Big data analysis-based college student sports course selection recommendation method

Abstract

The invention discloses a college student sports course selection recommendation method based on big data analysis, and relates to the technical field of data analysis, and the method comprises the steps: obtaining the physical measurement feature data of a jth student; acquiring course feature data of the ith physical education course; inputting the course feature data and the body measurement feature data into a pre-configured convolutional neural network to predict an estimated average heart rate interval when the jth student participates in the ith physical education course; according to the estimated heart rate interval and the standard heart rate interval, whether the ith physical education course is matched with the jth student or not is judged, and if yes, the ith physical education course serves as a first recommended physical education course selection course of the jth student; if not, i = i + 1; repeating the steps 1-4 until j is equal to N, and stopping circulation; according to the invention, full utilization of educational resources is guaranteed, and the risk of each student participating in the corresponding physical education course is minimized.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and specifically is a method for recommending physical education courses for college students based on big data analysis. Background Art

[0002] In the prior art, physical education course selection systems usually adopt a unified recommendation method, which fails to fully consider individual differences among students, such as physical condition, athletic ability, and course intensity. Such recommendation methods often lead to a mismatch between the recommended courses and students' actual needs, affecting exercise effects and students' enthusiasm for participation.

[0003] In addition, physical education courses usually have a limit on the number of participants, which leads to over-enrollment in some courses, while other courses may not fully utilize resources due to insufficient enrollment, resulting in uneven resource allocation. This phenomenon not only affects the reasonable arrangement of courses, but may also increase students' risk of sports injuries due to the mismatch between course intensity and students' physical fitness. Therefore, how to make personalized recommendations based on students' physical test data and course characteristics, and reasonably allocate course resources, has become a technical problem that needs to be urgently solved in the current physical education course selection system. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a method for recommending physical education courses for college students based on big data analysis.

[0005] To achieve the above objectives, the present invention provides a method for recommending physical education courses for college students based on big data analysis, comprising: Step 1: Obtain the physical test characteristic data of the jth student among the N students to be selected, where N and j are both integers greater than zero; Step 2: Obtain course feature data of the i-th physical education course among the M physical education courses to be recommended, where both M and i are integers greater than zero; Step 3: Input the course feature data of the i-th physical education course and the physical test feature data of the j-th student into the preconfigured convolutional neural network to predict the estimated average heart rate range of the j-th student when participating in the i-th physical education course; Step 4: Get the standard heart rate interval, and determine whether the i-th physical education course is suitable for the j-th student based on the estimated heart rate interval and the standard heart rate interval. If so, the i-th physical education course is recommended to the j-th student as the first recommended physical education elective course for the j-th student, and j=j+1 is set, and the process returns to step 1; if not, i=i+1 is set, and the process returns to step 2; Step 5: Repeat the above steps 1 to 4 until j=N, then stop the loop and get the first recommended physical education elective courses for all students.

[0006] Preferably, the physical measurement characteristic data include age, gender, blood pressure and cardiopulmonary health index; The method for obtaining the cardiopulmonary health index is as follows: Acquire cardiopulmonary function reflection characteristic data of the jth student, wherein the cardiopulmonary function reflection characteristic data includes body mass index, maximum oxygen uptake and resting heart rate; Substitute the cardiopulmonary function reflection characteristic data into the pre-built cardiopulmonary health quantitative model to obtain the cardiopulmonary health index of the jth student; The expression of the pre-built cardiopulmonary health quantification model is as follows: ; Where: is the cardiopulmonary health index, is the maximum oxygen uptake, is the resting heart rate, is the body mass index, is a constant coefficient.

[0007] Preferably, the course characteristic data includes the course exercise type and the course intensity coefficient; The method for obtaining the course intensity coefficient is as follows: Obtaining course intensity reflection characteristic data of the i-th physical education course, wherein the course intensity reflection characteristic data includes duration, activity density, and recovery time of the i-th physical education course; Substitute the characteristic data reflecting the course intensity into the pre-built course intensity quantification model to obtain the course intensity coefficient of the i-th physical education course; The expression of the pre-built course intensity quantification model is as follows: ; Where: is the course intensity coefficient, is the weighting factor of the course intensity coefficient; for the duration of the course; is the average duration of the course, The activity density of the course, which indicates the intensity of the activity per unit time; For recovery time.

