Big data-based sports competition organization planning method

Abstract

The invention relates to the technical field of sports competition, in particular to a big data-based sports competition organization planning method, which comprises the following steps: acquiring physiological data of an athlete at least comprising heart rate data and muscle fatigue data, executing state evaluation processing based on the physiological data of the athlete, generating a state index, and determining the state of the athlete based on the state index. Executing a strategy generation algorithm, determining at least one candidate strategy, generating a plurality of strategy options based on the state index, and determining a final personalized strategy based on the candidate strategy in combination with a preset competition target. By calculating the multi-dimensional first state score and the second state score, the fatigue risk and the expression potential of the athlete are subjected to refined and quantitative evaluation, and the strategy is generated and optimized in combination with the preset competition target, so that the finally output strategy is highly matched with the unique physiological characteristics of the athlete.

Description

Technical Field

[0001] This invention relates to the field of sports competition technology, and specifically to a method for organizing and planning sports competitions based on big data. Background Technology

[0002] In the field of modern sports competition organization and planning, with the expansion of competition scale, the improvement of project professionalism, and the prominence of individual differences among athletes, the traditional experience-based planning model can no longer meet the needs of precision, personalization, and efficiency. In traditional competition planning, the perception of athletes' physiological state mostly relies on pre-competition static physical examination data or post-competition review statistics, which cannot capture the dynamic physiological changes of athletes in real time during the competition. This fragmented data collection method makes it difficult for planners to accurately judge the fatigue risk and performance potential of athletes at different stages of the competition, and thus cannot make targeted adjustments to key strategies such as energy allocation and rest intervals, which easily leads to the problem of disconnect between strategy and physiological state. Summary of the Invention

[0003] This invention addresses the technical problems existing in the prior art by providing a big data-based method for organizing and planning sports competitions.

[0004] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A method for organizing and planning sports competitions based on big data, comprising the following steps: S101. Acquire the athlete's physiological data, which includes at least heart rate data and muscle fatigue data. The physiological data is acquired by obtaining the first heart rate data through a wearable sensor and the second muscle fatigue data through an electromyography sensor. S102. Based on the athlete's physiological data, perform state assessment processing and generate state indicators, including calculating a first state score and a first state score based on the athlete's physiological data, and generating state indicators based on the first state score and the first state score. S103. Based on the state indicators, execute the strategy generation algorithm to determine at least one candidate strategy and generate multiple strategy options based on the state indicators. The strategy options include adjusting the rest time and changing the exercise intensity. S104. Based on candidate strategies and combined with preset competition objectives, determine the final personalized strategy. The final personalized strategy is determined by executing simulation applications through candidate strategies to generate simulation performance data. Based on the simulation performance data and combined with preset adjustment rules, determine the final personalized strategy and output it to the athlete's terminal.

[0005] In a preferred embodiment, in step S101, raw physiological data of the athlete is collected by a dedicated sensor deployed on the athlete's body. This raw physiological data includes heart rate data and muscle fatigue data. The heart rate data is continuously monitored and acquired by a photoelectric sensor in a wearable device, including heart rate variability and peak heart rate. Heart rate variability refers to the variation in the difference between successive heartbeat cycles, determined by the standard deviation of adjacent RR intervals in the pulse wave signal. The specific calculation formula is as follows: Wherein, SDNN represents heart rate variability. This represents the i-th valid RR interval, i.e., the time interval between adjacent heartbeats. The average value of all valid RR intervals within a specific monitoring period is represented by N, which represents the total number of valid RR intervals within that period. Heart rate variability is used to quantify the regulatory function of the athlete's autonomic nervous system and the degree of fatigue accumulation. Peak heart rate is the highest heart rate value recorded within a specific monitoring period, which is determined by comparing the instantaneous heart rate with a preset historical heart rate baseline in real time, and is used to assess the athlete's current maximum cardiovascular load capacity. Muscle fatigue data is obtained by collecting electrical signals generated during muscle activity using electromyography (EMG) sensors attached to the surface of the athlete's muscle groups. This second set of data includes muscle activation level and recovery rate. Muscle activation level refers to the amplitude intensity of the EMG signal during muscle exertion, which is determined by calculating the root mean square value after filtering and rectifying the raw EMG signal. The specific calculation formula is as follows: in, EMG indicates the degree of muscle activation. This represents the electromyographic signal value after filtering and rectification. This indicates the length of the time window for integral calculation, which is preset according to the type of motion. This indicates that the square of the electromyographic signal is integrated over the time interval [0, T]. The degree of muscle activation directly reflects the mobilization level and exertion state of a specific muscle group in an athlete. The recovery rate refers to how quickly the electromyographic signal characteristics recover to the resting baseline level after high-intensity activity. The recovery rate is calculated by analyzing the recovery trend of the median frequency of the electromyographic spectrum after high-intensity activity. At a preset time point after the end of the activity ( , ,..., Calculate the median frequency of the electromyographic signal, then perform linear regression analysis with time as the independent variable and median frequency as the dependent variable. The recovery rate is the slope k of the regression line. The specific calculation formula is as follows: Where n represents the number of sampling time points, This represents the i-th time point. The median frequency value at the corresponding time point is represented by the slope k, which is the recovery rate. The recovery rate is used to assess the muscle's ability to eliminate fatigue and recover.

