An AI-assisted diagnosis and treatment system based on wearable active defense against sports injuries

Abstract

This invention relates to the field of sports injury prevention technology, and more particularly to an AI-assisted diagnosis and treatment system based on wearable active defense against sports injuries. The system includes a data acquisition module and a motion monitoring module. The motion monitoring module includes a risk assessment module for determining a risk assessment mode based on a comparison between movement continuity and a preset continuity mode; a mode determination module for optimizing the preset continuity mode based on the training injury density of several monitored subjects; a risk assessment unit for determining joint angle coordination and correcting the joint angle coordination based on the obstacle level of the sports field terrain and the tolerance level of the climate; and a level adjustment unit for determining whether the landing risk level is acceptable based on landing stability and optimizing the landing risk level based on the difference in pressure distribution between the two feet. This invention improves the safety of the monitored subject during exercise.

Description

Technical Field

[0001] This invention relates to the field of sports injury prevention technology, and in particular to an AI-assisted diagnosis and treatment system based on wearable active defense against sports injuries. Background Technology

[0002] In military training, competitive sports, and daily physical fitness exercises, the landing phase is a high-risk stage for sports injuries due to the instantaneous absorption of the body's weight and inertia. Especially during landing imbalance, acute injuries such as knee ligament tears and ankle sprains are easily caused, seriously affecting sports safety and training continuity. Traditional sports protection methods mostly rely on post-injury treatment or real-time human supervision, making it difficult to accurately predict landing risks. Human observation suffers from reaction delays and subjective biases, failing to capture early signs of landing imbalance such as abnormal posture and center of gravity shifts during exercise. Existing monitoring equipment also focuses primarily on monitoring physiological indicators after injury, lacking the ability to dynamically analyze and correlate risks with movement and posture data during exercise, resulting in a technological gap in pre-landing early warning intervention. To address this pain point, there is an urgent need to build an intelligent system based on wearable sensing technology. This system would collect key posture data such as center of gravity trajectory, joint angles, and limb symmetry during exercise in real time, combined with AI algorithms to predict landing imbalance risks in advance and trigger precise alerts before landing. This would achieve a proactive protection upgrade from post-injury treatment to pre-landing defense, significantly improving safety during sports.

[0003] Chinese Patent Application Publication No. CN117731243A discloses a method and system for auxiliary diagnosis of foot sports injuries based on gait data features. The method includes: data preprocessing, gait data feature space construction, injury auxiliary diagnosis, and effectiveness verification. This invention solves the problem of the lack of intelligent and accurate diagnostic methods in the existing diagnosis and treatment of foot sports injuries. Based on the collection of foot movement information of the subject, the method uses the Heidelberg foot measurement method to refine the range of motion of the joints during natural walking, establishes the gait data feature space of foot injuries, and realizes auxiliary diagnosis of foot sports injuries. This method and system provide a new and effective intelligent auxiliary tool for quantitative, comprehensive, and convenient diagnosis of foot injuries. At the same time, it also provides necessary anthropometry basis for research and application in related fields such as the development of foot rehabilitation aids and the development of lower limb exoskeleton robots.

[0004] The existing technology also has the following problems: the existing technology for sports injuries mostly relies on post-injury treatment or real-time human supervision, which makes it difficult to accurately predict and promptly warn of landing risks, resulting in excessive impact at the moment of landing and causing sports injuries, thereby reducing the safety of the sports process. Summary of the Invention

[0005] To address this issue, the present invention provides an AI-assisted diagnosis and treatment system based on wearable active defense against sports injuries, which overcomes the problem in existing technologies that make it difficult to accurately predict and promptly warn of landing risks during exercise, resulting in excessive impact at the moment of landing and causing sports injuries, thereby reducing the safety of the exercise process.

[0006] To achieve the above objectives, the present invention provides an AI-assisted diagnosis and treatment system based on wearable active defense against sports injuries, comprising:

[0007] The data acquisition module includes several wearable motion capture sensors for collecting motion data of the monitored subject, wherein the motion data includes center of gravity position, joint angles and pressure distribution;

[0008] A motion monitoring module, which is connected to the data acquisition module, includes,

[0009] The pattern determination unit is used to determine the motion continuity of the monitored subject based on the center of gravity trajectory formed by several center of gravity positions during the movement of the monitored subject, to determine the risk assessment pattern based on the comparison result of the motion continuity with the preset continuity, and to optimize the preset continuity based on the training injury density of several monitored subjects.

