Data management method and system for medical health care platform and electronic equipment
By obtaining and analyzing the training image information and body parameter information on the medical and health care platform, the activity type and quantity of the elderly are updated in real time, the problem of low data update frequency is solved, the timely adjustment of the rehabilitation training plan is achieved, and the body of the elderly is improved Health protection and data accuracy.
Patent Information
- Application Number
- CN202411050438.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-26
AI Technical Summary
The existing medical and health care platform has low data update frequency and cannot track the physical condition of the elderly in time, resulting in the inability to adjust the rehabilitation training plan in time, which may lead to secondary damage to the physical condition.
By obtaining training image information and body parameter information, determine the elderly’s history and current activity type and activity volume, analyze the changes in body parameters, update the body parameter data in real time, and adjust the rehabilitation training plan.
Real-time update of the physical parameters of the elderly and timely adjustment of the rehabilitation training plan, improving the physical health protection and data accuracy of the elderly.
Smart Images

Figure CN119028501A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data management, and in particular to a data management method, system and electronic equipment for a medical and health care platform. Background Art
[0002] Medical and health care is a collection of medical resources and elderly care resources. It is a new elderly care model that aims to provide comprehensive health and elderly care services for the elderly. This model emphasizes the combination of medical insurance and rehabilitation training, including necessary medical services such as examinations, treatments, rehabilitation training, as well as daily care, functional training, daily activities and other elderly care services. The purpose of medical and health care is to achieve disease progression and maintain or restore the patient's various functions. Through this model, the elderly can enjoy the dual protection of medical care and elderly care in nursing homes or home environments, improve their quality of life and ensure their physical health and safety.
[0003] The existing medical and health care platform is still mainly based on data reporting for the physical condition data of each elderly person, that is, a physical examination is performed on each elderly person at regular intervals, and the physical condition data after the physical examination is reported manually or by the system. This data reporting method has the problem of low data update frequency, which may easily lead to the inability to timely and comprehensively update and track the physical condition information of each elderly person in real time, and it is also impossible to formulate a new rehabilitation training plan based on the updated physical condition information. At this time, if the elderly still undergo rehabilitation training according to the original rehabilitation training plan, not only will the elderly's physical recovery speed not be improved, but there is also the possibility that the elderly's physical condition will be damaged again due to unreasonable rehabilitation training. Summary of the invention
[0004] In order to solve at least one of the above-mentioned technical problems, the present application provides a data management method, system and electronic device for a medical and health care platform.
[0005] In a first aspect, the present application provides a data management method for a medical and health care platform, which adopts the following technical solution: obtaining training image information and body parameter information, wherein the training image information is image information corresponding to different elderly people performing rehabilitation training in the current time and historical period, and the body parameter information is body parameter information of different elderly people on the medical and health care platform in the current time and historical period; Determine, based on the training image information, the historical activity type, the current activity type, the historical activity amount corresponding to the historical activity type, and the current activity amount corresponding to the current activity type for each of the elderly; Determine, according to the historical activity types, the historical activity amounts and the physical parameter information, the physical parameter change standards corresponding to each of the elderly performing different activity types and different activity amounts within the historical period; Determine, according to the body parameter change standard, the body parameter change information corresponding to the current activity type and the current activity amount of the elderly at different time points in the current time; Based on the body parameter change information, the parameter data of the current time in the body parameter information is updated in real time to obtain updated body parameter information.
[0006] In a possible implementation, determining the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type of each elderly person based on the training image information includes: Determine a historical training image and a current training image for each of the elderly according to the training image information; Determine a historical rehabilitation training plan and a historical target achievement status corresponding to the historical rehabilitation training plan based on the historical training image, wherein the historical rehabilitation training plan is a rehabilitation training plan corresponding to a time node of the historical training image, and the historical target achievement status includes the target achievement status of the action of the historical activity type corresponding to the historical rehabilitation training plan and the target achievement status of the historical activity amount; Creating a rehabilitation training model, and inputting the historical training images, the historical rehabilitation training plan, and the target achievement status into the rehabilitation training model according to time nodes for training, to obtain a trained rehabilitation training model; Inputting the current training image into the rehabilitation training model for recognition, and obtaining a current target achievement status corresponding to the current training image; Based on the historical target-reaching status and the current target-reaching status, the historical activity type, the current activity type, the historical activity amount corresponding to the historical activity type, and the current activity amount corresponding to the current activity type are determined for each of the elderly.
[0007] In a possible implementation, determining a historical rehabilitation training plan and a historical target achievement status corresponding to the historical rehabilitation training plan based on the historical training image includes: Performing image clarity analysis on the historical training images to determine whether there are unclear image points in the historical training images; if so, performing three-dimensional simulation processing based on the historical training images to obtain training three-dimensional images; converting the training three-dimensional images into training three-dimensional videos according to preset observation angles and preset action change rules; and performing visual frame acquisition on the training three-dimensional videos to obtain training image visual frames; Analyzing and processing the training image visual frame to obtain training image map points; Determine the coordinate information and training descriptor information corresponding to each image feature point in the historical training image based on the training image map point; Performing a multi-dimensional spatial data search on training images in a preset training image library based on the image feature points to obtain a training image set, wherein the preset training image library is used to store training images taken by different elderly people when they perform the historical rehabilitation training plan; Corresponding the coordinate information to the corresponding coordinate position of each training image in the training image set, respectively, to obtain contrast descriptor information, wherein the contrast descriptor information is used to represent the descriptor information corresponding to the coordinate information of each training image in the training image set; Perform matrix comparison on the descriptors in the training descriptor information and the descriptors in the comparison descriptor information to obtain similarity ratio information; Based on the similarity ratio information, a descriptor similarity ratio mean is determined, and it is judged whether the descriptor similarity ratio mean satisfies a preset similarity ratio condition; if so, a historical rehabilitation training plan of the historical training images and a historical achievement status corresponding to the historical rehabilitation training plan are determined based on the training labels in the training image set.
