A method and system for assessing post-training physical recovery status

Abstract

This invention relates to the field of sports assessment, specifically disclosing a method and system for assessing post-training physical recovery. It includes: collecting a user's physiological indicators; determining the user's current physical state parameters based on the physiological indicators; obtaining the training load parameters corresponding to the user's current training cycle; calculating the physical fitness value for the current training cycle using a preset fitness correction model; calculating the free energy for the current training cycle using a preset free energy calculation model based on the fitness value, physical state parameters, and training load parameters; and assessing the user's recovery status based on the free energy, a preset fitness baseline, and the physical state parameters, outputting the corresponding recovery status assessment result. This invention introduces the thermodynamic free energy model into the field of athlete recovery assessment, combining it with the principle of supercompensation in exercise physiology to construct a model based on the laws of human energy metabolism, resulting in assessment results that more closely reflect the actual fatigue and recovery patterns of the human body.

Description

Technical Field

[0001] This invention belongs to the field of physical condition assessment technology, and in particular relates to a method and system for assessing physical recovery status after training. Background Technology

[0002] With the continuous improvement of the scientific training system in competitive sports, precise monitoring of training load and quantitative assessment of athletes' physical recovery status have become core elements in improving athletes' competitive performance, preventing sports injuries, and extending their careers. Reasonable training load stimulation and sufficient physical recovery are the physiological basis for athletes to achieve supercompensation and improve athletic ability; however, inaccurate load monitoring and biased recovery status assessment can easily lead to serious problems such as overtraining syndrome, stress fractures, and endocrine disorders. These not only fail to improve athletic performance but also cause irreversible damage to the athlete's health.

[0003] Currently, mainstream athlete training status and fatigue assessment technologies fall into two main categories: statistical assessment systems based on quantified training load and single-point fatigue detection technologies based on physiological indicators. The training load-quantified assessment system is represented by metrics such as Training Stress Score (TSS), Chronic Training Load (CTL), and Acute Training Load (ATL). Its core logic involves quantifying training load input through data such as exercise duration and intensity, calculating training stress by comparing the difference between long-term and acute loads, and then assessing the athlete's fatigue state. This type of method is currently the most widely used basic assessment tool in competitive sports. Fatigue detection technologies based on physiological indicators primarily utilize physiological parameters such as Heart Rate Variability (HRV), morning pulse, resting heart rate, and salivary cortisol. These parameters are highly sensitive to physical fatigue levels, enabling auxiliary judgment of the athlete's fatigue level. HRV, due to its non-invasive, continuous data collection and accurate reflection of the autonomic nervous system state, has become the most widely used indicator in this type of technology.

[0004] However, due to the complexity of human bodily functions, existing fatigue assessment technologies still have certain shortcomings in terms of accuracy and reliability. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for assessing post-training physical recovery status, which partially solves or alleviates the above-mentioned deficiencies in the prior art. It can integrate multi-dimensional data on training load, physiological state, and recovery quality, and construct an assessment of the athlete's recovery status based on an underlying physical model.

[0006] To solve the aforementioned technical problems, the present invention specifically adopts the following technical solution: A first aspect of the present invention is to provide a method for assessing post-training physical recovery, comprising: Collect the user's physiological indicators and determine the user's current physical state parameters based on the physiological indicators; Obtain the training load parameters corresponding to the user's current training cycle; A preset fitness correction model is used to calculate the fitness value for the current training cycle; the fitness correction model is based on the user's free energy in the previous training cycle and corrects the fitness value for the current training cycle. Using a preset free energy calculation model, the free energy of the current training cycle is calculated based on the physical fitness value, body state parameters, and training load parameters. Based on the free energy, the preset physical fitness baseline, and the physical condition parameters, the user's recovery status is comprehensively evaluated, and the corresponding recovery status evaluation result is output.

[0007] Further, the body status parameter is calculated based on the HRV value, HRV baseline value, and HRV standard deviation in the physiological indicators; when HRV > HRV baseline value - HRV standard deviation, the body status parameter T = 1; when HRV ≤ HRV baseline value - HRV standard deviation, the body status parameter T = (HRV baseline value - HRV) / HRV standard deviation.

[0008] Furthermore, the physical fitness correction model is as follows: ; Among them, E i This represents the fitness level for the current training cycle. τ is the user's free energy at the end of the previous training cycle, τ is the recovery time parameter, and qs is the user's sleep recovery quality parameter.

[0009] Furthermore, the recovery time parameter τ is dynamically adjusted based on the user's free energy state, and the adjustment rules include: Calculate the reference free energy and the expected free energy F i The difference is such that when the difference is greater than a preset difference threshold, the recovery time parameter τ is increased; when the difference is less than or equal to the preset difference threshold, the recovery time parameter τ is decreased or maintained.

[0010] Furthermore, the reference free energy = reference free energy value - standard deviation of free energy; If the user has historical motion data that meets the preset requirements, the free energy baseline value and free energy standard deviation are calculated based on the historical motion data; if the user does not have historical motion data that meets the preset requirements, the default value is used.

[0011] Furthermore, it also includes a supplementary correction step for the recovery time parameter τ based on the physical fitness baseline: The system continuously monitors the user's physical fitness baseline trend. If, after N consecutive training cycles, the user's physical fitness baseline shows a downward trend and the decline exceeds a preset decline threshold, the recovery time parameter τ is increased, where N is a positive integer greater than or equal to 2.

[0012] Furthermore, the free energy calculation model is as follows: ; Among them, F i Let be the free energy of the current training cycle, k be the free energy dissipation coefficient, T be the user's current physical state parameters, S be the user's training load parameters for the current training cycle, and E be the free energy. i This represents the physical fitness value for the current training cycle.

