Campus intelligent sports system

Abstract

The invention relates to the technical field of smart schools, in particular to a smart campus sports system, which comprises a data acquisition module, a data processing module, a data processing module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring student learning course data, to-be-selected sports course data, student physical ability data and questionnaire data; the physical fitness analysis module is used for analyzing the physical fitness state of the student; the course intensity analysis module is used for constructing a physical education course intensity index to be selected; the academic pressure analysis module is used for constructing academic load indexes; the interest analysis module is used for constructing interest indexes of the students according to the collected interest scores of the students in the physical education courses; and the recommendation module is used for recommending the physical education courses to the students according to the analysis results of the physical fitness states of the students and the construction results of the strength indexes of the physical education courses to be selected, the academic load indexes and the interest indexes, and adjusting the recommendation process. The sports course recommendation efficiency is improved, and the satisfaction degree of students is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart campus, and in particular to a campus smart sports system. Background Art

[0002] Traditional physical education course arrangements are usually based on a fixed schedule or based on teacher experience, but lack personalized considerations. Different students have significant differences in physical fitness, interests, academic burden, and free time. Arranging physical education courses based on a fixed model may cause some students to have excessive or insufficient physical load, or students' low participation in the course, affecting their enthusiasm for physical exercise and long-term effects. In addition, the social needs of students are often ignored, resulting in some students with weak social skills being unable to fully integrate into group activities, further reducing their enthusiasm for physical exercise. Therefore, how to make personalized physical education course recommendations based on multiple dimensions such as students' physical fitness, academic pressure, interests and hobbies, social skills, and daily free time has become the key to solving current problems.

[0003] Chinese patent publication number CN115018271A discloses a student course selection intelligent recommendation management system based on smart campus construction, including: course selection information acquisition module, information storage library, physical fitness basic information analysis module, student attention analysis module, physical education course selection analysis module, physical education course recommendation analysis module and physical education course preferred display module. The present invention comprehensively analyzes the popularity index corresponding to each physical education course from four aspects, and then can scientifically, effectively and reasonably recommend physical education courses for students participating in course selection. While improving the rationality of the recommendation of preferred physical education courses, it further strengthens the experience of students participating in course selection, reduces the risk of students choosing the wrong physical education courses, and more importantly, mainly recommends physical education courses to students based on their own will, greatly meets the requirements of most students, and realizes the targeted matching needs of the recommendation of preferred physical education courses; it can be seen that the scheme does not take into account the academic load and psychological state of students, and there are problems of low efficiency in physical education course recommendation and low student satisfaction. Summary of the invention

[0004] The object of the present invention is to provide a campus smart sports system to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] Data collection module, used to collect students' learning course data, selected physical education course data, students' physical fitness data and questionnaire data;

[0007] Physical fitness analysis module, used to analyze students' physical fitness status based on the collected maximum oxygen uptake and resting heart rate of students;

[0008] A course intensity analysis module is used to construct an intensity index of the selected physical education course according to the intensity score of the selected physical education course and the number of class hours of the selected physical education course;

[0009] The academic stress analysis module is used to construct the difficulty coefficient of the learning course according to the collected historical scores of the students' learning courses, and to construct the academic load index according to the construction results of the course difficulty coefficient and the number of courses studied by the students and the number of class hours of the courses studied by the students;

[0010] The interest analysis module is used to construct the student interest index based on the collected student interest scores for physical education courses;

[0011] The recommendation module is used to recommend physical education courses to students based on the analysis results of the students' physical fitness status, the intensity index of the selected physical education courses, the construction results of the academic load index and the interest index, and adjust the recommendation process based on the collected student social scores and the students' daily free time.

[0012] Further, the physical fitness analysis module is provided with a first analysis unit, a second analysis unit and a physical fitness analysis unit, wherein the first analysis unit is used to compare the collected maximum oxygen uptake a0 of the student with the preset oxygen uptake a1 to construct an oxygen uptake index;

[0013] The second analysis unit compares the collected student's resting heart rate b0 with the preset heart rate b1 to construct a heart rate index. If b0≤b1, the physical fitness analysis module sets the heart rate index to XL1, setting XL1=[(b1-b0) / b1] 0.5 If b0>b1, the physical fitness analysis module sets the heart rate index to XL2, setting XL2=-[(b1-b0) / b1] 0.5 .

[0014] Furthermore, the physical fitness analysis unit is used to construct the student's physical fitness index TN according to the construction results of the oxygen uptake index and the heart rate index, and set TN=w1×oxygen uptake index+w2×heart rate index, where w1 is the oxygen uptake weight and w2 is the heart rate weight.

[0015] Furthermore, the course intensity analysis module sets the intensity index of the i-th selected physical education course as Qi, and sets Qi=x1×di / dmax+x2×ln(si / smax+1), where di is the intensity score of the i-th selected physical education course, dmax is the maximum threshold of the intensity score of the selected physical education course, si is the number of class hours of the i-th selected physical education course, smax is the maximum value of the physical education course class hours, x1 is the intensity weight, and x2 is the class hour weight.

[0016] Furthermore, the academic stress distraction module is provided with a difficulty coefficient analysis unit and an academic load analysis unit, and the difficulty coefficient analysis unit constructs the difficulty coefficient of the learning course according to the collected historical scores of the students learning the course, wherein:

[0017] The difficulty coefficient analysis unit sets the difficulty coefficient of the jth course of the student's course as Rj, and sets Mrj is the rj-th historical average score data of the j-th course in the student's course, mj is the number of historical average score data of the j-th course in the student's course, and Mj is the full score threshold of the j-th course in the student's course.