[0008] In a possible implementation, the method further includes determining the physical parameter change standard corresponding to each elderly person performing different activity types and different activity amounts in the historical period according to the historical activity type, the historical activity amount and the physical parameter information, and then further including: Determine the time series length when each of the elderly performs different activity types and different activity amounts, and perform unsupervised time series data sorting on the physical parameter change standard based on the time series length, the activity type and the activity amount to obtain first training matrix data; Inputting the first training matrix data into the trained feature extraction model to perform vector feature extraction to obtain the number of training feature dimensions, and combining the obtained number of training feature dimensions with the first training matrix data to generate second training matrix data; Processing the data contained in the second training matrix data to obtain rehabilitation training data, and inputting the obtained rehabilitation training data into a preset algorithm model for data calculation to generate future physical parameter change standards corresponding to different activity amounts of different activity types performed by each elderly person in a future preset time period; Determine whether the future body parameter change standard and the body parameter change standard meet a preset difference range condition; if not, update the body parameter change standard based on the future body parameter change standard to obtain an updated body parameter change standard.
[0009] In a possible implementation, the step of inputting the first training matrix data into a trained feature extraction model to extract vector features to obtain the number of training feature dimensions includes: Determine, based on the first training matrix data, the activity type, activity amount, and body parameter change information of each of the elderly during the execution of the rehabilitation training plan; Inputting the activity type, activity amount and body parameter change information into the feature extraction model respectively for vector extraction, and obtaining a category feature vector corresponding to the activity type, a data feature vector corresponding to the activity amount and a parameter feature vector corresponding to the body parameter change information; The category feature vector, the data feature vector, and the parameter feature vector are statistically analyzed to obtain the number of training feature dimensions.
[0010] In a possible implementation, the step of combining the obtained number of training feature dimensions with the first training matrix data to generate second training matrix data includes: Integrate the training feature dimension quantity with the first training matrix data to generate training dimension matrix data; Performing basic data distribution exploration on the training dimension matrix data, obtaining the relative periodicity law of changes in physical parameters of each elderly person during rehabilitation training, and determining the length of the time period based on the relative periodicity law; Performing supervised time series data sorting on the training dimension matrix data based on the time period length to obtain training prediction matrix data; Based on the training prediction matrix data, the changing trend of the physical parameters of each elderly person in different types and amounts of activities in a future preset time period is predicted to generate second training matrix data. ; In a possible implementation, the obtained rehabilitation training data is input into a preset algorithm model for data extrapolation to generate future physical parameter change standards corresponding to different activity amounts of different activity types performed by each elderly person in a future preset time period, and then further includes: Obtaining actual physical parameter change standards within the future preset time period after each elderly person performs the current activity type and the current activity amount; The future body parameter change standard is denormalized based on the actual body parameter change standard to restore the future body parameter change standard to the actual body parameter change standard.
[0011] In the second aspect, the present application provides a data management system for a medical and health care platform, which adopts the following technical solution: A data management system for a medical and health care platform, comprising: An information acquisition module is used to acquire training image information and body parameter information, wherein the training image information is image information corresponding to different elderly people performing rehabilitation training in the current time and historical period, and the body parameter information is body parameter information of different elderly people on the medical and health care platform in the current time and historical period; an activity determination module, for determining the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type of each of the elderly based on the training image information; a standard determination module, for determining the physical parameter change standard corresponding to when each of the elderly performs different activity types and different activity amounts within the historical period according to the historical activity type, the historical activity amount, and the physical parameter information; A parameter determination module, configured to determine, according to the body parameter change standard, body parameter change information corresponding to the current activity type and the current activity amount of the elderly at different time points in the current time; The data updating module is used to update the parameter data of the current time in the body parameter information in real time based on the body parameter change information to obtain updated body parameter information.
[0012] In a possible implementation, when the activity determination module determines the historical activity type, the current activity type, the historical activity amount corresponding to the historical activity type, and the current activity amount corresponding to the current activity type of each of the elderly based on the training image information, it is specifically used to: Determine a historical training image and a current training image for each of the elderly according to the training image information; Determine a historical rehabilitation training plan and a historical target achievement status corresponding to the historical rehabilitation training plan based on the historical training image, wherein the historical rehabilitation training plan is a rehabilitation training plan corresponding to a time node of the historical training image, and the historical target achievement status includes the target achievement status of the action of the historical activity type corresponding to the historical rehabilitation training plan and the target achievement status of the historical activity amount; Creating a rehabilitation training model, and inputting the historical training images, the historical rehabilitation training plan, and the target achievement status into the rehabilitation training model according to time nodes for training, to obtain a trained rehabilitation training model; Inputting the current training image into the rehabilitation training model for recognition, and obtaining a current target achievement status corresponding to the current training image; Based on the historical target-reaching status and the current target-reaching status, the historical activity type, the current activity type, the historical activity amount corresponding to the historical activity type, and the current activity amount corresponding to the current activity type are determined for each of the elderly.
[0013] In another possible implementation, when the activity determination module is used to determine a historical rehabilitation training plan and a historical target achievement status corresponding to the historical rehabilitation training plan based on the historical training image, it is specifically used to: Performing image clarity analysis on the historical training images to determine whether there are unclear image points in the historical training images; if so, performing three-dimensional simulation processing based on the historical training images to obtain training three-dimensional images; converting the training three-dimensional images into training three-dimensional videos according to preset observation angles and preset action change rules; and performing visual frame acquisition on the training three-dimensional videos to obtain training image visual frames; Analyzing and processing the training image visual frame to obtain training image map points; Determine the coordinate information and training descriptor information corresponding to each image feature point in the historical training image based on the training image map point; Performing a multi-dimensional spatial data search on training images in a preset training image library based on the image feature points to obtain a training image set, wherein the preset training image library is used to store training images taken by different elderly people when they perform the historical rehabilitation training plan; Corresponding the coordinate information to the corresponding coordinate position of each training image in the training image set, respectively, to obtain contrast descriptor information, wherein the contrast descriptor information is used to represent the descriptor information corresponding to the coordinate information of each training image in the training image set; Perform matrix comparison on the descriptors in the training descriptor information and the descriptors in the comparison descriptor information to obtain similarity ratio information; Based on the similarity ratio information, a descriptor similarity ratio mean is determined, and it is judged whether the descriptor similarity ratio mean satisfies a preset similarity ratio condition; if so, a historical rehabilitation training plan of the historical training images and a historical achievement status corresponding to the historical rehabilitation training plan are determined based on the training labels in the training image set.
