A data management system for cardiovascular and cerebrovascular disease rehabilitation based on PDCA model

Abstract

The present invention discloses a cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model, and relates to the technical field of data management. The cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model comprises cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment, which is used to collect cardiovascular and cerebrovascular health data of patients; the cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model provides an efficient rehabilitation management platform with personalized rehabilitation plans and dynamic adjustments; by real-time monitoring of the patient's rehabilitation progress, the system can adjust the rehabilitation plan in time to ensure the safety and effectiveness of the rehabilitation process; it can allocate tasks according to high-speed, medium-speed and low-speed labels, ensure the efficient operation of the entire system, and improve the fairness and flexibility of task allocation; reduce unnecessary resource consumption, ensure that the system can still maintain a high processing efficiency under low load conditions, and improve the energy efficiency and resource utilization of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, in particular to a cardiovascular and cerebrovascular disease rehabilitation data management system based on a PDCA model. Background Art

[0002] At present, with the rapid development of medical Internet of Things, big data processing and artificial intelligence technology, the data collection, processing and analysis capabilities in the medical and health field have been significantly improved, which provides new ideas for the rehabilitation management of cardiovascular and cerebrovascular diseases. In the rehabilitation management of cardiovascular and cerebrovascular diseases, the PDCA cycle (Plan-Do-Check-Act) model is an effective rehabilitation management method; this model can continuously adjust the rehabilitation plan according to the patient's rehabilitation progress to ensure that the rehabilitation plan is consistent with the patient's actual health status; however, the application of the PDCA model in the existing rehabilitation management system is not perfect enough, and there are still some problems: data processing is not efficient: a large amount of health data generated during the rehabilitation process has not been effectively processed and analyzed, and data cleaning and outlier processing lack systematization, resulting in insufficient accuracy of data analysis, which affects the formulation and adjustment of rehabilitation plans; rehabilitation plans do not have dynamic adjustment capabilities: the adjustment of traditional rehabilitation plans mainly relies on regular manual evaluations, and it is impossible to achieve real-time and dynamic plan adjustments, and it is difficult to respond to changes in the patient's health status in a timely manner, resulting in reduced rehabilitation efficiency; resource allocation is unbalanced: in the data processing link, traditional systems usually find it difficult to achieve dynamic allocation of tasks and reasonable scheduling of resources, which can easily lead to overload of some data processing modules, while other modules may be idle, and resource utilization is low. Summary of the invention

[0003] The purpose of the present invention is to provide a cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model.

[0004] The purpose of the present invention can be achieved by the following technical solutions: a cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model, including cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment, which is used to collect cardiovascular and cerebrovascular health data of patients;

[0005] Cardiopulmonary function assessment devices, used to monitor patients’ breathing, heart function, and movement;

[0006] The data encapsulation module is used to obtain medical data and encapsulate the medical data into a health data package containing the patient's health status, where the medical data includes cardiovascular and cerebrovascular health data, the patient's respiration, heart function, the patient's basic physiological data, such as heart rate, blood pressure, blood oxygen saturation, exercise data, such as the number of steps, cardiopulmonary endurance and other rehabilitation-related indicators;

[0007] A medical health data processing server, connected to the data encapsulation module, for acquiring health data packets, the medical health data processing server comprising a data preprocessing module, a data processing module, a task allocation module and an artificial intelligence analysis module;

[0008] The data preprocessing module is used to obtain health data packets and convert the health data packets into data records in a standard format;

[0009] The data processing module includes three data processing units, which are marked as a first data processing unit, a second data processing unit and a third data processing unit, and each data processing unit is preset with a maintenance action, which is used to clean up the cache in the data processing unit; the data processing module is used to obtain data records and generate real-time load conditions based on the data records;

[0010] The data processing unit is also used to form a rehabilitation process based on real-time load conditions and data processing tasks; at the same time, the data processing unit is also used to call the data in the database of the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment and the cardiopulmonary function evaluation device to form historical data;

[0011] The task allocation module is used to generate data processing tasks according to the real-time load situation and data records. The task allocation module is also used to allocate the data processing tasks to the first data processing unit, the second data processing unit and the third data processing unit in the data processing module according to the real-time load situation of the data processing module, and calculate the scheduling value in each data processing unit in the data processing module according to the polling algorithm formula, and allocate the data processing tasks based on the scheduling value to ensure the efficiency and accuracy of data processing;

[0012] The artificial intelligence analysis module generates a rehabilitation plan based on the rehabilitation process and historical data, and adopts a plan-execution-check-act-action cycle model, i.e., a PDCA cycle model, and dynamically adjusts the patient's rehabilitation plan based on the PDCA cycle model to improve rehabilitation efficiency;

[0013] The historical data includes the following:

[0014] Past rehabilitation training data includes the time, type, intensity, and patient response data of each rehabilitation training, such as heart rate changes and fatigue level.

[0015] Historical disease progression data, such as the patient’s hospitalization records, surgical records, long-term medication information, and complication occurrences.

[0016] The patient's living habits data, including eating habits, work and rest patterns, exercise habits, etc. These data will be used to formulate a rehabilitation plan.

