A real-time comprehensive evaluation system and method for sports risk in a venue

Abstract

The application discloses a kind of field in sports risk comprehensive real-time evaluation system and method, it is related to sports risk assessment technical field, the system includes: real-time monitoring module, data fusion module, data processing module, risk assessment module and optimization suggestion early warning module;Data fusion module processes the initial sports information collected by real-time monitoring module, obtains target sports information, data processing module is based on target sports information based on sports ground potential field, athlete kinetic energy field, ball kinetic energy field and athlete behavior psychology field four dimensions constructs sports risk field, and then establishes sports risk assessment model by sports risk field, solves sports risk assessment model, obtains risk reliability index, and when risk reliability index exceeds threshold value, alarm is carried out, the application can realize high-precision sports state monitoring, comprehensive risk assessment and real-time risk early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sports risk assessment, in particular to a comprehensive real-time evaluation system and method for sports risk in a venue. BACKGROUND

[0002] In the field of sports, with the progress of technology, sports monitoring and risk management technology has made significant development. Currently, traditional sports monitoring systems mainly rely on wearable devices (such as heart rate monitors and gait analyzers) and fixed sensors (such as cameras). These systems can collect physiological data and sports states of athletes, but there are still limitations in real-time data processing and multi-dimensional analysis. In addition, computer vision technologies such as OpenPose and YOLO have made breakthroughs in pose estimation and object detection, but may face challenges in real-time processing and computing resources when dealing with large-scale data streams. Existing risk assessment methods usually rely on static safety standards and empirical rules, which are not flexible and accurate enough when dealing with complex and dynamic environments. SUMMARY

[0003] The purpose of the present application is to provide a comprehensive real-time evaluation system and method for sports risk in a venue, which can realize high-precision sports state monitoring, comprehensive risk assessment and real-time risk warning.

[0004] To achieve the above-mentioned purpose, the present application provides the following solutions:

[0005] In a first aspect, the present application provides a comprehensive real-time evaluation system for sports risk in a venue, comprising:

[0006] a real-time monitoring module for collecting real-time sports data of an athlete when the athlete is playing a ball game; and calculating initial sports information according to the real-time sports data; the real-time sports data includes image data and sports state data, and the sports state data includes acceleration, angular velocity and attitude change of the athlete; the initial sports information includes position, speed, acceleration and sports mode of the athlete, as well as position, speed and acceleration of the ball;

[0007] a data fusion module for preprocessing the initial sports information to obtain target sports information;

[0008] a data processing module for: constructing a sports risk field based on the target sports information; the sports risk field is composed of a sports venue potential field, an athlete kinetic energy field, a ball kinetic energy field and an athlete behavior and psychological field; constructing a risk response influence function based on the change of the athlete's sports state in the sports risk field; and establishing a sports risk assessment model according to the risk response influence function and the sports risk field;

[0009] a risk assessment module configured to solve the sports risk assessment model to obtain a sports risk boundary value, wherein the sports risk boundary value comprises an upper risk boundary and a lower risk boundary, and the risk reliability index is calculated according to the sports risk boundary value;

[0010] an optimization suggestion warning module configured to give an alarm when the risk reliability index exceeds a sports risk threshold.

[0011] Optionally, the optimization suggestion warning module further comprises a display and notification unit, and the display and notification unit is configured to visualize the real-time sports state data of the athlete and the risk reliability index.

[0012] Optionally, the display and notification unit is further configured to send a warning notification to the user in a visual, auditory and / or tactile manner when the risk reliability index exceeds the sports risk threshold.

[0013] Optionally, the optimization suggestion warning module further comprises a database and history recording unit, and the database and history recording unit is configured to store historical sports data and risk assessment records of the athlete, wherein the risk assessment records comprise the risk reliability index corresponding to the historical sports data of the athlete.

[0014] Optionally, the optimization suggestion warning module is further configured to train a trained risk prediction model by using an intelligent algorithm according to the historical sports data and the risk assessment records, and input the real-time sports data of the athlete into the trained risk prediction model to predict the risk reliability index.

[0015] Optionally, the intelligent algorithm is a decision tree algorithm, a random forest algorithm or a convolutional neural network algorithm.

[0016] Optionally, the data processing module is configured to construct the risk intensity of the sports field potential energy field, the risk intensity of the athlete kinetic energy field, the risk intensity of the ball kinetic energy field and the risk intensity of the athlete behavior and psychology field based on the target sports information, and construct a sports risk field by weighted summing the risk intensity of the sports field potential energy field, the risk intensity of the athlete kinetic energy field, the risk intensity of the ball kinetic energy field and the risk intensity of the athlete behavior and psychology field.