[0014] In another possible implementation, the system further includes: a data sorting module, a vector extraction module, a data processing module and a standard updating module, wherein: The data sorting module is used to determine the time series length of each elderly person when performing different activity types and different activity amounts, and to perform unsupervised time series data sorting on the physical parameter change standard based on the time series length, the activity type and the activity amount to obtain first training matrix data; The vector extraction module is used to input the first training matrix data into the trained feature extraction model to perform vector feature extraction to obtain the number of training feature dimensions, and perform data combination processing on the obtained number of training feature dimensions and the first training matrix data to generate second training matrix data; The data processing module is used to process the data contained in the second training matrix data to obtain rehabilitation training data, and input the obtained rehabilitation training data into a preset algorithm model for data calculation to generate future physical parameter change standards corresponding to different activity amounts of different activity types performed by each elderly person in a future preset time period; The standard updating module is used to determine whether the future body parameter change standard and the body parameter change standard meet the preset difference range condition. If not, the body parameter change standard is updated based on the future body parameter change standard to obtain an updated body parameter change standard.
[0015] In another possible implementation, when the vector extraction module inputs the first training matrix data into the trained feature extraction model to extract vector features and obtains the number of training feature dimensions, it is specifically used to: Determine, based on the first training matrix data, the activity type, activity amount, and body parameter change information of each of the elderly during the execution of the rehabilitation training plan; Inputting the activity type, activity amount and body parameter change information into the feature extraction model respectively for vector extraction, and obtaining a category feature vector corresponding to the activity type, a data feature vector corresponding to the activity amount and a parameter feature vector corresponding to the body parameter change information; The category feature vector, the data feature vector, and the parameter feature vector are statistically analyzed to obtain the number of training feature dimensions.
[0016] In another possible implementation, when the vector extraction module combines the obtained number of training feature dimensions with the first training matrix data to generate the second training matrix data, it is specifically used to: Integrate the training feature dimension quantity with the first training matrix data to generate training dimension matrix data; Performing basic data distribution exploration on the training dimension matrix data, obtaining the relative periodicity law of changes in physical parameters of each elderly person during rehabilitation training, and determining the length of the time period based on the relative periodicity law; Performing supervised time series data sorting on the training dimension matrix data based on the time period length to obtain training prediction matrix data; Based on the training prediction matrix data, the changing trend of the physical parameters of each of the elderly people performing different types and amounts of activities in a future preset time period is predicted to generate second training matrix data.
[0017] In another possible implementation, the system further includes: an actual standard acquisition module and a standard recovery module, wherein: The actual standard acquisition module is used to obtain the actual physical parameter change standard of each elderly person within a preset time period in the future after performing the current activity type and current activity amount; The standard recovery module is used to perform denormalization processing on the future body parameter change standard based on the actual body parameter change standard, and restore the future body parameter change standard to the actual body parameter change standard.
[0018] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one application is configured to: execute a data management method for a medical and health care platform as described in any one of the first aspects.
[0019] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute any of the data management methods for a medical and health care platform as described in the first aspect.
[0020] In summary, the present application includes at least one of the following beneficial technical effects: When the elderly are undergoing rehabilitation training, in order to improve the real-time update of the elderly's physical parameters during the rehabilitation training process, so as to make timely adjustments to the rehabilitation training plan according to the physical parameters updated in real time, the present application adopts: obtaining training image information and physical parameter information, wherein the training image information is the image information corresponding to different elderly people when performing rehabilitation training in the current time and historical period, and the physical parameter information is the physical parameter information of different elderly people on the medical and health care platform in the current time and historical period, and then determining the historical activity type, current activity type, historical activity amount corresponding to the historical activity type and current activity amount corresponding to the current activity type of each elderly person based on the training image information, and then adjusting the rehabilitation training plan according to the historical activity parameters. The historical activity type, historical activity amount and body parameter information are used to determine the body parameter change standards corresponding to each elderly person performing different activity types and amounts within the historical period. Then, the body parameter change information corresponding to the current activity type and current activity amount at different time nodes in the current time is determined based on the body parameter change standards. Then, based on the body parameter change information, the parameter data of the current time in the body parameter information is updated in real time to obtain updated body parameter information. The staff makes timely adjustments to the subsequent rehabilitation training of each elderly person based on the real-time updated body health parameter data, which not only achieves the effect of protecting the health of the elderly, but also improves the real-time and accuracy of the elderly's body parameter data. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 A flowchart of a data management method for a medical and health care platform provided in an embodiment of the present application.
[0022] Figure 2 A schematic diagram of the structure of a data management system for a medical and health care platform provided in an embodiment of the present application.
[0023] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0024] The following is combined with Figure 1-3 This application is described in further detail.
[0025] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.
[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0027] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.
[0028] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.
[0029] The embodiment of the present application provides a method for data management of a medical and health care platform, which is executed by an electronic device, wherein the electronic device may be an independent physical electronic device, or an electronic device cluster or distributed system composed of multiple physical electronic devices, or a cloud electronic device providing cloud computing services. The embodiment of the present application is not limited here, such as Figure 1 As shown, the method includes: Step S10: Acquire training image information and body parameter information.
[0030] Among them, the training image information is the image information corresponding to different elderly people performing rehabilitation training in the current time and historical period, and the body parameter information is the body parameter information of different elderly people on the medical and health care platform in the current time and historical period.