[0017] Furthermore, the data preprocessing module is used to obtain and clean the health data packet, calibrate the abnormal values ​​in the health data packet based on the error range of the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment and the cardiopulmonary function evaluation device, and remove the abnormal values ​​and values ​​that do not meet the medical standards from the health data packet to obtain a health data packet without abnormal values;

[0018] Then, the inconsistent data in the healthy data package without outliers are corrected by weighted average method, and the format of the data in the corrected healthy data package without outliers is standardized by Min-Max standardization to obtain data records;

[0019] During the calibration of abnormal values ​​in the health data packet based on the error range of the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment and the cardiopulmonary function assessment device, the amount of abnormal data in the health data packet is read and recorded as the abnormal value, and the abnormal value is compared with the preset calibration value. When the abnormal value is greater than or equal to the calibration value, the health data packet is marked as invalid and deleted from the cleaning to ensure the accuracy and efficiency of data processing;

[0020] When the abnormal value is less than the calibration value, the healthy data packet is marked as valid, and the process of the healthy data packet in the current cleaning continues to ensure the accuracy and efficiency of data processing.

[0021] Furthermore, the task allocation module dynamically allocates data processing tasks based on the real-time processing speed of each data processing unit and the number of tasks currently waiting to be processed in the task queue:

[0022] Obtain the historical processing speed and current load status of each data processing module, calculate the scheduling value of each data processing unit by timing 10 seconds as a calculation time difference, and allocate new data processing tasks according to the specific arrangement of the scheduling value of the data processing unit, complete the dynamic allocation of data processing tasks by the task allocation module, and ensure the reasonable allocation of system processing resources.

[0023] Further, when the task allocation module allocates the data processing task to the data processing unit, when the task allocation module detects that the task queue length of one of the three data processing units is 0, a sleep instruction with an activation tag is generated corresponding to the data processing unit with the task queue length of 0, and the data processing unit enters the sleep state based on the sleep instruction;

[0024] When a new data processing task arrives, the activation tag on the sleep instruction is activated by the data processing task, so that the data processing unit is reactivated for use, thereby avoiding unnecessary waste of computing resources and reactivating it.

[0025] Furthermore, the data processing module sets a sleep timing unit in each data processing unit, and the sleep timing unit has a countdown unit with an adjustable time span. The countdown unit automatically sets the timing duration of the countdown unit in the sleep timing unit of the data processing unit based on the historical data and historical processing speed of the data processing unit, and the sleep timing unit counts down when the data processing unit starts to sleep. After the sleep timing unit expires, the cache of the data processing unit is cleared according to a pre-set maintenance action to improve the performance and stability of the module.

[0026] Furthermore, the scheduling value in each data processing unit in the data processing module is calculated according to the polling algorithm formula, and the data processing tasks are allocated based on the scheduling value. The process is as follows:

[0027] The first data processing unit, the second data processing unit and the third data processing unit in the data processing module are marked as M1, M2 and M3 respectively;

[0028] Each data processing unit has a task queue for storing tasks waiting to be processed;

[0029] Monitor the historical processing speed and current load status of each data processing unit, and calculate the real-time processing speed of each data processing unit, marked as S1, S2 and S3;

[0030] The number of tasks currently waiting to be processed in the task queue of each data processing unit, i.e., the task queue length, is marked as L1, L2, and L3;

[0031] Set the initial scheduling value of each data processing unit to D; for each data processing unit M i , its scheduling value D 0 i It can be calculated by the following formula: 0 i =L i / S i , that is, the ratio of the task queue length to the real-time processing speed. This ratio reflects the relative load of each data processing module. The larger the ratio, the heavier the load of the module. According to the scheduling value D 0 i The calculation formula is used to obtain the scheduling value D of the first data processing unit. 0 1, the scheduling value D of the second data processing unit 0 2. The scheduling value D of the third data processing unit 0 3. Arrange the three scheduling values ​​in order from large to small.

[0032] Furthermore, the scheduling value D of the data processing unit is 0i Arrange in order from largest to smallest:

[0033] When two of the scheduling values ​​are the same, the D of the data processing unit is 0 i According to the corresponding order from large to small, they are marked as: high speed, low speed, among which, when high speed or low speed corresponds to the D of two data processing units 0 i , the data processing tasks are allocated according to the prefix order of the data processing units;

[0034] When the three scheduling values ​​are the same, the D 0 i All are marked as: average speed; at this time, the data processing tasks are also allocated according to the prefix order of the data processing units, that is, the data processing tasks are allocated in the order of the first data processing unit, the second data processing unit, and the third data processing unit;

[0035] When the three scheduling values ​​are different, the D 0 i The corresponding order from large to small is marked as: high speed, medium speed, low speed; at this time, the newly arrived data processing task is assigned to the data processing unit with the current scheduling value of low speed, the next data processing task is assigned to the data processing unit with the current scheduling value of medium speed, and the next data processing task is assigned to the data processing unit with the current scheduling value of high speed. When a new data processing task arrives, the above allocation steps are repeated;

[0036] During this period, the task allocation module checks each data processing unit in sequence and makes corresponding allocations based on the specific arrangement of the scheduling values ​​of the data processing units.

[0037] Furthermore, the artificial intelligence analysis module generates a rehabilitation plan based on the rehabilitation process and historical data and adopts the PDCA cycle model as follows:

[0038] Based on the patient's rehabilitation progress and historical data, the system analyzes the gap between the current rehabilitation progress and the established rehabilitation goal, and evaluates the patient's current rehabilitation status. If the rehabilitation goal is to improve cardiopulmonary endurance or control a certain blood pressure indicator within a specific period of time, the system will analyze the progress of the current indicator to determine whether it meets expectations.