[0010] A risk assessment unit is used to determine the joint angle coordination degree based on several joint angles of the monitoring subject under a defined risk assessment mode, and to correct the joint angle coordination degree based on the obstacle level of the sports field terrain and the climate tolerance level, so as to determine the landing risk level of the monitoring subject based on the joint angle coordination degree.

[0011] The level adjustment unit is used to determine the landing stability based on the center of gravity offset distance of the monitored subject at the moment of landing, to determine whether the landing risk level is qualified based on the landing stability, and to optimize the landing risk level based on the pressure distribution difference of the two feet if the landing risk level is determined to be unqualified.

[0012] Furthermore, the risk assessment unit establishes a center of gravity trajectory based on the real-time center of gravity position of the monitored subject during the training process, and determines the standard deviation of several deviation amplitudes between the center of gravity trajectory and the corresponding motion frames of the standard trajectory as the motion continuity.

[0013] Furthermore, the risk assessment unit determines the risk assessment mode based on the comparison result of the action coherence being less than the preset coherence.

[0014] The risk assessment unit determines the assessment of movement risk using an immediate protection risk assessment mode based on the comparison result that the motion continuity is greater than or equal to the preset continuity.

[0015] Furthermore, the risk assessment unit determines the optimization of the preset coherence based on the comparison result of the training injury occurrence density being greater than the preset density. In this case, several coherence optimization coefficients are set based on the comparison result of the density difference between the training injury occurrence density and the preset density and the preset difference, so as to reduce the preset coherence according to the several coherence optimization coefficients.

[0016] Furthermore, the risk assessment unit determines several joint angles based on the real-time movements of the monitored subject, and determines the joint angle coordination degree by multiplying the percentage of the several joint angles with the corresponding preset angles.

[0017] Furthermore, the risk assessment unit determines, based on the comparison result that the obstacle level is greater than the preset obstacle level and the tolerance level is greater than the preset tolerance level, to correct the joint angle coordination with a first coordination correction coefficient.

[0018] The risk assessment unit determines, based on the comparison result that the obstacle level is less than or equal to the preset obstacle level and the tolerance level is less than or equal to the preset tolerance level, to correct the joint angle coordination with a second coordination correction coefficient.

[0019] The risk assessment unit determines to correct the joint angle coordination degree with a third coordination degree correction coefficient based on the comparison results of the obstacle level being greater than the preset obstacle level and the tolerance level being less than or equal to the preset tolerance level, or the obstacle level being less than or equal to the preset obstacle level and the tolerance level being greater than the preset tolerance level.

[0020] Furthermore, the risk assessment unit determines the landing risk level as Level 3 based on the comparison result that the joint angle coordination degree is greater than or equal to the first preset coordination degree;

[0021] The risk assessment unit determines the landing risk level as Level II based on the comparison result that the joint angle coordination degree is less than the first preset coordination degree and greater than or equal to the second preset coordination degree;

[0022] The risk assessment unit determines the landing risk level as Level 1 based on the comparison result that the joint angle coordination degree is less than the second preset coordination degree.

[0023] Furthermore, the level adjustment unit determines the distance between the vertical projection point of the center of gravity of the monitored subject on the ground at the moment of landing and the center of the double-foot support surface as the center of gravity offset distance, and determines the ratio of the center of gravity offset distance to the diagonal length of the double-foot support surface as the landing stability.

[0024] Furthermore, the level adjustment unit determines that the landing risk level is unqualified based on the comparison result of the landing stability being greater than the preset stability.

[0025] Furthermore, when the landing risk level is determined to be unqualified, the level adjustment unit sets several level optimization methods based on the comparison result of the bipedal pressure distribution difference and the preset distribution difference to optimize the landing risk level.