[0031] In the embodiment of the present application, the training image information represents a series of image data, which captures the scenes of different elderly people during rehabilitation training, including real-time images at the current time point and records in the historical period (such as the past few days, weeks or months). These image information are crucial for training rehabilitation assessment models because they intuitively show the movements, postures and changes of the elderly during the rehabilitation process. Physical parameter information refers to the various physical index data of different elderly people at the current time and in the historical period collected on the medical and health care platform, such as heart rate, blood pressure, weight, body fat rate, etc. These data are used to quantitatively evaluate the physical condition of the elderly, complement the training image information, and jointly provide a comprehensive basis for the evaluation of the effect of rehabilitation training. The elderly here specifically refer to the elderly group participating in the rehabilitation training program, who are the main body and focus of rehabilitation training. Rehabilitation training refers to a series of planned and purposeful activities or exercises carried out to improve or restore physical function. The current time refers to the instantaneous moment of data collection or evaluation, while the historical period refers to a period of time in the past, which is used to trace and compare the changes in the physical condition of the elderly.
[0032] Specifically, the electronic device will collect training image information and body parameter information from various data sources (such as cameras, sensors, health monitoring equipment, etc.) regularly or as needed. This information covers various aspects of data of different elderly people during rehabilitation training, providing a solid foundation for subsequent model training, effect evaluation and the formulation of personalized rehabilitation plans. Next, the electronic device will organize, clean and format this information to ensure the consistency and accuracy of the data. Finally, the processed data will be stored in a special database for use in subsequent steps.
[0033] Step S11: Determine the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type for each elderly person based on the training image information.
[0034] In the embodiment of the present application, the historical activity type and the current activity type refer to the types of activities that the elderly have been doing in a certain period of time in the past and are currently doing, respectively. For example, the historical activity type may be walking, and the current activity type may be doing exercises. The historical activity volume and the current activity volume are indicators for quantitatively evaluating these activity types, which are used to measure the intensity and duration of the elderly's activities in the corresponding time period. For example, the historical activity volume can be the total number of steps that the elderly have taken in the past week, and the current activity volume is the duration of the elderly's exercises in the current time period.
[0035] Specifically, the electronic device will first collect and organize the training image information of the elderly, which covers all aspects of the elderly's daily activities. Then, the electronic device will use image processing technology and machine learning algorithms to identify and classify the activities of the elderly in the image, so as to determine the historical activity type and current activity type of each elderly person. At the same time, the electronic device will also calculate the corresponding historical activity amount and current activity amount based on the characteristics of the activity type and other clues in the image (such as timestamps, movement amplitude, etc.). The timing of this step can be real-time or periodic, depending on the needs of the electronic device for monitoring the activities of the elderly.
[0036] In an embodiment of the present application, the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type of each elderly person are determined based on the training image information, including: determining the historical training images and current training images of each elderly person according to the training image information, determining the historical rehabilitation training plan and the historical target achievement corresponding to the historical rehabilitation training plan based on the historical training images, the historical rehabilitation training plan is a rehabilitation training plan corresponding to the time node of the historical training image, the historical target achievement includes the action target achievement of the historical activity type corresponding to the historical rehabilitation training plan and the target achievement of the historical activity amount, creating a rehabilitation training model, and inputting the historical training images, the historical rehabilitation training plans, and the target achievement into the rehabilitation training model according to the time nodes for training to obtain the trained rehabilitation training model, inputting the current training image into the rehabilitation training model for recognition to obtain the current target achievement corresponding to the current training image, and determining the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type of each elderly person based on the historical target achievement and the current target achievement.
[0037] Among them, the rehabilitation training model is a neural network model.
[0038] Specifically, determining a historical rehabilitation training plan and a historical achievement status corresponding to the historical rehabilitation training plan based on the historical training images includes: performing image clarity analysis on the historical training images to determine whether there are unclear image points in the historical training images, and if so, performing three-dimensional simulation processing based on the historical training images to obtain training three-dimensional images, converting the training three-dimensional images into training three-dimensional videos according to preset observation angles and preset action change rules, and performing visual frame acquisition on the training three-dimensional videos to obtain training image visual frames, analyzing and processing the training image visual frames to obtain training image map points, determining coordinate information and training descriptor information corresponding to each image feature point in the historical training images based on the training image map points, and performing multi-dimensional analysis on the training images in the preset training image library based on the image feature points. Spatial data search is performed to obtain a training image set. A preset training image library is used to store training images taken by different elderly people when executing historical rehabilitation training plans. The coordinate information is respectively matched with the corresponding coordinate position of each training image in the training image set to obtain comparative descriptor information. The comparative descriptor information is used to represent the descriptor information corresponding to the coordinate information of each training image in the training image set. The descriptors in the training descriptor information are respectively compared with the descriptors in the comparative descriptor information to obtain similarity ratio information. The mean of the descriptor similarity ratio is determined based on the similarity ratio information, and it is judged whether the mean of the descriptor similarity ratio meets the preset similarity ratio condition. If so, the historical rehabilitation training plan of the historical training image and the historical achievement corresponding to the historical rehabilitation training plan are determined based on the training labels in the training image set.
[0039] Specifically, the preset observation angle includes the initial observation angle of the historical training image and the final observation angle of the historical training image. The preset action change rule is used to represent the change process rule of the historical training image from the initial position to the final position. For example: when the historical training image is tiled, its observation angle is defined as 90 degrees, that is, the observation is perpendicular to the historical training image. At this time, the electronic device observes the image from left to right. The initial observation angle of the historical training image is 0 degrees, and the final observation angle of the historical training image is 180 degrees. The preset action change rule is based on the central axis of the historical training image to rotate counterclockwise, so that the observation angle of the historical training image changes from 0 degrees to 180 degrees.