[0017] Optionally, the field sports risk comprehensive real-time evaluation system further comprises a communication module, and the real-time monitoring module, the data fusion module, the data processing module, the risk assessment module and the optimization suggestion warning module are communicatively connected through the communication module.

[0018] Optionally, the preprocessing is Kalman filtering processing.

[0019] In a second aspect, the present application provides a field sports risk comprehensive real-time evaluation method, comprising:

[0020] Collecting real-time motion data of the player when the player is playing a ball game; and calculating initial motion information according to the real-time motion data; the real-time motion data includes image data and motion state data, and the motion state data includes acceleration, angular velocity and attitude change of the player; the initial motion information includes position, speed, acceleration and motion mode of the player, and position, speed and acceleration of the ball;

[0021] Preprocessing the initial motion information to obtain target motion information;

[0022] Constructing a motion risk field based on the target motion information; the motion risk field includes a motion field potential energy field, a player kinetic energy field, a ball kinetic energy field and a player behavior and psychology field; constructing a risk response influence function based on the change of the player's motion state in the motion risk field; and establishing a motion risk assessment model according to the risk response influence function and the motion risk field;

[0023] Solving the motion risk assessment model to obtain a motion risk boundary value; the motion risk boundary value includes an upper risk boundary and a lower risk boundary; and calculating a risk reliability index according to the motion risk boundary value;

[0024] When the risk reliability index exceeds a motion risk threshold value, an alarm is given.

[0025] According to the specific embodiments provided in the present application, the following technical effects are disclosed:

[0026] The present application provides a field motion risk comprehensive real-time evaluation system and method, which constructs a motion field potential energy field, a player kinetic energy field, a ball kinetic energy field and a player behavior and psychology field through real-time motion data, and then constructs a motion risk field by considering the four dimensions of the motion field potential energy field, the player kinetic energy field, the ball kinetic energy field and the player behavior and psychology field, and then establishes a motion risk assessment model by considering the multi-dimensional motion risk field, solves the motion risk assessment model, obtains accurate motion risk boundary values, and calculates the risk reliability index according to the motion risk boundary values, which has higher accuracy, solves the problem that the existing risk assessment method usually relies on static safety standards and empirical rules, and is not flexible and accurate in dealing with complex and dynamic environments, and realizes high-precision motion state monitoring, comprehensive risk assessment and real-time risk warning. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings described below only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0028] Figure 1 A functional module schematic diagram of a sports risk comprehensive real-time evaluation system in a venue is provided for an embodiment of the present application.

[0029] Figure 2 A schematic diagram of the state of athletes and balls in a sports venue is provided for an embodiment of the present application.

[0030] Figure 3 A flowchart of a sports risk comprehensive real-time evaluation method is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0032] Although there are some advances in sports monitoring and risk assessment in the prior art, there are still some technical problems. First, the accuracy of traditional sensors and monitoring devices is often insufficient, especially in dynamic and complex environments, which can lead to inaccurate data and affect the accuracy of risk assessment. Second, existing computer vision systems may have limited computing resources or inefficient algorithms when processing real-time data streams, resulting in delays and slow processing speeds. This can affect the timeliness of real-time warning and feedback. In addition, existing systems can only focus on a single risk factor and lack comprehensive analysis capabilities for multi-dimensional and multi-source data. Finally, traditional warning systems rely on fixed rules and thresholds, and have low intelligence and adaptability, which may not be able to accurately identify and handle complex risk situations.

[0033] To solve the above problems, the application provides a sports risk comprehensive real-time evaluation system and method. By introducing high-precision sensors, computer vision technology, data fusion algorithms and intelligent early warning systems, many problems in the prior art are effectively solved. The system improves the accuracy of data by combining high-precision cameras and IMU devices, overcoming the problem of insufficient accuracy of traditional sensors. Real-time feedback is achieved using efficient data stream processing and dynamic visualization technology, solving the problem of poor real-time performance of traditional systems. The comprehensive analysis method enhances the comprehensive evaluation ability of complex environments, making up for the lack of comprehensive ability of existing methods. The application of intelligent early warning algorithms and multi-channel notification systems realizes intelligent and adaptive early warning, improves the accuracy of risk identification and processing, and solves the problem of low intelligence level of traditional early warning systems. The system provides a more accurate and timely risk management solution for athletes and coaches.

[0034] The above objects, features and advantages of the application will be more apparent from the following detailed description of the application, taken in conjunction with the accompanying drawings and specific embodiments.

