Intelligent health assessment analysis method and system based on precise management

Abstract

The invention relates to the technical field of precise health management, in particular to an intelligent health assessment analysis method and system based on precise management, and the method comprises the following steps: accessing monitoring equipment of a patient, collecting physiological indexes in real time, combining historical health data, inputting physiological index data to a health management database, and carrying out grading processing. And establishing an initial health file. According to the method, the dynamic association network of the health factors is updated in real time, continuous monitoring and accurate prediction of the health state of the patient are achieved, prediction parameters can be adjusted in time when continuous health state simulation is conducted, health management is more adaptive and accurate, the health track is analyzed in real time, and the accuracy of health management is improved. In particular, in the aspect of identifying key health transition nodes, a scientific basis is provided for medical providers to intervene at key moments, and in combination with behavior data and change analysis of emotion cognition, individual health maintenance schemes can be accurately adjusted, and targeted and accurate health guidance is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of precision health management, and particularly to an intelligent health assessment and analysis method and system based on precision management. Background Art

[0002] Precision health management is an interdisciplinary technical field that combines bioinformatics, data science, medical technology, and personalized medical strategies. Its core goal is to optimize the health management and disease prevention of patients through highly personalized data analysis. This includes using advanced data analysis tools to analyze large amounts of health data from various sources, such as physiological parameters, lifestyle information, and environmental data. By accurately evaluating the data, it can help medical service providers customize more effective treatment plans and health maintenance plans for each patient, thereby improving the treatment effect and quality of life.

[0003] Among them, the intelligent health assessment and analysis method is an application in precision health management, mainly used to evaluate an individual's health status and predict potential health risks through intelligent algorithms. It usually combines technologies such as machine learning and artificial intelligence, as well as real-time data collected from medical devices and health applications. Its uses include but are not limited to early disease diagnosis, health risk assessment, disease prevention, and the formulation of personalized treatment plans, and it can provide faster and more accurate health assessment results to help medical professionals and patients make more informed health decisions.

[0004] Although existing precision health management technologies integrate data science and medical technology, they have limitations in processing real-time changing health data and predicting acute health events. Existing methods usually focus on the analysis of static data, lacking dynamic monitoring of the patient's condition and a real-time feedback mechanism, which may lead to delays in intervention measures in medical scenarios that require rapid response. In addition, existing technologies often fail to fully utilize the patient's behavior pattern and mood change data, resulting in deficiencies in the personalization and accuracy of health prediction and risk assessment. These technical limitations may affect the timely adjustment of treatment plans, reduce the effectiveness of disease prevention, increase the complexity of long-term health management, and thus affect the overall treatment effectiveness and quality of life of patients. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an intelligent health assessment and analysis method and system based on precision management.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: An intelligent health assessment and analysis method based on precision management, comprising the following steps:

[0007] S1: Connect the patient's monitoring device, collect physiological indicators in real time, combine with historical health data, input the physiological indicator data into the health management database, perform grading processing, and establish an initial health record;

[0008] S2: Based on the initial health record, analyze the data weights of the patient's health factors, construct a dynamic association network among the health factors, link and dynamically update the influence relationships of the health factors according to the actual influence weights, and establish a health factor interaction model;

[0009] S3: Based on the health factor interaction model, set a time window to perform simulation analysis of the patient's health status, adjust the prediction analysis parameters in real time, and output the health trajectory prediction result;

[0010] S4: Utilize the health trajectory prediction result, detect key health transition nodes through risk analysis, identify potential intervention points in combination with health management standards, and create a risk identification and intervention point mapping record;

[0011] S5: Combine the risk identification and intervention point mapping record, collect the patient's behavior data, predict the patient's emotional and cognitive changes through behavior pattern analysis, and obtain the patient's emotional and cognitive analysis result;

[0012] S6: Based on the patient's emotional and cognitive analysis result, deeply analyze the patient's comprehensive health information, combine with real-time monitoring data, perform health status assessment analysis, and generate a health status intelligent analysis result.

[0013] As a further solution of the present invention, the initial health record includes the patient's physiological baseline, historical treatment response records, and vaccination records. The health factor interaction model includes a physiological parameter influence diagram, a mental health connection diagram, and a social behavior pattern diagram. The health trajectory prediction result includes short-term health trend analysis records, long-term health prediction records, and critical health event probability analysis records. The risk identification and intervention point mapping record includes critical health indicators and potential risk areas. The patient's emotional and cognitive analysis result includes the patient's emotional stability score, cognitive function change analysis records, and behavior pattern deviation analysis results. The health status intelligent analysis result includes the patient's overall health rating, critical health indicator analysis results, and health improvement measures.

[0014] As a further solution of the present invention, the acquisition steps of the initial health record are as follows:

[0015] S101: Connect the patient monitoring device, collect physiological indicators in real time through a wireless sensor network, including heart rate, blood pressure, and blood oxygen saturation, and perform preliminary verification of the data to generate a real-time physiological data set;

[0016] S102: Use the real-time physiological data set for data cleaning, removing outliers, filling in missing values, and performing unified data format processing to obtain a standardized physiological data set;

[0017] S103: Import the standardized physiological data set into the health management database, integrate it with historical health data, and use time series analysis to archive the data and establish a preliminary health record.

