Rehabilitation training method and device based on eight-segment brocade and computer medium

Abstract

The invention discloses a rehabilitation training method based on eight-segment brocade. The method comprises the following steps: acquiring heart rate, blood oxygen and temperature data of a patient through a lower computer system; human skeletons are tracked and recognized through an upper computer system; decomposing eight-section brocade actions, and extracting key steps of each action; the identification rule of eight-section brocade actions is researched, and an action standard judgment rule and an electrocardiosignal judgment rule are set; acquiring position and motion information of human skeleton points, judging whether rehabilitation actions are qualified or not according to the skeleton point information of the patient, and giving feedback to the patient in a voice mode; a training target and a training period are set, after rehabilitation training is carried out, electrocardiogram monitoring continues to be carried out, the change condition of the heart rate of a patient after heart rehabilitation is observed, action training is adjusted according to the change of the heart rate, the heart health condition is monitored in real time, rehabilitation actions are accurately judged, and a rehabilitation training scheme is updated in real time. And the rehabilitation training result is effectively stored and evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to a rehabilitation training method, device and computer medium based on Ba Duan Jin. Background Art

[0002] With the development of society, the problem of unhealthy lifestyle has become increasingly prominent, especially the increasing morbidity and mortality of cardiovascular diseases such as acute myocardial infarction (AMI), which has become one of the main challenges to the health of urban and rural residents. Acute myocardial infarction has a long-term impact on the physical and mental health of patients, making it difficult for them to return to normal life. Therefore, early cardiac rehabilitation for patients with acute myocardial infarction is particularly important. Cardiac rehabilitation is a long-term comprehensive program covering medical evaluation, exercise prescription, correction of cardiac risk factors, education, consultation and behavioral intervention to reduce the impact of heart disease on the body and mind, reduce the risk of recurrent myocardial infarction and sudden death, control cardiac symptoms, stabilize or reverse the process of arteriosclerosis, and improve the psychological and occupational status of patients. Ba Duan Jin is one of the recommended exercise methods in cardiac rehabilitation. Compared with other traditional Chinese medicine exercise therapies, it has the advantages of short exercise duration and simple movements. It is suitable for patients with acute myocardial infarction and the elderly with poor physical fitness, and does not require equipment or venue restrictions. It is easy to learn and comfortable, and can effectively improve the rehabilitation effect.

[0003] In cardiac rehabilitation treatment, rehabilitation therapists usually determine the standards of rehabilitation movements, but there is currently a lack of strict standards. In order to make rehabilitation movements more standardized, better conduct cardiac rehabilitation, relieve the burden on medical staff, and ensure the treatment effect of patients, the introduction of robot-assisted technology to determine movement standards has become an innovative solution. Through robot intelligent assistance technology, it can not only reduce the burden of rehabilitation therapists, but also promote the development of Ba Duan Jin rehabilitation training methods and systems. First, the patient's electrocardiogram is monitored to assess his or her heart health. Then, through robot-assisted technology and Kinect device communication, the robot can assist the patient in intelligent Ba Duan Jin rehabilitation training, improve the patient's quality of life, and help the patient with cardiac rehabilitation. Summary of the invention

[0004] The embodiments of the present application provide a rehabilitation training method, device and computer medium based on Ba Duan Jin. By detecting data in real time and using a virtual rehabilitation robot to accurately determine whether the rehabilitation movements meet the standards and dynamically update the training plan, it is possible to automatically evaluate the rehabilitation effect, reduce the burden on rehabilitation therapists, and provide patients with more real-time intelligent rehabilitation training.

