Sports injury early warning method and storage medium

Abstract

The embodiment of the invention discloses a sports injury early warning method and a storage medium. The method comprises the steps that physiological parameters collected by preset equipment in the movement process are obtained, and the preset equipment can be multiple pieces of wearable equipment; determining a real-time physiological state corresponding to the user based on the physiological parameters, and determining motion characteristics of the user in combination with the motion type engaged by the user and the real-time physiological state; determining a feature deviation degree between the motion feature and a preset motion feature, and if the feature deviation degree reaches a preset feature deviation degree threshold value or above, determining a target wearable device based on the feature deviation degree; and generating early warning information corresponding to the target wearable device, and generating a motion relieving strategy of the user based on the early warning information to prompt the user to execute the motion relieving strategy. According to the embodiment of the invention, the accuracy of sports injury early warning can be improved, the sports of the user is more scientific and reasonable, the sports effect is improved, and the user is assisted to achieve the fitness goal more quickly.

Description

Technical Field

[0001] The present application relates to the technical field of sports risk warning, and in particular to a sports injury warning and a computer-readable storage medium. Background Art

[0002] With the booming development of modern competitive sports and the growing national fitness craze, various sports are becoming increasingly popular, and the number of people participating in sports is increasing day by day. However, sports injuries have become a major obstacle to the health and performance of athletes. Whether professional athletes pursuing excellence or the general public enjoying sports and improving their physical fitness, they all face a high risk of sports injuries.

[0003] In various sports scenes, actions such as sprinting, sudden stops and turns, taking off, and speed changes frequently occur. These actions require the body to achieve rapid changes in speed, direction, or posture in a short period of time, exerting tremendous pressure on various parts of the body, especially structures such as muscles, bones, joints, and ligaments. Take sprinting as an example. The leg muscles need to contract instantly to generate powerful explosive force, and the joints bear an impact force several times that of the body weight. When stopping and turning suddenly, the center of gravity of the body shifts rapidly, and the tissues around the joints need to adjust quickly to maintain balance, which can easily lead to excessive stretching, twisting, and even tearing of the tissues. Therefore, these actions can easily cause common injuries such as abrasions, contusions, and strains. In severe cases, fractures, joint dislocations, ligament ruptures, and other serious injuries that endanger sports careers and even physical health may occur. Therefore, there is an urgent need for a method to provide early warning of sports injuries during exercise. Summary of the Invention

[0004] To solve the above technical problems, the embodiments of the present application provide a sports injury warning method and device, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] According to one aspect of an embodiment of the present application, a sports injury warning method is provided, including: obtaining physiological parameters collected by a preset device during exercise, wherein the preset device can be multiple wearable devices; determining the real-time physiological state corresponding to the user based on the physiological parameters, and determining the user's motion characteristics in combination with the type of exercise the user engages in and the real-time physiological state; determining the feature deviation between the motion characteristics and the preset motion characteristics, and if the feature deviation reaches above a preset feature deviation threshold, determining the target wearable device based on the feature deviation; generating warning information corresponding to the target wearable device, and generating the user's motion relief strategy based on the warning information to prompt the user to execute the motion relief strategy.

[0006] According to one aspect of an embodiment of the present application, the method also includes: determining the target physiological characteristics and the target posture corresponding to the target physiological characteristics based on the motion type; obtaining the identity information corresponding to the user, and determining the personalized factor corresponding to the user based on the identity information; and correcting the target physiological characteristics and the target posture based on the personalized factor to obtain the preset motion characteristics corresponding to the user.

[0007] According to one aspect of an embodiment of the present application, the method also includes: if the movement type is static movement, determining the user's muscle state parameters and joint static stability parameters based on the real-time physiological state; comparing the muscle state parameters and joint static stability parameters with the corresponding preset muscle state parameters and preset joint static stability parameters in the preset movement characteristics to obtain a comparison result; and determining the feature deviation between the movement characteristics and the preset movement characteristics based on the comparison result.

[0008] According to one aspect of an embodiment of the present application, the method also includes: if the motion type is dynamic motion, determining the kinematic parameters and dynamic parameters of the user based on the real-time physiological state; comparing the kinematic parameters and the dynamic parameters with the corresponding preset kinematic parameters and preset dynamic parameters in the preset motion characteristics to obtain a comparison result; and determining the feature deviation between the motion characteristics and the preset motion characteristics based on the comparison result.

[0009] According to one aspect of an embodiment of the present application, the method also includes: determining the real-time load characteristics of the user based on the real-time physiological state; obtaining the historical load characteristics of the user, and comparing the load deviation between the real-time load characteristics and the historical load characteristics; if the load deviation reaches above a preset load deviation threshold, generating injury warning information, and prompting the user through a wearable device.

[0010] According to one aspect of an embodiment of the present application, the identity information includes gender, age and occupation, and the method further includes: determining the personalized correction factor of the user based on the gender, age and occupation; determining the key physiological characteristics of the user based on the personalized correction factor, and the key physiological characteristics are used to detect the health condition of the user; determining the preset physiological characteristic threshold corresponding to the key physiological characteristic, if the key physiological characteristic reaches the preset physiological characteristic threshold, generating early warning information corresponding to the target wearable device.

[0011] According to one aspect of an embodiment of the present application, the method also includes: obtaining the environmental parameters of the user, the environmental parameters including ambient temperature and ground hardness; obtaining the user's footwear, and determining the mechanical interaction parameters between the user and the ground based on the footwear and the ground hardness; determining the user's real-time impact force based on the user's real-time physiological parameters and the mechanical interaction parameters; if the real-time impact force is greater than a preset impact force threshold, generating early warning information corresponding to the target wearable device.

[0012] According to one aspect of an embodiment of the present application, the method also includes: generating a data set based on the user's historical physiological parameters and historical injury data; performing model training based on the data set to obtain a trained injury prediction model; inputting the user's physiological parameters as output parameters into the trained injury prediction model to evaluate the user's motion characteristics based on the output results of the trained injury prediction model.

[0013] According to one aspect of an embodiment of the present application, the physiological parameters include heart rate variability parameters, surface electromyography parameters and inertial sensing parameters, and the method also includes: determining the user's physiological function state based on the heart rate variability parameters and surface electromyography parameters; determining the user's dynamic parameters based on the inertial sensing parameters, the motion parameters including acceleration, angular velocity and posture angle; determining the user's joint injury warning parameters based on the dynamic parameters and the physiological function state; if the joint injury warning parameter is greater than or equal to a preset joint injury warning value, sending sports injury warning information to the user.

