Intelligent motion test scheme generation method for smart campus

Abstract

The invention relates to the technical field of intelligent sports, and discloses an intelligent sports test scheme generation method for a smart campus, comprising the following steps: S1, collecting personal basic information and historical sports records of students, and establishing a personalized archive database; s2, constructing a physiological state space model by using a support vector machine algorithm based on the individual information and historical data of the students; s3, generating a personalized exercise test scheme according to the physiological state space model; s4, comparing the real-time physiological data with the target parameters in the testing process, and dynamically adjusting to optimize the training effect; and S5, after the test is finished, updating the student physiological state space model according to a test result. Through real-time feedback and dynamic optimization of the physiological state space model, an accurate and personalized exercise test scheme is realized, the test accuracy and safety are improved, and it is ensured that each student adjusts the exercise load according to the actual physiological reaction.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent sports, and specifically to an intelligent generation method for sports test schemes for smart campuses. Background Art

[0002] In the fields of modern education and health management, personalized sports test schemes are becoming increasingly important. When students conduct sports tests, traditional fixed exercise intensities and durations often fail to effectively take into account the physiological states of each student, resulting in significant differences in exercise effects. With the improvement of people's health awareness, how to accurately evaluate students' sports performance and physiological responses has become an increasingly urgent problem to be solved.

[0003] In the prior art, traditional sports test schemes usually adopt fixed test standards and conduct tests based on set exercise intensities and durations. These schemes are relatively simple and can, to a certain extent, measure students' physical fitness levels and help educational institutions conduct group health assessments. In addition, some technologies based on fixed physiological models can also provide basic exercise load suggestions for students, making sports tests have a certain degree of scientificity and systematicness.

[0004] However, there are still some deficiencies in the prior art; firstly, traditional methods cannot be adjusted in real time according to students' actual physiological responses during the test, and the setting of exercise loads does not consider the individual differences of each student, often resulting in overweight or underweight exercise loads and affecting the accuracy of test results; in addition, existing physiological data prediction models mostly rely on simple linear regression or experience-based formulas and cannot effectively handle complex non-linear relationships, resulting in low prediction accuracy; finally, the parameters of the model are usually static and are no longer adjusted once set, lacking an optimization mechanism for students' actual states. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides an intelligent generation method for sports test schemes for smart campuses, which solves the problem in the prior art that the exercise test load cannot be dynamically adjusted according to students' actual physiological responses.

[0006] To achieve the above object, the present invention is realized through the following technical solutions: An intelligent generation method for sports test schemes for smart campuses, including the following steps: S1. Collect students' personal basic information and historical sports records, and establish a personalized profile database; S2. Based on students' individual information and historical data, use the support vector machine algorithm to construct a physiological state space model; S3. Generate a personalized sports test scheme according to the physiological state space model, where the test scheme includes action types, action parameters, and intensity settings; S4. During the test, collect the physiological data of the student in real time and compare it with the target parameters, and make dynamic adjustments to optimize the training effect and ensure the safety of the student; S5. After the test, update the physiological state space model of the student according to the test results, so as to optimize the personalized exercise test plan in the next test.

[0007] Preferably, the physiological state space model is modeled based on the following data: Physiological state data of the student's heart rate, blood pressure, breathing rate and fatigue factor; Individual characteristic parameters of the student's maximum heart rate and heart rate recovery time; The student's past exercise records and health history information.

[0008] Preferably, the personalized profile database includes the following: The student's basic personal information, including gender, age, height, weight; The student's exercise history records, including past achievements, types of exercise and participation frequency; The student's health history records, including past sports injuries, cardiovascular conditions; The student's dynamic physiological data records for tracking the student's physical changes.

[0009] Preferably, the exercise test plan includes: The types of test actions, action duration and number of tests; Action intensity settings, including the intensity and duration of each action; Recovery period settings, including the rest time between each test.

[0010] Preferably, the dynamic adjustment includes: During the exercise test, collect the physiological state data of the student's heart rate, blood pressure, breathing rate and fatigue factor in real time, and compare it with the set target parameters; When the physiological data exceeds the safe range, immediately adjust the exercise intensity or pause the test to ensure the safety of the student; According to the real-time feedback data, adjust the test intensity and extend or shorten the test time to maximize the training effect.

[0011] Preferably, the steps for updating the physiological state space model of the student include: Collect the real-time data of the student during the test, including physiological reactions and completion; Compare the actual performance of the student with the predicted results and adjust the parameters in the physiological model; Adjust the test plan according to the latest state of the student and optimize the personalized settings for the next test.