[0005] The present application provides a rehabilitation training method based on Ba Duan Jin, comprising the following steps:

[0006] Step S1, building a lower computer system, and collecting the patient's heart rate, blood oxygen, and temperature data through the lower computer system;

[0007] Step S2, building a login and real-time monitoring interface, realizing communication with the upper computer and the lower computer, saving real-time monitoring data and extracting monitoring data values, and generating images;

[0008] Step S3, building a host computer system, and tracking and identifying human bones through the host computer system; the host computer system includes a virtual rehabilitation robot, Coppeliasim, Visual Studio, and Kinect. Rehabilitation actions are set through Visual Studio, and Kinect obtains the position and motion information of human bone points to achieve joint simulation of the virtual rehabilitation robot and Kinect;

[0009] Step S4, decomposing the Ba Duan Jin movements and extracting the key steps of each movement; studying the recognition rules of the Ba Duan Jin movements and setting movement achievement evaluation rules and ECG signal evaluation rules;

[0010] Step S5, using Kinect to measure the projection and reflection of infrared light, obtain the position information and movement information of human skeleton points, track the position changes of these skeleton points, capture the patient's movement trajectory, analyze the trajectory to determine whether the rehabilitation action is qualified, and give feedback to the patient in voice;

[0011] The position information includes: joint angle and joint height;

[0012] The movement information includes: movement balance, significant changes in posture, speed and rhythm, joint range of motion, joint direction, and movement consistency;

[0013] Step S6, setting the angle values ​​and height differences of different points on the human body through Visual Studio to identify whether the action is qualified, and giving feedback to the patient in voice;

[0014] Step S7, setting training goals and training cycles, continuing ECG monitoring after rehabilitation training, observing changes in the patient's heart rate after cardiac rehabilitation, and adjusting movement training according to changes in heart rate.

[0015] Preferably, the lower computer system in step S1 includes an Arduino electrocardiograph and blood oxygen monitor, a blood oxygen and heart rate sensor, a temperature sensor, a display screen, and a respiratory rate sensor.

[0016] Preferably, in step S5, Kinect identifies different actions according to the skeletal coordinate points, the angle between two bones, and the relative position difference between the skeletal points, and uses the angle formula for the angle:

[0017]

[0018] Among them, a and b represent the lengths of two adjacent bones, c represents the length of the opposite sides of the two bones, and θ represents the angle between a and b;

[0019] Different actions are identified based on the coordinates of the skeleton points and the relative position difference of the skeleton points. The three-dimensional distance formula between two skeleton points is as follows:

[0020]

[0021] Preferably, the joint angle and joint height in step S5 are specifically:

[0022] The angle between the right upper arm and the right lower arm is set to 100°~120°; the coordinate difference of the right wrist above the highest point of the right shoulder along the y-axis direction is 0.3m; the angle between the left upper arm and the left lower arm is set to 100°~120°; the coordinate difference of the left wrist above the highest point of the left shoulder along the y-axis direction is 0.3m.

[0023] Preferably, the training target and training cycle in step S6 are: the training target heart rate is set to the resting heart rate plus 20 to 30 beats / min; the target heart rate is set to 60% to 80%, and the maximum heart rate is set to 220-age; the training cycle is 1 month.

[0024] Preferably, in step S6, adjusting the movement training according to the heart rate change is specifically: if the detected heart rate is higher than the training target, performing coordination training through Kinect; if the detected heart rate is lower than the training target, performing chest expansion training exercise through Kinect.

[0025] The present application also provides a rehabilitation training device based on Ba Duan Jin, comprising:

[0026] Data acquisition module, used to collect patient heart rate, blood oxygen and temperature data;

[0027] Storage and display module, used for logging in and real-time monitoring interface, realizing communication with the host computer and the slave computer, saving real-time monitoring data and extracting monitoring data values, and generating images;

[0028] Tracking and identification module, used to track and identify human skeleton; including virtual rehabilitation robot, Coppeliasim, Visual Studio, Kinect. Rehabilitation actions are set through Visual Studio, and Kinect obtains the position and movement information of human skeleton points to realize joint simulation of virtual rehabilitation robot and Kinect.

