Leisure physical exercise physical fitness test auxiliary method based on intelligent equipment

Abstract

The invention discloses a leisure physical exercise physical fitness test auxiliary method based on intelligent equipment, and relates to the technical field of physical fitness test, and the method comprises the following steps: firstly, collecting heart rate data of a user in exercise in real time through an intelligent heart rate monitoring chest strap, and preprocessing the obtained original heart rate data; the heart rate data is collected and preprocessed in real time, noise interference is eliminated, and the data accuracy is ensured; a data set is constructed and key motion features are extracted, so that the motion state distinguishing capability is improved; a machine learning model is utilized to intelligently evaluate the motion state, the sensitivity of the sensor is dynamically adjusted, and misjudgment is avoided. According to the method, the accuracy of the intelligent heart rate monitoring chest strap is improved, the sporter is helped to optimize training based on reliable data, unnecessary exercise adjustment or premature rest is avoided, the exercise efficiency is improved, and the health risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of physical fitness testing, and particularly to a method for assisting physical fitness testing of leisure sports based on intelligent devices. Background Art

[0002] The assistance of physical fitness testing for leisure sports based on intelligent devices refers to the use of intelligent devices (such as smartwatches, fitness trackers, smart treadmills, etc.) to assist in the physical fitness testing and evaluation during leisure sports activities. These intelligent devices can collect real-time physiological data of the exerciser, such as heart rate, step frequency, exercise intensity, calorie consumption, sleep quality, etc., and analyze these data using intelligent algorithms, thereby helping users comprehensively understand their physical fitness status. Through data feedback, users can adjust their exercise plans according to the test results to ensure more scientific and efficient training. Intelligent devices can also provide personalized suggestions and continuous tracking by connecting to a mobile APP or cloud platform, improving the quality and effect of leisure sports.

[0003] An intelligent heart rate monitoring chest strap is a device worn on the chest, usually consisting of a strap with a sensor and a receiver, specifically used to monitor and record the heart rate of the wearer in real time. Compared with wrist-mounted heart rate monitoring devices, the chest strap can capture the electrical activity of the heart more accurately because it is closely attached to the chest, avoiding data errors caused by changes in wrist position or movement. The intelligent heart rate monitoring chest strap can provide high-precision heart rate data, display the exercise intensity in real time, and help the exerciser stay in the optimal exercise zone according to their personal heart rate range to improve the exercise effect and prevent over-exercise. It is commonly used in sports such as running and cycling and is suitable for assisting in the physical fitness testing of leisure sports. By cooperating with sports equipment or mobile applications, the intelligent chest strap can help analyze the heart rate changes of the exerciser, evaluate the physical fitness level, and formulate a more personalized exercise plan. Therefore, the intelligent heart rate monitoring chest strap is an effective tool for physical fitness testing of leisure sports, which can help users more scientifically control the exercise intensity and optimize the exercise effect.

[0004] The prior art has the following deficiencies: In the prior art of intelligent heart rate monitoring chest straps, the sensitivity is usually set relatively high to enhance the device's response ability to cardiac electrical activity, so as to more accurately capture heart rate fluctuations, especially during strenuous exercise. The higher sensitivity can ensure that the sensor detects minute changes in the electrocardiogram signal, avoid missed detections, and guarantee the accuracy of heart rate data. However, excessively high sensitivity may also cause vibrations or body position changes during exercise to be misjudged as heart rate fluctuations, falsely indicating a heart rate higher than the actual level. This false high heart rate data may prompt the exerciser to prematurely adjust the exercise intensity or rest, believing that they have reached a state of over-exercise. Prolonged incorrect adjustments may lead to excessive fatigue, decreased physical fitness, missed optimal training effects, and even a decline in cardiac adaptability due to improper rest or premature cessation of exercise, increasing the risk of future heart problems.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide an auxiliary method for physical fitness testing of leisure sports based on intelligent devices. By real-time collecting and preprocessing heart rate data, noise interference is eliminated to ensure data accuracy; a data set is constructed and key motion features are extracted to improve the ability to distinguish motion states; a machine learning model is used to intelligently evaluate the motion state and dynamically adjust the sensor sensitivity to avoid misjudgment. This method improves the accuracy of intelligent heart rate monitoring chest straps, helps exercisers optimize training based on reliable data, avoids unnecessary exercise adjustments or premature rest, improves exercise efficiency and reduces health risks, so as to solve the problems in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solution: An auxiliary method for physical fitness testing of leisure sports based on intelligent devices, comprising the following steps:

[0008] First, the intelligent heart rate monitoring chest strap is used to real-time collect the heart rate data of the user during exercise, and the obtained original heart rate data is preprocessed;

[0009] Based on the preprocessed data, a data set is constructed, the heart rate data and its characteristics in the motion state are collected, and the key characteristics reflecting that the user is in strenuous exercise are extracted from the data set, and the extracted key characteristics are further analyzed to distinguish the motion state of the user;

[0010] The analyzed key characteristics are input into a pre-trained machine learning model, and the machine learning model is used to intelligently evaluate the motion state of the user to determine whether the user is in a state of strenuous exercise;

[0011] When the machine learning model determines that the user is in a strenuous exercise state, dynamically adjust the sensor sensitivity to reduce overreaction to the minute vibrations and postural changes caused by movement.

