the current monitoring period, calculate the node operation coordination value, and generate the cardiology health monitoring list.

[0011] As a further aspect of the present invention, the node operation coordination value refers to the node operation coordination value that reflects the degree of coordination between nodes by calculating the operation coordination performance index between nodes based on the interconnection relationship and operation parameters between nodes after the node working mode adjustment is completed.

[0012] As a further aspect of the present invention, the method further includes step S5: S5: Call the cardiology health monitoring list, compare the signal delay and temporal fluctuation rate in the monitoring path, perform matching and filtering based on path characteristics and key time points, and output the health monitoring recovery path and synchronization node configuration table. The health monitoring recovery path and synchronization node configuration table includes signal delay coefficient, synchronization configuration time point, and response characteristics.

[0013] As a further aspect of the present invention, the steps of configuring the health monitoring recovery path and synchronization node table are as follows: S501: Call the cardiology health monitoring list, extract the delay changes at key time points based on the signal delay data in the monitoring path, and perform correlation analysis with the time-series fluctuation rate to generate a signal delay fluctuation correlation coefficient. S502: Based on the signal delay fluctuation correlation coefficient and combined with the path characteristic parameters, perform a matching judgment operation on the path performance at key time points, filter the set of paths that meet the synchronization conditions, and obtain the synchronization path judgment value range. S503: Call the synchronization path determination value range, compare it with the synchronization node parameters in the time-series fluctuation signal, determine the optimal path and corresponding node parameters for health monitoring recovery, and output the health monitoring recovery path and synchronization node configuration table.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, through continuous acquisition and time-series analysis of multi-source health data, dynamic monitoring of an individual's multidimensional physiological indicators can be achieved. Changes in health status are quantified into trend graphs and time-balanced assessments are performed, allowing for a direct visualization of health fluctuations under different lifestyle conditions. After screening and sorting the frequency and duration of abnormal fluctuations, the monitoring focus automatically concentrates on key physiological parameters with potential risks. Monitoring nodes are intelligently matched under dual comparisons of operating environment and signal quality, making data acquisition more stable and efficient. During the monitoring process, the logical relationships between nodes are dynamically adjusted, and deviations between health status and target status are directionally corrected. The working mode within the monitoring period adapts to individual status, and the monitoring path is optimized based on signal delay and temporal fluctuation characteristics, ensuring the synchronization and accuracy of health information transmission and analysis. The overall monitoring process achieves an upgrade from static acquisition to dynamic linkage, reducing invalid data and duplicate acquisition, improving the utilization rate of monitoring resources and the value of data decision-making, and enabling cardiovascular risk monitoring to have real-time, continuous, and predictive capabilities, providing a continuous and reliable basis for clinical intervention. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the steps of the present invention; Figure 2 This is a detailed schematic diagram of S1 of the present invention; Figure 3 This is a detailed schematic diagram of S2 of the present invention; Figure 4 This is a detailed schematic diagram of S3 of the present invention; Figure 5 This is a detailed schematic diagram of S4 of the present invention; Figure 6 This is a detailed schematic diagram of S5 of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0018] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0019] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0020] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0021] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0022] Please see Figure 1 This invention provides a method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things, including the following steps: S1: Acquire the operating status of multi-source health sensing devices and the patient's daily activity records, combine the initial distribution characteristics of health indicators, analyze the temporal balance of health status, and generate a health status trend chart. S2: Call the health status trend chart, extract the abnormal fluctuation frequency and duration of each health indicator, sort by fluctuation frequency and exclude periods with duration below the set threshold, and generate a priority monitoring sequence. S3: Call the priority monitoring sequence, collect the operating environment parameters and signal quality assessment values ​​of the candidate monitoring nodes, compare and filter the nodes that meet the requirements, and map them through the logical relationship between the nodes and health indicators to obtain the node health association matching group; S4: Based on the node health association matching group, compare the current health status with the target health status, determine the direction of deviation, adjust the working mode of the monitoring node in the current monitoring cycle according to the direction of deviation, and generate a cardiology health monitoring list. S5: Call the cardiology health monitoring list, compare the signal delay and temporal fluctuation rate in the monitoring path, perform matching and filtering based on path characteristics and key time points, and output the health monitoring recovery path and synchronization node configuration table.