[0029] The standard setting module is used to decompose the Ba Duan Jin movements and extract the key steps of each movement; study the recognition rules of Ba Duan Jin movements and set the movement standard evaluation rules and ECG signal evaluation rules;

[0030] The evaluation feedback module is used to determine whether the rehabilitation action is qualified based on the patient's skeletal point information and give feedback to the patient in voice form;

[0031] The tracking and detection module is used to set training goals and training cycles. After rehabilitation training, ECG monitoring is continued to observe changes in the patient's heart rate after cardiac rehabilitation, and the movement training of the virtual robot is adjusted or updated according to the rehabilitation situation.

[0032] The present application also provides a computer medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned rehabilitation training method is implemented.

[0033] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0034] 1. The upper computer is used to unify and standardize the recognition and judgment of the movement standards of Ba Duan Jin, which realizes the accurate judgment of Ba Duan Jin movements and reduces the errors caused by the subjective judgment of the rehabilitation therapist.

[0035] 2. Use the lower computer system to perform real-time data detection and update the training program to better meet the individualized rehabilitation needs of patients and improve rehabilitation effects and treatment efficiency.

[0036] 3. Using the Kinect device to communicate with CoppeliaSim and Visual Studio, the virtual robot accurately monitors and guides rehabilitation movements to ensure standard movements, realizes the functions of guidance, supervision, and reproduction demonstration, and reduces the occurrence of non-standard movements. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flowchart of the rehabilitation training method in Example 1 of the present application;

[0038] Figure 2 This is a schematic diagram of the upper computer and the lower computer in the first embodiment of the present application;

[0039] Figure 3 This is the PCB diagram of the Arduino ECG detection device in Example 1 of this application;

[0040] Figure 4 This is the connection diagram of the Arduino ECG monitoring device in Example 1 of this application;

[0041] Figure 5 The human skeleton image recognized by Kinect in Example 1 of the present application;

[0042] Figure 6 This is a starting diagram of the virtual robot in Example 1 of the present application;

[0043] Figure 7 This is the third section of the virtual robot Ba Duan Jin in the first embodiment of the present application;

[0044] Figure 8 This is the third section of the robot Ba Duan Jin in the first embodiment of the present application;

[0045] Fig. 9 This is a diagram of the robot-assisted Ba Duan Jin rehabilitation training in Example 1 of the present application. DETAILED DESCRIPTION

[0046] The present application provides a rehabilitation training method, device and computer medium based on Ba Duan Jin, which solve the problems that the rehabilitation therapist is burdened with heavy treatment burden when the Ba Duan Jin rehabilitation training method is used in the current cardiac rehabilitation treatment process, the electrocardiogram detection data in the treatment process is not updated synchronously, and the treatment effect lacks standardized judgment. The intelligent Ba Duan Jin rehabilitation training method designed by robot-assisted technology, Arduino electrocardiogram data measurement function and virtual robot technology can monitor the heart health status in real time, accurately judge the rehabilitation movements, update the rehabilitation training plan in real time, and effectively store and evaluate the rehabilitation training results.

[0047] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0048] Embodiment 1

[0049] like Figure 1 As shown, a rehabilitation training method based on Ba Duan Jin comprises the following steps:

[0050] Step S1, build a lower computer system, and collect the patient's heart rate, blood oxygen, and temperature data through the lower computer system.

[0051] like Figure 2 As shown in the figure, the lower computer system includes an Arduino ECG blood oxygen monitor, which integrates MAX30102 (blood oxygen and heart rate sensor), LM35 (temperature sensor), SSD1306 (display), and HKH-11C (respiratory rate sensor). Figure 3 , Figure 4 The figure shows the connection diagram of Arduino ECG blood oxygen monitor, which determines the health status of the human body through the data monitored by the equipment of the lower computer system.

[0052] Step S2, build a login and real-time monitoring interface through Python, realize communication with the upper computer and the lower computer, save the real-time monitoring data and extract the monitoring data value, and generate an image.