[0014] According to one aspect of an embodiment of the present application, a sports injury warning device is provided, which includes: an acquisition module for acquiring physiological parameters collected by a preset device during exercise, and the preset device can be multiple wearable devices; a first determination module for determining the real-time physiological state corresponding to the user based on the physiological parameters, and determining the user's motion characteristics in combination with the type of exercise engaged in by the user and the real-time physiological state; a second determination module for determining the feature deviation between the motion characteristics and the preset motion characteristics, and if the feature deviation reaches above the preset feature deviation threshold, determining the target wearable device based on the feature deviation; an early warning module for generating early warning information corresponding to the target wearable device, and generating the user's motion relief strategy based on the early warning information, so as to prompt the user to execute the motion relief strategy.

[0015] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the sports injury warning method as described above.

[0016] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the sports injury warning method described above.

[0017] According to one aspect of an embodiment of the present application, a computer program product is further provided, including a computer program, which implements the steps in the sports injury early warning method described above when executed by a processor.

[0018] In the technical solutions provided in the embodiments of this application, multiple wearable devices collect physiological parameters in real time, which can comprehensively and accurately reflect the user's physical condition. By combining the exercise type and real-time physiological state to determine the movement characteristics, and comparing them with the preset movement characteristics, potential injury risks can be promptly identified. Based on the deviation between the user's movement characteristics and the preset characteristics, combined with the user's physical condition, exercise goals, etc., a personalized exercise mitigation strategy is generated to meet the personalized needs of different users, avoid a "one-size-fits-all" exercise guidance method, make the user's exercise more scientific and reasonable, improve exercise effects, and help users achieve fitness goals faster.

[0019] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0021] Figure 1 This is a schematic diagram of an implementation environment for sports injury warning during exercise, shown in an exemplary embodiment of the present application;

[0022] Figure 2 is a flow chart of a sports injury early warning method shown in an exemplary embodiment of the present application;

[0023] Figure 3 is a flow chart of a sports injury early warning method shown in another exemplary embodiment of the present application;

[0024] Figure 4 is a flow chart of a sports injury early warning method shown in another exemplary embodiment of the present application;

[0025] Figure 5 is a flow chart of a sports injury early warning method shown in another exemplary embodiment of the present application;

[0026] Figure 6 is a flow chart of a sports injury early warning method shown in another exemplary embodiment of the present application;

[0027] Figure 7 is a flow chart of a sports injury early warning method shown in another exemplary embodiment of the present application;

[0028] Figure 8 is a flow chart of a sports injury early warning method shown in another exemplary embodiment of the present application;

[0029] Figure 9 is a flow chart of a sports injury early warning method shown in another exemplary embodiment of the present application;

[0030] Figure 10 is a flow chart of a sports injury early warning method shown in another exemplary embodiment of the present application;

[0031] Figure 11 is a block diagram of a sports injury warning device shown in an exemplary embodiment of the present application;

[0032] Figure 12 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0034] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0035] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0036] In this application, "plurality" refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0037] First, it's important to note that with the booming development of modern competitive sports and the growing national fitness craze, various sports are becoming increasingly popular, and the number of people participating in them is increasing daily. However, sports injuries have become a significant barrier to the health and performance of athletes. Whether professional athletes pursuing excellence or the general public enjoying sports and improving their fitness, they all face a high risk of sports injuries. Non-contact mechanisms account for a significant proportion of sports injuries, with research showing that this proportion can reach 35% or more in some sports. Non-contact injuries don't stem from direct collisions between athletes, but rather from a combination of internal and external factors, such as movement errors, loss of balance, excessive workload, and the playing field environment. For example, when athletes suddenly change direction at high speed, insufficient lower limb joint flexibility and stability, or insufficient muscle strength to coordinate joint movement, can easily lead to joint sprains. Misjudging the hardness and flatness of the ground during a jump or improper landing posture can also cause excessive impact forces on joints such as the knee and ankle, leading to injuries.

[0038] Non-contact injuries are often hidden because they often occur without obvious external triggers, making them difficult to detect visually. Often, athletes fail to detect any abnormal body signals before an injury occurs, only realizing the severity of the problem afterward. This hidden nature significantly increases the difficulty of preventing non-contact injuries and highlights the urgency of establishing effective early warning mechanisms.

[0039] The occurrence of sports injuries is not caused by a single factor, but is the result of the interweaving and joint action of multiple factors, including internal injury factors, external injury factors, and inducing stimulus conditions. Internal injury factors include age, gender, body shape, previous injury history, physical fitness (such as strength, flexibility, coordination, etc.), physiological state (such as fatigue level, physical function level, etc.) and psychological factors (such as sports motivation, anxiety level, concentration, etc.). For example, with age, physical functions gradually decline, muscle strength, joint flexibility and bone strength decrease, and the risk of injury increases accordingly; female athletes may be affected by changes in hormone levels during certain physiological periods, and the incidence of injuries may also increase; athletes with a history of previous injuries may have structural weaknesses or functional defects in the injured area, and the risk of re-injury is relatively high.

[0040] Figure 1 FIG. 1 is a schematic diagram of an exemplary embodiment of the present application showing an implementation environment for sports injury warning during exercise. Figure 1 As shown, during a user's exercise, multiple wearable devices 110 collect the user's physiological parameters during exercise, and the physiological parameters collected by the multiple wearable devices can be sent to the server 120. The server 120 determines the user's corresponding real-time physiological state based on the physiological parameters, and determines the user's exercise characteristics based on the type of exercise the user is engaged in and the real-time physiological state. The server 120 determines the characteristic deviation between the exercise characteristics and the preset exercise characteristics. If the characteristic deviation reaches or exceeds the preset characteristic deviation threshold, the target wearable device 110 is determined based on the characteristic deviation. Warning information corresponding to the target wearable device 110 is generated, and a motion mitigation strategy for the user is generated based on the warning information to prompt the user to implement the motion mitigation strategy. In this way, sports injury warning can be implemented during the user's exercise.

[0041] Figure 1 The server side 120 shown can be, for example, an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, and there is no limitation here. The wearable device 110 can communicate with the server side 120 through wireless networks such as 3G (third generation mobile information technology), 4G (fourth generation mobile information technology), and 5G (fifth generation mobile information technology), and there is no limitation here.

[0042] In various sports scenes, sprinting, sudden stops and turns, jumping, speed changes and other actions frequently occur. These actions require the body to achieve rapid changes in speed, direction or posture in a short period of time, exerting tremendous pressure on various parts of the body, especially structures such as muscles, bones, joints and ligaments. Take sprinting as an example. The leg muscles need to contract instantly to generate powerful explosive power, and the joints bear an impact force several times that of the body weight; when stopping and turning suddenly, the center of gravity of the body shifts rapidly, and the tissues around the joints need to adjust quickly to maintain balance, which can easily lead to excessive stretching, twisting and even tearing of the tissues. Therefore, these actions are very likely to cause common injuries such as abrasions, contusions and strains. In severe cases, fractures, joint dislocations, ligament ruptures and other serious injuries that endanger sports careers and even physical health may occur.

