Sports event risk prediction method and system based on risk level model

By integrating historical injury case data and athlete data to calculate risk scores, the problems of inaccurate risk assessment and untimely warning in existing technologies are solved, accurate quantification and real-time warning of athlete risks are achieved, and the efficiency of event management and emergency response capabilities are improved.

CN120724336AInactive Publication Date: 2025-09-30QINGDAO AGRI UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510889666.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-30
Publication Date
2025-09-30
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing sports event risk management system lacks comprehensive consideration of athletes' physical condition and training load, resulting in incomplete risk identification and inaccurate assessment, inability to accurately quantify and predict risk levels, and untimely early warning mechanisms.

Method used

By integrating historical athlete injury case data, rules containing conditional statements and risk level adjustment values ​​are generated. Combined with the athlete's basic physical examination data and daily training load data, the total risk exposure score is calculated and an early warning is issued when the threshold is reached.

Benefits of technology

It has achieved precise quantification, dynamic monitoring and real-time warning of athlete injury risks, improved the accuracy and timeliness of risk assessment, reduced the incidence of athlete injuries, and improved the efficiency of event management and emergency response capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120724336A_ABST
    Figure CN120724336A_ABST
Patent Text Reader

Abstract

The invention discloses a sports event risk prediction method and system based on a risk level model, and belongs to the technical field of risk prevention and control. The method comprises the following steps: acquiring a historical athlete injury case data set; acquiring multiple data in each historical damage case, and generating a rule containing conditional statements and risk level adjustment values; acquiring multiple body data of the target athlete, and performing preprocessing; obtaining a total risk exposure degree integral based on the preprocessed multiple body data; and if the total risk exposure integral is not less than a preset integral threshold, generating a high risk level and sending an early warning instruction. According to the method, the body data and the training load of the athlete are comprehensively evaluated, the quantitative rule is generated in combination with the historical injury cases, the accurate and dynamic injury risk early warning effect is achieved, and the problems that in the prior art, risk evaluation is not accurate, and early warning is not timely are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of risk prevention and control technology, and in particular to a sports event risk prediction method and system based on a risk level model. Background Art

[0002] As the scale of university sports events continues to expand, the incidence of sports injuries among college athletes is showing a significant upward trend. According to 2023 statistics from the Ministry of Education's Department of Physical Education, Health, and Art, acute injuries during competitions accounted for 68% of annual sports injury cases in regular universities, with over half of these preventable injuries resulting from inadequate pre-competition physical assessments.

[0003] Existing sports event risk management systems typically identify and assess risks through simple classification statistics and empirical judgment. For example, they only roughly categorize and estimate the probability of common risks that have occurred in similar events in the past, such as athlete injuries and severe weather, and then formulate risk response strategies based on this.

[0004] Existing risk assessment methods are relatively one-sided and lack comprehensive consideration of athletes' physical condition and training load. This makes it difficult to accurately quantify and predict risk levels, resulting in the following problems:

[0005] Incomplete risk identification: Existing risk assessment methods mainly rely on simple classification statistics of historical data and empirical judgment, which cannot fully cover the various complex and changeable risk factors in sports events, especially those new or hidden risk factors, which are prone to omissions.

[0006] Inaccurate risk assessment: The lack of scientific and reasonable quantitative models and grading standards makes it impossible to accurately measure the severity and likelihood of different risks, resulting in blindness in resource allocation and risk response priority determination. Summary of the Invention

[0007] The embodiments of the present application provide a sports event risk prediction method and system based on a risk level model, which solves the problems of incomplete risk identification, inaccurate assessment and untimely early warning mechanism in the existing technology, and achieves the technical effects of accurate quantification, dynamic monitoring and real-time early warning of athlete injury risks.

[0008] The embodiment of the present application provides a sports event risk prediction method based on a risk level model, comprising: obtaining a historical athlete injury case data set and performing preprocessing;

[0009] Based on the pre-processed historical athlete injury case data set, multiple data in each historical injury case are obtained to generate rules containing conditional statements and risk level adjustment values;

[0010] Acquire multiple physical data of the target athlete and perform pre-processing;

[0011] Based on the pre-processed multiple body data, the total risk exposure score is obtained;

[0012] If the total risk exposure score is not less than the preset score threshold, a high risk level is generated and an early warning instruction is issued.

