Human body aging data dynamic identification early warning method and system

Abstract

The invention provides a human body aging data dynamic identification early warning method and system, and relates to the technical field of aging data dynamic identification early warning, and the method comprises the steps: obtaining user historical biological characteristic data, dividing the historical biological characteristic data according to a preset life monitoring period, and obtaining periodic biological characteristic data; generating a periodic biological aging portrait according to the periodic biological characteristic data, calculating a periodic biological aging age coefficient, performing periodic comparison and comprehensive comparison on the aging age coefficient, and further performing periodic aging judgment and user aging judgment; calculating an aging dynamic factor of each period according to the judgment information, judging an aging process, obtaining a period aging node, obtaining period interval data of the aging node, setting a weight according to the period interval data, and performing early warning; the accuracy and timeliness of human body aging monitoring can be improved, and powerful data support is provided for health management and disease prevention and intervention.

Description

Technical Field

[0001] The present invention proposes a method and system for dynamic identification and early warning of human aging data, which relate to the field of dynamic identification and early warning technology, and specifically to the field of dynamic identification and early warning technology of human aging data. Background Art

[0002] With the advancement of medical technology and the intensification of population aging, the monitoring and management of the human aging process has become an important direction of medical research. Traditional aging assessment methods mostly rely on single time points or static biometric data, such as age, blood pressure, blood sugar, etc., which are difficult to fully and dynamically reflect the complex process of human aging and its changing trends. In addition, there are significant differences in the aging speed and pattern between different individuals, which makes the assessment methods based on static data often lack personalization and accuracy.

[0003] In recent years, with the rapid development of technologies such as big data and artificial intelligence, dynamic monitoring and intelligent analysis of human biometric data have become possible. By continuously collecting and analyzing users' historical biometric data, we can have a more comprehensive and in-depth understanding of the physiological changes, disease risks, and health status of the human body during aging. However, most of the existing aging monitoring technologies remain at the data collection level, lacking effective data processing, analysis, and early warning mechanisms, making it difficult to accurately identify and timely intervene in the human aging process. Summary of the invention

[0004] The present invention provides a method and system for dynamic identification and early warning of human aging data to solve the above problems:

[0005] The present invention proposes a method and system for dynamic identification and early warning of human aging data, the method comprising:

[0006] S1. Obtain historical biometric data of the user, divide the historical biometric data according to a preset life monitoring period, and obtain periodic biometric data;

[0007] S2. Generate a periodic biological aging portrait based on the periodic biological characteristic data, calculate the periodic biological aging age coefficient, perform periodic comparison and comprehensive comparison of the aging age coefficient, and then perform periodic aging determination and user aging determination;

[0008] S3. Calculate the aging dynamic factor of each cycle according to the judgment information, and then judge the aging process, obtain the periodic aging node, obtain the periodic interval data of the aging node, set the weight according to the periodic interval data and issue an early warning.

[0009] Furthermore, the S1 includes:

[0010] Acquire the user's historical medical information, pre-process the user's historical medical information, and obtain the pre-processed user's historical medical information;

[0011] Extracting biometric data from the user's historical medical information to obtain historical biometric data;

[0012] Obtaining a preset life monitoring period, dividing the historical biometric data according to the preset life cycle, and obtaining periodic biometric data;

[0013] According to the preset life cycle and periodic biometric data, the idle life cycle and newly added feature data are obtained.

[0014] Further, the S2 includes:

[0015] Obtaining biometric data of each cycle, and generating a biological aging portrait of each cycle based on the biometric data of each cycle;

[0016] Calculate the periodic biological aging age coefficient based on the periodic characteristic data of the periodic biological aging portrait;

[0017] Calculate the average value of the periodic biological aging age coefficients of all periods of the user to obtain the user's comprehensive aging age coefficient;

[0018] Comparing the biological aging age coefficient of each cycle with the comprehensive aging age coefficient of the user to obtain a cycle comparison result;

[0019] Performing cycle aging determination on each cycle characteristic data according to the cycle comparison result to obtain a cycle aging determination result;

[0020] Compare the user's comprehensive aging age coefficient with the average aging age coefficient of all users to obtain a user comparison result;

[0021] Perform user aging determination on each user according to the user comparison result to obtain a user aging determination result.

[0022] Further, the S3 includes:

[0023] Acquire periodic aging determination information and user aging determination information, and calculate the aging dynamic factor of each period according to the periodic aging determination information combined with the user aging determination information;

[0024] Comparing the aging dynamic factor with a preset factor threshold to obtain a factor comparison result;

[0025] Determine the aging process change of the user according to the factor comparison result to obtain the process change determination result;

[0026] According to the process change determination result, the preset life cycle is marked with aging nodes to obtain a periodic aging node.

[0027] Furthermore, the S3 further includes:

[0028] Obtaining periodic aging nodes in a preset life cycle, and obtaining period interval data of each periodic aging node in the preset life cycle;

[0029] According to the periodic interval data, the periodic aging nodes are sorted from the smallest arrival to obtain the aging sorted nodes; and the weights of the aging sorted nodes are set to be correspondingly sorted according to the sorting information;

[0030] According to the weight data, graded warning is carried out for the periodic aging nodes to obtain graded warning information.

[0031] Furthermore, the system comprises:

[0032] A period division module is used to obtain historical biometric data of the user, divide the historical biometric data according to a preset life monitoring period, and obtain periodic biometric data;

[0033] An aging determination module, used to generate a periodic biological aging portrait according to the periodic biological characteristic data, calculate the periodic biological aging age coefficient, perform periodic comparison and comprehensive comparison of the aging age coefficient, and then perform periodic aging determination and user aging determination;

[0034] The aging dynamic warning module is used to calculate the aging dynamic factor of each cycle based on the judgment information, and then judge the aging process, obtain the periodic aging node, obtain the periodic interval data of the aging node, set the weight according to the periodic interval data and issue a warning.

[0035] Furthermore, the cycle division module includes:

[0036] An information acquisition module is used to acquire the user's historical medical information, pre-process the user's historical medical information, and obtain the pre-processed user's historical medical information;

[0037] A feature extraction module, used to extract biometric data from the user's historical medical information to obtain historical biometric data;

[0038] A data partitioning module, used to obtain a preset life monitoring period, divide the historical biometric data according to the preset life cycle, and obtain periodic biometric data;

[0039] The cycle classification module is used to obtain the idle life cycle and newly added feature data according to the preset life cycle and periodic biometric feature data.