[0008] Preferably, the method for generating the preconfigured convolutional neural network is as follows: Acquire historical heart rate interval training data, and divide the historical heart rate interval training data into a heart rate interval training set and a heart rate interval test set, wherein the historical heart rate interval training data includes heart rate reflection feature data and its corresponding estimated average heart rate interval; Wherein, the heart rate reflection characteristic data includes physical measurement characteristic data and course characteristic data; Construct a convolutional neural network, use the heart rate reflection feature data in the heart rate interval training set as the input of the convolutional neural network, and use the estimated average heart rate interval as the output of the convolutional neural network, train the convolutional neural network, and obtain a heart rate interval regression network; The heart rate interval test set is used to verify the model of the heart rate interval regression network, and the heart rate interval regression network with a test error threshold less than the preset value is output as the preconfigured convolutional neural network.

[0009] Preferably, the step of determining whether the i-th physical education course is suitable for the j-th student comprises: Calculate the intersection length of the estimated heart rate interval and the standard heart rate interval; Calculate the union length of the estimated heart rate interval and the standard heart rate interval; Calculate the ratio of the intersection length to the union length, and determine whether the ratio is greater than or equal to a preset ratio threshold. If so, determine that the corresponding i-th physical education course is suitable for the j-th student; if not, determine that the corresponding i-th physical education course is not suitable for the j-th student.

[0010] Preferably, the method further comprises: Step 6: According to the first recommended physical education courses of all students, obtain the number of students who have chosen each physical education course, and determine the excess courses, the number of students who have chosen the excess courses, the courses to be filled, and the number of students who need to be filled in the courses to be filled according to the number of students who have chosen; Step 7: Re-match and recommend the selected students of the excess courses using a pre-configured genetic algorithm to obtain the best permutation combination, wherein the permutation combination includes the second recommended physical education elective course corresponding to each student in the excess course; Step 8: Take the difference between the number of students who have chosen the excess courses and the number of students who need to be filled in the courses to be filled as the quantity scheduling target. Based on the best permutation and combination and according to the number specified by the quantity scheduling target, recommend some students from the excess courses to the courses to be filled.

[0011] Preferably, the re-matching recommendation of selected students of oversubscribed courses by using a pre-configured genetic algorithm comprises: a1: Initialize the population: randomly generate an original population, wherein the original population contains X individuals, each individual represents a permutation and combination, each permutation and combination contains the second recommended physical education elective course corresponding to each student in the excess courses, and X is an integer greater than zero; a2: Fitness evaluation: For each individual, predict the probability of injury for each student participating in the corresponding second recommended physical education elective course; input the injury probability into the pre-built fitness function to calculate the fitness of each individual; The calculation formula of the pre-constructed fitness function is: ; Where: For fitness, is the number of students who have chosen the oversubscribed course, is the probability of injury of the vth student; a3: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother; a4: Crossover: Perform crossover operation on the father and mother to produce new individuals; a5: Mutation: Perform mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2; a6: Repeat steps a2 to a5 above until the fitness of individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the permutation combination represented by the corresponding individual as the best permutation combination.

[0012] Preferably, the predicting the probability of injury of each student participating in the corresponding second recommended physical education elective course includes: Obtaining physical test characteristic data of each student and course characteristic data corresponding to the second recommended physical education elective course; Inputting the physical test characteristic data of each student and the course characteristic data of the corresponding second recommended physical education elective course into the pre-built injury risk prediction model in turn, and predicting the injury probability of each student participating in the corresponding second recommended physical education elective course; The method for generating the pre-built injury risk prediction model is as follows: Acquire historical injury risk training data, and divide the historical injury risk training data into an injury risk training set and an injury risk test set, wherein the historical injury risk training data includes injury risk feature data and its corresponding injury probability; Wherein, the injury risk characteristic data includes physical test characteristic data and course characteristic data; Constructing a decision tree model, taking the injury risk characteristic data in the injury risk training set as the input of the decision tree, and taking the injury probability as the input of the decision tree, and training the decision tree to obtain an initial injury risk prediction network; The initial injury risk prediction network is verified using the injury risk test set, and an initial injury risk prediction network that is less than or equal to a preset test error threshold is output as a pre-constructed injury risk prediction model.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention achieves the comprehensive technical effects of personalized recommendation, course resource optimization and sports safety guarantee. By accurately obtaining students' physical test data and course feature data and analyzing them with intelligent algorithms, the present invention can recommend the physical education course that best suits their physical fitness and needs for each student, significantly improving the accuracy and personalization level of course recommendation. Compared with the traditional recommendation method, the present invention avoids the problem of mismatch between course recommendation and students' actual needs, ensuring that the course selected by each student can better adapt to their physical condition and athletic ability, thereby improving the exercise effect and students' enthusiasm for participation. At the same time, the present invention optimizes the configuration of course resources by considering the matching of course number limit and course intensity. In practical applications, the number of participants in a course is often limited, and some courses may be oversubscribed due to too many students choosing them, while other courses may not be fully utilized due to insufficient number of students choosing them. The present invention uses an intelligent recommendation system to reasonably allocate the number of participating students in each course and optimize the matching degree of the courses, which is conducive to ensuring the efficient use of educational resources while minimizing the risk of each student participating in the corresponding physical education course. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a schematic diagram of the process of the present invention; Figure 2 It is another schematic flow chart of the method of the present invention; Figure 3 It is a structural schematic diagram of the system of the present invention; Figure 4 It is another structural schematic diagram of the system of the present invention. DETAILED DESCRIPTION