[0012] Preferably, the optimized personalized exercise test plan includes: Analyze the students' exercise ability and physiological data through deep learning algorithms to automatically identify changes in the students' physical states; Adopt a neural network model to predict the students' exercise performance under different intensities, and recommend suitable exercise content and intensity in real time; During the test process, according to the students' physiological feedback, adjust the test content and intensity through reinforcement learning algorithms to optimize the personalization and dynamic optimization of the exercise plan.

[0013] Preferably, the physiological data collected in real time during the test process is collected by the following devices: Use a smart bracelet to collect data on the students' heart rate, blood pressure, respiratory rate, and fatigue factor; Use a heart rate monitor to collect data on the students' maximum heart rate and heart rate recovery time; Use a sphygmomanometer to measure blood pressure data in real time to obtain accurate blood pressure data.

[0014] The present invention provides a method for intelligently generating an exercise test plan for a smart campus. It has the following beneficial effects: 1. The present invention adopts a dynamic optimization technical solution based on real-time physiological data feedback, achieving the technical effect of being able to adjust the exercise test plan in real time. Compared with the fixed-mode exercise test plan in the prior art, the present invention solves the problem that the traditional method cannot flexibly adapt to the individual differences of students by adjusting the test intensity and duration according to the actual physiological reactions of students, making each test more personalized and accurate.

[0015] 2. The present invention adopts an optimization method combining a physiological state space model and a support vector machine regression model, achieving high accuracy in predicting students' physiological reactions under complex exercise loads. Compared with the prediction models that only rely on simple statistical methods in the prior art, the present invention better captures the complex relationship between exercise load and physiological reaction through non-linear kernel function processing, effectively improving the prediction accuracy of the model.

[0016] 3. The present invention adopts a feedback mechanism to update the model parameters in real time, achieving the technical effect of gradually improving the model's prediction ability. Compared with the practice of fixing model parameters in traditional technologies, the present invention not only optimizes the model's prediction ability in the short term by dynamically adjusting the data of each test, but also avoids the limitation of over-relying on prior data, realizing continuous optimization within a long time period.

[0017] 4. The present invention adopts a personalized parameter adjustment strategy, achieving the technical effect of reducing the risk of overload and ensuring the safety of students. Different from the unified exercise load settings in the prior art, the present invention dynamically adjusts the exercise intensity based on the physiological data of each student, thereby avoiding potential health risks caused by excessive or insufficient load during the exercise test. Brief Description of the Drawings

[0018] Figure 1 It is a flowchart of the method of the present invention. Detailed Embodiments

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the specification of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0020] Please refer to the attached Figure 1 , the embodiment of the present invention provides an intelligent generation method for an exercise test plan for a smart campus, including the following steps: S1. Collect the personal basic information and historical exercise records of students, and establish a personalized profile database; The purpose of S1 is to establish a personalized profile database by comprehensively collecting the personal basic information, historical exercise records and health status of students, providing sufficient data support for the establishment of the physiological state space model and the generation of personalized exercise test plans in the subsequent steps. The establishment of the database not only depends on the basic information of students, but also needs to cover the exercise history and health data of students, which will help to ensure that the exercise test plans customized for each student are both challenging and in line with their individual differences.

[0021] In this process, the student data that the system needs to obtain includes not only the basic personal information of students, but also detailed exercise records such as students' historical exercise performance, exercise frequency, exercise items and intensity. These data provide the necessary basis for the system to calculate the exercise load and construct the physiological model in the future.

[0022] In the implementation process, the personal basic information of students usually comes from the registration form filled in when students enter school or the student status management system. The system obtains information such as students' names, genders, ages, heights, weights, etc., providing preliminary data for the generation of subsequent plans.

[0023] As an option, students' health information, such as whether they have had chronic diseases, sports injuries, etc., can also be supplemented through health records provided by parents or physical education teachers. These health data are crucial for formulating personalized exercise test plans because they can help the system evaluate students' risks during exercise and adjust the intensity and content of the test accordingly.

[0024] In this embodiment, students' historical exercise records are mainly collected by the school's physical education department or smart hardware devices. For example, devices such as smart bracelets and heart rate monitors can collect physiological data such as students' heart rate, exercise duration, exercise intensity, and types of exercise events in real time. Through these data, the system can evaluate students' past exercise abilities and thus provide support for generating subsequent exercise test plans.

[0025] Types of exercise events: The specific types of exercise that students participate in, such as running, swimming, strength training, yoga, etc.

