A method and system for monitoring dynamic assisted correction of scoliosis

Abstract

The present application relates to the technical field of follow-up training supervision, and in particular to a method and system for dynamic assisted correction of scoliosis, the method comprising obtaining a real-time displayed instruction video, identifying the instruction movements contained in the real-time displayed instruction video, and determining the instruction part model and instruction skeletal points based on the instruction movements; obtaining a real-time follow-up training video, and identifying the follow-up training skeletal points corresponding to each instruction skeletal point from the real-time follow-up training video; obtaining the patient's basic follow-up training part model based on the follow-up training skeletal points, and determining the patient's follow-up training pump feeling data based on the basic follow-up training part model, the follow-up training skeletal points, and the real-time follow-up training video; determining the corresponding instruction pump feeling data based on the instruction part model, the instruction skeletal points, and the real-time displayed instruction video, and comparing the follow-up training pump feeling data with the instruction pump feeling data, determining the patient's follow-up training score, and providing feedback on the follow-up training score. The present application improves the accuracy of judging whether the patient's follow-up training movements meet the standards.

Description

Technical Field

[0001] The present application relates to the technical field of training supervision, and in particular to a method and system for supervising dynamic assisted correction of scoliosis. Background Art

[0002] The causes of scoliosis are complex and varied. It may be caused by skeletal maldevelopment during the fetal period, resulting in abnormal spinal structure, which leads to scoliosis after birth. It may also be caused by long-term bad posture habits, such as long-term bending over and sitting in an incorrect posture. The specific cause is still unclear and may involve the interaction of multiple factors such as genetics, environment, and lifestyle habits. Scoliosis not only affects the patient's appearance, but may also cause compression to the internal organs, leading to dysfunction and even affecting the patient's mental health.

[0003] The treatment of scoliosis is a long process. In addition to cooperating with the treatment in the hospital, it is also particularly important to carry out corresponding rehabilitation and orthopedic training during the treatment outside the hospital. However, when practicing at home, patients may simply imitate some general exercise videos or tutorials and cannot accurately grasp the standard posture and force sequence of each movement. As a result, it is easy to ignore safety issues due to excessive movement range and excessive speed, thereby increasing the risk of further injury and greatly reducing the exercise effect. Summary of the invention

[0004] In order to improve the accuracy of judging whether the patient's training movements meet the standards, thereby improving the safety of the patient during the training process, the embodiment of the present application provides a scoliosis dynamic assisted correction training supervision method and supervision system.

[0005] In the first aspect, the present application provides a method for supervising dynamic assisted correction of scoliosis, which adopts the following technical solution:

[0006] A method for supervising dynamic assisted correction of scoliosis, comprising:

[0007] Acquire a real-time display guidance video, identify guidance actions contained in the real-time display guidance video, and determine a guidance part model and guidance bone points based on the guidance actions, wherein the real-time display guidance video is the orthopedic guidance content displayed on the display interface at the current moment;

[0008] Acquire a real-time follow-up training video, and identify the follow-up training bone point corresponding to each guidance bone point from the real-time follow-up training video, wherein the real-time follow-up training video is a follow-up training video of the patient during the orthopedic training according to the displayed guidance video;

[0009] Acquire a basic follow-up training part model of the patient based on the follow-up training skeletal points, and determine the follow-up training pump feeling data of the patient based on the basic follow-up training part model, the follow-up training skeletal points and the real-time follow-up training video, wherein the basic follow-up training part model is determined based on the treatment information and human body parameter information of the patient;

[0010] Based on the guidance part model, the guidance bone points and the real-time displayed guidance video, the corresponding guidance pump data is determined, and the follow-up pump data is compared with the guidance pump data to determine the patient's follow-up score, and the follow-up score is fed back.

[0011] By adopting the above technical solution, the guidance part model is determined from the real-time guidance video, and then the corresponding following part model of the patient during the following practice is determined based on the guidance part model. Finally, local supervision is performed by comparing the pump sensation data generated by the guidance part model and the following part model during the following practice, instead of supervising the entire body or all-round movements of the patient during the following practice. By locally supervising the patient's following practice behavior, it is convenient to focus the supervision attention on key parts or key movements, thereby facilitating the improvement of the accuracy of judging whether the patient's following practice movements meet the standards. In addition, in the process of local supervision, problems in the patient's following practice movements can be discovered more timely, so as to give targeted feedback and suggestions, thereby improving the safety of the patient during the following practice.

[0012] In a possible implementation, determining the patient's follow-up pump data based on the basic follow-up part model, the follow-up skeletal points, and the real-time follow-up video includes:

[0013] Identify the simulated follow-up skeletal point corresponding to each follow-up skeletal point from the basic follow-up part model, and bind each simulated follow-up skeletal point to the corresponding follow-up skeletal point to obtain a target follow-up part model;

[0014] Based on the real-time follow-up video, the target follow-up part model is driven to obtain the follow-up bone trajectory corresponding to each moment, and based on the mapping relationship between the follow-up bone trajectory corresponding to each moment and the preset change parameter, the follow-up change parameter corresponding to each moment is determined, wherein the preset change parameter mapping relationship is the corresponding relationship between the follow-up bone trajectory and the follow-up change parameter, and the follow-up change parameter includes the blood flow increase amount and the fiber activation amount;

[0015] The follow-up training change parameters corresponding to each moment in the preset time period are integrated to determine the follow-up training pump feeling data of the patient.

[0016] By adopting the above technical solution, by binding the simulated training bone points with the corresponding training bone points, it is convenient to improve the accuracy of driving the target training part model. In addition, by driving the target training part model through real-time training video, it is convenient to display the patient's training effect in a numerical form, thereby improving the accuracy of evaluating the patient's training process.

[0017] In a possible implementation, integrating the corresponding follow-up training change parameters at each moment in a preset time period to determine the follow-up training pump feeling data of the patient includes:

[0018] Dividing the preset time period into a plurality of sub-time periods based on the guiding action, integrating the follow-up training change parameters corresponding to each moment in each sub-time period, and obtaining a follow-up training change parameter group corresponding to each sub-time period, wherein each follow-up training change parameter group includes a blood flow parameter group and a fiber activation parameter group;

[0019] Determine a basic layer according to the guiding action, and determine a sub-change layer of each follow-up change parameter group in a corresponding sub-time period according to each follow-up change parameter group and the basic layer;

[0020] The corresponding sub-change layers are superimposed according to the order of each sub-time period within the preset time period to obtain the patient's follow-up pump feeling data.