[0016] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] See also Figure 1 The first embodiment of the present invention provides a method for recommending physical education courses for college students based on big data analysis, including: Step 1: Obtain the physical test characteristic data of the jth student among the N students to be selected, where N and j are both integers greater than zero; Specifically, the physical measurement characteristic data include age, gender, blood pressure (including systolic and diastolic blood pressure) and cardiopulmonary health index; It should be noted that: the physical measurement characteristic data is collected by a wearable device or manually entered by a technician in advance, and the wearable device includes but is not limited to an electronic bracelet and a smart chest strap, etc.; The method for obtaining the cardiopulmonary health index is as follows: Obtain the cardiopulmonary function reflection characteristic data of the jth student, the cardiopulmonary function reflection characteristic data including body mass index (BMI value, (weight (kg) / height (m)²), which can be used to measure body fat content), maximum oxygen uptake ( ) and resting heart rate; Substitute the cardiopulmonary function reflection characteristic data into the pre-built cardiopulmonary health quantitative model to obtain the cardiopulmonary health index of the jth student; The expression of the pre-built cardiopulmonary health quantification model is as follows: ; Where: is the cardiopulmonary health index, is the maximum oxygen uptake, is the resting heart rate, is the body mass index, is a constant coefficient, which is set according to experimental data.

[0018] Step 2: Obtain course feature data of the i-th physical education course among the M physical education courses to be recommended, where both M and i are integers greater than zero; Specifically, the course characteristic data includes the course exercise type and the course intensity coefficient; It should be noted that the characteristic data of each course is collected and counted by the technical staff based on the experimental data and recorded in the system database in advance; The method for obtaining the course intensity coefficient is as follows: Obtaining course intensity reflection characteristic data of the i-th physical education course, wherein the course intensity reflection characteristic data includes duration, activity density, and recovery time of the i-th physical education course; Substitute the characteristic data reflecting the course intensity into the pre-built course intensity quantification model to obtain the course intensity coefficient of the i-th physical education course; The expression of the pre-built course intensity quantification model is as follows: ; Where: is the course intensity coefficient, is the weighting factor of the course intensity coefficient, which adjusts the impact of course intensity on the total coefficient and is obtained through data analysis; is the duration of the course, indicating the length of time students spend exercising; is the average duration of the course, determined based on historical experimental data or records, The activity density of the course indicates the intensity of the activity per unit time and is defined by the number of actions per minute; Recovery time refers to the rest time between sports movements in a class. The length of recovery time directly affects the overall intensity and challenge of the class. For example, shorter recovery time means higher intensity.