[0053] For the early stage I rehabilitation of patients with acute myocardial infarction, PyCharm is used as the development environment to build a system rehabilitation interface, extract the monitored data values, and generate corresponding images.

[0054] Step S3, building a host computer system, and tracking and identifying human bones through the host computer system.

[0055] like Figure 2 As shown, the host computer system includes a virtual rehabilitation robot, Coppeliasim communication, Visual Studio communication, and Kinect device communication. The rehabilitation actions are set through Visual Studio, and Kinect obtains the position and motion information of the human skeleton points to realize the joint simulation of the virtual rehabilitation robot and Kinect.

[0056] Simulation process:

[0057] Step S31, virtual rehabilitation robot setting:

[0058] Use CoppeliaSim to create a model of a virtual rehabilitation robot, which needs to have motion freedom and joint parameters similar to those of the actual human skeleton.

[0059] Define the standard postures of Ba Duan Jin through the Visual Studio programming interface. Set the position and posture information of key bone points for each posture, such as the angles of the shoulder, elbow, knee and other joints.

[0060] Step S32, Kinect data acquisition and simulation synchronization:

[0061] The Kinect device collects the patient's bone data in real time and obtains the three-dimensional coordinates and motion trajectory of each bone point.

[0062] The skeletal data collected by Kinect is transmitted to CoppeliaSim through the communication interface, and the posture and motion status of the virtual rehabilitation robot are synchronously updated in the virtual environment.

[0063] Step S33, simulation feedback and correction:

[0064] Through the simulation module of CoppeliaSim, the patient's current posture is compared with the standard posture, and the deviation value of each bone point is calculated. The deviation can be expressed as the position difference and angle difference in three-dimensional space.

[0065] According to the deviation value, the movement of the virtual rehabilitation robot is dynamically adjusted to provide intuitive visual feedback, and voice prompts are issued to the patient through the Visual Studio control interface to guide the patient to correct the movement.

[0066] Step S4, decompose the Ba Duan Jin movements and extract the key steps of each movement; study the recognition rules of the Ba Duan Jin movements and set the movement achievement evaluation rules and the ECG signal evaluation rules.

[0067] The rules for judging whether an action meets the standard are as follows:

[0068] Movement decomposition: Each complete movement in Ba Duan Jin is broken down into multiple steps. Each movement consists of three parts: start, transition and end, and each part has specific postures and movement requirements.

[0069] Angle setting: For each step after decomposition, we set the angle range of the joints. The standard angle of the arm movement is set between 100° and 120° to ensure that the patient achieves the standard range of motion when performing the movement.

[0070] Height standards: In addition to angle settings, we also set the height difference of key body parts. For example, the height difference of the wrist relative to the shoulder should be 0.3 meters. These height standards are used to guide patients to maintain the correct posture during training.

[0071] By calculating the three-dimensional coordinates and angles of the bone points, it is determined whether the current action meets the set standards. For actions that do not meet the standards, the virtual rehabilitation robot and voice prompts are used to help the patient make adjustments.

[0072] Other judging rules:

[0073] (1) Posture stability and safety

[0074] Balance and stability: The key steps should ensure the balance and stability of the body during the movement. For example, in some bending or stretching movements in Ba Duan Jin, maintaining the stability of the spine is an important key step.

[0075] Avoid excessive stretching or loading: Identify those movements that may cause excessive stretching or loading of the joint and ensure that these movements are performed in a safe manner to avoid potential injury to the patient.

[0076] (2) Action recognition

[0077] Significant posture changes: Key steps are usually accompanied by obvious posture changes, which are easy to identify through the movement trajectory of the skeleton points. For example, the arm drawing the bow in "Drawing the bow like shooting the eagle" is a significant posture change and is one of the key steps.

[0078] Speed ​​and rhythm: The key steps of certain movements involve specific speeds or rhythms, and specific movements must be completed within a certain period of time, which is crucial to the effectiveness of rehabilitation training.