[0018] As a further solution of the present invention, the steps for obtaining the health factor interaction model are as follows:

[0019] S201: Use the preliminary health record to analyze the occurrence frequency of all health factors and the clinical feedback of patients, calculate the influence degree of each health factor on the health status, evaluate the data weight of the health factors, and sort them to generate a health factor weight list;

[0020] S202: Based on the health factor weight list, analyze the dependence relationship between different health factors, identify key health factors, and adjust the connection strength between health factors according to real-time updated health data to obtain a health factor dynamic association network;

[0021] S203: Use the health factor dynamic association network to comprehensively analyze the interaction between health factors, quantitatively update the mutual influence of each health factor, update and optimize the relationship model between health factors according to the interaction data, and establish a health factor interaction model.

[0022] As a further solution of the present invention, when constructing the health factor dynamic association network, according to the formula:

[0023]

[0024] Calculate the degree centrality of each health factor, where C ′ d (i) represents the degree centrality of the health factor, W ij is the original connection strength between node i and node j, S ij is the similarity score between health factors, T ij is the time dependence score between health factors, D ij is the distance between factor i and j, and λ is the attenuation coefficient.

[0025] As a further solution of the present invention, the steps for obtaining the health trajectory prediction result are as follows:

[0026] S301: Based on the health factor interaction model, set a time window, collect the patient's health data within the time window, perform periodic data input and status assessment, simulate the time-dependent changes in the patient's health status, and generate a simulation result of the health status time series;

[0027] S302: Use the simulation result of the health status time series to perform real-time data monitoring, adjust the influence weights of key health factors, dynamically update the model parameters based on the latest health data, match the real-time changes in the patient's health status, and obtain the prediction parameters adjusted in real time;

[0028] S303: Apply the prediction parameters adjusted in real time to perform a prospective analysis of the patient's health trajectory, output a health trajectory prediction result by simulating the potential paths of the patient's future health status.

[0029] As a further solution of the present invention, the steps for obtaining the risk identification and intervention point mapping file are as follows:

[0030] S401: Based on the health trajectory prediction result, perform time series analysis on each predicted data point, identify abnormal changes in physiological indicators, mark the change points as key health transition nodes, and generate a list of key health transition nodes;

[0031] S402: Use the list of key health transition nodes to compare with health management standards, including blood pressure control standards and diabetes management guidelines, analyze and determine the intervention points, and obtain the identification result of potential intervention points;

[0032] S403: Combine the key health transition nodes with the identification result of potential intervention points, create a mapping file, record each transition node and the corresponding intervention measures, and establish a risk identification and intervention point mapping file.

[0033] As a further solution of the present invention, the steps for obtaining the patient's emotional and cognitive analysis result are as follows:

[0034] S501: Based on the risk identification and intervention point mapping file, collect the patient's life behavior data through wearable devices and daily questionnaires, including sleep patterns, activity levels, and eating habits, capture the daily behavior patterns, and generate a patient behavior data set;

[0035] S502: Use the patient behavior data set to analyze the patient's behavior trends and habits, determine the behavior changes associated with the health transition nodes, compare the abnormal behavior patterns before and after the health transition, and predict the patient's potential emotional and cognitive changes to obtain the prediction result of emotional and cognitive changes;

[0036] S503: Analyze the relationship between the prediction results and the actual health status of the patient by synthesizing the predicted results of emotional and cognitive changes, evaluate the potential impact on the patient's health status, and establish the analysis results of the patient's emotions and cognition.

[0037] As a further solution of the present invention, the steps for obtaining the intelligent analysis results of the health status are as follows:

[0038] S601: Based on the analysis results of the patient's emotions and cognition, integrate the patient's historical medical records and real-time physiological monitoring data, including heart rate, blood pressure, number of steps walked, and sleep quality, construct a comprehensive health record of the patient, and generate a comprehensive health information set;

[0039] S602: Use the comprehensive health information set to analyze the current health status and potential risks of the patient, evaluate the changing trend of the health status and the key risk points, and conduct a preliminary analysis of the patient's health status through the comprehensive information to obtain the preliminary analysis results of the health status evaluation;

[0040] S603: According to the preliminary analysis results of the health status evaluation, conduct a in-depth analysis of the patient's health status, compare the preliminary evaluation results with the patient's treatment plan, optimize the health management measures, match the actual health status of the patient, and establish the intelligent analysis results of the health status.