[0013] Furthermore, the steps of obtaining a historical athlete injury case data set and performing preprocessing include:

[0014] Obtain and integrate historical athlete injury event information, construct an original data set, and obtain a historical athlete injury case data set;

[0015] The injury event information includes the injured body part, the nature of the injury, the stage of the sport at the time of the injury, and an objective assessment record of the severity of the injury;

[0016] A standardized cleaning operation is performed on the injury case data set.

[0017] Furthermore, the step of generating a rule including a conditional statement and a risk level adjustment value includes:

[0018] Based on the pre-processed historical athlete injury case data set, the numerical features of the environmental monitoring data, training behavior record data, and physiological index data in each injury case are extracted;

[0019] converting the numerical features into conditional statements;

[0020] Match the preset risk level adjustment value based on the injury severity recorded in the injury case;

[0021] The conditional statements are combined with risk level adjustment value generation rules and stored in a rule base.

[0022] Furthermore, the step of converting the numerical feature into a conditional statement includes:

[0023] Obtaining a data type of the numerical feature, wherein the data type includes a continuous value and a discrete value;

[0024] For continuous numerical features, the numerical interval judgment condition is generated by comparing the operator with the threshold boundary;

[0025] For discrete numerical features, classification matching judgment conditions are generated by enumerating matching operators;

[0026] The judgment conditions in the same damage case are combined through logical operators to obtain conditional statements with numerical characteristics.

[0027] Furthermore, the step of obtaining a total risk exposure score based on the pre-processed multiple body data includes:

[0028] Extract the target athlete's basic physical examination data and daily training load data based on the pre-processed multiple body data;

[0029] Based on the basic physical examination data of the target athlete, an initial risk score of the target athlete is obtained;

[0030] Based on the daily training load data of the target athlete, the newly added points of the target athlete on that day are obtained;

[0031] The total risk exposure score is obtained through the calculation formula of the total risk exposure score.

[0032] Furthermore, the total risk exposure score calculation formula is:

[0033] ;

[0034] Where, is the total risk exposure score, is the initial risk score of the target athlete, For the New points added on the day of the day, is the historical rule matching coefficient, ,in, For the The matching degree of the conditions of the rules, For the The risk level adjustment value of the rule.

[0035] Furthermore, based on the basic physical examination data of the target athlete, the step of obtaining the initial risk score of the target athlete includes:

[0036] Obtain the target athlete's physical and mental quality index, heart rate variability index, and body fat percentage through the target athlete's basic physical examination data;

[0037] The initial risk score is obtained by the initial risk score calculation formula;

[0038] The calculation formula for the initial risk score is:

[0039] ;

[0040] Where, is the body mass index, is the heart rate variability index, is the body fat percentage, For health Baseline value, Standard threshold, for Volatility tolerance, 、 、 Physiological risk factor.

[0041] Furthermore, based on the daily training load data of the target athlete, the step of obtaining the newly added points of the target athlete on that day includes:

[0042] Through the daily training load data of the target athlete, the quantitative value of the target athlete's training intensity level on that day, the actual value of the sleep duration on that day, the quantitative value of the subjective fatigue level on that day, and the quantitative value of the subjective fatigue level on that day are obtained;

[0043] Obtain the target athlete's newly added points for the day through the newly added points calculation formula for the day;

[0044] The calculation formula for the newly added points on the day is:

[0045] ;

[0046] Where, It is the quantitative value of the training intensity level of the day. is the actual measured value of sleep duration on that day, It is the quantitative value of subjective fatigue level on that day. is the difference in days from the event day, The starting days for pre-race training reduction, 、 、 、 is the dynamic adjustment coefficient.

[0047] Furthermore, the steps of generating a high risk level and issuing an early warning instruction include:

[0048] Generate text alert content including the total risk exposure score value, the corresponding sports event risk threshold value and the risk level identifier;

[0049] Calling the target athlete's pre-registered mobile terminal communication identifier and the associated coach's terminal communication identifier;

[0050] Sending the first alarm content to the mobile terminal communication identifier via the SMS transmission protocol;

[0051] sending the second alarm content to the coach terminal communication identifier via the mobile application data transmission protocol;

[0052] The first warning content includes a quantitative comparison result of the total risk exposure score and the risk threshold;

[0053] The second warning content additionally includes the target athlete's risk exposure score change curve data for seven consecutive days.