[0012] Preferably, extract key features reflecting the user's strenuous exercise from the data set, including the frequency of the heart rate reaching the maximum peak and the degree of deviation of the current heart rate from the normal resting heart rate. Further analyze the extracted frequency of the heart rate reaching the maximum peak and the degree of deviation of the current heart rate from the normal resting heart rate under the detection window, and generate a heart rate maximum peak reference value and a heart rate deviation degree reference value respectively. Quantify the frequency of the heart rate reaching the maximum peak through the heart rate maximum peak reference value, and quantify the degree of deviation between the current heart rate and the normal resting heart rate through the heart rate deviation degree reference value.

[0013] Preferably, the specific steps for analyzing the frequency of the heart rate reaching the maximum peak under the detection window to generate a heart rate maximum peak reference value are as follows:

[0014] First, process the heart rate data to find all the moments when the heart rate reaches the maximum peak. In this process, identify all the heart rate high peaks from the continuous heart rate data. For each peak occurrence moment, record the heart rate value at the current moment and count the frequency of these peaks. The calculation expression is as follows:

[0015] ,

[0016] In the formula, P k is the number of times the heart rate reaches the maximum peak within the detection window, n is the total number of time points in the detection window, HR i is the heart rate data at the i-th moment, HR max is the theoretical maximum heart rate, and δ is the threshold value representing the tolerance between the heart rate and the maximum heart rate;

[0017] After detecting the maximum peak frequency within the detection window, generate a heart rate maximum peak reference value according to the obtained data to quantify the relationship between the frequency of the maximum peak and the user's current exercise intensity. The calculation expression is as follows:

[0018] ,

[0019] In the formula, HR MA is the heart rate maximum peak reference value, and w i is the weight coefficient at each time point.

[0020] Preferably, the specific steps for analyzing the degree of deviation between the current heart rate and the normal resting heart rate under the detection window to generate a heart rate deviation degree reference value are as follows:

[0021] First, calculate the deviation degree between the current heart rate and the normal resting heart rate. Obtain the user's current heart rate value through real-time monitoring and the normal resting heart rate preset based on individual physiological data. The calculation is expressed as follows:

[0022] ,

[0023] In the formula, HR deviation is the heart rate deviation degree, HR current is the current heart rate data, and HR rest is the preset resting heart rate;

[0024] After obtaining the heart rate deviation degree HR deviation , convert the deviation degree into a heart rate deviation degree reference value to intuitively reflect the strenuous exercise state. The formula is as follows:

[0025] ,

[0026] In the formula, HR DX is the heart rate deviation degree reference value, and e is the natural base.

[0027] Preferably, input the analyzed maximum heart rate peak reference value and heart rate deviation degree reference value into a pre-trained machine learning model. Generate a motion intensity coefficient through the machine learning model, and use the motion intensity coefficient to intelligently evaluate the user's exercise state to determine whether the user is in a strenuous exercise state.

[0028] Preferably, compare and analyze the motion intensity coefficient generated when the pre-trained machine learning model intelligently evaluates the user's exercise state with the preset motion intensity coefficient reference threshold to determine whether the user is in a strenuous exercise state. The specific steps are as follows:

[0029] If the motion intensity coefficient is greater than the preset motion intensity coefficient reference threshold, it is determined that the user is currently in a strenuous exercise state; if the motion intensity coefficient is less than or equal to the preset motion intensity coefficient reference threshold, it is determined that the user is not currently in a strenuous exercise state.

