Visual ankle pump motion data effect acquisition method and system

Abstract

The invention discloses a visual ankle pump movement data effect acquisition method and system. The method comprises the steps of acquiring vital sign data, lower limb movement data and lower limb blood flow data when a user performs ankle pump movement through an ankle pump movement device; analyzing the blood flow data, associating the lower limb blood flow data with the lower limb movement data, and generating a three-dimensional blood flow visualization model to visually display the real-time blood flow dynamic change condition; according to the vital sign data, the lower limb movement data and the lower limb blood flow data, calculating a movement intensity index for evaluating the movement intensity effect in the ankle pump movement process of the user; and packaging the vital sign data, the lower limb movement data, the lower limb blood flow data and the movement intensity index into an ankle pump movement effect data set. By utilizing the embodiment of the invention, the data set for comprehensively evaluating the exercise effect can be constructed, and complex physiological changes are converted into information easy to understand through effective data analysis and visualization means, so that the exercise effect and safety are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to a method and system for collecting visual ankle pump exercise data effects. Background Art

[0002] With the increasing attention of people to a healthy lifestyle and sports science, ankle pump exercise, as an important exercise method for lower limb blood circulation, has gradually received wide attention. Ankle pump exercise not only helps to enhance the strength and endurance of lower limb muscles, but also can effectively improve blood circulation and promote venous return, and has a significant effect on preventing and treating diseases such as lower limb venous insufficiency and deep vein thrombosis. Traditional exercise monitoring methods mainly rely on basic parameters such as heart rate, steps, and activity time. Although these methods can provide a certain assessment of exercise intensity, they often cannot comprehensively reflect the physiological changes during exercise, especially the direct impact of lower limb blood flow dynamics on exercise effects. Therefore, there are certain limitations in the prior art for real-time monitoring and evaluating the effects of ankle pump exercise. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for collecting visual ankle pump exercise data effects to solve the deficiencies in the prior art, be able to construct a dataset for comprehensively evaluating exercise effects, and through effective data analysis and visualization means, convert complex physiological changes into easily understandable information, and improve the effectiveness and safety of exercise.

[0004] An embodiment of the present application provides a method for collecting visual ankle pump exercise data effects, and the method includes:

[0005] Collecting vital sign data, lower limb movement data, and lower limb blood flow data of a user during ankle pump exercise through an ankle pump exercise device;

[0006] Analyzing the blood flow data, correlating the lower limb blood flow data with the lower limb movement data, and generating a three-dimensional blood flow visualization model to visually display the real-time blood flow dynamic changes;

[0007] Calculating an exercise intensity index for evaluating the exercise intensity effect of the user during ankle pump exercise according to the vital sign data, the lower limb movement data, and the lower limb blood flow data;

[0008] Packing the vital sign data, the lower limb movement data, the lower limb blood flow data, and their corresponding exercise intensity indexes into an ankle pump exercise effect dataset to achieve the collection of visual ankle pump exercise data effects.

[0009] Optionally, analyze the blood flow data, correlate the lower limb blood flow data with the lower limb movement data, and generate a three-dimensional blood flow visualization model to visually display the real-time dynamic changes in blood flow, including:

[0010] Use a kinematic algorithm to convert the lower limb movement data into joint angles and positions. Combine the joint angle and position data, and use computer graphics technology to generate a three-dimensional bone model of the lower limb;

[0011] According to the preset local regions of the lower limb, map the blood flow characteristics extracted from the lower limb blood flow data to the corresponding voxel space to form a three-dimensional voxel cloud, where each voxel represents the local blood flow characteristics within the monitoring volume;

[0012] Couple the three-dimensional bone model and the three-dimensional voxel cloud spatially to ensure their alignment in the physical space. Adopt ray tracing combined with volume rendering technology to achieve realistic rendering of blood flow movement, obtain a three-dimensional blood flow visualization model, and use a dynamic particle tracking algorithm to simulate the movement of blood flow particles to visually display the real-time dynamic changes in blood flow.

[0013] Optionally, the calculation formula for the exercise intensity index is:

[0014]

[0015] where EII is the exercise intensity index, HR_avg is the average heart rate of the user during exercise, HR_rest is the resting heart rate of the user, HR_max is the maximum heart rate of the user during exercise, V_max is the instantaneous maximum value of the lower limb blood flow velocity during exercise, V_rest is the lower limb blood flow velocity in the resting state, f_i is the action frequency of the i-th action of the ankle pump exercise, w_i is the weight of the i-th action, and n is the type of action in the ankle pump exercise.

[0016] Optionally, the use of a kinematic algorithm to convert the lower limb movement data into joint angles and positions, combine the joint angle and position data, and use computer graphics technology to generate a three-dimensional bone model of the lower limb includes:

[0017] Use quaternions or direction cosine matrices to convert the lower limb movement data collected by the sensor into joint angles, and calculate the rotation matrix of each joint by fusing the accelerometer and gyroscope data;

[0018] Based on the joint angles, use forward kinematics to calculate the positions of the lower limb joints, and recursively calculate the positions of each joint in the three-dimensional space through the known bone lengths and joint angles;

[0019] Define the skeletal structure of the lower limb, which includes key joints such as the hip joint, knee joint, and ankle joint, and assign initial positions and connection relationships to each joint node;

[0020] Using computer graphics technology, build a three-dimensional skeletal model using the OpenGL or Unity graphics engine, apply the calculated joint positions and joint angles to the three-dimensional skeletal model, dynamically update the skeletal posture, and render the three-dimensional skeletal model onto the visualization interface in real time through the rendering pipeline of the graphics engine.

[0021] Optionally, mapping the blood flow characteristics extracted from the lower limb blood flow data to the corresponding voxel space according to the preset local regions of the lower limb to form a three-dimensional voxel cloud, including:

[0022] Extract key blood flow characteristics from the lower limb blood flow data for voxel attribute definition;

[0023] Divide the lower limb into multiple local regions and generate voxel grids for each local region in three-dimensional space;

[0024] Map the extracted key blood flow characteristics to the corresponding voxels, where the attribute value of each voxel is determined by the blood flow characteristics within its monitoring volume, and interpolation methods are used to process boundary voxels;

[0025] Integrate the voxel data of all local regions to form a complete three-dimensional voxel cloud.