[0019] Step 3: Input the course feature data of the i-th physical education course and the physical test feature data of the j-th student into the preconfigured convolutional neural network to predict the estimated average heart rate range of the j-th student when participating in the i-th physical education course; In implementation, the method for generating the preconfigured convolutional neural network is as follows: Acquire historical heart rate interval training data, and divide the historical heart rate interval training data into a heart rate interval training set and a heart rate interval test set, wherein the historical heart rate interval training data includes heart rate reflection feature data and its corresponding estimated average heart rate interval; Wherein, the heart rate reflection characteristic data includes physical measurement characteristic data and course characteristic data; It should be understood that: the heart rate reflection characteristic data in the historical heart rate interval training data is actually collected and calculated by the technicians, and part of the calculation logic is referred to above, which will not be repeated here; and the estimated average heart rate interval in the historical heart rate interval training data is specifically collected and recorded by the technicians based on the experimental data; Construct a convolutional neural network, use the heart rate reflection feature data in the heart rate interval training set as the input of the convolutional neural network, and use the estimated average heart rate interval as the output of the convolutional neural network, train the convolutional neural network, and obtain a heart rate interval regression network; The heart rate interval test set is used to verify the model of the heart rate interval regression network, and the heart rate interval regression network with a test error threshold less than the preset value is output as the preconfigured convolutional neural network.

[0020] Step 4: Get the standard heart rate interval, and determine whether the i-th physical education course is suitable for the j-th student based on the estimated heart rate interval and the standard heart rate interval. If so, the i-th physical education course is recommended to the j-th student as the first recommended physical education elective course for the j-th student, and j=j+1 is set, and the process returns to step 1; if not, i=i+1 is set, and the process returns to step 2; In implementation, the step of determining whether the i-th physical education course is suitable for the j-th student includes: Calculate the intersection length of the estimated heart rate interval and the standard heart rate interval; Calculate the union length of the estimated heart rate interval and the standard heart rate interval; Calculate the ratio of the intersection length to the union length, and determine whether the ratio is greater than or equal to a preset ratio threshold. If so, determine that the corresponding ith physical education course is suitable for the jth student; if not, determine that the corresponding ith physical education course is not suitable for the jth student; For example, assuming that there is an estimated heart rate interval of [a1, a2] and a standard heart rate interval of [b1, b2], the length of the intersection of the estimated heart rate interval and the standard heart rate interval is: , where: is the intersection length, Represents the smaller value of the right endpoints of the two intervals, indicating the end position of the intersection, Represents the larger value of the left endpoints of the two intervals, indicating the starting position of the intersection, It is used to ensure that the intersection length is non-negative. If the two intervals do not overlap, the intersection length is 0; and the union length of the estimated heart rate interval and the standard heart rate interval is: , where: is the length of the union of the estimated heart rate interval and the standard heart rate interval, Represents the larger value of the right endpoints of the two intervals, that is, the right endpoint of the merged interval, represents the smaller value of the left endpoints of the two intervals, that is, the left endpoint of the merged interval; finally, the ratio of the intersection length to the union length is calculated as ;when When , it means that the two intervals are completely consistent. , it means that the two intervals are completely different, that is, they do not overlap. It can be understood that The larger it is, the higher the suitability of the corresponding physical education course for the jth student is.

[0021] Step 5: Repeat the above steps 1 to 4 until j=N, then stop the loop and get the first recommended physical education elective courses for all students; By jointly analyzing each student's physical test characteristic data and each physical education course characteristic data to be selected, and based on the prediction of the student's heart rate performance, the present invention can make each student's selected physical education course fully adapt to his or her own physical condition, thereby providing each student with personalized physical education course selection; However, it is worth noting that obtaining the first recommended physical education course for all students does not mean the end of the course recommendation matching task. This is because, in the actual physical education course selection scenario, it is also subject to the constraints of the number of course participants. A further explanation is that each physical education course generally limits the number of course participants. This is why some physical education courses may have more participants, while some courses may have fewer participants, resulting in resource imbalance. For example, suppose there are 20 students to be selected, and there are two physical education courses to be recommended, one is basketball and the other is jogging, and each physical education course to be recommended is limited to 10 participants. Suppose that according to the above matching process, 15 of the 20 students are suitable for basketball, and only 5 students are suitable for jogging. If the course arrangement is carried out according to the current situation, it will inevitably cause a waste of educational resources. Therefore, 5 students need to be selected from the 15 students to enter the jogging course. There are large differences in exercise intensity between different physical education courses. Therefore, inappropriate random arrangement may increase the probability of student injury. Therefore, how to ensure student sports safety while making reasonable and scientific course recommendations has become a technical problem that college physical education teachers are currently urgently trying to solve; See also Figure 2 In an optional implementation, the method further includes: Step 6: According to the first recommended physical education courses of all students, obtain the number of students who have chosen each physical education course, and determine the excess courses, the number of students who have chosen the excess courses, the courses to be filled, and the number of students who need to be filled in the courses to be filled according to the number of students who have chosen; Exemplarily, following the above assumptions, suppose there are 20 students to be selected, and there are two physical education courses to be recommended, one is basketball class and the other is jogging class, and each physical education course to be recommended is limited to 10 participants, and according to the first recommended physical education elective courses of all students, it is known that 15 students are recommended to choose basketball class, and 5 students are recommended to choose jogging class. Therefore, it can be known that basketball class is an excess course and jogging class is a course to be filled. Moreover, the number of selected students of basketball class (excess course) is 15, and the number of students who need to be filled in jogging class (course to be filled) is 5. Then, the 15 students are randomly combined with jogging class and basketball class respectively, and the best permutation combination is screened out according to the following genetic algorithm, that is, the second recommended physical education elective course for each of the 15 students is obtained.