[0006] In a preferred embodiment, in S102, a first state score is calculated based on heart rate variability and muscle recovery rate as core input parameters. A preset weighting coefficient is assigned to heart rate variability and muscle recovery rate. The weighting coefficient is preset based on the importance of each parameter's contribution to fatigue risk. The first state score is output through linear weighting. The specific calculation formula is as follows: in, Represents the first-state score. This represents the current value of heart rate variability. This represents the current value indicating the muscle recovery rate. and These represent the results after normalizing HRV and RR, respectively. and The first state score is calculated using preset weighting coefficients for normalized parameter allocation. If a score is within a pre-defined standardized range, it indicates that the athlete is experiencing high levels of physiological fatigue and faces a greater risk of sports injuries and performance decline. Based on peak heart rate and muscle activation level as core input parameters, and after normalization of the input parameters, another set of preset weighting coefficients are assigned to peak heart rate and muscle activation level. The second state score is then output through a corresponding weighted calculation model. The specific calculation formula is as follows: in, This represents the current peak heart rate. The current value indicating the level of muscle activation. , They represent respectively to and The result after normalization and These are preset weighting coefficients assigned to the parameters. The value of the second state score is standardized within a preset range. A high score indicates that the athlete has high potential to complete high-intensity technical movements at the current moment. After generating the first and second state scores, a final state index is generated based on these two scores. This state index is a structured dataset containing at least the first and second state scores, and a state level label based on a comprehensive assessment of both scores. The state level label is determined by mapping the first and second state scores to a preset state matrix. This state matrix defines the state levels corresponding to different score combinations. and The value is used to determine the region to which it belongs in the state matrix. The judgment logic is as follows: Where L represents the status level label, , It refers to the score of the first state. The preset threshold, , It refers to the second state score. The preset thresholds, and the resulting state indicators, quantify the athlete's fatigue risk and performance potential.

[0007] In a preferred embodiment, in step S103, based on the output state indicators, a matching and instantiation operation is performed by querying a preset strategy regulation library. First, the state level label is parsed and used as the top-level basis for the strategy direction. After determining the strategy direction, the strategy type is specifically parameterized using the quantitative parameters in the state indicators, namely the first state score and the second state score. For adjusting rest time, the specific rest duration is calculated based on the value of the first state score using a rest-fatigue relationship function. This function defines a positive correlation between fatigue level and required recovery time. The specific calculation formula is as follows: in, Indicates the specific rest duration. This indicates the preset minimum rest duration. This indicates the preset maximum rest duration. This represents the preset fatigue risk score baseline value. This represents the minimum allowed value of the preset fatigue risk score in the calculation. For changes in exercise intensity, the target intensity value is determined based on the value of the second state score through an intensity-potential relationship function. This function ensures that the recommended intensity matches the current physical potential. The specific calculation formula is as follows: in, Indicates the target motion intensity value. This indicates the preset minimum intensity limit. This indicates the preset maximum intensity limit. This represents the current second-state score. This represents the preset performance potential score benchmark. This indicates the maximum allowed value for the preset performance potential score in the calculation; When performing impact analysis on each strategy option, two key pre-defined boundary conditions are relied upon: a performance threshold and a risk threshold. For each generated strategy option with specific parameters, a predictive model is launched. The input to the predictive model is the current state index and the parameters of the strategy option. After the model runs, it outputs two core predicted values: the first is the predicted performance gain, representing the expected change in the athlete's second state score after implementing the strategy; the second is the predicted risk change, representing the expected change in the athlete's first state score after implementing the strategy. For each strategy option, the predicted performance gain is... Compared with the predicted risk change value The calculation is performed using the following linear model, and the specific calculation formula is as follows: in, This represents the predicted performance gain value, which is the expected change in the second-state score. This represents the predicted risk change value, which is the expected change in the first-state score. This indicates the specific input parameters for the policy option being evaluated. , This represents the preset scaling factor and intercept for performance gain. , This represents the preset proportional coefficient and intercept for risk changes. The predicted output of each strategy option is compared with the preset boundary conditions to initially screen out strategy options that meet the basic safety and effectiveness requirements. A two-stage screening and optimization decision-making process is implemented to determine the final optimal strategy. The first stage is safety screening, which compares the predicted risk change value of all strategy phenomena with a preset risk threshold and excludes all strategy options whose predicted risk change value is greater than the preset risk threshold. The second stage is performance optimization, which sorts the feasible strategy options that passed the first stage screening in descending order according to the predicted performance gain value of each option and selects the strategy option with the highest predicted performance gain value as the final candidate strategy. When multiple strategy options have the same predicted risk change value, a preset priority rule will be used for final decision. The final candidate strategy is encapsulated into a structured data object containing specific action instructions and output to the competition organization and management unit.