[0041] An intelligent health assessment and analysis system based on precision management, comprising:

[0042] The physiological data acquisition module is connected to the patient monitoring device, and real-time physiological indicators are collected through a wireless sensor network, and preliminary verification and data cleaning of the data are carried out, and unified processing of the data format is carried out, and the data is imported into the health management database, and integrated and archived with the historical health data to establish a preliminary health record;

[0043] The health factor analysis module calculates the influence degree of each health factor on the health status based on the preliminary health record, evaluates the data weight of the health factor, analyzes the dependence relationship between different health factors, adjusts the connection strength between the health factors, and establishes a dynamic association network of health factors;

[0044] The health status simulation module uses the dynamic association network of health factors to analyze the interaction between health factors, quantitatively update the mutual influence of each health factor, and set a time window to collect the patient's health data, and perform periodic data input and status evaluation to generate a simulation result of the health status time series;

[0045] The health trajectory prediction module uses the simulation result of the health status time series to perform real-time data monitoring, adjusts the influence weight of the key health factors, matches the real-time changes of the patient's health status, and conducts a prospective analysis of the patient's health trajectory to output the health trajectory prediction result;

[0046] Based on the health trajectory prediction results, the risk mapping module performs a time series analysis on the prediction data points, marks the key health transition nodes, compares them with the health management standards, analyzes and determines the intervention points, records each transition node and the corresponding intervention measures, and establishes a risk identification and intervention point mapping file;

[0047] Based on the risk identification and intervention point mapping file, the behavior pattern analysis module collects the patient's life behavior data, captures the patient's daily behavior patterns, analyzes the patient's behavior trends and habits, compares the abnormal behavior patterns before and after the health transition, evaluates the potential impact on the patient's health status, and establishes the patient's emotional cognitive analysis results;

[0048] Based on the patient's emotional cognitive analysis results, the health status assessment module integrates the patient's historical medical records and real-time physiological monitoring data, analyzes the patient's current health status and potential risks, evaluates the change trend of the health status and the key risk points, optimizes the health management measures, and establishes the intelligent analysis results of the health status.

[0049] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0050] In the present invention, by continuously updating the dynamic association network of health factors, continuous monitoring and accurate prediction of the patient's health status are achieved. During the continuous health status simulation, the prediction parameters can be adjusted in a timely manner, making the health management more adaptable and accurate. Real-time analysis of the health trajectory, especially in identifying the key health transition nodes, provides a scientific basis for medical providers to intervene at critical moments. Combining the analysis of behavior data and emotional cognitive changes, the individual's health maintenance plan can be accurately adjusted, providing targeted and accurate health guidance, not only improving the pertinence of the treatment plan, but also effectively improving the overall efficiency of health management and the patient's quality of life. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the working process of the present invention;

[0052] Figure 2 It is a flowchart for obtaining the initial health file of the present invention;

[0053] Figure 3 It is a flowchart for obtaining the health factor interaction model of the present invention;

[0054] Figure 4 It is a flowchart for obtaining the health trajectory prediction results of the present invention;

[0055] Figure 5 It is a flowchart for obtaining the risk identification and intervention point mapping file of the present invention;

[0056] Figure 6This is the flowchart for obtaining the analysis results of the patient's emotional cognition in the present invention;

[0057] Figure 7 This is the flowchart for obtaining the analysis results of the intelligent analysis of the health status in the present invention. Detailed implementation manners

[0058] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be 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 used to limit the present invention.

[0059] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, in the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0060] Embodiment 1

[0061] Please refer to Figure 1 , the present invention provides a technical solution: an intelligent health assessment and analysis method based on precise management, including the following steps:

[0062] S1: Connect the patient's monitoring device, collect physiological indicators in real time, combine historical health data, input the physiological indicator data into the health management database, perform grading processing, and establish an initial health record;

[0063] S2: Based on the initial health record, analyze the data weights of the patient's health factors, construct a dynamic association network between health factors, link and dynamically update the influence relationship of health factors according to the actual influence weights, and establish a health factor interaction model;

[0064] S3: Based on the health factor interaction model, set a time window to perform simulation analysis of the patient's health status, adjust the prediction analysis parameters in real time, and output the health trajectory prediction result;

[0065] S4: Use the health trajectory prediction result, detect key health transition nodes through risk analysis, identify potential intervention points in combination with health management standards, and create a risk identification and intervention point mapping record;

[0066] S5: Combine the risk identification and intervention point mapping file, collect the patient's behavior data, predict the patient's emotional and cognitive changes through behavioral pattern analysis, and obtain the patient's emotional and cognitive analysis results;

[0067] S6: Based on the patient's emotional and cognitive analysis results, deeply analyze the patient's comprehensive health information, combine the real-time monitoring data, conduct a health status assessment analysis, and generate an intelligent health status analysis result.

[0068] The initial health file includes the patient's physiological baseline, historical treatment response records, and vaccination records. The health factor interaction model includes physiological parameter influence diagrams, mental health connection diagrams, and social behavior pattern diagrams. The health trajectory prediction results include short-term health trend analysis records, long-term health prediction records, and critical health event probability analysis records. The risk identification and intervention point mapping file includes critical health indicators and potential risk areas. The patient's emotional and cognitive analysis results include the patient's emotional stability score, cognitive function change analysis records, and behavioral pattern deviation analysis results. The intelligent health status analysis result includes the patient's overall health rating, critical health indicator analysis results, and health improvement measures.