[0040] Furthermore, the aging determination module includes:

[0041] A portrait generation module, used to obtain biometric data of each cycle, and generate a biological aging portrait of each cycle according to the biometric data of each cycle;

[0042] A cycle calculation module, used to calculate the cycle biological aging age coefficient according to the cycle characteristic data of the cycle biological aging portrait;

[0043] A comprehensive calculation module, used to calculate the average value of the periodic biological aging age coefficients of all periods of the user to obtain the user's comprehensive aging age coefficient;

[0044] A cycle comparison module, used to compare the biological aging age coefficient of each cycle with the user's comprehensive aging age coefficient to obtain a cycle comparison result;

[0045] A cycle determination module, used for performing cycle aging determination on each cycle characteristic data according to the cycle comparison result to obtain a cycle aging determination result;

[0046] A user comparison module is used to compare the user's comprehensive aging age coefficient with the average aging age coefficient of all users to obtain a user comparison result;

[0047] The user determination module is used to perform user aging determination on each user according to the user comparison result to obtain a user aging determination result.

[0048] Furthermore, the aging dynamic early warning module includes:

[0049] A dynamic calculation module, used to obtain periodic aging determination information and user aging determination information, and calculate the aging dynamic factor of each period according to the periodic aging determination information combined with the user aging determination information;

[0050] A dynamic determination module, used to compare the aging dynamic factor with a preset factor threshold to obtain a factor comparison result;

[0051] Determine the aging process change of the user according to the factor comparison result to obtain the process change determination result;

[0052] The node marking module is used to mark the aging nodes of the preset life cycle according to the process change determination result to obtain the periodic aging nodes.

[0053] Furthermore, the aging dynamic early warning module also includes:

[0054] An interval data acquisition module, used to acquire periodic aging nodes in a preset life cycle, and to acquire periodic interval data of each periodic aging node in the preset life cycle;

[0055] A node sorting module, used for sorting the periodic aging nodes from the smallest arrival according to the periodic interval data, to obtain aging sorted nodes;

[0056] A hierarchical warning module is used to set the weights of the corresponding rankings of aging ranking nodes according to the ranking information;

[0057] According to the weight data, graded warning is carried out for the periodic aging nodes to obtain graded warning information.

[0058] Beneficial effects of the present invention: Through dynamic analysis of historical biometric data of users, the system can provide personalized aging monitoring and early warning services to help users understand their aging status and progress in a timely manner. By identifying aging nodes and periodic interval data, the system can accurately predict the user's aging trend, changes in aging speed and key nodes of aging, and provide users with scientific health intervention suggestions to delay the aging process. The method and system help users establish a scientific health management system, and through continuous monitoring and early warning, guide users to adopt positive health behaviors and improve their quality of life. The biometric data and aging analysis results of a large number of users can provide valuable data support for health science research and help formulate more scientific and reasonable health policies and intervention measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of a method for dynamic identification and early warning of human aging data;

[0060] Figure 2 Schematic diagram of various organs / parts of the human body. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0062] In one embodiment of the present invention, a method and system for dynamic identification and early warning of human aging data are proposed, and the method comprises:

[0063] S1. Obtain historical biometric data of the user, divide the historical biometric data according to a preset life monitoring period, and obtain periodic biometric data;

[0064] S2. Generate a periodic biological aging portrait based on the periodic biological characteristic data, calculate the periodic biological aging age coefficient, perform periodic comparison and comprehensive comparison of the aging age coefficient, and then perform periodic aging determination and user aging determination;

[0065] S3, calculate the aging dynamic factor of each cycle according to the judgment information, and then judge the aging process, obtain the periodic aging node, obtain the periodic interval data of the aging node, set the weight according to the periodic interval data and issue an early warning, such as Figure 1 shown.

[0066] The working principle of the above technical solution is as follows: the system obtains the user's historical biometric data through various biosensors (such as heart rate monitors, skin elasticity testers, bone density scanners or physical examination instruments, etc.). According to the preset life monitoring cycle (such as annually, quarterly or monthly), the system divides these historical data into multiple periodic biometric data sets. The data of each period reflects the changes in the user's biological state during the time period. The period is each stage of the life detection cycle; for the biometric data of each period, the system generates a periodic biological aging portrait. These portraits show the aging state of the user in a specific period in a visual or numerical way. The periodic biological aging age coefficient is calculated, which is obtained by comparing the user's actual age with the "biological age" of each period reflected by the biometrics, and is used to quantify the user's aging degree. The system performs periodic comparison (i.e. comparison between adjacent periods) and comprehensive comparison (comparison of all periods with benchmarks or standard values) of the aging age coefficient to perform periodic aging judgment and overall aging judgment of the user. Based on the periodic aging judgment results, the system calculates the aging dynamic factors of each period. These factors reflect the aging speed, trend or rate of change of specific biometrics. By analyzing the dynamic factors of aging, the system can determine the user's aging process and identify key periodic aging nodes, that is, time points when the aging rate changes significantly or reaches a certain threshold. Obtain the periodic interval data of the aging nodes, which reveal the changing pattern of the user's aging rate. Based on the periodic interval data, the system sets personalized early warning weights for each user. Cycles with higher weights mean faster aging or more significant changes, so more frequent monitoring and earlier early warnings are required. The system sets corresponding early warning mechanisms based on these weights, such as sending reminder messages, adjusting monitoring frequency, or suggesting that users take health intervention measures.

[0067] The technical effect of the above technical solution is: through dynamic analysis of the user's historical biometric data, the system can provide personalized aging monitoring and early warning services to help users understand their aging status and progress in a timely manner. By identifying aging nodes and periodic interval data, the system can accurately predict the user's aging trend, changes in aging speed and key nodes of aging, and provide users with scientific health intervention suggestions to delay the aging process. The method and system help users establish a scientific health management system, and through continuous monitoring and early warning, guide users to take positive health behaviors and improve their quality of life. The biometric data and aging analysis results of a large number of users can provide valuable data support for health science research and help formulate more scientific and reasonable health policies and intervention measures.