[0054] The embodiment of the present application provides a sports event risk prediction system based on a risk level model, which is used to implement a sports event risk prediction method based on a risk level model, and is characterized by comprising: a historical data acquisition module, a rule generation module, a target data acquisition module, a score calculation module, and a risk level generation module;

[0055] The historical data acquisition module is used to acquire a historical athlete injury case data set and perform pre-processing;

[0056] The rule generation module is used to obtain multiple data in each historical injury case based on the pre-processed historical athlete injury case data set, and generate a rule containing a conditional statement and a risk level adjustment value;

[0057] The target data acquisition module is used to acquire multiple physical data of the target athlete and perform preprocessing;

[0058] The score calculation module is used to obtain a total risk exposure score based on the pre-processed multiple body data;

[0059] The risk level generating module is configured to generate a high risk level and issue an early warning instruction if the total risk exposure score is not less than a preset score threshold.

[0060] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0061] 1. By integrating historical athlete injury case data and generating rules containing conditional statements and risk level adjustment values, the system accurately quantifies and assesses different risk factors. This enables dynamic monitoring and early warning of athlete injury risks, effectively resolving the existing issues of inaccurate risk assessment and the inability to fully encompass complex and changing risk factors, thus avoiding event management loopholes caused by incomplete risk identification.

[0062] 2. By constructing a total risk exposure score calculation model that comprehensively considers basic physical examination data and daily training load data, we can achieve dynamic tracking and quantitative assessment of athletes' risk status. This enables refined management of athletes' training processes, effectively resolving the existing technology's inability to accurately measure risk severity and likelihood, and avoiding blind resource allocation and delayed risk response.

[0063] 3. Through a multi-dimensional risk assessment and early warning mechanism, combined with real-time and historical data, comprehensive control and timely response to athlete risk status are achieved. This enables efficient management of sports event risks, effectively resolving the existing problem of insufficiently timely risk warnings and the inability to meet the real-time management needs of events. This improves the emergency response capabilities and risk management efficiency of event organizations. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flow chart of a sports event risk prediction method based on a risk level model provided in an embodiment of the present application;

[0065] Figure 2 A schematic diagram of the structure of a sports event risk prediction system based on a risk level model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The embodiments of the present application provide a sports event risk prediction method and system based on a risk level model, thereby solving the problems of inaccurate risk assessment and untimely warning in the prior art. By integrating historical athlete injury case data to generate quantitative rules and comprehensively evaluating the athlete's physical data and training load to dynamically calculate the risk exposure score, accurate quantification, dynamic monitoring and real-time warning of athlete injury risks are achieved.

[0067] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0068] like Figure 1 FIG2 is a flow chart of a method for predicting sports event risks based on a risk level model according to an embodiment of the present application. The method is applied to a sports event risk prediction system based on a risk level model. The method includes the following steps: obtaining a historical athlete injury case data set and performing preprocessing;

[0069] Based on the pre-processed historical athlete injury case data set, multiple data from each historical injury case is obtained, wherein the multiple data includes environmental data, training behavior data, and physiological monitoring data, and a rule containing a conditional statement and a risk level adjustment value is generated;

[0070] Obtain and pre-process multiple physical data of the target athlete; the multiple physical data include basic physical examination data (including height, weight, heart rate), daily training load data, and subjective state feedback data.

[0071] Based on the pre-processed multiple body data, a total risk exposure score is obtained; an initial risk score is calculated based on basic physical examination data, and a new daily score is calculated based on daily training load data and subjective state feedback data. The initial risk score and the new daily scores are accumulated to generate a total risk score;

[0072] If the total risk exposure score is not less than the preset score threshold, a high risk level is generated and an early warning instruction is issued.

[0073] Furthermore, the steps of obtaining a historical athlete injury case data set and performing preprocessing include:

[0074] Obtain and integrate historical athlete injury event information, construct an original data set, and obtain a historical athlete injury case data set;

[0075] The injury event information includes the injured body part, the nature of the injury, the stage of the sport at the time of the injury, and an objective assessment record of the severity of the injury;

[0076] Standardized cleaning operations are performed on the injury case data set, thereby identifying and processing empty fields in data records, and making consistent processing of measurement units and record formats for data from different sources or different batches. At the same time, data records with exactly the same content and data records with logical conflicts are detected and eliminated, thereby forming a historical athlete injury case data set with unified structure and regular content for use in subsequent rule generation steps.