[0039] Then, according to the patient's age and gender, individual differences in medical history, and the patient's current stage of rehabilitation, clear rehabilitation goals are set, such as rehabilitation goals: number of steps walked per day, control of heart rate range, intensity of breathing training, etc. In other words, the goals in the rehabilitation plan will be gradually set in stages according to the current rehabilitation process; for example, the early goals of rehabilitation will tend to be light exercise, such as walking for 10 minutes, and as the rehabilitation progresses, the goals may be gradually adjusted to walking for 30 minutes a day or performing more intense aerobic training;

[0040] Develop a rehabilitation plan for the patient based on the patient's real-time health data and historical data during the rehabilitation process;

[0041] Finally, the rehabilitation data of patients with the same disease are compared according to the patient's age, gender and physical condition characteristics, and the rehabilitation plan is adjusted individually, and an expected plan is generated at the same time;

[0042] For example, older patients with more serious conditions will have a more conservative rehabilitation plan, focusing on low-intensity and less frequent rehabilitation training; younger patients who recover faster will receive higher-intensity training recommendations to help them recover faster.

[0043] After the rehabilitation plan is formulated, the rehabilitation training content is arranged based on the daily training time and execution order to generate a specific rehabilitation plan;

[0044] Based on the generation of the rehabilitation plan, it is synchronized to the patient's rehabilitation terminal device to provide the patient with a basis for rehabilitation training and ensure that the patient can strictly follow the plan for rehabilitation training. Among them, the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment, the cardiopulmonary function assessment device and the smart bracelet together constitute the rehabilitation terminal equipment;

[0045] At the same time, the artificial intelligence analysis module is also used to monitor the patient's implementation of the rehabilitation plan in real time to ensure that every step of the rehabilitation plan can be effectively implemented.

[0046] Furthermore, the rehabilitation plan includes training content and training intensity; the training content includes cardiopulmonary function training, muscle strength training, and psychological counseling, and the training intensity is set and adjusted based on the patient's age, gender and physical condition, and in combination with the patient's current exercise tolerance and the severity of the disease; based on this, the rehabilitation plan is set as mild rehabilitation training for female patients and moderate rehabilitation training for male patients; among them, mild rehabilitation training is: walking for 15 minutes a day, with the heart rate controlled within 120 beats / minute; moderate rehabilitation training is: walking for 30 minutes a day, with the heart rate controlled within 150 beats / minute; the system will automatically set the type of training content, such as jogging, brisk walking, breathing training, strength training, etc. The frequency, time and intensity of each training are adjusted according to the patient's real-time health status.

[0047] Furthermore, the process of the artificial intelligence analysis module monitoring the patient's implementation of the rehabilitation program in real time is as follows:

[0048] The implementation of the patient's rehabilitation plan and physical reaction are monitored in real time through rehabilitation terminal equipment; based on the patient's physical reaction during the implementation of the rehabilitation plan and the health data package containing the patient's health status collected by the rehabilitation terminal equipment, the health status is retrieved from the health data package, and the physical condition matched by the health status is compared with the physical condition of the patient with the same disease in the expected plan; when the patient's physical condition is monitored to deviate from the expected plan, such as the patient's heart rate exceeds the safe range or the exercise tolerance is reduced, the patient is prevented from having accidents due to excessive exercise load by reducing the exercise intensity or shortening the training time, and the type of rehabilitation training is adjusted, and aerobic training is replaced by breathing training to ensure that the patient can safely complete the rehabilitation goals and complete the dynamic adjustment of the rehabilitation plan;

[0049] This real-time adjustment mechanism ensures that the rehabilitation plan can flexibly respond to changes in the patient's physical condition and optimize the rehabilitation effect;

[0050] The PDCA cycle model extracts data information related to the patient's rehabilitation process from the patient's rehabilitation process and historical data, generates a personalized rehabilitation plan based on the patient's individual differences, and provides real-time feedback and adjustments based on the patient's actual implementation, ensuring the safety and effectiveness of the rehabilitation process.

[0051] Compared with the prior art, the beneficial effects of the present invention are: the system integrates advanced health data collection, intelligent data processing, dynamic task allocation and artificial intelligence analysis technology to form an efficient rehabilitation management platform that can provide personalized rehabilitation plans and dynamically adjust; by real-time monitoring of the patient's rehabilitation progress, the system can adjust the rehabilitation plan in time to ensure the safety and effectiveness of the rehabilitation process; at the same time, the intelligent rehabilitation plan generation and adjustment function based on the PDCA cycle model makes rehabilitation training more scientific, personalized and flexible, greatly improving the patient's rehabilitation efficiency and rehabilitation effect; the overall technical effect of the system significantly improves the treatment quality of patients with cardiovascular and cerebrovascular diseases during the rehabilitation process, reduces the risks in the rehabilitation process, and ensures that patients can receive continuous and accurate treatment and recovery.

[0052] It can allocate tasks according to high-speed, medium-speed and low-speed labels to ensure reasonable distribution of tasks; this mechanism has significant advantages in task load balancing, and can prevent individual data processing units from being overloaded or idle, thereby ensuring the efficient operation of the entire system; in addition, the system uses prefix order for allocation when the scheduling values ​​are equal, which further improves the fairness and flexibility of task allocation.