[0021] By adopting the above technical solution, by constructing a sub-change layer for each follow-up change parameter group, and superimposing each sub-change layer in sequence, it is convenient to intuitively display the changes in the pump feeling of the follow-up part of the patient during the follow-up process, and to enhance the patient's follow-up experience through visual expression, so that the patient can more intuitively feel the changes brought about by the follow-up, thereby facilitating the improvement of the enthusiasm and satisfaction of the follow-up. In addition, the follow-up effect of the patient can be intuitively analyzed through the change layer, so as to formulate personalized follow-up content for the patient, avoid injuries caused by excessive follow-up, and also facilitate the improvement of the follow-up results.

[0022] In one possible implementation, it also includes:

[0023] When the end of the follow-up training is detected, the follow-up training scores corresponding to the follow-up training movements when the patient follows each guided movement during the current follow-up training are integrated, and each follow-up training score is compared with a preset score threshold, and a difference follow-up training movement is determined from all the follow-up training movements, and the follow-up training score of the difference follow-up training movement is lower than the preset score threshold;

[0024] When the difference following exercises include multiple ones, obtaining at least one following skeleton point corresponding to each difference following exercise, and counting the occurrence frequency of each following skeleton point in all the difference following exercises;

[0025] All the following practice skeleton points are sorted based on the frequency of occurrence of each following practice skeleton point, and following practice skeleton points with a higher order than a preset order are determined as focus skeleton points, and the difference following practice movements containing the focus skeleton points are determined as focus following practice movements;

[0026] Based on each focus practice action and the corresponding guidance action, the guidance prompts to be corrected for each focus skeletal point in the corresponding focus practice action are determined, and when a new focus skeletal point is detected in the real-time practice video of the patient during the next practice period, the corresponding guidance prompts to be corrected are fed back to the patient during the patient's practice based on the guidance action corresponding to the new focus skeletal point.

[0027] By adopting the above technical solution, by integrating the follow-up scores generated by the patient after following each guided action during the entire follow-up period, it is convenient to determine the guided actions with poor follow-up effects, so as to provide data support for the subsequent adjustment of training content or supervision strategies. In addition, when there are many different follow-up actions, the follow-up skeletal points corresponding to different different follow-up actions are analyzed and integrated to determine the skeletal points that need attention, so as to provide corrective guidance in time during the follow-up process, thereby facilitating the improvement of the patient's follow-up effect. When providing corrective guidance for the focused skeletal points, based on each focused follow-up action and the corresponding guided action, the guidance to be corrected for each focused skeletal point in the corresponding focused follow-up action is determined, so as to accurately point out the problems that the patient has when performing the corresponding action, thereby facilitating the effectiveness of the guidance prompts to be corrected, and further facilitating the improvement of the patient's accuracy during the follow-up process.

[0028] In a possible implementation, based on the focus follow-up action and the corresponding guidance action, determining the guidance prompt to be corrected of the focus skeletal point in the corresponding focus follow-up action includes:

[0029] Determine the guidance action corresponding to the focus follow-up action as the focus guidance action, and determine the focus guidance pump feeling data corresponding to the focus guidance action and the focus follow-up pump feeling data corresponding to the focus follow-up action based on the guidance pump feeling data and the follow-up pump feeling data;

[0030] Determine a pump difference based on the focused guidance pump data and the focused follow-up pump data, and determine the strength to be corrected corresponding to the focused skeletal point based on the pump difference and a preset strength mapping relationship, wherein the preset strength mapping relationship is a corresponding relationship between the pump difference and the strength to be corrected;

[0031] Determine the focus guidance edge data corresponding to the focus guidance action and the focus follow-up training edge data corresponding to the focus follow-up training action from the real-time display guidance video and the real-time follow-up training video;

[0032] Determine the posture to be corrected corresponding to the focus skeleton point based on the focus guidance edge data and the focus follow-up edge data;

[0033] Based on the strength to be corrected and the posture to be corrected, a guidance prompt to be corrected of the focus skeletal point in the corresponding focus training action is determined.

[0034] By adopting the above technical solution, by comparing the focus-guidance pump feeling data with the focus-follow-practice pump feeling data, the intensity that the patient needs to correct during the follow-up practice can be determined. In addition, by analyzing the focus-guidance edge data and the focus-follow-practice edge data, the posture that the patient needs to correct during the follow-up practice can be determined. When it is detected that the patient has posture deviation or insufficient pump feeling during the follow-up practice, corresponding personalized correction guidance prompts can be given in time, thereby facilitating improving the patient's follow-up practice effect.

[0035] In one possible implementation, it also includes:

[0036] Obtaining follow-up information, and determining the change displacement corresponding to each abnormal bone point based on the follow-up information and the treatment information, wherein the abnormal bone point is a bone point that has a lateral position in the treatment information;

[0037] Determine an abnormal bone point whose change displacement is higher than a preset change threshold as a positive abnormal bone point, and determine a target adjustment value corresponding to the change displacement based on a mapping relationship between the change displacement and a preset adjustment value, wherein the preset adjustment value mapping relationship is a corresponding relationship between the change displacement and the target adjustment value;

[0038] Based on the target adjustment value, a preset score threshold corresponding to the follow-up exercise including the positive abnormal skeletal point is updated to obtain an updated preset score threshold;

[0039] Based on the updated preset score threshold, it is judged whether the following action containing the positive abnormal bone point in the real-time following action video during the next following action is a difference following action.

[0040] By adopting the above technical scheme, the follow-up information is analyzed so that the supervision intensity of the patient during the follow-up training process can be adjusted based on the follow-up information, thereby improving the adaptability between the supervision intensity and the patient's own recovery situation. In addition, by effectively managing and utilizing the patient's follow-up information, it is convenient to understand the changes in abnormal bone points during the patient's follow-up training process, and adjust the preset score threshold for judging abnormal follow-up movements based on the changes, so as to improve the pertinence and effectiveness of rehabilitation training.

[0041] In the second aspect, the present application provides a monitoring system, which adopts the following technical solution:

[0042] A monitoring system, comprising:

[0043] at least one processor;

[0044] Memory;

[0045] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned scoliosis dynamic assisted correction training supervision method.