[0022] Step 7: Re-match and recommend the selected students of the excess courses using a pre-configured genetic algorithm to obtain the best permutation combination, wherein the permutation combination includes the second recommended physical education elective course corresponding to each student in the excess course; Specifically, the method of re-matching and recommending selected students for oversubscribed courses by using a pre-configured genetic algorithm includes: a1: Initialize the population: randomly generate an original population, wherein the original population contains X individuals, each individual represents a permutation and combination, each permutation and combination contains the second recommended physical education elective course corresponding to each student in the excess courses, and X is an integer greater than zero; a2: Fitness evaluation: For each individual (i.e., each permutation combination in the original population), predict the probability of injury for each student participating in the corresponding second recommended physical education elective course; input the injury probability into the pre-built fitness function to calculate the fitness of each individual; In implementation, the prediction of the probability of injury of each student participating in the corresponding second recommended physical education elective course includes: Obtaining physical test characteristic data of each student and course characteristic data corresponding to the second recommended physical education elective course; Inputting the physical test characteristic data of each student and the course characteristic data of the corresponding second recommended physical education elective course into the pre-built injury risk prediction model in turn, and predicting the injury probability of each student participating in the corresponding second recommended physical education elective course; The method for generating the pre-built injury risk prediction model is as follows: Acquire historical injury risk training data, and divide the historical injury risk training data into an injury risk training set and an injury risk test set, wherein the historical injury risk training data includes injury risk feature data and its corresponding injury probability; Wherein, the injury risk characteristic data includes physical test characteristic data and course characteristic data; It should be noted that the injury risk characteristic data in the historical injury risk training data is collected and calculated in advance by technical personnel, and the injury probability in the injury risk characteristic data is obtained by technical personnel based on statistical data of experimental data; Constructing a decision tree model, taking the injury risk characteristic data in the injury risk training set as the input of the decision tree, and taking the injury probability as the input of the decision tree, and training the decision tree to obtain an initial injury risk prediction network; Using the injury risk test set to verify the initial injury risk prediction network, outputting an initial injury risk prediction network that is less than or equal to a preset test error threshold as a pre-built injury risk prediction model; In genetic algorithms, fitness evaluation is one of the core steps, which is used to determine the fitness of each individual, that is, to determine how well each individual performs in a given problem; the design of the fitness function directly affects the efficiency of the algorithm and the quality of the final solution; The calculation formula of the pre-constructed fitness function is: ; Where: For fitness, is the number of students who have chosen the oversubscribed course, is the probability of injury of the vth student; a3: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother; The roulette wheel method is a commonly used selection method, which is used in genetic algorithms to select individuals with higher fitness to enter the next generation. It simulates the process of roulette, and each individual obtains a corresponding "roulette wheel" area according to its fitness. The higher the fitness of the individual, the larger the corresponding area, and the higher the probability of being selected. a4: Crossover: Perform crossover operation on the father and mother to produce new individuals; It should be noted that the crossover operation on the paternal parent and the maternal parent is implemented based on a crossover operation, and the crossover operation includes but is not limited to one of a single-point crossover, a uniform crossover or a sequential crossover, etc.; In genetic algorithms, crossover is an important genetic operation used to generate a new generation of candidate solutions; the basic idea of ​​crossover is to simulate the sexual reproduction process in biological genetics, in which two parents produce offspring by combining their genetic information; this process helps to introduce diversity in the solution space and may produce new individuals that are more adaptable to the environment; a5: Mutation: Perform mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2; In genetic algorithms, mutation operations are used to introduce genetic diversity and prevent the algorithm from falling into a local optimum. The mutation operation on new individuals is implemented by uniform mutation or Gaussian mutation. a6: Repeat steps a2 to a5 above until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the permutation combination represented by the corresponding individual as the best permutation combination; For example, assuming that the maximum number of iterations is 100, the individual with the highest fitness in the current population and its fitness value are recorded after each iteration; if it is found that the fitness value has not changed significantly in a certain generation, it is considered that the convergence condition has been met, the iteration is stopped, and the permutation combination represented by the corresponding individual is output as the best permutation combination; Exemplarily, following the above assumptions, suppose there are 15 students, namely A1, A2, A3, ..., A15. After recombining according to the genetic algorithm, it is found that the 5 students A1-A5 are recommended to the jogging class, and the permutation combination at this time is the best. Therefore, basketball class will continue to be the second recommended physical education elective course for the 15 students A6-A15, and jogging class will be the second recommended physical education elective course for the 5 students A1-A5, thereby completing the secondary recommendation regulation in the initial uneven distribution scenario, which is beneficial to ensure the full utilization of educational resources while minimizing the risk of each student participating in the corresponding physical education course, and ensuring the rationality, fairness and scientificity of course recommendations from a global perspective.