[0023] The health status trend chart includes health indicator number, time distribution characteristic identifier, and environmental adaptation value. The priority monitoring sequence includes fluctuation frequency parameter, duration limit value, and priority label. The node health association matching group includes logical association relationship identifier, signal quality benchmark range, and operating environment stability judgment value. The cardiology health monitoring list includes working mode code, health status adjustment direction, and optimization parameters within the monitoring cycle. The health monitoring recovery path and synchronization node configuration table includes signal delay coefficient, synchronization configuration time point, and response characteristics.

[0024] Please see Figure 2 The specific steps for creating a health status trend chart are as follows: S101: Acquire the operating status of multi-source health sensing devices and the patient's daily activity records, perform comparison calculations between activity volume and initial health index distribution, identify the time distribution characteristics of health status, and generate a health status distribution sequence; Acquire the operational status of health sensing devices and patient activity records. Operational status data is recorded hourly, including heart rate (beats / minute), steps (steps), sleep duration (hours), systolic blood pressure (mmHg), and diastolic blood pressure (mmHg). Integrate dietary and medication adherence information. Less than 5000 steps are defined as low activity level, 5000 to 10000 steps as moderate activity level, and more than 10000 steps as high activity level. Set baseline resting heart rate of 60-75 beats / minute, systolic blood pressure of 110-125 mmHg, and diastolic blood pressure of 70-85 mmHg. Compare daily data to the baseline range. For example, a patient with 8500 steps is considered moderate activity level, with an average resting heart rate of 70 beats / minute, systolic blood pressure of 122 mmHg, and diastolic blood pressure of 81 mmHg, all within the baseline range. A heart rate of 80 beats / minute exceeds the upper limit by 5 beats / minute. Track activity levels and compare them with health indicators over seven consecutive days. Identify the temporal distribution characteristics of health status. If a patient's daily step count is less than 5000 steps for three consecutive days, and their average resting heart rate is higher than 75 beats / minute for three consecutive days (78, 80, and 77 beats / minute respectively), the "low activity level accompanied by elevated heart rate" characteristic pattern is identified. The identified daily health status characteristics are arranged to generate a health status distribution sequence. Each record in the sequence includes the date, activity level, baseline compliance with health indicators, and deviation value. For example, the record for the current day is: low activity level, elevated heart rate (78 beats / minute), normal systolic blood pressure, elevated diastolic blood pressure (88 beats / minute), and normal sleep.

[0025] S102: Call the health status distribution sequence, compare it with the set balance threshold on a cycle-by-cycle basis according to the time distribution characteristics, filter the time period when the continuous characteristic value is lower than the balance threshold, extract the corresponding health indicator number and time window, and obtain the time distribution balance segment index set. The system retrieves a health status distribution sequence, which includes daily activity level, heart rate, blood pressure, and sleep duration. A daily health stability score is defined: 0.25 points are added for normal heart rate, normal blood pressure, normal sleep duration, and moderate to high activity level. No points are added if the indicators do not meet the criteria, with a total score of 0 to 1. A balance threshold of 0.75 is set, based on data analysis. Daily scores are compared to the threshold. For example, if a day's score is 1.0, another day's score is 0.25 (high heart rate, high diastolic blood pressure, low activity), another day's score is 0 (high heart rate, high systolic blood pressure, high diastolic blood pressure, low sleep, low activity), and another day's score is 0.5 (high heart rate, low activity), the system identifies the number of consecutive days with scores below 0.75. For example, three consecutive days with scores below 0.75. Health indicator IDs: Heart Rate (HR), Systolic Blood Pressure (SBP), Diastolic Blood Pressure (DBP), Sleep Duration (SD), Activity Level (AL). Extract health indicator IDs and time windows. During this three-day period, deviation indicators include HR, DBP, AL, SBP, and SD. Organize the selected time periods and health indicator IDs to generate a time-balanced interval index set. The index set contains the time period and deviation indicators, for example: Time window: from a certain day to a certain day; Unbalanced indicators: HR, DBP, AL, SBP, SD.

