Athlete fatigue recovery auxiliary system based on biofeedback

Abstract

An athlete fatigue recovery auxiliary system based on biofeedback belongs to the field of fatigue recovery assistance and comprises a data acquisition module, a processing extraction module, a state evaluation module, a scheme making module, an adjustment monitoring module and an evaluation feedback module. According to the method, the fatigue state of the athlete is comprehensively evaluated based on various physiological signals, and the physiological and exercise load state of the athlete can be effectively and accurately reflected. According to the method, personalized recovery suggestions can be provided according to individual differences of all athletes. The recovery strategy can be dynamically adjusted to meet the actual requirements of different athletes, so that the recovery effect is improved, and the risk of excessive recovery or insufficient recovery is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of fatigue recovery assistance, and more specifically, particularly relates to an athlete fatigue recovery assistance system based on biofeedback. Background Art

[0002] The fatigue state of athletes is not determined by a single physiological signal, but by multiple physiological and psychological factors intertwined. Common physiological signals include heart rate variability (HRV), lactate concentration, electromyogram (EMG), skin conductance response, etc. Each signal reflects different aspects of the athlete's physical state. Since the response mechanisms of each signal to the fatigue state are different, therefore, how to effectively combine multiple physiological signals to provide a more accurate fatigue assessment is still a technical problem. The interaction between different signals is complex and has individual differences, and a single signal cannot comprehensively reflect the fatigue state of athletes. The physiological feedback patterns of different athletes are also different, which makes the universality of the fatigue recovery plan poor and the difficulty of personalized adjustment large.

[0003] To achieve effective biofeedback, precise physiological data acquisition devices must be relied on. These devices usually include wearable sensors, monitoring devices, etc., for collecting the real-time physiological data of athletes. However, these devices may be affected by factors such as the external environment, exercise intensity, device errors, etc., resulting in problems with the accuracy and consistency of data collection. During high-intensity exercise or rapid movement, the device may not be able to stably obtain accurate data, resulting in misjudgment of the fatigue state or delayed feedback. In addition, individual differences of athletes (such as skin type, exercise habits, etc.) may also cause large measurement errors of the device.

[0004] One of the goals of the biofeedback system is to provide feedback in real time so that athletes can make quick adjustments during training or competitions to avoid over-fatigue or injury. The change of physiological data is often not instantaneous, but gradually reflected, and this time lag may cause a delay in the feedback mechanism. The delay of biofeedback may cause athletes to receive recovery suggestions only after fatigue has accumulated excessively, and may not be able to effectively avoid athletes from over-fatiguing or increasing the risk of injury due to untimely recovery. Summary of the Invention

[0005] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above or existing problems of the athlete fatigue recovery assistance system based on biofeedback, the present invention is proposed.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] An embodiment of the present invention provides an athlete fatigue recovery assistance system based on biofeedback, including: a data acquisition module for collecting physiological signals of athletes using wearable devices;

[0009] A processing and extraction module for filtering and denoising the collected raw data, extracting features, analyzing the response of the autonomic nervous system to fatigue through HRV features, and evaluating the degree of muscle fatigue through electromyogram features;

[0010] A state evaluation module for predicting the fatigue state of athletes using a machine learning model in combination with the extracted physiological features;

[0011] A plan formulation module for formulating a recovery plan for athletes based on the fatigue state evaluation results;

[0012] An adjustment and monitoring module for real-time monitoring of the physiological state of athletes and adjusting the recovery plan using real-time feedback;

[0013] An evaluation and feedback module for regularly evaluating the recovery effect of athletes, providing feedback based on physiological signals and sports performance, updating the recovery strategy, and using the performance of athletes as an evaluation index to evaluate the recovery effect.

[0014] As a preferred solution of the athlete fatigue recovery assistance system based on biofeedback according to the present invention, wherein: the wearable device includes a heart rate monitor, an EMG electromyography sensor, and a body temperature sensor.