[0068] In one embodiment of the present invention, the S1 includes:

[0069] Acquire the user's historical medical information, pre-process the user's historical medical information, and obtain the pre-processed user's historical medical information;

[0070] Extracting biometric data from the user's historical medical information to obtain historical biometric data;

[0071] Obtaining a preset life monitoring period, dividing the historical biometric data according to the preset life cycle, and obtaining periodic biometric data;

[0072] According to the preset life cycle and periodic biometric data, an idle life cycle and newly added characteristic data are obtained. The idle life cycle is a life cycle that has not been experienced, and the newly added characteristic data is a dynamic variable of the characteristic data of the life cycle that is being experienced.

[0073] The working principle of the above technical solution is as follows: the system first obtains the user's historical medical information through a medical database, an electronic medical record system or a user-authorized method. This information includes but is not limited to diagnosis records, examination reports, treatment plans, medication history, etc. The obtained historical medical information is preprocessed, including data cleaning (removing duplicate, erroneous or irrelevant information), data formatting (unifying data formats and standards) and data integration (integrating scattered information into structured data) to obtain the preprocessed user's historical medical information. From the preprocessed user's historical medical information, the system uses natural language processing (NLP), machine learning or rule engines and other technologies to extract data related to biometrics. These data may include but are not limited to biological indicators such as heart rate, blood pressure, blood sugar level, bone density, skin condition, and related disease diagnosis, treatment response and other information. The extracted biometric data constitutes a historical biometric data set, which provides a basis for subsequent analysis. The system divides the historical biometric data according to a preset life monitoring cycle (such as annually, quarterly, monthly, or a custom cycle based on factors such as the user's age and health status). The data in each cycle reflects the changes in the user's biological state during that time period. Through the division, the system obtains periodic biometric data, which are arranged in chronological order to facilitate subsequent period comparison and trend analysis. Within the preset life monitoring cycle, there may be life cycles that the user has not yet experienced (idle life cycles), and these cycles have no corresponding records in the user's historical data. As the user ages and changes in health status, new biometric data (newly added feature data) will continue to appear. These newly added feature data reflect the dynamic changes in the user's current life cycle. The system identifies idle life cycles and newly added feature data by comparing the coverage of the preset life cycle with the user's historical biometric data. The identification of idle life cycles helps the system predict the health risks that users may face in the future; and the identification of newly added feature data helps the system to adjust monitoring strategies and early warning mechanisms in a timely manner.

[0074] The technical effect of the above technical solution is: by extracting and analyzing the biometric data in the user's historical medical information, the system can more accurately monitor the user's health status and aging process. According to the user's actual life cycle and changes in biometric data, the system can provide users with personalized health management advice and services to meet the health needs of users at different stages. By identifying idle life cycles and newly added feature data, the system can predict in advance the health risks that users may face in the future and take corresponding preventive measures. Based on the analysis of users' historical medical information and biometric data, medical institutions can allocate medical resources more reasonably and improve the efficiency and quality of medical services. The biometric data and health monitoring results of a large number of users can provide rich data support for health science research, and help formulate more scientific and reasonable health policies and intervention measures.

[0075] In one embodiment of the present invention, S2 includes:

[0076] Obtain biometric data for each cycle, and generate a biological aging portrait for each cycle based on the biometric data for each cycle; the biological aging portrait includes the age of each organ / part of the human body (such as Figure 2 Various types of periodic characteristic data (as shown), including gene data, health index and preset disease weights of diseases, etc., are visualized through digital charts;

[0077] Calculate the periodic biological aging age coefficient based on the periodic characteristic data of the periodic biological aging portrait;

[0078] The calculation formula of the periodic biological aging age coefficient is:

[0079]

[0080] Among them, Z sl is the periodic biological aging age coefficient of the cycle, N sj is the actual age data of the period, E is the total number of types of biometric data of the biological aging portrait of the period, T si is the biometric data of the i-th biometric data type in the period, Y si is the characteristic data threshold of the i-th biometric data type in the cycle, Z is the total number of cycles in the preset life cycle, N sd is the actual age data of the dth period, T di is the biometric data of the ith biometric data type in the dth period, Y di is the preset data of the biometric data of the ith biometric data type in the dth period, α is the time decay factor of the period, r d is the time decay factor of the dth period;

[0081] Calculate the average value of the periodic biological aging age coefficients of all periods of the user to obtain the user's comprehensive aging age coefficient;

[0082] Comparing the biological aging age coefficient of each cycle with the comprehensive aging age coefficient of the user to obtain a cycle comparison result;

[0083] Performing cycle aging determination on each cycle characteristic data according to the cycle comparison result to obtain a cycle aging determination result;

[0084] When the periodic biological aging age coefficient is greater than the user's comprehensive aging age coefficient, the periodic characteristic data is determined as an aging period, otherwise it is determined as a non-aging period (a relatively qualified determination);

[0085] Compare the user's comprehensive aging age coefficient with the average aging age coefficient of all users to obtain a user comparison result;

[0086] Perform user aging determination on each user according to the user comparison result to obtain a user aging determination result.

[0087] When the user's comprehensive aging age coefficient is greater than the average aging age coefficient of all users, the user is determined to be an aging user, otherwise it is determined to be a non-aging user.

[0088] The working principle of the above technical solution is as follows: the system first obtains the biometric data of each cycle, which covers various types of organs / parts of the human body. For each cycle, the system uses this data to generate a cycle biological aging portrait. The portrait is presented in the form of a digital chart, which intuitively reflects the dynamic changes of the user's biometric characteristics during the cycle. Based on the cycle characteristic data in the cycle biological aging portrait, the system calculates the cycle biological aging age coefficient (Z sl ). This coefficient takes into account multiple factors such as the actual age of the period, the type of biometric data, the specific value of each feature data and its threshold, the total number of periods in the preset life cycle, and the time decay factor. The time decay factor (α and r d ) is used to adjust the impact of data from different time periods on the current aging assessment to ensure that the assessment results are more accurate and in line with the actual situation. The system calculates the average of the biological aging age coefficients of all periods to obtain the user's comprehensive aging age coefficient. This coefficient is a comprehensive assessment of the user's overall aging level. The periodic biological aging age coefficient of each period is compared with the user's comprehensive aging age coefficient to determine whether the period is an aging period or a non-aging period. This helps to identify the aging speed and trend of users in different time periods. Compare the user's comprehensive aging age coefficient with the average aging age coefficient of all users to determine whether the user belongs to the aging user group. This comparison provides the user's relative aging position in the entire user group.