[0026] Compared with existing technologies, the advantages of this invention lie in that it determines the risk assessment mode by monitoring the continuity of the subject's movements during exercise. Different risk assessment modes are adopted for different subjects. For subjects with high movement continuity, a trend-optimized risk assessment mode is used, employing historical training data trends as the assessment standard. For subjects with low movement continuity, an immediate protection risk assessment mode is used, employing real-time collected data as the assessment standard. Simultaneously, the preset continuity is adjusted based on the density of training injuries, fully considering individual differences of the subject, scene characteristics, and differences in risk triggers, making risk alerts and intervention measures more tailored to the subject's needs. Under the determined risk assessment mode, the joint angle coordination of the subject is corrected based on the terrain and climate of the sports field, and then adjusted according to the joint... Joint angle coordination determines the landing risk level. When joint angle coordination is high, each joint can buffer the impact force in an orderly manner according to biomechanical laws, avoiding excessive stress on a single joint, and significantly reducing the landing risk level. When joint angle coordination is low, the angle coordination between joints is unbalanced, which can lead to interruption or local concentration of impact force transmission, easily causing injuries such as ligament sprains and bone contusions, and significantly increasing the landing risk level. At the same time, when the terrain obstacle level is high and the climate tolerance level is high, the requirements for joint angle coordination will be even higher by changing the landing support conditions and the physiological state of the human body. Therefore, reducing the joint angle coordination according to the terrain obstacle level and the climate tolerance level makes the landing risk level judgment more in line with the actual scenario, thereby issuing more accurate warnings to the monitoring subject and improving the safety of the movement process.

[0027] Furthermore, this invention determines landing stability by monitoring the distance of the center of gravity shift at the moment of landing. Higher landing stability indicates that the warning issued for the landing risk level is more in line with the needs of the monitored subject, and the landing risk level is qualified. Lower landing stability indicates that the landing risk level is unqualified, and the warning issued based on the landing risk level does not meet the needs of the monitored subject. Therefore, the landing risk level is optimized based on the pressure distribution difference between the two feet, providing warnings that are more in line with the individual differences of the monitored subject for subsequent monitoring processes, thereby further improving the safety of the movement process. Attached Figure Description

[0028] Figure 1 This is a structural block diagram of an AI-assisted diagnosis and treatment system for active defense against wearable sports injuries, as described in an embodiment of the present invention.

[0029] Figure 2 A flowchart for determining the risk assessment model in an embodiment of the present invention;

[0030] Figure 3 This is a flowchart illustrating how to determine whether to optimize a preset coherence level in an embodiment of the present invention.

[0031] Figure 4 This is a flowchart illustrating whether the risk level of an embodiment of the present invention is qualified. Detailed Implementation

[0032] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0033] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0034] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0035] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0036] Please see Figures 1-4 As shown, Figure 1 This is a structural block diagram of an AI-assisted diagnosis and treatment system for active defense against wearable sports injuries, as described in an embodiment of the present invention. Figure 2 A flowchart for determining the risk assessment model in an embodiment of the present invention; Figure 3 This is a flowchart illustrating how to determine whether to optimize a preset coherence level in an embodiment of the present invention. Figure 4 This is a flowchart illustrating whether the risk level of an embodiment of the present invention is qualified.

[0037] This invention provides an AI-assisted diagnosis and treatment system for active defense against wearable sports injuries, comprising:

[0038] The data acquisition module includes several wearable motion capture sensors for collecting motion data of the monitored subject, wherein the motion data includes center of gravity position, joint angles and pressure distribution;

[0039] A motion monitoring module, which is connected to the data acquisition module, includes,

[0040] The pattern determination unit is used to determine the motion continuity of the monitored subject based on the center of gravity trajectory formed by several center of gravity positions during the movement of the monitored subject, to determine the risk assessment pattern based on the comparison result of the motion continuity with the preset continuity, and to optimize the preset continuity based on the training injury density of several monitored subjects.

[0041] A risk assessment unit is used to determine the joint angle coordination degree based on several joint angles of the monitoring subject, and to correct the joint angle coordination degree based on the obstacle level of the sports field terrain and the climate tolerance level, so as to determine the landing risk level of the monitoring subject based on the joint angle coordination degree.

[0042] The level adjustment unit is used to determine the landing stability based on the center of gravity offset distance of the monitored subject at the moment of landing, to determine whether the landing risk level is qualified based on the landing stability, and to optimize the landing risk level based on the pressure distribution difference of the two feet if the landing risk level is determined to be unqualified.