[0008] In a preferred embodiment, in step S104, based on the parameters of the candidate strategy and the athlete's current state indicators, the strategy effect is deduced in a virtual environment. First, a digital simulation environment is initialized, and the initial state of this environment is set to the athlete's current physiological state, i.e., the first state score. With second state score The measured values ​​are used to input the specific parameters of the candidate strategy into a preset state evolution model. The state evolution model simulates the trajectory of the athlete's physiological state over time under strategy intervention through a predefined state transition equation. The specific calculation formula is as follows: in, This represents the predicted fatigue score at simulation time t. This represents the initial fatigue score at the start of the simulation. represents the predicted performance score at simulation time t, and represents the initial performance score at the start of the simulation. These values ​​are directly derived from the athlete's current real-time performance indicators. Represents the intensity function. This represents the recovery function. This represents the fatigue accumulation function. , , , This represents the preset physiological response coefficient. Representing the integral sign, after a simulation cycle Then, the simulation performance data is output, including the predicted fatigue score and the predicted performance score at the end of the simulation, forming a quantitative prediction of the consequences of strategy execution. The simulated performance data is matched with the preset competition goals. If the goal is to finish the race safely, the predicted fatigue score must always be higher than the preset minimum safety threshold. If the goal is to achieve the best performance, the predicted performance score must reach the preset excellent performance threshold. When the simulation results fully meet the competition goals, the candidate strategy is directly determined as the final strategy. When the simulation results do not meet the requirements, an iterative optimization program is started. The iterative optimization program adjusts the mapping table according to the preset parameters, makes targeted corrections to the strategy parameters, and then re-executes the simulation application until a strategy that meets the conditions is found. The verified personalized strategy is encapsulated into a standardized executable instruction set, which includes the strategy type, specific execution parameters, and expected effects. This executable instruction set is then transmitted to the athlete's terminal.

[0009] The beneficial effects of this invention are as follows: By continuously acquiring and processing physiological data streams, this invention can dynamically capture subtle changes in the athlete's state and simulate and predict the effect of strategies based on state evolution models. This overcomes the drawbacks of traditional methods that rely on experience-based judgment and lag analysis, enabling strategy intervention to occur before the athlete's state deteriorates significantly. By calculating multi-dimensional first and second state scores, the fatigue risk and performance potential of athletes can be assessed in a refined and quantitative manner. Combined with preset competition goals, strategies are generated and optimized, ensuring that the final output strategy is highly consistent with the athlete's unique physiological characteristics. Attached Figure Description