[0030] Preferably, when the machine learning model determines that the user is in a strenuous exercise state, dynamically adjust the sensor sensitivity to reduce the overreaction to the small vibrations and posture changes caused by exercise. The specific steps are as follows:

[0031] First, analyze the user's heart rate data, and combine the motion intensity coefficient EI to evaluate the current exercise state. When it is determined that the user is in a strenuous exercise state, introduce a dynamic adjustment coefficient to guide the adjustment of sensitivity to ensure that the adjustment of sensitivity can adapt to the current exercise. The calculation expression is as follows:

[0032] ,

[0033] In the formula, ΔS adj is the dynamic adjustment coefficient, EI ref is the reference threshold of the exercise intensity coefficient, γ1 is the proportionality factor used to adjust the adjustment range of the sensitivity, γ2 is the basic reduction parameter, and β is the non-linear adjustment index;

[0034] After obtaining the dynamic adjustment coefficient ΔS adj the sensitivity of the sensor is dynamically adjusted through the dynamic adjustment coefficient ΔS adj to reduce the interference of the minute vibrations and postural changes caused by movement on the heart rate data. The calculation formula for the sensitivity adjustment is as follows:

[0035] S new = S base ·exp(-α·ΔS adj )

[0036] , where S new is the adjusted sensor sensitivity, S base is the basic sensitivity, and α is the sensitivity adjustment rate.

[0037] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0038] The present invention preprocesses the heart rate data by real-time acquisition to eliminate noise interference and ensure the accuracy of the data; constructs a data set and extracts key motion features to improve the system's discrimination ability for the motion state; uses a pre-trained machine learning model for intelligent evaluation to achieve accurate motion state recognition; and when a violent motion state is detected, adaptively adjusts the sensor sensitivity to avoid misjudgment caused by too high sensitivity and ensure the authenticity and reliability of the heart rate monitoring data. This method effectively improves the accuracy of the intelligent heart rate monitoring chest strap, enables the exerciser to optimize the training plan based on more reliable physiological data, avoids unnecessary motion adjustments or premature rest caused by misjudgment, thereby improving the exercise efficiency, optimizing the exercise experience, and reducing the health risks brought by incorrect heart rate data during exercise. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0040] Figure 1 is the method flow chart of the leisure sports physical fitness test assistance method based on the intelligent device of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

[0042] The present invention provides a method for assisting in physical fitness testing of recreational sports based on intelligent devices as Figure 1 shown, comprising the following steps:

[0043] First, the heart rate data of the user during exercise is collected in real time through an intelligent heart rate monitoring chest strap, and the obtained original heart rate data is preprocessed;

[0044] The heart rate monitoring chest strap contacts the skin through electrode sensors, captures the electrical signals from the heart, and converts them into heart rate data. The core function of this step is to provide basic physiological data, reflecting the heart state of the exerciser. Through real-time monitoring, the system can continuously track the heart rate changes of the user, ensuring the timeliness and continuity of the data. This step provides the most basic information for subsequent analysis and processing, ensuring that the assessment of the exercise state has the latest and most accurate heart rate data.

[0045] The preprocessing process includes denoising, smoothing, and outlier detection, etc. Heart rate data is usually affected by external noise or irregular fluctuations during exercise, so it is necessary to filter out irrelevant noise information through algorithms. Common preprocessing methods include low-pass filtering, mean filtering, etc., which help to eliminate short-term signal fluctuations caused by strenuous exercise or device wearing problems. The goal of preprocessing is to correct the data into a more stable and accurate state, providing a cleaner data basis for subsequent feature extraction and machine learning analysis, ensuring the accuracy and availability of the data.

[0046] Based on the preprocessed data, a data set is constructed, collecting heart rate data and its features in the exercise state, extracting key features reflecting that the user is in strenuous exercise from the data set, and further analyzing the extracted key features to distinguish the exercise state of the user;

[0047] The data set will include heart rate data under different exercise intensities, different types of exercise (such as running, cycling, swimming, etc.) and different physiological states (such as fatigue, recovery, etc.). The establishment of the data set not only helps the system understand the change trend of heart rate under different exercise conditions, but also provides data required for training and verification for machine learning models. This process is crucial for subsequent identification of exercise states through machine learning models, and the diversity and integrity of the data will directly affect the accuracy and generalization ability of the model.

[0048] Extract key features from the data set that reflect the user's intense exercise, including the frequency of the heart rate reaching the maximum peak and the deviation of the current heart rate from the normal resting heart rate. Further analyze the extracted frequency of the heart rate reaching the maximum peak and the deviation of the current heart rate from the normal resting heart rate under the detection window to generate a reference value for the maximum heart rate peak and a reference value for the heart rate deviation degree respectively. Quantify the frequency of the heart rate reaching the maximum peak through the reference value for the maximum heart rate peak, and quantify the deviation degree between the current heart rate and the normal resting heart rate through the reference value for the heart rate deviation degree.