[0046] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0047] A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned scoliosis dynamic assisted correction training supervision method.

[0048] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution:

[0049] A computer program product includes a computer program, which, when executed by a processor, implements the above-mentioned dynamic assisted correction and training supervision method for scoliosis.

[0050] In summary, the present application includes at least one of the following beneficial technical effects:

[0051] By determining the guidance part model from the real-time guidance video, and then determining the corresponding following part model of the patient during the following practice based on the guidance part model, and finally performing local supervision by comparing the pump sensation data generated by the guidance part model and the following part model during the following practice, rather than supervising the patient's entire body or all-round movements during the following practice, local supervision of the patient's following practice behavior makes it easier to focus supervision attention on key parts or key movements, thereby facilitating the improvement of the accuracy of judging whether the patient's following practice movements meet the standards. In addition, in the process of local supervision, problems in the patient's following practice movements can be discovered more promptly, so as to provide targeted feedback and suggestions, thereby improving the safety of the patient during the following practice.

[0052] By integrating the follow-up scores generated by the patient's follow-up of each guided movement during the entire follow-up period, it is convenient to determine the guided movements with poor follow-up effects, so as to provide data support for the subsequent adjustment of training content or supervision strategies. In addition, when there are many different follow-up movements, the follow-up skeletal points corresponding to different different follow-up movements are analyzed and integrated to determine the skeletal points that need attention, so as to provide corrective guidance in time during the follow-up process, thereby facilitating the improvement of the patient's follow-up effect. When providing corrective guidance for the focus skeletal points, based on each focus follow-up movement and the corresponding guiding movement, the guidance to be corrected for each focus skeletal point in the corresponding focus follow-up movement is determined, so as to accurately point out the problems that patients have when performing the corresponding movements, thereby facilitating the effectiveness of the guidance prompts to be corrected, and then facilitating the improvement of the accuracy of the patient's follow-up process. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a flowchart of a method for supervising dynamic assisted correction of scoliosis in an embodiment of the present application;

[0054] Figure 2 It is a schematic diagram of a process for determining a guidance prompt to be corrected in an embodiment of the present application;

[0055] Figure 3 It is a structural diagram of a monitoring system in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following is combined with Figures 1 to 3 This application is described in further detail.

[0057] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0060] Specifically, the embodiment of the present application provides a method for monitoring dynamic assisted correction training of scoliosis, which is executed by a monitoring system, and the monitoring system can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this.

[0061] refer to Figure 1 , Figure 1 1 is a flow chart of a method for supervising dynamic assisted correction of scoliosis in an embodiment of the present application, the method comprising steps S110-S140, wherein:

[0062] Step S110: acquiring a real-time display guidance video, identifying guidance actions contained in the real-time display guidance video, and determining guidance part models and guidance bone points based on the guidance actions. The real-time display guidance video is the orthopedic guidance content displayed on the display interface at the current moment.

[0063] Specifically, scoliosis is a common spinal deformity disease, especially in adolescents. Timely and effective orthopedic treatment is essential for scoliosis patients. When treating scoliosis, comprehensive physical therapy, use of orthotics, exercise training, etc. are generally used to improve the treatment effect. Among them, orthopedic videos, as an intuitive and convenient teaching tool, can provide patients with continuous guidance and support at home or outside the hospital to improve the mechanical balance of the patient's spine, help alleviate the symptoms of scoliosis, prevent further deterioration of the disease, and promote the natural recovery of the spine. However, if the patient ignores safety issues such as improper force, excessive movement, and excessive speed during the follow-up training, it may increase the risk of further injury to the patient, so the patient's follow-up training process needs to be supervised.

[0064] The instructional video can be prepared by the relevant doctors according to the actual situation of the patient and uploaded to the supervision system. The patient can view the corresponding instructional video by logging in or accessing the supervision system at home or outside the hospital. Since the scoliosis conditions of different patients are different and the self-recovery abilities of different patients are different, the instructional video content corresponding to different patients may be different. With treatment and recovery, the instructional video content corresponding to the same patient at different times may also be different. For example, the relevant doctor can adjust the patient's instructional video according to the patient's regular re-examination. The real-time display instructional video is the content played by the patient's follow-up display device at the current moment, where the follow-up device can be a computer terminal, a mobile phone terminal, etc., as long as it is a display terminal that can play the instructional video.

[0065] Through following exercises, it is easy to enhance the patient's muscle strength, improve basic flexibility and balance to correct the scoliosis. The guiding movements contained in the real-time guidance video can include lifting a wooden stick for correction, side-lying wooden stick support, ballet-style stretching correction, and thoracic rotation correction. Among them, when the patient is following the wooden stick correction, he needs to hold the wooden stick with both hands in parallel and raise it above his head. If the correction effect of scoliosis needs to be enhanced, weight can also be added to the end of the wooden stick on the side that can straighten the spine. It is more suitable for segmental correction, such as patients with left thoracic convexity and right lumbar convexity; when the patient is following the wooden stick support in the side-lying position When doing ballet-style stretching correction, the patient needs to lie on the side and place the stick on one side of the body, support the stick with the arms or legs, and keep the body balanced to enhance the muscle strength in the side-lying position; when the patient is practicing ballet-style stretching correction, the patient needs to stand upright, cross the legs and lean against the door frame or similar support, raise the outer hand, grab the door frame or support with the inner hand, stretch the side waist to relax the tense side waist muscles; when the patient is doing thoracic rotation correction, the patient needs to support the ground with both hands and feet, cross the right hand across the chest, rotate the body to the left as much as possible, then raise the right arm, open the chest, support with the left hand, and rotate the body to the right to increase the flexibility and rotation ability of the thoracic spine.

[0066] Different guiding actions focus on different bone points and muscle groups, so the guiding bone points corresponding to different guiding actions may be different. For example, the guiding bone points corresponding to the lifting of a wooden stick correction are the scapula, humerus, ulna, radius, carpal bones, metacarpal bones and phalanges. Specifically, the rotation and lifting of the scapula, the abduction and external rotation of the humerus, the rotation of the ulna and radius, and the extension and grasping of the wrist and fingers are all involved in the completion of the lifting of the wooden stick correction action. The guiding part models corresponding to different guiding actions are also different. The guiding part model contains at least guiding bone points. For example, when the guiding action is lifting a wooden stick correction, the corresponding guiding part model only needs to contain the guiding bone points corresponding to the guiding action, and the bone points corresponding to the legs, feet, abdomen and buttocks do not need to be included. The guiding video generally contains multiple guiding actions. The guiding part model and guiding bone points corresponding to each guiding action can be determined by relevant staff based on historical experimental data and uploaded to the supervision system. The specific content is not specifically limited in the embodiments of this application and can be set by relevant technical personnel.