[0077] Furthermore, the step of generating a rule including a conditional statement and a risk level adjustment value includes:

[0078] Based on the pre-processed historical athlete injury case data set, the numerical features of the environmental monitoring data, training behavior record data, and physiological index data in each injury case are extracted;

[0079] converting the numerical features into conditional statements;

[0080] Match the preset risk level adjustment value based on the injury severity recorded in the injury case;

[0081] The conditional statements are combined with risk level adjustment value generation rules and stored in a rule base.

[0082] In this embodiment, by extracting multiple data features from historical damage cases and converting them into conditional statements, and matching the risk level adjustment value generation rules, different types of risk factors can be accurately identified and quantified, thereby improving the accuracy and adaptability of risk assessment, ensuring that the rule base can comprehensively cover various potential risk scenarios, and providing a reliable basis for subsequent risk prediction.

[0083] By processing different data types separately, the integrity and detailed information of the data can be retained, making the conditional statements more in line with the actual risk situation and enhancing the refinement of risk assessment.

[0084] Furthermore, the step of converting the numerical feature into a conditional statement includes:

[0085] Obtaining a data type of the numerical feature, wherein the data type includes a continuous value and a discrete value;

[0086] For continuous numerical features, the numerical interval judgment condition is generated by comparing the operator with the threshold boundary;

[0087] For discrete numerical features, classification matching judgment conditions are generated by enumerating matching operators;

[0088] The judgment conditions in the same damage case are combined through logical operators to obtain conditional statements with numerical characteristics.

[0089] Furthermore, the step of obtaining a total risk exposure score based on the pre-processed multiple body data includes:

[0090] Extract the target athlete's basic physical examination data and daily training load data based on the pre-processed multiple body data;

[0091] Based on the basic physical examination data of the target athlete, an initial risk score of the target athlete is obtained;

[0092] Based on the daily training load data of the target athlete, the newly added points of the target athlete on that day are obtained;

[0093] The total risk exposure score is obtained through the calculation formula of the total risk exposure score.

[0094] In this embodiment, the total risk exposure score is calculated by comprehensively evaluating the basic physical examination data and daily training load data of the target athletes, which can fully reflect the health and training status of the athletes during the competition and realize dynamic monitoring of risks.

[0095] The initial risk score provides a baseline risk assessment based on the athlete's physiological indicators, while the daily added points are adjusted based on daily training load and physical response, allowing the total risk exposure score to reflect real-time changes in an athlete's risk. This not only improves the accuracy of risk assessments but also provides timely risk warnings to event organizers and coaches, helping them implement preventative measures and reduce the incidence of athlete injuries.

[0096] Furthermore, the total risk exposure score calculation formula is:

[0097] ;

[0098] Where, is the total risk exposure score, is the initial risk score of the target athlete, For the New points added on the day of the day, is the historical rule matching coefficient, ,in, For the The matching degree of the conditions of the rules, For the The risk level adjustment value of the rule.

[0099] Furthermore, based on the basic physical examination data of the target athlete, the step of obtaining the initial risk score of the target athlete includes:

[0100] Obtain the target athlete's physical and mental quality index, heart rate variability index, and body fat percentage through the target athlete's basic physical examination data;

[0101] The initial risk score is obtained by the initial risk score calculation formula;

[0102] The calculation formula for the initial risk score is:

[0103] ;

[0104] Where, is the body mass index, is the heart rate variability index, is the body fat percentage, For health Baseline value, Standard threshold, for Volatility tolerance, 、 、 is the physiological risk factor ( 、 、 ).