[0053] When it is detected that the task queue length of a data processing unit is 0, the task allocation module will generate a sleep instruction with an activation tag to put the data processing unit into a sleep state; this mechanism can effectively reduce unnecessary resource consumption and automatically activate related units when new tasks arrive, ensuring that the system can still maintain a high processing efficiency under low load conditions, thereby improving the system's energy efficiency and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 The present invention is a structural block diagram of a cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model. DETAILED DESCRIPTION

[0055] like Figure 1 As shown, a cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model includes cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment for collecting cardiovascular and cerebrovascular health data of patients;

[0056] Cardiopulmonary function assessment devices, used to monitor patients’ breathing, heart function, and movement;

[0057] The data encapsulation module is used to obtain medical data and encapsulate the medical data into a health data package containing the patient's health status, where the medical data includes cardiovascular and cerebrovascular health data, the patient's respiration, heart function, the patient's basic physiological data, such as heart rate, blood pressure, blood oxygen saturation, exercise data, such as the number of steps, cardiopulmonary endurance and other rehabilitation-related indicators;

[0058] A medical health data processing server, connected to the data encapsulation module, for acquiring health data packets, the medical health data processing server comprising a data preprocessing module, a data processing module, a task allocation module and an artificial intelligence analysis module;

[0059] The data preprocessing module is used to obtain health data packets and convert the health data packets into data records in a standard format;

[0060] The data processing module includes three data processing units, which are marked as a first data processing unit, a second data processing unit and a third data processing unit, and each data processing unit is preset with a maintenance action, which is used to clean up the cache in the data processing unit; the data processing module is used to obtain data records and generate real-time load conditions based on the data records;

[0061] The data processing unit is also used to form a rehabilitation process based on real-time load conditions and data processing tasks; at the same time, the data processing unit is also used to call the data in the database of the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment and the cardiopulmonary function evaluation device to form historical data;

[0062] The task allocation module is used to generate data processing tasks according to the real-time load situation and data records. The task allocation module is also used to allocate the data processing tasks to the first data processing unit, the second data processing unit and the third data processing unit in the data processing module according to the real-time load situation of the data processing module, and calculate the scheduling value in each data processing unit in the data processing module according to the polling algorithm formula, and allocate the data processing tasks based on the scheduling value to ensure the efficiency and accuracy of data processing;

[0063] The artificial intelligence analysis module generates a rehabilitation plan based on the rehabilitation process and historical data, and adopts a plan-execution-check-act-action cycle model, i.e., a PDCA cycle model, and dynamically adjusts the patient's rehabilitation plan based on the PDCA cycle model to improve rehabilitation efficiency;

[0064] The historical data includes the following:

[0065] Past rehabilitation training data includes the time, type, intensity, and patient response data of each rehabilitation training, such as heart rate changes and fatigue level.

[0066] Historical disease progression data, such as the patient’s hospitalization records, surgical records, long-term medication information, and complication occurrences.

[0067] The patient's living habits data, including eating habits, work and rest patterns, exercise habits, etc. These data will be used to formulate a rehabilitation plan.

[0068] It should be further explained that, in the specific implementation process, the system collects the patient's health data in real time through cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment and cardiopulmonary function assessment devices, and can comprehensively monitor the patient's cardiovascular and cerebrovascular status and rehabilitation progress; the data encapsulation module encapsulates the collected health data into standardized data packets for subsequent processing and analysis; the data processing server cleans and standardizes the data through the data preprocessing module, and based on the intelligent scheduling mechanism of the task allocation module, realizes efficient data processing and optimal resource allocation; at the same time, the artificial intelligence analysis module uses historical data and real-time data to generate personalized rehabilitation plans based on the PDCA model, and dynamically adjusts the rehabilitation plan, so that the rehabilitation plan can be flexibly changed according to the patient's specific situation to ensure the maximization of the rehabilitation effect.

[0069] Furthermore, the data preprocessing module is used to obtain and clean the health data packet, calibrate the abnormal values ​​in the health data packet based on the error range of the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment and the cardiopulmonary function evaluation device, and remove the abnormal values ​​and values ​​that do not meet the medical standards from the health data packet to obtain a health data packet without abnormal values;

[0070] Then, the inconsistent data in the healthy data package without outliers are corrected by weighted average method, and the format of the data in the corrected healthy data package without outliers is standardized by Min-Max standardization to obtain data records;

[0071] During the calibration of abnormal values ​​in the health data packet based on the error range of the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment and the cardiopulmonary function assessment device, the amount of abnormal data in the health data packet is read and recorded as the abnormal value, and the abnormal value is compared with the preset calibration value. When the abnormal value is greater than or equal to the calibration value, the health data packet is marked as invalid and deleted from the cleaning to ensure the accuracy and efficiency of data processing;

[0072] When the abnormal value is less than the calibration value, the healthy data packet is marked as valid, and the process of the healthy data packet in the current cleaning continues to ensure the accuracy and efficiency of data processing.