[0043] The problems pointed out above are generally applicable in general sports scenarios. To solve these problems, the embodiments of the present application respectively propose a sports injury warning method, a sports injury warning device, an electronic device, a computer-readable storage medium and a computer program product. These embodiments will be described in detail below.

[0044] See also Figure 2 , Figure 2 This is a flow chart of a sports injury early warning method according to an exemplary embodiment of the present application. Figure 2 The implementation environment shown is specifically executed by the server 120 in the implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0045] like Figure 2 As shown, in an exemplary embodiment, the sports injury early warning method includes at least steps S210 to S240, which are described in detail as follows:

[0046] Step S210, obtaining physiological parameters collected by a preset device during exercise, where the preset device may be a plurality of wearable devices;

[0047] Step S220, determining the real-time physiological state of the user based on the physiological parameters, and determining the user's exercise characteristics in combination with the user's exercise type and the real-time physiological state;

[0048] Step S230, determining a characteristic deviation between the motion characteristic and a preset motion characteristic, and if the characteristic deviation reaches or exceeds a preset characteristic deviation threshold, determining a target wearable device based on the characteristic deviation;

[0049] Step S240: generating warning information corresponding to the target wearable device, and generating a motion mitigation strategy for the user based on the warning information, so as to prompt the user to execute the motion mitigation strategy.

[0050] Specifically, a monitoring network composed of multiple wearable devices worn by the user (such as smart watches, heart rate belts, sports bracelets, smart insoles, etc.) can be used to collect multi-dimensional physiological parameters of the user during exercise in real time. The user's review parameter types include, but are not limited to, basic vital signs: heart rate, blood pressure, blood oxygen saturation, and respiratory rate; sports-specific indicators: muscle electroencephalogram (EMG), joint range of motion, and plantar pressure distribution; energy metabolism parameters: calorie consumption, lactate threshold, and maximum oxygen uptake (VO2max); and biomechanical data: cadence and stride, center of gravity offset trajectory, and joint force analysis. A personalized physiological model is then constructed based on basic information such as the user's age, gender, and body mass index (BMI). The user's real-time physiological state can then be determined based on the acquired physiological parameters. State identification can use a machine learning algorithm to analyze the physiological state in real time. The obtained physiological state includes the user's fatigue level: comprehensively judged through heart rate variability and muscle electroencephalogram (EMG), the user's dehydration risk can be combined with weight change monitoring and sweat composition analysis, and the user's joint stress state: evaluated using plantar pressure sensors and joint angle data, and the corresponding preset sports feature library is called according to the type of exercise (such as marathon / basketball / strength training).

[0051] Furthermore, the user's exercise characteristics can be determined based on the type of exercise the user engages in and the user's real-time physiological state, where the exercise types may include: endurance exercise: focusing on lactate accumulation rate and aerobic metabolic efficiency, explosive exercise: focusing on muscle power output and neuromuscular coordination, and skill exercise: emphasizing joint stability and consistency of movement patterns.

[0052] Then, based on the extracted user features, a sliding window algorithm is used to update the user's feature deviation threshold in real time to adapt to different exercise stages. The feature deviation between the user and the type of exercise they are engaged in can also be evaluated in multiple dimensions. For example, it can combine physiological deviation (heart rate exceeds the anaerobic threshold and continues to rise), biomechanical deviation (joint force exceeds the historical average by 2 standard deviations), metabolic deviation (glycogen consumption rate exceeds 80% of the individual's historical maximum), etc.

[0053] Sports injury warnings can be provided through pre-established correspondences between wearable devices and body parts. For example, abnormal plantar pressure can be warned through smart insoles, cardiovascular system warnings can be warned through heart rate belts, and trunk muscle tension can be warned through compression clothing sensors. A graded warning method can also be used. For example, yellow warning: a single parameter is critical (such as the heart rate reaches 85% of the maximum heart rate); red warning: multiple parameters are coordinated abnormal (such as an increase in heart rate and a decrease in gait symmetry).

[0054] Optionally, a personalized mitigation strategy for the user can be generated by considering the user's historical response data and preference settings, where the mitigation strategy includes: immediate intervention (such as recommendations to reduce exercise intensity, replenish electrolytes, etc.); long-term adjustment (such as recommended muscle strength training programs, sports equipment optimization suggestions).

[0055] In some embodiments of the present application, multiple wearable devices collect physiological parameters in real time, which can comprehensively and accurately reflect the user's physical condition. By combining exercise type and real-time physiological status to determine motion characteristics and comparing them with preset motion characteristics, potential injury risks can be promptly identified. Based on the degree of deviation between the user's motion characteristics and the preset characteristics, combined with the user's physical condition, exercise goals, etc., a personalized exercise mitigation strategy is generated to meet the personalized needs of different users, avoid a "one-size-fits-all" exercise guidance approach, make user exercise more scientific and reasonable, improve exercise results, and help users achieve their fitness goals more quickly.

[0056] Further, based on the above embodiment, please refer to Figure 3 In one of the exemplary embodiments provided in this application, the specific implementation process of the above sports injury warning method may further include steps S310 to S330, which are described in detail as follows:

[0057] Step S310, determining target physiological characteristics and target posture corresponding to the target physiological characteristics based on the motion type;

[0058] Step S320: obtaining identity information corresponding to the user, and determining a personalized factor corresponding to the user based on the identity information;

[0059] Step S330 : Correcting the target physiological characteristics and target posture based on the personalized factors to obtain the preset motion characteristics corresponding to the user.

[0060] For example, different sports have specific requirements for physiological function and body posture. For example: long-distance running: The target physiological characteristics focus on efficient aerobic metabolism and slow muscle fiber activation at a low heart rate; the target posture emphasizes a slight forward lean of the trunk, a stable cadence and stride length, and a natural and symmetrical arm swing to reduce energy consumption; basketball: anaerobic explosive power and fast muscle fiber recruitment in a high heart rate range are required; posture requires hip and knee flexion to lower the center of gravity and flexible joint rotation to adapt to the needs of changing direction and breaking through; yoga: emphasizes heart rate variability (HRV) indicators and isometric contraction endurance of the core muscles; posture focuses on maintaining a neutral spinal position and extending the joint range of motion to achieve posture accuracy, etc.