[0089] The technical effect of the above technical solution is: by integrating multiple biometric data and complex computational models, the system can accurately evaluate the user's aging status, including the overall aging level and aging changes in each time period. Based on the periodic biological aging portrait and aging determination results, the system can provide users with personalized health advice and management plans to help users delay the aging process or improve their health. By continuously monitoring and evaluating the user's aging status, the system can scientifically guide the user's health management behavior, including diet, exercise, disease prevention and other aspects. For medical institutions, the aging assessment results provided by the system can serve as an important reference for medical decision-making, helping doctors to develop more accurate treatment plans and preventive measures. The aging assessment data of a large number of users provides valuable resources for health science research, helps to reveal the biological mechanisms and influencing factors of aging, and provides a scientific basis for relevant policy formulation.

[0090] In one embodiment of the present invention, S3 includes:

[0091] Acquire periodic aging determination information and user aging determination information, and calculate the aging dynamic factor of each period according to the periodic aging determination information combined with the user aging determination information;

[0092] The calculation formula of the aging dynamic factor is:

[0093]

[0094] Among them, D sl is the aging dynamic factor of the cycle, F qb To preset the dynamic factors of aging, I k is the periodic biological aging age coefficient of the cycle, I k-1 is the biological aging age coefficient of the k-1th cycle (calculation cycle - 1 cycle), I d is the biological aging age coefficient of the dth cycle, I d-1 is the periodic biological aging age coefficient of the d-1th period;

[0095] Comparing the aging dynamic factor with a preset factor threshold to obtain a factor comparison result;

[0096] Determine the aging process change of the user according to the factor comparison result to obtain the process change determination result;

[0097] When the aging dynamic factor is greater than the preset factor threshold, the aging process is determined to be abnormal, otherwise the aging process is determined to be normal.

[0098] According to the process change determination result, the preset life cycle is marked with aging nodes to obtain a periodic aging node.

[0099] When the aging dynamic factor is greater than a preset factor threshold, the aging node of the corresponding period is marked to obtain the periodic aging node of the corresponding period.

[0100] The working principle of the above technical solution is as follows: the system first obtains the periodic aging determination information and the user aging determination information. This information is obtained based on the periodic biological aging age coefficient and the user comprehensive aging age coefficient calculated in the previous step. The system calculates the aging dynamic factor (D sl ). This formula takes into account the cyclical biological aging age coefficient (I k ), the biological aging age coefficient of the previous cycle (I k-1 ), and the cyclic biological aging age coefficient of any two adjacent cycles in all cycles (such as I d and I d-1 ) and introduces a preset aging dynamic factor (F qb ) as a benchmark. In this way, the system is able to quantify the degree of change in the user's aging speed in each cycle, namely the aging dynamic factor. The system compares the calculated aging dynamic factor with the preset factor threshold. This threshold is derived from a large amount of statistical analysis of user data and is used to distinguish between normal and abnormal changes in the aging process. Based on the comparison results, the system determines the changes in the user's aging process. If the aging dynamic factor is greater than the preset factor threshold, the aging process is judged to be abnormal, which may mean that the user has experienced significant accelerated aging or deterioration of health during the cycle; otherwise, the aging process is judged to be normal. Based on the process change judgment results, the system marks the aging nodes for specific cycles in the preset life cycle. These nodes represent key time points or turning points in the user's aging process. In particular, when the aging dynamic factor is greater than the preset factor threshold, the system will mark the corresponding cycles with aging nodes to highlight the significant changes in the user's aging process during these cycles.

[0101] The technical effect of the above technical solution is: by calculating the aging dynamic factor and comparing it with the preset threshold, the system can accurately monitor the changes in the user's aging process and promptly discover abnormal aging trends. For periods of abnormal changes in the aging process, the system can automatically issue a warning signal and provide users with corresponding health intervention suggestions to help users slow down the aging process or improve their health. Based on the results of aging node annotation, the system can provide users with more personalized health management plans and formulate corresponding health plans based on the aging characteristics of users at different stages of the life cycle. The aging dynamic factor data and aging node annotation results of a large number of users can provide valuable data support for health science research and help reveal the biological mechanisms and influencing factors of aging. By accurately monitoring the user's aging process and providing early warning and intervention suggestions, the system can help medical institutions allocate medical resources more reasonably and improve the efficiency and quality of medical services.

[0102] In one embodiment of the present invention, the S3 further includes:

[0103] Obtain the periodic aging nodes in a preset life cycle, and obtain the periodic interval data of each periodic aging node in the preset life cycle; the interval data includes the interval duration of the node in the cycle.

[0104] According to the periodic interval data, the periodic aging nodes are sorted from the smallest arrival to obtain the aging sorted nodes; the nodes with the smallest interval are sorted first.

[0105] According to the sorting information, the weights of the aging sorting nodes are set accordingly;

[0106] According to the weight data, graded warning is carried out for the periodic aging nodes to obtain graded warning information.

[0107] The working principle of the above technical solution is as follows: the system first obtains all time points marked as periodic aging nodes in the preset life cycle. These nodes represent significant changes or turning points in the user's aging process. The system calculates the periodic interval data of each periodic aging node in the preset life cycle. These interval data refer to the length of time between two adjacent aging nodes, reflecting the speed changes of the aging process at different stages. According to the periodic interval data, the system sorts the periodic aging nodes from small to large. The basis for sorting is the interval length between nodes, and the nodes with the smallest interval are ranked in front, indicating that the aging speed is faster or the changes are more significant at this stage. The sorted node list is called the aging sorting node, and they are arranged in order according to the speed of aging. According to the sorting information, the system sets a corresponding weight for each aging sorting node. The size of the weight reflects the importance or urgency of the node in the aging process. Generally, the smaller the interval, the higher the weight of the node. With the weight data, the system can perform graded warnings on periodic aging nodes. According to different weights, the system divides the nodes into different warning levels, such as high, medium, and low. Each level corresponds to different warning information and intervention measures.