[0026] Another embodiment of the present application provides a visualization ankle pump motion data effect acquisition system, and the system includes:

[0027] An acquisition module for acquiring vital sign data, lower limb motion data, and lower limb blood flow data when the user performs ankle pump motion through an ankle pump motion device;

[0028] A generation module for analyzing the blood flow data, correlating the lower limb blood flow data with the lower limb motion data, and generating a three-dimensional blood flow visualization model to visually display the real-time blood flow dynamic changes;

[0029] A calculation module for calculating a motion intensity index for evaluating the motion intensity effect of the user during the ankle pump motion according to the vital sign data, the lower limb motion data, and the lower limb blood flow data;

[0030] A packaging module for packaging the vital sign data, the lower limb motion data, the lower limb blood flow data, and their corresponding motion intensity indices into an ankle pump motion effect data set to achieve visualization of ankle pump motion data effects acquisition.

[0031] Another embodiment of the present application provides a storage medium, in which a computer program is stored. Wherein, the computer program is configured to execute the method described in any one of the above when running.

[0032] Another embodiment of the present application provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described in any one of the above.

[0033] Compared with the prior art, a method for collecting visual ankle pump exercise data effects provided by the present invention collects vital sign data, lower limb movement data, and lower limb blood flow data when a user performs ankle pump exercises through an ankle pump exercise device; analyzes the blood flow data, correlates the lower limb blood flow data with the lower limb movement data, and generates a three-dimensional blood flow visualization model to visually display the real-time dynamic changes in blood flow; calculates an exercise intensity index for evaluating the exercise intensity effect during the ankle pump exercise according to the vital sign data, lower limb movement data, and lower limb blood flow data; packages the vital sign data, lower limb movement data, lower limb blood flow data, and their corresponding exercise intensity indexes into an ankle pump exercise effect data set to achieve the collection of visual ankle pump exercise data effects, so as to be able to construct a data set for comprehensively evaluating exercise effects, and through effective data analysis and visualization means, convert complex physiological changes into easily understandable information, improving the exercise effect and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a hardware structure block diagram of a computer terminal for a method of collecting visual ankle pump exercise data effects provided by an embodiment of the present invention;

[0035] Figure 2 It is a flowchart of a method for collecting visual ankle pump exercise data effects provided by an embodiment of the present invention;

[0036] Figure 3 It is a structural diagram of a system for collecting visual ankle pump exercise data effects provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be construed as a limitation to the present invention.

[0038] An embodiment of the present invention first provides a method for collecting visual ankle pump exercise data effects. This method can be applied to an electronic device, such as a computer terminal, specifically, an ordinary computer, etc.

[0039] The following takes running on a computer terminal as an example to describe it in detail. Figure 1The block diagram of the hardware structure of a computer terminal for a method of collecting visual ankle pump motion data effects provided by an embodiment of the present invention. As Figure 1 shown, the computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the memory may include a non-volatile storage medium and an internal memory.

[0040] The non-volatile storage medium can store an operating system and computer programs. The computer programs include program instructions, and when the program instructions are executed, the processor can execute any method of collecting visual ankle pump motion data effects.

[0041] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0042] The internal memory provides an environment for the operation of the computer programs in the non-volatile storage medium. When the computer programs are executed by the processor, the processor can execute any method of collecting visual ankle pump motion data effects.

[0043] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 1 the structure shown in

[0044] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0045] See Figure 2 , an embodiment of the present invention provides a method of collecting visual ankle pump motion data effects, which may include the following steps:

[0046] S201, collect the vital sign data, lower limb motion data, and lower limb blood flow data of the user when performing ankle pump motion through an ankle pump motion device;

[0047] In this method, collecting the vital sign data, lower limb movement data, and lower limb blood flow data of the user during ankle pump exercise is a crucial step. The vital sign data usually includes the user's heart rate, blood oxygen saturation, and respiratory rate, etc. These data can reflect the user's physiological state during exercise and help evaluate the exercise intensity. The lower limb movement data involves the execution of the user's movements during ankle pump exercise, such as the frequency, duration, and posture of the movements, which are collected in real-time through high-precision sensors (such as accelerometers and gyroscopes) to effectively capture the dynamic changes of the lower limbs. The lower limb blood flow data is obtained through technologies such as photoplethysmography, which can provide real-time blood flow velocity and flow information, revealing the changes in lower limb blood circulation. These three types of data are interrelated and jointly provide a basis for subsequent exercise effect evaluation and visualization display.

[0048] The implementation of this method can not only comprehensively monitor the physiological state of the user during ankle pump exercise but also provide real-time feedback through data fusion and analysis, which helps the user understand their own exercise state and effect. Specifically, timely collection of vital sign, movement, and blood flow data can help the user identify whether there is excessive fatigue or other health risks during exercise, so as to adjust the exercise intensity, frequency, and duration to ensure the safety and effectiveness of the exercise. In addition, integrating these data into a visualization platform enables the user to intuitively observe the dynamic changes in lower limb blood flow, enhancing the perception and understanding of the exercise effect and further increasing the enthusiasm and participation in exercise.

[0049] In the specific implementation process, the user first wears an ankle pump exercise device equipped with multiple sensors, which can collect the user's physiological data in real-time. Before starting the exercise, the system will first record the user's resting state for subsequent data analysis. When the user starts ankle pump exercise, the built-in accelerometer and gyroscope in the device will synchronously capture the lower limb movement data, including joint angle changes, movement frequency, etc., to ensure accurate monitoring of each movement. At the same time, through advanced blood flow monitoring technology, the device will obtain the lower limb blood flow data in real-time, such as blood flow velocity and its fluctuations. For example, when the user starts ankle pump exercise, the sensor may record that the user's heart rate rises from 60 BPM (resting state) to 120 BPM, showing significant physiological changes, and the lower limb movement frequency may reach 30 times per minute. These data will be summarized in real-time in the background.

[0050] After the data collection is completed, the system will perform a correlation analysis on the collected vital sign data, lower limb movement data, and blood flow data, and generate an exercise intensity index (EII) to quantify the user's exercise intensity. The user can view a three-dimensional model through a visual interface to display the dynamic blood flow changes in the lower limbs during exercise. This not only allows the user to have an intuitive understanding of their exercise effect but also encourages them to continue to persevere or adjust their exercise plan in future workouts. Through this method, both the scientific nature of exercise is improved, and a personalized health management tool is provided for the user, thus achieving better exercise results.