[0010] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0011] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0013] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0014] like Figure 1 This embodiment provides a method for organizing and planning sports competitions based on big data, including the following steps: S101. Acquire the athlete's physiological data, which includes at least heart rate data and muscle fatigue data. The physiological data is acquired by obtaining the first heart rate data through a wearable sensor and the second muscle fatigue data through an electromyography sensor. Furthermore, raw physiological data of athletes is collected through dedicated sensors deployed on their bodies. This raw physiological data includes heart rate data and muscle fatigue data. Heart rate data is continuously monitored and acquired through photoelectric sensors in wearable devices. This first heart rate data does not refer to the static heart rate value, but rather includes heart rate variability and peak heart rate. Heart rate variability refers to the variation in the difference between successive heartbeat cycles, which is determined by the standard deviation of adjacent RR intervals in the pulse wave signal. The specific calculation formula is as follows: Wherein, SDNN represents heart rate variability. This represents the i-th valid RR interval, i.e., the time interval between adjacent heartbeats. The average value of all valid RR intervals within a specific monitoring period is represented by N, which represents the total number of valid RR intervals within that period. Heart rate variability is used to quantify the regulatory function of the athlete's autonomic nervous system and the degree of fatigue accumulation. Peak heart rate is the highest heart rate value recorded within a specific monitoring period, which is determined by comparing the instantaneous heart rate with a preset historical heart rate baseline in real time, and is used to assess the athlete's current maximum cardiovascular load capacity. Muscle fatigue data is obtained by collecting electrical signals generated during muscle activity using electromyography (EMG) sensors attached to the surface of the athlete's muscle groups. This second set of data includes muscle activation level and recovery rate. Muscle activation level refers to the amplitude intensity of the EMG signal during muscle exertion, which is determined by calculating the root mean square value after filtering and rectifying the raw EMG signal. The specific calculation formula is as follows: in, EMG indicates the degree of muscle activation. This represents the electromyographic signal value after filtering and rectification. This indicates the length of the time window for integral calculation, which is preset according to the type of motion. This indicates that the square of the electromyographic signal is integrated over the time interval [0, T]. The degree of muscle activation directly reflects the mobilization level and exertion state of a specific muscle group in an athlete. The recovery rate refers to how quickly the electromyographic signal characteristics recover to the resting baseline level after high-intensity activity. The recovery rate is calculated by analyzing the recovery trend of the median frequency of the electromyographic spectrum after high-intensity activity. At a preset time point after the end of the activity ( , ,..., Calculate the median frequency of the electromyographic signal, then perform linear regression analysis with time as the independent variable and median frequency as the dependent variable. The recovery rate is the slope k of the regression line. The specific calculation formula is as follows: Where n represents the number of sampling time points, This represents the i-th time point. The median frequency value at the corresponding time point is represented by the slope k, which is the recovery rate. The recovery rate is used to assess the muscle's ability to eliminate fatigue and recover.

[0015] It should be noted that the first heart rate data acquired through wearable sensors and the second muscle fatigue data acquired through electromyography sensors together constitute a multi-dimensional athlete physiological state monitoring system. After acquiring these two types of data, a data synchronization and preprocessing step is performed, which aligns the time-stamped data streams from different sensors on a unified time axis and filters out any noise that may exist during signal acquisition. The cutoff frequency used for this filtering is set based on the preset performance parameters of the sensors, ensuring the consistency of the first heart rate data and the second muscle fatigue data in terms of timing and the cleanliness of the data itself, thus avoiding logical gaps in analysis caused by data quality issues.

[0016] S102. Based on the athlete's physiological data, perform state assessment processing and generate state indicators, including calculating a first state score and a first state score based on the athlete's physiological data, and generating state indicators based on the first state score and the first state score. Furthermore, based on heart rate variability and muscle recovery rate as core input parameters, a first-state score is calculated. A preset weighting coefficient is assigned to heart rate variability and muscle recovery rate, with the weighting coefficient pre-set based on the importance of each parameter's contribution to fatigue risk. The first-state score is output through linear weighting, and the specific calculation formula is as follows: in, Represents the first-state score. This represents the current value of heart rate variability. This represents the current value indicating the muscle recovery rate. and These represent the results after normalizing HRV and RR, respectively. and The first state score is calculated using preset weighting coefficients for normalized parameter allocation. If a score is within a pre-defined standardized range, it indicates that the athlete is experiencing high levels of physiological fatigue and faces a greater risk of sports injuries and performance decline. Based on peak heart rate and muscle activation level as core input parameters, the input parameters are normalized, and another set of preset weighting coefficients are assigned to peak heart rate and muscle activation level. These weighting coefficients are independently set according to the degree of influence of each parameter on explosive power and sustained output capability. A second state score is output through a corresponding weighted calculation model. The specific calculation formula is as follows: in, This represents the current peak heart rate. The current value indicating the level of muscle activation. , They represent respectively to and The result after normalization and These are preset weighting coefficients assigned to the parameters. This set of weights is set independently based on the degree of influence of each parameter on explosive power and sustained output ability. The value of the second state score is standardized within a preset range. A high score indicates that the athlete has high potential to complete high-intensity technical movements at the current moment. After generating the first and second state scores, a final state index is generated based on these two scores. This state index is a structured dataset containing at least the first and second state scores, and a state level label based on a comprehensive assessment of both scores. The state level label is determined by mapping the first and second state scores to a preset state matrix. This state matrix defines the state levels corresponding to different score combinations. and The value is used to determine the region to which it belongs in the state matrix. The judgment logic is as follows: Where L represents the status level label, , It refers to the score of the first state. The preset threshold, , It refers to the second state score. The preset thresholds are used to generate a final state index, which serves as a comprehensive assessment conclusion and accurately quantifies the athlete's fatigue risk and performance potential.