[0108] The technical effect of the above technical solution is that by sorting and weighting the periodic aging nodes, the system can more accurately identify the key stages and potential risk points in the user's aging process, thereby improving the accuracy and timeliness of the early warning. Based on the sorting and hierarchical early warning mechanism, the system can provide users with personalized early warning services. Different users may receive different early warning information and intervention suggestions due to differences in their aging process and health status, thereby meeting their personalized health management needs. The hierarchical early warning mechanism helps medical institutions and health management agencies optimize resource allocation. For users or nodes with higher warning levels, more medical resources and attention can be invested first to improve the intervention effect and patient satisfaction. Through the transmission of hierarchical early warning information, the system can enhance the user's health awareness and encourage users to pay more attention to their health status and aging process. This helps users take active health management measures, slow down the aging process and improve the quality of life. Periodic aging nodes and hierarchical early warning data provide rich materials for health science research. Researchers can use these data to explore the biological mechanisms of aging, influencing factors, and the effectiveness of intervention strategies, and provide a scientific basis for the formulation of more scientific and reasonable health policies and intervention measures.

[0109] In one embodiment of the present invention, the system comprises:

[0110] A period division module is used to obtain historical biometric data of the user, divide the historical biometric data according to a preset life monitoring period, and obtain periodic biometric data;

[0111] An aging determination module, used to generate a periodic biological aging portrait according to the periodic biological characteristic data, calculate the periodic biological aging age coefficient, perform periodic comparison and comprehensive comparison of the aging age coefficient, and then perform periodic aging determination and user aging determination;

[0112] The aging dynamic warning module is used to calculate the aging dynamic factor of each cycle based on the judgment information, and then judge the aging process, obtain the periodic aging node, obtain the periodic interval data of the aging node, set the weight according to the periodic interval data and issue a warning.

[0113] The working principle of the above technical solution is as follows: the system obtains the user's historical biometric data through various biosensors (such as heart rate monitors, skin elasticity testers, bone density scanners or physical examination instruments, etc.). According to the preset life monitoring cycle (such as annually, quarterly or monthly), the system divides these historical data into multiple periodic biometric data sets. The data of each period reflects the changes in the user's biological state during the time period. The period is each stage of the life detection cycle; for the biometric data of each period, the system generates a periodic biological aging portrait. These portraits show the aging state of the user in a specific period in a visual or numerical way. The periodic biological aging age coefficient is calculated, which is obtained by comparing the user's actual age with the "biological age" of each period reflected by the biometrics, and is used to quantify the user's aging degree. The system performs periodic comparison (i.e. comparison between adjacent periods) and comprehensive comparison (comparison of all periods with benchmarks or standard values) of the aging age coefficient to perform periodic aging judgment and overall aging judgment of the user. Based on the periodic aging judgment results, the system calculates the aging dynamic factors of each period. These factors reflect the aging speed, trend or rate of change of specific biometrics. By analyzing the dynamic factors of aging, the system can determine the user's aging process and identify key periodic aging nodes, that is, time points when the aging rate changes significantly or reaches a certain threshold. Obtain the periodic interval data of the aging nodes, which reveal the changing pattern of the user's aging rate. Based on the periodic interval data, the system sets personalized early warning weights for each user. Cycles with higher weights mean faster aging or more significant changes, so more frequent monitoring and earlier early warnings are required. The system sets corresponding early warning mechanisms based on these weights, such as sending reminder messages, adjusting monitoring frequency, or suggesting that users take health intervention measures.

[0114] The technical effect of the above technical solution is: through dynamic analysis of the user's historical biometric data, the system can provide personalized aging monitoring and early warning services to help users understand their aging status and progress in a timely manner. By identifying aging nodes and periodic interval data, the system can accurately predict the user's aging trend, changes in aging speed and key nodes of aging, and provide users with scientific health intervention suggestions to delay the aging process. The method and system help users establish a scientific health management system, and through continuous monitoring and early warning, guide users to take positive health behaviors and improve their quality of life. The biometric data and aging analysis results of a large number of users can provide valuable data support for health science research and help formulate more scientific and reasonable health policies and intervention measures.

[0115] In one embodiment of the present invention, the period division module includes:

[0116] An information acquisition module is used to acquire the user's historical medical information, pre-process the user's historical medical information, and obtain the pre-processed user's historical medical information;

[0117] A feature extraction module, used to extract biometric data from the user's historical medical information to obtain historical biometric data;

[0118] A data partitioning module, used to obtain a preset life monitoring period, divide the historical biometric data according to the preset life cycle, and obtain periodic biometric data;

[0119] The cycle classification module is used to obtain an idle life cycle and newly added characteristic data according to the preset life cycle and the periodic biometric characteristic data. The idle life cycle is a life cycle that has not been experienced, and the newly added characteristic data is a dynamic variable of the characteristic data of the life cycle that is being experienced.

[0120] The working principle of the above technical solution is as follows: the system first obtains the user's historical medical information through a medical database, an electronic medical record system or a user-authorized method. This information includes but is not limited to diagnosis records, examination reports, treatment plans, medication history, etc. The obtained historical medical information is preprocessed, including data cleaning (removing duplicate, erroneous or irrelevant information), data formatting (unifying data formats and standards) and data integration (integrating scattered information into structured data) to obtain the preprocessed user's historical medical information. From the preprocessed user's historical medical information, the system uses natural language processing (NLP), machine learning or rule engines and other technologies to extract data related to biometrics. These data may include but are not limited to biological indicators such as heart rate, blood pressure, blood sugar level, bone density, skin condition, and related disease diagnosis, treatment response and other information. The extracted biometric data constitutes a historical biometric data set, which provides a basis for subsequent analysis. The system divides the historical biometric data according to a preset life monitoring cycle (such as annually, quarterly, monthly, or a custom cycle based on factors such as the user's age and health status). The data in each cycle reflects the changes in the user's biological state during that time period. Through the division, the system obtains periodic biometric data, which are arranged in chronological order to facilitate subsequent period comparison and trend analysis. Within the preset life monitoring cycle, there may be life cycles that the user has not yet experienced (idle life cycles), and these cycles have no corresponding records in the user's historical data. As the user ages and changes in health status, new biometric data (newly added feature data) will continue to appear. These newly added feature data reflect the dynamic changes in the user's current life cycle. The system identifies idle life cycles and newly added feature data by comparing the coverage of the preset life cycle with the user's historical biometric data. The identification of idle life cycles helps the system predict the health risks that users may face in the future; and the identification of newly added feature data helps the system to adjust monitoring strategies and early warning mechanisms in a timely manner.