[0079] (3) Biomechanical properties

[0080] Joint mobility: Based on the range of joint motion, extract those steps that require a larger range of joint motion. For example, some movements in Ba Duan Jin require full extension of the arms or legs, and these steps should be considered key steps.

[0081] Angle and direction: Focus on extracting actions that are completed at a specific angle or direction. The angle relationship between skeleton points is used to identify these key steps.

[0082] (4) Repeatability and consistency of actions

[0083] High repetition: The key steps of certain movements appear frequently throughout Ba Duan Jin, and strict consistency is required each time they appear. For example, the synchronization of breathing and movement needs to be extracted as a key step.

[0084] Standardization requirements: Key steps need to have a high degree of consistency and be able to perform standardized assessments among different patients to ensure the predictability and repeatability of rehabilitation effects.

[0085] By combining movement decomposition, angle and height settings with the above standards, we can more accurately extract key steps, evaluate whether the movements meet the standards, and provide patients with safe and effective rehabilitation training.

[0086] Step S5, using Kinect to measure the projection and reflection of infrared light, obtain the position and movement information of human skeleton points, track the position changes of these skeleton points, capture the patient's movement trajectory, analyze the trajectory to determine whether the rehabilitation movements are qualified, and give feedback to the patient in the form of voice.

[0087] The Kinect device communicates with CoppeliaSim and Vs Studio. Through the study of Ba Duan Jin movements, the angle between the right upper arm and the right lower arm is a relatively unique and fixed angle, which is set to 100°~120°. The coordinate difference along the y-axis direction of the right wrist above the highest point of the right shoulder is 0.3m. Similarly, the left arm is set in the same way. And the completion of the action is printed through the command box.

[0088] like Figure 5 As shown in the figure, the three-dimensional bone data obtained by Kinect is used to identify the patient's key bone points, such as the head, shoulders, elbows, wrists, hips, knees, ankles, etc. The coordinate information of the bone points is used to calculate the angles of each joint. When the human body moves, Kinect identifies different actions based on the bone coordinate points, the angle between the two bones, and the relative position difference between the bone points. For the angle, the angle formula can be used:

[0089]

[0090] Where a and b represent the lengths of two adjacent bones, c represents the length of the opposite sides of the two bones, and θ represents the angle between a and b. Different actions will produce different angles, so the angle recognition method can be used to determine different actions.

[0091] Different actions are identified based on the coordinates of the skeleton points and the relative position difference of the skeleton points. The three-dimensional distance between two skeleton points can be measured by Euclidean three-dimensional distance measurement. Different distances are set according to different actions. The formula is as follows:

[0092]

[0093] like Figure 6 , Figure 7 , Figure 8 , Fig. 9 The figure shows the robot's posture during the entire process of performing the third section of Ba Duan Jin, "To regulate the spleen and stomach, you must lift one arm." The system gives corresponding feedback based on the degree to which the patient's movements meet the standards. When the patient completes the movement well, the virtual robot will give a thumbs up and express affirmation through voice encouragement; if the patient's movements do not meet the standards, the virtual robot will guide and reproduce the rehabilitation movements and give the patient voice encouragement.

[0094] Step S6: Monitor the patient's heart rate and other information in real time through the ECG blood oxygen monitor device, and evaluate the patient's rehabilitation effect in real time by combining physiological data such as heart rate and blood oxygen. If it is detected that the patient's heart rate deviates from the set training target, the difficulty or rhythm of the training action is automatically adjusted to better meet the patient's rehabilitation needs. The training target heart rate is set to the resting heart rate plus 20 to 30 beats per minute; the target heart rate is set to 60% to 80%, and the maximum heart rate = 220-age. During training, the heart rate should be between the target heart rate and the target heart rate, pay attention to the patient's tolerance, and take one month as the training cycle. After the patient undergoes rehabilitation training, the ECG monitoring is continued to observe the changes in the patient's heart rate after cardiac rehabilitation, and the action training of the virtual robot is adjusted or updated according to the rehabilitation situation, thereby realizing early rehabilitation training for patients with myocardial infarction in the supervised mode. Through the above implementation method, the simulation process and the recognition process are concretized, further improving the accuracy and effectiveness of rehabilitation training.

