Intelligent management method and system for retirees

Abstract

This invention discloses an intelligent management method and system for retirees, belonging to the field of information management technology for retirees. It acquires retirees' dynamic health data and behavioral monitoring data. The dynamic health data includes physical examination data, medication records, and medical records. The behavioral monitoring data includes access control data, business interaction data, and communication records. The method involves weighted summation of the dynamic health data to obtain a health risk level; constructing a daily behavioral baseline based on the behavioral monitoring data and calculating the behavioral deviation to obtain a silent anomaly level; fusing the health risk level and the silent anomaly level to obtain a comprehensive risk level; and generating an emergency verification task and pushing it to the management terminal if the comprehensive risk level reaches a warning threshold. This invention achieves dual-dimensional fusion warning of health data and behavioral data, improving the accuracy of risk identification for key personnel.

Description

Technical Field

[0001] This invention belongs to the field of information management technology for retirees, specifically a smart management method and system for retirees. Background Technology

[0002] Currently, government agencies and enterprises mostly manage retirees through basic information registration, regular manual visits, and static file labeling. This only enables simple storage and retrieval of personnel information. As the number of retirees increases and the requirements for more refined management become more stringent, the data is often scattered across multiple independent departments such as personnel, finance, labor union, and medical clinic.

[0003] Due to inter-departmental data management permissions and privacy protection requirements, raw data cannot be directly shared or centrally stored, making cross-departmental joint analysis difficult. This makes it impossible to comprehensively assess retirees' health risks, behavioral abnormalities, and comprehensive support needs. Existing systems either adopt centralized data management, which poses risks of data leakage and unauthorized access, or each department manages data independently, creating data silos and leading to inaccurate identification of key personnel. On the other hand, existing health early warning methods rely solely on health data or static labels from a single department, lacking joint monitoring of retirees' daily behavioral abnormalities, such as long-term absence of access control records or business interactions, resulting in high rates of missed reports of high-risk conditions and delayed early warnings. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent management method and system for retirees to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent management method for retirees, the method comprising the following steps:

[0006] Step S1: Obtain the health dynamic data and behavior monitoring data of the target retirees. The health dynamic data includes physical examination data, medication records, and medical records. The behavior monitoring data includes access control data, business interaction data, and communication records.

[0007] Step S2: Perform a weighted summation operation on the health dynamic data to obtain the health risk score corresponding to the target retiree, and match the corresponding health risk level according to the health risk score;

[0008] Step S3: Construct the daily behavior baseline of the target retiree based on the behavior monitoring data, calculate the behavior deviation of the behavior monitoring data relative to the daily behavior baseline, and match the corresponding silent abnormality level based on the behavior deviation.

[0009] Step S4: Perform a fusion calculation on the health risk level and the silent abnormality level to obtain the comprehensive risk score corresponding to the target retiree, and determine the comprehensive risk level based on the comprehensive risk score;

[0010] Step S5: Determine whether the comprehensive risk level has reached the preset warning threshold. If it has, generate an emergency verification task and push the emergency verification task to the corresponding management terminal.

[0011] As a further preferred embodiment of this technical solution: the weighted summation operation in step S2 specifically includes: configuring weight coefficients for the physical examination data, the medication record, and the medical record respectively, multiplying each data item by the corresponding weight coefficient, and then summing them to obtain the health risk score; the weight coefficients are determined based on the statistical correlation between historical retiree health data and adverse health outcomes.

[0012] As a further preferred embodiment of this technical solution: the construction of the daily behavior baseline in step S3 specifically includes: extracting historical behavior monitoring data of the target retirees within a preset period, calculating the average behavior indicators at each time point using a sliding time window, and obtaining the daily behavior baseline, which includes daily passage frequency, daily interaction duration, and daily communication frequency.

[0013] As a further preferred embodiment of this technical solution: the calculation of behavioral deviation in step S3 specifically includes:

[0014] Extract individual attribute tags from the target retirees, including tags for living alone and age segmentation tags;

[0015] The baseline threshold range of access control data is determined based on the age segmentation labels. When the real-time access data is lower than the baseline average and exceeds the baseline threshold range, the absolute value of the difference is taken as the behavior deviation.

[0016] When the solitary status label is "solo", when the real-time communication data is lower than the baseline average by more than a first preset deviation threshold, the absolute value of the difference is used as the behavioral deviation degree; when the solitary status label is "non-solo", when the real-time communication data is lower than the baseline average by more than a second preset deviation threshold, the absolute value of the difference is used as the behavioral deviation degree, wherein the second preset deviation threshold is stricter than the first preset deviation threshold.