[0067] The direction of the guidance skeleton points corresponding to each guidance action is different. By identifying the movement trajectory of the key guidance skeleton points in the real-time displayed guidance video, it is convenient to determine the guidance action in the real-time displayed guidance video. In order to facilitate the rapid identification of the guidance action, the relevant staff can determine the key guidance skeleton points from the guidance skeleton points corresponding to the guidance action in advance. The number of key guidance skeleton points is not specifically limited in the embodiments of the present application.

[0068] Step S120: obtaining a real-time follow-up training video, and identifying the follow-up training bone point corresponding to each guidance bone point from the real-time follow-up training video, wherein the real-time follow-up training video is a follow-up training video of the patient during the orthopedic training according to the displayed guidance video.

[0069] Specifically, the real-time follow-up video is a follow-up video of the patient practicing outside the hospital or at home at the current moment, which can be collected by an image acquisition device set at the follow-up device and uploaded to the supervision system. Based on the guidance skeleton point, the follow-up skeleton point corresponding to each guidance skeleton point is located from the real-time follow-up video. When locating the follow-up skeleton point from the real-time follow-up video, the patient's body contour can be first identified from the real-time follow-up video, and then each follow-up skeleton point can be identified from the body contour based on the preset human skeleton diagram. The specific identification method is not specifically limited in the embodiment of this application, as long as the follow-up skeleton point corresponding to each guidance skeleton point can be identified from the real-time follow-up video.

[0070] Step S130: Obtain the patient's basic following exercise part model based on the following exercise skeletal points, and determine the patient's following exercise pump data based on the basic following exercise part model, the following exercise skeletal points and the real-time following exercise video. The basic following exercise part model is determined based on the patient's treatment information and human body parameter information.

[0071] Specifically, a simulated human model corresponding to the patient can be constructed based on the patient's treatment information and human body parameter information, wherein the human body parameter information includes basic information such as height and weight, and the patient's treatment information includes the patient's current scoliosis status. Since the scoliosis conditions corresponding to different patients are unique, including the type, position, angle of scoliosis and the impact on other parts of the patient's body, therefore, constructing a simulated human model of the patient based on the patient's human body parameter information and treatment information facilitates accurate reflection of the patient's true condition. The patient's treatment information and human body parameter information can be uploaded to the supervision system by the patient himself, and can also be uploaded to the supervision system by the relevant doctor. The specific upload method is not specifically limited in the embodiments of this application.

[0072] Based on the training bone points, the basic training part model of the patient is determined from the simulated human body model, wherein the basic training part model at least includes all the training bone points. By viewing and analyzing the pump sense data generated by the basic training part model, rather than viewing and analyzing the pump sense data generated by the simulated human body model, it is convenient to improve the attention of patients or relevant staff to the training effect corresponding to the training part. The training pump sense data refers to the movement of the training bone points during the training process, which causes a large amount of blood to flow into the muscles corresponding to the training parts, causing muscle swelling and congestion. In addition, as the patient's training bone points move during the training process, the fibers in the muscles are activated to enhance the patient's muscle strength, improve basic flexibility and balance, etc., thereby correcting the scoliosis state.

[0073] Furthermore, the specific process of determining the patient's follow-up pump data based on the basic follow-up part model, the follow-up bone points, and the real-time follow-up video may include:

[0074] Identify the simulated following bone point corresponding to each following bone point in the basic following part model, and bind each simulated following bone point to the corresponding following bone point to obtain the target following part model; drive the target following part model based on the real-time following video to obtain the following bone trajectory corresponding to each moment, and determine the following change parameters corresponding to each moment based on the mapping relationship between the following bone trajectory corresponding to each moment and the preset change parameters, the preset change parameter mapping relationship is the correspondence between the following bone trajectory and the following change parameters, and the following change parameters include the increase in blood flow and the amount of fiber activation; integrate the following change parameters corresponding to each moment in the preset time period to determine the patient's following pump data.

[0075] Specifically, each follow-up bone point of the patient in the actual simulated follow-up is bound to the simulated follow-up bone point in the basic follow-up part model. Through the binding process between the bone points, it is convenient to ensure that the movement of each follow-up bone point of the patient in the actual follow-up process is accurately reflected on the basic follow-up part model. By reflecting the follow-up behavior on the basic follow-up part model, it is convenient for the patient to intuitively view the changes or stress states of each follow-up bone point during the follow-up process. After the binding of the follow-up bone point and the simulated follow-up bone point is completed, the basic follow-up part model can be deformed according to the movement of the simulated bone point through skinning technology. It is necessary to adjust the movement range and limit of the simulated follow-up bone point to prevent the basic follow-up part model from unnatural distortion or penetration during movement.

[0076] The target follow-up part model is driven based on the real-time follow-up video, that is, the simulated follow-up skeletal points in the target follow-up part model are controlled to move according to the movement trajectory of each follow-up skeletal point in the real-time follow-up video, that is, by driving the target follow-up part model, the patient's follow-up behavior is displayed through the basic part model. Different follow-up skeletal trajectories correspond to different follow-up change parameters. For example, when the guided action is to raise a wooden stick for correction, the follow-up change parameters corresponding to holding the wooden stick with both hands in parallel and raising it above the head are different from the follow-up change parameters corresponding to holding the wooden stick with both hands in parallel and lowering it to the chest. Based on the preset change parameter mapping relationship, the follow-up change parameters corresponding to each follow-up skeletal trajectory can be determined, wherein the specific content of the preset change parameter mapping relationship is not specifically limited in the embodiments of the present application, and can be determined by relevant staff based on historical experimental data and uploaded to the supervision system. The specific content of the preset change parameter mapping relationship is not specifically limited in the embodiments of the present application.