[0026] Exercise intensity: The intensity settings for each exercise can be classified as low, medium, and high intensity, or quantified through specific measurement standards such as watts (W), times per minute, etc.

[0027] Exercise duration and frequency: The duration of each exercise (unit: minutes), and the frequency of students' participation in exercise (such as the number of times per week).

[0028] Through these historical exercise records, the system can not only understand students' basic exercise performance but also evaluate their endurance, strength, recovery ability, etc. based on factors such as exercise intensity and duration.

[0029] In addition to basic information and exercise records, the system also needs to collect students' health history records to provide more accurate guidance for personalized exercise test plans. These health records can be collected through the school's school doctor or health management system, specifically including: History of sports injuries: Record whether students have a history of sports-related injuries (such as knee injuries, muscle strains, etc.) to avoid overloading when generating exercise test plans.

[0030] Cardiovascular status: Cardiovascular data such as students' blood pressure and heart rate are very important for evaluating exercise intensity.

[0031] Chronic diseases: For example, whether students have chronic diseases such as diabetes and asthma, which will affect the setting of exercise loads.

[0032] The system can also collect real-time physiological data through smart devices, such as heart rate and blood pressure during exercise, to continuously track students' physiological changes. These data help build a dynamic personalized exercise profile.

[0033] Based on the collected personal information, exercise records, and health data of students, the system needs to design a structured database to store and manage this data. Generally, a relational database design is adopted, which includes the following main data tables: Student Basic Information Table: This table records basic data such as students' names, genders, ages, heights, weights, and health status. The student ID is used as the unique identifier.

[0034] Field examples: Student ID; Name; Gender; Age; Height (unit: cm); Weight (unit: kg); Health status (such as no chronic diseases, previous sports injuries, etc.); Exercise History Record Table: This table records information such as the sports events students participated in, exercise intensity, duration, and exercise performance.

[0035] Field examples: Student ID; Sports event (such as running, swimming, etc.); Exercise intensity (low, medium, high); Exercise duration (unit: minutes); Exercise performance (such as running time, number of push-ups, etc.); Health History Record Table: Records students' health information, including sports injury history, chronic diseases, etc.

[0036] Field examples: Student ID; Sports injury history (such as no injury, knee injury, etc.); Cardiovascular condition (such as no problem, hypertension, etc.); Chronic diseases (such as diabetes, asthma, etc.); Physiological Data Table: Real-time collected physiological data, including heart rate, blood pressure, respiratory rate, etc.

[0037] Field examples: Student ID; Measurement time; Heart rate (unit: bpm); Blood pressure (unit: mmHg); Respiratory rate (unit: times / minute); After the data enters the database, the system also needs to preprocess and standardize the collected data. Data preprocessing includes removing missing values, handling outliers, etc. To avoid data inconsistency issues, the system needs to standardize data from different sources. For example, all physiological data is uniformly converted to standard units (such as blood pressure unified to mmHg, heart rate unified to bpm, etc.).

[0038] During the data processing stage, especially in the process of processing physiological data, the system may use some data normalization techniques. Generally, for different physiological data (such as heart rate, blood pressure, etc.), the system will perform normalization processing according to their dimensions to ensure that they have the same scale, thus avoiding some data having too much impact on subsequent modeling.

[0039] Step S1 provides comprehensive data support for the subsequent construction of the physiological model by collecting and organizing the student's personal basic information, historical exercise records, and health status in detail. The establishment of the personalized profile database can not only ensure that each student's exercise test plan conforms to their physiological characteristics, but also avoid overloading based on the student's historical data and health status, ensuring safety and effectiveness.

[0040] S2. Based on the student's individual information and historical data, use the support vector machine algorithm to construct a physiological state space model; In step S2, the system will use the support vector machine (SVM) algorithm to construct a physiological state space model based on the student's personal information, exercise history records, and health status data collected in step S1. The core goal of this step is to establish a mathematical model that can predict the student's physiological responses at different exercise intensities and durations by analyzing the student's physiological data and exercise records. This model can not only provide a basis for generating personalized exercise test plans, but also dynamically adjust the test plans, optimize the student's exercise effects, and ensure their safety.

[0041] Support vector machine (SVM) is a very powerful machine learning tool, usually used for classification problems and also widely used for regression problems. For the construction of the physiological state space model, SVM adopts a regression model, namely support vector regression (SVR). Through this model, the system can establish a non-linear relationship between factors such as exercise intensity, duration, etc. and physiological responses based on the student's historical exercise data and physiological responses. SVM can learn these complex relationships and map them to a high-dimensional space, where the optimal hyperplane is found for regression.