[0069] Please refer to Figure 2 , the steps for obtaining the initial health file are as follows:

[0070] S101: Connect the patient monitoring device, and real-time collect physiological indicators through the wireless sensor network, including heart rate, blood pressure, and blood oxygen saturation, and conduct preliminary verification of the data to generate a real-time physiological data set;

[0071] After connecting the monitoring device, conduct a preliminary inspection on each received data. The inspection includes confirming data integrity and basic physiological rationality checks. For example, the heart rate data should be within the set normal range, such as 40 to 200 beats per minute. In addition, the blood pressure data should be within the controlled range, for example, the systolic blood pressure is not less than 90 mmHg and does not exceed 180 mmHg. All out-of-range data will be marked as abnormal and recorded in the data set. In this way, ensure that each data point in the collected data set meets the basic physiological parameter requirements, providing accurate basic data for subsequent analysis and processing.

[0072] S102: Use the real-time physiological data set, conduct data cleaning, remove outliers, fill in missing values, and conduct unified data format processing to obtain a standardized physiological data set;

[0073] First, outliers are removed, that is, records with a heart rate exceeding 200 beats per minute or below 40 beats per minute are excluded, and the same applies to records in blood pressure data where the systolic blood pressure exceeds 180 mmHg or is below 90 mmHg. For missing data points, the adjacent value filling method is used, that is, the average value of the front and back data points is used to replace the missing value. In addition, the data format needs to be unified to ensure that all data is stored in a unified format, such as unifying the timestamp format to: YYYY-MM-DD HH:MM. Through these specific operations, the consistency and accuracy of the data set can be ensured, providing a standardized input for subsequent analysis.

[0074] S103: Import the standardized physiological data set into the health management database, integrate it with the historical health data, and use time series analysis to archive the data to establish a preliminary health record;

[0075] The newly collected data is merged with the existing historical data, and time series analysis techniques are used to evaluate the long-term trends and periodic changes in the data. Specific operations include applying time series models, such as ARIMA, to predict future health trends. This step not only helps to establish the health record of each patient but also provides information on the past and expected future health status for medical staff, thus supporting more precise health management and disease prevention strategies. By comprehensively utilizing the results of time series analysis, the information value of the health record can be enhanced, making it an important resource to support medical decision-making.

[0076] Please refer to Figure 3 , and the steps to obtain the health factor interaction model are as follows:

[0077] S201: Using the preliminary health record, analyze the occurrence frequency of all health factors and the clinical feedback of patients, calculate the impact degree of each health factor on the health status, evaluate the data weight of the health factors, and sort them to generate a health factor weight list;

[0078] In this process, first, the occurrence frequency of health factors in different patients is statistically analyzed, and then the importance of each factor is evaluated in combination with the clinical feedback of patients. Specifically, the occurrence frequency of each health factor is associated with the improvement or deterioration of the patient's health, and the following formula is used to calculate the weight of the factor:

[0079]

[0080] Among them, W i represents the weight of health factor i, f i is the occurrence frequency of factor i, R jis the feedback score of the patient associated with factor i, and N is the total number of scores. Then, all health factors are sorted according to the calculated weights to generate a weight list, which helps to identify the factors that have the greatest impact on the patient's health status.

[0081] S202: Based on the health factor weight list, analyze the dependencies between different health factors, identify key health factors, adjust the connection strength between health factors according to real-time updated health data, and construct a dynamic association network of health factors;

[0082] For the construction of the dynamic association network of health factors, according to the formula:

[0083]

[0084] calculate the degree centrality of each health factor, where C ′ d (i) represents the degree centrality of the health factor, W ij is the original connection strength between node i and node j, S ij is the similarity score between health factors, T ij is the time dependence score between health factors, D ij is the distance between factor i and j, and λ is the attenuation coefficient.

[0085] The execution process is as follows:

[0086] First, the basic association between factors is characterized by the original connection strength W ij and then multiplied by the similarity score S ij , which can be calculated through the feature similarity between factors, and then multiplied by the time dependence score T ij , which is calculated according to the dependence strength between two health factors in time series data, and finally multiplied by an exponential decay term This term is used to adjust the influence when the physical or logical distance between factors is relatively far. The attenuation coefficient λ can be learned on the training dataset through an optimization algorithm (such as gradient descent) to comprehensively explain the overall execution process of the improved formula.

[0087] S203: Use the dynamic association network of health factors to comprehensively analyze the interactions between health factors, quantitatively update the mutual influence of each health factor, update and optimize the relationship model between health factors according to interaction data, and establish a health factor interaction model;

[0088] In this step, through the dynamic association network, the interaction relationships between health factors are continuously updated and refined. The real-time updated health data is used to adjust the connection strength in the network, ensuring that the model can reflect the latest health status and the mutual influence between factors. In particular, by regularly comparing the historical and current data analysis results, the weights and connection methods between factors are adjusted, so that the health factor interaction model always maintains an optimal state and can more accurately predict and manage the patient's health status.