[0013] Furthermore, it also includes a life load correction step: Collect users' lifestyle load data and adjust the physical condition parameters and / or training load parameters based on the lifestyle load; the lifestyle load data is obtained based on the users' heart rate variability (HRV) data.

[0014] Furthermore, the method for obtaining the living load data includes: Long-term heart rate variability (HRV) data of users are collected and filtered using conventional filtering algorithms to remove isolated outliers in the data; Life load is assessed based on HRV data; sudden drops in HRV data are marked as stress points, and the number of stress points is positively correlated with life load.

[0015] Furthermore, the method for evaluating a user's recovery status is as follows: If the free energy of the current training cycle is lower than the preset acute fatigue threshold, the user's body is determined to be in an acute fatigue state after overload. Within the preset response period after being identified as an acute fatigue state, if the user's physical fitness baseline decline does not exceed the preset safety threshold ratio and the physical condition parameters are less than the safety parameters, then the overtraining caused by this overload is determined to be functional overtraining, and the user can withstand the current overload. If, within the preset response period after being identified as an acute fatigue state, the user's physical fitness baseline declines by more than the preset safety threshold ratio, or the physical condition parameters are greater than the safety parameters, then the overtraining caused by this overload is determined to be non-functional overtraining, corresponding to the user being unable to withstand the current overload and having a risk of sports injury. If, within a preset training period after being identified as having functional overtraining, a user's fitness score is greater than the sum of the fitness baseline and the corresponding standard deviation, then the user's body is considered to have completed supercompensation.

[0016] The present invention also provides a system for assessing post-training physical recovery, comprising: The body status parameter acquisition module is used to collect the user's physiological indicators and determine the user's current body status parameters based on the physiological indicators. The training load parameter acquisition module is used to acquire the training load parameters corresponding to the user's current training cycle. The physical fitness value acquisition module uses a preset physical fitness correction model to calculate the physical fitness value of the current training cycle; the physical fitness correction model is based on the user's free energy in the previous training cycle to correct the physical fitness value of the current training cycle. The free energy acquisition module is used to calculate the free energy of the current training cycle based on the physical fitness value, body state parameters, and training load parameters using a preset free energy calculation model. The assessment module comprehensively evaluates the user's recovery status based on the free energy, the preset physical fitness baseline, and the physical state parameters, and outputs the corresponding recovery status assessment results.

[0017] Beneficial technical effects: Unlike traditional linear and static training status and fatigue assessments, this invention introduces the dynamic response of the human body to training load when assessing athletes' exercise, so as to provide more reliable status guidance for athletes by comprehensively considering their current physical condition and recovery trend.

[0018] Specifically, this invention incorporates the athlete's dynamic physical response (or recovery trend) into the condition assessment scheme through a two-dimensional assessment, based on both the time dimension and the energy assessment level. 1) The time dimension needs to consider the energy information of the past and the current training cycle: that is, it is necessary to consider the physical condition at the current moment (i.e., correct the physical condition value), and at the same time, the free energy condition of the previous cycle, such as the previous day.

[0019] 2) The energy dimension needs to take into account the athlete's basic physical fitness (i.e., the corrected physical fitness value) as well as the athlete's recovery trend (i.e., the remaining free energy in the previous cycle). 3) Simultaneously, the impact of training load on energy levels is adjusted based on physical condition; Therefore, by combining the time and energy dimensions, and by incorporating physical condition to modify the energy dimension, it is possible to incorporate the athlete's dynamic recovery into the assessment of athletic performance using a limited set of core factors.

[0020] From another perspective, this invention is the first to introduce the thermodynamic free energy model into the field of athlete recovery assessment. Combined with the supercompensation principle of exercise physiology, it constructs a fundamental physical model based on the laws of human energy metabolism. All assessment logic revolves around the physiological mechanisms of human energy intake, consumption, surplus, and recovery, rather than pure data fitting. This solves the underlying logical defects of traditional methods, and the assessment results are more in line with the real fatigue and recovery laws of the human body, possessing strong scientific validity and universality.

[0021] This invention constructs a daily iterative nonlinear dynamic evaluation system. Using the free energy at the end of the previous training cycle as the core correction factor, it dynamically corrects the physical fitness value of the current training cycle. It incorporates the dynamic physiological effects of previous training fatigue accumulation, sleep recovery quality, and changes in physical condition into the current physical fitness and recovery status evaluation, upgrading from single-point static evaluation to full-cycle dynamic tracking, and accurately adapting to the nonlinear physiological laws of human fatigue, recovery, and adaptation.

[0022] This invention also constructs a quantitative assessment framework, which transforms HRV into standardized physical state parameters, standardizes the training stress score (TSS) into training load parameters, incorporates sleep quality into the core model of physical fitness correction, and transforms life stress into a life load correction factor. Data from all dimensions are organically integrated into the core free energy calculation model, realizing the linkage assessment of four dimensions: training, physiology, recovery, and life, and solving the core pain points of traditional assessment systems such as data fragmentation and one-sided dimensions. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. The elements or parts in the drawings are not necessarily drawn to scale. Obviously, the drawings described below are some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0024] Figure 1 A flowchart illustrating an exemplary embodiment of the present invention; Figure 2 This is a structural diagram of an exemplary embodiment of the present invention; Figure 3 This is a result analysis diagram of an application example of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0026] In this document, suffixes such as "module," "part," or "unit" used to denote elements are used only for the purpose of illustrative purposes and have no specific meaning in themselves. Therefore, "module," "part," or "unit" may be used interchangeably.