[0095] This application uses an ECG monitoring system to monitor the patient's health data in real time, and dynamically adjusts the rehabilitation training program based on these data to better meet the patient's individualized rehabilitation needs and improve rehabilitation effects and treatment efficiency. The Eight-Section Brocade rehabilitation training system for patients with early myocardial infarction was studied, and a phased rehabilitation plan was developed. Patients with acute myocardial infarction complete the first 4 sections of the Eight-Section Brocade in a sitting position 1-3 days after surgery; 4-7 days after surgery, complete all 8 sections in a standing position. This method ensures that patients gradually adapt to training, reduces the risk of premature excessive exercise, and improves rehabilitation effects.

[0096] This application combines the ECG monitoring system with cardiac rehabilitation work, proposes different rehabilitation training programs based on real-time data, and realizes the standardized judgment of rehabilitation movements. Using the Kinect device to communicate with CoppeliaSim and VisualStudio, the virtual robot accurately monitors and guides the rehabilitation movements to ensure the movement standards and reduce the occurrence of irregular movements. Compared with traditional rehabilitation methods, the accuracy of rehabilitation movements has increased by about 30%, reducing the impact of subjective errors and making the training effect more consistent.

[0097] Embodiment 2

[0098] The present application provides a rehabilitation training device based on Ba Duan Jin, which executes the method in the above embodiment 1 and includes the following modules:

[0099] The data monitoring module is used to collect the patient's heart rate, blood oxygen and temperature data.

[0100] The storage and display module is used to build a login and real-time monitoring interface, realize communication with the host computer and the slave computer, save real-time monitoring data and extract monitoring data values, and generate images.

[0101] The tracking and recognition module is used to set rehabilitation actions through VisualStudio communication, remotely control the virtual rehabilitation robot through VisualStudio communication, realize joint simulation of the virtual rehabilitation robot and Kinect, and realize tracking and recognition of human bones.

[0102] The standard setting module is used to decompose the Ba Duan Jin movements and extract the key steps of each movement; study the recognition rules of Ba Duan Jin movements and set the movement standard evaluation rules and ECG signal evaluation rules

[0103] The evaluation feedback module is used to set the angle values ​​and height differences of different points on the human body to identify whether the action is qualified, and give feedback to the patient in the form of voice.

[0104] The tracking detection module is used to continue ECG monitoring after rehabilitation training, observe changes in the patient's heart rate after cardiac rehabilitation, and adjust or update the virtual robot's motion training according to the rehabilitation situation.

[0105] Embodiment 3

[0106] The present application provides a computer storage medium, including instructions, characterized in that when the instructions are executed on a computer, the computer executes the method in the above embodiment 1.

[0107] In the above embodiment 1, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product.

[0108] The above-mentioned computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0109] The embodiments of this specific implementation method are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

[0110] Although preferred embodiments of the present invention have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A rehabilitation training method based on Ba Duan Jin, characterized in that: The following steps are involved: Step S1, building a lower computer system, and collecting the patient's heart rate, blood oxygen, and temperature data through the lower computer system; Step S2, building a login and real-time monitoring interface, realizing communication with the upper computer and the lower computer, saving real-time monitoring data and extracting monitoring data values, and generating images; Step S3, building a host computer system, and tracking and identifying human bones through the host computer system; the host computer system includes a virtual rehabilitation robot, Coppeliasim, Visual Studio, and Kinect. Rehabilitation actions are set through Visual Studio, and Kinect obtains the position and motion information of human bone points to achieve joint simulation of the virtual rehabilitation robot and Kinect; Step S4, decomposing the Ba Duan Jin movements and extracting the key steps of each movement; studying the recognition rules of the Ba Duan Jin movements and setting movement achievement evaluation rules and ECG signal evaluation rules; Step S5, using Kinect to measure the projection and reflection of infrared light, obtain the position information and movement information of human skeleton points, track the position changes of these skeleton points, capture the patient's movement trajectory, analyze the trajectory to determine whether the rehabilitation action is qualified, and give feedback to the patient in voice; The position information includes: joint angle and joint height; The movement information includes: movement balance, significant changes in posture, speed and rhythm, joint range of motion, joint direction, and movement consistency; Step S6, setting training goals and training cycles, continuing ECG monitoring after rehabilitation training, observing changes in the patient's heart rate after cardiac rehabilitation, and adjusting movement training according to changes in heart rate.