[0015] As a preferred solution of the athlete fatigue recovery assistance system based on biofeedback according to the present invention, wherein: the collection of physiological signals of athletes using wearable devices includes:

[0016] The athlete wears the device to collect heart rate data and analyze the variation of the time interval between heart rates. Its expression is as follows:

[0017]

[0018] Wherein, RR i is the RR interval and N is the number of samples;

[0019] The athlete wears an electromyography sensor and collects data with multiple sensors distributed on different muscle groups. The degree of muscle fatigue is evaluated through the frequency and amplitude changes of the electromyogram signal. Its expression is as follows:

[0020]

[0021] Wherein, xi Represents the time-domain data of the electromyogram signal. N is the number of samples, and RMS is the root mean square value of the signal, which reflects the overall activity level of the muscle.

[0022] As a preferred embodiment of the adaptive microgrid energy management and optimization control system described in the present invention, wherein: the reaction of the autonomic nervous system to fatigue through HRV feature analysis includes:

[0023] HRV is evaluated by analyzing the statistical characteristics of the heart rate intervals in the time domain, and the parasympathetic nerve activity is measured by the root mean square deviation. The expression is as follows:

[0024]

[0025] where RR i+1 and RR i are adjacent RR intervals;

[0026] After training or competition, the activity of the sympathetic nervous system increases, and the activity of the parasympathetic nervous system decreases, resulting in a significant decrease in HRV; if the athlete fails to get sufficient recovery, high-intensity training causes the sympathetic nervous system to remain active and the parasympathetic nerve activity to be low, resulting in HRV remaining at a low level for a long time; when the athlete rests or performs recovery activities, the parasympathetic nerve activity increases, and HRV gradually returns to the normal level.

[0027] As a preferred embodiment of the athlete fatigue recovery assistance system based on biofeedback described in the present invention, wherein: the evaluation of muscle fatigue degree through electromyogram characteristics includes:

[0028] Frequency domain analysis transforms the EMG signal into frequency components through Fourier transform to help evaluate the degree of muscle fatigue. In a fatigued state, the spectral characteristics of the EMG signal change, manifested as an increase in the low-frequency component and a decrease in the high-frequency component. As muscle fatigue intensifies, the electrical activity of the muscle becomes more low-frequency, and the MNF value will decrease. The relevant expression is as follows:

[0029]

[0030] where f is the frequency, P(f) is the power spectral density at frequency f, and f max is the maximum frequency of the signal.

[0031] As a preferred embodiment of the athlete fatigue recovery assistance system based on biofeedback described in the present invention, wherein: combining the extracted physiological characteristics and using a machine learning model to predict the fatigue state of the athlete includes:

[0032] Adopting a random forest model to predict the fatigue state of the athlete, the steps are as follows:

[0033] Collect physiological data of athletes such as HRV, EMG, respiratory rate, and lactate concentration, extract time-domain, frequency-domain, and non-linear features from the signals, give fatigue level labels based on lactate concentration and athlete feedback, train a model using the random forest algorithm, and select hyperparameters using cross-validation. The model predicts the fatigue state based on real-time input physiological features and provides recovery suggestions for athletes.

[0034] As a preferred embodiment of the biofeedback-based athlete fatigue recovery assistance system of the present invention, wherein: using a random forest model to predict the fatigue state of athletes includes:

[0035] If the random forest model training is completed, it is used for predicting the fatigue state. Given new input data, through the input data X, for each tree, the model gives a prediction result y t , and voting or averaging is used to obtain the final fatigue state prediction result.

[0036] As a preferred embodiment of the biofeedback-based athlete fatigue recovery assistance system of the present invention, wherein: formulating a recovery plan for athletes based on the fatigue state assessment result includes:

[0037] Assume that the recovery time of athletes is predicted through HRV and lactate concentration, and the following formula is used to calculate the required recovery time:

[0038]

[0039] wherein, HRV initial and HRV current respectively represent the initial HRV value and the current HRV value of the athlete, HRV recovery represents the speed of HRV recovery, Lactate current represents the current lactate concentration, Lactate decay_rate represents the rate of decrease in lactate concentration.