[0027] In this document, the terms "upper," "lower," "inner," "outer," "front," "rear," "one end," and "the other end," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the present invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0028] In this document, unless otherwise explicitly specified and limited, the terms "installed," "equipped with," "connected," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0029] In this document, "and / or" includes any and all combinations of one or more of the listed related items.

[0030] In this article, "multiple" means two or more, that is, it includes two, three, four, five, etc.

[0031] As used in this specification, the term "about" typically means + / -5% of the value, more typically + / -4% of the value, more typically + / -3% of the value, more typically + / -2% of the value, even more typically + / -1% of the value, and even more typically + / -0.5% of the value.

[0032] In this specification, certain embodiments may be disclosed in a range-bound format. It should be understood that this "range-bound" description is merely for convenience and brevity and should not be construed as a rigid limitation on the disclosed range. Therefore, the description of a range should be considered as having specifically disclosed all possible subranges and the individual numerical values ​​within those ranges. For example, a description of the range 1-6 should be considered as having specifically disclosed subranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., and the individual numbers within those ranges, such as 1, 2, 3, 4, 5, and 6. This rule applies regardless of the breadth of the range.

[0033] Example 1: This invention provides a method for assessing physical condition, comprising the following steps: 1) Collect the user's physiological indicators and determine the user's current physical state parameters based on the physiological indicators; 2) Obtain the training load parameters corresponding to the user's current training cycle; For example, the longer the training cycle, or the higher the exercise intensity within the training cycle, the greater the training load parameter.

[0034] 3) Using a preset fitness correction model, the corrected fitness value for the current training cycle is calculated; the fitness correction model is based on the user's free energy in the previous training cycle and corrects the initial fitness value for the current training cycle to obtain the corrected fitness value. The free energy is used to define the amount of energy remaining in the body after a training cycle ends, and the physical fitness value is used to define the user's ability to bear the training load in the current training cycle. The correction mode of the physical fitness correction model is that the greater the free energy in the current training cycle, the greater the difference between the initial physical fitness value and the corrected physical fitness value.

[0035] For example, free energy can be used to adjust a user's (i.e., athlete's) initial fitness level. Initial fitness level typically has an initial value (e.g., set to 1). If a significant amount of fitness was consumed in the previous training cycle (leaving less free energy), the initial value needs to be appropriately reduced, taking into account the athlete's recovery.

[0036] The larger the difference between the initial physical fitness value and the modified physical fitness value (i.e., initial physical fitness value - modified physical fitness value), the greater the reduction in the initial physical fitness value.

[0037] Understandably, the specific reduction amount can be adjusted individually based on different user groups.

[0038] 4) Using a preset free energy calculation model, based on the corrected physical fitness value, body state parameters, and training load parameters, the expected free energy for the current training cycle is calculated. The free energy calculation model includes: expected free energy = corrected physical fitness value - expected energy expenditure, and the expected energy expenditure is defined by training load parameters and body state parameters, wherein the body state parameters are used to represent the magnitude of physical fitness expenditure under different body states for the same training load parameters. 5) Assess the user's recovery status based on the expected free energy and output the corresponding recovery status assessment results.

[0039] In this embodiment, expected energy consumption is used to define the amount of energy that an athlete may consume after undergoing a set exercise cycle.

[0040] For example, the expected energy consumption can be defined by the training load parameter. That is, the larger the training load parameter, the greater the expected energy consumption.

[0041] For example, expected energy expenditure can be defined by both training load parameters and physical condition parameters. For instance, expected energy expenditure could be a*T*S, where T is the training load parameter, S is the physical condition parameter, and a is a weighting coefficient (e.g., in the embodiments below, a can be represented by the free energy dissipation coefficient). Specifically, in this embodiment, a larger physical condition parameter is generally defined as a poorer physical condition, meaning that athletes tend to experience more noticeable fatigue when subjected to the same training load.

[0042] In other words, in this embodiment, the magnitude of the body state parameter is negatively correlated with the user's physical condition; correspondingly, in the free energy calculation model, for the same training load parameter, the larger the body state parameter, the greater the expected energy consumption.

[0043] For example, in some embodiments, assessing the user's recovery status based on the expected free energy includes: If the expected free energy is lower than the preset free energy threshold (e.g., the preset acute fatigue threshold), it indicates that the user may be in an acute fatigue state after overloading.

[0044] like Figure 1 As shown, a specific exemplary embodiment of the method for assessing post-training physical recovery status provided in this embodiment will be introduced, and its specific steps include: S1 collects the user's physiological indicators and determines the user's current physical state parameters based on the physiological indicators.

[0045] In this embodiment, the magnitude of the physical condition parameter is negatively correlated with the user's physical condition. For example, the physical condition parameter can be an indicator to measure the degree of poor physiological function or health risk level of the user; the larger the physical condition parameter, the worse the user's physical function.

[0046] It is understood that the body status parameters in this embodiment can be assessed using preset rules based on HRV value, blood oxygen saturation, body temperature, skin conductance, blood pressure, or respiratory rate. In practical applications, those skilled in the art can assess the approximate state of a user's current physical function based on basic physiological knowledge and the above parameters. Therefore, this invention does not limit the specific assessment method.

[0047] For example, the physiological indicator used in this step is heart rate variability (HRV), specifically the root mean square (RMSSD) of the difference between adjacent normal heartbeats in the HRV time domain characteristics is selected as the calculation parameter.

[0048] RMSSD is highly sensitive to changes in the activity of the human parasympathetic nervous system and can accurately reflect the body's autonomic nervous system regulation ability, fatigue accumulation and recovery status. It is a non-invasive physiological indicator recognized in the field of exercise physiology as having the highest correlation with the body's recovery level after exercise. At the same time, this indicator can be stably collected by wearable devices, and highly reliable results can be obtained with short-term collection, making it suitable for high-frequency monitoring scenarios in athletes' daily training.