[0042] In this embodiment, the support vector machine is used to predict the student's physiological responses (such as heart rate changes, blood pressure, etc.) by inputting data such as exercise intensity and duration. This regression model realizes the efficient prediction of the student's physiological state by establishing the optimal fitting curve between samples.

[0043] Specifically, assume that the student has an exercise intensity of , an exercise duration of , and a maximum heart rate after exercise of . Then, the support vector machine regression model can model the relationship between exercise load and physiological response in the following form: ; where: is the physiological response (such as heart rate change, blood pressure, etc.) of the student at a given exercise intensity and exercise duration ; represents the number of support vectors; is an index representing the number of each training sample; is the Lagrange multiplier in the support vector machine, representing the weight of the support vector; is the kernel function used to calculate the similarity between data points and . Commonly used kernel functions include the radial basis kernel (RBF kernel) or the Gaussian kernel function. The kernel function helps map the data into a high-dimensional space, thus simplifying the non-linear regression problem; is the bias term that controls the output of the model and is usually determined by optimization during the learning process.

[0044] In this embodiment, the system first collects and organizes the historical exercise records and physiological data of the student. These data include the student's exercise intensity, exercise duration, maximum heart rate, blood pressure, recovery after exercise, etc. The system inputs these data as a training set into the support vector machine model and trains the model parameters through an optimization algorithm (such as the gradient descent method or the quadratic programming method). The purpose of training is to find the relationship between the exercise intensity and physiological response that is most suitable for the individual student, and then establish an accurate regression model.

[0045] Specifically, the training data set will contain physiological data such as heart rate and blood pressure of the student at different exercise intensities, and the model will learn the relationship between exercise intensity and physiological response. Through multiple iterations of optimization, the system can adjust kernel function parameters, regularization parameters, etc. until the model can minimize the prediction error and generate an optimal physiological state space model that best fits the data.

[0046] After the model training is completed, the system needs to verify the prediction accuracy of the model. Generally, the cross-validation method is adopted. By dividing the training set into several subsets, the model is tested and its prediction accuracy is calculated. Cross-validation can effectively avoid the overfitting problem and ensure the generalization ability of the model. During the verification process, if it is found that there is a large gap between the prediction results of the model and the actual physiological data, the system will optimize by adjusting the kernel function type or regularization parameter of the SVM model.

[0047] In a possible implementation, an independent test data set can also be used in the verification phase to test the effect of the model. This verification ensures the applicability and reliability of the model on different data sets.

[0048] After the model training is completed, the physiological state space model will be used to predict the physiological responses of students under different exercise intensities and durations. According to the trained model, the system can accurately predict physiological responses such as heart rate changes and blood pressure fluctuations of students under a given exercise load.

[0049] For example, assume the student has an exercise intensity set to medium intensity and an exercise duration set to 30 minutes. The physiological state space model predicts the maximum heart rate change of the student through the SVM algorithm. According to this prediction result, the system can adjust parameters such as exercise intensity and duration to ensure that the physiological responses of the student are within a safe range.

[0050] In the physiological state space model, the system may apply the following formula to calculate the exercise load and physiological responses of students to ensure the optimization of the personalized exercise test plan.

[0051] Assume the exercise intensity of the student is and the exercise duration is and the maximum heart rate is , then the exercise load of the student can be calculated through the following formula: ; Where: is the exercise load of the student , and the unit can be "times / minute" or "watt (W)". It represents the total load of the student under the given exercise intensity and duration; is the exercise intensity of the student , and the unit is times / minute or watt (W). It is usually set through the type of exercise item (such as running, swimming) and the intensity level (such as low intensity, medium intensity, high intensity); is the exercise duration of the student The duration of exercise, in minutes (min). Usually set by the test protocol, representing the duration of each exercise item; For students The maximum heart rate recorded for the student during the test, in beats per minute (bpm). The maximum heart rate is usually obtained from the highest heart rate value during the exercise test.

[0052] This formula quantifies the exercise load of the student by combining exercise intensity, duration, and maximum heart rate. In this way, the system can predict the exercise load and adjust the test protocol according to the actual physiological response to ensure the safety and effectiveness of training.

[0053] Through the support vector machine (SVM) regression model in step S2, the system can establish an accurate physiological state space model based on the student's exercise history data and physiological data. This model can predict the physiological response of the student under different exercise intensities, and thus provide a basis for the generation of personalized exercise test protocols.