[0105] Furthermore, based on the daily training load data of the target athlete, the step of obtaining the newly added points of the target athlete on that day includes:

[0106] Through the daily training load data of the target athlete, the quantitative value of the target athlete's training intensity level on that day, the actual value of the sleep duration on that day, the quantitative value of the subjective fatigue level on that day, and the quantitative value of the subjective fatigue level on that day are obtained;

[0107] Obtain the target athlete's newly added points for the day through the newly added points calculation formula for the day;

[0108] The calculation formula for the newly added points on the day is:

[0109] ;

[0110] Where, It is the quantitative value of the training intensity level of the day. is the actual measured value of sleep duration on that day, It is the quantitative value of subjective fatigue level on that day. is the difference in days from the event day, The starting days for pre-race training reduction, 、 、 、 is the dynamic adjustment coefficient ( 、 、 、 ).

[0111] Furthermore, the steps of generating a high risk level and issuing an early warning instruction include:

[0112] Generate text alert content including the total risk exposure score value, the corresponding sports event risk threshold value and the risk level identifier;

[0113] Calling the target athlete's pre-registered mobile terminal communication identifier and the associated coach's terminal communication identifier;

[0114] Sending the first alarm content to the mobile terminal communication identifier via the SMS transmission protocol;

[0115] sending the second alarm content to the coach terminal communication identifier via the mobile application data transmission protocol;

[0116] The first warning content includes a quantitative comparison result of the total risk exposure score and the risk threshold;

[0117] The second warning content additionally includes the target athlete's risk exposure score change curve data for seven consecutive days.

[0118] In this embodiment, a multi-channel, multi-content early warning mechanism ensures the timely dissemination and effective utilization of risk information. Alerts are sent to athletes and coaches via SMS and mobile apps, respectively. This not only improves information delivery efficiency but also ensures that each recipient receives information tailored to their needs. Athletes can promptly understand their risk status, while coaches can leverage detailed risk profile data for deeper analysis and decision-making, enabling them to implement more effective preventative measures and reduce the risk of injury.

[0119] like Figure 2 , which is a schematic diagram of the structure of a sports event risk prediction system based on a risk level model provided in an embodiment of the present application, and is used to implement a sports event risk prediction method based on a risk level model. The sports event risk prediction system based on a risk level model provided in an embodiment of the present application includes: a historical data acquisition module, a rule generation module, a target data acquisition module, a score calculation module, and a risk level generation module;

[0120] The historical data acquisition module is used to acquire a historical athlete injury case data set and perform pre-processing;

[0121] The rule generation module is used to obtain multiple data in each historical injury case based on the pre-processed historical athlete injury case data set, and generate a rule containing a conditional statement and a risk level adjustment value;

[0122] The target data acquisition module is used to acquire multiple physical data of the target athlete and perform preprocessing;

[0123] The score calculation module is used to obtain a total risk exposure score based on the pre-processed multiple body data;

[0124] The risk level generating module is configured to generate a high risk level and issue an early warning instruction if the total risk exposure score is not less than a preset score threshold.

[0125] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0127] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0129] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0130] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A sports event risk prediction method based on a risk level model, characterized in that: The following steps are involved: Obtain a historical athlete injury case data set and perform preprocessing; Based on the pre-processed historical athlete injury case data set, multiple data in each historical injury case are obtained to generate rules containing conditional statements and risk level adjustment values; Acquire multiple physical data of the target athlete and perform pre-processing; Based on the pre-processed multiple body data, the total risk exposure score is obtained; If the total risk exposure score is not less than the preset score threshold, a high risk level is generated and an early warning instruction is issued.

2. A sports event risk prediction method based on a risk level model as claimed in claim 1, characterized in that: The steps to obtain a historical athlete injury case data set and perform preprocessing include: Obtain and integrate historical athlete injury event information, construct an original data set, and obtain a historical athlete injury case data set; The injury event information includes the injured body part, the nature of the injury, the stage of the sport at the time of the injury, and an objective assessment record of the severity of the injury; A standardized cleaning operation is performed on the injury case data set.

3. A sports event risk prediction method based on a risk level model as claimed in claim 1, characterized in that: The steps for generating a rule containing conditional statements and risk level adjustment values ​​include: Based on the pre-processed historical athlete injury case data set, the numerical features of the environmental monitoring data, training behavior record data, and physiological index data in each injury case are extracted; Converting the numerical features into conditional statements; Match the preset risk level adjustment value based on the injury severity recorded in the injury case; The conditional statements are combined with risk level adjustment value generation rules and stored in a rule base.