[0089] Please refer to Figure 4 , the steps for obtaining the health trajectory prediction results are as follows:

[0090] S301: Based on the health factor interaction model, set a time window, collect the patient's health data within the time window, perform periodic data input and status evaluation, simulate the time-dependent changes in the patient's health status, and generate the simulation results of the health status time series;

[0091] Within the set time window (such as weekly), the system automatically collects data on key health indicators including heart rate, blood pressure, etc. The collected data is preliminarily processed through the formula where x i,t represents the value of the i-th health indicator at time t, k is the total number of monitored health factors, and D t is the data after preliminary processing. Next, the weighted moving average method is used to smooth the data, and the formula is S t =αx t +(1-α)S t-1 , where α is the smoothing coefficient used to adjust the influence degree of historical data on the prediction. Here, S t is the predicted value at time point t after smoothing, and S t-1 is the predicted value at the previous time point t-1, so as to adapt to the rapid changes in the patient's health status. Through this method, the generated health status time series can more accurately simulate the patient's health changes and provide a basis for subsequent analysis.

[0092] S302: Using the simulation results of the health status time series, perform real-time data monitoring, adjust the influence weights of key health factors, dynamically update the model parameters based on the latest health data, match the real-time changes in the patient's health status, and obtain the real-time adjusted prediction parameters;

[0093] During the monitoring process, identify key health trend changes and adjust the weights of health factors through the formula: Here, w i,new and w i,old are the weights of health factor i before and after adjustment respectively, β is the adjustment rate parameter, and y t is the measured health indicator. is the predicted value of the model, and exp represents the natural exponential function. In addition, to ensure the adaptability and flexibility of the model, the gradient descent algorithm is periodically used to optimize the parameter settings of the entire model. The dynamic adjustment mechanism ensures that the model can immediately reflect the latest status of health data and accurately predict future health trends.

[0094] S303: Apply the real-time adjusted prediction parameters to conduct a prospective analysis of the patient's health trajectory. By simulating the potential paths of the patient's future health status, output the health trajectory prediction results;

[0095] During this process, use the formula for prediction, where δ i represents the future change amount of the health factor i predicted according to the current trend, H future is the future predicted health status, H current is the current health status, and w i is the weight of factor i. To further improve the prediction accuracy, Monte Carlo simulation is combined to generate multiple possibilities of the patient's future health status, so as to provide more comprehensive data support for medical decision-making. Through this method, the combined effects of various health factors and their potential impacts on the future health status can be comprehensively considered, and a more personalized and accurate health management plan can be provided for the patient.

[0096] Please refer to Figure 5 for the steps to obtain the risk identification and intervention point mapping file:

[0097] S401: Based on the health trajectory prediction results, conduct a time series analysis on each predicted data point, identify abnormal changes in physiological indicators, mark the change points as key health transition nodes, and generate a list of key health transition nodes;

[0098] In this step, the moving average model is used to smooth the data to identify abnormal points. The specific calculation method is the moving average where X i is the physiological indicator value at the i-th time point, and n is the size of the time window considered, usually selected according to specific circumstances such as 24 hours or one week. When identifying abnormal points, by comparing the deviation between the actual data point and its moving average, if the deviation exceeds the set threshold (such as twice the standard deviation), it is marked as a key health transition node. This method can balance the random fluctuations and trend changes of the data and effectively mark the mutation points.

[0099] S402: Use the list of key health transition nodes to compare with health management standards, including blood pressure control standards and diabetes management guidelines, analyze and determine the intervention points, and obtain the potential intervention point identification results;

[0100] For each critical health transition node, compare it with the existing health management standards and use the formula ΔX t = X t - S norm to quantify the degree of deviation. Here, ΔX t is the deviation value, X t is the physiological index value at the critical node, and S norm is the upper or lower limit of the normal range of the corresponding index. If the absolute value of ΔX t exceeds the tolerance threshold, these nodes are identified as potential points requiring intervention. This step ensures the accuracy and timeliness of the intervention measures and helps to prevent and control the patient's health risks in advance.

[0101] S403: Combine the critical health transition nodes with the results of potential intervention point identification, create a mapping file, record each transition node and the corresponding intervention measures, and establish a risk identification and intervention point mapping file;

[0102] At this stage, the association between the critical nodes and the intervention points is achieved through a mapping function. Use the conditional function I t = f(N t , G t ), where N t represents the node time, G t is the intervention requirement flag (1 represents the need for intervention, 0 represents no need), and I t is the corresponding intervention measure description. This mapping record not only helps to quickly identify health events that require immediate response but also systematically organizes and updates the intervention strategies to ensure the efficiency and orderliness of the entire intervention process.