[0040] As a preferred embodiment of the biofeedback-based athlete fatigue recovery assistance system of the present invention, wherein: real-time monitoring of the physiological state of athletes and adjusting the recovery plan using real-time feedback includes:

[0041] If the recovery level R(t) of the athlete is dynamically calculated based on his fatigue state and historical data, it is adjusted through the following formula:

[0042] R(t) = f(HRV t , Lactate t , EMG t , T sleep , T hydration )

[0043] Among them, HRV t represents the heart rate variability at the current time point, Lactate t represents the current lactate concentration, EMG t represents the current electromyogram fatigue index, T sleep represents the sleep duration of the previous day, T hydration represents the water replenishment situation of the previous day;

[0044] If mild fatigue is reached, the athlete performs aerobic activities, replenishes water and electrolytes;

[0045] If moderate fatigue is reached, the athlete performs restorative stretching, massage and gets sufficient sleep;

[0046] If severe fatigue is reached, the athlete undergoes a 48 - 72 - hour recovery period and performs relaxation meditation, hot compress or cold compress recovery measures.

[0047] As a preferred scheme of the biofeedback - based athlete fatigue recovery assistance system described in the present invention, wherein: regularly evaluate the athlete's recovery effect, give feedback based on physiological signals and sports performance, update the recovery strategy, use the athlete's performance as an evaluation index to evaluate the recovery effect, including:

[0048] The recovery effect E(t) is a comprehensive evaluation based on physiological signals and sports performance, and is expressed by the following formula:

[0049] E(t) = α·HRV(t)+β·Lactate(t)+γ·EMG(t)+δ·Performance(t)

[0050] Among them, HRV(t) represents the HRV level at the current moment, Lactate(t) represents the lactate concentration at the current moment, EMG(t) represents the electromyogram signal at the current moment, Performance(t) represents the sports performance at the current moment, and α, β, γ are weight coefficients, which are adjusted according to different individual differences and recovery goals of athletes;

[0051] Determine the recovery strategy according to the value of E(t):

[0052] If E(t)>0.8, it means good recovery, and gradually increase the training intensity;

[0053] If E(t)<0.5, it means insufficient recovery, and increase the recovery time;

[0054] If E(t) is between 0.5 and 0.8, it means moderate recovery, and perform low - intensity restorative training.

[0055] The beneficial effects of the present invention are as follows: Based on multiple physiological signals, the present invention comprehensively evaluates the fatigue state of athletes, and can effectively and accurately reflect the physiological and exercise load states of athletes. Through multi-signal fusion, the limitations of single physiological indicators are avoided, making the fatigue assessment more comprehensive and objective. By adopting technologies such as machine learning and data analysis, the present invention can provide personalized recovery suggestions according to the individual differences of each athlete. Compared with the traditional one-size-fits-all recovery plan, the present invention can dynamically adjust the recovery strategy to adapt to the actual needs of different athletes, thereby improving the recovery effect and reducing the risk of over-recovery or under-recovery. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0057] Figure 1 FIG. is a schematic structural diagram of an athlete fatigue recovery assistance system based on biofeedback provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] In order to make the above-mentioned objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0059] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0060] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or selectively exclusive embodiments from other embodiments.

[0061] Embodiment

[0062] The following refers to Figure 1 , which is an embodiment of the present invention.

[0063] S1: A data acquisition module, which is used to collect the physiological signals of athletes by using wearable devices.

[0064] Preferably, the athlete wears a device to collect heart rate data and analyze the variation of the time interval between heart rates. The expression is as follows:

[0065]

[0066] Among them, RR i is the RR interval, and N is the number of samples;

[0067] The athlete wears an electromyogram sensor, which is collected by distributing multiple sensors on different muscle groups. The degree of muscle fatigue is evaluated through the frequency and amplitude changes of the electromyogram signal. The expression is as follows:

[0068]

[0069] Among them, x i represents the time-domain data of the electromyogram signal. N is the number of samples, and RMS is the root mean square value of the signal, which reflects the overall activity level of the muscle.

[0070] Furthermore, assume that the athlete is performing a high-intensity training and wears a heart rate monitor and an electromyogram sensor. The system starts to collect the athlete's physiological data and perform real-time analysis.