[0051] S202, analyze the blood flow data, correlate the lower limb blood flow data with the lower limb movement data, and generate a three-dimensional blood flow visualization model to visually display the real-time blood flow dynamic changes;

[0052] In this method, the core of analyzing the blood flow data lies in correlating the lower limb blood flow data with the lower limb movement data to generate a three-dimensional blood flow visualization model. This step first requires understanding and integrating the lower limb movement data to dynamically display the blood flow changes corresponding to different movements during exercise. Through data fusion, it can reveal how blood flows in the lower limbs during the ankle pump exercise, providing visual feedback on the exercise effect for the user. The generation of this three-dimensional model not only includes the exercise data but also takes into account the cadaveric conditions and real-time feedback, making the visualization result more realistic and interactive, and enabling the user to more intuitively understand the impact of exercise on blood flow.

[0053] The implementation of this step is of great significance for improving the user's exercise experience and effect monitoring. By visually displaying the real-time blood flow dynamic changes, the user can clearly see the change trend and distribution state of blood flow when performing the ankle pump exercise. This informative visual representation will help the user identify the state of blood flow during exercise, thereby optimizing their exercise strategy and adjusting the exercise intensity to achieve the best effect. In addition, with the help of the display of the three-dimensional model, the user's understanding of exercise physiology will be deepened, thus maintaining higher enthusiasm and self-management ability in future workouts.

[0054] Specifically, the lower limb movement data can be converted into joint angles and positions using a kinematic algorithm, and combined with the joint angle and position data, a three-dimensional bone model of the lower limb can be generated using computer graphics technology;

[0055] In this step, a kinematic algorithm is used to parse the collected lower limb motion data so as to convert it into joint angles and positions. With the help of quaternions or direction cosine matrices, the rotation states of each joint of the lower limb can be accurately calculated. Based on the measured acceleration and angular velocity, the system can obtain the motion information of each joint in real time and calculate the positions of each joint of the lower limb in three-dimensional space through forward kinematics, thereby generating a dynamically updated three-dimensional skeletal model.

[0056] This step means that the motion data will be transformed into a vivid skeletal model through a scientific kinematic analysis process, making it not just abstract data but a visual representation. This model can dynamically reflect the user's motion pattern and joint angle changes, providing the user with a more intuitive feedback on their motion state. At the same time, this skeletal model can provide a structural basis for the visualization of subsequent blood flow data, enhancing the effectiveness of comprehensive data analysis.

[0057] In the specific implementation, first, the system combines the lower limb motion data collected by the sensor and uses the quaternion method to convert it into the rotation angles of the joints. This step calculates the rotation matrix of each joint through the data fusion of the accelerometer and gyroscope. Then, using the principle of forward kinematics, these joint angle information is associated with the preset bone lengths, and the positions of each joint in three-dimensional space are gradually derived. At this time, the system defines the skeletal structure of the lower limb, focusing on key nodes such as the hip joint, knee joint, and ankle joint, assigns initial positions to each node and establishes connection relationships. Finally, using computer graphics technologies such as OpenGL or Unity engine, these dynamically calculated joint positions and angles are applied to the three-dimensional skeletal model to update the skeletal model in real time to ensure its match with the user's motion state.

[0058] Among them, the lower limb motion data collected by the sensor can be converted into joint angles using quaternions or direction cosine matrices, and the rotation matrix of each joint is calculated by fusing the data of the accelerometer and gyroscope;

[0059] The main purpose of this process is to convert the original lower limb motion data collected by the motion sensor into joint angles that are more suitable for analysis. This is achieved through the mathematical methods of using quaternions or direction cosine matrices, among which quaternions have better numerical stability and efficiency. By fusing the data from the accelerometer and gyroscope, the system can accurately calculate the rotation matrix of each joint, which can provide a reliable basis for subsequent kinematic analysis.

[0060] The implementation of this step has greatly improved the accuracy and effectiveness of motion data, laying a foundation for the structured analysis of lower limb movements. Through precise joint angles and rotation matrices, it is possible to better understand the specific performance of each joint during movement, and also make the subsequent generation of the skeletal model more scientific and reasonable. Accurate joint data can provide users with more intuitive motion feedback, thereby enhancing the user's motion experience.

[0061] In the specific implementation process, first, the system collects acceleration and angular velocity data from the user's lower limb motion sensors. Subsequently, quaternions and direction cosine matrices are used to calculate the rotation angles of each joint. For example, the acceleration information collected by the sensor can be used to determine the initial direction of joint movement. Combining with the data of the gyroscope, the system can construct a complete rotation matrix. These rotation matrices are obtained through a series of linear transformations and matrix multiplications. On this basis, by applying the multiplication rules of quaternions, the calculation results are further optimized to improve accuracy. Finally, all calculation results are stored in the system for subsequent steps to use, thus ensuring that the generated motion model has high precision.

[0062] Based on the joint angles, use forward kinematics to calculate the positions of the lower limb joints. Through the known bone lengths and joint angles, recursively calculate the positions of each joint in three-dimensional space;

[0063] In this step, the system calculates the spatial positions of the lower limb joints using the principle of forward kinematics based on the joint angle information obtained in the first step. This process requires the known bone length data as a basis, and recursively calculates the accurate positions of the lower limb joints in three-dimensional space step by step, thereby creating a complete set of model data. This method determines the spatial coordinates of each joint by using a relative coordinate system, providing the necessary data support for the subsequent generation of a three-dimensional skeletal model.

[0064] Through the calculation of forward kinematics, the system can generate a detailed lower limb motion model, making the positions of each joint in three-dimensional space clear. This not only provides a structural basis for the subsequent construction of the skeletal model, but also enables in-depth motion analysis. Through the precise calculation of joint positions, the key postures and dynamic changes of the user during movement are captured, realizing more scientific motion monitoring.

[0065] In the specific implementation process, the system will first define the skeletal structure of the lower limbs, including the femur, tibia, etc., and distinguish the relative positions of each joint node. Then, with the help of known joint angles and bone lengths, the forward kinematics algorithm is used to dynamically calculate the positions of each joint. For example, setting the hip joint as the first joint, the position of the knee joint is calculated through its position and angle, and then the position and angle of the knee joint are used to calculate the position of the ankle joint. This process is recursively applied to all joints, and the calculation of each joint depends on the previous joint, finally generating a series of three-dimensional coordinate data. All calculation results will be integrated into a three-dimensional space framework, laying a solid foundation for the implementation of subsequent steps.