[0103] Please refer to Figure 6 , the steps to obtain the patient's emotional cognitive analysis results are as follows:

[0104] S501: Based on the risk identification and intervention point mapping file, collect the patient's life behavior data through wearable devices and daily questionnaires, including sleep patterns, activity levels, and eating habits, capture the daily behavior patterns, and generate the patient behavior dataset;

[0105] In this process, use wearable devices to automatically record physiological indicators such as the patient's activity intensity, sleep quality, and heart rate. At the same time, supplement the information on eating habits and lifestyle through daily or weekly questionnaires. By integrating these data, calculate the comprehensive behavior score B t using the following formula: where S t , A t , and D tStandardized scores representing sleep patterns, activity levels, and eating habits, respectively. This method provides a quantitative way to observe the daily behavior patterns of patients and convert this information into a dataset for further analysis.

[0106] S502: Utilize the patient behavior dataset to analyze patient behavior trends and habits, identify behavior changes associated with healthy transition nodes, compare abnormal behavior patterns before and after healthy transitions, predict potential emotional and cognitive changes in patients, and obtain prediction results for emotional and cognitive changes;

[0107] Identify key change points in behavior patterns through time series analysis and conduct correlation analysis with healthy transition nodes. Use the difference analysis formula: ΔB t =B t -B t-1 to identify significant behavior changes, where B t and B t-1 are the behavior scores at two consecutive time points respectively. This difference value helps determine the mutation points of behavior, corresponding to the healthy transition nodes, thereby revealing the potential connection between behavior changes and changes in health status. Further, these change points can be used to predict changes in the emotional and cognitive states of patients, providing a basis for subsequent interventions.

[0108] S503: Synthesize the prediction results of emotional and cognitive changes, analyze the relationship between the prediction results and the actual health status of the patient, evaluate the potential impact on the patient's health status, and establish the analysis results of the patient's emotional cognition;

[0109] At this stage, by comparing the results of emotional and cognitive changes with the medical data recorded in the patient's health record, use the correlation analysis formula: where x i and y i are the observed values of the emotional and cognitive state and the health status respectively, represents the average value. By calculating the correlation coefficient C between these two datasets, the degree of influence of changes in the emotional and cognitive states on the patient's health status can be evaluated. The results of this analysis help understand how emotions and cognition interact with physical health and provide a scientific basis for formulating personalized treatment plans.

[0110] Please refer to Figure 7 for the steps to obtain the intelligent analysis results of the health status:

[0111] S601: Based on the analysis results of the patient's emotional cognition, integrate the patient's historical medical records and real-time physiological monitoring data, including heart rate, blood pressure, number of steps walked, and sleep quality, construct a comprehensive health record of the patient, and generate a comprehensive health information set;

[0112] In this process, use the data integration formula Htotal = α1H hist + α2H real , where H hist represents the weighted value of historical medical records, and H real represents the weighted value of real-time physiological monitoring data. α1 and α2 are weight coefficients for adjusting the influence of the two types of data. Such integration helps to comprehensively understand the patient's long-term and immediate health status, providing a more complete picture of health, thus supporting more accurate health assessment and management.

[0113] S602: Using the comprehensive health information set, analyze the patient's current health status and potential risks, evaluate the changing trend of the health status and key risk points, conduct a preliminary analysis of the patient's health status through the comprehensive information, and obtain the preliminary analysis result of the health status assessment;

[0114] In this step, the linear trend analysis formula ΔH = β1Δt + β0 is adopted, where ΔH represents the change in the health status, Δt is the time variable, and β1 and β0 are parameters determined through data regression. This formula can help reveal the changing trend of the health status over time, thereby identifying potential health risks and key change points, providing decision support for further health management.

[0115] S603: According to the preliminary analysis result of the health status assessment, conduct a in-depth analysis of the patient's health status, compare the preliminary assessment result with the patient's treatment plan, optimize the health management measures, match the actual health status of the patient, and establish the intelligent analysis result of the health status;

[0116] In this step, the complex statistical correlation analysis formula R = γ1P current + γ2P plan + ∈ is applied, where P current is the current health status parameter, P plan is the predefined parameter in the treatment plan, γ1 and γ2 are weight coefficients, and ∈ is the error term. In this way, the matching degree between the patient's current health status and the predefined treatment plan can be accurately evaluated, and the treatment plan can be adjusted if necessary to better meet the actual health needs of the patient, thereby achieving the purpose of optimizing the health management measures. These analysis results support the construction of more personalized and accurate health intervention strategies.

[0117] An intelligent health assessment and analysis system based on precision management, comprising:

[0118] The physiological data acquisition module is connected to the patient monitoring device, and real-time physiological indicators are collected through a wireless sensor network, and preliminary verification and data cleaning of the data are carried out, and unified processing of the data format is carried out, and the data is imported into the health management database, integrated and archived with the historical health data, and a preliminary health record is established;

[0119] Based on the preliminary health records, the health factor analysis module calculates the impact degree of each health factor on the health status, evaluates the data weights of the health factors, analyzes the dependency relationships among different health factors, adjusts the connection strengths among the health factors, and establishes a dynamic association network of health factors;

[0120] Using the dynamic association network of health factors, the health status simulation module analyzes the interactions among the health factors, quantitatively updates the mutual influences of each health factor, sets a time window to collect the patient's health data, performs periodic data input and status evaluation, and generates the simulation results of the health status time series;