[0017] The difference between real-time business interaction data and the baseline mean is used as the behavioral deviation.

[0018] As a further preferred embodiment of this technical solution: the fusion operation in step S4 specifically includes: multiplying the health risk level and the silent anomaly level by their respective fusion coefficients and then summing them to obtain a preliminary comprehensive score; when both the health risk level and the silent anomaly level are at the highest level, applying a nonlinear correction factor to the preliminary comprehensive score, wherein the nonlinear correction factor is determined according to the joint probability distribution of the health risk level and the silent anomaly level to obtain the comprehensive risk score.

[0019] As a further preferred embodiment of this technical solution: the generation of the emergency verification task in step S5 specifically includes: extracting the identity information, residential address, health risk level, silent abnormality level and comprehensive risk level of retirees who have reached the preset warning threshold, packaging them into a task list, and matching the corresponding administrator account according to the management area to which the retiree belongs.

[0020] As a further preferred embodiment of this technical solution, the method further includes a task execution closed-loop step: receiving task execution status data fed back by the management terminal, the task execution status data including executor information, execution time, and execution result, and encrypting the task execution status data before writing it into the task ledger.

[0021] The present invention also provides an intelligent management system for retirees, characterized in that the system comprises:

[0022] The data acquisition module is used to acquire the target retirees’ health dynamic data and behavior monitoring data. The health dynamic data includes physical examination data, medication records, and medical records. The behavior monitoring data includes access control data, business interaction data, and communication records.

[0023] The health assessment module, connected to the data acquisition module, is used to perform weighted summation on the dynamic health data to obtain the health risk score corresponding to the target retiree, and to match the corresponding health risk level based on the health risk score;

[0024] The behavior assessment module, connected to the data acquisition module, is used to construct the daily behavior baseline of the target retiree based on the behavior monitoring data, calculate the behavior deviation of the behavior monitoring data relative to the daily behavior baseline, and match the corresponding silent abnormality level based on the behavior deviation.

[0025] The fusion assessment module is connected to the health assessment module and the behavior assessment module respectively, and is used to perform fusion calculation on the health risk level and the silent abnormality level to obtain the comprehensive risk score corresponding to the target retiree, and determine the comprehensive risk level based on the comprehensive risk score;

[0026] The task management module, connected to the fusion assessment module, is used to determine whether the comprehensive risk level has reached a preset warning threshold. If it has, an emergency verification task is generated and pushed to the corresponding management terminal.

[0027] As a further preferred embodiment of this technical solution: the fusion assessment module includes: a linear weighting unit, used to multiply the health risk level and the silent abnormality level by their respective fusion coefficients and then sum them to obtain a preliminary comprehensive score; and a nonlinear correction unit, used to apply a nonlinear correction factor to the preliminary comprehensive score when both the health risk level and the silent abnormality level are at their highest levels, to obtain the comprehensive risk score.

[0028] As a further preferred embodiment of this technical solution: the system further includes a task closed-loop management module, which is connected to the task management module and is used to receive task execution status data fed back by the management terminal, encrypt the task execution status data and write it into the task ledger; the task execution status data includes executor information, execution time and execution result.

[0029] Compared with the prior art, the beneficial effects of the present invention are:

[0030] 1. In this invention, by simultaneously collecting dynamic health data, namely physical examination data, medication records, medical records, and government-specific behavioral data, namely access control data, business interaction data, and communication records, multi-dimensional data fusion is achieved, which solves the problem that single-dimensional data is difficult to accurately assess the comprehensive risks of retirees.

[0031] 2. In this invention, a sliding time window is used to construct a baseline of daily behavior, and individual attribute labels, namely, labels for living alone and age segmentation labels, are introduced to differentiate the calculation of deviation, which significantly improves the accuracy of abnormal behavior detection.

[0032] 3. In this invention, a nonlinear correction factor is introduced into the fusion operation. It is triggered when both health risk and silent anomaly are at the highest level, which effectively avoids the insufficient early warning of the linear model in extreme cases and improves the recall rate of emergency events.

[0033] 4. This invention forms a complete closed-loop management system from data collection, risk assessment, task generation, execution feedback to ledger encryption, supports traceability and auditing, and meets the internal management standards of the organization. Attached Figure Description

[0034] Figure 1 This is a flowchart of an intelligent management method for retirees according to the present invention;

[0035] Figure 2 This is a structural diagram of a module of an intelligent management system for retirees according to the present invention;

[0036] Figure 3 This is a flowchart illustrating the behavioral deviation calculation of an intelligent management method and system for retirees according to the present invention.