[0026] S103: Based on the time distribution balanced segment index set, select health indicators with balanced characteristics as key monitoring objects, mark controllable interfaces and indicators with predictable health status, and generate a health status trend chart. The system receives an index set of balanced health status distribution segments, which indicates unbalanced health indicators, including HR, DBP, AL, SBP, and SD. Indicators in the index set are identified as key monitoring targets. For these key targets, they are labeled according to a health indicator attribute knowledge base. The knowledge base defines the controllability and predictability levels for each health indicator. Controllability levels are categorized as high, medium, and low controllability, while predictability levels are categorized as high, medium, and low predictability. For example, HR is labeled as medium and high predictability, AL as high and high predictability, and SBP and DBP as medium and medium predictability. A chart is generated with time on the horizontal axis and the deviation, controllability, and predictability of the health indicators on the vertical axis. The chart displays the daily changes in HR, DBP, AL, SBP, and SD, using color depth or icon size to represent the degree of deviation from the baseline, and labeling controllability and predictability. For example, on the trend chart, if the heart rate line shows a consistently higher-than-normal range, it is labeled "medium controllable, high predictable." A health status trend chart is then generated.

[0027] Please see Figure 3 The specific steps for prioritizing sequence monitoring are as follows: S201: Call the health status trend chart, extract the corresponding health indicator number, abnormal fluctuation frequency and duration, identify the number to match each data item, and establish a set of health indicator operation parameters; Read the health status trend chart data, which includes daily records of various key monitored health indicators. Calculate the frequency and duration of abnormal fluctuations. The frequency of abnormal fluctuations is the number of consecutive deviations of the indicator value from the baseline, and the duration is the total number of days of deviation from the baseline. For example, if heart rate (HR) is high for three consecutive days, the frequency of abnormal fluctuation is 1, and the duration is 3 days; if diastolic blood pressure (DBP) is high for two consecutive days, the frequency of abnormal fluctuation is 1, and the duration is 2 days; if activity level (AL) is low for three consecutive days, the frequency of abnormal fluctuation is 1, and the duration is 3 days; if systolic blood pressure (SBP) is high for one day, the frequency of abnormal fluctuation is 1, and the duration is 1 day. Sleep duration (SD) is low for one day, with an abnormal fluctuation frequency of 1 time and a duration of 1 day. Health indicator numbers: heart rate 001, diastolic blood pressure 002, activity level 003, systolic blood pressure 004, sleep duration 005. Match the health indicator number, abnormal fluctuation frequency, and duration to generate a set of health indicator operating parameters. The set includes: heart rate 001 (frequency 1 time, duration 3 days), diastolic blood pressure 002 (frequency 1 time, duration 2 days), activity level 003 (frequency 1 time, duration 3 days), systolic blood pressure 004 (frequency 1 time, duration 1 day), sleep duration 005 (frequency 1 time, duration 1 day).

[0028] S202: Based on the set of health indicator operating parameters, sort them in ascending order according to the frequency of abnormal fluctuations, filter the health indicator sequences with lower fluctuation frequencies, and obtain a fluctuation frequency sorted list. The system reads the set of health indicator parameters and sorts them in ascending order based on the frequency of abnormal fluctuations. If the frequencies are the same, they are sorted in descending order based on the duration. Priority is given to events with longer durations. The data set includes: heart rate (frequency 1, duration 3), activity level (frequency 1, duration 3), diastolic blood pressure (frequency 1, duration 2), systolic blood pressure (frequency 1, duration 1), and sleep duration (frequency 1, duration 1). The sorted results are: heart rate, activity level, diastolic blood pressure, systolic blood pressure, and sleep duration. The low-frequency standard is defined as an abnormal fluctuation frequency value less than or equal to 2. This threshold is set based on data analysis. Currently, all indicators have an abnormal fluctuation frequency of 1, which meets the low-frequency condition. All indicators are retained, and a fluctuation frequency sorted list is generated. The list includes: heart rate 001 (frequency 1 time, duration 3 days), activity level 003 (frequency 1 time, duration 3 days), diastolic blood pressure 002 (frequency 1 time, duration 2 days), systolic blood pressure 004 (frequency 1 time, duration 1 day), and sleep duration 005 (frequency 1 time, duration 1 day).