[0040] Specifically, the main components of the training image map point include: coordinates, descriptors, observation keyframe sets, observation distance ranges, and average observation directions. Among them, coordinates are generally in the form of (u, v) to represent the position coordinates of feature points in the building image. Descriptors are data structures that characterize features, generally represented in the form of matrices. Observation keyframe sets are sets composed of multiple observation keyframes. Observation keyframes are map points that are associated with (observed) a feature point in a keyframe in the training image map point. The observation distance range is the minimum and maximum interval between the distance between the observation keyframe and the map point. The average observation direction is the direction of the straight line formed by the observation keyframe and the map point in the world coordinate system. Image feature points refer to some pixels in the historical training image that are significantly different from other pixels, as well as the texture information formed by the surrounding pixels. Common feature points often have the characteristics of particularly high or low brightness, surrounding pixels showing surrounding distribution, and pixel gradients being at extreme values in multiple directions. The extraction of feature points is to find these special pixels from the image and record their coordinate information.
[0041] Specifically, the description of feature points is to assign a specific and identifiable ID to the extracted feature points, which is usually related to the brightness of the surrounding image, which can be compared to issuing an ID number to each person. At the same time, the description of feature points generally also includes an intensity value of the feature point, indicating the prominence of this feature. The higher the intensity, the less sensitive and more stable it is to the influence of ambient light, and the lower the intensity, the less reliable it is. Each extracted feature point can be expressed as: {(u,v),s,d}.
[0042] Where (u, v) represents the position coordinates of the feature point, s is its intensity value, and d is the descriptor (usually a matrix of fixed size).
[0043] Specifically, the descriptor matrix in the training descriptor information is compared with the descriptor matrix in the comparison descriptor information, and the matching degree in the two matrices is calculated to obtain the similarity ratio information. For example, the descriptor matrix in the training descriptor information and the descriptor matrix in the comparison descriptor information both have three rows and three columns of data, that is, nine groups of data, of which five groups of data are the same, then the similarity ratio of the two matrices is 5 / 9.
[0044] In the embodiment of the present application, the preset similarity condition is that the average value of the similarity ratio is not less than 98%.
[0045] Step S12: Determine the physical parameter change standard corresponding to each elderly person performing different activity types and different activity amounts in the historical period according to the historical activity types, historical activity amounts and physical parameter information.
[0046] Specifically, the physical parameter change standard refers to the normal range or trend of physical parameters that the elderly should have when performing different types and amounts of activities, which is obtained through analysis based on historical activity types, historical activity amounts, and physical parameter information, and is used to evaluate the health status and exercise effect of the elderly. For example, for an elderly person who often walks, his historical activity types include walking, and the historical activity amount can be the number of steps taken every day. At the same time, the heart rate, blood pressure and other physical parameter information of the elderly during this time period are obtained through physical examination. When performing the above-mentioned activity types, it can be determined that as the number of steps of the elderly increases, the heart rate should gradually increase and fluctuate within a certain range, and the blood pressure should remain stable within a certain range or slightly decrease, and other normal physical parameter changes. This application uses the above physical parameter changes as the physical parameter change standard, that is, when the elderly are undergoing rehabilitation training, the physical parameter changes meet a standard for normal physical parameter changes of personnel.
[0047] However, as the elderly age, after the corresponding amount of activity is completed, the normal standard for judging the change of the elderly's physical condition parameters needs to be updated in time, so this application will also analyze different elderly groups to ensure the accuracy of the physical parameter change standard of each elderly person in each elderly group after the activity is completed. For example: at a certain moment in history, the elderly's heart rate at the beginning of the walk was 60 beats / minute, and after two hours of walking, its heart rate was 89 beats / minute, and the elderly's body did not feel any abnormality at this time, so the normal heart rate standard of the elderly was determined to be 60-89 beats / minute, and at the current moment, the elderly's heart rate at the initial moment of the walk was 50 beats / minute, and after two hours of walking, its heart rate was 70 beats / minute, and the elderly's body did not feel any abnormality at this time. After walking for three hours, the heart rate suddenly rose to 80 beats / minute, and the elderly also felt unwell at this time, so the normal heart rate standard in the process became 50-70 beats / minute, which shows that the standard of change of the elderly's physical parameters changes with time.
[0048] In an embodiment of the present application, in order to ensure the real-time accuracy of the physical parameter change standard, the time series length of each elderly person when performing different activity types and different activity amounts is determined, and the physical parameter change standard is unsupervisedly sorted based on the time series length, activity type and activity amount to obtain the first training matrix data, and then the first training matrix data is input into the trained feature extraction model for vector feature extraction to obtain the number of training feature dimensions, and the obtained number of training feature dimensions is combined with the first training matrix data for data processing to generate the second training matrix data, and then the data contained in the second training matrix data is processed to obtain rehabilitation training data, and the obtained rehabilitation training data is input into the preset algorithm model for data extrapolation to generate the future physical parameter change standard corresponding to the different activity amounts of different activity types performed by each elderly person in the future preset time period, and then it is determined whether the future physical parameter change standard meets the preset difference range condition with the physical parameter change standard. If not, the physical parameter change standard is updated based on the future physical parameter change standard to obtain the updated physical parameter change standard.
[0049] Specifically, the first training matrix data is input into the trained feature extraction model for vector feature extraction to obtain the number of training feature dimensions, including: determining the activity type, activity amount and body parameter change information of each elderly person during the execution of the rehabilitation training plan based on the first training matrix data, and then inputting the activity type, activity amount and body parameter change information into the feature extraction model for vector extraction to obtain the category feature vector corresponding to the activity type, the data feature vector corresponding to the activity amount and the parameter feature vector corresponding to the body parameter change information, and performing quantitative statistics on the category feature vectors, data feature vectors and parameter feature vectors to obtain the number of training feature dimensions.