[0061] Furthermore, a knowledge graph of exercise types can be pre-constructed, linking and encoding each exercise with corresponding physiological characteristics (such as maximum oxygen uptake and lactate threshold) and posture parameters (such as joint angle range and body center of gravity trajectory). Identity information includes basic physiological data (age, gender, height, weight, and BMI), athletic ability data (historical athletic performance, maximum strength, and flexibility test results), health status data (previous injury history, chronic diseases, and abnormal metabolic indicators), and psychological trait data (exercise motivation intensity, risk preference, and pain tolerance threshold). Principal component analysis (PCA) and the analytic hierarchy process (AHP) are then used to reduce the dimensionality and assign weights to the multi-source data to form a personalized factor vector. For example, for elderly users, the weight of the age factor in the personalized factor may be significantly increased to reflect the impact of physiological decline on their exercise characteristics. A personalized correction mechanism dynamically adjusts the algorithm: Utilizing a fuzzy logic control algorithm, nonlinear corrections are applied to the target physiological characteristics and target posture based on the personalized factors. By pre-setting personalized exercise characteristics, potential exercise risks can be identified and avoided in advance. For example, for users with a history of knee injuries, their stride length and joint flexion angle requirements when running can be reduced to reduce the possibility of re-injury. Using the corrected preset motion characteristics as warning thresholds improves the accuracy and timeliness of the warning system. When the user's actual motion characteristics deviate from the preset values, the system can issue a more accurate warning signal to guide the user to adjust their exercise behavior in a timely manner. Using the corrected preset motion characteristics as a benchmark, the user's athletic ability is objectively assessed. This avoids assessment bias caused by ignoring individual differences and provides users with more accurate athletic ability feedback and development suggestions.

[0062] In some embodiments of the present application, personalized threshold correction can be used to reduce the incidence of sports injuries in users, improve the standardization of user movements, and achieve sports safety protection from passive monitoring to active prevention. It is particularly suitable for professional sports training, rehabilitation medicine, and high-risk job protection scenarios.

[0063] Further, based on the above embodiment, please refer to Figure 4 In one of the exemplary embodiments provided in this application, the specific implementation process of the above sports injury warning method may further include steps S410 to S430, which are described in detail as follows:

[0064] Step S410: If the exercise type is static exercise, determine the user's muscle state parameters and joint static stability parameters based on the real-time physiological state;

[0065] Step S420, comparing the muscle state parameters and the joint static stability parameters with the preset muscle state parameters and the preset joint static stability parameters corresponding to the preset motion characteristics to obtain a comparison result;

[0066] Step S430 : determining a feature deviation between the motion feature and the preset motion feature based on the comparison result.

[0067] For example, if the type of exercise the user is engaged in is static exercise, such as yoga, the user's muscle state parameters and joint static stability parameters can be determined by the user's real-time physiological state. Specifically, the root mean square amplitude (RMS) of the surface electromyography (sEMG) or the integrated electromyography value (iEMG) can be quantified to reflect the muscle recruitment intensity. For example, the quadriceps RMS in the yoga tree pose should reach more than 80% of the baseline value to maintain stability. Then, based on the dynamic changes of the sEMG median frequency (MF), a decrease of more than 15% in MF indicates that fast muscle fiber fatigue has turned to slow muscle fiber dominance, and the duration of the action needs to be adjusted or the difficulty needs to be reduced. Then, the sEMG amplitude ratio of the antagonist muscle to the agonist muscle (such as the hamstring / quadriceps ratio) is analyzed. The normal range is 0.7-1.2. Deviation may cause compensatory joint injury.

[0068] Static joint stability parameters quantify the mechanical balance of joints under static loads, including joint angle stability. This can be monitored using an inertial measurement unit (IMU) to measure fluctuations in the range of motion (ROM). For example, fluctuations in lumbar ROM during scoliosis poses should be less than 3°; exceeding this level indicates insufficient core muscle control. Alternatively, joint torque can be calculated using pressure sensors or plantar pressure plates. For example, the hip abduction torque in Trikonasana should account for 15%-20% of body weight. Imbalanced torque can easily lead to wear of joint cartilage.

[0069] Optionally, quantification can be based on vibration perception threshold (VPT) or joint position error (JPE). A JPE > 5° indicates decreased proprioception and the need for enhanced balance training. Parameter data from resting users and basic static exercises (such as a 30-second plank) are normalized based on age, gender, and exercise history. For example, the baseline RMS of the external rotator muscles in women's shoulder joints is 20% lower than that in men, requiring separate thresholds. Furthermore, correction factors such as ambient temperature, humidity, and altitude can be incorporated. For example, in low-temperature environments, the muscle activation threshold may need to be increased by 10% to compensate for increased muscle viscosity. Static stretching training for office workers can be evaluated through muscle fatigue (MF reduction < 10%) and joint torque distribution (cervical torque < 5% of body weight) to prevent cervical spondylosis and lumbar disc herniation. Special occupational protection: Balance training is conducted for workers working at heights to reduce fall risk through joint angle stability (ankle ROM fluctuation < 1.5°) and symmetrical pressure distribution (left and right foot pressure difference < 5%).

[0070] In some embodiments of the present application, by real-time dynamic comparison of the individualized deviation of muscle activation and joint steady-state parameters in static movement, quantitative early warning of micro-injury risk is achieved, the early detection rate of chronic strain is improved, and precise intervention anchor points for muscle and joint coordinated imbalance are established, thereby improving the user experience.

[0071] Further, based on the above embodiment, please refer to Figure 5 In one of the exemplary embodiments provided in this application, the specific implementation process of the above sports injury warning method may further include steps S510 to S530, which are described in detail as follows:

[0072] Step S510: If the exercise type is dynamic exercise, determining the user's kinematic parameters and kinetic parameters based on the real-time physiological state;

[0073] Step S520, comparing the kinematic parameters and the dynamic parameters with the corresponding preset kinematic parameters and preset dynamic parameters in the preset motion characteristics to obtain a comparison result;

[0074] Step S530 : determining a feature deviation between the motion feature and the preset motion feature based on the comparison result.

[0075] For example, if the user is engaging in dynamic sports, such as basketball or running, the maximum joint angle within the movement cycle can be extracted (e.g., the peak knee flexion angle during a squat), and the root mean square error (RMSE) of the left and right limb motion trajectories can be calculated. An RMSE < 5 mm is considered symmetrical. The maximum limb velocity can also be extracted (e.g., the peak leg swing velocity).

[0076] The user's dynamic parameters include: extracting the maximum vertical ground reaction force (e.g., the vertical GRF peak can reach 2.5 times body weight when running); joint torque peak: extracting the maximum joint torque (e.g., the knee adduction torque peak when landing from a jump); power peak: extracting the maximum instantaneous power (e.g., the hip joint power peak can reach 2000W at the start of a sprint). Parameter data for the user's standard movements (e.g., squats, running) is collected and normalized (e.g., based on body weight or height). Training parameters (e.g., treadmill slope, load weight) are dynamically adjusted based on the degree of deviation.