[0071] The first stage (beginning of training):

[0072] The heart rate variability (HRV) begins to change. The RR interval is stable in the initial stage, but as the training continues, the RR interval becomes more volatile and the HRV value decreases. At the same time, the root mean square value (RMS) of the electromyogram signal gradually increases, indicating the initial signs of muscle fatigue.

[0073] The second stage (mid-training):

[0074] The heart rate data continues to show a low HRV value. The amplitude and frequency of the electromyogram signal change significantly, and the RMS value continues to increase, indicating an increase in muscle fatigue. The system feeds back to the athlete to reduce the training intensity and take a short rest and muscle relaxation.

[0075] The third stage (end of training)

[0076] After the training ends, the HRV value drops to a low point and the RMS value reaches a peak, indicating high muscle fatigue. The system recommends taking appropriate recovery measures, such as using cold compresses, massages, and stretches, to promote muscle recovery.

[0077] S2: The processing and extraction module is used to filter and denoise the collected raw data, extract features, analyze the response of the autonomic nervous system to fatigue through HRV features, and evaluate the degree of muscle fatigue through electromyogram features.

[0078] Preferably, the statistical characteristics of the heart rate intervals are analyzed in the time domain to evaluate HRV, and the parasympathetic nerve activity is measured by the root mean square deviation, and its expression is as follows:

[0079]

[0080] where RR i+1 and RR i are adjacent RR intervals;

[0081] After training or competition, the activity of the sympathetic nervous system increases, and the activity of the parasympathetic nervous system decreases, resulting in a significant decrease in HRV; if the athlete fails to get enough recovery, high-intensity training causes the sympathetic nervous system to remain active and the parasympathetic nerve activity to be low, resulting in HRV remaining at a low level for a long time; when the athlete rests or engages in restorative activities, the parasympathetic nerve activity increases and HRV gradually returns to the normal level.

[0082] Preferably, frequency domain analysis transforms the EMG signal into frequency components through Fourier transform to help evaluate the degree of muscle fatigue. In the fatigue state, the spectral characteristics of the EMG signal change, manifested as an increase in the low-frequency component and a decrease in the high-frequency component. As muscle fatigue intensifies, the electrical activity of the muscle becomes more low-frequency and the MNF value will decrease, and the relevant expression is as follows:

[0083]

[0084] where f is the frequency, P(f) is the power spectral density at frequency f, and f max is the maximum frequency of the signal.

[0085] Furthermore, assume that after an athlete conducts a high-intensity competition, the system collects the RR interval data of the athlete in real time through the worn heart rate monitoring device. Based on these data, the system calculates RMSSD in real time and judges the recovery status of the athlete. During the competition, the system collects the RR interval data RR1, RR2,..., RRN in real time through the heart rate sensor. After the competition, the system continues to monitor the HRV of the athlete and gradually collects new RR interval data.

[0086] By calculating the RMSSD value, the system can evaluate the change of HRV of the athlete. According to the HRV values in different stages, the system can make the following judgments:

[0087] Immediately after the competition: The initial HRV value is low and the RMSSD decreases significantly, indicating that the sympathetic nervous system of the athlete is highly active and the parasympathetic nervous system is less active, indicating that the athlete is in a state of fatigue.

[0088] After 24 hours: If the HRV remains at a low level and the RMSSD does not increase significantly, it indicates that the athlete's fatigue has not been fully recovered and recovery measures (such as rest, cold compress, massage, etc.) need to be increased.

[0089] After 48 hours: If the HRV value returns to the normal level and the RMSSD increases, it indicates that the parasympathetic nerve activity is enhanced, the athlete's recovery state is good, and the fatigue has gradually disappeared.

[0090] Based on the real-time HRV assessment results, the system can provide targeted recovery suggestions. For example:

[0091] The system recommends increasing the rest time, avoiding high-intensity training, and using recovery means (such as cold compress, stretching, etc.) to promote parasympathetic nerve activity.

[0092] If the RMSSD value is high and the HRV is close to the normal level, it indicates that the athlete's body has started to recover and moderate training or recovery activities can be carried out.