4. A sports event risk prediction method based on a risk level model as claimed in claim 1, characterized in that: The steps of converting the numerical features into conditional statements include: Obtaining a data type of the numerical feature, wherein the data type includes a continuous value and a discrete value; For continuous numerical features, the numerical interval judgment condition is generated by comparing the operator with the threshold boundary; For discrete numerical features, classification matching judgment conditions are generated by enumerating matching operators; The judgment conditions in the same damage case are combined through logical operators to obtain conditional statements with numerical characteristics.

5. A sports event risk prediction method based on a risk level model as claimed in claim 1, characterized in that: The steps of obtaining the total risk exposure score based on the pre-processed multiple body data include: Extract the target athlete's basic physical examination data and daily training load data based on the pre-processed multiple body data; Based on the basic physical examination data of the target athlete, an initial risk score of the target athlete is obtained; Based on the daily training load data of the target athlete, the newly added points of the target athlete on that day are obtained; The total risk exposure score is obtained through the calculation formula of the total risk exposure score.

6. A sports event risk prediction method based on a risk level model as claimed in claim 5, characterized in that: The total risk exposure score calculation formula is: ; Where, is the total risk exposure score, is the initial risk score of the target athlete, For the The points added on the day of the is the historical rule matching coefficient, ,in, For the The matching degree of the conditions of the rules, For the The risk level adjustment value of the rule.

7. A sports event risk prediction method based on a risk level model as claimed in claim 5, characterized in that: The steps of obtaining the initial risk score of the target athlete based on the basic physical examination data of the target athlete include: Obtain the target athlete's physical and mental quality index, heart rate variability index, and body fat percentage through the target athlete's basic physical examination data; The initial risk score is obtained by the initial risk score calculation formula; The calculation formula for the initial risk score is: ; Where, is the body mass index, is the heart rate variability index, is the body fat percentage, For health Baseline value, Standard threshold, for Volatility tolerance, 、 、 Physiological risk factor.

8. A sports event risk prediction method based on a risk level model as claimed in claim 5, characterized in that: The steps of obtaining the target athlete's daily newly added points based on the target athlete's daily training load data include: Through the daily training load data of the target athlete, the quantitative value of the target athlete's training intensity level on that day, the actual value of the sleep duration on that day, the quantitative value of the subjective fatigue level on that day, and the quantitative value of the subjective fatigue level on that day are obtained; Obtain the target athlete's newly added points for the day through the newly added points calculation formula for the day; The calculation formula for the newly added points on the day is: ; Where, It is the quantitative value of the training intensity level of the day. is the actual measured value of sleep duration on that day, It is the quantitative value of subjective fatigue level on that day. is the difference in days from the event day, The starting days for pre-race training reduction, 、 、 、 is the dynamic adjustment coefficient.

9. A sports event risk prediction method based on a risk level model as claimed in claim 1, characterized in that: The steps to generate a high risk level and issue an early warning instruction include: Generate text alert content including the total risk exposure score value, the corresponding sports event risk threshold value and the risk level identifier; Calling the target athlete's pre-registered mobile terminal communication identifier and the associated coach's terminal communication identifier; Sending the first alarm content to the mobile terminal communication identifier via the SMS transmission protocol; sending the second alarm content to the coach terminal communication identifier via the mobile application data transmission protocol; The first warning content includes a quantitative comparison result of the total risk exposure score and the risk threshold; The second warning content additionally includes the target athlete's risk exposure score change curve data for seven consecutive days.

10. A sports event risk prediction system based on a risk level model, used to implement a sports event risk prediction method based on a risk level model as described in any one of claims 1 to 9, characterized in that: include: Historical data acquisition module, rule generation module, target data acquisition module, integral calculation module, risk level generation module; The historical data acquisition module is used to acquire a historical athlete injury case data set and perform pre-processing; The rule generation module is used to obtain multiple data in each historical injury case based on the pre-processed historical athlete injury case data set, and generate a rule containing a conditional statement and a risk level adjustment value; The target data acquisition module is used to acquire multiple physical data of the target athlete and perform preprocessing; The score calculation module is used to obtain a total risk exposure score based on the pre-processed multiple body data; The risk level generating module is configured to generate a high risk level and issue an early warning instruction if the total risk exposure score is not less than a preset score threshold.