[0066] Define the skeletal structure of the lower limbs, where the skeletal structure includes key nodes such as the hip joint, knee joint, and ankle joint, and assign initial positions and connection relationships to each joint node;

[0067] In this step, the system first needs to define a complete skeletal structure of the lower limbs, which will include key joint nodes such as the hip joint, knee joint, and ankle joint. After assigning initial positions to each joint node, the system needs to design the connection relationships between various parts of the limb when constructing the entire skeletal mesh, so as to form a complete three-dimensional skeletal model that can move. This structured design not only ensures the accuracy of the motion model but also lays a foundation for subsequent motion simulations.

[0068] The significance of this step is that through the accurate definition of the skeletal structure, the system can generate a three-dimensional model with a rigorous logic and easy operation, making subsequent visual displays and data analyses more intuitive and effective. Reasonable initial positions and connection relationships can improve the simulation effect of the model, making the motion interaction relationships between joints more realistic during dynamic simulations and enhancing the user's understanding and experience.

[0069] In the specific implementation, first, the system defines the basic skeletal structure of the lower limbs according to the joint positions calculated in the previous steps. Starting from the hip joint as the initial node, the system will set corresponding initial positions for each joint and mark the connection relationships between each joint. For example, the hip joint is connected to the knee joint, and the knee joint is connected to the ankle joint. To ensure the naturalness of the model during movement, the system will define appropriate motion ranges and rotation axes for each joint. All this information will be integrated into the system for use in subsequent steps, forming a refined motion model.

[0070] Using computer graphics technology, build a three-dimensional skeletal model using OpenGL or Unity graphics engines, apply the calculated joint positions and joint angles to the three-dimensional skeletal model, dynamically update the skeletal posture, and through the rendering pipeline of the graphics engine, render the three-dimensional skeletal model onto the visualization interface in real time.

[0071] In this step, the system will utilize modern computer graphics technology and combine with graphics engines such as OpenGL or Unity to construct and optimize the three-dimensional skeletal model of the lower limbs. By applying the joint position and angle information calculated previously to the skeletal model, the system can dynamically update the skeletal posture, enabling the perfect presentation of the real-time performance of the movement. The rendering pipeline in this process will ensure the smooth and realistic visual effect of the model.

[0072] The implementation of this step means that users can intuitively see the dynamic changes in the movement of the lower limbs, greatly enhancing the visualization effect of movement monitoring. Through the real-time rendered three-dimensional skeletal model, users can more clearly understand their movement patterns and posture adjustments, providing first-hand visual data support for movement improvement, and further promoting scientific movement management and effect evaluation.

[0073] In the specific implementation process, first, based on the defined skeletal structure, the system will use the OpenGL or Unity graphics engine to build the basic framework of the three-dimensional skeletal model. Then, the joint position and angle information calculated previously will be applied to different parts of the model as needed. In the dynamic update stage, with the help of the rendering pipeline of the graphics engine, the system can achieve real-time rendering and animation effects of the skeletal model. For example, when the user performs ankle pump exercises, the system will continuously update the joint angles and positions according to the sensor data, generate the current skeletal posture in real time, and display this effect on the visualization interface through the graphics engine. The whole process is not only smooth but also efficient, enabling users to obtain instant feedback when participating in the movement and further improving the movement performance.

[0074] According to the preset local regions of the lower limbs, map the blood flow characteristics extracted from the lower limb blood flow data to the corresponding voxel space to form a three-dimensional voxel cloud, where each voxel represents the local blood flow characteristics within the monitoring volume;

[0075] In this step, by extracting key blood flow characteristics from the lower limb blood flow data, the system can map this information to the voxels of the preset local regions to form a three-dimensional voxel cloud. Each voxel represents the local blood flow characteristics, and the attribute value of the voxel is determined by the blood flow characteristics within its monitoring volume, ensuring the accuracy and authenticity of the mapping.

[0076] By mapping the blood flow characteristics to the three-dimensional voxel cloud, more detailed blood flow analysis can be achieved. This meticulous perspective enables users to observe the blood flow changes in each local region of the lower limbs under different movement states. The three-dimensional voxel cloud generated in this way provides rich information for visualization, helping users understand the relationship between blood flow and movement, and thus making more scientific movement adjustments and optimizations.

[0077] Specifically, first, the lower limbs are divided into several local regions, such as the thigh, knee, calf, etc., and corresponding voxel grids are generated for each region. Next, key blood flow characteristics, such as blood flow velocity and blood flow direction, are extracted from the lower limb blood flow data, and these characteristics are used to define the attributes of each voxel. Then, interpolation methods are used to process the boundary voxels to ensure a natural and smooth transition of the voxel cloud between regions. By integrating the voxel data of all local regions, a complete and continuous three-dimensional voxel cloud is finally formed, providing a basis for subsequent visual display.

[0078] Among them, key blood flow characteristics can be extracted from the lower limb blood flow data for use in defining the attributes of voxels;

[0079] In this step, the goal of the system is to extract blood flow characteristics that are crucial for evaluating the exercise effect from the collected lower limb blood flow data. These characteristics may include key parameters such as the instantaneous blood flow velocity, blood flow volume, and blood flow pressure of the lower limbs. By analyzing the changes in blood flow velocity at different time points and its relationship with the exercise state, it is possible to identify which blood flow characteristics have the greatest impact on the exercise effect during the ankle pump exercise, and use these characteristics as the basic data for voxel attributes. This process may use statistical analysis methods, signal processing techniques, etc. to ensure that the extracted blood flow characteristics are accurate and representative.

[0080] The process of extracting key blood flow characteristics is crucial for voxel attribute definition because it directly affects the construction quality and visualization effect of the subsequent three-dimensional voxel cloud. Accurate blood flow characteristics can help users better understand the blood circulation status under different exercise states and provide a scientific basis for exercise optimization. This kind of visual display not only increases users' understanding of the impact of exercise on the body, but also provides strong data support for rehabilitation and health monitoring in the medical field, and has important application value.

[0081] In the specific implementation process, first, the system performs data cleaning on the original blood flow data obtained during the ankle pump exercise to remove noise and outliers. For example, a filter is used to remove low-frequency noise, and the instantaneous blood flow velocity of the lower limbs is extracted through higher-frequency signals. Then, the system will perform time series analysis on the cleaned data, segment the signal using the sliding window method, and calculate the average blood flow velocity and other key parameters within each segment. Next, the system will compare different exercise stages (such as the starting stage, high-intensity stage, and ending stage), identify the most representative blood flow characteristics, and combine these characteristics with information such as heart rate data and lower limb movement forms during exercise for subsequent mapping into voxels. This series of data extraction and analysis ensures that the system provides a scientific basis for the attribute definition required for subsequent voxel cloud construction.