[0093] Furthermore, assume that the collected EMG signals are: x1(t), x2(t), …, xn(t)x_1(t), and each xi(t) is the EMG signal data within a time period. For each group of EMG signals xi(t), perform Fourier transform to obtain its frequency domain representation Xi(f), and then calculate its power spectral density Pi(f):

[0094] By integrating the power spectral density and frequency, calculate the mean frequency (MNF) of each group of signals. Assume that we have n groups of EMG signals, then the MNF calculation formula for each group of signals is:

[0095]

[0096] For multiple groups of electromyography signals, the overall MNF value can be calculated by taking the average:

[0097]

[0098] If the MNF value is lower than the set fatigue threshold, it indicates that the muscle is in a fatigued state and the muscle electrical activity shows a low-frequency phenomenon. The system will prompt the athlete to rest or perform recovery activities.

[0099] If the MNF value gradually increases, it indicates that the parasympathetic nerve activity is enhanced and the muscle gradually returns to the normal state. The system will adjust the training plan according to the recovery situation.

[0100] S3: State assessment module, which is used to combine the extracted physiological characteristics and use a machine learning model to predict the fatigue state of the athlete.

[0101] Preferably, a random forest model is used to predict the fatigue state of athletes, and the steps are as follows:

[0102] Collect the physiological data of athletes including HRV, EMG, respiratory rate and lactic acid concentration. Extract time-domain, frequency-domain and non-linear features from the signals. According to the lactic acid concentration and the feedback of athletes, give fatigue level labels, train the model using the random forest algorithm, and select hyperparameters using cross-validation. The model predicts the fatigue state based on the real-time input physiological features and provides recovery suggestions for athletes.

[0103] Preferably, if the random forest model training is completed, it is used for predicting the fatigue state. Given new input data, through the input data X, for each tree, the model gives a prediction result y t , and voting or averaging is used to obtain the final fatigue state prediction result.

[0104] Furthermore, during the training or competition of athletes, collect the HRV, EMG, respiratory rate and lactic acid concentration data of athletes in real time, and extract features (such as mean, standard deviation, root mean square value, frequency-domain features, etc.) from them. Transmit the real-time input feature data X input to the trained random forest model. For each decision tree t, the model gives a prediction result y t , representing the fatigue level of the current state. The random forest model obtains the final fatigue state prediction through the following voting mechanism:

[0105] y final = majority-vote(y1, y2,..., y T )

[0106] where, y finaly is the final fatigue state prediction result of the model, y1, y2,..., yT are the prediction results of each tree, and the majority vote determines the final result;

[0107] According to the prediction result y final of the model, the model provides corresponding recovery suggestions for athletes:

[0108] Fatigue level 0 (not fatigued): Continue training or carry out daily activities;

[0109] Fatigue level 1 (mild fatigue): Carry out mild restorative activities such as stretching, yoga, etc.;

[0110] Fatigue level 2 (moderate fatigue): Rest or carry out low-intensity aerobic activities to help recovery;

[0111] Fatigue level 3 (severe fatigue): It is recommended to rest completely or carry out deep recovery such as massage, hot compress, etc.

[0112] S4: A solution formulation module, which is used to formulate a recovery plan for the athlete based on the fatigue state assessment result.

[0113] Preferably, assuming that the recovery time of the athlete is predicted by HRV and lactate concentration, the following formula is used to calculate the required recovery time:

[0114]

[0115] where, HRV initial and HRV current respectively represent the initial HRV value and the current HRV value of the athlete, HRV recovery represents the recovery speed of HRV, Lactate current represents the current lactate concentration, Lactate decay_rate represents the rate of decrease in lactate concentration.

[0116] Furthermore, before the athlete's training, data is collected through a heart rate monitoring device to calculate the initial HRV. After training or a competition, the current HRV value is obtained by real-time monitoring of the athlete's HRV. The current lactate concentration is obtained through a lactate monitoring device. According to the athlete's physical condition, training intensity, and recovery situation, the rate of decrease in lactate concentration is set, which is obtained from historical data.