[0029] S203: Call the fluctuation frequency sorting list, compare the duration with the set minimum duration threshold, remove the periods with durations below the threshold, and generate a priority monitoring sequence; The system reads the frequency fluctuation ranking list. For each health indicator in the list, the duration is compared with the minimum duration threshold, which is set to 2 days. This threshold is based on clinical experience and health management goals. The duration of heart rate is 3 days, which is greater than the 2-day threshold. The duration of activity is 3 days, which is greater than the 2-day threshold. The duration of diastolic blood pressure is 2 days, which is equal to the 2-day threshold. The duration of systolic blood pressure is 1 day, which is less than the 2-day threshold. The duration of sleep is 1 day, which is less than the 2-day threshold. Indicators with a duration less than the minimum duration threshold are removed. Systolic blood pressure and sleep duration are removed. The remaining indicators, including heart rate, activity, and diastolic blood pressure, are used to generate a priority monitoring sequence. The sequence includes: heart rate 001 (frequency 1 time, duration 3 days), activity 003 (frequency 1 time, duration 3 days), and diastolic blood pressure 002 (frequency 1 time, duration 2 days).

[0030] Please see Figure 4 The specific steps for matching node health association groups are as follows: S301: Call the priority monitoring sequence, capture the operating environment parameters and signal quality evaluation values ​​of candidate monitoring nodes, summarize the real-time environmental parameters and signal quality values ​​of the nodes, and generate node operating status parameters; Node operating status parameters include standardizing the mean environmental parameters and signal quality assessment values ​​of candidate monitoring nodes to obtain a node operating score; The system reads the priority monitoring sequence, obtains the list of health indicators to be monitored, activates and queries the status of candidate monitoring nodes. Candidate monitoring nodes include Node A (wristband), Node B (ECG patch), and Node C (home gateway). It captures the operating environment parameters and signal quality assessment values ​​for each candidate monitoring node. Node A's operating environment parameters are: battery level 85%, network latency 50 milliseconds, wearing status "Wearing"; signal quality assessment values ​​are: heart rate data integrity 98%, signal-to-noise ratio (SNR) 20 dB. Node B's operating environment parameters are: battery level 70%, network latency 60 milliseconds, electrode contact impedance 1.5 kΩ; signal quality assessment values ​​are: ECG signal integrity 95%, SNR 22 dB. Node C's operating environment parameters are: network bandwidth utilization 30%, CPU load 15%. The quality assessment value is: packet loss rate 1%. Parameter values ​​are aggregated and summarized by node, and the summarized parameters are standardized and mapped to the range of 0 to 1. The standardized value for battery power is current battery power / 100, network latency is 1 - (current latency / 100), data integrity rate is current integrity rate / 100, and SNR is current SNR / 30. A weighted average is used to calculate the node's performance score, with the following weights: battery power 0.1, network latency 0.1, data integrity rate 0.4, SNR 0.4. For example, node A's score is: (0.85×0.1)+(0.7×0.1)+(0.98×0.4)+(0.75×0.4)=0.842. This generates node performance status parameters, including standardized parameters and the node performance score.

[0031] S302: Based on the node operating status parameters, and by comparing environmental parameters, signal quality values, and required ranges, select nodes that meet the requirements to obtain a set of available nodes for health monitoring; The system reads the set of node operating status parameters, which includes standardized environmental parameters, signal quality values, and node operating scores for each candidate monitoring node. It defines requirement ranges based on device standards and consensus settings: standardized battery power range [0.70, 1.00], standardized network latency range [0.60, 1.00], standardized data integrity range [0.95, 1.00], and standardized SNR range [0.70, 1.00]. Each node's parameters are compared one by one with the requirement ranges. For example, node A has a battery power of 0.85, which meets the requirements; a network latency of 0.70, which meets the requirements; a data integrity rate of 0.98, which meets the requirements; and an SNR of 0.75, which meets the requirements. Node B has a network latency of 0.40, which does not meet the requirements. Node C has all parameters that meet the requirements. The system then filters out nodes that meet the requirements, for example, nodes A and C. Finally, it generates a set of available health monitoring nodes, which includes nodes A and C.