[0050] Specifically, the obtained number of training feature dimensions is combined with the first training matrix data for data processing to generate second training matrix data, including: integrating the number of training feature dimensions with the first training matrix data to generate training dimension matrix data, performing basic data distribution exploration on the training dimension matrix data, obtaining the relative periodicity of changes in physical parameters of each elderly person during rehabilitation training, and determining the length of the time period based on the relative periodicity, performing supervised time series data sorting on the training dimension matrix data based on the length of the time period to obtain training prediction matrix data, and predicting the trend of changes in physical parameters of each elderly person performing different types and amounts of activities in a preset time period in the future based on the training prediction matrix data to generate second training matrix data.
[0051] Specifically, the obtained rehabilitation training data is input into a preset algorithm model for data extrapolation to generate future body parameter change standards corresponding to different activity types and amounts of each elderly person performing different activities in a preset time period in the future. It also includes: obtaining the actual body parameter change standards in a preset time period in the future after each elderly person performs the current activity type and the current activity amount, and performing denormalization processing on the future body parameter change standards based on the actual body parameter change standards to restore the future body parameter change standards to the actual body parameter change standards.
[0052] Step S13: Determine the body parameter change information corresponding to the current activity type and current activity amount of the elderly at different time nodes in the current time according to the body parameter change standard.
[0053] Specifically, according to the body parameter change standard, we can know the changes in the body parameters of the elderly at different time nodes during a certain training process. Therefore, this application uses the body parameter change standard as a parameter evaluation model, and inputs the time node, activity type and activity amount into the model respectively, so as to know the real-time body parameter changes of the elderly without using body monitoring equipment to perform physical examinations on the elderly.
[0054] Step S14: based on the body parameter change information, the parameter data of the current time in the body parameter information is updated in real time to obtain updated body parameter information.
[0055] Based on the above embodiments, when the elderly are undergoing rehabilitation training, in order to improve the real-time update and acquisition of the elderly's physical parameters during the rehabilitation training process, so as to facilitate timely adjustment of the rehabilitation training plan according to the physical parameters acquired through real-time updates, the present application adopts: acquiring training image information and physical parameter information, wherein the training image information is the image information corresponding to different elderly people performing rehabilitation training in the current time and historical period, and the physical parameter information is the physical parameter information of different elderly people on the medical and health care platform in the current time and historical period, and then determining the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type for each elderly person based on the training image information, and then Then, based on the historical activity types, historical activity amounts and body parameter information, the body parameter change standards corresponding to each elderly person performing different activity types and amounts during the historical period are determined. Then, based on the body parameter change standards, the body parameter change information corresponding to the current activity type and current activity amount of the elderly at different time nodes in the current time is determined. Then, based on the body parameter change information, the parameter data of the current time in the body parameter information is updated in real time to obtain updated body parameter information. The staff makes timely adjustments to the subsequent rehabilitation training of each elderly person based on the real-time updated body health parameter data, which not only achieves the effect of protecting the health of the elderly, but also improves the real-time and accuracy of the elderly's body parameter data.
[0056] The following is an introduction to a data management system for a medical and health care platform provided in an embodiment of the present application. The data management system for the medical and health care platform described below and the data management method for the medical and health care platform described above can be referred to each other. Please refer to Figure 2 , Figure 2 : is a structural diagram of a data management system 20 for a medical and health care platform provided in an embodiment of the present application, including: The information acquisition module 21 is used to acquire training image information and body parameter information. The training image information is the image information corresponding to different elderly people performing rehabilitation training in the current time and historical period. The body parameter information is the body parameter information of different elderly people on the medical and health care platform in the current time and historical period. An activity determination module 22 is used to determine the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type of each elderly person based on the training image information; The standard determination module 23 is used to determine the physical parameter change standard corresponding to each elderly person performing different activity types and different activity amounts in the historical period according to the historical activity types, historical activity amounts and physical parameter information; The parameter determination module 24 is used to determine the body parameter change information corresponding to the current activity type and current activity amount of the elderly at different time points in the current time according to the body parameter change standard; The data updating module 25 is used to update the parameter data of the current time in the body parameter information in real time based on the body parameter change information to obtain updated body parameter information.
[0057] In a possible implementation of the embodiment of the present application, the activity determination module 22 is specifically used to determine the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type of each elderly person based on the training image information: Determine the historical training image and the current training image of each elderly person according to the training image information; Determine a historical rehabilitation training plan and a historical target achievement status corresponding to the historical rehabilitation training plan based on the historical training images, wherein the historical rehabilitation training plan is a rehabilitation training plan corresponding to the time node of the historical training image, and the historical target achievement status includes the target achievement status of the action type of the historical activity corresponding to the historical rehabilitation training plan and the target achievement status of the historical activity amount; create a rehabilitation training model, and input the historical training images, the historical rehabilitation training plan and the target achievement status into the rehabilitation training model according to the time node for training, so as to obtain a trained rehabilitation training model; Input the current training image into the rehabilitation training model for recognition, and obtain the current target achievement status corresponding to the current training image; Based on the historical target-reaching status and the current target-reaching status, the historical activity type, the current activity type, the historical activity amount corresponding to the historical activity type, and the current activity amount corresponding to the current activity type are determined for each elderly person.
[0058] In another possible implementation of the embodiment of the present application, the activity determination module 22 is used to determine the historical rehabilitation training plan and the historical target achievement status corresponding to the historical rehabilitation training plan based on the historical training image, specifically for: Perform image clarity analysis on historical training images to determine whether there are unclear image points in the historical training images. If so, perform 3D simulation processing based on the historical training images to obtain training 3D images, convert the training 3D images into training 3D videos according to preset observation angles and preset action change rules, and perform visual frame acquisition on the training 3D videos to obtain training image visual frames; Analyze and process the visual frames of the training images to obtain map points of the training images; Determine the coordinate information and training descriptor information corresponding to each image feature point in the historical training image based on the training image map points; Based on the image feature points, a multi-dimensional spatial data search is performed on the training images in the preset training image library to obtain a training image set, where the preset training image library is used to store the training images taken by different elderly people when they perform historical rehabilitation training plans; Corresponding the coordinate information to the corresponding coordinate position of each training image in the training image set, respectively, to obtain contrast descriptor information, where the contrast descriptor information is used to represent the descriptor information corresponding to the coordinate information of each training image in the training image set; Perform matrix comparison on the descriptors in the training descriptor information and the descriptors in the comparison descriptor information to obtain similarity ratio information; Based on the similarity ratio information, the mean similarity ratio of the descriptors is determined, and it is judged whether the mean similarity ratio of the descriptors meets the preset similarity ratio condition. If so, the historical rehabilitation training plan of the historical training images and the historical achievement status corresponding to the historical rehabilitation training plan are determined based on the training labels in the training image set.