[0054] S3. Generate a personalized exercise test protocol according to the physiological state space model, where the test protocol includes action type, action parameters, and intensity settings; In the aforementioned step S2, the system constructed a physiological state space model based on the student's individual information and historical data by using the support vector machine (SVM) algorithm. This model can accurately predict the physiological response of the student under different exercise intensities. Based on this physiological state space model, the main task of step S3 is to generate a personalized exercise test protocol. This protocol not only includes the type, duration, and intensity of exercise actions, but also needs to set key parameters such as the recovery period to ensure that the training protocol can fully improve the student's exercise ability while avoiding health risks caused by excessive exercise.

[0055] In this embodiment, the generation of the exercise test protocol depends on the prediction results provided by the physiological state space model. Specifically, based on the physiological response of the student predicted by the model under different exercise loads, the system will customize an exercise plan suitable for each student's physical fitness level. The plan will be designed according to the student's historical data, health status, and individual differences to ensure that the student can train within a safe and effective range.

[0056] First, the system selects the most suitable exercise items for the student according to the prediction results of the physiological state space model. Generally, the system will select exercise items according to the student's historical exercise records, health status, and individual physiological characteristics. For example, for students with higher exercise ability, the system may recommend high-intensity aerobic exercises (such as fast running, swimming, cycling, etc.); while for students with weaker exercise ability or health problems, the system will recommend low-intensity exercises (such as walking, yoga, etc.).

[0057] Next, the system determines the duration and number of repetitions of each exercise based on the physiological state and predicted physiological responses of each student. Generally, the system decides the exercise duration and number of repetitions according to the student's maximum heart rate, blood pressure, and recovery after exercise. For high-intensity exercises, the duration is shorter, while for low-intensity exercises, the duration can be appropriately extended to improve the student's endurance.

[0058] For example, if the model predicts that a student's heart rate will increase rapidly during high-intensity running, the system will accordingly reduce the duration of running; while for low-intensity walking, the system may set a longer exercise duration to help the student gradually improve endurance.

[0059] Exercise intensity is a crucial part of the test plan. The system sets the intensity of each exercise based on the prediction of the student's physiological data (such as heart rate, blood pressure, fatigue factor, etc.) by the physiological state space model. Generally, the exercise intensity is set according to the individual differences, historical exercise performance, and health status of the student.

[0060] The system uses the predicted physiological responses of the model to evaluate factors such as heart rate and blood pressure changes at different intensities. For example, when the system predicts that a student's heart rate will remain within a safe range during a certain exercise, the system can appropriately increase the exercise intensity. On the contrary, if the prediction shows that the intensity is too high, the system will automatically reduce the exercise intensity to ensure that the exercise is carried out within a healthy and safe range.

[0061] The recovery period is also an important part of the exercise test plan. The system calculates the recovery time based on the student's exercise intensity and physiological responses. For example, after high-intensity exercise, the system will recommend a longer recovery period so that the student can better recover physical strength. For low-intensity exercises, the recovery period can be set shorter to ensure the continuity of the exercise.

[0062] This step quantifies physiological data such as the student's exercise load, heart rate changes, and recovery period through the formula for calculating the student's exercise load disclosed in S2, thereby helping to generate a personalized exercise test plan.

[0063] The following formula can also be used to predict the heart rate changes of students during exercise to help optimize the exercise intensity: ; Where: is the predicted heart rate change of the student at a given exercise intensity and duration, in beats per minute (bpm); is the resting heart rate of the student in beats per minute (bpm); the exercise intensity of the student in "times per minute" or "watts (W)"; Student Duration of exercise, in minutes (min); For the student Maximum exercise load, in "times / minute" or "watts (W)".

[0064] This formula predicts the heart rate change during exercise based on the student's resting heart rate and exercise load. The system dynamically adjusts the exercise intensity based on this prediction result to ensure that the heart rate always remains within a healthy range.

[0065] The length of the recovery period is crucial for the student's exercise test plan. The system can calculate the recovery period according to the following formula : ; Where: Represents the recovery period of the student , in minutes (min); Is the exercise load of the student , defined previously; Is the maximum heart rate of the student , in beats per minute (bpm).

[0066] This formula helps the system determine the appropriate recovery period by combining the exercise load and the maximum heart rate, ensuring that the student can get sufficient rest after high-intensity exercise and avoiding over-fatigue.