[0082] The lower limb is divided into multiple local regions, and a voxel grid is generated for each local region in three-dimensional space;

[0083] In this step, the system divides the lower limb into multiple local regions according to anatomical structures and the needs of the motion scenario, such as parts like the thigh, knee, calf, and ankle joint. Each region will be regarded as an independent voxel grid to facilitate subsequent blood flow feature mapping. The voxel grid is the basic building unit in three-dimensional space, similar to three-dimensional pixels, and each voxel will carry certain physical properties. By reasonably dividing the regions and generating the grid, the system can more accurately simulate the anatomical structure and blood flow distribution of the lower limb, ensuring that the overall performance and visualization effect of the voxel cloud are more realistic.

[0084] The step of dividing the lower limb into multiple local regions and generating the voxel grid significantly improves the spatial resolution of the blood flow data, making the subsequent feature mapping more refined. Through accurate partitioning, the system can better represent the local blood flow features in three-dimensional space, thereby helping users understand the physiological changes of different parts during movement. This meticulous division not only improves the visualization effect of the data but also helps medical researchers conduct more in-depth physiological and sports biomechanics research.

[0085] In the specific implementation process, first, the system will divide the lower limb into multiple local regions including the thigh, knee joint, calf, and ankle joint according to the anatomical structure of the lower limb. To achieve scientific voxel grid generation, the system will use basic shapes such as cubes or hexahedrons to construct the voxel grid according to the actual size and shape of each region. The size of each grid can be adjusted according to the different regional characteristics of the lower limb to ensure that smaller voxels are used in important parts (such as near joints) to obtain higher resolution. After generating the voxel grid, the system will assign position coordinates to each voxel so that it can be correctly represented in three-dimensional space. Thereafter, the system will prepare to map the key blood flow features to these voxels to form an overall three-dimensional voxel cloud, providing a basis for subsequent data integration.

[0086] Map the extracted key blood flow features to the corresponding voxels, where the attribute value of each voxel is determined by the blood flow features within its monitoring volume, and interpolation methods are used to process the boundary voxels;

[0087] In this step, the system will correspond the key blood flow features extracted in the previous step with the generated voxel grid to ensure that the attribute values (such as blood flow velocity, blood flow volume, etc.) of each voxel can accurately reflect the blood flow features it monitors. This process requires assigning values to the voxels and considering the spatial relationship between voxels, and interpolation methods are used to process the boundary voxels to ensure that the blood flow features transition naturally and smoothly between different voxels. Through this operation, the system can generate a three-dimensional voxel cloud containing rich blood flow dynamic information, providing accurate data support for visualization display.

[0088] The process of mapping key blood flow characteristics to corresponding voxels is a crucial step in achieving a high-quality three-dimensional voxel cloud, which can present dynamic physiological data in a spatial form. This mapping relationship not only enhances the realism of the visualization effect but also enables users to intuitively understand the blood flow characteristics and their dynamic changes in different parts. This is of great reference value for the monitoring and evaluation of exercise effects, especially in health management and rehabilitation therapy.

[0089] In the specific implementation process, the system first assigns corresponding blood flow characteristic values to each voxel, using the previously extracted key blood flow characteristics. To achieve accurate mapping, the system takes into account the spatial volume monitored by different voxels and calculates the average blood flow characteristic value within each voxel. For example, within a voxel, if the monitored blood flow velocity is 0.5 m / s, the value of the voxel is set to 0.5. For boundary voxels, since they are greatly affected by neighboring voxels, the system uses the method of linear interpolation, based on the average attribute values of adjacent voxels, to ensure a natural transition of blood flow characteristics at the boundary. After the assignment is completed, the system integrates the voxel attributes of each local area into a complete three-dimensional voxel cloud, and then prepares for the final visualization effect. Through this series of steps, the generated three-dimensional voxel cloud will accurately reflect the dynamic blood flow characteristics of the lower limb during the ankle pump exercise, ensuring that users obtain high-quality visual information.

[0090] Integrate the voxel data of all local areas to form a complete three-dimensional voxel cloud.

[0091] In this step, the system integrates the voxel data previously generated for each local area (such as the thigh, knee, calf, and ankle joint) to form a complete three-dimensional voxel cloud. This process requires merging the voxel grids of each local area and ensuring the consistency and integrity of the data during the merging process. The final three-dimensional voxel cloud will provide users with a comprehensive visualization display of the blood flow characteristics of the lower limb.

[0092] Integrating the voxel data of local areas is a key step in generating the final three-dimensional voxel cloud. By combining the data of each area, the system can present the overall blood flow dynamic characteristics of the lower limb during exercise to users. This integration not only enhances the visualization effect, allowing users to observe the blood flow state of the lower limb in a unified view, but also provides basic support for subsequent analysis and research, especially in applications in the medical, exercise physiology, and rehabilitation fields.

[0093] In the specific implementation process, the system will first number the voxel grids of each local area and maintain the corresponding blood flow characteristic data for each voxel. Next, the system will align the coordinates of the voxel grids of each local area to ensure that their positional relationship in three-dimensional space is accurate. By writing a merging algorithm, the system will integrate the voxel data of each local area one by one to form a unified three-dimensional voxel cloud.

[0094] To ensure data consistency, the system will check and process possible overlapping areas to avoid data redundancy. After integration, the system will perform a series of optimization processes on the final 3D voxel cloud, such as smoothing and data compression, to improve visualization and computational efficiency. Ultimately, the generated complete 3D voxel cloud will be able to intuitively display the dynamic blood flow characteristics of the lower limbs, providing a scientific basis for the user's exercise effect evaluation and health management.

[0095] The three-dimensional skeletal model and the three-dimensional voxel cloud are spatially coupled to ensure the alignment of the two in physical space. Ray tracing combined with volume rendering technology is used to achieve realistic rendering of blood flow movement, obtain a three-dimensional blood flow visualization model, and use a dynamic particle tracking algorithm to simulate the movement of blood flow particles to visualize the real-time dynamic changes of blood flow.

[0096] In this process, the 3D bone model is spatially coupled with the voxel cloud to ensure that the two can be accurately aligned in physical space. By using a rendering method that combines ray tracing technology with volume rendering, a realistic visual presentation of flowing blood can be achieved. At the same time, a dynamic particle tracking algorithm is used to simulate the motion trajectory of blood flow particles, thereby creating a vivid 3D blood flow visualization model.