[0023] Step 8: Take the difference between the number of students who have chosen the excess courses and the number of students who need to be filled in the courses to be filled as the quantity scheduling target. Based on the best permutation and combination and according to the number specified by the quantity scheduling target, recommend some students from the excess courses to the courses to be filled.

[0024] See also Figure 3 Based on the same inventive concept, the second aspect of the present invention provides a college student sports course selection recommendation system based on big data analysis. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The system includes: The first acquisition module is used to obtain the physical measurement characteristic data of the jth student among the N students to be selected, where N and j are both integers greater than zero; The second acquisition module is used to acquire the course characteristic data of the i-th physical education course among the M physical education courses to be recommended, where M and i are both integers greater than zero; A heart rate prediction module is used to input the course characteristic data of the i-th physical education course and the physical test characteristic data of the j-th student into a preconfigured convolutional neural network to predict the estimated average heart rate range of the j-th student when participating in the i-th physical education course; A primary adaptation analysis module is used to obtain the standard heart rate interval, and determine whether the i-th physical education course is compatible with the j-th student according to the estimated heart rate interval and the standard heart rate interval. If so, the i-th physical education course is recommended to the j-th student as the first recommended physical education elective course for the j-th student, and j=j+1 is set, and the process returns to step one; if not, i=i+1 is set, and the process returns to step two; The loop analysis module is used to repeat the above steps 1 to 4 until j=N, then stop the loop and obtain the first recommended physical education elective courses for all students.

[0025] See also Figure 4 In an optional embodiment, the system further comprises: The third acquisition module is used to obtain the number of students who have chosen each physical education course according to the first recommended physical education elective courses of all students, and determine the excess courses, the number of students who have chosen the excess courses, the courses to be filled, and the number of students who need to be filled in the courses to be filled according to the number of students who have chosen; A secondary adaptation analysis module is used to re-match and recommend the selected students of the excess courses by using a pre-configured genetic algorithm to obtain the best permutation combination, wherein the permutation combination includes a second recommended sports elective course corresponding to each student in the excess course; The local recommendation analysis module is used to take the difference between the number of students who have chosen the excess courses and the number of students who need to be filled in the to-be-filled courses as the quantity scheduling target, and recommend some students from the excess courses to the to-be-filled courses based on the best permutation and combination and according to the number specified by the quantity scheduling target.

[0026] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0027] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0028] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0029] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0030] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0031] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for recommending physical education courses for college students based on big data analysis, characterized in that: include: Step 1: Obtain the physical test characteristic data of the jth student among the N students to be selected, where N and j are both integers greater than zero; Step 2: Obtain course feature data of the i-th physical education course among the M physical education courses to be recommended, where both M and i are integers greater than zero; Step 3: Input the course feature data of the i-th physical education course and the physical test feature data of the j-th student into the preconfigured convolutional neural network to predict the estimated average heart rate range of the j-th student when participating in the i-th physical education course; Step 4: Get the standard heart rate interval, and determine whether the i-th physical education course is suitable for the j-th student based on the estimated heart rate interval and the standard heart rate interval. If so, the i-th physical education course is recommended to the j-th student as the first recommended physical education elective course for the j-th student, and j=j+1 is set, and the process returns to step 1; if not, i=i+1 is set, and the process returns to step 2; Step 5: Repeat the above steps 1 to 4 until j=N, then stop the loop and get the first recommended physical education elective courses for all students.