[0035] In one exemplary embodiment, as shown in Figure 1 A sports risk comprehensive real-time evaluation system is provided, including a real-time monitoring module, a data fusion module, a data processing module, a risk assessment module, a communication module and an optimization suggestion and early warning module. The real-time monitoring module, data fusion module, data processing module, risk assessment module and optimization suggestion and early warning module are connected by the communication module.

[0036] The real-time monitoring module is used to collect real-time motion data of the athlete when the athlete is playing ball games, and to calculate initial motion information according to the real-time motion data. The real-time motion data includes image data and motion state data, and the motion state data includes the acceleration, angular velocity and attitude change of the athlete. The initial motion information includes the position, speed, acceleration and motion mode of the athlete, as well as the position, speed and acceleration of the ball.

[0037] The real-time monitoring module uses high-precision cameras and inertial measurement units (IMUs) and other sensor units to monitor the athlete's movement state in real time. The high-precision camera captures image data of the athlete and uses computer vision techniques such as object detection and pose estimation to track the athlete's position, speed, and movement patterns. By matching features in consecutive image frames, the high-precision camera can calculate the athlete's speed and acceleration and identify different movement patterns. The IMU measures the athlete's acceleration, angular velocity, and attitude changes through accelerometers, gyroscopes, and magnetometers. Through filtering and integration operations, the athlete's speed, position, and acceleration are accurately calculated, and features such as the rate of change of linear acceleration, the rate of change of angular velocity, and the intensity of movement in each axis are extracted from the acceleration and angular velocity data. Machine learning algorithms (such as support vector machines, decision trees, random forests, etc.) or deep learning algorithms (such as convolutional neural networks) are used to classify the extracted features to obtain movement patterns. Movement patterns include jumping, turning, side stepping, and sprinting, etc.

[0038] The data fusion module is used to preprocess the initial movement information to obtain target movement information; the preprocessing is Kalman filtering processing. That is, the visual information provided by the high-precision camera and the sensor data of the IMU are comprehensively processed through a data fusion algorithm (such as a Kalman filtering algorithm), thereby improving the accuracy of position, speed, and attitude estimation.

[0039] The data processing module is used to: construct a movement risk field based on the target movement information; the movement risk field is composed of a superposition of a movement field potential field, an athlete kinetic energy field, a ball kinetic energy field, and an athlete behavior and psychology field; construct a risk response influence function based on the changes in the athlete's movement state in the movement risk field; and establish a movement risk assessment model according to the risk response influence function and the movement risk field.

[0040] As an optional implementation, constructing a movement risk field based on the target movement information specifically includes: constructing the risk intensity of the movement field potential field, the risk intensity of the athlete kinetic energy field, the risk intensity of the ball kinetic energy field, and the risk intensity of the athlete behavior and psychology field based on the target movement information; and performing weighted summation on the risk intensity of the movement field potential field, the risk intensity of the athlete kinetic energy field, the risk intensity of the ball kinetic energy field, and the risk intensity of the athlete behavior and psychology field to construct the movement risk field.

[0041] Based on the detected spatiotemporal position and speed of the athletes and the ball, a risk assessment method is constructed based on the field-based concept. On the sports field, each component element such as the field condition and the athlete will generate a potential field, the size of which is determined by the attribute of the element itself. In addition, each component element will affect each other, and the superposition state of multiple fields constitutes the change of the athlete's movement state, thus forming different risk points. According to the nature of the component elements, the sports risk field is divided into sports field potential field, athlete kinetic field, ball kinetic field and athlete behavior and psychological field, and the superposition of the four fields constitutes the sports risk field. The strength of the sports risk field at a certain point on the field is defined as the weighted sum of the field strength generated by different elements E, as shown in equation (1).

[0042] E = ω r E r + ω y E y + ω q E q + ω x E x (1).

[0043] E = ω r E y E q E x E = ω r E = ω y E = ω q E = ω x represent the weight coefficients of different risk fields.

[0044] (1) Sports field potential field

[0045] When the athlete is close to the boundary of the field (such as the baseline and the sideline), the action accuracy requirement is higher, and the risk is also increased. When the athlete moves close to the baseline, the control force of the ball hitting is required to be higher, because once the mistake is made, the ball is easy to go out of bounds, which means that the potential field increases rapidly. Considering that most of the field ball games have the property of central symmetry, the potential fields on the left and right sides are also different, and usually the athlete will choose to stand in the middle position. Based on this principle, the risk strength function of the sports field potential field is constructed, as shown in equations (2), (3) and (4).