[0121] Using the simulation results of the health status time series, the health trajectory prediction module conducts real-time data monitoring, adjusts the influence weights of key health factors, matches the real-time changes in the patient's health status, conducts a prospective analysis of the patient's health trajectory, and outputs the health trajectory prediction results;

[0122] Based on the health trajectory prediction results, the risk mapping module conducts a time series analysis of the predicted data points, marks the key health transition nodes, compares with the health management standards, analyzes and determines the intervention points, records each transition node and the corresponding intervention measures, and establishes a risk identification and intervention point mapping file;

[0123] Based on the risk identification and intervention point mapping file, the behavior pattern analysis module collects the patient's life behavior data, captures the patient's daily behavior patterns, analyzes the patient's behavior trends and habits, compares the abnormal behavior patterns before and after the health transition, evaluates the potential impact on the patient's health status, and establishes the analysis results of the patient's emotional cognition;

[0124] Based on the analysis results of the patient's emotional cognition, the health status evaluation module integrates the patient's historical medical records and real-time physiological monitoring data, analyzes the patient's current health condition and potential risks, evaluates the change trend of the health status and the key risk points, optimizes the health management measures, and establishes the intelligent analysis results of the health status.

[0125] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the relevant art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent health assessment and analysis method based on precise management, characterized in that: The following steps are involved: Access the patient's monitoring equipment, collect physiological indicators in real time, combine historical health data, input physiological indicator data into the health management database, perform classification processing, and establish an initial health record; Based on the initial health record, the data weights of the patient's health factors are analyzed, a dynamic association network between health factors is constructed, the influence relationship of health factors is dynamically updated according to the actual influence weight links, and a health factor interaction model is established; Based on the health factor interaction model, a time window is set to simulate and analyze the patient's health status, and the prediction analysis parameters are adjusted in real time to output the health trajectory prediction results; Using the health trajectory prediction results, detecting key health transition nodes through risk analysis, identifying potential intervention points in combination with health management standards, and creating a risk identification and intervention point mapping archive; In combination with the risk identification and intervention point mapping archive, patient behavior data is collected, and patient emotions and cognitive changes are predicted through behavioral pattern analysis to obtain patient emotion and cognitive analysis results; Based on the patient's emotional cognitive analysis results, the patient's comprehensive health information is deeply analyzed, and health status assessment and analysis are performed in combination with real-time monitoring data to generate health status intelligent analysis results.

2. The intelligent health assessment and analysis method based on precise management according to claim 1 is characterized in that: The initial health record includes the patient's physiological baseline, historical treatment response records and vaccination records; the health factor interaction model includes a physiological parameter influence diagram, a mental health connection diagram and a social behavior pattern diagram; the health trajectory prediction results include short-term health trend analysis records, long-term health prediction records and key health event probability analysis records; the risk identification and intervention point mapping archive includes critical health indicators and potential risk areas; the patient's emotional cognitive analysis results include the patient's emotional stability score, cognitive function change analysis records and behavioral pattern deviation analysis results; the health status intelligent analysis results include the patient's overall health rating, key health indicator analysis results and health improvement measures.

3. The intelligent health assessment and analysis method based on precise management according to claim 1 is characterized in that: The steps for obtaining the initial health record are: Connect patient monitoring equipment to collect physiological indicators in real time through wireless sensor networks, including heart rate, blood pressure, and blood oxygen saturation, and perform preliminary verification of the data to generate a real-time physiological data set; Using the real-time physiological data set, data cleaning is performed to remove outliers, fill in missing values, and perform data format unification processing to obtain a standardized physiological data set; The standardized physiological data set is imported into the health management database, integrated with the historical health data, and the data is archived using time series analysis to establish a preliminary health record.

4. The intelligent health assessment and analysis method based on precise management according to claim 1 is characterized in that: The steps for obtaining the health factor interaction model are: Using the preliminary health records, analyzing the occurrence frequency of all health factors and clinical feedback from patients, calculating the degree of influence of each health factor on health status, evaluating the data weights of the health factors, and ranking them to generate a health factor weight list; Based on the health factor weight list, the dependency between the different health factors is analyzed, key health factors are identified, and the connection strength between the health factors is adjusted according to the real-time updated health data to build a dynamic association network of health factors; The health factor dynamic association network is used to comprehensively analyze the interactions between health factors, quantify and update the mutual influence of each health factor, update and optimize the relationship model between health factors based on the interaction data, and establish a health factor interaction model.

5. The intelligent health assessment and analysis method based on precise management according to claim 4 is characterized in that: The health factor dynamic association network is constructed according to the formula: Calculate the degree centrality of each health factor, where C ′ d (i) represents the health factor degree centrality, W ij is the original connection strength between node i and node j, S ij is the similarity score between health factors, T ij is the time-dependency score between health factors, D ij is the distance between factors i and j, and λ is the attenuation coefficient.