[0067] After generating the preliminary exercise test plan, the system will also perform dynamic optimization based on the real-time data of the student during the test. Specifically, the system adjusts each test through the physiological data such as heart rate and blood pressure collected in real time. For example, if it is detected that the student's heart rate exceeds the safe range during exercise, the system will immediately adjust the exercise intensity or pause the test to ensure the safety of the student.

[0068] In a possible implementation, the system will further adjust the test content and intensity according to the student's feedback (such as fatigue, exercise completion, etc.) to maximize the training effect and avoid any risks during training.

[0069] Step S3 is based on the prediction result of the physiological state space model. This plan includes multiple elements such as action type, intensity, duration, recovery period, etc., and fully considers the individual differences, exercise ability and health status of each student. Through dynamic adjustment and personalized optimization, the system ensures the efficiency and safety of training, thus providing a comprehensive and scientific exercise test plan for students.

[0070] S4. During the test, the physiological data of the students is collected in real time and compared with the target parameters, and dynamic adjustment is carried out to optimize the training effect and ensure the safety of the students; The core of step S4 is to dynamically adjust the exercise intensity, duration and recovery period through real-time physiological data collection and comparison with target parameters. This process is based on the data collected by intelligent hardware devices (such as smart bracelets, heart rate monitors, blood pressure monitors, etc.) and physiological feedback mechanisms to optimize the exercise test in real time, ensuring that the physiological state of the students remains within a healthy range during the training process.

[0071] In this embodiment, real-time physiological data collection is achieved through a variety of intelligent devices. These devices can continuously monitor physiological data such as the heart rate, blood pressure, respiratory rate, and fatigue factor of the students. Specifically, the key physiological data monitored by the system includes but is not limited to: Heart rate (HR): The heart rate of the student during exercise, in beats per minute (bpm). Heart rate is an important indicator reflecting exercise intensity and fatigue level.

[0072] Blood pressure (BP): The blood pressure data of the student, in mmHg (millimeters of mercury). Blood pressure reflects the changes in blood circulation during exercise, and too high or too low blood pressure indicates excessive exercise load.

[0073] Respiratory rate (BR): The number of breaths per unit time, in breaths per minute. Respiratory rate reflects the respiratory state of the student during exercise and is usually directly related to exercise intensity.

[0074] Fatigue factor (TF): A factor that synthesizes physiological data and reflects the fatigue level of the student during exercise. Usually, it is calculated by synthesizing factors such as heart rate and blood pressure.

[0075] These data will be transmitted to the system in real time through intelligent devices for real-time analysis and dynamic adjustment by the system. By comparing the real-time data with the target parameters, the system can determine whether the student needs to reduce the exercise intensity or increase the rest time to ensure that the student does not exercise overload.

[0076] During the test, the system compares the physiological data collected in real time with the preset target parameters. The target parameters are set according to the physiological state space model and personalized profile database of the students and usually include the following: Target heart rate range: Usually calculated based on the maximum heart rate of the student. The target heart rate range is used to ensure that the heart rate of the student does not become too high or too low during exercise.

[0077] Target blood pressure range: Set the upper and lower limits of blood pressure according to the student's health history and exercise ability to ensure that the blood pressure is within a safe range during exercise.

[0078] Target respiratory rate range: The target range of respiratory rate is usually set according to the student's exercise intensity and ability to ensure that the student's respiratory rate during exercise is neither too fast nor too slow.

[0079] For example, assuming the target heart rate range for a student is 120 - 150 bpm, the system will monitor the student's heart rate in real time. If the student's heart rate exceeds this range, the system will adjust the exercise intensity or pause the test according to the following mechanism to ensure that the heart rate returns to the target range.

[0080] In this embodiment, the system will dynamically adjust the exercise intensity, duration, and recovery period based on real-time data to ensure that each student has an appropriate and safe exercise load. Specifically, the system will perform the following adjustments according to the student's heart rate, blood pressure, and other physiological responses: Exercise intensity adjustment: If the system detects that the student's heart rate exceeds the target range or the blood pressure is abnormal, the system will adjust the exercise intensity in real time. For example, when the student's heart rate is too high, the system will reduce the exercise intensity, which can help the student return to the normal range by slowing down running or reducing other exercise intensities.

[0081] Exercise duration adjustment: If data such as the student's heart rate and blood pressure exceed the preset safety range, the system may reduce the exercise duration. For example, the system will reduce the running time to avoid risks caused by the student's excessive fatigue; for relatively easy exercises, the system can extend the duration to enhance the student's endurance.