[0032] S303: Call the available set of health monitoring nodes, map the node number to the health indicator channel according to the logical relationship between the list nodes and health indicators, calculate the node health correlation index, and obtain the node health correlation matching group; The node health correlation index refers to the node health correlation calculated based on the correlation coefficient between the node operation score in the available node set for health monitoring and the corresponding health indicator channel. When the node health correlation index value is greater than the threshold, the node is determined to belong to the node health correlation matching group. Access the set of available health monitoring nodes, which includes node A and node C. Query the mapping table of logical associations between the nodes and health indicators. The mapping table defines the health indicators and health indicator channels monitored or associated by each node. Node A monitors heart rate 001 (channel A_HR) and activity level 003 (channel A_AL). Node C is associated with the data channels of heart rate 001, diastolic blood pressure 002, and activity level 003 (channel C_ALL). Combining the node's performance score (node ​​A score 0.842, node C score 0.890) with the historical data quality of the indicator channels, calculate the node's health correlation index. The correlation index is a comprehensive score combining the node's performance score, the accuracy, stability, and timeliness of historical monitoring data indicators, reflecting the effectiveness of the node in monitoring specific health indicators. For example, node A has a correlation of 0.92 with heart rate 001. The correlation coefficient for activity level 003 is 0.95. The correlation coefficient for node C with heart rate 001, diastolic blood pressure 002, and activity level 003 is 0.88. A correlation coefficient threshold of 0.85 is set, which is based on clinical validation. Nodes with a health correlation coefficient value greater than or equal to 0.85 are matched with the associated health indicator channels. Node A has a correlation coefficient of 0.92 with heart rate 001 and matches. Node A has a correlation coefficient of 0.95 with activity level 003 and matches. Node C has a correlation coefficient of 0.88 with heart rate 001, diastolic blood pressure 002, and activity level 003 and matches. A node health correlation matching group is generated, which includes: node A - heart rate 001 (0.92), node A - activity level 003 (0.95), node C - heart rate 001 (0.88), node C - diastolic blood pressure 002 (0.88), and node C - activity level 003 (0.88).

[0033] Please see Figure 5 The specific steps for the cardiology health monitoring checklist are as follows: S401: Based on the node health association matching group, collect the real-time status values ​​of health indicators within the current monitoring period, match the target status value corresponding to each indicator, merge the current value and the target value according to the indicator number, and generate a health status difference data group. Based on the node health association matching group, the system identifies the health indicators that require real-time data collection and their corresponding monitoring nodes. Within the current monitoring period (e.g., every 5 minutes), it requests the collection of real-time status values ​​of the health indicators from the nodes in the matching group. For example, the real-time value of heart rate (001) collected through node A is 82 beats / minute; the real-time value of activity level (003) collected through node A is 150 steps in the current 5 minutes (estimated 4500 steps per day); and the real-time value of diastolic blood pressure (002) collected through node C is 88 mmHg. A target status value is matched for each health indicator, and the target value is set based on the patient's health record, clinical guidelines, and expert recommendations. For example, the target range for heart rate (001) is 60-75 beats / minute, the target value for activity level (003) is greater than or equal to 8000 steps / day, and the target range for diastolic blood pressure (002) is 70-85 mmHg. The collected real-time status values ​​and target status values ​​are grouped according to health indicator numbers, the differences are calculated, and a health status difference data set is generated. The data set includes: heart rate (001) (currently 82 beats / minute, target 60-75 beats / minute), activity level (003) (currently estimated 4500 steps / day, target greater than or equal to 8000 steps / day), and diastolic blood pressure (002) (currently 88 mmHg, target 70-85 mmHg).

[0034] S402: Call the health status difference data group, determine the deviation direction between the current status and the target status of each health indicator, and classify the status into excess and deficiency according to the positive and negative values ​​of the deviation values ​​to obtain the health status deviation direction identifier set; Read the health status difference data group. The group contains the current real-time value and target status value / range of health indicators. Evaluate each indicator in the group one by one. Heart rate (001): Current 82 beats / minute, target 60-75 beats / minute. 82 is greater than 75, judged as "exceeding the target", deviation value 82-75=7 beats / minute. Activity level (003): Current estimated 4500 steps, target greater than or equal to 8000 steps / day. 4500 is less than 8000, judged as "insufficient", deviation value 4500-8000=-3. 500 steps / day, diastolic blood pressure 002, current 88 mmHg, target 70-85 mmHg. 88 is greater than 85, judged as "exceeding the standard". Deviation value 88-85=3 mmHg. The deviation value is judged by positive or negative. Positive value indicates "exceeding the standard" and negative value indicates "insufficient". A set of health status deviation direction indicators is generated. The indicator set includes: heart rate 001 (exceeding the standard, +7 beats / minute), activity level 003 (insufficient, -3500 steps / day), diastolic blood pressure 002 (exceeding the standard, +3 mmHg).