6. The intelligent health assessment and analysis method based on precise management according to claim 1 is characterized in that: The steps for obtaining the health trajectory prediction result are: Based on the health factor interaction model, a time window is set, patient health data within the time window is collected, periodic data input and status evaluation are performed, time-dependent changes in the patient's health status are simulated, and health status time series simulation results are generated; Using the health status time series simulation results, real-time data monitoring is performed to adjust the impact weights of key health factors, dynamically update model parameters based on the latest health data, match the real-time changes in the patient's health status, and obtain real-time adjusted prediction parameters; The real-time adjusted prediction parameters are applied to conduct a forward-looking analysis of the patient's health trajectory, and the health trajectory prediction results are output by simulating the potential path of the patient's future health status.

7. The intelligent health assessment and analysis method based on precise management according to claim 1 is characterized in that: The steps for obtaining the risk identification and intervention point mapping archive are as follows: Based on the health trajectory prediction results, perform time series analysis on each predicted data point, identify abnormal changes in physiological indicators, mark the change points as key health transition nodes, and generate a list of key health transition nodes; By using the list of key health transition nodes, comparing health management standards, including blood pressure control standards and diabetes management guidelines, analyzing and determining intervention points, and obtaining potential intervention point identification results; Combine the key health transition nodes with the potential intervention point identification results to create a mapping file, record each transition node and the corresponding intervention measures, and establish a risk identification and intervention point mapping file.

8. The intelligent health assessment and analysis method based on precise management according to claim 1 is characterized in that: The steps for obtaining the patient's emotional cognitive analysis results are: Based on the risk identification and intervention point mapping profile, collect patient life behavior data, including sleep patterns, activity levels, and eating habits, through wearable devices and daily questionnaires to capture daily behavior patterns and generate patient behavior data sets; Utilizing the patient behavior data set, analyzing the patient behavior trends and habits, determining the behavior changes associated with the health transition node, comparing the abnormal behavior patterns before and after the health transition, predicting the patient's potential emotions and cognitive changes, and obtaining the emotion and cognitive change prediction results; The predicted results of the emotions and cognitive changes are synthesized, the relationship between the predicted results and the actual health status of the patient is analyzed, the potential impact on the patient's health status is evaluated, and the patient's emotional cognitive analysis results are established.

9. The intelligent health assessment and analysis method based on precise management according to claim 1 is characterized in that: The steps for obtaining the health status intelligent analysis result are: Based on the patient's emotional cognitive analysis results, the patient's historical medical records and real-time physiological monitoring data, including heart rate, blood pressure, number of steps and sleep quality, are integrated to build a comprehensive health profile of the patient and generate a comprehensive health information set; Analyze the patient's current health status and potential risks using the comprehensive health information set, evaluate the changing trend of the health status and key risk points, conduct a preliminary analysis of the patient's health status through the comprehensive information, and obtain preliminary analysis results of the health status assessment; Based on the preliminary analysis results of the health status assessment, an in-depth health status analysis of the patient is conducted, the preliminary assessment results are compared with the patient's treatment plan, health management measures are optimized, the patient's actual health status is matched, and an intelligent health status analysis result is established.

10. An intelligent health assessment and analysis system based on precise management, characterized in that: According to any one of claims 1 to 9, the intelligent health assessment and analysis method based on precise management comprises: The physiological data collection module connects to the patient monitoring equipment, collects physiological indicators in real time through the wireless sensor network, performs preliminary data verification and data cleaning, and processes the data in a unified format, imports it into the health management database, integrates it with historical health data, and archives it to establish a preliminary health file; The health factor analysis module calculates the influence of each health factor on the health status based on the preliminary health records, evaluates the data weight of the health factors, analyzes the dependency between the different health factors, adjusts the connection strength between the health factors, and establishes a dynamic association network of health factors; The health status simulation module uses the health factor dynamic association network to analyze the interaction between health factors, quantify and update the mutual influence of each health factor, set a time window to collect patient health data, perform periodic data input and status evaluation, and generate health status time series simulation results; The health trajectory prediction module uses the health status time series simulation results to perform real-time data monitoring, adjust the influence weights of key health factors, match the real-time changes in the patient's health status, perform forward-looking analysis of the patient's health trajectory, and output the health trajectory prediction results; The risk mapping module performs time series analysis on the predicted data points based on the health trajectory prediction results, marks key health transition nodes, compares health management standards, analyzes and determines intervention points, records each transition node and corresponding intervention measures, and establishes a risk identification and intervention point mapping file; The behavior pattern analysis module collects patient life behavior data based on the risk identification and intervention point mapping archive, captures the patient's daily behavior pattern, analyzes the patient's behavior trends and habits, compares the abnormal behavior patterns before and after the health transition, evaluates the potential impact on the patient's health status, and establishes the patient's emotional cognitive analysis results; The health status assessment module is based on the patient's emotional cognitive analysis results, integrates the patient's historical medical records and real-time physiological monitoring data, analyzes the patient's current health status and potential risks, evaluates the changing trends and key risk points of the health status, optimizes health management measures, and establishes intelligent health status analysis results.

Images