[0049] By quantifying the user's basic fatigue state through changes in HRV, physiological indicators that were only used as auxiliary references in traditional technologies are transformed into standardized parameters that can be directly substituted into the core physical model, thereby integrating physiological state with training load assessment.

[0050] In this embodiment, HRV data used to calculate body state parameters can be collected from the user in a resting state after waking up each morning. The user is required to have not engaged in any physical activity, consumed no stimulants such as caffeine or nicotine, or engaged in activities with intense emotional fluctuations before the data collection. The user should maintain a quiet sitting or supine resting posture and the data collection time should be 2 to 5 minutes to ensure that the collected data is the autonomic nervous system data in a basic resting state and to avoid interference from daytime activities, training, and emotional stress.

[0051] The data acquisition equipment supports medical-grade ECG monitoring devices, professional sports heart rate belts, and smart wearable devices with high-precision heart rate monitoring capabilities, such as smartwatches and fitness trackers.

[0052] In this step, the body status parameter can be calculated based on the HRV value, HRV baseline value, and HRV standard deviation in the physiological indicators; when HRV > HRV baseline value - HRV standard deviation, the body status parameter T = the set value (e.g., 1); when HRV < HRV baseline value - HRV standard deviation, the body status parameter T = (HRV baseline value - HRV) / HRV standard deviation.

[0053] The calculation of body status parameters uses HRV baseline value and HRV standard deviation as reference standards. In this invention, for users with sufficient historical data, the effective morning resting HRV data of the past 7 consecutive days are used to calculate the HRV baseline value, which is the arithmetic mean of the 7-day data, and the HRV standard deviation, which is the overall standard deviation of the 7-day data.

[0054] For first-time users with less than 7 days of valid historical HRV data, a general default value for the corresponding group is adopted. The general default value is divided according to the user's age, gender, and athletic ability level. The athletic ability level can be divided into three categories: elite athletes, advanced serious athletes, and ordinary athletes. This ensures that the default value matches the user's basic physical condition and guarantees the normal operation of the algorithm when the baseline has not been established.

[0055] Body state parameters reflect the user's current level of physical fatigue and autonomic nervous system regulation ability. The larger the T value, the more severe the user's accumulated physical fatigue, the higher the degree of free energy dissipation under the same training load, and the worse the tolerance to training stimuli.

[0056] This invention uses a phased linear quantization rule to calculate the body state parameter T, which perfectly matches the physiological response law of the human autonomic nervous system. The specific calculation method is as follows: When the effective HRV value collected by the user on the same day is greater than the HRV baseline value minus the HRV standard deviation, the user is considered to be in good autonomic nervous system condition, with no obvious unrecovered cumulative fatigue, and parasympathetic nerve activity at or above normal levels, capable of coping with training load stimuli. At this time, the body state parameter is assigned the baseline value: T=1. Under this assignment rule, the user's basic body state has no additional fatigue amplification effect, and the subsequent calculation of free energy is determined only by physical fitness value, training load, and free energy dissipation coefficient, ensuring the stability of the assessment results under normal conditions.

[0057] When a user's effective HRV value collected on a given day is ≤ HRV baseline value - HRV standard deviation, it is determined that the user's current autonomic nervous activity has significantly decreased, indicating obvious cumulative fatigue, insufficient parasympathetic nervous system recovery capacity, and decreased tolerance to training load. In this case, the body state parameter T is quantitatively calculated using a linear formula: T = (HRV baseline value - HRV) / HRV standard deviation. Under this calculation rule, the body state parameter T must be greater than 1, and the lower the user's daily HRV value, the larger the T value, representing a more severe degree of fatigue. An increase in the T value directly amplifies the free energy dissipation caused by the same training load, accurately reflecting the physiological pattern of decreased training tolerance under fatigue accumulation, thus achieving a linkage between physiological state and energy metabolism model.

[0058] In addition, this embodiment also includes a life load correction step, which involves collecting the user's life load data and correcting the physical state parameters based on the life load.

[0059] Specifically, the linear amplification correction formula T′=T×(1+k) can be used. stress ×L stress The body state parameter T is corrected to obtain the corrected body state parameter T′ for subsequent calculations. Where k stress L is the living load correction factor. stress A comprehensive score for living load.

[0060] In this embodiment, the lifestyle load correction factor is used to assess the impact of lifestyle load on physical condition. The specific value of this factor can be a standardized parameter set by the engineer.

[0061] Alternatively, in some embodiments, the lifestyle load correction coefficient can be set differently for different groups of people. For example, for office workers who do not have a habit of exercising, their k... stress This can often be set higher, implying that this group is relatively more susceptible to life stress. Conversely, if the user is a professional athlete, then their k... stress It can often be set too low. Alternatively, in some embodiments, it is possible to monitor the user's response to the workload over a period of time and adjust the coefficient adaptively based on the user's tolerance for the workload.

[0062] For example, the lifestyle load data is obtained based on the user's heart rate variability (HRV) data. Specifically, the method for obtaining the lifestyle load data includes: S11 collects long-term heart rate variability (HRV) data from users and uses a filtering algorithm to filter out isolated outliers in the data.

[0063] In this embodiment, long-term heart rate variability (HRV) data refers to HRV data collected for a duration exceeding a set period.

[0064] Specifically, time-domain filtering is used to remove motion artifacts. When a user is engaged in moderate to high-intensity activities such as walking, running, or climbing stairs, if the motion acceleration data synchronously collected by the device's accelerometer exceeds a preset threshold, the HRV data for that period is marked as motion interference data and initially removed. Frequency-domain filtering is used to remove baseline drift and high-frequency noise. A Butterworth bandpass filter is used to remove baseline drift caused by breathing and micro-movements, as well as high-frequency noise caused by electromyography interference and device electromagnetic interference.