[0082] Recovery period adjustment: According to the student's physiological state and exercise intensity, the system will dynamically adjust the recovery period after each exercise. The recovery period after high-intensity exercise is generally longer, while low-intensity exercise may require a shorter recovery period. The system determines whether to extend the recovery period by monitoring the student's heart rate recovery rate. If the student's heart rate fails to quickly return to the target heart rate range after rest, the system will extend the recovery time. This step quantifies physiological data such as the student's exercise load, heart rate changes, and recovery period through the formula for calculating the student's exercise load disclosed in S2, in order to customize a suitable exercise intensity for each student.

[0083] It also uses the formula for predicting the heart rate change during exercise and the formula for calculating the recovery period disclosed in S3 to be able to dynamically adjust the exercise plan according to the prediction results, ensure that the student's heart rate is always within the safe range, and at the same time ensure that the student can get sufficient rest after high-intensity exercise to avoid excessive fatigue.

[0084] Step S4 ensures that parameters such as exercise intensity, duration, and recovery period can be dynamically adjusted according to real-time feedback during the test by collecting the student's physiological data in real time and comparing it with the target parameters.

[0085] S5. After the test, update the student's physiological state space model according to the test results to optimize the personalized exercise test plan for the next test; The core objective of step S5 is to compare the actual data collected during the test with the model prediction results by analyzing the results of each test, and adjust the parameters of the physiological state space model according to the feedback. Through continuous updating and optimization, the system can provide a more accurate and personalized exercise test plan for each subsequent test.

[0086] After each exercise test, the system will collect the actual physiological data of the students during the test, including indicators such as heart rate, blood pressure, respiratory rate, and exercise performance. Then, the system will compare these actual data with the prediction results of the physiological state space model and calculate the difference between the predicted value and the actual value. Specifically, the test results include the following aspects: Actual heart rate: Record the actual heart rate of the student during the test, in beats per minute (bpm).

[0087] Actual blood pressure: Record the actual blood pressure data of the student during the test, in mmHg.

[0088] Actual respiratory rate: Record the actual respiratory rate of the student during exercise, in breaths per minute.

[0089] These data will be input into the system and compared with the pre-set target parameters. If there is a large deviation between the actual data in the test and the results predicted by the model, the system will use this feedback information to adjust the relevant parameters of the model, thereby improving the prediction accuracy of the model and providing more reliable data support for subsequent tests.

[0090] In this embodiment, the system updates the parameters of the physiological state space model through the following steps to ensure that the next test plan can more accurately adapt to the actual physiological state of the student: During the test, the system will calculate the adjustment value by comparing the error between the actual heart rate, blood pressure, etc. and the results predicted by the physiological state space model. Assume the student During a certain test, the actual heart rate is , and the heart rate predicted by the model is , then the error can be calculated by the following formula: ; Where: represents the difference between the actual heart rate and the predicted heart rate of the student during this test; is the student The actual heart rate during the test, in beats per minute (bpm); is the heart rate of the student predicted by the system during the test, in beats per minute (bpm).

[0091] By calculating this error, the system can understand the bias existing in the model during the prediction process and adjust the parameters of the model based on these biases. By gradually adjusting the model parameters, the system can improve the accuracy of the prediction in the next exercise test.

[0092] By calculating the error, the system can update the parameters in the physiological state space model according to the following formula. Assume that the system needs to adjust the parameters related to the exercise intensity in the physiological model, then the update formula is: ; where: represents the adjustment value of the parameter in the model; is the learning rate, controlling the amplitude of each update; is the student the difference between the actual heart rate and the predicted heart rate during the test.

[0093] The function of this formula is to adjust the parameters of the model through error feedback so that the system can more accurately predict the physiological response of the student in the next test. By continuously adjusting the parameters, the system can gradually optimize the physiological state space model, making the personalized plan for each exercise test more accurate.

[0094] After updating the parameter , the system will optimize the next exercise test plan by adjusting other parameters in the physiological state space model (such as exercise intensity, exercise duration, recovery period, etc.). In this way, the system can not only improve the prediction ability of the physiological model, but also accurately reflect the physiological state of the student in the test plan, ensuring that each test can provide the most suitable personalized exercise plan for the student.

[0095] For example, assume that the student failed to reach the expected exercise intensity in the previous test. After updating the model parameters, the system can provide a more appropriate exercise intensity for this student, avoiding excessive or insufficient load, thereby improving the exercise effect.

[0096] After the parameter update is completed, the system will use the new physiological state space model to generate the next exercise test plan. The updated model will readjust test parameters such as exercise intensity, duration, and recovery period according to the student's latest physiological data, health status, and exercise performance. For example, the updated model may increase the student's exercise intensity or extend the exercise duration to further enhance the training effect; at the same time, the system may also extend the recovery period to ensure that the student's physiological state is fully restored.