[0097] The realization of this step is crucial for users to understand the dynamic changes of blood flow. By combining the bone model with the dynamic blood flow, users will be able to intuitively see how blood flows inside the lower limbs. This real-time feedback effect will greatly enhance the scientificity and fun of exercise and provide users with a more in-depth analysis of exercise effects.

[0098] In the specific implementation, the spatial alignment between the 3D skeletal model and the 3D voxel cloud is first performed to ensure that the skeletal model and the voxel cloud are consistent in physical space, which means that the coordinates of each local area need to be accurately calculated. After that, the 3D model is rendered through ray tracing technology combined with volume rendering technology, so that the blood flow can visually appear to be flowing. Next, using the dynamic particle tracking algorithm, the system assigns speed and direction to each particle of the blood flow to simulate the process of blood flow from the heart through the arteries to the lower limbs. Through these efficient rendering and simulation technologies, users can observe in real time how the blood flow changes and flows during movement, so that the data visualization effect is optimal.

[0099] S203. Calculate an exercise intensity index for evaluating the exercise intensity effect during the ankle pump exercise of the user according to the vital sign data, the lower limb movement data, and the lower limb blood flow data.

[0100] In this method, by combining the vital sign data, the lower limb movement data, and the lower limb blood flow data, the system can effectively calculate the exercise intensity index (EII) experienced by the user during the ankle pump exercise. This process involves comprehensively considering the user's average heart rate, resting heart rate, and maximum heart rate to reflect the user's physiological state during exercise. At the same time, the system also compares the instantaneous maximum value of the blood flow velocity in the lower limbs during the exercise with the blood flow velocity in the resting state to evaluate the impact of exercise on blood flow. By performing a weighted sum of the action frequency and its weight of the ankle pump exercise performed by the user, a comprehensive index (EII) is finally obtained, which can reflect the user's exercise intensity and its adaptation situation in real time.

[0101] The calculation of the exercise intensity index has important clinical and sports science application values. First of all, it can help users monitor their own exercise intensity during the ankle pump exercise in real time, so as to adjust the exercise intensity to avoid over-fatigue or insufficient exercise. Secondly, the EII provides an objective evaluation of the exercise effect for users, which is helpful for exercise health management and the formulation of personalized training programs. By tracking the exercise intensity index, medical professionals can also better evaluate the rehabilitation progress of patients and optimize the rehabilitation strategy. Therefore, this calculation method not only improves the scientific nature of exercise monitoring, but also provides an effective basis for exercise intervention and health management.

[0102] Specifically, a calculation formula for an exercise intensity index can be:

[0103]

[0104] Its structural significance lies in comprehensively quantifying the overall exercise intensity of the user during the ankle pump exercise, and reflecting the physiological changes and exercise effects through multiple dimensions.

[0105] Among them, the EII is the exercise intensity index, which reflects the physiological load and overall exercise state of the user during the ankle pump exercise. The HR_avg is the average heart rate of the user during the exercise, which is a direct indicator of the physiological load and indicates the working intensity of the heart during the exercise. The HR_rest is the resting heart rate of the user, which provides a reference baseline for the user's basic heart state and ensures the comparability of the indicators under individual differences. The HR_max is the maximum heart rate of the user during the exercise, which is used to measure the ability of the heart during extreme exercise and helps to understand the relationship between heart rate and exercise intensity. The V_max is the instantaneous maximum value of the blood flow velocity in the lower limbs during the exercise, which reflects the dynamic changes of blood flow during the exercise and is an important indicator of hemodynamics, indicating the effect of exercise on blood flow changes. The V_rest is the blood flow velocity in the lower limbs in the resting state, which is the baseline state of blood flow and can help to evaluate the degree of influence of exercise on blood flow. The f_i is the action frequency of the i-th action of the ankle pump exercise, and the execution frequency of each ankle pump exercise directly affects the energy consumption and intensity evaluation of the exercise. The w_i is the weight of the i-th action, which is the weight value assigned to different actions and reflects the relative importance of each action in the overall exercise intensity, ensuring that the calculation can accurately reflect the actual exercise situation. The n is the type of action in the ankle pump exercise.

[0106] S204, package the vital sign data, the lower limb movement data, the lower limb blood flow data and their corresponding exercise intensity index into an ankle pump exercise effect data set to realize the acquisition of visual ankle pump exercise data effect.

[0107] In this step, the system integrates various types of data obtained by the user during the ankle pump exercise to form a comprehensive ankle pump exercise effect data set. This data set includes the user's vital sign data (such as heart rate, blood pressure, blood oxygen saturation, etc.), lower limb movement data (such as exercise frequency, joint angle and position changes, etc.), lower limb blood flow data (such as blood flow rate, pressure dynamic changes) and the corresponding exercise intensity index (EII). By systematically integrating this information together, the data set can not only reflect the physiological state of each exercise stage, but also show the specific impact of exercise on lower limb blood flow. After integration, the data set can be stored in a standardized format for subsequent analysis and visual display.

[0108] Packing various types of data into an ankle pump exercise effect dataset can provide users with an intuitive overview of their exercise performance, helping them understand their physiological responses and exercise effects during exercise. For example, users can easily view the changing trend of the exercise intensity index and analyze their performance at different exercise stages in combination with heart rate and blood flow data. This not only provides a basis for users to adjust their exercises but also offers a valuable data source for rehabilitation training or sports science research. Relevant health managers and coaches can also develop more precise personalized exercise plans for users based on the information in the dataset, thereby enhancing exercise effects and safety.

[0109] This can be achieved by constructing an integrated data management platform. First, the system will set up a data receiving module in the data acquisition device, which can receive and store in real-time the vital signs, exercise, and blood flow data collected during users' exercises. In addition, this platform can have a data processing module to clean and format the raw data. For example, convert the heart rate from beats per minute to beats per second to ensure data consistency and accuracy. Then, the system packs all the processed data according to a preset data structure, such as using the JSON or XML format, making the dataset easy to store and convenient for subsequent retrieval and visual display. Finally, for easy user access, this platform can also provide a user-friendly interface through which users can easily view and analyze their ankle pump exercise effect dataset, such as plotting a comparison graph of the exercise intensity index and blood flow rate, or reviewing past exercise records and performances. This systematic way of data integration and display will greatly enhance users' ability to understand and manage exercise effects.