[0037] Figure 4 This is a flowchart illustrating the fusion operation of an intelligent management method and system for retirees according to the present invention. Detailed Implementation

[0038] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Example 1: Health Risk Score Calculation

[0040] Mr. Zhang, a 75-year-old retiree living alone, had high blood pressure (0.8) according to his physical examination data; regular use of antihypertensive medication (0.4); and one medical visit in the past three months (0.3). Based on historical data and logistic regression, the weighting coefficients were 0.35, 0.42, and 0.23. His health risk score was calculated as: 0.8 × 0.35 + 0.4 × 0.42 + 0.3 × 0.23 = 0.28 + 0.168 + 0.069 = 0.517. A score ≥ 0.5 was defined as high risk, 0.2 to 0.5 as medium risk, and less than 0.2 as low risk. Mr. Zhang was therefore classified as high risk.

[0041] Example 2: Calculation of Behavioral Deviation

[0042] Zhang's status as a single person is labeled as "single person," and his age segment label is "over 75 years old." His historical baseline for access control is 2 times per day, with a standard deviation of 0.5. The normal range is the mean ± 2 times the standard deviation, i.e., 1 to 3 times. The real-time access control data is 0 times, which is lower than the baseline mean and exceeds the normal range. The behavioral deviation is calculated as the absolute value of the difference between 0 and 2 divided by 2 = 1.0. The historical baseline for communication records is 5 minutes per day, with the first preset deviation threshold set at 50%. The real-time communication data is 1 minute, which is 80% lower than the baseline mean. If it exceeds 50%, a deviation is triggered. The behavioral deviation is calculated as the absolute value of the difference between 1 and 5 divided by 5 = 0.8. The baseline for business interaction data is 0.5 times per day, and the real-time data is 0 times. The difference of -0.5 is used as the behavioral deviation. After considering all indicators, the silent abnormality level is matched as severe.

[0043] Example 3: Fusion Computation and Early Warning

[0044] Mr. Zhang's health risk level is high, assigned a value of 0.9, and his silent abnormality level is severe, also assigned a value of 0.9. The fusion coefficient for both is 0.5, and the initial comprehensive score is 0.5 × 0.9 + 0.5 × 0.9 = 0.9. Since both are the highest levels, based on the joint probability distribution over the past 3 years, the probability of having a high health level and a severe silent abnormality level is 0.73. A non-linear correction factor of 0.2 is applied, and the final comprehensive risk score is 0.9 + 0.2 = 1.1, which is mapped to the highest comprehensive risk level. This reaches the preset warning threshold, and the system generates an emergency verification task, which is pushed to the terminal of the community administrator. After the administrator visits Mr. Zhang's home, he discovers that Mr. Zhang has suddenly fallen ill and promptly takes him to the hospital.

[0045] Example 4: Task Closed Loop

[0046] The administrator provided feedback via the terminal: Executor: Li, Execution time: 14:30 on March 15, 2025, Execution result: "Sent to hospital, condition is stable". The system encrypted the feedback data and wrote it into the task log to form a traceable record.

[0047] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart management method for retirees, characterized in that, The method includes the following steps: Step S1: Obtain the health dynamic data and behavior monitoring data of the target retirees. The health dynamic data includes physical examination data, medication records, and medical records. The behavior monitoring data includes access control data, business interaction data, and communication records. Step S2: Perform a weighted summation operation on the health dynamic data to obtain the health risk score corresponding to the target retiree, and match the corresponding health risk level according to the health risk score; Step S3: Construct the daily behavior baseline of the target retiree based on the behavior monitoring data, calculate the behavior deviation of the behavior monitoring data relative to the daily behavior baseline, and match the corresponding silent abnormality level based on the behavior deviation. Step S4: Perform a fusion calculation on the health risk level and the silent abnormality level to obtain the comprehensive risk score corresponding to the target retiree, and determine the comprehensive risk level based on the comprehensive risk score; Step S5: Determine whether the comprehensive risk level has reached the preset warning threshold. If it has, generate an emergency verification task and push the emergency verification task to the corresponding management terminal.