[0077] Alternatively, if the user is a 30-year-old male amateur runner, and the target action is standard back-pedaling running form, the following physiological data are obtained through real-time monitoring: kinematic parameters: knee flexion angle peak = 120° (preset 110°-130°), stride length symmetry RMSE = 8mm (preset <5mm); kinetic parameters: vertical GRF peak = 2.8 times body weight (preset 2.5-3.0 times), hip adduction torque peak = 0.15N·m (preset <0.12N·m). The calculated deviation between the user and the target action is: total deviation = 18.5% (yellow), and the voice prompt "Shorten stride length, reduce hip adduction" is displayed.

[0078] Alternatively, user information: 18-year-old teenager, target action: vertical jump dunk, physiological parameters obtained through real-time monitoring are: kinematic parameters: take-off angle = 45° (preset 40°-50°), air time = 0.8 seconds (preset 0.7-0.9 seconds); dynamic parameters: knee joint extension torque peak = 3.5 N·m / kg (preset 3.0-4.0 N·m / kg), hip joint power peak = 1800 W (preset 1500-2000 W); deviation calculation result is total deviation = 9.2% (green), tactile feedback "excellent movement, maintain current training".

[0079] In some embodiments of the present application, by capturing multi-dimensional parameters of kinematics (such as joint angle trajectory, limb displacement speed) and dynamics (such as impact force peak, ground reaction torque) in dynamic motion in real time and quantifying their deviation from individualized safety thresholds, abnormal movement patterns can be accurately identified, and the acute sports injury warning window can be advanced to before the injury occurs. At the same time, a mechanical and physiological dual-dimensional calibration basis is provided for sports performance optimization, thereby improving the accuracy of injury warning during exercise.

[0080] Further, based on the above embodiment, please refer to Figure 6 In one of the exemplary embodiments provided in this application, the specific implementation process of the above sports injury warning method may further include steps S610 to S630, which are described in detail as follows:

[0081] Step S610, determining the user's real-time load characteristics based on the real-time physiological state;

[0082] Step S620: Obtain the user's historical load characteristics and compare the load deviation between the real-time load characteristics and the historical load characteristics;

[0083] Step S630: If the load deviation reaches or exceeds a preset load deviation threshold, an injury warning message is generated and the user is prompted via the wearable device.

[0084] For example, the real-time load characteristics of the user can be determined based on the user's real-time physiological state, and combined with the user's historical load characteristics, the load deviation of the user can be compared. If the load deviation reaches above the preset load deviation threshold, it means that the user's real-time load has exceeded the historical load capacity and there is a risk of sports injury, or the user's real-time load is too small to achieve the effect of exercise. The user can then be prompted through the corresponding wearable device, and a load risk report can be generated every month to provide training plan optimization suggestions.

[0085] Optionally, in some feasible embodiments, three core indicators are integrated: cardiopulmonary (heart rate, respiratory rate), muscle (electromyographic signal strength, fatigue index), and neural (reaction time, concentration fluctuation). Then, dynamic weighting is performed based on the user's daily training data for 3-6 months, and three load thresholds are divided into basic, moderate, and extreme levels. Load characteristic templates for different exercise types (strength training / aerobic exercise / flexibility training) are distinguished. Monthly automatic calibration is performed: the baseline value is adjusted according to the user's recent physical changes (such as an increase in maximum oxygen uptake). Scenario-based adaptation is also performed. For example, independent load models are generated for special scenarios such as plateau training and high-temperature environments. A multi-level comparison mechanism can be used, such as: first-level comparison: the deviation between the real-time load and the historical average load of the day (to identify sudden anomalies); second-level comparison: the deviation between the real-time load and the load trend of periodic training (to prevent chronic injuries). Risk correction can also be performed based on the user's age, previous injury history, and recovery ability score, and high-risk movements (such as abnormal knee angle during squats) are monitored.

[0086] In some embodiments of the present application, by dynamically tracking the user's real-time physiological load characteristics (such as heart rate variability slope, muscle metabolic equivalent, joint pressure integral) and performing quantitative analysis of trend deviation with individualized historical load baselines, the fatigue accumulation inflection point (abnormal load detection rate) can be accurately captured, and the timeliness of overwork injury warning can be improved to before the injury threshold. At the same time, closed-loop feedback of load, risk and intervention can be achieved through wearable devices to reduce the incidence of sports injuries.

[0087] Further, based on the above embodiment, please refer to Figure 7 In one of the exemplary embodiments provided in this application, the identity information includes gender, age, and occupation. The specific implementation process of the sports injury warning method may further include steps S710 to S730, which are described in detail as follows:

[0088] Step S710, determining a personalized correction factor for the user based on gender, age, and occupation;

[0089] Step S720, determining the key physiological characteristics of the user based on the personalized correction factor, where the key physiological characteristics are used to detect the health condition of the user;

[0090] Step S730: determining a preset physiological characteristic threshold corresponding to the key physiological characteristic, and generating warning information corresponding to the target wearable device if the key physiological characteristic reaches the preset physiological characteristic threshold.

[0091] For example, it is possible to differentiate between male and female physiological differences in muscle mass, fat distribution, and hormone levels based on gender differences; age stratification, such as dividing the three stages into adolescents (<18 years old), adults (19-59 years old), and the elderly (≥60 years old); occupational characteristics, such as identifying sedentary occupations (office workers), physical occupations (construction workers), high-pressure occupations (medical staff), and other occupational types to build a basic health risk model, and then make a first personalized correction to the health risk model. For example, it can be corrected based on gender, such as adding osteoporosis risk factors for female users and strengthening cardiovascular warning thresholds for male users; age compensation, such as lowering the heart rate warning range by 10-15bpm for users over 40 years old; occupational adaptation, such as establishing a circadian rhythm adjustment coefficient for night shift workers. In some feasible embodiments, secondary personalized corrections can also be made. For example, by accessing the user's sleep quality data, dietary preferences, etc., the user's corresponding health risk model is personalized and corrected to obtain the user's corresponding personalized health risk model and the key physiological characteristics that the user needs to focus on.

[0092] During exercise, the key physiological characteristics of the user are monitored. If the key physiological characteristics meet the preset physiological characteristic threshold in the health risk model, a warning message corresponding to the target wearable device is generated to remind the user that there is a risk in the current exercise. Exemplarily, the user's gender, age and occupation information are obtained through a wearable device or APP. For example, the user information is: gender: female; age: 40 years old; occupation: white-collar worker (sedentary); then the user's personalized correction factor is calculated. The correction factor can be calculated based on the preset weight coefficient table, combined with gender, age and occupation. Gender weight: Women usually have more fragile joints and ligaments, and the weight is set to 1.2, that is, the user's joint stress can be focused on during exercise, and the collected joint stress can be compared with the joint stress threshold corrected based on the personalized weight in the personalized health risk model.