[0065] If the HRV-RMSSD value at a certain moment decreases by more than 30% compared to the average RMSSD value of the previous 15 minutes, and there are no other consecutive HRV decrease points within 15 minutes before and after this decrease point, it is marked as an isolated outlier. For the HRV data marked as isolated outliers, linear interpolation of the valid HRV data within 15 minutes before and after is used to replace it to ensure the continuity of long-term data.

[0066] S12 assesses life load based on HRV data; where sudden drops in HRV data (such as points where the drop exceeds the expected range) are marked as stress points, and the number of stress points is positively correlated with life load.

[0067] A sustained, sudden drop in HRV data is marked as a stress point. A stress point represents a user experiencing a sustained life stressor event, specifically: If the average HRV-RMSSD over a continuous period, such as 30 minutes, decreases by more than 20% compared to the average RMSSD of the preceding hour, and there is no labeled training interference data within that period, then that period is marked as a stress period, and the starting point of the stress period is marked as the stress point. Users experience high-intensity meetings at work, mentally taxing social activities, long-term sleep disturbances, and continuous family and work stress. These are all continuous non-training life stresses that significantly affect a user's physical recovery and training tolerance.

[0068] The total number of pressure points identified in the valid long-term HRV data for the day is denoted as N. stress The total cumulative duration of all stress periods on that day is recorded as T. stress The unit is hour; the daily living load comprehensive score is calculated using a linear weighted formula: L stress =w1×N stress +w2×T stress ; Where w1 is the weight of the number of pressure points, and w2 is the weight of the cumulative duration of the pressure period.

[0069] Preferably, the w 1、 w2 can use preset empirical values. Alternatively, it can be adjusted by product engineers based on the differences in the stress tolerance or stress response of different groups of people to different stress scenarios.

[0070] S2 obtains the training load parameters corresponding to the user's current training cycle.

[0071] In this embodiment, the training cycle is 1 day. In this step, the training load is quantified based on the Training Stress Score (TSS). TSS is currently recognized in the field of competitive sports as a comprehensive training load index that can simultaneously quantify exercise intensity and exercise duration. The higher the TSS value, the greater the total stimulation to the user's body from the training that day, and the higher the energy consumption and fatigue accumulation.

[0072] TSS supports multi-channel and multi-device data collection, including automatic collection from wearable devices, synchronization with third-party sports platforms, and manual input and estimation. TSS calculation uses the user's lactate threshold heart rate (LTHR) or maximum heart rate (MHR) as the baseline intensity reference. For endurance sports with power meters, such as road cycling and track cycling, TSS is primarily calculated based on power data. The ratio of power output during training to the user's functional threshold power is used to quantify training intensity, and the total TSS is calculated by combining this with exercise duration. For sports without power meters, such as running, swimming, and trail running, TSS is calculated based on heart rate data. Heart rate zones are divided by the ratio of heart rate to LTHR / MHR during training, the cumulative duration of each heart rate zone is calculated, and the total TSS is calculated by combining the intensity weight of the corresponding zone. There is no fixed upper limit to the TSS value. Typically, the TSS value for a low-intensity recovery training session is below 30, the TSS value for a moderate-intensity training session is between 50 and 100, and the TSS value for a high-intensity extreme training session can exceed 150.

[0073] Because the TSS values ​​of users with different fitness levels vary greatly, they cannot be directly substituted into the free energy calculation model (the model requires the training load parameter to be within the normalized range of 0 to 1). Therefore, the TSS must be standardized to obtain the standardized training load parameter S.

[0074] The present invention uses the Sigmoid function as the core algorithm for normalization. The Sigmoid function can map any real number to the open interval of (0, 1). The normalized training load S satisfies 0 < S < 1. The closer the S value is to 1, the closer the training load of the day is to the user's tolerance limit, and the greater the consumption of free energy.

[0075] In this embodiment, the training load S can also be corrected based on the life load, and the correction method can be the same as that of the body state parameters, which will not be elaborated here.

[0076] S3: Use a preset physical fitness correction model to calculate the physical fitness value of the current training cycle; the physical fitness correction model corrects the physical fitness value of the current training cycle based on the free energy of the user's previous training cycle.

[0077] Specifically, the physical fitness correction model in this step is: ; where E i is the physical fitness value of the current training cycle (or the corrected physical fitness value), is the free energy after the end of the user's previous training cycle, τ is the recovery time parameter, and qs is the user's sleep recovery quality parameter.

[0078] The free energy is the remaining and actually available energy of the body at the current moment after the end of the training cycle, which is an instant remaining energy index under a short time scale and directly reflects the instant recovery level after the previous training; while the physical fitness is the maximum energy that the user can use to withstand the exercise load during the current training cycle, which is a movement ability upper limit index under a long time scale and corresponds to the maximum movement potential that the user can call.

[0079] The physical fitness is not a fixed static value, but dynamically recovers based on the free energy after the end of the previous cycle. The higher the free energy of the previous cycle, the more remaining energy after the previous training, and the greater the physical fitness recovery potential of the current cycle; at the same time, combined with the sleep recovery quality and the recovery time parameter, the dynamic recovery process of the physical fitness is quantified to achieve the mapping from the previous remaining energy to the current maximum movement potential.