[0073] It should be further explained that, in the specific implementation process, the data preprocessing module ensures the accuracy and reliability of the data processed by the system through strict outlier calibration and data cleaning mechanisms; this module eliminates outliers and corrects inconsistent data in data packets, effectively reducing data noise and improving the accuracy of data analysis; the use of Min-Max standardization ensures the uniformity of the data format, so that the subsequent data processing modules can perform data processing tasks efficiently and accurately; at the same time, the automatic filtering and deletion of abnormal data during the data cleaning process further ensures the validity of the data and provides a high-quality data foundation for the formulation and adjustment of subsequent rehabilitation plans.

[0074] Furthermore, the task allocation module dynamically allocates data processing tasks based on the real-time processing speed of each data processing unit and the number of tasks currently waiting to be processed in the task queue:

[0075] Obtain the historical processing speed and current load status of each data processing module, calculate the scheduling value of each data processing unit by timing 10 seconds as a calculation time difference, and allocate new data processing tasks according to the specific arrangement of the scheduling value of the data processing unit, complete the dynamic allocation of data processing tasks by the task allocation module, and ensure the reasonable allocation of system processing resources.

[0076] It should be further explained that, in the specific implementation process, the dynamic allocation mechanism of the task allocation module realizes the reasonable scheduling of system processing resources by real-time monitoring of the processing speed and task load of each data processing unit. By calculating the scheduling value of each data processing unit with a time difference of 10 seconds, the task allocation process can be dynamically optimized to ensure that the data processing module runs efficiently while avoiding the problem of task accumulation or resource waste, thereby improving the response speed and processing efficiency of the entire system.

[0077] Further, when the task allocation module allocates the data processing task to the data processing unit, when the task allocation module detects that the task queue length of one of the three data processing units is 0, a sleep instruction with an activation tag is generated corresponding to the data processing unit with the task queue length of 0, and the data processing unit enters the sleep state based on the sleep instruction;

[0078] When a new data processing task arrives, the activation tag on the sleep instruction is activated by the data processing task, so that the data processing unit is reactivated for use, thereby avoiding unnecessary waste of computing resources and reactivating it.

[0079] It should be further explained that, in the specific implementation process, when it is detected that the length of the task queue of a data processing unit is 0, the task allocation module will generate a sleep instruction with an activation tag to put the data processing unit into a sleep state; this mechanism can effectively reduce unnecessary resource consumption and automatically activate related units when new tasks arrive, ensuring that the system can still maintain a high processing efficiency under low load conditions, thereby improving the system's energy efficiency and resource utilization.

[0080] Furthermore, the data processing module sets a sleep timing unit in each data processing unit, and the sleep timing unit has a countdown unit with an adjustable time span. The countdown unit automatically sets the timing duration of the countdown unit in the sleep timing unit of the data processing unit based on the historical data and historical processing speed of the data processing unit, and the sleep timing unit counts down when the data processing unit starts to sleep. After the sleep timing unit expires, the cache of the data processing unit is cleared according to a pre-set maintenance action to improve the performance and stability of the module.

[0081] It should be further explained that, during the specific implementation, the sleep timing unit in each data processing unit can automatically set the timing duration according to historical data and processing speed. When the countdown ends, the system will automatically perform a cache cleanup action. This mechanism ensures the efficient operation of the data processing unit and avoids performance degradation caused by excessive cache. At the same time, it effectively saves computing resources and further optimizes the system's processing performance.

[0082] Furthermore, the scheduling value in each data processing unit in the data processing module is calculated according to the polling algorithm formula, and the data processing tasks are allocated based on the scheduling value. The process is as follows:

[0083] The first data processing unit, the second data processing unit and the third data processing unit in the data processing module are marked as M1, M2 and M3 respectively;

[0084] Each data processing unit has a task queue for storing tasks waiting to be processed;

[0085] Monitor the historical processing speed and current load status of each data processing unit, and calculate the real-time processing speed of each data processing unit, marked as S1, S2 and S3;

[0086] The number of tasks currently waiting to be processed in the task queue of each data processing unit, i.e., the task queue length, is marked as L1, L2, and L3;

[0087] Set the initial scheduling value of each data processing unit to D; for each data processing unit M i , its scheduling value D 0 i It can be calculated by the following formula: 0 i =L i / S i , that is, the ratio of the task queue length to the real-time processing speed. This ratio reflects the relative load of each data processing module. The larger the ratio, the heavier the load of the module. According to the scheduling value D 0 i The calculation formula is used to obtain the scheduling value D of the first data processing unit. 0 1, the scheduling value D of the second data processing unit 0 2. The scheduling value D of the third data processing unit 0 3. Arrange the three scheduling values ​​in order from large to small.

[0088] It should be further explained that in the specific implementation process, through the polling algorithm, the system can accurately calculate the scheduling value of each data processing unit and reasonably allocate tasks according to the scheduling value. This process effectively balances the load of each data processing unit and ensures efficient data processing. At the same time, the dynamic update of the scheduling value ensures that the system can adapt to the changes in real-time load, avoids task accumulation and processing delays, and further improves the stability and processing efficiency of the system.