[0017] S103. Based on the state indicators, execute the strategy generation algorithm to determine at least one candidate strategy and generate multiple strategy options based on the state indicators. The strategy options include adjusting the rest time and changing the exercise intensity. Furthermore, based on the output status indicators, matching and instantiation operations are performed by querying a pre-defined strategy rule base. This strategy rule base is a knowledge set that predefines the correspondence between status patterns and strategy types. First, the status level label is parsed and used as the top-level basis for the strategy direction. For example, when L represents high risk and low potential, the rule base indicates that the strategy direction should prioritize risk control and recovery; when L represents low risk and high potential, the strategy direction should prioritize potential mining and output. After determining the strategy direction, the strategy type is specifically parameterized using quantitative parameters in the status indicators, namely the first status score and the second status score. For adjusting rest time, the specific rest duration is calculated based on the value of the first status score using a rest-fatigue relationship function. This function defines a positive correlation between fatigue level and required recovery time. The specific calculation formula is as follows: in, Indicates the specific rest duration. This indicates the preset minimum rest duration. This indicates the preset maximum rest duration. This represents the preset fatigue risk score baseline value. This represents the minimum allowed value of the preset fatigue risk score in the calculation. For changes in exercise intensity, the target intensity value is determined based on the value of the second state score through an intensity-potential relationship function. This function ensures that the recommended intensity matches the current physical potential. The specific calculation formula is as follows: in, Indicates the target motion intensity value. This indicates the preset minimum intensity limit. This indicates the preset maximum intensity limit. This represents the current second-state score. This represents the preset performance potential score benchmark. This indicates the maximum allowed value for the preset performance potential score in the calculation; When performing impact analysis on each strategy option, two key pre-defined boundary conditions are relied upon: a performance threshold and a risk threshold. For each generated strategy option with specific parameters, a predictive model is launched. The input to the predictive model is the current state index and the parameters of the strategy option. After the model runs, it outputs two core predicted values: the first is the predicted performance gain, representing the expected change in the athlete's second state score after implementing the strategy; the second is the predicted risk change, representing the expected change in the athlete's first state score after implementing the strategy. For each strategy option, the predicted performance gain is... Compared with the predicted risk change value The calculation is performed using the following linear model, and the specific calculation formula is as follows: in, This represents the predicted performance gain value, which is the expected change in the second-state score. This represents the predicted risk change value, which is the expected change in the first-state score. This indicates the specific input parameters for the policy option being evaluated. , This represents the preset scaling factor and intercept for performance gain. , This represents the preset proportional coefficient and intercept for risk changes. For example, extending the rest time may be predicted as a significant decrease, while increasing the exercise intensity may be predicted as increasing the predicted performance gain value while also increasing the predicted risk change value. The predicted output (predicted performance gain value, predicted risk change value) of each strategy option is compared with the preset boundary conditions to initially screen out strategy options that meet the basic safety and effectiveness requirements. A two-stage screening and optimization decision-making process is implemented to determine the optimal strategy. The first stage is safety screening, which compares the predicted risk change value of all strategy phenomena with a preset risk threshold and eliminates all strategy options with a predicted risk change value greater than the preset risk threshold, ensuring that no candidate strategy will cause the athlete's fatigue risk to exceed the safe range. The second stage is performance optimization, which sorts the feasible strategy options that passed the first stage screening in descending order according to the predicted performance gain value of each option and selects the strategy option with the highest predicted performance gain value as the final candidate strategy. When multiple strategy options have the same predicted risk change value, a preset priority rule will be used for the final decision. For example, "adjusting rest time" will be given priority to consolidate the safety foundation, or "modifying tactics" will be given priority to maintain the tactical consistency of the competition. The final candidate strategy is encapsulated into a structured data object containing specific action instructions and output to the competition organization and management unit.

[0018] It should be noted that the preset strategy rule base is a structured knowledge database pre-stored in the system. It defines the mapping relationship between different athlete state patterns and corresponding strategy types and parameterization methods. It is the core decision-making basis for automatically generating specific strategy options from state assessments, including the relationship between athlete physiological states and strategy mappings, as well as strategy parameterization rules. The relationship between athlete physiological states and strategy mappings usually exists in the form of rule tables, defining how to determine the core strategy direction based on state level labels. For example: When the status level label is high risk and low potential, the mapped strategy direction is risk control and recovery, prioritizing the instantiation of strategy options such as adjusting rest time and reducing exercise intensity. When the status level label is low risk and high potential, the strategy direction is potential exploitation and output, prioritizing the instantiation of strategy options such as maintaining or increasing exercise intensity and enabling aggressive tactics. When the status level label is a complex state such as high risk and high potential, the mapped strategy direction is precise control and balance, which may simultaneously generate a combination of strategy options involving intensity fine-tuning, tactical compensation, and rest arrangements. The strategy parameterization rules are a set of calculation rules used to generate specific, quantifiable parameters after the strategy direction is determined. They can be represented as follows: storing the parameters required to calculate rest duration, the parameters required to calculate target intensity, and specific rules for calculating target intensity based on the relationship between the current performance score and the baseline and maximum values. The rule base also stores a set of tactical instructions, in which specific state score ranges or level labels will trigger corresponding predefined tactical instructions.