[0093] In some embodiments of this application, personalized correction factors are calculated based on gender, age, and occupation, dynamically adjusting thresholds for key physiological characteristics and generating early warning information based on real-time monitoring data, effectively reducing the risk of sports injuries. This solution is suitable for professional athletes, fitness enthusiasts, and sedentary people, enabling precise health management through wearable devices.

[0094] Further, based on the above embodiment, please refer to Figure 8 In one of the exemplary embodiments provided in this application, the specific implementation process of the above sports injury warning method may further include steps S810 to S840, which are described in detail as follows:

[0095] Step S810, obtaining the user's environmental parameters, including ambient temperature and ground hardness;

[0096] Step S820: Acquire the user's shoes, and determine the mechanical interaction parameters between the user and the ground based on the shoes and the hardness of the ground;

[0097] Step S830, determining the user's real-time impact force based on the user's real-time physiological parameters and mechanical action parameters;

[0098] Step S740: If the real-time impact force is greater than the preset impact force threshold, a warning message corresponding to the target wearable device is generated.

[0099] For example, the ambient temperature can be obtained in real time through the built-in sensor of the wearable device, and the high temperature (>30℃), normal temperature (15-30℃), and low temperature (<15℃) intervals can be distinguished. At the same time, the pressure distribution insole can be used in conjunction with the acceleration sensor to identify hard (concrete), medium (artificial turf), soft (natural grass) ground, etc., and then the environmental risk level is determined according to the ambient temperature and hardness. Then, the user's shoe information (for example, running shoes, basketball shoes or hiking shoes) can be determined through image recognition or the user's own input of shoes, and the corresponding sole material database can be called to determine the mechanical parameters of the user's shoes, where the mechanical parameters include the shoe cushioning coefficient. Then, the energy rebound rate can be calculated based on the shoe cushioning coefficient and the ground hardness, and the instantaneous pressure peak when a single foot lands can be calculated in combination with the user's weight and gait analysis. Then, the real-time impact force is calculated. For example, a sliding window algorithm (50ms window is recommended) can be used to capture impact events. The electromyographic signal (tibialis anterior muscle activity intensity) and acceleration data (vertical / horizontal impact components) are then integrated to determine the user's real-time impact force. A basic impact force threshold is set based on personal information such as the user's age and joint surgery history. The impact force threshold can also be corrected in real time during exercise. For example, the threshold for jumping movements can be automatically increased by 20-30%.

[0100] In addition, in some feasible embodiments, a graded warning system can be used for exercise sequence warning. If a level one warning is triggered, a vibration prompt can be given through the wearable device, and a voice suggestion "please reduce your stride" can be given; if a level two warning is triggered, the wearable device can be used to force a reduction in exercise intensity and recommend a buffering action mode; if a level three warning is triggered, the exercise can be stopped immediately and the emergency contact can be automatically contacted for warning. In addition, in some special scenarios, the warning threshold can be adjusted. For example, for users wearing protective gear (such as knee pads), the warning threshold is increased by 15%, and in nighttime exercise scenarios, the warning sensitivity is increased by 20%.

[0101] In some embodiments of the present application, by integrating environmental parameters (temperature / hardness) and shoe cushioning characteristics to quantify the user-ground mechanical interaction effect, and coupling real-time physiological status (such as electromyographic fatigue index, bone density compensation coefficient) to dynamically calibrate the impact force threshold, the impact overload risk caused by the synergy of environment and equipment can be accurately identified, and the sensitivity of joint injury warning can be improved to a response of seconds. At the same time, wearable devices can be used to implement three-dimensional risk intervention of environment, equipment and physiology, thereby reducing the acute injury rate of high-impact sports (such as basketball and running).

[0102] Further, based on the above embodiment, please refer to Figure 9 In one of the exemplary embodiments provided in this application, the specific implementation process of the above sports injury warning method may further include steps S910 to S930, which are described in detail as follows:

[0103] Step S910, generating a data set based on the user's historical physiological parameters and historical injury data;

[0104] Step S920: performing model training based on the data set to obtain a trained damage prediction model;

[0105] Step S930 : Inputting the user's physiological parameters as output parameters into the trained injury prediction model to evaluate the user's movement characteristics based on the output results of the trained injury prediction model.

[0106] For example, the following data can be extracted from a user's wearable devices (such as smartwatches and smart insoles) and medical records: historical physiological parameters: heart rate variability (HRV), range of motion (ROM), plantar pressure distribution, cadence, stride length, etc.; historical injury data: previous injury type (such as ankle sprain), exercise intensity at the time of injury, recovery time, etc. The collected data is then cleaned, for example, by removing outliers (such as invalid data caused by sensor failure) and missing values; and data annotation is performed, for example, by labeling each record based on the injury data (such as "high risk" or "low risk"). The cleaned data is then divided into time windows (such as weekly) to form a structured dataset, where each record contains: input features: HRV, ROM, plantar pressure ratio, etc.; output label: injury risk level (high / low). A machine learning model suitable for time series data is selected, such as: random forest: to handle multi-feature nonlinear relationships; or LSTM (long short-term memory network): to capture long-term dependencies in time series.

[0107] Then, the collected historical data is divided into a training set and a test set. The training set is 70% of the historical data, which is used for the relationship between model learning features and injuries; the test set is 30% of the historical data, which is used to verify the accuracy of the model prediction. The injury prediction model is then trained to obtain a trained injury prediction model. The user's current physiological parameters (such as HRV = 45ms, ROM = 10°) can then be input into the trained model to obtain the corresponding model output result: the probability of predicting "high risk" (such as 70%). And further risk classification can be performed, for example, low risk: probability <50%, you can continue the current exercise; high risk: probability ≥50%, you need to adjust the exercise plan.

[0108] In some embodiments of the present application, by constructing a multimodal data set between historical physiology and injury and training an injury prediction model with the ability to fuse spatiotemporal features, the nonlinear correlation between the user's current motion characteristics and injury risk can be accurately quantified, thereby reducing the error rate of individualized injury probability prediction. At the same time, the preventive intervention window is changed from passive response after injury to active regulation before risk, thereby reducing the cost of sports injury prevention and treatment.