[0049] The frequent reaching of the maximum heart rate peak usually indicates that the user is currently in a state of intense exercise. The maximum peak of the heart rate is the highest heart rate that the heart can reach during exercise, which usually occurs during high-intensity activities such as short sprints, high-intensity interval training, or climbing slopes. During intense exercise, the body needs to quickly supply a large amount of oxygen and energy to the muscles, and the heart must beat faster to meet this demand, so the heart rate will rise rapidly and reach a peak. Especially when the heart rate reaches or approaches the maximum value multiple times within a short period, it indicates that the exerciser's body is under high-intensity load, and this load can usually only be maintained through intense exercise. The frequent fluctuation of the heart rate to the maximum peak reflects the continuous fluctuation of the exercise intensity, especially reflecting the characteristics of short-term high-intensity exercise. In this state, the rapid increase and frequent reaching of the maximum peak of the heart rate indicate the intensity of the exercise, which is usually related to the sharp increase in the body's oxygen demand and the reaction of lactic acid accumulation. Therefore, the frequent reaching of the maximum heart rate peak is an important indicator for evaluating whether the user is in intense exercise and can help judge the exercise intensity and the body's load situation.

[0050] The specific steps for analyzing the frequency of the heart rate reaching the maximum peak under the detection window to generate a reference value for the maximum heart rate peak are as follows:

[0051] First, process the heart rate data to find all the moments when the heart rate reaches the maximum peak. These maximum peaks usually appear in the high-intensity stage of exercise. In this process, identify all the high heart rate peaks from the continuous heart rate data, that is, the heart rate reaches the user's theoretical maximum heart rate within a certain time interval. When the heart rate approaches this maximum value within a certain time window, it is considered to have reached a peak. For each moment when the peak appears, record the heart rate value at the current moment and count the frequency of these peaks. The calculation formula is as follows:

[0052] ,

[0053] In the formula, P k is the number of times the heart rate reaches the maximum peak within the detection window, n is the total number of time points in the detection window, HR i is the heart rate data at the i-th moment, HR maxis the theoretical maximum heart rate, and δ is the threshold, representing the tolerance between the heart rate and the maximum heart rate;

[0054] By detecting the heart rate data within the detection window, identify and record each moment when the maximum heart rate peak is reached. By counting the frequency of these heart rates reaching the maximum peak, it provides the basic data for calculating the heart rate maximum peak index later.

[0055] After detecting the maximum peak frequency within the detection window, generate the heart rate maximum peak reference value based on the obtained data, quantifying the relationship between the frequency of the maximum peak and the user's current exercise intensity. The magnitude of the heart rate maximum peak reference value reflects the frequency of the heart rate reaching the maximum peak within a specific time. By weighting each peak moment, considering the influence of the exercise state on the heart rate fluctuation, the calculation expression is as follows:

[0056] ,

[0057] In the formula, HR MA is the heart rate maximum peak reference value, and w i is the weight coefficient at each time point, used to represent the relative influence degree of the heart rate fluctuation in different time periods.

[0058] The larger the heart rate maximum peak reference value generated by analyzing the frequency of the heart rate reaching the maximum peak under the detection window, usually means that the user is in a strenuous exercise state. The heart rate maximum peak reference value is obtained by analyzing the frequency of the heart rate reaching the maximum peak within the monitoring window. During strenuous exercise, the heart rate will frequently reach relatively high peaks, especially during high-intensity activities (such as sprints, interval training, or rapid hill climbing), the heart rate will rise rapidly and repeatedly reach the maximum value. This phenomenon reflects the body's response to high-intensity exercise, indicating that the user is under a relatively large exercise load and pressure. Therefore, the higher the heart rate maximum peak reference value, the greater the exercise intensity, and the closer the user's current exercise state is to strenuous exercise. On the contrary, when this reference value is relatively low, it indicates that the frequency of the heart rate peak appearance is less, usually meaning that the user's exercise intensity is relatively low, and may be in a mild exercise or resting state.

[0059] A significant deviation of the current heart rate from the normal resting heart rate usually indicates that the user is in a state of intense exercise. The resting heart rate represents the normal heart activity frequency of the body at rest. Generally, the resting heart rate range for adults is between 60 - 100 beats per minute. When the body starts intense exercise, the heart needs to deliver more oxygen and nutrients to the whole body to cope with the accelerated metabolic process, so the heart rate will increase significantly. Intense exercise causes the heart rate to increase rapidly, especially within a short period, and the heart rate may exceed twice or more of the usual resting heart rate. This large deviation reflects that the heart is quickly responding to the exercise demand and increasing blood circulation to support muscle activity. Compared with the resting heart rate, the heart rate during intense exercise rises faster and to a greater extent and remains at a higher level. By monitoring this change, the system can determine that the user is in a high-intensity exercise state. Especially during high-intensity interval training or endurance exercise, the greater the deviation of the heart rate, the higher the exercise intensity. Therefore, when the current heart rate significantly deviates from the normal resting heart rate, it can be almost certain that the user is performing intense exercise, and the system can dynamically adjust the exercise monitoring strategy based on this change.