[0019] S104. Based on candidate strategies and combined with preset competition objectives, determine the final personalized strategy. The final personalized strategy is determined by executing simulation applications through candidate strategies to generate simulation performance data. Based on the simulation performance data and combined with preset adjustment rules, determine the final personalized strategy and output it to the athlete's terminal. Furthermore, based on the parameters of the candidate strategy and the athlete's current state indicators, the strategy effect is deduced in a virtual environment. First, a digital simulation environment is initialized, and the initial state of this environment is set to the athlete's current physiological state and the first state score. With second state score The measured values ​​are used to input the specific parameters of the candidate strategy into a preset state evolution model. The state evolution model simulates the trajectory of the athlete's physiological state over time under strategy intervention through a predefined state transition equation. The specific calculation formula is as follows: in, This represents the predicted fatigue score at simulation time t. This represents the initial fatigue score at the start of the simulation. represents the predicted performance score at simulation time t, and represents the initial performance score at the start of the simulation. These values ​​are directly derived from the athlete's current real-time performance indicators. Represents the intensity function. This represents the recovery function. This represents the fatigue accumulation function. , , , This represents the preset physiological response coefficient. The symbol represents an integral, indicating that the expression within the parentheses is summed over the entire simulation period from start to finish. This reflects the dynamic process of fatigue accumulating or alleviating over time, over the simulation cycle. Then, the simulation performance data is output, including the predicted fatigue score and the predicted performance score at the end of the simulation, forming a quantitative prediction of the consequences of strategy execution. The simulated performance data is matched with the preset competition goals. If the goal is to finish the race safely, the predicted fatigue score must always be higher than the preset minimum safety threshold. If the goal is to achieve the best performance, the predicted performance score must reach the preset excellent performance threshold. When the simulation results fully meet the competition goals, the candidate strategy is directly determined as the final strategy. When the simulation results do not meet the requirements, an iterative optimization program is started. The iterative optimization program adjusts the mapping table according to the preset parameters, makes targeted corrections to the strategy parameters, and then re-executes the simulation application until a strategy that meets the conditions is found. The verified personalized strategy is encapsulated into a standardized executable instruction set, which includes the strategy type, specific execution parameters, and expected effects. This executable instruction set is then transmitted to the athlete's terminal.

[0020] It should be noted that after receiving the instruction set, the athlete's terminal presents it in a way that conforms to the usage habits of sports scenarios, including a graphical interface, voice prompts, and haptic feedback. The graphical interface displays the heart rate zone corresponding to the current actual heart rate through a progress bar. The voice prompts provide parameters in the form of voice broadcast at strategy switching nodes, such as when entering the sprint node and the intensity needs to be increased. When the actual intensity deviates from the strength heart rate by ±5%, the terminal vibrates to remind and adjust.

[0021] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0022] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0023] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0024] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0025] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0026] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0027] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for organizing and planning sports competitions based on big data, characterized in that, Includes the following steps: S101. Acquire the athlete's physiological data, which includes at least heart rate data and muscle fatigue data. The physiological data is acquired by obtaining the first heart rate data through a wearable sensor and the second muscle fatigue data through an electromyography sensor. S102. Based on the athlete's physiological data, perform state assessment processing and generate state indicators, including calculating a first state score and a first state score based on the athlete's physiological data, and generating state indicators based on the first state score and the first state score. S103. Based on the state indicators, execute the strategy generation algorithm to determine at least one candidate strategy and generate multiple strategy options based on the state indicators. The strategy options include adjusting the rest time and changing the exercise intensity. S104. Based on candidate strategies and combined with preset competition objectives, determine the final personalized strategy. The final personalized strategy is determined by executing simulation applications through candidate strategies to generate simulation performance data. Based on the simulation performance data and combined with preset adjustment rules, determine the final personalized strategy and output it to the athlete's terminal.