[0109] Further, based on the above embodiment, please refer to Figure 10 In one of the exemplary embodiments provided in this application, the specific implementation process of the above sports injury warning method may further include steps S1010 to S1040, which are described in detail as follows:

[0110] Step S1010, determining the user's physiological function state based on heart rate variability parameters and surface electromyography parameters;

[0111] Step S1020, determining the user's dynamic parameters based on the inertial sensing parameters, where the motion parameters include acceleration, angular velocity, and posture angle;

[0112] Step S1030, determining the user's joint injury warning parameters based on the dynamic parameters and physiological function status;

[0113] Step S1040: If the joint injury warning parameter is greater than or equal to the preset joint injury warning value, a sports injury warning message is sent to the user.

[0114] For example, the user's heart rate signal is collected by a wearable device worn by the user, and heart rate variability parameter (HRV) features such as time domain (such as SDNN) and frequency domain (such as LF / HF ratio) are extracted. If the HRV value is low or the frequency domain distribution is abnormal, it may indicate that the user is in a state of high stress or fatigue. Surface electromyography parameters (sEMG signals) can also be collected by electrodes attached to the surface of the muscle to analyze the amplitude (such as RMS value) and frequency (such as MPF value) of muscle activity. If continuous high-amplitude discharge of the muscle is detected or the spectrum is shifted to the left, it may indicate muscle fatigue or over-activation.

[0115] Then, combining HRV and sEMG data, if a user simultaneously experiences a decrease in HRV (sympathetic nervous system dominance) and signs of muscle fatigue (e.g., a persistent increase in sEMG amplitude), their physiological state is determined to be "high load" or "fatigue." Sensors with built-in inertial measurement units (IMUs), such as athletic shoe insoles or waistbands, collect the user's acceleration, angular velocity, and posture angle (e.g., knee flexion and extension angle). Motion parameter processing is performed on the collected inertial data. For example, for acceleration / angular velocity, noise is removed through low-pass filtering, and the combined acceleration and peak joint angular velocity are calculated. For posture angle, joint angles (e.g., hip and knee angles) are estimated in real time based on gyroscope and accelerometer data using complementary filtering or Kalman filter fusion algorithms. Dynamic and physiological synergistic analysis correlates dynamic parameters with physiological state. If a user is in a "fatigue" state (determined by HRV / sEMG) and a sudden change in joint angular velocity (e.g., a sudden stop) or a posture angle approaching the extreme range (e.g., excessive knee flexion) is detected, the risk of joint injury is determined to be elevated.

[0116] For example, when a user is running, if the user is physically fatigued and the knee flexion angle during the gait cycle exceeds the safety threshold (calibrated by historical data), an early warning is triggered. In addition, the early warning threshold of the joint angle / angular velocity can be dynamically adjusted according to individual differences such as the user's age and exercise history (for example, the threshold for the elderly is lower than that for young people). In some embodiments of the present application, through the three-dimensional fusion analysis of physiological state, motion parameters and environmental factors, sports safety protection from passive monitoring to active prevention is achieved, which is particularly suitable for professional sports training, rehabilitation medicine and high-risk occupational protection scenarios.

[0117] In some embodiments of the present application, by integrating dual-modal physiological function evaluation of autonomic nervous system regulation (heart rate variability) and muscle electrophysiology (surface electromyography) and three-dimensional feature solution of motion dynamics (acceleration / angular velocity / posture angle), a physiological and mechanical collaborative injury warning model is constructed to achieve real-time dynamic matching analysis of joint impact load and functional reserve, thereby improving the sensitivity of joint injury warning and significantly reducing the acute injury rate in high-intensity exercise scenarios.

[0118] Figure 11 This is a block diagram of a sports injury warning device shown in an exemplary embodiment of the present application. The device can be applied to Figure 1 The implementation environment shown is specifically configured in the server 120. The apparatus may also be applicable to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the apparatus is applicable.

[0119] like Figure 11 As shown, the exemplary sports injury warning device includes: an acquisition module 1110, which is used to obtain physiological parameters collected by a preset device during exercise, and the preset device can be multiple wearable devices; a first determination module 1120, which is used to determine the real-time physiological state of the user based on the physiological parameters, and determine the user's motion characteristics in combination with the type of exercise the user engages in and the real-time physiological state; a second determination module 1130, which is used to determine the feature deviation between the motion characteristics and the preset motion characteristics, if the feature deviation reaches above the preset feature deviation threshold, the target wearable device is determined based on the feature deviation; an early warning module 1140, which is used to generate early warning information corresponding to the target wearable device, and generate the user's motion relief strategy based on the early warning information to prompt the user to execute the motion relief strategy.

[0120] According to one aspect of an embodiment of the present application, the above-mentioned second determination module 1130 is also used to determine the target physiological characteristics and the target posture corresponding to the target physiological characteristics based on the motion type; obtain the identity information corresponding to the user, and determine the personalized factor corresponding to the user based on the identity information; correct the target physiological characteristics and the target posture based on the personalized factor to obtain the preset motion characteristics corresponding to the user.

[0121] According to one aspect of an embodiment of the present application, the above-mentioned second determination module 1130 is also used to, if the movement type is static movement, determine the user's muscle state parameters and joint static stability parameters based on the real-time physiological state; compare the muscle state parameters and joint static stability parameters with the corresponding preset muscle state parameters and preset joint static stability parameters in the preset movement characteristics to obtain a comparison result; and determine the feature deviation between the movement characteristics and the preset movement characteristics based on the comparison result.

[0122] According to one aspect of an embodiment of the present application, the above-mentioned second determination module 1130 is also used to, if the motion type is dynamic motion, determine the user's kinematic parameters and dynamic parameters based on the real-time physiological state; compare the kinematic parameters and dynamic parameters with the corresponding preset kinematic parameters and preset dynamic parameters in the preset motion characteristics to obtain a comparison result; and determine the feature deviation between the motion characteristics and the preset motion characteristics based on the comparison result.

[0123] According to one aspect of an embodiment of the present application, the above-mentioned warning module 1140 is also used to determine the real-time load characteristics of the user based on the real-time physiological state; obtain the user's historical load characteristics, and compare the load deviation between the real-time load characteristics and the historical load characteristics; if the load deviation reaches above the preset load deviation threshold, an injury warning information is generated, and the user is prompted through a wearable device.

[0124] According to one aspect of an embodiment of the present application, the above-mentioned second determination module 1130 is also used to determine the user's personalized correction factor based on gender, age and occupation; determine the user's key physiological characteristics based on the personalized correction factor, and the key physiological characteristics are used to detect the user's health condition; determine the preset physiological characteristic threshold corresponding to the key physiological characteristic, and if the key physiological characteristic reaches the preset physiological characteristic threshold, generate warning information corresponding to the target wearable device.