[0046]

[0047] wherein E1 and E2 represent a first angular motion field potential energy and a second angular motion field potential energy respectively, are potential energy sizes considered from different angles, represent motion risks, E1 is modeled according to a function with a larger amplitude and a faster change speed, so as to represent a rapid increase of the potential energy field; E2 represents a basic risk with a linear function, and superposition of E1 and E2 can reflect a more real motion risk situation; Z(t) is a real-time position of the athlete; Z l is a single-side center line position of the field; d is a single-side half width of the field; ε i is a single-side center line potential energy field coefficient of the field; i = 1, 2 represent a left boundary and a right boundary of the field respectively; Z b1 , Z b2 are horizontal coordinates of the left boundary and the right boundary of the field respectively, and Z is a horizontal coordinate of the athlete in the field, i.e. a distance between the athlete and the left boundary or the right boundary of the field; is a boundary-related parameter.

[0048] Summing up formula (2) and formula (3), a motion field potential energy field function E r is obtained.

[0049] E r = E1 + E2 (4).

[0050] (2) Athlete kinetic energy field

[0051] In ball games, factors such as moving speed and acceleration of the athlete will affect the motion direction, and high-speed movement or sudden stop will affect the physical fitness and action accuracy of the athlete. Therefore, an athlete kinetic energy field is constructed to analyze the motion risk level, and the size thereof is related to the athlete's weight, motion state and the like. A risk intensity calculation formula of the athlete kinetic energy field is specifically shown in formula (5).

[0052]

[0053] wherein F(x, z) is a correction function, which considers that the kinetic energy of the athlete at different positions has different influences on the risk, and is corrected; δ0 is a kinetic energy field correction coefficient; m is an equivalent mass of the athlete; v is a speed of the athlete. An expression of the above correction function F(x, z) is formula (6).

[0054]

[0055] wherein the correction function considers the most unfavorable situation, i.e. selecting a maximum value in two situations in formula (6) as a final correction value; x(t) is a distance between the athlete and a single-side front boundary line of the field at t; η(t) is a distance between the athlete and a single-side rear boundary line of the field at t; (x1, Z1) and (x2, Z2) are respectively a single-side front boundary line coordinate and a single-side rear boundary line coordinate of the field; δ1 and δ2 are respectively an athlete kinetic energy field adjustment coefficient.

[0056] (3) Ball kinetic energy field

[0057] The mass and speed of the ball will affect the risk of the athlete hitting the ball during the movement. It is related to the ball speed, mass, movement state and direction. Based on this, a ball kinetic energy risk field model is established. The calculation formula of the risk intensity of the ball kinetic energy field is shown in formula (7).

[0058]

[0059] Where: Q x (t) and Q y (t) are the horizontal and vertical coordinates of the ball respectively; δ3 is the adjustment coefficient of the ball's kinetic energy field; a is the acceleration of the ball; θ is the angle formed between the ball and the player.

[0060] (4) Athletes’ behavioral psychology

[0061] The athlete's behavior is related to the landing point and speed of the target ball, as shown in formula (8).

[0062]

[0063] Among them, Eb n is the basic field strength value formed by the target; v n is the speed of the target ball, which refers to the speed of the ball when the opponent hits the ball; L0 is the distance from the origin of the target ball along the target direction, v ε is the correction value.

[0064] Calculate the psychological field strength of athletes at any point on the field based on the behavioral psychological field model. Figure 2 As shown, OP x OP is the distance from the intersection of the equipotential line, the moving obstacle and the line connecting them to the target ball. y is the distance from the point of intersection of the equipotential line and the perpendicular line to the line connecting the athlete and the moving obstacle to the target ball. x With OP y The ratio is α, and the value of α is related to the speed of the athlete.

[0065] ρ=L0-(1-α)L0|sinθ| (9).

[0066] Where ρ is the distance between the point on the equipotential line and the athlete's origin O.

[0067] The basic field strength calculation model of the psychological field formed by the athlete at any point in space is as follows: n (x,y) is the basic field strength at point (x,y).

[0068]

[0069] Where, ρ(x,y) is the distance from the origin O of the player, Eb n (x, y) has no special meaning, just introduce the coordinates of the point, and then assign it to E x .

[0070] The model based on the behavior of the psychological field of the player should include two parts, respectively, the description of the player's own psychological field and the description of the motion state and attribute of other objects in the psychological field. Therefore, the following formula is constructed as shown in the framework structure of the player behavior model.

[0071] F n = E n (Eb n )·g n (F inf , E inf , P inf , S inf ) (11)。

[0072] Where F n is the force on the player's psychology; E n is the field strength formed by the player in the sports field, which is transformed from the basic field strength Eb n ; F inf is the influence of the field facilities on the psychology of the pedestrian; E inf is the influence of the external environment on the player when playing the ball in the psychological field, including noise and other influencing factors; P inf indicates the influence of the opponent on itself, and S inf indicates the influence of social factors on the player.