2. The method for organizing and planning sports competitions based on big data according to claim 1, characterized in that, In step S101, raw physiological data of the athlete is collected by a dedicated sensor deployed on the athlete's body. The raw physiological data includes heart rate data and muscle fatigue data. The heart rate data is continuously monitored and acquired by the photoelectric sensor of the wearable device. The heart rate data includes heart rate variability and peak heart rate. Heart rate variability refers to the variation of the difference between successive heartbeat cycles. It is determined by the standard deviation of adjacent RR intervals in the pulse wave signal. Heart rate variability is used to quantify the regulatory function of the athlete's autonomic nervous system and the degree of fatigue accumulation. Peak heart rate is the highest heart rate value recorded during a specific monitoring period. It is determined by comparing the instantaneous heart rate with the preset historical heart rate baseline in real time. It is used to assess the athlete's current maximum cardiovascular load capacity. Muscle fatigue data is obtained by collecting electrical signals generated during muscle activity using electromyography (EMG) sensors attached to the surface of the athlete's muscle groups. This second set of data includes muscle activation level and recovery rate. Muscle activation level refers to the amplitude and intensity of the EMG signal during muscle exertion. The RMS value is calculated after filtering and rectifying the raw EMG signal to determine the activation level, which directly reflects the mobilization level and exertion state of a specific muscle group in the athlete. Recovery rate refers to how quickly the EMG signal characteristics recover to the resting baseline level after high-intensity activity. The recovery rate is calculated by analyzing the recovery trend of the median frequency of the EMG spectrum after high-intensity activity, at a preset time point after the activity ends. , ,..., Calculate the median frequency of the electromyographic signal, with time as the independent variable and median frequency as the dependent variable, and perform linear regression analysis. The recovery rate is the slope k of the regression line. The specific calculation formula is as follows: Where n represents the number of sampling time points, This represents the i-th time point. The median frequency value at the corresponding time point is represented by the slope k, which is the recovery rate. The recovery rate is used to assess the muscle's ability to eliminate fatigue and recover.

3. The method for organizing and planning sports competitions based on big data according to claim 1, characterized in that, In step S102, heart rate variability and muscle recovery rate are used as core input parameters to calculate the first state score. A preset weighting coefficient is assigned to heart rate variability and muscle recovery rate. The weighting coefficient is preset based on the importance of each parameter's contribution to fatigue risk. The first state score is output through linear weighting. The specific calculation formula is as follows: in, Represents the first-state score. This represents the current value of heart rate variability. This represents the current value indicating the muscle recovery rate. and These represent the results after normalizing HRV and RR, respectively. and The first state score is calculated using preset weighting coefficients for normalized parameter allocation. If a score is within a pre-defined standardized range, a low score indicates that the athlete is experiencing high levels of physiological fatigue and faces a greater risk of sports injuries and performance decline.

4. The method for organizing and planning sports competitions based on big data according to claim 1, characterized in that, Based on peak heart rate and muscle activation level as core input parameters, and after normalization of the input parameters, another set of preset weighting coefficients are assigned to peak heart rate and muscle activation level. The second state score is then output through a corresponding weighted calculation model. The specific calculation formula is as follows: in, This represents the current peak heart rate. The current value indicating the level of muscle activation. , They represent respectively to and The result after normalization and These are preset weighting coefficients assigned to the parameters. The value of the second state score is standardized within a preset range. A high score indicates that the athlete has high potential to complete high-intensity technical movements at the current moment.

5. The method for organizing and planning sports competitions based on big data according to claim 4, characterized in that, After generating the first and second state scores, a final state index is generated based on these two scores. This state index is a structured dataset containing at least the first and second state scores, and a state level label based on a comprehensive assessment of both scores. The state level label is determined by mapping the first and second state scores to a preset state matrix. This state matrix defines the state levels corresponding to different score combinations. and The value is used to determine the region to which it belongs in the state matrix. The judgment logic is as follows: Where L represents the status level label, , It refers to the score of the first state. The preset threshold, , It refers to the second state score. The preset thresholds, and the resulting state indicators, quantify the athlete's fatigue risk and performance potential.