[0035] S403: Based on the health status deviation direction identifier set, locate the list monitoring node connected to the corresponding health indicator, adjust the node working mode in the current monitoring cycle, calculate the node operation coordination value, and generate the cardiology health monitoring list. The node operation coordination value refers to the node operation coordination value that reflects the degree of coordination between nodes by calculating the operation coordination performance index between nodes based on the interconnection relationship and operation parameters between nodes after the node working mode is adjusted. The system reads the set of health status deviation direction identifiers, which indicate whether health indicators are excessive or insufficient: heart rate 001, activity level 003, and diastolic blood pressure 002. It queries the node health association matching group to determine the monitoring nodes responsible for collecting deviation data. For heart rate 001 and activity level 003, it locates nodes A and C; for diastolic blood pressure 002, it locates node C. Based on the direction and degree of indicator deviation and the located node, it adjusts the node's working mode. The working mode adjustment strategy is preset in the rule base. If an indicator is excessive or insufficient, the sampling frequency of the monitoring node is increased from the default every 5 minutes to every 1 minute, and the priority of indicator data transmission is increased. For example, if heart rate 001 and activity level 003 are excessive or insufficient, node A's working mode is adjusted to high-frequency monitoring mode, increasing the sampling frequency to 5 times the default mode; node C's working mode is adjusted to high-priority data transmission mode, ensuring that data from node A and diastolic blood pressure sensor data are processed and uploaded first. After the node working mode adjustment is completed, based on the interconnection relationship between nodes and operating parameters, the node operation coordination value is calculated. With the same value: 0.4 × (Node A's adjusted operating score) + 0.4 × (Node C's adjusted operating score) + 0.2 × (adjusted network transmission stability score), Node A's operating score decreased from 0.842 to 0.75, Node C's operating score fluctuated to 0.87, and the transmission stability score was 0.90. The coordination value was (0.4 × 0.75) + (0.4 × 0.87) + (0.2 × 0.90) = 0.828. A coordination value threshold of 0.75 was set, as 0.828 is higher than 0.7. 5. Good synergy: It integrates health indicators, responsible monitoring nodes, adjusts the working mode of the nodes, and calculates the node operation synergy value to generate a cardiology health monitoring list. The list includes: heart rate 001 (exceeding the standard, A, C, node A high-frequency monitoring, node C high-priority transmission, 0.828), activity level 003 (insufficient, A, C, node A high-frequency monitoring, node C high-priority transmission, 0.828), and diastolic blood pressure 002 (exceeding the standard, C, node C high-priority transmission, 0.828).

[0036] Please see Figure 6 The specific steps for configuring the health monitoring recovery path and synchronization node table are as follows: S501: Call the cardiology health monitoring list, extract the delay changes at key time points based on the signal delay data in the monitoring path, and perform correlation analysis with the time-series fluctuation rate to generate the signal delay fluctuation correlation coefficient. The cardiology health monitoring checklist is retrieved, listing key health indicators, monitoring points, and adjusted operating modes. Based on signal delay data along the monitoring path, delay changes at key time points are extracted. The monitoring path extends from the sensor to the gateway and then to the cloud. Signal delay data is obtained by recording send and receive timestamps. For example, within the adjusted monitoring period, signal delay data for five consecutive time points are: T1 52 ms, T2 55 ms, T3 53 ms, T4 58 ms, T5 60 ms. The delay difference between adjacent time points is calculated: the delay change between T2 and T1 is 55ms - 52ms = 3ms, and the delay change between T3 and T2 is... The change is 53ms - 55ms = -2ms. Correlation analysis is performed between the delay change data and the time-series fluctuation rate. The time-series fluctuation rate is the ratio of the absolute value of the signal delay change to the time interval. The fluctuation rate of T2-T1 is |3ms| / 5min = 0.6ms / min. The Pearson correlation coefficient between the signal delay change sequence and the time-series fluctuation rate sequence is calculated. The correlation coefficient reflects whether the delay fluctuation is a trend change or random noise. A correlation coefficient threshold of 0.7 is set. This threshold is set based on data analysis. The correlation coefficient is 0.85. A correlation coefficient higher than 0.7 indicates that the signal delay fluctuation and the time-series fluctuation rate are positively correlated. The signal delay fluctuation correlation coefficient is generated.