[0097] To ensure that the system can dynamically optimize the physiological state space model, the following formula is the system parameter update formula: ; Where: is the adjustment amount of the th parameter in the physiological state space model ; is the learning rate, which controls the step size or amplitude of each model parameter adjustment; is the actual heart rate of the student during the test, in beats per minute (bpm); is the heart rate of the student predicted by the system during the test, in beats per minute (bpm).

[0098] This formula optimizes the prediction ability of the model by calculating the error and adjusting the model parameters according to the learning rate.

[0099] By gradually adjusting each parameter in the model, the system can dynamically optimize the physiological state space model and generate a new personalized exercise test plan based on the updated model.

[0100] In step S5, by comparing the actual physiological data and predicted data of the student during the test, the system can dynamically adjust the model parameters and optimize the next personalized exercise test plan. Through this adaptive optimization process, the system can improve the prediction accuracy in continuous iterations, ensuring that each exercise test can maximize the training effect and maintain the safety of the student.

[0101] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent generation method for a motion test scheme for a smart campus, characterized in that: The following steps are involved: S1. Collect students’ basic personal information and historical sports records to establish a personalized archive database; S2, based on the students’ individual information and historical data, the support vector machine algorithm was used to construct the physiological state space model; S3, generating a personalized exercise test plan according to the physiological state space model, wherein the test plan includes action type, action parameters and intensity setting; S4. During the test, students’ physiological data is collected in real time and compared with target parameters, and dynamic adjustments are made to optimize the training effect and ensure student safety; S5. After the test, the student's physiological state space model is updated according to the test results so as to optimize the personalized exercise test plan in the next test.

2. The method for intelligently generating a sports test plan for a smart campus according to claim 1, characterized in that: The physiological state space model is modeled based on the following data: Physiological status data of students’ heart rate, blood pressure, respiratory rate and fatigue factor; Individual characteristic parameters of students’ maximum heart rate and heart rate recovery time; The student's past athletic records and health history information.

3. The intelligent generation method of sports test scheme for smart campus according to claim 1 is characterized in that: The personalized archive database includes the following contents: Students’ basic personal information, including gender, age, height, and weight; The student's athletic history, including past performance, types of sports, and frequency of participation; The student’s health history, including past sports injuries and cardiovascular conditions; The students' dynamic physiological data record is used to track their physical changes.

4. The method for intelligently generating a motion test scheme for a smart campus according to claim 1, characterized in that: The exercise testing protocol includes: Type of test action, duration of action and number of tests; Action intensity settings, including the intensity and duration of each action; Recovery period settings, including rest time between each test.

5. The method for intelligently generating a motion test scheme for a smart campus according to claim 1, characterized in that: The dynamic adjustment includes: During the exercise test, the students' physiological status data of heart rate, blood pressure, respiratory rate and fatigue factor are collected in real time and compared with the set target parameters; When physiological data exceeds the safe range, immediately adjust the exercise intensity or suspend the test to ensure the safety of students; Based on real-time feedback data, adjust the test intensity and extend or shorten the test time to maximize the training effect.

6. The intelligent generation method of sports test scheme for smart campus according to claim 1 is characterized in that: The step of updating the student's physiological state space model comprises: Collect real-time data from students during the test, including physiological responses and completion; Compare students’ actual performance with predicted results and adjust parameters in the physiological model; Adjust the test plan according to the students' latest status and optimize the personalized settings for the next test.

7. The method for intelligently generating a sports test plan for a smart campus according to claim 1, characterized in that: The optimized personalized exercise test program includes: Analyze students' athletic ability and physiological data through deep learning algorithms to automatically identify changes in students' physical conditions; Use neural network models to predict students' sports performance at different intensities and recommend appropriate sports content and intensity in real time; During the test, the test content and intensity are adjusted based on the students' physiological feedback through reinforcement learning algorithms to optimize the personalization and dynamic optimization of the exercise plan.

8. The method for intelligently generating a sports test plan for a smart campus according to claim 1, characterized in that: The physiological data collected in real time during the test is collected by the following equipment: Use smart bracelets to collect data on students’ heart rate, blood pressure, respiratory rate, and fatigue factor; Use a heart rate monitor to collect data on students’ maximum heart rate and heart rate recovery time; Use a sphygmomanometer to measure blood pressure data in real time to obtain accurate blood pressure data.

Images