[0117] Assume that the athlete's initial HRV value is 60 ms, the current HRV value is 45 ms, the HRV recovery speed is 5 ms / hour, the current lactate concentration is 15 mmol / L, and the rate of decrease in lactate concentration is 3 mmol / L / hour.

[0118] Trecovery = 8 hours

[0119] Therefore, the predicted recovery time of the athlete is 8 hours;

[0120] During the athlete's recovery process, by wearing a device to real-time monitor HRV and lactate concentration, the system can real-time calculate the athlete's recovery status and dynamically adjust the recovery time.

[0121] Real-time HRV monitoring: If the HRV of the athlete gradually rises during the recovery process and HRV _current gradually approaches HRV _initial , the recovery time will be correspondingly shortened.

[0122] Real-time lactate monitoring: As the lactate concentration decreases, the system will reduce the contribution of the lactate concentration part to the recovery time. If the lactate concentration decreases rapidly, the recovery time may also be correspondingly shortened.

[0123] Based on the real-time prediction of the recovery time, the athlete can adopt different recovery strategies according to his own recovery situation:

[0124] Short-term recovery: Perform light activities or rest to help the HRV recover and promote the reduction of lactate concentration.

[0125] Long-term recovery: Perform deep recovery, including massage, hot compress, low-intensity aerobic exercise, etc., to help relieve muscle fatigue and lactate accumulation.

[0126] S5: Adjust the monitoring module to continuously monitor the physiological state of the athlete and adjust the recovery plan using real-time feedback.

[0127] Preferably, if the recovery level R(t) of the athlete is dynamically calculated based on their fatigue state and historical data, it is adjusted through the following formula:

[0128] R(t) = f(HRV t , Lactate t , EMG t , T sleep , T hydration )

[0129] Wherein, HRV t represents the heart rate variability at the current time point, Lactate t represents the current lactate concentration, EMG t represents the current electromyogram fatigue index, T sleep represents the sleep duration of the previous day, T hydration represents the water replenishment situation of the previous day;

[0130] If mild fatigue is reached, the athlete performs aerobic activities, replenishes water and electrolytes;

[0131] If moderate fatigue is reached, the athlete performs restorative stretching, massage, and gets sufficient sleep;

[0132] If severe fatigue is reached, the athlete undergoes a 48 - 72-hour recovery period and performs relaxation meditation, hot compress or cold compress recovery measures.

[0133] Furthermore, based on the real-time collected data, substitute it into the formula to calculate the athlete's recovery level R(t)

[0134] and determine the fatigue level:

[0135] R(t) = w1·HRV t + w2·Lactate t + w3·EMG t + w4·T sleep + w5·T hydration

[0136] Assume the following data HRV t= 55, Lactate t = 12, EMG t = 6.5, T sleep = 7.5 hours, T hydration = 2.5 L, Set weight coefficients: w1 = 0.3, w2 = 0.2, w3 = 0.2, w4 = 0.2, w5 = 0.1;

[0137] Then R(t) = 21.95. If the fatigue degree threshold is set to 20, the athlete is in a state of mild fatigue at this time.

[0138] S6: Evaluation and feedback module, used to regularly evaluate the athlete's recovery effect, give feedback based on physiological signals and sports performance, update the recovery strategy, and use the athlete's performance as an evaluation index to evaluate the recovery effect.

[0139] Preferably, the recovery effect E(t) is a comprehensive evaluation based on physiological signals and sports performance, and is expressed by the following formula:

[0140] E(t) = α·HRV(t) + β·Lactate(t) + γ·EMG(t) + δ·Performance(t)

[0141] Wherein, HRV(t) represents the HRV level at the current moment, Lactate(t) represents the lactate concentration at the current moment, EMG(t) represents the electromyogram signal at the current moment, Performance(t) represents the sports performance at the current moment, and α, β, γ are weight coefficients, which are adjusted according to different individual differences and recovery goals of athletes;

[0142] Determine the recovery strategy according to the value of E(t):

[0143] If E(t) > 0.8, it means the recovery is good, and gradually increase the training intensity;

[0144] If E(t) < 0.5, it means the recovery is insufficient, and increase the recovery time;

[0145] If E(t) is between 0.5 and 0.8, it means the recovery is medium, and carry out low-intensity recovery training.