[0059] In another possible implementation of the embodiment of the present application, the system 20 further includes: a data sorting module, a vector extraction module, a data processing module and a standard updating module, wherein: A data sorting module is used to determine the time series length of each elderly person when performing different types of activities and different amounts of activities, and to sort the body parameter change standards unsupervisedly based on the time series length, activity type and activity amount to obtain the first training matrix data; A vector extraction module is used to input the first training matrix data into the trained feature extraction model to perform vector feature extraction, obtain the number of training feature dimensions, and perform data combination processing on the obtained number of training feature dimensions and the first training matrix data to generate second training matrix data; A data processing module is used to process the data contained in the second training matrix data to obtain rehabilitation training data, and input the obtained rehabilitation training data into a preset algorithm model for data calculation to generate future physical parameter change standards corresponding to different activity amounts of different activity types performed by each elderly person in a preset time period in the future; The standard update module is used to determine whether the future body parameter change standard and the body parameter change standard meet the preset difference range condition. If not, the body parameter change standard is updated based on the future body parameter change standard to obtain the updated body parameter change standard.
[0060] In another possible implementation of the embodiment of the present application, when the vector extraction module inputs the first training matrix data into the trained feature extraction model to extract vector features and obtains the number of training feature dimensions, it is specifically used to: Determine the activity type, activity amount and body parameter change information of each elderly person during the rehabilitation training program based on the first training matrix data; The activity type, activity amount and body parameter change information are respectively input into the feature extraction model for vector extraction, so as to obtain a category feature vector corresponding to the activity type, a data feature vector corresponding to the activity amount and a parameter feature vector corresponding to the body parameter change information; The number of category feature vectors, data feature vectors and parameter feature vectors is counted to obtain the number of training feature dimensions.
[0061] In another possible implementation of the embodiment of the present application, when the vector extraction module combines the obtained number of training feature dimensions with the first training matrix data to generate the second training matrix data, it is specifically used to: Integrate the number of training feature dimensions with the first training matrix data to generate training dimension matrix data; Conduct basic data distribution exploration on the training dimension matrix data to obtain the relative periodicity of changes in physical parameters of each elderly person during rehabilitation training, and determine the length of the time period based on the relative periodicity; Perform supervised time series data sorting on the training dimension matrix data based on the time period length to obtain the training prediction matrix data; Based on the training prediction matrix data, the changing trend of the body parameters of each elderly person performing different types and amounts of activities in a future preset time period is predicted to generate the second training matrix data.
[0062] In another possible implementation of the embodiment of the present application, the system 20 further includes: an actual standard acquisition module and a standard recovery module, wherein: The actual standard acquisition module is used to obtain the actual physical parameter change standard of each elderly person within a preset time period in the future after performing the current activity type and current activity amount; The standard recovery module is used to perform denormalization processing on the future body parameter change standard based on the actual body parameter change standard, and restore the future body parameter change standard to the actual body parameter change standard.
[0063] The present application embodiment provides an electronic device, such as Figure 3 As shown, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, Figure 3The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.
[0064] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the embodiments of the present application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
[0065] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0066] The memory 303 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.
[0067] The memory 303 is used to store application code for executing the solution of the embodiment of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above method embodiment.
[0068] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0069] A computer-readable storage medium provided in an embodiment of the present application is introduced below. The computer-readable storage medium described below and the method described above can be referenced to each other.
[0070] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the data management method for a medical and health care platform as described above are implemented.
[0071] Since the embodiments of the computer-readable storage medium part and the embodiments of the method part correspond to each other, the embodiments of the computer-readable storage medium part refer to the description of the embodiments of the method part.
[0072] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0073] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A data management method for a medical and health care platform, characterized in that: include: Acquire training image information and body parameter information, wherein the training image information is image information corresponding to different elderly people performing rehabilitation training in the current time and historical period, and the body parameter information is body parameter information of different elderly people on the medical and health care platform in the current time and historical period; Determine, based on the training image information, the historical activity type, the current activity type, the historical activity amount corresponding to the historical activity type, and the current activity amount corresponding to the current activity type for each of the elderly; Determine, according to the historical activity types, the historical activity amounts and the physical parameter information, the physical parameter change standards corresponding to each of the elderly performing different activity types and different activity amounts within the historical period; Determine, according to the body parameter change standard, the body parameter change information corresponding to the current activity type and the current activity amount of the elderly at different time points in the current time; Based on the body parameter change information, the parameter data of the current time in the body parameter information is updated in real time to obtain updated body parameter information.
2. A data management method for a medical and health care platform according to claim 1, characterized in that: The determining of the historical activity type, the current activity type, the historical activity amount corresponding to the historical activity type, and the current activity amount corresponding to the current activity type of each elderly person based on the training image information includes: Determine a historical training image and a current training image for each of the elderly according to the training image information; Determine a historical rehabilitation training plan and a historical target achievement status corresponding to the historical rehabilitation training plan based on the historical training image, wherein the historical rehabilitation training plan is a rehabilitation training plan corresponding to a time node of the historical training image, and the historical target achievement status includes the target achievement status of the action of the historical activity type corresponding to the historical rehabilitation training plan and the target achievement status of the historical activity amount; Creating a rehabilitation training model, and inputting the historical training images, the historical rehabilitation training plan, and the target achievement status into the rehabilitation training model according to time nodes for training, to obtain a trained rehabilitation training model; Inputting the current training image into the rehabilitation training model for recognition, and obtaining a current target achievement status corresponding to the current training image; Based on the historical target-reaching status and the current target-reaching status, the historical activity type, the current activity type, the historical activity amount corresponding to the historical activity type, and the current activity amount corresponding to the current activity type are determined for each of the elderly.