[0080] The sleep recovery quality qs is calculated based on the user's overnight sleep data the previous night, specifically including the RMSSD mean of the whole-night HRV during sleep, the RMSSD value of the morning resting HRV, the total sleep duration, the proportion of deep sleep duration, the night resting heart rate, and the night blood oxygen saturation. The formula is qs = (6 - x) / 6, where x is the number of abnormal sleep indicators on the current day. For example, when all 6 indicators are normal, x = 0, qs = 1, representing the best sleep recovery quality; when all 6 indicators are abnormal, x = 6, qs = 0, representing extremely poor sleep recovery quality.

[0081] The recovery time parameter τ is dynamically adjusted based on the user's free energy state, and the adjustment rules include: Calculate the reference free energy and the expected free energy F i The difference is such that when the difference is greater than a preset difference threshold, the recovery time parameter τ is increased; when the difference is less than or equal to the preset difference threshold, the recovery time parameter τ is decreased or maintained.

[0082] Among them, expected free energy refers to the free energy that an athlete will have after a set training cycle (such as the current training cycle) based on the free energy calculation model.

[0083] The default value for the recovery time parameter τ is 1, based on the free energy at the end of the previous training cycle. To regulate τ: if The free energy baseline value minus the free energy standard deviation represents sufficient free energy at the end of the previous cycle, with no significant fatigue accumulation. Therefore, τ is maintained at its default value or appropriately reduced. A value ≤ the baseline free energy minus the standard deviation of free energy indicates insufficient free energy at the end of the previous cycle, indicating significant fatigue accumulation. τ is doubled to allow users more time to recover, reduce the rate of physical recovery in the current cycle, and avoid overtraining.

[0084] More specifically, the reference free energy = free energy baseline value - free energy standard deviation; if the user has historical motion data that meets the preset requirements, the free energy baseline value and free energy standard deviation are calculated based on the historical motion data; if the user does not have historical motion data that meets the preset requirements, the default value is used.

[0085] S4 uses a preset free energy calculation model to calculate the free energy of the current training cycle based on the physical fitness value, body state parameters, and training load parameters.

[0086] Specifically, the free energy calculation model described in this embodiment is as follows: ; Among them, F i The free energy (i.e., expected free energy) of the current training cycle, k is the free energy dissipation coefficient, T is the user's current physical state parameter, S is the user's training load parameter for the current training cycle, and E is the free energy. i This represents the current training cycle's fitness level (i.e., the adjusted fitness level). k is an energy expenditure coefficient matched to the user's athletic ability, quantifying the energy dissipation of different users under training load. In this embodiment, k is assigned a personalized value based on the user's athletic ability level, for example, 0.3 for elite athletes, 0.5 for advanced serious athletes, and 1 for ordinary people.

[0087] In some embodiments, when a user first uses the free energy calculation model of the present invention... It can be initially set to an initial value, which can be the average or median value based on multi-user fitness data. Alternatively, different initial values ​​can be set specifically for the user's group (such as athletes, fitness enthusiasts, or ordinary people without exercise habits), and can be set independently by engineers.

[0088] For example, the free energy of the previous day can be estimated based on an assumed physical fitness value. Subsequently, through repeated use of the free energy calculation model by the user over a longer period of time (such as a week or a month), the free energy calculation model can continuously adapt to the user's actual physical condition.

[0089] Free energy is the effective exercise energy that a user has available for direct use after the training cycle ends, excluding the consumption of training load and physiological fatigue. It is an instantaneous energy status indicator on a short time scale, directly reflecting the immediate recovery level and the degree of fatigue accumulation after training. The higher the value, the more usable energy the body has, the less fatigue accumulation, and the better the recovery state; the lower the value, the more severe the energy consumption and fatigue loss, the less usable energy left, and the higher the recovery needs.

[0090] S5 comprehensively assesses the user's recovery status based on the free energy, the preset physical fitness baseline, and the physical state parameters, and outputs the corresponding recovery status assessment result.

[0091] In this embodiment, the physical fitness baseline is the long-term rolling average of the user's physical fitness value, reflecting the user's current basic physical fitness level and its trend. Specifically, it is based on the daily physical fitness value E over the past 7 consecutive days. i The system uses a sliding window to calculate the arithmetic mean as the daily fitness baseline; if no baseline is established, the system uses the default value corresponding to the user's fitness level.

[0092] In this embodiment, the method for evaluating the user's recovery status is as follows: S51 determines that the athlete's body is in an acute fatigue state after overload when the free energy of the current training cycle is lower than the preset acute fatigue threshold.

[0093] When the free energy F calculated in step S4 ends at the end of the current training cycle i When the preset acute fatigue threshold is 0.1, the user's body is directly determined to be in an acute fatigue state after overload, the acute fatigue trigger time point is marked simultaneously, and continuous monitoring is initiated for the next 3-day response cycle.

[0094] Acute fatigue indicates that a user's daily training load has depleted their body's available energy to its critical limit, a prerequisite for supercompensation, but also a high-risk starting point for overtraining. For example, in the early stages of a season, elite athletes' high-quality training sessions push their free energy close to zero. The algorithm identifies this as controllable acute fatigue, meeting the overload prerequisite for supercompensation. The system marks the state as acute fatigue and simultaneously triggers a dynamic increase in the recovery time parameter τ, providing immediate recovery suggestions.

[0095] If, within the preset response period after an acute fatigue state is determined, the athlete's baseline physical fitness does not decrease by more than the preset safety threshold ratio and the physical condition parameters are less than the safety parameters, then the overtraining caused by this overload is determined to be functional overtraining, and the athlete can withstand the current overload. If, within the preset response period after an acute fatigue state is identified, the athlete's baseline physical fitness declines by more than the preset safety threshold percentage, or the physical condition parameters exceed the safety parameters, then the overtraining caused by this overload is determined to be non-functional overtraining, meaning the athlete cannot withstand the current overload and there is a risk of sports injury.