[0077] After determining the follow-up training change parameters corresponding to each moment in the preset time period based on the above method, the follow-up training change parameters corresponding to each moment in the preset time period are integrated to determine the follow-up training pump feeling data corresponding to the patient's follow-up training in the preset time period. The preset time period corresponds to a duration of 20 minutes or 30 minutes. The specific duration is not specifically limited in the embodiments of the present application.

[0078] Step S140: Determine the corresponding guidance pump data based on the guidance part model, guidance bone points and real-time display guidance video, compare the follow-up pump data with the guidance pump data, determine the patient's follow-up score, and provide feedback on the follow-up score.

[0079] Specifically, the specific implementation method of determining the corresponding guidance pump feeling data based on the guidance part model, guidance skeletal points, and real-time display guidance video can refer to the method of determining the patient's follow-up pump feeling data based on the basic follow-up training part model, follow-up training skeletal points, and real-time follow-up training video in the above-mentioned embodiment, which will not be repeated here. After determining the follow-up pump feeling data and the guidance pump feeling data, the two can be data matched to determine the data matching value. The higher the data matching value, the higher the corresponding follow-up score. The follow-up score corresponding to the data matching value can be determined based on the preset score mapping relationship. The preset score mapping relationship is the corresponding relationship between the data matching value and the follow-up score. It can be determined by relevant staff based on historical experimental data and uploaded to the supervision system. The specific content is not specifically limited in the embodiments of this application.

[0080] For the embodiments of the present application, a guidance part model is determined from the real-time guidance video, and then the corresponding following part model of the patient during the following practice is determined based on the guidance part model. Finally, local supervision is performed by comparing the pump sensation data generated by the guidance part model and the following part model during the following practice, rather than supervising the entire body or all-round movements of the patient during the following practice. By locally supervising the patient's following practice behavior, it is convenient to focus the supervision attention on key parts or key movements, thereby facilitating the improvement of the accuracy of judging whether the patient's following practice movements meet the standards. In addition, in the process of local supervision, problems in the patient's following practice movements can be discovered more promptly, so as to provide targeted feedback and suggestions, thereby improving the safety of the patient during the following practice.

[0081] Furthermore, in order to intuitively display the changes in the pump feeling of the patient's training part during the training process, the training change parameters corresponding to each moment in the preset time period are integrated to determine the patient's training pump feeling data, which may specifically include:

[0082] Based on the guided actions, the preset time period is divided into multiple sub-time periods, and the follow-up change parameters corresponding to each moment in each sub-time period are integrated to obtain a follow-up change parameter group corresponding to each sub-time period. Each follow-up change parameter group includes a blood flow parameter group and a fiber activation parameter group.

[0083] Specifically, the preset time period can be divided according to a preset division strategy, wherein, since different guided actions correspond to different execution difficulties, the patient's response time when following different guided actions is also different, and therefore different guided actions correspond to different preset division strategies. The preset division strategy is that after the preset time period is divided, the division time corresponding to each sub-time period, the higher the execution difficulty, the longer the corresponding division time.

[0084] Each sub-time period includes at least two moments, and the follow-up training change parameters corresponding to each moment in each sub-time period are integrated, that is, the follow-up training change parameters corresponding to at least two moments in each sub-time period are integrated into a follow-up training change parameter group, and the follow-up training change parameter group is composed of a blood flow parameter group and a fiber activation parameter group, wherein the blood flow parameter group includes the blood flow increase corresponding to each moment in the corresponding sub-time period, and the fiber activation parameter group includes the fiber activation amount corresponding to each moment in the corresponding sub-time period.

[0085] The basic layer is determined according to the guidance action, and the sub-change layer of each follow-up change parameter group in the corresponding sub-time period is determined according to each follow-up change parameter group and the basic layer.

[0086] Specifically, different guided movements correspond to different basic layers, and the sub-change layer of each follow-up variation parameter group in the corresponding sub-time period is determined, that is, the pumping data generated by the patient when following a certain guided movement is visualized, wherein the basic layer corresponding to the guided movement can be the basic blood flow and basic fiber activation of the corresponding part of the guided movement. By mapping the increase in blood flow and fiber activation corresponding to each moment in each follow-up variation parameter group to the basic layer, the sub-change layer of each follow-up variation parameter group in the corresponding sub-time period can be obtained. In the process of mapping the increase in blood flow and fiber activation corresponding to each moment in the follow-up variation parameter group to the basic layer, it may involve converting the data value into color, size, shape or other visual attributes for representation on the basic layer.

[0087] The corresponding sub-change layers are superimposed according to the order of each sub-time period within the preset time period to obtain the patient's follow-up pump feeling data.

[0088] Specifically, after determining the sub-change layer corresponding to each sub-time period, different colors and transparencies can be set for each sub-change layer to ensure that the information between layers does not block each other. By constructing a sub-change layer for each follow-up change parameter group and superimposing each sub-change layer in sequence, it is convenient to intuitively display the changes in the patient's pumping sensation in the follow-up part during the follow-up process. Through a visual expression method, it is convenient to enhance the patient's follow-up experience, so that the patient can more intuitively feel the changes brought about by the follow-up, thereby facilitating the improvement of the enthusiasm and satisfaction of the follow-up.

[0089] Furthermore, in order to improve the accuracy of the patient's training, the method provided in the embodiment of the present application further includes steps S1 to S4, such as Figure 2 As shown, where:

[0090] Step S1: When it is detected that the follow-up practice is over, the follow-up practice scores corresponding to the follow-up practice movements when the patient follows each guided movement during the current follow-up practice are integrated, and each follow-up practice score is compared with a preset score threshold, and a difference follow-up practice movement is determined from all the follow-up practice movements, and the follow-up practice score of the difference follow-up practice movement is lower than the preset score threshold.

[0091] Specifically, the duration corresponding to the current follow-up training cycle is consistent with the duration corresponding to the instruction video. The follow-up training result indicates that the patient has completed the follow-up orthopedic training according to the instruction video. When it is detected that the instruction video has been played, it can be determined that the follow-up training is over. The patient can also determine that the follow-up training is over by clicking the follow-up training completion button displayed on the follow-up training device interface. The specific method of determining the end of the follow-up training is not specifically limited in the embodiments of the present application.