[0110] It can be seen that collect the vital signs data, lower limb movement data, and lower limb blood flow data of users during ankle pump exercises through an ankle pump exercise device; analyze the blood flow data, correlate the lower limb blood flow data with the lower limb movement data, and generate a three-dimensional blood flow visualization model to visually display the real-time dynamic changes in blood flow; calculate the exercise intensity index for evaluating the exercise intensity effect of users during ankle pump exercises based on the vital signs data, lower limb movement data, and lower limb blood flow data; pack the vital signs data, lower limb movement data, lower limb blood flow data, and their corresponding exercise intensity indexes into an ankle pump exercise effect dataset to achieve the acquisition of visualized ankle pump exercise data effects, thereby enabling the construction of a dataset for comprehensively evaluating exercise effects, and through effective data analysis and visualization means, converting complex physiological changes into easily understandable information to improve the effectiveness and safety of exercise.

[0111] Another embodiment of the present invention provides a system for collecting visualized ankle pump exercise data effects. Refer to Figure 3 , the system may include:

[0112] The acquisition module 301 is used to acquire the vital sign data, lower limb movement data, and lower limb blood flow data of the user during ankle pump exercise through the ankle pump exercise device;

[0113] The generation module 302 is used to analyze the blood flow data, associate the lower limb blood flow data with the lower limb movement data, and generate a three-dimensional blood flow visualization model to visually display the real-time dynamic changes of blood flow;

[0114] The calculation module 303 is used to calculate the exercise intensity index for evaluating the exercise intensity effect of the user during ankle pump exercise according to the vital sign data, the lower limb movement data, and the lower limb blood flow data;

[0115] The packaging module 304 is used to package the vital sign data, the lower limb movement data, the lower limb blood flow data, and their corresponding exercise intensity indices into an ankle pump exercise effect data set to achieve the acquisition of the visualized ankle pump exercise data effect.

[0116] It can be seen that the vital sign data, lower limb movement data, and lower limb blood flow data of the user during ankle pump exercise through the ankle pump exercise device are acquired; the blood flow data is analyzed, the lower limb blood flow data is associated with the lower limb movement data, and a three-dimensional blood flow visualization model is generated to visually display the real-time dynamic changes of blood flow; according to the vital sign data, lower limb movement data, and lower limb blood flow data, the exercise intensity index for evaluating the exercise intensity effect of the user during ankle pump exercise is calculated; the vital sign data, lower limb movement data, lower limb blood flow data, and their corresponding exercise intensity indices are packaged into an ankle pump exercise effect data set to achieve the acquisition of the visualized ankle pump exercise data effect, so as to be able to construct a data set for comprehensively evaluating the exercise effect, and through effective data analysis and visualization means, convert complex physiological changes into easy-to-understand information, and improve the exercise effect and safety.

[0117] An embodiment of the present invention also provides a storage medium, in which a computer program is stored, and the computer program is set to execute the steps in any one of the above method embodiments when running.

[0118] Specifically, in this embodiment, the above storage medium can be set to store a computer program for executing the following steps:

[0119] S201, acquire the vital sign data, lower limb movement data, and lower limb blood flow data of the user during ankle pump exercise through the ankle pump exercise device;

[0120] S202, analyze the blood flow data, associate the lower limb blood flow data with the lower limb movement data, and generate a three-dimensional blood flow visualization model to visually display the real-time dynamic changes of blood flow;

[0121] S203. Calculate an exercise intensity index for evaluating the exercise intensity effect during the user's ankle pump exercise based on the vital sign data, the lower limb movement data, and the lower limb blood flow data.

[0122] S204. Package the vital sign data, the lower limb movement data, the lower limb blood flow data, and their corresponding exercise intensity indices into an ankle pump exercise effect dataset to achieve visual collection of ankle pump exercise data effects.

[0123] It can be seen that the vital sign data, the lower limb movement data, and the lower limb blood flow data of the user during ankle pump exercise through the ankle pump exercise device are collected; the blood flow data is analyzed, the lower limb blood flow data is associated with the lower limb movement data to generate a three-dimensional blood flow visualization model to visually display the real-time blood flow dynamic changes; according to the vital sign data, the lower limb movement data, and the lower limb blood flow data, an exercise intensity index for evaluating the exercise intensity effect during the user's ankle pump exercise is calculated; the vital sign data, the lower limb movement data, the lower limb blood flow data, and their corresponding exercise intensity indices are packaged into an ankle pump exercise effect dataset to achieve visual collection of ankle pump exercise data effects, so as to be able to construct a dataset for comprehensively evaluating exercise effects, and through effective data analysis and visualization means, convert complex physiological changes into easily understandable information, and improve the exercise effect and safety.

[0124] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0125] Specifically, the above electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0126] Specifically, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0127] S201. Collect the vital sign data, the lower limb movement data, and the lower limb blood flow data of the user during ankle pump exercise through the ankle pump exercise device.

[0128] S202. Analyze the blood flow data, associate the lower limb blood flow data with the lower limb movement data, and generate a three-dimensional blood flow visualization model to visually display the real-time blood flow dynamic changes.

[0129] S203. Calculate an exercise intensity index for evaluating the exercise intensity effect during the user's ankle pump exercise based on the vital sign data, the lower limb movement data, and the lower limb blood flow data.

[0130] S204, pack the vital sign data, the lower limb movement data, the lower limb blood flow data and their corresponding exercise intensity indexes into an ankle pump exercise effect data set to realize the acquisition of the visualized ankle pump exercise data effect.

[0131] It can be seen that the vital sign data, the lower limb movement data and the lower limb blood flow data of the user during ankle pump exercise through the ankle pump exercise device are collected; the blood flow data is analyzed, the lower limb blood flow data is associated with the lower limb movement data, and a three-dimensional blood flow visualization model is generated to visually display the real-time blood flow dynamic changes; according to the vital sign data, the lower limb movement data and the lower limb blood flow data, calculate the exercise intensity index for evaluating the exercise intensity effect of the user during the ankle pump exercise; pack the vital sign data, the lower limb movement data, the lower limb blood flow data and their corresponding exercise intensity indexes into an ankle pump exercise effect data set to realize the acquisition of the visualized ankle pump exercise data effect, so as to be able to construct a data set for comprehensively evaluating the exercise effect, and through effective data analysis and visualization means, convert complex physiological changes into easy-to-understand information, and improve the exercise effect and safety.

[0132] The structure, features and function effects of the present invention have been described in detail based on the embodiments shown in the drawings. The above is only the preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or equivalent embodiments modified into equivalent changes, still within the spirit covered by the specification and the drawings, shall be within the protection scope of the present invention.