[0060] The specific steps to analyze the deviation degree between the current heart rate and the normal resting heart rate under the detection window to generate a heart rate deviation reference value are as follows:

[0061] First, calculate the deviation degree between the current heart rate and the normal resting heart rate. Obtain the current heart rate value of the user through real-time monitoring and the normal resting heart rate preset based on individual physiological data (such as age, gender, health status, etc.). The calculation is expressed as follows:

[0062] ,

[0063] In the formula, HR deviation is the heart rate deviation, HR current is the current heart rate data, and HR rest is the preset resting heart rate;

[0064] By calculating the difference between the current heart rate and the resting heart rate, quantify the deviation degree of the heart rate. The purpose of this step is to obtain a basic heart rate deviation, reflecting the exercise intensity of the user. When the deviation degree is large, it indicates a high exercise intensity and an increased heart burden.

[0065] After obtaining the heart rate deviation HR deviation , convert the deviation degree into a heart rate deviation reference value to intuitively reflect the state of intense exercise. The formula is as follows:

[0066] ,

[0067] In the formula, HR DX is the heart rate deviation reference value, and e is the natural base.

[0068] Convert the heart rate deviation HR deviation into a heart rate deviation reference value HR DX . By introducing an exponential decay function, the change in the deviation is further amplified, enabling the reference value to more sensitively reflect the state of strenuous exercise. The larger the HR DX , the higher the exercise intensity, which helps accurately determine whether the user is in a state of strenuous exercise.

[0069] The larger the heart rate deviation reference value generated by analyzing the degree of deviation between the current heart rate and the normal resting heart rate under the detection window usually indicates that the user is currently in a state of strenuous exercise. The heart rate deviation reference value reflects the exercise intensity by measuring the difference between the current heart rate and the normal resting heart rate. When the user performs strenuous exercise, the heart needs to beat faster to supply more oxygen and nutrients to the muscles, resulting in a significant increase in heart rate. At this time, the heart rate will deviate significantly from the resting heart rate, and the heart rate deviation reference value will increase. Conversely, during light exercise or at rest, the difference between the heart rate and the resting heart rate is small, and the deviation reference value is low. Therefore, the larger the deviation reference value, the higher the exercise intensity, and the user is in a state of strenuous exercise; when the deviation reference value is small, it means that the heart rate is close to the resting state, the exercise intensity is low, and the user is not in a state of strenuous exercise.

[0070] Input the analyzed key features into a pre-trained machine learning model, and use the machine learning model to intelligently evaluate the user's exercise state to determine whether the user is in a state of strenuous exercise;

[0071] Input the analyzed maximum heart rate peak reference value and heart rate deviation reference value into a pre-trained machine learning model, generate an exercise intensity coefficient through the machine learning model, and use the exercise intensity coefficient to intelligently evaluate the user's exercise state to determine whether the user is in a state of strenuous exercise.

[0072] A pre-trained machine learning model refers to a model constructed through training with machine learning algorithms after collecting a large amount of motion data and related labels (such as exercise intensity, exercise status, etc.), which is used to analyze and predict the motion state. During the training process, the model will learn the heart rate change patterns and characteristics under different motion states. For example, the machine learning model will understand the heart rate change rules under different exercise intensities based on features such as the maximum heart rate peak reference value and the heart rate deviation reference value. When training the model, supervised learning algorithms (such as support vector machines, decision trees, random forests, neural networks, etc.) are usually used, and a large amount of labeled data is used to "teach" the model how to distinguish different motion states. The training dataset usually includes various exercise types (such as running, swimming, cycling, etc.) and heart rate data under different intensities. The rules learned by the model can help it make accurate predictions on new and unseen data.

[0073] In practical applications, the role of the pre-trained machine learning model is to process input features such as the analyzed maximum heart rate peak reference value and heart rate deviation reference value, and evaluate the exercise intensity of the exerciser according to the rules learned by the model. By parsing the input data, the model can generate an "exercise intensity coefficient", which quantifies the current exercise intensity of the exerciser. When the model evaluates a relatively high exercise intensity coefficient, it usually means that the user is in a relatively high-intensity exercise state, and vice versa for a low-intensity or resting state. Based on this evaluation, the system can intelligently judge whether the user is in a strenuous exercise state, thereby helping the user better understand their exercise intensity, adjust the training plan, and avoid excessive exercise or inappropriate training intensity. Through this machine learning model, intelligent sports monitoring devices can automatically analyze and predict the motion state, providing accurate and personalized exercise suggestions.