[0096] Specifically, if, within three consecutive training cycles following an acute fatigue trigger, the user's baseline physical fitness decline does not exceed a preset safety threshold (e.g., 10%), and the user's daily physical condition parameter T remains consistently below 1 without abnormal fluctuations, then it is considered functional overtraining. Excessive load provides sufficient training stimulation to the body, triggering its adaptation mechanisms, but does not exceed the body's recovery capacity, thus preventing irreversible fatigue accumulation and sports injuries. This is a necessary prerequisite for subsequent supercompensation.

[0097] If a user's baseline physical fitness declines beyond a preset safety threshold within three consecutive training cycles following an acute fatigue trigger, it is considered non-functional overtraining. Non-functional overtraining indicates that the excessive load has exceeded the body's recovery capacity, leading to a continuous decline in physical fitness and autonomic nervous system dysfunction. If the training plan is not adjusted in time, it can easily cause serious problems such as stress fractures, central nervous system fatigue, endocrine disorders, and overtraining syndrome. This is a high-risk state that this invention focuses on warning of. Once non-functional overtraining is identified, the algorithm immediately and forcibly increases the recovery time parameter τ, strongly recommending that high-intensity training be stopped and a full recovery cycle be entered to avoid irreversible damage.

[0098] If, within a preset training period after functional overtraining, the S53 determines that the user's body has completed supercompensation if the athlete's fitness score is greater than the sum of the fitness baseline and the corresponding standard deviation, then the user's body has completed supercompensation.

[0099] Within a 7-day training cycle monitoring window following the completion of functional overtraining assessment, the user's daily fitness score E... i>If the physical fitness baseline plus the standard deviation of the physical fitness baseline, and the physical condition parameter T is stably maintained at around 1, then the user's body is judged to have completed supercompensation.

[0100] Supercompensation is the physiological mechanism for improving athletic performance. After the body has endured a tolerable superload, it achieves a super-baseline improvement in physical fitness through sufficient recovery. At this time, the user's athletic performance and training tolerance are at their peak, making it the best time to arrange high-intensity competition simulations and key technology training.

[0101] The invention will be illustrated below through an application example, which provides analysis and suggestions on supercompensation for elite athletes at different stages of competition preparation.

[0102] like Figure 3 As shown, the period before September 15, 2025, was mainly the pre-match preparation period, while the period from September 15 to October 1 was mainly the season.

[0103] During the pre-season preparation phase, a period of heavy training load accumulation, fitness and free energy levels tend to decline throughout the month, with free energy levels approaching zero three times (this is because high-quality training sessions that week pushed athletes to their limits). Subsequently, athletes enter a supercompensation phase of recovery, which is evident in the surge in fitness and free energy levels at the beginning of September.

[0104] By using energy values ​​(i.e., free energy, physical fitness) to guide athlete training, a recovery phase of supercompensation can be initiated during the transition period from pre-season to season, allowing the energy curve to rise and reach a better competitive state. Subsequently, during the season, energy reserves drop to near zero, mainly due to various test events.

[0105] In summary, during the testing process, coaches primarily adjusted athletes' training cycles (such as training duration and intensity) based on the physical condition assessment provided by this method, offering them exercise guidance. Furthermore, it can be seen that through appropriate exercise guidance, athletes ensured high-intensity training before the competition and were able to maintain high-intensity physical fitness during the competition through the principle of supercompensation.

[0106] Example 2: like Figure 2 As shown, this embodiment also provides a post-training physical recovery status assessment system, including: The body status parameter acquisition module is used to collect the user's physiological indicators and determine the user's current body status parameters based on the physiological indicators. The training load parameter acquisition module is used to acquire the training load parameters corresponding to the user's current training cycle. The physical fitness value acquisition module uses a preset physical fitness correction model to calculate the physical fitness value of the current training cycle; the physical fitness correction model is based on the user's free energy in the previous training cycle to correct the physical fitness value of the current training cycle. The free energy acquisition module is used to calculate the free energy of the current training cycle based on the physical fitness value, body state parameters, and training load parameters using a preset free energy calculation model. The assessment module comprehensively evaluates the user's recovery status based on the free energy, the preset physical fitness baseline, and the physical state parameters, and outputs the corresponding recovery status assessment results.

[0107] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a computer terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0109] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A method for assessing post-training physical recovery, characterized in that, include: The system collects the user's physiological indicators and determines the user's current physical condition parameters based on these indicators. These physiological indicators include: HRV value, blood oxygen saturation, body temperature, skin conductance, blood pressure, or respiratory rate. The magnitude of these physical condition parameters is negatively correlated with the user's level of physical well-being. Obtain the training load parameters corresponding to the user's current training cycle; A preset fitness correction model is used to calculate the corrected fitness value for the current training cycle. The fitness correction model is based on the user's free energy from the previous training cycle and corrects the initial fitness value for the current training cycle to obtain the corrected fitness value. The free energy is used to define the amount of energy remaining in the user's body after the end of the training cycle, and the fitness value is used to define the user's ability to carry the training load in the current training cycle. The correction mode of the fitness correction model is that the larger the free energy of the previous training cycle, the larger the difference between the initial fitness value and the corrected fitness value. Using a preset free energy calculation model, based on the corrected physical fitness value, body state parameters, and training load parameters, the expected free energy of the current training cycle is calculated. The free energy calculation model includes: expected free energy = corrected physical fitness value - expected energy expenditure, and the expected energy expenditure is defined by training load parameters and body state parameters, wherein the body state parameters are used to represent the energy expenditure capacity of the same training load parameter under different body states; the user's recovery status is evaluated based on the expected free energy, and the corresponding recovery status evaluation result is output.