6. The method for organizing and planning sports competitions based on big data according to claim 1, characterized in that, In step S103, based on the output status indicators, matching and instantiation operations are performed by querying a preset strategy regulation library. First, the status level label is parsed and used as the top-level basis for the strategy direction. After determining the strategy direction, the strategy type is specifically parameterized using the quantitative parameters in the status indicators, namely the first status score and the second status score. For adjusting rest time, the specific rest duration is calculated based on the value of the first status score using a rest-fatigue relationship function. This function defines a positive correlation between fatigue level and required recovery time. The specific calculation formula is as follows: in, Indicates the specific rest duration. This indicates the preset minimum rest duration. This indicates the preset maximum rest duration. This represents the preset fatigue risk score baseline value. This represents the minimum allowed value of the preset fatigue risk score in the calculation. For changes in exercise intensity, the target intensity value is determined based on the value of the second state score through an intensity-potential relationship function. This function ensures that the recommended intensity matches the current physical potential. The specific calculation formula is as follows: in, Indicates the target motion intensity value. This indicates the preset minimum intensity limit. This indicates the preset maximum intensity limit. This represents the current second-state score. This represents the preset performance potential score benchmark. This represents the maximum allowed value for the preset performance potential score in the calculation.

7. The method for organizing and planning sports competitions based on big data according to claim 6, characterized in that, When performing impact analysis on each strategy option, two key pre-defined boundary conditions are relied upon: a performance threshold and a risk threshold. For each generated strategy option with specific parameters, a predictive model is launched. The input to the predictive model is the current state index and the parameters of the strategy option. After the model runs, it outputs two core predicted values: the first is the predicted performance gain, representing the expected change in the athlete's second state score after implementing the strategy; the second is the predicted risk change, representing the expected change in the athlete's first state score after implementing the strategy. For each strategy option, the predicted performance gain is... Compared with the predicted risk change value The calculation is performed using the following linear model, and the specific calculation formula is as follows: in, This represents the predicted performance gain value, which is the expected change in the second-state score. This represents the predicted change in risk, which is the expected change in the first-state score. This indicates the specific input parameters for the policy option being evaluated. , This represents the preset scaling factor and intercept for performance gain. , This represents the preset proportional coefficient and intercept for risk changes. The predicted output of each strategy option is compared with the preset boundary conditions to initially screen out strategy options that meet the basic safety and effectiveness requirements.

8. The method for organizing and planning sports competitions based on big data according to claim 7, characterized in that, A two-stage screening and optimization decision-making process is implemented to determine the final optimal strategy. The first stage is safety screening, which compares the predicted risk change value of all strategy phenomena with a preset risk threshold and excludes all strategy options whose predicted risk change value is greater than the preset risk threshold. The second stage is performance optimization, which sorts the feasible strategy options that passed the first stage screening in descending order according to the predicted performance gain value of each option and selects the strategy option with the highest predicted performance gain value as the final candidate strategy. When multiple strategy options have the same predicted risk change value, a preset priority rule will be used for final decision. The final candidate strategy is encapsulated into a structured data object containing specific action instructions and output to the competition organization and management unit.

9. The method for organizing and planning sports competitions based on big data according to claim 1, characterized in that, In step S104, based on the parameters of the candidate strategy and the athlete's current state indicators, the strategy effect is deduced in a virtual environment. First, a digital simulation environment is initialized, and the initial state of this environment is set to the athlete's current physiological state, i.e., the first state score. With second state score The measured values ​​are used to input the specific parameters of the candidate strategy into a preset state evolution model. The state evolution model simulates the trajectory of the athlete's physiological state over time under strategy intervention through a predefined state transition equation. The specific calculation formula is as follows: in, This represents the predicted fatigue score at simulation time t. This represents the initial fatigue score at the start of the simulation. represents the predicted performance score at simulation time t, and represents the initial performance score at the start of the simulation. These values ​​are directly derived from the athlete's current real-time performance indicators. Represents the intensity function. This represents the recovery function. This represents the fatigue accumulation function. , , , This represents the preset physiological response coefficient. Representing the integral sign, after an analog cycle Then, the simulation performance data is output, including the predicted fatigue score and the predicted performance score at the end of the simulation, forming a quantitative prediction of the consequences of strategy execution.

10. A method for organizing and planning sports competitions based on big data according to claim 9, characterized in that, The simulated performance data is matched with the preset competition goals. If the goal is to finish the race safely, the predicted fatigue score must always be higher than the preset minimum safety threshold. If the goal is to achieve the best performance, the predicted performance score must reach the preset excellent performance threshold. When the simulation results fully meet the competition goals, the candidate strategy is directly determined as the final strategy. When the simulation results do not meet the requirements, an iterative optimization program is started. The iterative optimization program adjusts the mapping table according to the preset parameters, makes targeted corrections to the strategy parameters, and then re-executes the simulation application until a strategy that meets the conditions is found. The verified personalized strategy is encapsulated into a standardized executable instruction set, which includes the strategy type, specific execution parameters, and expected effects. This executable instruction set is then transmitted to the athlete's terminal.

Images