[0074] The machine learning model is not limited here, and any machine learning model that can comprehensively analyze the maximum heart rate peak reference value HR MA and the heart rate deviation reference value HR DX to generate an exercise intensity coefficient EI is acceptable. To implement the technical solution of the present invention, the present invention provides a specific implementation method;

[0075] The formula for generating the exercise intensity coefficient EI is as follows: EI = α1·HR MA +α2·HR DX , where α1 and α2 are the preset proportionality coefficients of the maximum heart rate peak reference value HR MA and the heart rate deviation reference value HR DX respectively, and both α1 and α2 are greater than 0.

[0076] The preset proportionality coefficients, α1 and α2 refer to when calculating the exercise intensity coefficient EI, which are used toMA and the heart rate deviation reference value HR DX The constant coefficients for weighting. Specifically, these coefficients determine the importance and influence degree of each heart rate parameter in the overall exercise intensity.

[0077] The role of these coefficients is to adjust the contribution degree of each factor to the exercise intensity calculation. By setting reasonable proportional coefficients, the model can balance the influence of the maximum heart rate and heart rate deviation on the exercise intensity according to the actual exercise data. Usually, α1 and α2 are preset through experimental research or expert experience, which helps the model more accurately reflect the relationship of heart rate changes under different exercise intensities.

[0078] The preset proportional coefficients allow the model to flexibly adjust the response to the maximum heart rate and heart rate deviation, making the calculation of exercise intensity more personalized and accurate. These coefficients ensure the reasonable weighting of each factor in calculating the exercise intensity, thus improving the accuracy and applicability of the model.

[0079] It can be seen from the exercise intensity coefficient that the larger the reference value of the maximum heart rate peak generated after analyzing the frequency of reaching the maximum heart rate peak under the detection window, and the larger the reference value of the heart rate deviation generated after analyzing the deviation degree of the current heart rate from the normal resting heart rate under the detection window, it indicates that the larger the exercise intensity coefficient generated when the pre-trained machine learning model intelligently evaluates the user's exercise state, indicating that the user is currently in a strenuous exercise state; on the contrary, it indicates that the user is not in a strenuous exercise state.

[0080] Compare and analyze the exercise intensity coefficient generated when the pre-trained machine learning model intelligently evaluates the user's exercise state with the preset exercise intensity coefficient reference threshold to determine whether the user is in a strenuous exercise state. The specific steps are as follows:

[0081] If the exercise intensity coefficient is greater than the preset exercise intensity coefficient reference threshold, it is judged that the user is currently in a strenuous exercise state; if the exercise intensity coefficient is less than or equal to the preset exercise intensity coefficient reference threshold, it is judged that the user is currently not in a strenuous exercise state.

[0082] When the machine learning model determines that the user is in a strenuous exercise state, dynamically adjust the sensor sensitivity to reduce the overreaction to the small vibrations and postural changes caused by exercise;

[0083] When the machine learning model determines that the user is in a strenuous exercise state, the main function of the step of dynamically adjusting the sensor sensitivity is to optimize the accuracy of heart rate monitoring and avoid misjudgment caused by excessive sensitivity. During strenuous exercise, the user's body will generate a large amount of vibration and posture changes, such as the foot vibration during running and the up-and-down fluctuation of the body during jumping. These small changes generated by the exercise may be misinterpreted by the sensors of the intelligent chest strap as heart rate fluctuations. Especially when the sensor sensitivity is set too high, the device may overreact to the signals generated by these non-heart activities, resulting in false heart rate data. For example, the vibration during strenuous exercise may be misjudged as a signal of abnormal heart, causing the device to wrongly display that the user has an abnormally high heart rate, and even leading to behaviors such as excessive rest or incorrect adjustment of exercise intensity.

[0084] By dynamically adjusting the sensitivity, when the machine learning model detects that the user enters a strenuous exercise state, the system will automatically reduce the sensor sensitivity, thereby reducing the response to these small vibrations and posture changes. At this time, the sensor mainly focuses on the real fluctuations of heart activities and ignores the non-heart signal interference caused by exercise. In this way, the device can more accurately capture the user's heart rate changes, provide real and reliable data, and thus help the user more scientifically adjust the exercise intensity and avoid unnecessary exercise adjustments caused by incorrect data. This not only improves the user experience of the device but also ensures the reliability of the data, ensuring that users can perform effective exercise management based on accurate physiological feedback.