2. The method for assessing post-training physical recovery status according to claim 1, characterized in that, In the free energy calculation model, for the same training load parameter, the larger the body state parameter, the greater the corresponding expected energy consumption.

3. The method for assessing post-training physical recovery status according to claim 1, characterized in that, Determining the user's current physical condition parameters based on the aforementioned physiological indicators includes: Body status parameters are calculated based on the HRV value, HRV baseline value, and HRV standard deviation in the physiological indicators. When the HRV value is greater than the HRV baseline value minus the HRV standard deviation, the body status parameter T is the set value. When the HRV value is less than or equal to the HRV baseline value minus the HRV standard deviation, the body status parameter T is (HRV baseline value minus HRV value) / HRV standard deviation.

4. The method for assessing post-training physical recovery status according to claim 1, characterized in that, The physical fitness correction model is as follows: ； Among them, E i F represents the fitness level for the current training cycle. i-1 τ is the user's free energy at the end of the previous training cycle, τ is the recovery time parameter, and qs is the user's sleep recovery quality parameter.

5. The method for assessing post-training physical recovery status according to claim 4, characterized in that, The recovery time parameter τ is dynamically adjusted based on the user's free energy state, and the adjustment rules include: Calculate the reference free energy and the expected free energy F i The difference is such that when the difference is greater than a preset difference threshold, the recovery time parameter τ is increased; when the difference is less than or equal to the preset difference threshold, the recovery time parameter τ is decreased or maintained. The reference free energy = free energy baseline value - free energy standard deviation; wherein, the free energy baseline value is determined by the user's historical motion data within a historical period; And / or, the method further includes a supplementary correction step for the recovery time parameter τ based on a physical fitness baseline: The system continuously monitors the user's physical fitness baseline trend. If, after N consecutive training cycles, the user's physical fitness baseline shows a downward trend and the decline exceeds a preset decline threshold, the recovery time parameter τ is increased, where N is a positive integer greater than or equal to 2.

6. The method for assessing post-training physical recovery status according to claim 1, characterized in that, The free energy calculation model is as follows: ； Among them, F i Let E be the expected free energy, k be the free energy dissipation coefficient, T be the user's current physical state parameter, S be the user's training load parameter for the current training cycle, and E be the free energy. i This is the corrected fitness value for the current training cycle.

7. The method for assessing post-training physical recovery status according to claim 1, characterized in that, It also includes a workload correction step: Collect users' lifestyle load data and adjust the physical condition parameters and / or training load parameters based on the lifestyle load; the lifestyle load data is obtained based on the users' heart rate variability (HRV) data.

8. The method for assessing post-training physical recovery status according to claim 7, characterized in that, The method for obtaining the living load data includes: Long-term heart rate variability (HRV) data of users are collected, the collected data are filtered, and isolated outliers are removed. Life load is assessed based on HRV data; points in the HRV data where the decline exceeds the expected magnitude are marked as stress points, and the number of stress points is positively correlated with life load.

9. The method for assessing post-training physical recovery status according to claim 1, characterized in that, The method for assessing a user's recovery status is as follows: If the expected free energy is lower than the preset acute fatigue threshold, the user's body is determined to be in an acute fatigue state after overload. Within the preset response period after being identified as an acute fatigue state, if the user's physical fitness baseline decline does not exceed the preset safety threshold ratio and the physical condition parameters are less than the safety parameters, then the overtraining caused by this overload is determined to be functional overtraining, and the user can withstand the current overload. If, within the preset response period after being identified as an acute fatigue state, the user's physical fitness baseline declines by more than the preset safety threshold ratio, or the physical condition parameters are greater than the safety parameters, then the overtraining caused by this overload is determined to be non-functional overtraining, corresponding to the user being unable to withstand the current overload and having a risk of sports injury. If, within a preset training period after being identified as having functional overtraining, a user's fitness score is greater than the sum of the fitness baseline and the corresponding standard deviation, then the user's body is considered to have completed supercompensation.

10. A system for assessing post-training physical recovery, characterized in that, include: The body status parameter acquisition module is used to collect the user's physiological indicators and determine the user's current body status parameters based on the physiological indicators; wherein, the physiological indicators include: HRV value, blood oxygen saturation, body temperature, skin conductance, blood pressure or respiratory rate; the magnitude of the body status parameters is negatively correlated with the user's level of physical condition. The training load parameter acquisition module is used to acquire the training load parameters corresponding to the user's current training cycle. The physical fitness value acquisition module is used to calculate the corrected physical fitness value for the current training cycle using a preset physical fitness correction model. The physical fitness correction model is based on the user's free energy from the previous training cycle and corrects the initial physical fitness value for the current training cycle to obtain the corrected physical fitness value. The free energy is used to define the amount of energy remaining in the user's body after the end of the training cycle, and the physical fitness value is used to define the user's ability to bear the training load in the current training cycle. The correction mode of the physical fitness correction model is that the larger the free energy of the previous training cycle, the larger the difference between the initial physical fitness value and the corrected physical fitness value. The free energy acquisition module is used to calculate the expected free energy of the current training cycle based on the corrected physical fitness value, body state parameters, and training load parameters using a preset free energy calculation model. The free energy calculation model includes: expected free energy = corrected physical fitness value - expected energy expenditure, and the expected energy expenditure is defined by training load parameters and body state parameters, wherein the body state parameters are used to represent the magnitude of physical fitness expenditure under different body states for the same training load parameters. The evaluation module is used to assess the user's recovery status based on the expected free energy and output the corresponding recovery status evaluation results.

Images