[0073] In order to further analyze the influence of the external environmental factors in the sports field on the player, the player behavior field model framework based on the behavior field theory is established, as shown in formula (12).

[0074]

[0075] Where r j is a variable adjustment coefficient that expresses the severity of the influence of the influencing factor on the player's behavior, which is determined by the membership function of each parameter and the weight in the psychological field; ΔE n is the field strength change amplitude in the behavior psychological field, which changes with the attribute of the influencing factor, the real-time environment and the change of the influence on the player's psychology; j = F inf , E inf , P inf , S inf , that is, m = 4.

[0076] (5) Risk response field construction

[0077] Based on the change analysis of the athlete's movement state in the superposition state of multiple fields, the risk response influence function G(t) is constructed, and the basic equation of the risk field as shown in formula (13) is constructed.

[0078]

[0079] In the formula, E(t) is the movement risk field intensity calculated by formula (1), is the gradient of the risk field, indicating the change of the risk with the position; γ and β are influence coefficients; y i (t) is the risk response function, which is determined by the change of the athlete's speed, acceleration and the like with time, and in a specific example, i represents the athlete's speed, acceleration and position, then n=3; m represents the initial moment, T i represents the sampling moment of the athlete's movement state data.

[0080] (6) Risk assessment model

[0081] Considering the mutual relationship between the risk response measures and the movement risk, a movement risk assessment model D(t) is constructed.

[0082]

[0083] Wherein, μ1 and μ2 are the weights of the risk response influence function and the movement risk field intensity respectively, is a correction parameter, G(t) is the risk response influence function, E(t) is the movement risk field intensity, and the uncertainty domain thereof is described by a generalized hyperellipsoid model:

[0084]

[0085] In the formula, G(t) c and E(t) c represent the midpoints of the function value interval; G(t) r and E(t) r are the radii of the function value interval, and κ is an adjustment coefficient; N1 and N2 are parameters of the generalized hyperellipsoid model, and different integer values greater than 1 are taken to ensure that the model is a convex set and has more flexibility.

[0086]

[0087] Wherein, ξ is a risk reliability index, reflecting the importance of the influence degree of the movement risk field and the risk response measures on the movement risk, when ξ is greater than 1, the movement risk is low, and when ξ is less than-1, the movement risk is extremely high; f c (G,E) and f r (G,E) are the mean and deviation of the function respectively, and f U(G,E) and f L (G,E) and f

[0088] a risk assessment module configured to solve the motion risk assessment model to obtain a motion risk boundary value, wherein the motion risk boundary value comprises a risk upper boundary and a risk lower boundary, and to calculate a risk reliability index according to the motion risk boundary value.

[0089] The motion risk assessment model is solved by constructing a Lagrange function to obtain a risk upper boundary f U (G,E) and a risk lower boundary f L (G,E), and the constructed Lagrange function is shown in equation (18).

[0090]

[0091] In the equation, L(G(t), E(t), λ) represents the Lagrange function, and λ represents the Lagrange multiplier.

[0092] The optimization suggestion and real-time warning technology provided by the optimization suggestion and warning module are as follows:

[0093] By means of the motion risk assessment method, a set of devices are developed by integrating the data acquisition and processing module, which can provide accurate risk assessment and optimization suggestions by comprehensively analyzing the real-time data of athletes.

[0094] (1) Rule engine: set risk trigger conditions and automatically send warning signals. The optimization suggestion and warning module is used to alarm when the risk reliability index exceeds the motion risk threshold. Based on the regular motion performance of athletes, the motion risk threshold is set, and when the athletes are in a high-risk motion state for a long time, an alarm is sent to remind the athletes to stop motion and reduce motion injury events.

[0095] (2) Multi-channel notification system: send warnings through visual, auditory and tactile methods, and use mobile applications, emails and SMS to convey information to relevant personnel.

[0096] The optimization suggestion and warning module further comprises a display and notification unit and a database and historical record unit.

[0097] The display and notification unit is used to visualize the real-time motion state data of athletes and the risk reliability index.

[0098] The database and historical record unit is used to store historical motion data and risk assessment records of athletes, and the risk assessment records comprise risk reliability indexes corresponding to the historical motion data of athletes.

[0099] (3) Intelligent early warning algorithm: based on real-time data and historical data analysis, using motion risk assessment model combined with deep learning algorithms such as decision tree, random forest or neural network for risk judgment.