[0085] When the machine learning model determines that the user is in a strenuous exercise state, the specific steps of dynamically adjusting the sensor sensitivity to reduce the overreaction to the small vibrations and posture changes caused by exercise are as follows:

[0086] First, analyze the user's heart rate data and combine the exercise intensity coefficient EI to evaluate the current exercise state. When it is determined that the user is in a strenuous exercise state, introduce a dynamic adjustment coefficient to guide the adjustment of sensitivity. The dynamic adjustment coefficient is calculated based on the deviation between the exercise intensity coefficient EI and the reference threshold of the exercise intensity coefficient to ensure that the adjustment of sensitivity can adapt to the current exercise. The calculation expression is as follows:

[0087] ,

[0088] In the formula, ΔS adj is the dynamic adjustment coefficient, EI ref is the reference threshold of the exercise intensity coefficient, γ1 is a proportionality factor used to adjust the adjustment amplitude of sensitivity, γ2 is a basic reduction parameter to ensure that the sensitivity will not be overly reduced, thereby ensuring the normal operation of the sensor in all states, and β is a non-linear adjustment exponent used to enhance the influence of high exercise intensity on the sensitivity adjustment, so that the system can more significantly reduce the sensitivity during strenuous exercise;

[0089] Evaluate the user's exercise intensity through a machine learning model and calculate the dynamic adjustment coefficient ΔS adj , providing a basis for subsequent sensitivity adjustment. This step is based on the relationship between the exercise intensity coefficient EI and the reference threshold EI ref to ensure that the sensitivity adjustment adapts to different exercise states, avoiding excessive interference and improving the accuracy of data.

[0090] After obtaining the dynamic adjustment coefficient ΔS adj , dynamically adjust the sensitivity of the sensor through the dynamic adjustment coefficient ΔS adj to reduce the interference of small vibrations and posture changes caused by exercise on heart rate data. The sensitivity adjustment calculation formula is as follows:

[0091] S new = S base ·exp(-α·ΔS adj )

[0092] , where S new is the adjusted sensor sensitivity, which is the new sensitivity value obtained to reduce the interference of small vibrations and posture changes caused by exercise, S base is the base sensitivity, and α is the sensitivity adjustment rate. By adjusting α, the system can control the rate of sensitivity reduction to ensure adaptation to different intensities of exercise.

[0093] Ensure that during strenuous exercise, the sensor sensitivity is intelligently adjusted according to the exercise intensity change, reducing the over-response to non-heart signals, thereby improving the accuracy of data. Through the exponential decay method, the sensitivity adjustment can gradually adapt to high-intensity exercise, reducing the impact of vibrations and posture changes, and ensuring that the device monitors heart rate data more stably and accurately during exercise.

[0094] The present invention preprocesses the real-time collected heart rate data to eliminate noise interference and ensure data accuracy; constructs a data set and extracts key exercise features to improve the system's discrimination ability for exercise states; uses a pre-trained machine learning model for intelligent evaluation to achieve accurate exercise state recognition; and when detecting a strenuous exercise state, adaptively adjusts the sensor sensitivity to avoid misjudgment caused by excessive sensitivity, ensuring the authenticity and reliability of heart rate monitoring data. This method effectively improves the accuracy of the intelligent heart rate monitoring chest strap, enabling athletes to optimize their training programs based on more reliable physiological data, avoiding unnecessary exercise adjustments or premature rest caused by misjudgment, thereby improving exercise efficiency, optimizing the exercise experience, and reducing the health risks brought by incorrect heart rate data during exercise.

[0095] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0096] Only some exemplary embodiments of the present invention have been described above by way of illustration. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0097] It should be noted that in this text, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of another identical element in the process, method, article or device comprising the element.

[0098] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution is prior or subsequent. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0099] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this text can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0100] 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 repeated here.

[0101] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or may be 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.

[0102] In addition, in each embodiment of the present application, each functional unit may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit.

[0103] As mentioned above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0104] Only some exemplary embodiments of the present invention have been described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. A method for assisting physical fitness testing in leisure sports based on intelligent equipment, characterized in that: The following steps are involved: First, the user's heart rate data during exercise is collected in real time through a smart heart rate monitoring chest strap, and the acquired raw heart rate data is preprocessed; Based on the preprocessed data, a data set is constructed to collect the heart rate data and its features in the exercise state, and key features reflecting the user's intense exercise are extracted from the data set, and the extracted key features are further analyzed to identify the user's exercise state; The analyzed key features are input into the pre-trained machine learning model, and the user's motion state is intelligently evaluated through the machine learning model to determine whether the user is in a strenuous running state; When the machine learning model determines that the user is in a state of strenuous exercise, it dynamically adjusts the sensor sensitivity to reduce over-reaction to tiny vibrations and posture changes caused by exercise.

2. The method for assisting the physical fitness test of leisure sports based on intelligent equipment according to claim 1, characterized in that: Key features reflecting that the user is in strenuous exercise are extracted from the data set, including the frequency of the heart rate reaching the maximum peak and the degree of deviation of the current heart rate from the normal resting heart rate. The extracted frequency of the heart rate reaching the maximum peak and the degree of deviation of the current heart rate from the normal resting heart rate are further analyzed under the detection window to generate a heart rate maximum peak reference value and a heart rate deviation reference value, respectively. The frequency of the heart rate reaching the maximum peak is quantified by the heart rate maximum peak reference value, and the degree of deviation between the current heart rate and the normal resting heart rate is quantified by the heart rate deviation reference value.