[0037] S502: Based on the signal delay fluctuation correlation coefficient and combined with the path characteristic parameters, perform a matching judgment operation on the path performance at key time points, filter the set of paths that meet the synchronization conditions, and obtain the synchronization path judgment value range. The correlation coefficient of signal delay fluctuation is read and evaluated in conjunction with the path characteristic parameters, including path bandwidth (100Mbps), network congestion level (20%), and node processing capacity (CPU utilization 60%). The path performance at key time points is analyzed, and a matching judgment operation is performed. The matching judgment compares the correlation coefficient with the synchronization condition threshold and the path characteristic parameters with the path performance range. The synchronization condition threshold is set to 0.75. The path bandwidth performance range is higher than 80Mbps, the network congestion performance range is lower than 30%, and the node processing capacity performance range is lower than 75%. The correlation coefficient is 0.85, which is higher than 0.75. The path bandwidth is 100Mbps, the congestion is 20%, and the processing capacity is 60%, all within the performance range. The path meets the synchronization condition. The set of paths that meet the synchronization condition is filtered. For example, if the path is from node A to node C and then to the cloud, it is filtered as a path that meets the synchronization condition, and its reliability score is 0.88. A synchronization path judgment value range is generated, which includes the path reliability score of 0.88.

[0038] S503: Call the synchronization path determination value range, compare it with the synchronization node parameters in the time-series fluctuation signal, determine the optimal path and corresponding node parameters for health monitoring recovery, and output the health monitoring recovery path and synchronization node configuration table. Read the synchronization path determination value range, which identifies the set of optimal paths that meet the synchronization conditions. Read the synchronization node parameters from the timing fluctuation signal. The parameters include the timestamp synchronization protocol (NTP) for node A, the data caching strategy (512MB cache, 30 seconds) for node C, and the data packet retransmission mechanism (3 retransmissions). Compare the synchronization path determination value range with the synchronization node parameters one by one. The optimal path determination value is 0.88, and the ideal determination value range is [0.80, 1.00]. The path meets the determination value requirements. Check the synchronization node parameters of nodes A and C on the path to ensure that the NTP protocol is running. The C-caching strategy effectively handles high-frequency data, and the retransmission mechanism ensures that data is not lost. It determines the optimal path for health monitoring and recovery and the corresponding node parameters. The optimal path has a high judgment value among paths that meet the synchronization conditions. The corresponding node parameters refer to the configuration required to ensure the operation of the optimal path. For example, the optimal path for health monitoring and recovery is determined from node A to node C and then to the cloud. The node parameter configuration is as follows: node A uses NTP time synchronization with a sampling frequency of 1 minute, node C uses a 512MB data cache, 3 retransmissions, and enables bandwidth priority allocation. A health monitoring and recovery path and synchronization node configuration table is generated.

[0039] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things, characterized in that, Includes the following steps: S1: Acquire the operating status of multi-source health sensing devices and the patient's daily activity records, combine the initial distribution characteristics of health indicators, analyze the temporal balance of health status, and generate a health status trend chart. S2: Call the health status trend chart, extract the abnormal fluctuation frequency and duration of each health indicator, sort by fluctuation frequency and exclude periods with duration below the set threshold, and generate a priority monitoring sequence. S3: Call the priority monitoring sequence, collect the operating environment parameters and signal quality assessment values ​​of the candidate monitoring nodes, compare and screen the nodes that meet the requirements, and map them through the logical correlation between the nodes and health indicators to obtain the node health correlation matching group; S4: Based on the node health association matching group, compare the current health status with the target health status, determine the direction of deviation, adjust the working mode of the monitoring node in the current monitoring cycle according to the direction of deviation, and generate a cardiology health monitoring list.

2. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 1, characterized in that, The health status trend chart includes health indicator number, time distribution feature identifier, and environmental adaptation value. The priority monitoring sequence includes fluctuation frequency parameter, duration limit value, and priority label. The node health association matching group includes logical association relationship identifier, signal quality benchmark range, and operating environment stability judgment value. The cardiology health monitoring list includes working mode code, health status adjustment direction, and optimization parameters within the monitoring period.

3. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 1, characterized in that, The specific steps for creating the health status trend chart are as follows: S101: Acquire the operating status of multi-source health sensing devices and the patient's daily activity records, perform comparison calculations between activity volume and initial health index distribution, identify the time distribution characteristics of health status, and generate a health status distribution sequence; S102: Call the health status distribution sequence, compare it with the set balance threshold according to the time distribution characteristics, filter the time period when the continuous characteristic value is lower than the balance threshold, extract the corresponding health indicator number and time window, and obtain the time distribution balance segment index set. S103: Based on the time distribution balanced segment index set, select health indicators with balanced characteristics as key monitoring objects, mark controllable interfaces and indicators with predictable health status, and generate a health status trend chart.

4. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 3, characterized in that, The specific steps for the priority monitoring sequence are as follows: S201: Call the health status trend chart, extract the corresponding health indicator number, abnormal fluctuation frequency and duration, identify the number to match each data item, and establish a set of health indicator operation parameters; S202: Based on the set of health indicator operating parameters, sort them in ascending order according to the frequency of abnormal fluctuations, filter the health indicator sequences with lower fluctuation frequencies, and obtain a fluctuation frequency sorting list. S203: Call the fluctuation frequency sorting list, compare the duration with the set minimum duration threshold, remove the periods with durations lower than the threshold, and generate a priority monitoring sequence.

5. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 4, characterized in that, The specific steps for the node health association matching group are as follows: S301: Call the priority monitoring sequence to capture the operating environment parameters and signal quality evaluation values ​​of the candidate monitoring nodes, summarize the real-time environmental parameters and signal quality values ​​of the nodes, and generate node operating status parameters; S302: Based on the node operating status parameters, and by comparing the environmental parameters, signal quality values, and required ranges, select nodes that meet the requirements to obtain a set of available nodes for health monitoring; S303: Call the set of available health monitoring nodes, map the node number to the health indicator channel according to the logical relationship between the list nodes and health indicators, calculate the node health correlation index, and obtain the node health correlation matching group.

6. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 5, characterized in that, The node operation status parameters include standardizing the mean environmental parameters and signal quality assessment values ​​of the candidate monitoring nodes to obtain a node operation score; The node health correlation index refers to the node health correlation calculated based on the correlation coefficient between the node operation score in the available node set for health monitoring and the corresponding health indicator channel. When the node health correlation index value is greater than the threshold, the node is determined to belong to the node health correlation matching group.

7. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 5, characterized in that, The specific steps for the cardiology health monitoring checklist are as follows: S401: Based on the node health association matching group, collect the real-time status values ​​of health indicators within the current monitoring period, match the target status value corresponding to each indicator, merge the current value and the target value according to the indicator number, and generate a health status difference data group. S402: Call the health status difference data group, determine the deviation direction between the current state and the target state of each health indicator, and classify the state into exceeding the standard and insufficient according to the positive and negative values ​​of the deviation values ​​to obtain the health status deviation direction identifier set; S403: Based on the set of health status deviation direction identifiers, locate the list monitoring nodes connected to the corresponding health indicators, adjust the node working mode within the current monitoring period, calculate the node operation coordination value, and generate the cardiology health monitoring list.

8. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 7, characterized in that, The node operation coordination value refers to the node operation coordination value that reflects the degree of coordination between nodes, obtained by calculating the operation coordination performance index between nodes based on the interconnection relationship and operation parameters between nodes after the node working mode adjustment is completed.

9. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 1, characterized in that, The method also includes step S5: S5: Call the cardiology health monitoring list, compare the signal delay and temporal fluctuation rate in the monitoring path, perform matching and filtering based on path characteristics and key time points, and output the health monitoring recovery path and synchronization node configuration table. The health monitoring recovery path and synchronization node configuration table includes signal delay coefficient, synchronization configuration time point, and response characteristics.

10. The method for monitoring health data of high-risk groups for cardiovascular disease based on the Internet of Things according to claim 9, characterized in that, The specific steps for configuring the health monitoring recovery path and synchronization node table are as follows: S501: Call the cardiology health monitoring list, extract the delay changes at key time points based on the signal delay data in the monitoring path, and perform correlation analysis with the time-series fluctuation rate to generate a signal delay fluctuation correlation coefficient. S502: Based on the signal delay fluctuation correlation coefficient and combined with the path characteristic parameters, perform a matching judgment operation on the path performance at key time points, filter the set of paths that meet the synchronization conditions, and obtain the synchronization path judgment value range. S503: Call the synchronization path determination value range, compare it with the synchronization node parameters in the time-series fluctuation signal, determine the optimal path and corresponding node parameters for health monitoring recovery, and output the health monitoring recovery path and synchronization node configuration table.

Images