[0089] Furthermore, the scheduling value D of the data processing unit is 0 i Arrange in order from largest to smallest:

[0090] When two of the scheduling values ​​are the same, the D of the data processing unit is 0 i According to the corresponding order from large to small, they are marked as: high speed, low speed, among which, when high speed or low speed corresponds to the D of two data processing units 0 i , the data processing tasks are allocated according to the prefix order of the data processing units;

[0091] When the three scheduling values ​​are the same, the D 0 i All are marked as: average speed; at this time, the data processing tasks are also allocated according to the prefix order of the data processing units, that is, the data processing tasks are allocated in the order of the first data processing unit, the second data processing unit, and the third data processing unit;

[0092] When the three scheduling values ​​are different, the D 0 i The corresponding order from large to small is marked as: high speed, medium speed, low speed; at this time, the newly arrived data processing task is assigned to the data processing unit with the current scheduling value of low speed, the next data processing task is assigned to the data processing unit with the current scheduling value of medium speed, and the next data processing task is assigned to the data processing unit with the current scheduling value of high speed. When a new data processing task arrives, the above allocation steps are repeated;

[0093] During this period, the task allocation module checks each data processing unit in sequence and makes corresponding allocations based on the specific arrangement of the scheduling values ​​of the data processing units.

[0094] It should be further explained that, in the specific implementation process, when the scheduling values ​​of multiple data processing units are the same, the system can allocate tasks according to the high-speed, medium-speed and low-speed labels to ensure a reasonable distribution of tasks; this mechanism has significant advantages in task load balancing, and can prevent individual data processing units from being overloaded or idle, thereby ensuring the efficient operation of the entire system; in addition, the system uses prefix order for allocation when the scheduling values ​​are equal, which further improves the fairness and flexibility of task allocation.

[0095] Furthermore, the artificial intelligence analysis module generates a rehabilitation plan based on the rehabilitation process and historical data and adopts the PDCA cycle model as follows:

[0096] Based on the patient's rehabilitation progress and historical data, the system analyzes the gap between the current rehabilitation progress and the established rehabilitation goal, and evaluates the patient's current rehabilitation status. If the rehabilitation goal is to improve cardiopulmonary endurance or control a certain blood pressure indicator within a specific period of time, the system will analyze the progress of the current indicator to determine whether it meets expectations.

[0097] Then, according to the patient's age and gender, individual differences in medical history, and the patient's current stage of rehabilitation, clear rehabilitation goals are set, such as rehabilitation goals: number of steps walked per day, control of heart rate range, intensity of breathing training, etc. In other words, the goals in the rehabilitation plan will be gradually set in stages according to the current rehabilitation process; for example, the early goals of rehabilitation will tend to be light exercise, such as walking for 10 minutes, and as the rehabilitation progresses, the goals may be gradually adjusted to walking for 30 minutes a day or performing more intense aerobic training;

[0098] Develop a rehabilitation plan for the patient based on the patient's real-time health data and historical data during the rehabilitation process;

[0099] Finally, the rehabilitation data of patients with the same disease are compared according to the patient's age, gender and physical condition characteristics, and the rehabilitation plan is adjusted individually, and an expected plan is generated at the same time;

[0100] For example, older patients with more serious conditions will have a more conservative rehabilitation plan, focusing on low-intensity and less frequent rehabilitation training; younger patients who recover faster will receive higher-intensity training recommendations to help them recover faster.

[0101] After the rehabilitation plan is formulated, the rehabilitation training content is arranged based on the daily training time and execution order to generate a specific rehabilitation plan;

[0102] Based on the generation of the rehabilitation plan, it is synchronized to the patient's rehabilitation terminal device to provide the patient with a basis for rehabilitation training and ensure that the patient can strictly follow the plan for rehabilitation training. Among them, the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment, the cardiopulmonary function assessment device and the smart bracelet together constitute the rehabilitation terminal equipment;

[0103] At the same time, the artificial intelligence analysis module is also used to monitor the patient's implementation of the rehabilitation plan in real time to ensure that every step of the rehabilitation plan can be effectively implemented.

[0104] It should be further explained that, during the specific implementation process, the artificial intelligence analysis module generates a rehabilitation plan through the PDCA cycle model, and dynamically adjusts the plan based on the patient's real-time rehabilitation data and historical data; this module can accurately assess the gap between the patient's rehabilitation progress and the established rehabilitation goals, and combine the patient's individual differences, such as age, gender and medical history; personalized rehabilitation goal setting to ensure the scientificity and rationality of the rehabilitation plan; at the same time, the system generates the most suitable rehabilitation plan for the patient based on comparative analysis of historical data, further improving rehabilitation efficiency.

[0105] Furthermore, the rehabilitation plan includes training content and training intensity; the training content includes cardiopulmonary function training, muscle strength training, and psychological counseling, and the training intensity is set and adjusted based on the patient's age, gender and physical condition, and in combination with the patient's current exercise tolerance and the severity of the disease; based on this, the rehabilitation plan is set as mild rehabilitation training for female patients and moderate rehabilitation training for male patients; among them, mild rehabilitation training is: walking for 15 minutes a day, with the heart rate controlled within 120 beats / minute; moderate rehabilitation training is: walking for 30 minutes a day, with the heart rate controlled within 150 beats / minute; the system will automatically set the type of training content, such as jogging, brisk walking, breathing training, strength training, etc. The frequency, time and intensity of each training are adjusted according to the patient's real-time health status.