3. The method for assisting the physical fitness test of leisure sports based on intelligent equipment according to claim 2, characterized in that: The specific steps for analyzing the frequency at which the heart rate reaches the maximum peak value in the detection window to generate the maximum peak value reference value of the heart rate are as follows: First, the heart rate data is processed to find the moment when all heart rates reach the maximum peak. In this process, all the high heart rate peaks are identified from the continuous heart rate data. For each peak moment, the heart rate value at the current moment is recorded, and the frequency of these peaks is counted. The calculation expression is as follows: ， Where P k is the number of times the heart rate reaches the maximum peak in the detection window, n is the total number of time points in the detection window, HR i is the heart rate data at the i-th moment, HR max is the theoretical maximum heart rate, δ is the threshold, which indicates the tolerance between the heart rate and the maximum heart rate; After detecting the maximum peak frequency within the detection window, the maximum peak reference value of the heart rate is generated according to the acquired data to quantify the relationship between the maximum peak frequency and the user's current exercise intensity. The calculation expression is as follows: ， In the formula, HR MA is the maximum peak heart rate reference value, w i is the weight coefficient at each time point.

4. The method for assisting the physical fitness test of leisure sports based on intelligent equipment according to claim 2, characterized in that: The specific steps for analyzing the deviation between the current heart rate and the normal resting heart rate in the detection window to generate a heart rate deviation reference value are as follows: First, the deviation between the current heart rate and the normal resting heart rate is calculated. The user's current heart rate value and the normal resting heart rate pre-set based on individual physiological data are obtained through real-time monitoring. The calculation is expressed as follows: ， In the formula, HR deviation is the heart rate deviation, HR current is the current heart rate data, HR rest is the preset resting heart rate; Get heart rate deviation HR deviation Finally, the deviation is converted into a heart rate deviation reference value to intuitively reflect the state of intense exercise. The formula is as follows: ， In the formula, HR DX is the reference value of heart rate deviation, and e is the natural base.

5. The method for assisting the physical fitness test of leisure sports based on intelligent equipment according to claim 2, characterized in that: The analyzed maximum heart rate peak reference value and heart rate deviation reference value are input into a pre-trained machine learning model, and the exercise intensity coefficient is generated by the machine learning model. The user's exercise state is intelligently evaluated through the exercise intensity coefficient to determine whether the user is in a strenuous running state.

6. The method for assisting the physical fitness test of leisure sports based on intelligent equipment according to claim 5, characterized in that: The exercise intensity coefficient generated by the pre-trained machine learning model when intelligently evaluating the user's exercise state is compared and analyzed with the pre-set exercise intensity coefficient reference threshold to determine whether the user is in a strenuous running state. The specific steps are as follows: If the exercise intensity coefficient is greater than the preset exercise intensity coefficient reference threshold, it is determined that the user is currently in an intense running state; if the exercise intensity coefficient is less than or equal to the preset exercise intensity coefficient reference threshold, it is determined that the user is not currently in an intense running state.

7. The method for assisting the physical fitness test of leisure sports based on intelligent equipment according to claim 6, characterized in that: When the machine learning model determines that the user is in a state of intense exercise, the sensor sensitivity is dynamically adjusted to reduce overreaction to small vibrations and posture changes caused by exercise. The specific steps are as follows: First, the user's heart rate data is analyzed, and the current exercise state is evaluated in combination with the exercise intensity coefficient EI. When the user is determined to be in a state of intense exercise, a dynamic adjustment coefficient is introduced to guide the adjustment of sensitivity to ensure that the sensitivity adjustment can adapt to the current exercise. The calculation expression is as follows: ， In the formula, ΔS adj is the dynamic adjustment coefficient, EI ref is the reference threshold of the exercise intensity coefficient, γ1 is the proportional factor used to adjust the adjustment amplitude of the sensitivity, γ2 is the basic impairment parameter, and β is the nonlinear adjustment index; In order to obtain the dynamic adjustment coefficient ΔS adj After that, the coefficient ΔS is adjusted dynamically. adj Dynamically adjust the sensitivity of the sensor to reduce the interference of small vibrations and posture changes caused by exercise on the heart rate data. The sensitivity adjustment calculation formula is as follows: S new =S base ·exp(-α·ΔS adj ), In the formula, S new is the adjusted sensor sensitivity, S base is the base sensitivity and α is the sensitivity adjustment rate.

Images