[0092] Obtain the follow-up practice score of the patient for each guided action during the current follow-up practice period, and compare the follow-up practice score corresponding to each guided action with the preset score threshold, and determine the difference follow-up practice action whose follow-up practice score is lower than the preset score threshold from all the follow-up practice actions. The preset score threshold can be 85 or 95. The specific score is not specifically limited in the embodiments of the present application and can be set by relevant technical personnel. The number of difference follow-up practice actions can be 0, 1, 2 or more, and the specific number is not specifically limited in the embodiments of the present application. When the number of difference follow-up practice actions is 0, it indicates that all the follow-up practice actions of the patient in the orthopedic follow-up practice process have met the standards.

[0093] Step S2: When there are multiple difference following exercises, obtain at least one following skeleton point corresponding to each difference following exercise, and count the occurrence frequency of each following skeleton point in all difference following exercises.

[0094] Specifically, when there are multiple differential follow-up movements, it may indicate that the patient has insufficient technical mastery of the guided movements during the orthopedic follow-up training process. However, substandard follow-up movements may cause the muscles or bone points of the follow-up training area to bear loads beyond the normal range, which may increase the risk of injury. For example, when the follow-up movement has a large amplitude, it may cause excessive extension or compression of the joints corresponding to the follow-up training area, thereby causing joint injury. Therefore, when there are multiple differential follow-up movements, it is necessary to analyze the bone points of all differential follow-up movements, and then accurately correct the patient's follow-up movements during the next follow-up period based on the analysis results.

[0095] Different following exercises may correspond to different following bone points. By counting the frequency of occurrence of each following bone point in all different following exercises, it is possible to evaluate the patient's use of each following bone point during the orthopedic following exercise, as well as the probability of abnormal conditions at each following bone point.

[0096] Step S3: sorting all the following practice skeleton points based on the frequency of occurrence of each following practice skeleton point, determining the following practice skeleton points that are higher than the preset order as the focus skeleton points, and determining the difference following practice actions containing the focus skeleton points as the focus following practice actions.

[0097] Specifically, all the follow-up skeletal points are sorted according to the frequency of occurrence of each follow-up skeletal point to obtain a skeletal point sequence. The preset order is related to the number of focus skeletal points. For example, when the preset order is 4, the first 3 follow-up skeletal points in the skeletal point sequence are determined as focus skeletal points. The number of focus skeletal points is not specifically limited in the embodiment of the present application, and the specific preset order can be set by relevant technical personnel. For the convenience of description, the difference follow-up action containing the focus skeletal point can be determined as the focus follow-up action, wherein the follow-up skeletal points corresponding to the focus follow-up action may include 1 focus skeletal point or multiple focus skeletal points.

[0098] Step S4: Based on each focus practice movement and the corresponding guidance movement, determine the guidance prompts to be corrected for each focus skeletal point in the corresponding focus practice movement, and when it is detected that a new focus skeletal point appears in the real-time practice video of the patient during the next practice, based on the guidance movement corresponding to the new focus skeletal point, the corresponding guidance prompts to be corrected are fed back to the patient during the patient's practice.

[0099] Specifically, for any focused follow-up exercise, after determining the focused follow-up exercise, the content that needs to be corrected needs to be determined based on the orthopedic standard corresponding to the focused follow-up exercise, and the content that needs to be corrected is organized as a guide prompt to be corrected, which is used to remind the patient to follow the orthopedic standard during the next follow-up exercise. The orthopedic standard corresponding to the focused follow-up exercise is the guiding action corresponding to the focused follow-up exercise, including but not limited to the execution intensity and execution posture of the guiding action.

[0100] Furthermore, based on the focused follow-up action and the corresponding guidance action, determining the guidance prompt to be corrected of the focused skeletal point in the corresponding focused follow-up action may specifically include:

[0101] Determine the guiding action corresponding to the focused and followed action as the focused guiding action, and determine the focused guiding pump data corresponding to the focused guiding action and the focused and followed practice pump data corresponding to the focused and followed practice action based on the guiding pump data and the followed practice pump data; determine the pump difference based on the focused guiding pump data and the focused and followed practice pump data, and determine the intensity to be corrected corresponding to the focused bone point based on the pump difference and the preset intensity mapping relationship, and the preset intensity mapping relationship is the correspondence between the pump difference and the intensity to be corrected; determine the focused guiding edge data corresponding to the focused guiding action and the focused and followed practice edge data corresponding to the focused and followed practice action from the real-time displayed guiding video and the real-time followed practice video; determine the posture to be corrected corresponding to the focused bone point based on the focused guiding edge data and the focused and followed practice edge data; determine the guidance prompt to be corrected for the focused bone point in the corresponding focused and followed practice action based on the intensity to be corrected and the posture to be corrected.

[0102] Specifically, for the convenience of description, the guided action corresponding to the focused follow-up exercise can be determined as the focused guided action. The guided pump feeling data includes pump feeling data corresponding to multiple guided actions. When determining the focused guided pump feeling data corresponding to the focused guided action from the guided pump feeling data, the guided time period of the focused guided action can be first determined from the guided video, and the focused guided pump feeling data can be intercepted from the guided pump feeling data based on the guided time period. The focused follow-up exercise pump feeling data corresponding to the focused guided action can be determined from the follow-up exercise pump feeling data in the above manner. The specific determination method will not be described in detail here. The focused guided pump feeling data is the blood flow and fiber activation of the corresponding guided part after following the focused guided action within the guided time period. Correspondingly, the focused follow-up exercise pump feeling data is the blood flow and fiber activation of the corresponding follow-up exercise part after the patient follows the focused follow-up exercise within the follow-up exercise time period corresponding to the guided time period.

[0103] When the focus-following action is inconsistent with the focus-guiding action, the focus-following pump feeling data corresponding to the focus-following action is different from the focus-guiding pump feeling data corresponding to the focus-guiding action, and the lower the matching between the focus-following action and the focus-guiding work, the greater the pump feeling difference between the corresponding focus-following pump feeling data and the focus-guiding pump feeling data, and different pump feeling differences correspond to different intensities to be corrected, wherein the intensity to be corrected corresponding to any pump feeling difference can be determined according to a preset intensity mapping relationship, and the preset intensity mapping relationship can be determined by relevant staff according to historical experimental data and uploaded to the supervision system, and the specific content of the mapping relationship is not specifically limited in the embodiments of the present application. Since the execution intensity can directly affect the pump feeling data in the follow-up training process, the intensity to be corrected in the follow-up training process is determined by the pump feeling difference between the focus-following pump feeling data and the focus-guiding pump feeling data in the embodiments of the present application.