[0125] According to one aspect of an embodiment of the present application, the above-mentioned early warning module 1140 is also used to obtain the environmental parameters of the user, which include ambient temperature and ground hardness; obtain the user's footwear, and determine the mechanical interaction parameters between the user and the ground based on the footwear and the ground hardness; determine the user's real-time impact force based on the user's real-time physiological parameters and mechanical interaction parameters; if the real-time impact force is greater than the preset impact force threshold, generate early warning information corresponding to the target wearable device.

[0126] According to one aspect of an embodiment of the present application, the above-mentioned early warning module 1140 is also used to generate a data set based on the user's historical physiological parameters and historical injury data; perform model training based on the data set to obtain a trained injury prediction model; input the user's physiological parameters as output parameters into the trained injury prediction model to evaluate the user's motion characteristics based on the output results of the trained injury prediction model.

[0127] According to one aspect of an embodiment of the present application, the above-mentioned warning module 1140 is also used to determine the user's physiological function state based on heart rate variability parameters and surface electromyography parameters; determine the user's dynamic parameters based on inertial sensing parameters, and the motion parameters include acceleration, angular velocity and posture angle; determine the user's joint injury warning parameters based on dynamic parameters and physiological function state; if the joint injury warning parameter is greater than or equal to the preset joint injury warning value, send sports injury warning information to the user.

[0128] It should be noted that the sports injury warning device provided in the above embodiment and the sports injury warning method provided in the above embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the sports injury warning device provided in the above embodiment can, as needed, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0129] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, which, when executed by one or more processors, enables the electronic device to implement the sports injury warning method provided in the above-mentioned embodiments.

[0130] Figure 12 The following is a schematic diagram showing the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application. Figure 12 The computer system 1200 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0131] like Figure 12 As shown, the computer system 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1202 or the program loaded from the storage part 1208 into the random access memory (RAM) 1203, such as executing the method in the above embodiment. Various programs and data required for system operation are also stored in the RAM 1203. The CPU 1201, ROM 1202 and RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0132] The following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, and the like; an output section 1207 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 1208 including a hard disk; and a communication section 1209 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as needed. Removable media 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 1210 as needed, so that computer programs read from the removable media can be installed in the storage section 1208 as needed.

[0133] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1209, and / or installed from a removable medium 1211. When the computer program is executed by the central processing unit (CPU) 1201, the various functions defined in the system of the present application are executed.

[0134] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0137] Another aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned sports injury warning method. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device.

[0138] Another aspect of the present application provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the sports injury early warning method provided in each of the above embodiments.

[0139] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. Ordinary technicians in this field can easily make corresponding changes or modifications based on the main ideas and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.

Claims

1. A sports injury early warning method, characterized in that: include: Acquiring physiological parameters collected by a preset device during exercise, where the preset device may be multiple wearable devices; Determining a real-time physiological state of the user based on the physiological parameters, and determining a movement characteristic of the user in combination with the type of movement the user engages in and the real-time physiological state; determining a characteristic deviation between the motion characteristic and a preset motion characteristic, and if the characteristic deviation reaches or exceeds a preset characteristic deviation threshold, determining a target wearable device based on the characteristic deviation; Generate warning information corresponding to the target wearable device, and generate a motion mitigation strategy for the user based on the warning information to prompt the user to execute the motion mitigation strategy.

2. The method according to claim 1, wherein The method further comprises: Determining a target physiological characteristic based on the motion type, and a target posture corresponding to the target physiological characteristic; Obtaining identity information corresponding to the user, and determining a personalized factor corresponding to the user based on the identity information; The target physiological characteristics and target posture are corrected based on the personalized factors to obtain the preset motion characteristics corresponding to the user.

3. The method according to claim 2, wherein The method further comprises: If the exercise type is static exercise, determining the user's muscle state parameters and joint static stability parameters based on the real-time physiological state; Comparing the muscle state parameters and joint static stability parameters with the preset muscle state parameters and preset joint static stability parameters corresponding to the preset motion characteristics to obtain a comparison result; A feature deviation between the motion feature and the preset motion feature is determined based on the comparison result.

4. The method according to claim 2, wherein The method further comprises: If the exercise type is dynamic exercise, determining kinematic parameters and kinetic parameters of the user based on the real-time physiological state; Comparing the kinematic parameters and the dynamic parameters with corresponding preset kinematic parameters and preset dynamic parameters in the preset motion characteristics to obtain a comparison result; A feature deviation between the motion feature and the preset motion feature is determined based on the comparison result.

5. The method according to claim 1, wherein The method further comprises: determining a real-time load characteristic of the user based on the real-time physiological state; Obtaining historical load characteristics of the user, and comparing the load deviation between the real-time load characteristics and the historical load characteristics; If the load deviation reaches or exceeds a preset load deviation threshold, an injury warning message is generated and the user is prompted via a wearable device.

6. The method according to claim 2, wherein The identity information includes gender, age, and occupation. The method further includes: determining a personalized correction factor for the user based on the gender, the age, and the occupation; determining a key physiological characteristic of the user based on the personalized correction factor, wherein the key physiological characteristic is used to detect the health condition of the user; A preset physiological characteristic threshold corresponding to the key physiological characteristic is determined, and if the key physiological characteristic reaches the preset physiological characteristic threshold, warning information corresponding to the target wearable device is generated.

7. The method according to claim 1, wherein The method further comprises: Acquiring environmental parameters of the user, wherein the environmental parameters include ambient temperature and ground hardness; obtaining the user's shoes, and determining the mechanical interaction parameters between the user and the ground based on the shoes and the hardness of the ground; determining a real-time impact force of the user based on the real-time physiological parameters of the user and the mechanical action parameters; If the real-time impact force is greater than a preset impact force threshold, a warning message corresponding to the target wearable device is generated.

8. The method according to claim 1, wherein The method further comprises: Generate a data set based on the user's historical physiological parameters and historical injury data; Performing model training based on the data set to obtain a trained damage prediction model; The physiological parameters of the user are input as output parameters into the trained injury prediction model, so as to evaluate the movement characteristics of the user based on the output results of the trained injury prediction model.

9. The method according to claim 1, wherein The physiological parameters include heart rate variability parameters, surface electromyography parameters and inertial sensing parameters, and the method further includes: determining the user's physiological function state based on the heart rate variability parameter and the surface electromyography parameter; Determining the user's dynamic parameters based on the inertial sensing parameters, wherein the motion parameters include acceleration, angular velocity, and posture angle; determining a joint injury warning parameter of the user based on the kinetic parameter and the physiological function state; If the joint injury warning parameter is greater than or equal to a preset joint injury warning value, a sports injury warning message is sent to the user.

10. A computer-readable storage medium, characterized in that Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the sports injury early warning method according to any one of claims 1 to 9.

Images