[0146] Furthermore, use the collected real-time data to calculate the recovery effect according to the formula:

[0147] For example, assume the following data:

[0148] HRV(t) = 50; Lactate(t) = 8; EMG(t) = 6.0; Performance(t) = 85Performance(t)

[0149] = 85;

[0150] The weight coefficients are set as follows: α = 0.3, β = 0.2, γ = 0.2, δ = 0.3, and the recovery effect is:

[0151] E(t) = 43.3

[0152] According to the value of the recovery effect E(t), a recovery strategy is formulated:

[0153] If E(t) > 0., it is recommended to increase the training intensity; if E(t) < 0.5, it is recommended to increase the recovery time; if 0.5 ≤ E(t) < 0.8, low-intensity restorative training is carried out.

[0154] In the description of the present invention, it should be noted that the terms "first", "second", and "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0155] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0156] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0157] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0158] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0159] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions described in the foregoing embodiments or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0160] In addition, although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

Claims

1. A biofeedback-based athlete fatigue recovery auxiliary system, characterized in that: include: A data acquisition module, used to collect athletes’ physiological signals using wearable devices; The processing and extraction module is used to filter and denoise the collected raw data, extract features, analyze the response of the autonomic nervous system to fatigue through HRV features, and evaluate the degree of muscle fatigue through electromyography features; A state assessment module is used to combine the extracted physiological features and use a machine learning model to predict the athlete's fatigue state; A program development module is used to develop a recovery plan for athletes based on fatigue status assessment results; Adjustment monitoring module, used to monitor the athlete's physiological state in real time and adjust the recovery plan using real-time feedback; The evaluation and feedback module is used to regularly evaluate the recovery effect of athletes, provide feedback based on physiological signals and athletic performance, update recovery strategies, and use the performance of athletes as an evaluation indicator to evaluate the recovery effect.

2. The athlete fatigue recovery auxiliary system based on biofeedback as claimed in claim 1, characterized in that: The wearable device includes a heart rate monitor, an EMG electromyography sensor and a body temperature sensor.

3. The athlete fatigue recovery auxiliary system based on biofeedback as claimed in claim 1, characterized in that: The method of collecting the athlete's physiological signals by using a wearable device includes: Athletes wear equipment to collect heart rate data and analyze the changes in the time intervals between heart rates. The expression is as follows: Among them, RR i is the RR interval, N is the number of samples; Athletes wear electromyography sensors, with multiple sensors distributed on different muscle groups for collection. The frequency and amplitude changes of electromyographic signals are used to evaluate the degree of muscle fatigue. The expression is as follows: Among them, x i Represents the time domain data of the electromyographic signal, N is the number of samples, and RMS is the root mean square value of the signal, which reflects the overall activity level of the muscle.

4. The athlete fatigue recovery auxiliary system based on biofeedback as claimed in claim 1, characterized in that: The analysis of the reaction of the autonomic nervous system to fatigue through HRV characteristics includes: HRV is evaluated by analyzing the statistical characteristics of heart rate intervals in the time domain, and parasympathetic nerve activity is measured by the root mean square error, which is expressed as follows: Among them, RR i+1 and RR i is the adjacent RR interval; After training or competition, the activity of the sympathetic nervous system increases and the activity of the parasympathetic nervous system decreases, resulting in a significant decrease in HRV; if athletes fail to get enough recovery, high-intensity training causes the sympathetic nervous system to continue to be active and the parasympathetic nervous system to be low in activity, causing HRV to remain at a low level for a long time; when athletes rest or perform restorative activities, parasympathetic nervous system activity increases and HRV gradually returns to normal levels.