[0043] An alarm module, which is connected to the motion monitoring module, is used to issue corresponding alarms based on the landing risk level.

[0044] Specifically, the wearable motion capture sensor, such as the Xsens wearable motion capture system, can capture the body's motion data in real time by placing miniature inertial sensors on various parts of the body; no specific limitation is made.

[0045] In practice, this invention combines the historical movement data of the monitored subject with military training standards and sports medicine databases. It uses AI algorithms to determine the individual physical fitness baseline of the monitored subject and determines the corresponding training plan based on the individual physical fitness baseline. During the execution of the training plan, the monitored subject's movement data is collected in real time for monitoring and reminders.

[0046] Specifically, the risk assessment unit establishes a center of gravity trajectory based on the real-time center of gravity position of the monitored subject during the training process, and determines the standard deviation of several deviation amplitudes between the center of gravity trajectory and the corresponding motion frames of the standard trajectory as the motion continuity.

[0047] Specifically, the risk assessment unit determines the risk assessment mode based on the comparison result that the motion continuity is less than the preset continuity.

[0048] The risk assessment unit determines the assessment of movement risk using an immediate protection risk assessment mode based on the comparison result that the motion continuity is greater than or equal to the preset continuity.

[0049] Understandably, the center of gravity position is a core quantitative indicator of balance control and movement coordination in human movement. Its changing pattern directly reflects the smoothness, stability, and biomechanical rationality of the movement. The essence of continuous movement is that the various parts of the human body coordinate in an orderly manner according to the preset movement logic. At this time, the center of gravity will show a smooth and regular curve change with the progress of the movement. For example, when running, the center of gravity first sinks slightly to buffer the landing, and then rises with the push-off. The curve has no abrupt fluctuations. However, when the movement is not continuous, such as when the movement is stuck, the force is disjointed, or the balance is lost, the center of gravity will suddenly shift, oscillate abnormally, or become disordered due to the imbalance of the coordination of the body parts. This regularity can be quantified by calculating the standard deviation of the deviation of the center of gravity trajectory from the standard trajectory corresponding to the movement frames: the smaller the standard deviation, the more stable the center of gravity shift in each movement frame is, the smooth the transition of the center of gravity in each stage of the movement, and the high degree of movement continuity; the larger the standard deviation, the more irregular the center of gravity shift is, the more violent the fluctuations are, the disjointed or compensatory coordination of the various parts of the movement exists, and the low degree of movement continuity. The risk of injury for those with high mobility is more due to long-term cumulative effects than immediate imbalance, while the risk of injury for those with low mobility is mainly immediate and sudden.

[0050] Specifically, the difference between the trend optimization risk assessment mode and the real-time protection assessment mode lies in the different ways of determining the thresholds. In the trend optimization risk assessment mode, the thresholds are determined based on the historical movement process of the monitored subject, while in the real-time protection risk assessment mode, the thresholds are values ​​output by the AI ​​algorithm based on the individual physical fitness baseline of the monitored subject.

[0051] Specifically, the preset coherence degree is set to a value range of [5%, 10%], and preferably 8% in this embodiment of the invention.

[0052] Specifically, the risk assessment unit determines the optimization of the preset coherence degree based on the comparison result that the training injury occurrence density is greater than the preset density;

[0053] The risk assessment unit determines not to optimize the preset coherence based on the comparison result that the training injury occurrence density is less than or equal to the preset density;

[0054] Specifically, several coherence optimization coefficients are set based on the comparison results of the density difference between the training injury occurrence density and the preset density and the preset difference, so as to reduce the preset coherence according to the several coherence optimization coefficients.

[0055] Specifically, the risk assessment unit determines to reduce the preset coherence by using a first coherence optimization coefficient based on the comparison result that the density difference is greater than the preset difference.

[0056] The risk assessment unit determines, based on the comparison result that the density difference is less than or equal to the preset difference, to reduce the preset coherence by using a second coherence optimization coefficient.

[0057] Specifically, the training injury density is the frequency of training injuries occurring per unit of trainee per unit of time.