[0121] The technical effect of the above technical solution is: by extracting and analyzing the biometric data in the user's historical medical information, the system can more accurately monitor the user's health status and aging process. According to the user's actual life cycle and changes in biometric data, the system can provide users with personalized health management advice and services to meet the health needs of users at different stages. By identifying idle life cycles and newly added feature data, the system can predict in advance the health risks that users may face in the future and take corresponding preventive measures. Based on the analysis of users' historical medical information and biometric data, medical institutions can allocate medical resources more reasonably and improve the efficiency and quality of medical services. The biometric data and health monitoring results of a large number of users can provide rich data support for health science research, and help formulate more scientific and reasonable health policies and intervention measures.

[0122] In one embodiment of the present invention, the aging determination module includes:

[0123] A portrait generation module is used to obtain the biometric data of each cycle, and generate a periodic biological aging portrait of each cycle according to the biometric data of each cycle; the periodic biological aging portrait includes various types of periodic characteristic data of various organs / parts of the human body within the same stage of the time period, and the types include genetic data, health index and preset disease weights of diseases, etc., which are visualized through digital charts;

[0124] A cycle calculation module, used to calculate the cycle biological aging age coefficient according to the cycle characteristic data of the cycle biological aging portrait;

[0125] The calculation formula of the periodic biological aging age coefficient is:

[0126]

[0127] Among them, Z sl is the periodic biological aging age coefficient of the cycle, N sj is the actual age data of the period, E is the total number of types of biometric data of the biological aging portrait of the period, T si is the biometric data of the i-th biometric data type in the period, Y si is the characteristic data threshold of the i-th biometric data type in the cycle, Z is the total number of cycles in the preset life cycle, N sd is the actual age data of the dth period, T di is the biometric data of the ith biometric data type in the dth period, Y di is the preset data of the biometric data of the ith biometric data type in the dth period, α is the time decay factor of the period, r d is the time decay factor of the dth period;

[0128] A comprehensive calculation module, used to calculate the average value of the periodic biological aging age coefficients of all periods of the user to obtain the user's comprehensive aging age coefficient;

[0129] A cycle comparison module, used to compare the biological aging age coefficient of each cycle with the user's comprehensive aging age coefficient to obtain a cycle comparison result;

[0130] A cycle determination module, used for performing cycle aging determination on each cycle characteristic data according to the cycle comparison result to obtain a cycle aging determination result;

[0131] When the periodic biological aging age coefficient is greater than the user's comprehensive aging age coefficient, the periodic characteristic data is determined as an aging period, otherwise it is determined as a non-aging period (a relatively qualified determination);

[0132] A user comparison module is used to compare the user's comprehensive aging age coefficient with the average aging age coefficient of all users to obtain a user comparison result;

[0133] The user determination module is used to perform user aging determination on each user according to the user comparison result to obtain a user aging determination result.

[0134] When the user's comprehensive aging age coefficient is greater than the average aging age coefficient of all users, the user is determined to be an aging user, otherwise it is determined to be a non-aging user.

[0135] The working principle of the above technical solution is as follows: the system first obtains the biometric data of each cycle, which covers various types of organs / parts of the human body. For each cycle, the system uses this data to generate a cycle biological aging portrait. The portrait is presented in the form of a digital chart, which intuitively reflects the dynamic changes of the user's biometric characteristics during the cycle. Based on the cycle characteristic data in the cycle biological aging portrait, the system calculates the cycle biological aging age coefficient (Z sl ). This coefficient takes into account multiple factors such as the actual age of the period, the type of biometric data, the specific value of each feature data and its threshold, the total number of periods in the preset life cycle, and the time decay factor. The time decay factor (α and r d ) is used to adjust the impact of data from different time periods on the current aging assessment to ensure that the assessment results are more accurate and in line with the actual situation. The system calculates the average of the biological aging age coefficients of all periods to obtain the user's comprehensive aging age coefficient. This coefficient is a comprehensive assessment of the user's overall aging level. The periodic biological aging age coefficient of each period is compared with the user's comprehensive aging age coefficient to determine whether the period is an aging period or a non-aging period. This helps to identify the aging speed and trend of users in different time periods. Compare the user's comprehensive aging age coefficient with the average aging age coefficient of all users to determine whether the user belongs to the aging user group. This comparison provides the user's relative aging position in the entire user group.

[0136] The technical effect of the above technical solution is: by integrating multiple biometric data and complex computational models, the system can accurately evaluate the user's aging status, including the overall aging level and aging changes in each time period. Based on the periodic biological aging portrait and aging determination results, the system can provide users with personalized health advice and management plans to help users delay the aging process or improve their health. By continuously monitoring and evaluating the user's aging status, the system can scientifically guide the user's health management behavior, including diet, exercise, disease prevention and other aspects. For medical institutions, the aging assessment results provided by the system can serve as an important reference for medical decision-making, helping doctors to develop more accurate treatment plans and preventive measures. The aging assessment data of a large number of users provides valuable resources for health science research, helps to reveal the biological mechanisms and influencing factors of aging, and provides a scientific basis for relevant policy formulation.