3. A data management method for a medical and health care platform according to claim 2, characterized in that: The determining of a historical rehabilitation training plan and a historical target achievement status corresponding to the historical rehabilitation training plan based on the historical training image includes: Performing image clarity analysis on the historical training images to determine whether there are unclear image points in the historical training images; if so, performing three-dimensional simulation processing based on the historical training images to obtain training three-dimensional images; converting the training three-dimensional images into training three-dimensional videos according to preset observation angles and preset action change rules; and performing visual frame acquisition on the training three-dimensional videos to obtain training image visual frames; Analyzing and processing the training image visual frame to obtain training image map points; Determine the coordinate information and training descriptor information corresponding to each image feature point in the historical training image based on the training image map point; Performing a multi-dimensional spatial data search on training images in a preset training image library based on the image feature points to obtain a training image set, wherein the preset training image library is used to store training images taken by different elderly people when they perform the historical rehabilitation training plan; Corresponding the coordinate information to the corresponding coordinate position of each training image in the training image set, respectively, to obtain contrast descriptor information, wherein the contrast descriptor information is used to represent the descriptor information corresponding to the coordinate information of each training image in the training image set; Perform matrix comparison on the descriptors in the training descriptor information and the descriptors in the comparison descriptor information to obtain similarity ratio information; Based on the similarity ratio information, a descriptor similarity ratio mean is determined, and it is judged whether the descriptor similarity ratio mean satisfies a preset similarity ratio condition; if so, a historical rehabilitation training plan of the historical training images and a historical achievement status corresponding to the historical rehabilitation training plan are determined based on the training labels in the training image set.
4. A data management method for a medical and health care platform according to claim 1, characterized in that: The step of determining the physical parameter change standard corresponding to each elderly person performing different activity types and different activity amounts in the historical period according to the historical activity types, the historical activity amounts and the physical parameter information further includes: Determine the time series length when each of the elderly performs different activity types and different activity amounts, and perform unsupervised time series data sorting on the physical parameter change standard based on the time series length, the activity type and the activity amount to obtain first training matrix data; Inputting the first training matrix data into the trained feature extraction model to perform vector feature extraction to obtain the number of training feature dimensions, and combining the obtained number of training feature dimensions with the first training matrix data to generate second training matrix data; Processing the data contained in the second training matrix data to obtain rehabilitation training data, and inputting the obtained rehabilitation training data into a preset algorithm model for data calculation to generate future physical parameter change standards corresponding to different activity amounts of different activity types performed by each elderly person in a future preset time period; Determine whether the future body parameter change standard and the body parameter change standard meet a preset difference range condition; if not, update the body parameter change standard based on the future body parameter change standard to obtain an updated body parameter change standard.
5. A data management method for a medical and health care platform according to claim 4, characterized in that: The step of inputting the first training matrix data into a trained feature extraction model to extract vector features and obtain the number of training feature dimensions includes: Determine, based on the first training matrix data, the activity type, activity amount, and body parameter change information of each of the elderly during the execution of the rehabilitation training plan; Inputting the activity type, activity amount and body parameter change information into the feature extraction model respectively for vector extraction, and obtaining a category feature vector corresponding to the activity type, a data feature vector corresponding to the activity amount and a parameter feature vector corresponding to the body parameter change information; The category feature vector, the data feature vector, and the parameter feature vector are statistically analyzed to obtain the number of training feature dimensions.
6. A data management method for a medical and health care platform according to claim 4, characterized in that: The step of combining the obtained number of training feature dimensions with the first training matrix data to generate second training matrix data includes: Integrate the training feature dimension quantity with the first training matrix data to generate training dimension matrix data; Performing basic data distribution exploration on the training dimension matrix data, obtaining the relative periodicity law of changes in physical parameters of each elderly person during rehabilitation training, and determining the length of the time period based on the relative periodicity law; Performing supervised time series data sorting on the training dimension matrix data based on the time period length to obtain training prediction matrix data; Based on the training prediction matrix data, the changing trend of the physical parameters of each of the elderly people performing different types and amounts of activities in a future preset time period is predicted to generate second training matrix data.
7. A data management method for a medical and health care platform according to claim 4, characterized in that: The obtained rehabilitation training data is input into a preset algorithm model for data calculation to generate future physical parameter change standards corresponding to different activity amounts of different activity types performed by each elderly person in a future preset time period, and then further includes: Obtaining actual physical parameter change standards within the future preset time period after each elderly person performs the current activity type and the current activity amount; The future body parameter change standard is denormalized based on the actual body parameter change standard to restore the future body parameter change standard to the actual body parameter change standard.
8. A data management system for a medical and health care platform, characterized in that: include: An information acquisition module is used to acquire training image information and body parameter information, wherein the training image information is image information corresponding to different elderly people performing rehabilitation training in the current time and historical period, and the body parameter information is body parameter information of different elderly people on the medical and health care platform in the current time and historical period; An activity determination module, used to determine the historical activity type, current activity type, historical activity amount corresponding to the historical activity type, and current activity amount corresponding to the current activity type of each of the elderly based on the training image information; A standard determination module, used to determine the physical parameter change standard corresponding to each elderly person performing different activity types and different activity amounts within the historical period according to the historical activity types, the historical activity amounts and the physical parameter information; A parameter determination module, configured to determine, according to the body parameter change standard, body parameter change information corresponding to the current activity type and the current activity amount of the elderly at different time points in the current time; The data updating module is used to update the parameter data of the current time in the body parameter information in real time based on the body parameter change information to obtain updated body parameter information.
9. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a data management method for a medical and health care platform as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and execute a data management method for a medical and health care platform as described in any one of claims 1 to 7.