[0104] In addition, the following posture of the practice action will also affect the patient's degree of completion of the guidance work. If the difference between the following posture of the practice action and the guidance posture of the corresponding guidance action is large, it will also affect the patient's corrective effect. Therefore, in the example of the present application, the posture to be corrected corresponding to the focus bone point is determined based on the focus guidance edge data and the focus following edge data. Among them, the edge recognition algorithm can be used to determine the focus guidance edge data corresponding to the focus guidance action and the focus following edge data corresponding to the focus following action from the real-time guidance video and the real-time following video. The specific edge recognition algorithm is not specifically limited in the embodiment of the present application, as long as the edge data of the focus guidance action and the focus following action can be identified.

[0105] The guidance prompt to be corrected includes the intensity to be corrected and the posture to be corrected corresponding to the focus and training action. When the patient follows the guidance prompt to be corrected, the focus and training action can reach the standard of the corresponding guided action. Based on the disclosure of the above embodiment, the guidance prompt to be corrected for each focus and training action can be determined.

[0106] Each guidance prompt to be corrected can be bound to the corresponding bone point of interest and the focused guiding action, so that when the focused guiding action appears again in the real-time following training video during the next following training period, the guidance prompt to be corrected corresponding to the bone point of interest and the focused guiding action will be fed back to the following training device to remind the patient to adjust his or her following training action according to the guidance prompt to be corrected. By determining the guidance to be corrected for each bone point of interest in the corresponding following training action based on each following training action and the corresponding guiding action, it is convenient to accurately point out the problems that the patient has when performing the corresponding action, thereby facilitating the effectiveness of the guidance prompt to be corrected, and further facilitating improving the accuracy of the patient's following training process.

[0107] Furthermore, in order to improve the pertinence and effectiveness of rehabilitation training, the method provided in the embodiment of the present application also includes:

[0108] Obtain follow-up information, and determine the change displacement corresponding to each abnormal skeletal point based on the follow-up information and the treatment information, the abnormal skeletal point being the skeletal point that occurs lateral position in the treatment information; determine the abnormal skeletal point whose change displacement is higher than a preset change threshold as a positive abnormal skeletal point, and determine the target adjustment value corresponding to the change displacement based on a mapping relationship between the change displacement and the preset adjustment value, the preset adjustment value mapping relationship being the correspondence between the change displacement and the target adjustment value; update the preset score threshold corresponding to the follow-up action containing the positive abnormal skeletal point based on the target adjustment value, and obtain the updated preset score threshold; based on the updated preset score threshold, judge whether the follow-up action containing the positive abnormal skeletal point in the real-time follow-up video during the next follow-up period is a difference follow-up action.

[0109] Specifically, follow-up information may be generated when a patient returns to the hospital for a follow-up visit after a course of treatment, and may be uploaded to the supervision system by the relevant doctor or patient. Based on the follow-up information, the patient's scoliosis recovery may be analyzed, and the patient's guidance video may be adjusted to improve the fit between the guidance video and the patient's actual condition, thereby improving the patient's correction effect. The larger the change displacement of the abnormal bone point, the better the recovery effect of the bone point during the correction process. When determining the change displacement corresponding to each abnormal bone point, the corresponding spinal bone diagram at the time of the visit may be compared with the follow-up spinal bone diagram corresponding to the follow-up information. The specific method of determining the change displacement is not specifically limited in the embodiments of the present application.

[0110] Specifically, when the change displacement of an abnormal bone point is higher than a preset change threshold, it indicates that the recovery state of the abnormal bone point is in line with expectations. At this time, the abnormal bone point whose change displacement is higher than the preset change threshold can be determined as a positive abnormal bone point. At the same time, the abnormal bone point whose change displacement is not higher than the preset change threshold can be determined as a reverse abnormal bone point.

[0111] The supervision standard for the positive bone points can be lowered during the subsequent patient training process. The specific adjustment value can be determined based on the mapping relationship between the change displacement and the preset adjustment value. The larger the change displacement, the larger the corresponding target adjustment value. The target adjustment value corresponding to any change displacement can be determined based on the preset adjustment value mapping relationship. The preset adjustment value mapping relationship can be determined by relevant staff based on historical experimental data and uploaded to the supervision system. The specific content is not specifically limited in the embodiments of the present application.

[0112] Lower the supervision standard for positive skeleton points, that is, lower the judgment standard for judging whether the follow-up action containing positive abnormal skeleton points is a differential follow-up action. For example, the follow-up action containing skeleton point a is the follow-up action g, and the preset score threshold for judging whether the follow-up action g is a differential follow-up action is 95, that is, when the follow-up score of the follow-up action g is lower than 95 points, it is determined that the follow-up action g is a differential follow-up action. At this time, if it is determined that skeleton point a is a positive abnormal skeleton point, and the target adjustment value corresponding to the positive abnormal skeleton point a is determined to be 5 based on the change displacement of the positive abnormal skeleton point a, at this time, the preset score threshold corresponding to the follow-up action of the positive abnormal skeleton point a can be updated based on the target adjustment value. The updated preset score threshold is 95-5=90, that is, during the next follow-up period, the preset score threshold for judging whether the follow-up action g is a difference follow-up action is 90, that is, when the follow-up score of the follow-up action g is lower than 90 points, it will be determined that the follow-up action g is a difference follow-up action.

[0113] By effectively managing and utilizing the patient's follow-up information, it is easy to understand the changes in abnormal bone points during the patient's follow-up training process, and adjust the preset score threshold for judging abnormal follow-up movements based on the changes, so as to improve the pertinence and effectiveness of rehabilitation training.

[0114] The present application embodiment provides a monitoring system, such as Figure 3 As shown, Figure 3 The monitoring system 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the monitoring system 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the monitoring system 300 does not constitute a limitation on the embodiments of the present application.

[0115] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0116] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The fact that only one line is used in the diagram does not mean that there is only one bus or only one type of bus.

[0117] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0118] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0119] The monitoring system includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The supervision system shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0120] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0121] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in any of the above embodiments is implemented.