Claims

1. A method for collecting visual ankle pump exercise data effects, characterized in that: The method comprises: Collecting vital sign data, lower limb movement data, and lower limb blood flow data of the user when performing ankle pump exercise through an ankle pump exercise device; Analyzing the blood flow data, associating the lower limb blood flow data with the lower limb movement data, and generating a three-dimensional blood flow visualization model to visualize the real-time dynamic changes of blood flow; Calculating an exercise intensity index for evaluating the exercise intensity effect of the user during ankle pump exercise according to the vital sign data, the lower limb exercise data and the lower limb blood flow data; The vital sign data, the lower limb movement data, the lower limb blood flow data and their corresponding movement intensity index are packaged into an ankle pump movement effect data set to achieve visualized ankle pump movement data effect collection.

2. The method according to claim 1, characterized in that The analyzing the blood flow data, associating the lower limb blood flow data with the lower limb movement data, and generating a three-dimensional blood flow visualization model to visualize the real-time dynamic changes of blood flow include: The kinematic algorithm is used to convert the lower limb motion data into joint angles and positions, and the three-dimensional skeleton model of the lower limb is generated by combining the joint angle and position data with computer graphics technology; According to a preset lower limb local area, the blood flow features extracted from the lower limb blood flow data are mapped to a corresponding voxel space to form a three-dimensional voxel cloud, wherein each voxel represents a local blood flow feature within the monitoring volume; The three-dimensional skeletal model and the three-dimensional voxel cloud are spatially coupled to ensure the alignment of the two in physical space. Ray tracing combined with volume rendering technology is used to achieve realistic rendering of blood flow movement, obtain a three-dimensional blood flow visualization model, and use a dynamic particle tracking algorithm to simulate the movement of blood flow particles to visualize the real-time dynamic changes of blood flow.

3. The method according to claim 2, characterized in that The calculation formula of the exercise intensity index is: Among them, the EII is the exercise intensity index, the HR_{avg} is the average heart rate of the user during exercise, the HR_{rest} is the resting heart rate of the user, the HR_{max} is the maximum heart rate of the user during exercise, the V_{max} is the instantaneous maximum value of the blood flow velocity in the lower limbs during exercise, the V_{rest} is the blood flow velocity in the lower limbs in a resting state, the fi is the action frequency of the i-th action of the ankle pump exercise, the w_i is the weight of the i-th action, and the n is the action type in the ankle pump exercise.

4. The method according to claim 3, characterized in that The method of converting the lower limb motion data into joint angles and positions by using a kinematic algorithm, combining the joint angle and position data, and generating a three-dimensional skeleton model of the lower limb by using computer graphics technology includes: The lower limb motion data collected by the sensor is converted into joint angles using quaternions or direction cosine matrices, and the rotation matrix of each joint is calculated by fusing the accelerometer and gyroscope data; Based on the joint angles, forward kinematics is used to calculate the position of each joint of the lower limbs. The position of each joint in three-dimensional space is recursively calculated using the known bone length and joint angles. defining the skeletal structure of the lower limbs, the skeletal structure including key nodes including the hip joint, the knee joint, and the ankle joint, and assigning an initial position and a connection relationship to each joint node; Utilize computer graphics technology and use OpenGL or Unity graphics engine to build a three-dimensional skeleton model. Apply the calculated joint positions and joint angles to the three-dimensional skeleton model, dynamically update the skeleton posture, and render the three-dimensional skeleton model to the visualization interface in real time through the rendering pipeline of the graphics engine.

5. The method according to claim 4, characterized in that According to the preset lower limb local area, the blood flow features extracted from the lower limb blood flow data are mapped to the corresponding voxel space to form a three-dimensional voxel cloud, including: Extracting key blood flow features from the lower limb blood flow data for use in voxel attribute definition; Divide the lower limb into multiple local areas, and generate a voxel grid for each local area in a three-dimensional space; Mapping the extracted key blood flow features to corresponding voxels, wherein the attribute value of each voxel is determined by the blood flow characteristics within its monitoring volume, and using an interpolation method to process boundary voxels; The voxel data of all local areas are integrated to form a complete three-dimensional voxel cloud.

6. A visual ankle pump exercise data effect collection system, characterized in that: The system comprises: A collection module, used to collect vital sign data, lower limb movement data and lower limb blood flow data of a user when performing ankle pump exercise through an ankle pump exercise device; A generation module is used to analyze the blood flow data, associate the lower limb blood flow data with the lower limb movement data, and generate a three-dimensional blood flow visualization model to visualize the real-time dynamic changes of blood flow; A calculation module, configured to calculate an exercise intensity index for evaluating the exercise intensity effect of the user during the ankle pump exercise according to the vital sign data, the lower limb movement data and the lower limb blood flow data; The packaging module is used to package the vital sign data, the lower limb movement data, the lower limb blood flow data and their corresponding exercise intensity index into an ankle pump exercise effect data set to achieve visualized ankle pump exercise data effect collection.

7. The system according to claim 6, characterized in that The generating module is specifically used for: The kinematic algorithm is used to convert the lower limb motion data into joint angles and positions, and the three-dimensional skeleton model of the lower limb is generated by combining the joint angle and position data with computer graphics technology; According to a preset lower limb local area, the blood flow features extracted from the lower limb blood flow data are mapped to a corresponding voxel space to form a three-dimensional voxel cloud, wherein each voxel represents a local blood flow feature within the monitoring volume; The three-dimensional skeletal model and the three-dimensional voxel cloud are spatially coupled to ensure the alignment of the two in physical space. Ray tracing combined with volume rendering technology is used to achieve realistic rendering of blood flow movement, obtain a three-dimensional blood flow visualization model, and use a dynamic particle tracking algorithm to simulate the movement of blood flow particles to visualize the real-time dynamic changes of blood flow.

8. The method according to claim 7, characterized in that The calculation formula of the exercise intensity index is: Among them, the EII is the exercise intensity index, the HR_{avg} is the average heart rate of the user during exercise, the HR_{rest} is the resting heart rate of the user, the HR_{max} is the maximum heart rate of the user during exercise, the V_{max} is the instantaneous maximum value of the blood flow velocity in the lower limbs during exercise, the V_{rest} is the blood flow velocity in the lower limbs in a resting state, the fi is the action frequency of the i-th action of the ankle pump exercise, the w_i is the weight of the i-th action, and the n is the action type in the ankle pump exercise.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 5 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 5.

Images