5. The athlete fatigue recovery auxiliary system based on biofeedback as claimed in claim 1, characterized in that: The muscle fatigue degree is assessed by electromyographic characteristics, including: Frequency domain analysis helps assess the degree of muscle fatigue by converting EMG signals into frequency components through Fourier transformation. Under fatigue conditions, the spectral characteristics of EMG signals generally change, showing an increase in low-frequency components and an attenuation of high-frequency components. As muscle fatigue increases, the electrical activity of the muscles becomes more low-frequency, and the MNF value decreases. The relevant expression is as follows: Where, f is the frequency, P(f) is the power spectral density of frequency f, and f max is the maximum frequency of the signal.

6. The athlete fatigue recovery auxiliary system based on biofeedback as claimed in claim 1, characterized in that: The method combines the extracted physiological features and uses a machine learning model to predict the fatigue state of athletes, including: The random forest model is used to predict the fatigue status of athletes. The steps are as follows: The athletes' HRV, EMG, respiratory rate and lactate concentration physiological data are collected, and time domain, frequency domain and nonlinear features are extracted from the signals. According to the lactate concentration and athlete feedback, fatigue level labels are given. The model is trained using the random forest algorithm, and cross-validation is used to select hyperparameters. The model predicts fatigue status based on the physiological characteristics input in real time and provides recovery suggestions for athletes.

7. The athlete fatigue recovery auxiliary system based on biofeedback as claimed in claim 6, characterized in that: The random forest model is used to predict the fatigue state of athletes, including: If the random forest model is trained, it is used to predict fatigue status. Given new input data, the model gives a prediction result y for each tree through the input data X. t , use voting or averaging to get the final fatigue state prediction result.

8. The athlete fatigue recovery auxiliary system based on biofeedback as claimed in claim 1, characterized in that: Based on the fatigue status assessment results, a recovery plan is developed for the athlete, including: Assuming that the athlete's recovery time is predicted by HRV and lactate concentration, the required recovery time can be calculated using the following formula: Among them, HRV initial and HRV current Respectively represent the athlete's initial HRV value and current HRV value, HRV recovery Indicates the speed of HRV recovery, Lactate current Indicates the current lactate concentration, Lactate decay_rate Indicates the rate at which lactate concentration decreases.

9. The athlete fatigue recovery auxiliary system based on biofeedback as claimed in claim 1, characterized in that: The real-time monitoring of the athlete's physiological state and the use of real-time feedback to adjust the recovery plan include: If the mobilized recovery level R(t) is dynamically calculated based on its fatigue status and historical data, it is adjusted by the following formula: R(t)=f(HRV t ,Lactate t ,EMG t ,T sleep ,T hydration ) Among them, HRV t Indicates the heart rate variability at the current time point, Lactate t Indicates the current lactate concentration, EMG t Represents the current EMG fatigue index, T sleep Indicates the sleep duration of the previous day, T hydration Indicates the water replenishment status of the previous day; If mild fatigue is reached, the athlete performs aerobic activities, replenishes water and electrolytes; If moderate fatigue is reached, athletes perform restorative stretching, massage, and adequate sleep; If severe fatigue is reached, the athlete will undergo a 48-72 hour recovery period, using relaxation meditation, hot compresses, or cold compresses.

10. The athlete fatigue recovery auxiliary system based on biofeedback according to claim 1, characterized in that: Regularly evaluate the recovery of athletes, provide feedback based on physiological signals and athletic performance, update recovery strategies, use athlete performance as an evaluation indicator, and evaluate recovery effectiveness, including: The recovery effect E(t) is a comprehensive evaluation based on physiological signals and exercise performance, expressed by the following formula: E(t)=α·HRV(t)+β·Lactate(t)+γ·EMG(t)+δ·Performance(t) Among them, HRV(t) represents the current HRV level, Lactate(t) represents the current lactate concentration, EMG(t) represents the current electromyography signal, Performance(t) represents the current sports performance, α, β, γ are weight coefficients, which are adjusted according to the individual differences of different athletes and recovery goals; The recovery strategy is determined according to the value of E(t): If E(t)>0.8, it means recovery is good and training intensity can be gradually increased; If E(t)<0.5, it means that the recovery is insufficient and the recovery time should be increased; If E(t) is between 0.5 and 0.8, it indicates moderate recovery and low-intensity recovery training should be performed.

Images