[0137] In one embodiment of the present invention, the aging dynamic early warning module includes:

[0138] A dynamic calculation module, used to obtain periodic aging determination information and user aging determination information, and calculate the aging dynamic factor of each period according to the periodic aging determination information combined with the user aging determination information;

[0139] The calculation formula of the aging dynamic factor is:

[0140]

[0141] Among them, D sl is the aging dynamic factor of the cycle, F qb To preset the dynamic factors of aging, I k is the periodic biological aging age coefficient of the cycle, I k-1 is the biological aging age coefficient of the k-1th cycle (calculation cycle - 1 cycle), I d is the biological aging age coefficient of the dth cycle, I d-1 is the periodic biological aging age coefficient of the d-1th period;

[0142] A dynamic determination module, used to compare the aging dynamic factor with a preset factor threshold to obtain a factor comparison result;

[0143] Determine the aging process change of the user according to the factor comparison result to obtain the process change determination result;

[0144] When the aging dynamic factor is greater than the preset factor threshold, the aging process is determined to be abnormal, otherwise the aging process is determined to be normal.

[0145] The node marking module is used to mark the aging nodes of the preset life cycle according to the process change determination result to obtain the periodic aging nodes.

[0146] When the aging dynamic factor is greater than a preset factor threshold, the aging node of the corresponding period is marked to obtain the periodic aging node of the corresponding period.

[0147] The working principle of the above technical solution is as follows: the system first obtains the periodic aging determination information and the user aging determination information. This information is obtained based on the periodic biological aging age coefficient and the user comprehensive aging age coefficient calculated in the previous step. The system calculates the aging dynamic factor (D sl ). This formula takes into account the cyclical biological aging age coefficient (I k ), the biological aging age coefficient of the previous cycle (I k-1 ), and the cyclic biological aging age coefficient of any two adjacent cycles in all cycles (such as I d and I d-1 ) and introduces a preset aging dynamic factor (F qb ) as a benchmark. In this way, the system is able to quantify the degree of change in the user's aging speed in each cycle, namely the aging dynamic factor. The system compares the calculated aging dynamic factor with the preset factor threshold. This threshold is derived from a large amount of statistical analysis of user data and is used to distinguish between normal and abnormal changes in the aging process. Based on the comparison results, the system determines the changes in the user's aging process. If the aging dynamic factor is greater than the preset factor threshold, the aging process is judged to be abnormal, which may mean that the user has experienced significant accelerated aging or deterioration of health during the cycle; otherwise, the aging process is judged to be normal. Based on the process change judgment results, the system marks the aging nodes for specific cycles in the preset life cycle. These nodes represent key time points or turning points in the user's aging process. In particular, when the aging dynamic factor is greater than the preset factor threshold, the system will mark the corresponding cycles with aging nodes to highlight the significant changes in the user's aging process during these cycles.

[0148] The technical effect of the above technical solution is: by calculating the aging dynamic factor and comparing it with the preset threshold, the system can accurately monitor the changes in the user's aging process and promptly discover abnormal aging trends. For periods of abnormal changes in the aging process, the system can automatically issue a warning signal and provide users with corresponding health intervention suggestions to help users slow down the aging process or improve their health. Based on the results of aging node annotation, the system can provide users with more personalized health management plans and formulate corresponding health plans based on the aging characteristics of users at different stages of the life cycle. The aging dynamic factor data and aging node annotation results of a large number of users can provide valuable data support for health science research and help reveal the biological mechanisms and influencing factors of aging. By accurately monitoring the user's aging process and providing early warning and intervention suggestions, the system can help medical institutions allocate medical resources more reasonably and improve the efficiency and quality of medical services.

[0149] In one embodiment of the present invention, the aging dynamic early warning module further includes:

[0150] The interval data acquisition module is used to acquire the periodic aging nodes in the preset life cycle, and acquire the periodic interval data of each periodic aging node in the preset life cycle; the interval data includes the interval duration of the node in the cycle.

[0151] The node sorting module is used to sort the periodic aging nodes from the smallest arrival according to the periodic interval data to obtain the aging sorted nodes; the nodes with the smallest interval are sorted first.

[0152] A hierarchical warning module is used to set the weights of the corresponding rankings of aging ranking nodes according to the ranking information;

[0153] According to the weight data, graded warning is carried out for the periodic aging nodes to obtain graded warning information.

[0154] The working principle of the above technical solution is as follows: the system first obtains all time points marked as periodic aging nodes in the preset life cycle. These nodes represent significant changes or turning points in the user's aging process. The system calculates the periodic interval data of each periodic aging node in the preset life cycle. These interval data refer to the length of time between two adjacent aging nodes, reflecting the speed changes of the aging process at different stages. According to the periodic interval data, the system sorts the periodic aging nodes from small to large. The basis for sorting is the interval length between nodes, and the nodes with the smallest interval are ranked in front, indicating that the aging speed is faster or the changes are more significant at this stage. The sorted node list is called the aging sorting node, and they are arranged in order according to the speed of aging. According to the sorting information, the system sets a corresponding weight for each aging sorting node. The size of the weight reflects the importance or urgency of the node in the aging process. Generally, the smaller the interval, the higher the weight of the node. With the weight data, the system can perform graded warnings on periodic aging nodes. According to different weights, the system divides the nodes into different warning levels, such as high, medium, and low. Each level corresponds to different warning information and intervention measures.

[0155] The technical effect of the above technical solution is that by sorting and weighting the periodic aging nodes, the system can more accurately identify the key stages and potential risk points in the user's aging process, thereby improving the accuracy and timeliness of the early warning. Based on the sorting and hierarchical early warning mechanism, the system can provide users with personalized early warning services. Different users may receive different early warning information and intervention suggestions due to differences in their aging process and health status, thereby meeting their personalized health management needs. The hierarchical early warning mechanism helps medical institutions and health management agencies optimize resource allocation. For users or nodes with higher warning levels, more medical resources and attention can be invested first to improve the intervention effect and patient satisfaction. Through the transmission of hierarchical early warning information, the system can enhance the user's health awareness and encourage users to pay more attention to their health status and aging process. This helps users take active health management measures, slow down the aging process and improve the quality of life. Periodic aging nodes and hierarchical early warning data provide rich materials for health science research. Researchers can use these data to explore the biological mechanisms of aging, influencing factors, and the effectiveness of intervention strategies, and provide a scientific basis for the formulation of more scientific and reasonable health policies and intervention measures.