[0058] Specifically, the preset density is set to a range of [2 times / 100h, 5 times / 100h], preferably 4 times / 100h in this embodiment of the invention; the preset difference is set to a range of [1 time / 100h, 3 times / 100h], preferably 2 times / 100h in this embodiment of the invention; the first continuity optimization coefficient is set to a range of [0.8, 0.88], preferably 0.85 in this embodiment of the invention; and the second continuity optimization coefficient is set to a range of [0.89, 0.93], preferably 0.91 in this embodiment of the invention.

[0059] In practice, the preset coherence is the core criterion for distinguishing between the trend-optimized risk assessment mode and the immediate protection risk assessment mode. Its rationality directly determines the accuracy of the risk assessment mode. When the density of training injuries is greater than the preset density, it indicates that the existing preset coherence does not match the risk characteristics of the actual training scenario. The existing preset coherence may be too low, causing some actions that should be judged as low coherence to be misjudged as high coherence due to the low threshold. As a result, the immediate risk is not intervened in time and eventually turns into actual injury.

[0060] Specifically, the risk assessment unit determines several joint angles based on the real-time movements of the monitored subject, and determines the joint angle coordination degree by multiplying the percentage of the several joint angles with the corresponding preset angles.

[0061] Specifically, joint angle refers to the angle formed between two adjacent bones at the joint. The measurement of joint angle is based on the anatomical axis of the bone. The vertex of the angle corresponds to the center of rotation of the joint. Usually, the anatomical neutral position is taken as the starting point of the angle (0°). The deviation from the neutral position is the joint angle value. For example, the elbow joint is 0° when it is straight and is called elbow joint flexion 90° when it is bent.

[0062] Understandably, different movements correspond to different preset angles. Preset angles refer to the ideal angle benchmarks or reasonable ranges set for key joints in a specific exercise, training scenario, or rehabilitation goal, based on human anatomy principles, biomechanical safety, and the effectiveness of movement function. For example, squats involve the coordinated flexion and extension of the hip, knee, and ankle joints. The preset angle range for the hip joint is 80° to 90°, the preset angle range for the knee joint is 90° to 110°, and the preset angle range for the ankle joint is 15° to 20°. When running, the preset angle range for the hip joint is 25° to 30°, the preset angle range for the knee joint is 15° to 25°, and the preset angle range for the ankle joint is 10° to 15°.

[0063] Specifically, the risk assessment unit determines to correct the joint angle coordination degree with a first coordination degree correction coefficient based on the comparison result that the obstacle level is greater than the preset obstacle level and the tolerance level is greater than the preset tolerance level.

[0064] The risk assessment unit determines, based on the comparison result that the obstacle level is less than or equal to the preset obstacle level and the tolerance level is less than or equal to the preset tolerance level, to correct the joint angle coordination with a second coordination correction coefficient.

[0065] The risk assessment unit determines to correct the joint angle coordination degree with a third coordination degree correction coefficient based on the comparison results of the obstacle level being greater than the preset obstacle level and the tolerance level being less than or equal to the preset tolerance level, or the obstacle level being less than or equal to the preset obstacle level and the tolerance level being greater than the preset tolerance level.

[0066] Understandably, different terrains and climates have a significant impact on the human body's support stability, balance requirements, and range of motion. Under low-obstacle terrain and low-tolerance climate conditions, the human body experiences less balance pressure and requires less joint angle coordination to maintain balance. However, under high-obstacle terrain and high-tolerance climate conditions, the human body experiences greater balance pressure and requires greater joint angle coordination to maintain balance. Therefore, appropriately reducing the real-time joint angle coordination of the monitoring subject based on terrain and climate can improve the risk level classification and thus enhance the safety of the monitoring subject during training.

[0067] Specifically, the obstacle level classification of terrain can be determined based on factors such as slope, road surface stability, obstacle density, terrain undulation and traffic mode restrictions, as shown in Table 1 for example, without specific limitations; the climate tolerance level classification can be determined based on factors such as temperature, humidity and wind speed, as shown in Table 2 for example, without specific limitations.