[0106] It should be further explained that, in the specific implementation process, the training content and intensity of the rehabilitation plan are personalized according to multiple factors such as the patient's age, gender, physical condition, and exercise tolerance. By dividing the training content into mild and moderate rehabilitation programs, the system provides patients of different genders and physical conditions with more adaptable rehabilitation training plans, ensuring that each patient can effectively carry out rehabilitation training within a safe range. In addition, the clarity and scientific nature of the rehabilitation program help doctors and patients to better follow and implement it.

[0107] Furthermore, the process of the artificial intelligence analysis module monitoring the patient's implementation of the rehabilitation program in real time is as follows:

[0108] The implementation of the patient's rehabilitation plan and physical reaction are monitored in real time through rehabilitation terminal equipment; based on the patient's physical reaction during the implementation of the rehabilitation plan and the health data package containing the patient's health status collected by the rehabilitation terminal equipment, the health status is retrieved from the health data package, and the physical condition matched by the health status is compared with the physical condition of the patient with the same disease in the expected plan; when the patient's physical condition is monitored to deviate from the expected plan, such as the patient's heart rate exceeds the safe range or the exercise tolerance is reduced, the patient is prevented from having accidents due to excessive exercise load by reducing the exercise intensity or shortening the training time, and the type of rehabilitation training is adjusted, and aerobic training is replaced by breathing training to ensure that the patient can safely complete the rehabilitation goals and complete the dynamic adjustment of the rehabilitation plan;

[0109] This real-time adjustment mechanism ensures that the rehabilitation plan can flexibly respond to changes in the patient's physical condition and optimize the rehabilitation effect;

[0110] The PDCA cycle model extracts data information related to the patient's rehabilitation process from the patient's rehabilitation process and historical data, generates a personalized rehabilitation plan based on the patient's individual differences, and provides real-time feedback and adjustments based on the patient's actual implementation, ensuring the safety and effectiveness of the rehabilitation process.

[0111] It should be further explained that, during the specific implementation process, the artificial intelligence analysis module monitors the patient's rehabilitation progress in real time through the rehabilitation terminal equipment, and can dynamically adjust the rehabilitation plan according to the patient's actual physical reaction; this dynamic adjustment mechanism ensures that the patient will not experience adverse reactions due to excessive exercise load during the rehabilitation process; at the same time, the system can adjust the training type and intensity to make the rehabilitation plan more flexible and adaptable, thereby ensuring the patient's rehabilitation effect and safety; this real-time monitoring and dynamic adjustment function greatly improves the personalization and accuracy of the rehabilitation plan.