[0100] The optimization suggestion early warning module is also used for: using an intelligent algorithm, training a trained risk prediction model according to historical motion data and risk assessment records; inputting the real-time motion data of the athlete into the trained risk prediction model to obtain a risk reliability index. The intelligent algorithm is a decision tree algorithm, a random forest algorithm or a convolutional neural network algorithm.

[0101] (4) API interface: for data exchange and integration with other systems (such as training management system, health monitoring system).

[0102] (5) Real-time communication protocol: ensures real-time data synchronization between system components, such as WebSocket, MQTT, etc.

[0103] The application is based on key points, that is, the motion risk of athletes can be accurately determined, there is no device that affects the motion state in the above process, and it is not restricted by the factors of the motion site conditions; based on the above, the application can accurately detect the motion risk in real time and issue a risk warning prompt.

[0104] The high-precision camera and IMU device are connected to the data acquisition module through data lines. The high-precision camera is responsible for capturing image data of the athlete, and the IMU device is responsible for measuring the athlete's acceleration, angular velocity, and attitude changes. The data acquisition module transmits the collected data to the data fusion module. The data acquisition module is responsible for preliminary processing of data from the high-precision camera and IMU device. The data fusion module receives data from the data acquisition module and passes these data to the real-time data processing module. The data fusion module uses data fusion algorithms (such as Kalman filtering) to comprehensively process data, improving the accuracy of position, velocity, and attitude estimation. The data processing module transmits the processed data to the risk assessment module. The real-time data processing module is responsible for real-time analysis and processing of the movement state, providing accurate and reliable data support for risk assessment. The risk assessment module comprehensively analyzes the data and sends the assessment results to the display and notification unit and the database and historical record unit. The risk assessment module constructs a movement risk field based on the comprehensive analysis results and generates a corresponding risk assessment report. The display and notification unit is responsible for real-time display of risk assessment results and sends early warning notifications to users through visual, auditory, and tactile means. It ensures that information is timely communicated to relevant personnel for quick response. The database and historical record unit is responsible for storing historical data and risk assessment records. It supports long-term data analysis to help identify risk patterns and trends, optimize training plans and risk management strategies. Through the above module structure and its connection relationship, the site movement risk comprehensive real-time evaluation system provided by the application can realize high-precision movement state monitoring, comprehensive risk assessment, and timely risk warning, providing an efficient risk management solution for athletes and coaches.

[0105] The movement risk assessment model can analyze the spatiotemporal position, velocity, and other data of the athlete and the ball, and the system constructs a comprehensive risk field including the field potential field, athlete kinetic field, ball kinetic field, and athlete behavior field. This comprehensive risk assessment method not only considers single factors but also integrates the influence of multiple fields, providing more comprehensive risk analysis and better identifying potential risk points. The application can quickly display the athlete's movement state and risk area based on real-time processing of sensor data. Through dynamic identification and visualization, the real-time position of the athlete and the risk distribution in the sports field can be immediately seen, helping coaches and athletes to quickly make adjustments. This real-time feedback improves the immediate understanding of the athlete's state and enhances the response ability to potential risks. The early warning system uses intelligent algorithms (such as machine learning models) based on real-time data and historical data to judge risks and issue warnings. The trigger conditions set by the rule engine combined with the dynamic adjustment ability of the intelligent algorithm enable the early warning system to accurately identify and predict risks, reducing the likelihood of false positives and false negatives. The intelligentization of early warning improves the accuracy and response speed of the system.

[0106] Based on the same inventive concept, the embodiments of the present application also provide a field sports risk comprehensive real-time evaluation method for implementing the field sports risk comprehensive real-time evaluation system as described above. The implementation scheme for solving the problem provided by the method is similar to the implementation scheme described in the system, so the specific limitations in one or more field sports risk comprehensive real-time evaluation method embodiments provided below can refer to the limitations of the field sports risk comprehensive real-time evaluation system described above, which will not be repeated here.

[0107] In one exemplary embodiment, as shown in Figure 3 a field sports risk comprehensive real-time evaluation method is provided, which includes the following steps S1-S5:

[0108] Step S1: When the athlete is playing a ball game, collect real-time sports data of the athlete; and calculate initial sports information according to the real-time sports data; the real-time sports data includes image data and sports state data, and the sports state data includes acceleration, angular velocity and attitude change of the athlete; the initial sports information includes position, speed, acceleration, sports mode of the athlete, and position, speed, acceleration of the ball.

[0109] Step S2: Preprocess the initial sports information to obtain target sports information.