[0122] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0123] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for supervising dynamic assisted correction of scoliosis, characterized in that: include: Acquire a real-time display guidance video, identify guidance actions contained in the real-time display guidance video, and determine a guidance part model and guidance bone points based on the guidance actions, wherein the real-time display guidance video is the orthopedic guidance content displayed on the display interface at the current moment; Acquire a real-time follow-up training video, and identify the follow-up training bone point corresponding to each guidance bone point from the real-time follow-up training video, wherein the real-time follow-up training video is a follow-up training video of the patient during the orthopedic training according to the displayed guidance video; Acquire a basic follow-up training part model of the patient based on the follow-up training skeletal points, and determine the follow-up training pump feeling data of the patient based on the basic follow-up training part model, the follow-up training skeletal points and the real-time follow-up training video, wherein the basic follow-up training part model is determined based on the treatment information and human body parameter information of the patient; Determine corresponding guidance pump data based on the guidance part model, the guidance skeletal point and the real-time displayed guidance video, compare the follow-up pump data with the guidance pump data, determine the follow-up score of the patient, and provide feedback on the follow-up score; Wherein, determining the patient's follow-up pump feeling data based on the basic follow-up part model, the follow-up skeletal points and the real-time follow-up video includes: Identify the simulated follow-up skeletal point corresponding to each follow-up skeletal point from the basic follow-up part model, and bind each simulated follow-up skeletal point to the corresponding follow-up skeletal point to obtain a target follow-up part model; Based on the real-time follow-up video, the target follow-up part model is driven to obtain the follow-up bone trajectory corresponding to each moment, and based on the mapping relationship between the follow-up bone trajectory corresponding to each moment and the preset change parameter, the follow-up change parameter corresponding to each moment is determined, wherein the preset change parameter mapping relationship is the corresponding relationship between the follow-up bone trajectory and the follow-up change parameter, and the follow-up change parameter includes the blood flow increase amount and the fiber activation amount; Integrate the follow-up training change parameters corresponding to each moment in the preset time period to determine the follow-up training pump feeling data of the patient; Among them, it also includes: When the end of the follow-up training is detected, the follow-up training scores corresponding to the follow-up training movements when the patient follows each guided movement during the current follow-up training are integrated, and each follow-up training score is compared with a preset score threshold, and a difference follow-up training movement is determined from all the follow-up training movements, and the follow-up training score of the difference follow-up training movement is lower than the preset score threshold; When the difference following exercises include multiple ones, obtaining at least one following skeleton point corresponding to each difference following exercise, and counting the occurrence frequency of each following skeleton point in all the difference following exercises; All the following practice skeleton points are sorted based on the frequency of occurrence of each following practice skeleton point, and following practice skeleton points with a higher order than a preset order are determined as focus skeleton points, and the difference following practice movements containing the focus skeleton points are determined as focus following practice movements; Based on each focus training action and the corresponding guidance action, determine the guidance prompt to be corrected for each focus skeletal point in the corresponding focus training action, and when it is detected that a new focus skeletal point appears in the real-time training video of the patient during the next training period, feedback the corresponding guidance prompt to be corrected to the patient during the patient's training based on the guidance action corresponding to the new focus skeletal point; Wherein, based on the focused follow-up action and the corresponding guidance action, determining the guidance prompt to be corrected of the focused skeletal point in the corresponding focused follow-up action includes: Determine the guidance action corresponding to the focus follow-up action as the focus guidance action, and determine the focus guidance pump feeling data corresponding to the focus guidance action and the focus follow-up pump feeling data corresponding to the focus follow-up action based on the guidance pump feeling data and the follow-up pump feeling data; Determine a pump difference based on the focused guidance pump data and the focused follow-up pump data, and determine the strength to be corrected corresponding to the focused skeletal point based on the pump difference and a preset strength mapping relationship, wherein the preset strength mapping relationship is a corresponding relationship between the pump difference and the strength to be corrected; Determine the focus guidance edge data corresponding to the focus guidance action and the focus follow-up training edge data corresponding to the focus follow-up training action from the real-time display guidance video and the real-time follow-up training video; Determine the posture to be corrected corresponding to the focus skeleton point based on the focus guidance edge data and the focus follow-up edge data; Based on the strength to be corrected and the posture to be corrected, a guidance prompt to be corrected of the focus skeletal point in the corresponding focus training action is determined.

2. A method for supervising dynamic assisted correction of scoliosis according to claim 1, characterized in that: The step of integrating the corresponding follow-up training change parameters at each moment in the preset time period to determine the follow-up training pump feeling data of the patient includes: Dividing the preset time period into a plurality of sub-time periods based on the guiding action, integrating the follow-up training change parameters corresponding to each moment in each sub-time period, and obtaining a follow-up training change parameter group corresponding to each sub-time period, wherein each follow-up training change parameter group includes a blood flow parameter group and a fiber activation parameter group; Determine a basic layer according to the guiding action, and determine a sub-change layer of each follow-up change parameter group in a corresponding sub-time period according to each follow-up change parameter group and the basic layer; The corresponding sub-change layers are superimposed according to the order of each sub-time period within the preset time period to obtain the patient's follow-up pump feeling data.

3. A method for dynamic assisted correction and training supervision of scoliosis according to claim 1, characterized in that: Also includes: Obtaining follow-up information, and determining the change displacement corresponding to each abnormal bone point based on the follow-up information and the treatment information, wherein the abnormal bone point is a bone point that has a lateral position in the treatment information; Determine an abnormal bone point whose change displacement is higher than a preset change threshold as a positive abnormal bone point, and determine a target adjustment value corresponding to the change displacement based on a mapping relationship between the change displacement and a preset adjustment value, wherein the preset adjustment value mapping relationship is a corresponding relationship between the change displacement and the target adjustment value; Based on the target adjustment value, a preset score threshold corresponding to the follow-up exercise including the positive abnormal skeletal point is updated to obtain an updated preset score threshold; Based on the updated preset score threshold, it is judged whether the following action containing the positive abnormal bone point in the real-time following action video during the next following action is a difference following action.

4. A monitoring system, characterized in that: The monitoring system includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a scoliosis dynamic assisted correction training supervision method as described in any one of claims 1-3.

5. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and execute a method for supervising dynamic assisted correction training of scoliosis as described in any one of claims 1-3.

6. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the steps of a method for supervising dynamic assisted correction training of scoliosis as described in any one of claims 1 to 3.

Images