[0068] Table 1. Classification of Obstacle Levels in Terrain

[0069]

[0070] Table 2 Climate Tolerance Level Classification

[0071]

[0072]

[0073] Specifically, the preset obstacle level is level 3, the preset tolerance level is level 3, the value range of the first synergy correction coefficient is set to [0.6, 0.7], and the preferred value in this embodiment of the invention is 0.65; the value range of the second synergy correction coefficient is set to [0.81, 0.9], and the preferred value in this embodiment of the invention is 0.85; the value range of the third synergy correction coefficient is set to [0.71, 0.8], and the preferred value in this embodiment of the invention is 0.75.

[0074] Specifically, the risk assessment unit determines the landing risk level as level three based on the comparison result that the joint angle coordination degree is greater than or equal to the first preset coordination degree;

[0075] The risk assessment unit determines the landing risk level as Level II based on the comparison result that the joint angle coordination degree is less than the first preset coordination degree and greater than or equal to the second preset coordination degree;

[0076] The risk assessment unit determines the landing risk level as Level 1 based on the comparison result that the joint angle coordination degree is less than the second preset coordination degree.

[0077] Specifically, the first preset degree of synergy is set to a value range of [70%, 75%], with 72% preferred in this embodiment of the invention; the second preset degree of synergy is set to a value range of [50%, 60%], with 55% preferred in this embodiment of the invention.

[0078] It is understandable that there is a significant negative correlation between joint angle coordination and landing risk level: the higher the joint angle coordination, the more reasonable the force line matching and buffer distribution of multiple joints during landing, and the lower the landing risk level. Conversely, the lower the coordination, the more unbalanced the force transmission between joints and the excessive concentration of local load, and the higher the landing risk level.

[0079] Specifically, the level adjustment unit determines the distance between the vertical projection point of the center of gravity on the ground at the moment of landing and the center of the double-foot support surface as the center of gravity offset distance, and determines the landing stability as the ratio of the center of gravity offset distance to the diagonal length of the double-foot support surface.

[0080] Specifically, the foot support surface refers to the rectangular area formed by the lines connecting the heels and toes of both feet.

[0081] Specifically, the level adjustment unit determines that the landing risk level is qualified based on the comparison result that the landing stability is less than or equal to the preset stability;

[0082] The level adjustment unit determines that the landing risk level is unqualified based on the comparison result that the landing stability is greater than the preset stability.

[0083] Specifically, a smaller landing stability indicates a smaller center of gravity offset distance, which in turn indicates better stability of the monitored object at the moment of landing.

[0084] Specifically, the preset stability value range is set to [0.25, 0.4], and in this embodiment of the invention, 0.3 is preferred.

[0085] Specifically, when the landing risk level is determined to be unqualified, the level adjustment unit sets several level optimization methods based on the comparison result of the bipedal pressure distribution difference and the preset distribution difference to optimize the landing risk level.

[0086] Specifically, the level adjustment unit determines to raise the landing risk level by two based on the comparison result that the pressure distribution difference between the two feet is greater than the first preset distribution difference;

[0087] The level adjustment unit determines to raise the landing risk level by one based on the comparison result that the pressure distribution difference between the two feet is less than or equal to the first preset distribution difference and greater than the second preset difference;

[0088] The level adjustment unit determines that the landing risk level remains unchanged based on the comparison result that the pressure distribution difference between the two feet is less than the second preset distribution difference.

[0089] Specifically, the pressure distribution difference between the two feet refers to the ratio of the larger to the smaller value of the vertical pressure exerted on the left and right feet by the ground at the moment of landing. The further the ratio deviates from 1, the more unbalanced the force is and the worse the stability at the moment of landing.

[0090] Specifically, the value range of the first preset distribution difference is set to [1.8, 2.3], which is preferred in embodiment 2 of the present invention, and the value range of the second preset distribution difference is set to [1.2, 1.7], which is preferred in embodiment 1.5 of the present invention.