[0110] Step S3: Construct a sports risk field based on the target sports information; the sports risk field includes a sports field potential energy field, an athlete kinetic energy field, a ball kinetic energy field, and an athlete behavior and psychology field; construct a risk response influence function based on the change of the athlete's sports state in the sports risk field; and establish a sports risk evaluation model according to the risk response influence function and the sports risk field.

[0111] Step S4: Solve the sports risk evaluation model to obtain a sports risk boundary value; the sports risk boundary value includes an upper risk boundary and a lower risk boundary; and calculate a risk reliability index according to the sports risk boundary value.

[0112] Step S5: When the risk reliability index exceeds a sports risk threshold, an alarm is given.

[0113] The position, speed and acceleration of the athlete are monitored in real time, the potential energy field and the kinetic energy field are calculated according to the field position and speed of the athlete, the potential energy field and the kinetic energy field are comprehensively analyzed, the overall energy state of the athlete is evaluated, optimization suggestions and risk warnings are provided, so as to improve the performance of the athlete and reduce the risk of injury. The position, speed and action of the athlete in the sports field are dynamically combined for comprehensive analysis, and real-time performance optimization and risk management solutions are provided for the athlete.

[0114] Any technical features in the above embodiments can be combined, and for the sake of brevity, not all possible combinations are described above, however, it should be understood that the application encompasses all possible combinations of the technical features unless such a combination is not technically possible.

[0115] The principles and implementation manners of the present application are described herein by using specific examples, and the above embodiments are only used to help understand the method of the present application and its core idea; meanwhile, according to the idea of the present application, the specific implementation manners and application scopes will be changed by those skilled in the art. In conclusion, the content of the present specification should not be understood as a limitation of the present application.

Claims

1. A comprehensive real-time assessment system for sports risks in a venue, characterized by: The comprehensive real-time assessment system for sports risks in the venue includes: A real-time monitoring module is configured to collect real-time motion data of an athlete while the athlete is playing a ball game; and calculate initial motion information based on the real-time motion data; the real-time motion data includes image data and motion state data, the motion state data including acceleration, angular velocity, and posture change of the athlete; and the initial motion information includes the position, velocity, acceleration, motion pattern of the athlete and the position, velocity, and acceleration of the ball; Data fusion module, used to pre-process the initial motion information to obtain target motion information; The data processing module is used to: construct a sports risk field based on the target motion information; the sports risk field is composed of the superposition of the sports field potential energy field, the athlete kinetic energy field, the ball kinetic energy field, and the athlete's behavioral psychological field; construct a risk response influence function based on the change of the athlete's motion state in the sports risk field; establish a sports risk assessment model based on the risk response influence function and the sports risk field; define the sports risk field intensity at a certain point on the field as the weighted sum E of the field intensity generated by different elements, as shown in formula (1): E=ω r E r +oh y E y +oh q E q +oh x E x (1); Among them, E r is the risk intensity of the potential energy field of the sports field; E y is the risk intensity of the athlete's kinetic energy field; E q is the risk intensity of the ball kinetic energy field; E x is the risk intensity of the athlete's behavioral psychological field; r 、ω y 、ω q 、ω x Represent the weight coefficients of different risk fields respectively; The risk intensity function of the potential energy field of the sports venue is constructed as shown in Equations (2), (3) and (4): Among them, E1 and E2 represent the potential energy of the sports field at the first angle and the potential energy of the sports field at the second angle, respectively. They are the potential energy sizes considered from different angles and represent the sports risk. E1 is modeled based on a function with large amplitude and fast change speed to represent the rapid increase of the potential energy field; E2 uses a linear function to represent the basic risk, which is superimposed with E1 to reflect the actual sports risk situation; Z(t) is the real-time position of the athlete; Z l is the centerline position of one side of the field; d is the half width of one side of the field; ε i is the potential energy field coefficient of the center line of the site; i = 1, 2 represent the left and right boundaries of the site respectively; Z b1 , Z b2 are the horizontal coordinates of the left and right boundaries of the field, respectively, and Z is the horizontal coordinate of the athlete within the field; is the boundary-related parameter; Summing equations (2) and (3), we can get the potential energy field function E of the sports field: r ; THE r =E1+E2 (4); The specific formula for calculating the risk intensity of the athlete's kinetic energy field is shown in formula (5): Among them, F(x,z) is the correction function; δ0 is the kinetic energy field correction coefficient; m is the athlete's equivalent mass; v is the athlete's speed; The calculation formula of the risk intensity of the ball kinetic energy field is shown in formula (7): Where: Q x (t) and Q y (t) are the horizontal and vertical coordinates of the ball respectively; δ3 is the kinetic energy field adjustment coefficient of the ball; a is the acceleration of the ball; θ is the angle formed between the ball and the player; (x2, Z2) are the coordinates of the center line of the back boundary of one side of the field; The athlete's behavioral psychological field is shown in formula (8): Among them, Eb n is the basic field strength value formed by the target; v n is the speed of the target ball, which refers to the speed of the ball when the opponent hits the ball; L0 is the distance from the origin of the target ball along the target direction, v ε is the correction value; Construct the risk response impact function G(t) to construct the basic risk field equation as shown in formula (13): Where E(t) is the intensity of the motion risk field calculated by formula (1), is the gradient of the risk field; γ and β are the influence coefficients; y i (t) is the risk response function, i represents the speed, acceleration and position of the athlete, then n = 3; m represents the initial time, T i Indicates the sampling time of the athlete's motion status data; Constructing the sports risk assessment model D(t): Among them, μ1 and μ2 are the weights of the risk response impact function and the intensity of the sports risk field, respectively. is the correction parameter; Among them, ξ is the risk reliability index, which reflects the importance of the impact of sports risk field and risk response measures on sports risk; f c (G,E) and f r (G, E) are the mean and deviation of the function, respectively, f U (G,E) and f L (G, E) are the upper and lower risk boundaries respectively; A risk assessment module is configured to solve the motion risk assessment model to obtain a motion risk boundary value; the motion risk boundary value includes an upper risk boundary and a lower risk boundary; and calculate a risk reliability index based on the motion risk boundary value; The optimization suggestion warning module is used to issue an alarm when the risk reliability index exceeds the motion risk threshold.