2. The rehabilitation training method according to claim 1, characterized in that: The lower computer system in step S1 includes an Arduino electrocardiogram and blood oxygen monitor, a blood oxygen and heart rate sensor, a temperature sensor, a display screen, and a respiratory rate sensor.

3. The rehabilitation training method according to claim 1, characterized in that: In step S5, Kinect recognizes different actions based on the skeleton coordinate points, the angle between two skeletons, and the relative position difference between the skeleton points, and uses the angle formula for the angle: Among them, a and b represent the lengths of two adjacent bones, c represents the length of the opposite sides of the two bones, and θ represents the angle between a and b; Different actions are identified based on the coordinates of the skeleton points and the relative position difference of the skeleton points. The three-dimensional distance formula between two skeleton points is as follows:

4. The rehabilitation training method according to claim 1, characterized in that: The joint angle and joint height in step S5 are specifically: The angle between the right upper arm and the right lower arm is set to 100°~120°; the coordinate difference of the right wrist above the highest point of the right shoulder along the y-axis direction is 0.3m; the angle between the left upper arm and the left lower arm is set to 100°~120°; the coordinate difference of the left wrist above the highest point of the left shoulder along the y-axis direction is 0.3m.

5. The rehabilitation training method according to claim 1, characterized in that: The training objectives and training cycles in step S6 are: the training target heart rate is set to the resting heart rate plus 20 to 30 beats / min; the target heart rate is set to 60% to 80%, and the maximum heart rate is set to 220-age; the training cycle is 1 month.

6. The rehabilitation training method according to claim 1, characterized in that: The specific steps of adjusting the action training according to the heart rate change in step S6 are as follows: If the detected heart rate is higher than the training target, coordination training is performed through Kinect; if the detected heart rate is lower than the training target, chest expansion training exercises are performed through Kinect.

7. A rehabilitation training device based on Ba Duan Jin, characterized in that: include: Data acquisition module, used to collect patient heart rate, blood oxygen and temperature data; Storage and display module, used for logging in and real-time monitoring interface, realizing communication with the host computer and the slave computer, saving real-time monitoring data and extracting monitoring data values, and generating images; Tracking and identification module, used to track and identify human skeleton; including virtual rehabilitation robot, Coppeliasim, Visual Studio, Kinect. Rehabilitation actions are set through Visual Studio, and Kinect obtains the position and movement information of human skeleton points to realize joint simulation of virtual rehabilitation robot and Kinect. The standard setting module is used to decompose the Ba Duan Jin movements and extract the key steps of each movement; study the recognition rules of Ba Duan Jin movements and set the movement standard evaluation rules and ECG signal evaluation rules; The evaluation feedback module is used to determine whether the rehabilitation action is qualified based on the patient's skeletal point information and give feedback to the patient in voice form; The tracking and detection module is used to set training goals and training cycles. After rehabilitation training, ECG monitoring is continued to observe changes in the patient's heart rate after cardiac rehabilitation, and the movement training of the virtual robot is adjusted or updated according to the rehabilitation situation.

8. A computer medium, characterized in that The computer medium stores a computer program, and when the computer program is executed by a processor, the rehabilitation training method according to any one of claims 1 to 6 is implemented.

Images