[0091] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. An AI-assisted diagnosis and treatment system based on a wearable active defense against sports injuries, characterized in that, The application comprises: a data acquisition module comprising a plurality of wearable motion capture sensors for acquiring motion data of a monitoring subject, wherein the motion data comprises center of mass position, joint angle and pressure distribution; a motion monitoring module connected with the data acquisition module, comprising, a mode determination unit for establishing a center of mass trajectory based on real-time center of mass position of the monitoring subject during training, determining a standard deviation of a plurality of deviation amplitudes of the center of mass trajectory corresponding to a standard trajectory as motion continuity, determining a risk assessment mode according to a comparison result of the motion continuity and a preset continuity, and optimizing the preset continuity based on training injury occurrence density of a plurality of monitoring subjects; a risk assessment unit for determining a plurality of joint angles based on real-time motion of the monitoring subject, determining joint angle coordination degree as a product of a plurality of the joint angles and a percentage corresponding to a preset angle, and correcting the joint angle coordination degree based on obstacle level of a motion field terrain and tolerance level of climate, to determine landing risk level of the monitoring subject based on the joint angle coordination degree; a level adjustment unit for determining landing stability based on center of mass offset distance at landing moment of the monitoring subject, determining whether the landing risk level is qualified based on the landing stability, and optimizing the landing risk level based on biped pressure distribution difference on condition that the landing risk level is unqualified; an alarm module connected with the motion monitoring module, for issuing corresponding alarm according to the landing risk level; the mode determination unit determines to assess motion risk in a trend optimization risk assessment mode based on a comparison result that the motion continuity is less than the preset continuity; the mode determination unit determines to assess motion risk in an instant protection risk assessment mode based on a comparison result that the motion continuity is greater than or equal to the preset continuity. 2.The AI-assisted diagnosis and treatment system based on wearable motion injury active defense according to claim 1, wherein, the mode determination unit determines to optimize the preset continuity based on a comparison result that the training injury occurrence density is greater than a preset density, wherein a plurality of continuity optimization coefficients are set based on a density difference value between the training injury occurrence density and the preset density and a comparison result of the density difference value and a preset difference value, to reduce the preset continuity according to a plurality of the continuity optimization coefficients. 3.The AI-assisted diagnosis and treatment system based on the wearable motion injury active defense according to claim 2, characterized in that, the risk assessment unit determines to correct the joint angle coordination degree with a first coordination degree correction coefficient based on a comparison result that the obstacle level is greater than a preset obstacle level and the tolerance level is greater than a preset tolerance level; the risk assessment unit determines to correct the joint angle coordination degree with a second coordination degree correction coefficient based on a comparison result that the obstacle level is less than or equal to the preset obstacle level and the tolerance level is less than or equal to the preset tolerance level; the risk assessment unit determines to correct the joint angle coordination degree with a third coordination degree correction coefficient based on a comparison result that the obstacle level is greater than the preset obstacle level and the tolerance level is less than or equal to the preset tolerance level, or the obstacle level is less than or equal to the preset obstacle level and the tolerance level is greater than the preset tolerance level. 4.The AI-assisted diagnosis and treatment system based on the wearable active defense against sports injuries according to claim 3, wherein, The risk assessment unit determines that the landing risk level is level three based on a comparison result that the joint angle coordination degree is greater than or equal to a first preset coordination degree; The risk assessment unit determines that the landing risk level is level two based on a comparison result that the joint angle coordination degree is less than the first preset coordination degree and greater than or equal to a second preset coordination degree; The risk assessment unit determines that the landing risk level is level one based on a comparison result that the joint angle coordination degree is less than the second preset coordination degree. 5.The AI-assisted diagnosis and treatment system based on wearable motion injury active defense according to claim 4, characterized in that, The level adjustment unit determines a distance between a vertical projection point of a center of gravity of a monitoring subject at a landing moment on the ground and a center of a double-foot support surface as a center of gravity offset distance, and determines a ratio of the center of gravity offset distance to a diagonal line length of the double-foot support surface as a landing stability degree. 6.The AI-assisted diagnosis and treatment system based on wearable motion injury active defense according to claim 5, characterized in that, The level adjustment unit determines that the landing risk level is unqualified based on a comparison result that the landing stability degree is greater than a preset stability degree. 7.The AI-assisted diagnosis and treatment system based on wearable motion injury active defense according to claim 6, characterized in that, The level adjustment unit sets a plurality of level optimization modes based on a comparison result of the double-foot pressure distribution difference and a preset distribution difference to optimize the landing risk level under the condition that the landing risk level is determined to be unqualified.

Images