[0112] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model, characterized in that: include: Cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment, used to collect patients' cardiovascular and cerebrovascular health data; Cardiopulmonary function assessment devices, used to monitor patients’ breathing, heart function, and movement; A data encapsulation module is used to obtain medical data and encapsulate the medical data into a health data packet containing the patient's health status; A medical health data processing server, connected to the data encapsulation module, for acquiring health data packets, the medical health data processing server comprising a data preprocessing module, a data processing module, a task allocation module and an artificial intelligence analysis module; The data preprocessing module is used to obtain health data packets and convert the health data packets into data records in a standard format; The data processing module includes three data processing units, which are marked as a first data processing unit, a second data processing unit and a third data processing unit, and each data processing unit is preset with a maintenance action, which is used to clean up the cache in the data processing unit; the data processing module is used to obtain data records and generate real-time load conditions based on the data records; The data processing unit is also used to form a rehabilitation process based on real-time load conditions and data processing tasks; at the same time, the data processing unit is also used to call the data in the database of the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment and the cardiopulmonary function evaluation device to form historical data; The task allocation module is used to generate data processing tasks according to the real-time load situation and data records. The task allocation module is also used to allocate the data processing tasks to the first data processing unit, the second data processing unit and the third data processing unit in the data processing module according to the real-time load situation of the data processing module, and calculate the scheduling value in each data processing unit in the data processing module according to the polling algorithm formula, and allocate the data processing tasks based on the scheduling value to ensure the efficiency and accuracy of data processing; The artificial intelligence analysis module generates a rehabilitation plan based on the rehabilitation process and historical data, and adopts a plan-execution-check-act-action cycle model, i.e., a PDCA cycle model, and dynamically adjusts the patient's rehabilitation plan based on the PDCA cycle model; The task allocation module dynamically allocates data processing tasks based on the real-time processing speed of each data processing unit and the number of tasks currently waiting to be processed in the task queue: Obtain the historical processing speed and current load status of each data processing module, calculate the scheduling value of each data processing unit by timing 10 seconds as a calculation time difference, and allocate new data processing tasks according to the specific arrangement of the scheduling value of the data processing unit, complete the dynamic allocation of data processing tasks by the task allocation module, and ensure the reasonable allocation of system processing resources; When the task allocation module allocates the data processing task to the data processing unit, when the task allocation module detects that the task queue length of one of the three data processing units is 0, a sleep instruction with an activation tag is generated for the data processing unit with the task queue length of 0, and the data processing unit enters a sleep state based on the sleep instruction; When a new data processing task arrives, the activation tag on the sleep instruction is activated by the data processing task, so that the data processing unit is reactivated for use and reactivated; The data processing module sets a sleep timing unit in each data processing unit, and the sleep timing unit has a countdown unit with an adjustable time span. The countdown unit automatically sets the timing duration of the countdown unit in the sleep timing unit of the data processing unit based on the historical data and historical processing speed of the data processing unit, and the sleep timing unit counts down when the data processing unit starts to sleep. After the sleep timing unit expires, the cache of the data processing unit is cleared according to a preset maintenance action; The scheduling value in each data processing unit in the data processing module is calculated according to the polling algorithm formula, and the data processing tasks are allocated based on the scheduling value. The process is as follows: The first data processing unit, the second data processing unit and the third data processing unit in the data processing module are marked as M1, M2 and M3 respectively; Each data processing unit has a task queue for storing tasks waiting to be processed; Monitor the historical processing speed and current load status of each data processing unit, and calculate the real-time processing speed of each data processing unit, marked as S1, S2 and S3; The number of tasks currently waiting to be processed in the task queue of each data processing unit, i.e., the task queue length, is marked as L1, L2, and L3; Set the initial scheduling value of each data processing unit to D; for each data processing unit M i , its scheduling value D 0 i Calculated by the following formula: 0 i =L i / S i , according to the scheduling value D 0 i The calculation formula is used to obtain the scheduling value D of the first data processing unit. 0 1, the scheduling value D of the second data processing unit 0 2. The scheduling value D of the third data processing unit 0 3. Arrange the three scheduling values ​​in order from largest to smallest; The scheduling value D of the data processing unit 0 i Arrange in order from largest to smallest: When two of the scheduling values ​​are the same, the D of the data processing unit is 0 i According to the corresponding order from large to small, they are marked as: high speed, low speed, among which, when high speed or low speed corresponds to the D of two data processing units 0 i , the data processing tasks are allocated according to the prefix order of the data processing units; When the three scheduling values ​​are the same, the D 0 i All are marked as: average speed; at this time, the data processing tasks are also allocated according to the prefix order of the data processing units, that is, the data processing tasks are allocated in the order of the first data processing unit, the second data processing unit, and the third data processing unit; When the three scheduling values ​​are different, the D 0 i The corresponding order from large to small is marked as: high speed, medium speed, low speed; at this time, the newly arrived data processing task is assigned to the data processing unit with the current scheduling value of low speed, the next data processing task is assigned to the data processing unit with the current scheduling value of medium speed, and the next data processing task is assigned to the data processing unit with the current scheduling value of high speed. When a new data processing task arrives, the above allocation steps are repeated; During this period, the task allocation module checks each data processing unit in order and makes corresponding allocations based on the specific arrangement of the scheduling values ​​of the data processing units; The process of the artificial intelligence analysis module generating a rehabilitation plan based on the rehabilitation process and historical data and using the PDCA cycle model is as follows: Based on the patient's rehabilitation progress and historical data, analyze the gap between the current rehabilitation process and the established rehabilitation goals, and evaluate the patient's current rehabilitation status; Then, based on the patient’s age and gender, individual differences in medical history, and the patient’s current state of recovery, clear rehabilitation goals are set; Develop a rehabilitation plan for the patient based on the patient's real-time health data and historical data during the rehabilitation process; Finally, the rehabilitation data of patients with the same disease are compared according to the patient's age, gender and physical condition characteristics, and the rehabilitation plan is adjusted individually, and an expected plan is generated at the same time; After the rehabilitation plan is formulated, the rehabilitation training content is arranged based on the daily training time and execution order to generate a specific rehabilitation plan; Based on the generation of the rehabilitation plan, it is synchronized to the patient's rehabilitation terminal device to provide the patient with a basis for rehabilitation training. Among them, the cardiovascular and cerebrovascular rehabilitation monitoring terminal equipment, the cardiopulmonary function assessment device and the smart bracelet together constitute the rehabilitation terminal equipment; At the same time, the artificial intelligence analysis module is also used to monitor the patient's implementation of the rehabilitation plan in real time.

2. According to claim 1, a cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model is characterized in that: The rehabilitation plan includes training content and training intensity; The training content includes cardiopulmonary function training, muscle strength training, and psychological counseling. The training intensity is based on the patient's age, gender, and physical condition, and is set and adjusted in combination with the patient's current exercise tolerance and the severity of the disease. Based on this, the rehabilitation plan is set as mild rehabilitation training for female patients and moderate rehabilitation training for male patients. Among them, mild rehabilitation training is: walking for 15 minutes a day, with the heart rate controlled within 120 beats / minute; moderate rehabilitation training is: walking for 30 minutes a day, with the heart rate controlled within 150 beats / minute.

3. A cardiovascular and cerebrovascular disease rehabilitation data management system based on the PDCA model according to claim 2, characterized in that: The process of the artificial intelligence analysis module monitoring the patient's implementation of the rehabilitation plan in real time is as follows: The implementation of the patient's rehabilitation plan and physical reactions are monitored in real time through rehabilitation terminal equipment; based on the patient's physical reaction during the implementation of the rehabilitation plan and the health data packet containing the patient's health status collected by the rehabilitation terminal equipment, the health status is retrieved from the health data packet, and the physical condition matching the health status is compared with the physical condition of the patient with the same disease in the expected plan; when it is monitored that the patient's physical condition deviates from the expected plan, the patient is prevented from having accidents due to excessive exercise load by reducing the exercise intensity or shortening the training time, and the type of rehabilitation training is adjusted at the same time, replacing aerobic training with breathing training to complete the dynamic adjustment of the rehabilitation plan.

Images