2. The method for recommending physical education courses for college students based on big data analysis according to claim 1 is characterized in that: The physical test characteristic data include age, gender, blood pressure and cardiopulmonary health index; The method for obtaining the cardiopulmonary health index is as follows: Acquire cardiopulmonary function reflection characteristic data of the jth student, wherein the cardiopulmonary function reflection characteristic data includes body mass index, maximum oxygen uptake and resting heart rate; Substitute the cardiopulmonary function reflection characteristic data into the pre-built cardiopulmonary health quantitative model to obtain the cardiopulmonary health index of the jth student; The expression of the pre-built cardiopulmonary health quantification model is as follows: ; Where: is the cardiopulmonary health index, is the maximum oxygen uptake, is the resting heart rate, is the body mass index, is a constant coefficient.

3. The method for recommending physical education courses for college students based on big data analysis according to claim 2 is characterized in that: The course characteristic data includes course exercise type and course intensity coefficient; The method for obtaining the course intensity coefficient is as follows: Obtaining course intensity reflection characteristic data of the i-th physical education course, wherein the course intensity reflection characteristic data includes duration, activity density, and recovery time of the i-th physical education course; Substitute the characteristic data reflecting the course intensity into the pre-built course intensity quantification model to obtain the course intensity coefficient of the i-th physical education course; The expression of the pre-built course intensity quantification model is as follows: ; Where: is the course intensity coefficient, is the weighting factor of the course intensity coefficient; for the duration of the course; is the average duration of the course, The activity density of the course, which indicates the intensity of the activity per unit time; For recovery time.

4. The method for recommending physical education courses for college students based on big data analysis according to claim 3 is characterized in that: The method for generating the preconfigured convolutional neural network is as follows: Acquire historical heart rate interval training data, and divide the historical heart rate interval training data into a heart rate interval training set and a heart rate interval test set, wherein the historical heart rate interval training data includes heart rate reflection feature data and its corresponding estimated average heart rate interval; Wherein, the heart rate reflection characteristic data includes physical measurement characteristic data and course characteristic data; Construct a convolutional neural network, use the heart rate reflection feature data in the heart rate interval training set as the input of the convolutional neural network, and use the estimated average heart rate interval as the output of the convolutional neural network, train the convolutional neural network, and obtain a heart rate interval regression network; The heart rate interval test set is used to verify the model of the heart rate interval regression network, and the heart rate interval regression network with a test error threshold less than the preset value is output as the preconfigured convolutional neural network.

5. The method for recommending physical education courses for college students based on big data analysis according to claim 4 is characterized in that: The step of judging whether the i-th physical education course is suitable for the j-th student includes: Calculate the intersection length of the estimated heart rate interval and the standard heart rate interval; Calculate the union length of the estimated heart rate interval and the standard heart rate interval; Calculate the ratio of the intersection length to the union length, and determine whether the ratio is greater than or equal to a preset ratio threshold. If so, determine that the corresponding i-th physical education course is suitable for the j-th student; if not, determine that the corresponding i-th physical education course is not suitable for the j-th student.

6. The method for recommending physical education courses for college students based on big data analysis according to claim 5 is characterized in that: The method further comprises: Step 6: According to the first recommended physical education courses of all students, obtain the number of students who have chosen each physical education course, and determine the excess courses, the number of students who have chosen the excess courses, the courses to be filled, and the number of students who need to be filled in the courses to be filled according to the number of students who have chosen; Step 7: Re-match and recommend the selected students of the excess courses using a pre-configured genetic algorithm to obtain the best permutation combination, wherein the permutation combination includes the second recommended physical education elective course corresponding to each student in the excess course; Step 8: Take the difference between the number of students who have chosen the excess courses and the number of students who need to be filled in the courses to be filled as the quantity scheduling target. Based on the best permutation and combination and according to the number specified by the quantity scheduling target, recommend some students from the excess courses to the courses to be filled.