2. The comprehensive real-time assessment system for sports risks in a venue according to claim 1, characterized in that: The optimization suggestion warning module further includes a display and notification unit; the display and notification unit is used to visualize the athlete's real-time motion status data and risk reliability index.

3. The comprehensive real-time assessment system for sports risks in a venue according to claim 2, characterized in that: The display and notification unit is further configured to send a warning notification to the user via visual, auditory and / or tactile means when the risk reliability index exceeds a motion risk threshold.

4. The comprehensive real-time assessment system for sports risks in a venue according to claim 1, characterized in that: The optimization suggestion warning module also includes a database and a history recording unit; the database and history recording unit are used to: store the athlete's historical sports data and risk assessment records; the risk assessment records include the risk reliability index corresponding to the athlete's historical sports data.

5. The comprehensive real-time assessment system for sports risks in a venue according to claim 4, characterized in that: The optimization suggestion warning module is also used to: use an intelligent algorithm to obtain a trained risk prediction model based on historical sports data and risk assessment records; input the athlete's real-time sports data into the trained risk prediction model to predict a risk reliability index.

6. The comprehensive real-time assessment system for sports risks in a venue according to claim 5, characterized in that: The intelligent algorithm is a decision tree algorithm, a random forest algorithm or a convolutional neural network algorithm.

7. The comprehensive real-time assessment system for sports risks in a venue according to claim 1, characterized in that: The comprehensive real-time assessment system for sports risks in the venue also includes a communication module; the real-time monitoring module, the data fusion module, the data processing module, the risk assessment module and the optimization suggestion warning module are communicatively connected through the communication module.

8. The comprehensive real-time assessment system for sports risks in a venue according to claim 1, characterized in that: The preprocessing is Kalman filtering.

9. A method for comprehensive real-time assessment of on-site sports risk based on the on-site sports risk comprehensive real-time assessment system according to any one of claims 1 to 8, characterized in that: The method for comprehensive real-time assessment of sports risks within a venue includes: When an athlete plays a ball game, real-time motion data of the athlete is collected; and initial motion information is calculated based on the real-time motion data; the real-time motion data includes image data and motion state data, and the motion state data includes acceleration, angular velocity, and posture change of the athlete; the initial motion information includes the position, velocity, acceleration, motion mode of the athlete and the position, velocity, and acceleration of the ball; Preprocessing the initial motion information to obtain target motion information; Constructing a sports risk field based on the target motion information; the sports risk field includes a sports field potential energy field, an athlete kinetic energy field, a ball kinetic energy field, and an athlete behavioral psychology field; constructing a risk response influence function based on changes in the athlete's motion state in the sports risk field; and establishing a sports risk assessment model based on the risk response influence function and the sports risk field; Solving the motion risk assessment model to obtain a motion risk boundary value; the motion risk boundary value includes an upper risk boundary and a lower risk boundary; calculating a risk reliability index based on the motion risk boundary value; When the risk reliability index exceeds the motion risk threshold, an alarm is issued.

Images