2. The intelligent management method for retirees according to claim 1, characterized in that, The weighted summation operation in step S2 specifically includes: assigning weight coefficients to the physical examination data, the medication record, and the medical record respectively; multiplying each data item by its corresponding weight coefficient and then summing them to obtain the health risk score; the weight coefficients are determined based on the statistical correlation between historical retiree health data and adverse health outcomes.

3. The intelligent management method for retirees according to claim 1, characterized in that, The construction of the daily behavior baseline in step S3 specifically includes: extracting historical behavior monitoring data of the target retirees within a preset period, calculating the average behavior indicators at each time point using a sliding time window, and obtaining the daily behavior baseline, which includes daily passage frequency, daily interaction duration, and daily communication frequency.

4. The intelligent management method for retirees according to claim 3, characterized in that, The calculation of behavioral deviation in step S3 specifically includes: Extract individual attribute tags from the target retirees, including tags for living alone and age segmentation tags; The baseline threshold range of access control data is determined based on the age segmentation labels. When the real-time access data is lower than the baseline average and exceeds the baseline threshold range, the absolute value of the difference is taken as the behavior deviation. When the solitary status label is "solo", when the real-time communication data is lower than the baseline average by more than a first preset deviation threshold, the absolute value of the difference is used as the behavioral deviation degree; when the solitary status label is "non-solo", when the real-time communication data is lower than the baseline average by more than a second preset deviation threshold, the absolute value of the difference is used as the behavioral deviation degree, wherein the second preset deviation threshold is stricter than the first preset deviation threshold. The difference between real-time business interaction data and the baseline mean is used as the behavioral deviation.

5. The intelligent management method for retirees according to claim 1, characterized in that, The fusion operation in step S4 specifically includes: multiplying the health risk level and the silent anomaly level by their respective fusion coefficients and then summing them to obtain a preliminary comprehensive score; when both the health risk level and the silent anomaly level are at the highest level, applying a nonlinear correction factor to the preliminary comprehensive score, wherein the nonlinear correction factor is determined based on the joint probability distribution of the health risk level and the silent anomaly level to obtain the comprehensive risk score.

6. The intelligent management method for retirees according to claim 1, characterized in that, The specific steps in step S5 for generating an emergency verification task include: extracting the identity information, residential address, health risk level, silent anomaly level, and comprehensive risk level of retirees who have reached the preset warning threshold, packaging them into a task list, and matching the corresponding administrator account according to the management area to which the retiree belongs.

7. The intelligent management method for retirees according to claim 1, characterized in that, The method further includes a task execution closed-loop step: receiving task execution status data fed back by the management terminal, the task execution status data including executor information, execution time, and execution result, and encrypting the task execution status data before writing it into the task ledger.

8. An intelligent management system for retirees, characterized in that, The system includes: The data acquisition module is used to acquire the target retirees’ health dynamic data and behavior monitoring data. The health dynamic data includes physical examination data, medication records, and medical records. The behavior monitoring data includes access control data, business interaction data, and communication records. The health assessment module, connected to the data acquisition module, is used to perform weighted summation on the dynamic health data to obtain the health risk score corresponding to the target retiree, and to match the corresponding health risk level based on the health risk score; The behavior assessment module, connected to the data acquisition module, is used to construct the daily behavior baseline of the target retiree based on the behavior monitoring data, calculate the behavior deviation of the behavior monitoring data relative to the daily behavior baseline, and match the corresponding silent abnormality level based on the behavior deviation. The fusion assessment module is connected to the health assessment module and the behavior assessment module respectively, and is used to perform fusion calculation on the health risk level and the silent abnormality level to obtain the comprehensive risk score corresponding to the target retiree, and determine the comprehensive risk level based on the comprehensive risk score; The task management module, connected to the fusion assessment module, is used to determine whether the comprehensive risk level has reached a preset warning threshold. If it has, an emergency verification task is generated and pushed to the corresponding management terminal.

9. The intelligent management system for retirees according to claim 8, characterized in that, The fusion assessment module includes: a linear weighting unit, used to multiply the health risk level and the silent abnormality level by their respective fusion coefficients and then sum them to obtain a preliminary comprehensive score; and a nonlinear correction unit, used to apply a nonlinear correction factor to the preliminary comprehensive score when both the health risk level and the silent abnormality level are at the highest level, to obtain the comprehensive risk score.

10. The intelligent management system for retirees according to claim 8, characterized in that, The system also includes a task closed-loop management module, which is connected to the task management module. This module receives task execution status data from the management terminal, encrypts the task execution status data, and writes it into the task ledger. The task execution status data includes executor information, execution time, and execution result.

Images