7. The method for recommending physical education courses for college students based on big data analysis according to claim 6 is characterized in that: The method of using a preconfigured genetic algorithm to re-match selected students of oversubscribed courses includes: a1: Initialize the population: randomly generate an original population, wherein the original population contains X individuals, each individual represents a permutation and combination, each permutation and combination contains the second recommended physical education elective course corresponding to each student in the excess courses, and X is an integer greater than zero; a2: Fitness evaluation: For each individual, predict the probability of injury for each student participating in the corresponding second recommended physical education elective course; input the injury probability into the pre-built fitness function to calculate the fitness of each individual; The calculation formula of the pre-constructed fitness function is: ; Where: For fitness, is the number of students who have chosen the oversubscribed course, is the probability of injury of the vth student; a3: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother; a4: Crossover: Perform crossover operation on the father and mother to produce new individuals; a5: Mutation: Perform mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2; a6: Repeat steps a2 to a5 above until the fitness of individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the permutation combination represented by the corresponding individual as the best permutation combination.

8. The method for recommending physical education courses for college students based on big data analysis according to claim 7 is characterized in that: The predicting of the probability of injury of each student participating in the second recommended physical education elective course includes: Obtaining physical test characteristic data of each student and course characteristic data corresponding to the second recommended physical education elective course; Inputting the physical test characteristic data of each student and the course characteristic data of the corresponding second recommended physical education elective course into the pre-built injury risk prediction model in turn, and predicting the injury probability of each student participating in the corresponding second recommended physical education elective course; The method for generating the pre-built injury risk prediction model is as follows: Acquire historical injury risk training data, and divide the historical injury risk training data into an injury risk training set and an injury risk test set, wherein the historical injury risk training data includes injury risk feature data and its corresponding injury probability; Wherein, the injury risk characteristic data includes physical test characteristic data and course characteristic data; A decision tree model is constructed, and the injury risk characteristic data in the injury risk training set is used as the input of the decision tree, and the injury probability is used as the input of the decision tree, and the decision tree is trained to obtain an initial injury risk prediction network; The initial injury risk prediction network is verified using the injury risk test set, and an initial injury risk prediction network that is less than or equal to a preset test error threshold is output as a pre-built injury risk prediction model.

9. A system for recommending physical education courses for college students based on big data analysis, implemented based on the method for recommending physical education courses for college students based on big data analysis as described in any one of claims 1 to 8, characterized in that: include: The first acquisition module is used to obtain the physical measurement characteristic data of the jth student among the N students to be selected, where N and j are both integers greater than zero; The second acquisition module is used to acquire the course characteristic data of the i-th physical education course among the M physical education courses to be recommended, where M and i are both integers greater than zero; A heart rate prediction module is used to input the course characteristic data of the i-th physical education course and the physical test characteristic data of the j-th student into a preconfigured convolutional neural network to predict the estimated average heart rate range of the j-th student when participating in the i-th physical education course; A primary adaptation analysis module is used to obtain the standard heart rate interval, and determine whether the i-th physical education course is compatible with the j-th student according to the estimated heart rate interval and the standard heart rate interval. If so, the i-th physical education course is recommended to the j-th student as the first recommended physical education elective course for the j-th student, and j=j+1 is set, and the process returns to step one; if not, i=i+1 is set, and the process returns to step two; The loop analysis module is used to repeat the above steps 1 to 4 until j=N, then stop the loop and obtain the first recommended physical education elective courses for all students.

10. The college student sports course selection recommendation system based on big data analysis according to claim 9 is characterized in that: The system further comprises: The third acquisition module is used to obtain the number of students who have chosen each physical education course according to the first recommended physical education elective courses of all students, and determine the excess courses, the number of students who have chosen the excess courses, the courses to be filled, and the number of students who need to be filled in the courses to be filled according to the number of students who have chosen; A secondary adaptation analysis module is used to re-match and recommend the selected students of the excess courses by using a pre-configured genetic algorithm to obtain the best permutation combination, wherein the permutation combination includes a second recommended sports elective course corresponding to each student in the excess course; The local recommendation analysis module is used to take the difference between the number of students who have chosen the excess courses and the number of students who need to be filled in the to-be-filled courses as the quantity scheduling target, and recommend some students from the excess courses to the to-be-filled courses based on the best permutation and combination and according to the number specified by the quantity scheduling target.

Images