[0156] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for dynamic identification and early warning of human aging data, characterized in that: The method comprises: S1. Obtain historical biometric data of the user, divide the historical biometric data according to a preset life monitoring period, and obtain periodic biometric data; S2. Generate a periodic biological aging portrait based on the periodic biological characteristic data, calculate the periodic biological aging age coefficient, perform periodic comparison and comprehensive comparison of the aging age coefficient, and then perform periodic aging determination and user aging determination; S3. Calculate the aging dynamic factor of each cycle according to the judgment information, and then judge the aging process, obtain the periodic aging node, obtain the periodic interval data of the aging node, set the weight according to the periodic interval data and issue an early warning.

2. According to claim 1, a human aging data dynamic identification and early warning method is characterized in that: The S1 includes: Acquire the user's historical medical information, pre-process the user's historical medical information, and obtain the pre-processed user's historical medical information; Extracting biometric data from the user's historical medical information to obtain historical biometric data; Obtaining a preset life monitoring period, dividing the historical biometric data according to the preset life cycle, and obtaining periodic biometric data; According to the preset life cycle and periodic biometric data, the idle life cycle and newly added feature data are obtained.

3. According to claim 1, a human aging data dynamic identification and early warning method is characterized in that: The S2 includes: Obtaining biometric data of each cycle, and generating a biological aging portrait of each cycle based on the biometric data of each cycle; Calculate the periodic biological aging age coefficient based on the periodic characteristic data of the periodic biological aging portrait; Calculate the average value of the periodic biological aging age coefficients of all periods of the user to obtain the user's comprehensive aging age coefficient; Comparing the biological aging age coefficient of each cycle with the comprehensive aging age coefficient of the user to obtain a cycle comparison result; Performing cycle aging determination on each cycle characteristic data according to the cycle comparison result to obtain a cycle aging determination result; Compare the user's comprehensive aging age coefficient with the average aging age coefficient of all users to obtain a user comparison result; Perform user aging determination on each user according to the user comparison result to obtain a user aging determination result.

4. According to claim 1, a human aging data dynamic identification and early warning method is characterized in that: The S3 includes: Acquire periodic aging determination information and user aging determination information, and calculate the aging dynamic factor of each period according to the periodic aging determination information combined with the user aging determination information; Comparing the aging dynamic factor with a preset factor threshold to obtain a factor comparison result; Determine the aging process change of the user according to the factor comparison result to obtain the process change determination result; According to the process change determination result, the preset life cycle is marked with aging nodes to obtain a periodic aging node.

5. According to claim 1, a human aging data dynamic identification and early warning method is characterized in that: The S3 further includes: Obtaining periodic aging nodes in a preset life cycle, and obtaining period interval data of each periodic aging node in the preset life cycle; According to the periodic interval data, the periodic aging nodes are sorted from the smallest arrival to obtain the aging sorted nodes; According to the sorting information, the weights of the aging sorting nodes are set accordingly; According to the weight data, graded warning is carried out for the periodic aging nodes to obtain graded warning information.

6. A human aging data dynamic identification and early warning system, characterized in that: The system comprises: A period division module is used to obtain historical biometric data of the user, divide the historical biometric data according to a preset life monitoring period, and obtain periodic biometric data; An aging determination module, used to generate a periodic biological aging portrait according to the periodic biological characteristic data, calculate the periodic biological aging age coefficient, perform periodic comparison and comprehensive comparison of the aging age coefficient, and then perform periodic aging determination and user aging determination; The aging dynamic warning module is used to calculate the aging dynamic factor of each cycle based on the judgment information, and then judge the aging process, obtain the periodic aging node, obtain the periodic interval data of the aging node, set the weight according to the periodic interval data and issue a warning.

7. According to claim 6, a human aging data dynamic identification and early warning system is characterized in that: The cycle division module comprises: An information acquisition module is used to acquire the user's historical medical information, pre-process the user's historical medical information, and obtain the pre-processed user's historical medical information; A feature extraction module, used to extract biometric data from the user's historical medical information to obtain historical biometric data; A data partitioning module, used to obtain a preset life monitoring period, divide the historical biometric data according to the preset life cycle, and obtain periodic biometric data; The cycle classification module is used to obtain the idle life cycle and newly added feature data according to the preset life cycle and periodic biometric feature data.

8. According to claim 6, a human aging data dynamic identification and early warning system is characterized in that: The aging determination module comprises: A portrait generation module, used to obtain biometric data of each cycle, and generate a biological aging portrait of each cycle according to the biometric data of each cycle; A cycle calculation module, used to calculate the cycle biological aging age coefficient according to the cycle characteristic data of the cycle biological aging portrait; A comprehensive calculation module, used to calculate the average value of the periodic biological aging age coefficients of all periods of the user to obtain the user's comprehensive aging age coefficient; A cycle comparison module, used to compare the biological aging age coefficient of each cycle with the user's comprehensive aging age coefficient to obtain a cycle comparison result; A cycle determination module, used for performing cycle aging determination on each cycle characteristic data according to the cycle comparison result to obtain a cycle aging determination result; A user comparison module is used to compare the user's comprehensive aging age coefficient with the average aging age coefficient of all users to obtain a user comparison result; The user determination module is used to perform user aging determination on each user according to the user comparison result to obtain a user aging determination result.

9. According to claim 6, a human aging data dynamic identification and early warning system is characterized in that: The aging dynamic early warning module includes: A dynamic calculation module, used to obtain periodic aging determination information and user aging determination information, and calculate the aging dynamic factor of each period according to the periodic aging determination information combined with the user aging determination information; A dynamic determination module, used to compare the aging dynamic factor with a preset factor threshold to obtain a factor comparison result; Determine the aging process change of the user according to the factor comparison result to obtain the process change determination result; The node marking module is used to mark the aging nodes of the preset life cycle according to the process change determination result to obtain the periodic aging nodes.

10. A human aging data dynamic identification and early warning system according to claim 6, characterized in that: The aging dynamic early warning module also includes: An interval data acquisition module, used to acquire periodic aging nodes in a preset life cycle, and to acquire periodic interval data of each periodic aging node in the preset life cycle; A node sorting module, used for sorting the periodic aging nodes from the smallest arrival according to the periodic interval data, to obtain aging sorted nodes; A hierarchical warning module is used to set the weights of the corresponding rankings of aging ranking nodes according to the ranking information; According to the weight data, graded warning is carried out for the periodic aging nodes to obtain graded warning information.

Images