[0018] Furthermore, the academic load analysis unit is used to construct an academic load index according to the construction result of the course difficulty coefficient and the collected number of courses studied by the students and the number of class hours of the courses studied by the students. The academic load analysis unit sets the student's academic load index to F, and sets:

[0019] Hj is the number of hours of the jth course studied by the student, C is the number of courses studied by the student, Z is the total number of hours of courses studied by the student, f0 is the preset difficulty coefficient threshold, α1 is the course quantity weight, α2 is the course difficulty weight, α1+α2=1.

[0020] Furthermore, the interest analysis module constructs the student interest index according to the collected student interest scores for the physical education course, wherein:

[0021] The interest analysis module sets the student's interest index for the i-th optional physical education course as Pi, and sets Pi=3×(ui / u0)2+2×(ui / u0)3, where ui is the student's interest score for the i-th optional physical education course, and u0 is the preset score threshold.

[0022] Furthermore, the recommendation module is provided with a recommendation unit, a social analysis unit and a free time analysis unit, and the recommendation unit is used to recommend physical education courses to students according to the construction results of the students' physical fitness index, physical education course intensity index, academic load index and interest index, wherein:

[0023] The recommendation unit sets the recommendation coefficient of the i-th selected physical education course as Ti, and sets: Ti=-|[t1×TN-t2×ln(F+1) / ln2+t3×(ePi-1) / (e-1)]-γ×Qi|, wherein t1 is the physical fitness weight, t2 is the academic load weight, t3 is the interest weight, t1+t2+t3=1, t1>t3≥t2, and γ is the preset adjustment coefficient;

[0024] The recommendation unit sorts the recommendation coefficients of the physical education courses, and pushes the physical education course with the largest recommendation coefficient to the user as a recommended course.

[0025] Furthermore, the social analysis unit constructs a social factor Y0 using the collected student social score y0, and sets: Y0=y0 / y1, where y1 is a social score threshold;

[0026] The social analysis unit compares the social factor with the preset social factor threshold Y1 to adjust the sports course recommendation process. If Y0≤Y1 and the i-th sports course type to be selected is a team project, the social analysis unit sets the recommendation coefficient of the i-th sports course to be selected to Ti1, and sets Ti1=Ti-η×(Y1-Y0) / Y1. If Y0>Y1 and the i-th sports course type to be selected is an individual project, the social analysis unit does not make any adjustment. If Y0>Y1 and the i-th sports course type to be selected is a team project, the social analysis unit does not make any adjustment. If Y0>Y1 and the i-th sports course type to be selected is an individual project, the social analysis unit sets the recommendation coefficient of the i-th sports course to be selected to Ti2, and sets Ti2=Ti-η×(Y0-Y1) / Y1, where η is a preset correction proportional coefficient.

[0027] Furthermore, the idle analysis unit is used to compare the collected daily idle time g0 of the students with the preset idle time g1 to optimize the adjustment process of the physical education course recommendation process. If g0≤g1, the idle analysis unit determines that the student's idle time is normal and does not perform optimization. If g0≥g1, the idle analysis unit determines that the student's idle time is abnormal, and optimizes the physical education course recommendation process, and sets the optimized preset adjustment coefficient to γ1.

[0028] The beneficial effects of the present invention are as follows:

[0029] The system integrates a physical fitness analysis module, a course intensity analysis module, an academic stress analysis module, an interest analysis module and a recommendation module, aiming to provide students with personalized physical education course recommendations. Through the collection and analysis of multi-dimensional data, it helps students to arrange physical education courses scientifically and rationally, so as to balance academic studies and interests while maintaining physical health. The system has the characteristics of multi-level, multi-dimensional, personalized and dynamic adjustment, providing students with customized comprehensive solutions; the physical fitness analysis module realizes the accurate assessment of students' physical fitness. Through the dual data collection of maximum oxygen uptake and resting heart rate, the module uses the oxygen uptake index and heart rate index to conduct a comprehensive analysis of students' cardiopulmonary function, cardiovascular health and exercise adaptability, and through Weight distribution realizes highly targeted individualized physical fitness assessment, especially the calculation method that is dynamically adjusted according to the gender differences of students, making the analysis results more in line with reality. This module provides an important basis for course recommendation, ensuring that the recommended exercise intensity matches the physical condition of students, and avoiding students' health status being affected by excessive or insufficient exercise. The course intensity analysis module can accurately quantify the intensity of different physical education courses, and scientifically construct a course intensity index based on intensity scores and the number of class hours. This ensures that when recommending courses, the system can accurately evaluate the load of each course on students' physical fitness and reasonably allocate the amount of exercise, so that students will not suffer from excessive fatigue or insufficient exercise intensity due to improper course load while ensuring the effect of exercise. Through the reasonable setting of intensity weights and class hour weights, students can balance the exercise intensity and time allocation of different courses, and thus achieve the goal of gradually improving physical fitness. The introduction of the academic stress analysis module adds an academic burden assessment function to the system, and constructs the difficulty coefficient of the learning course through historical performance data. The interest analysis module constructs an interest index by analyzing the data of students' interest in the course, thereby helping the system to pay more attention to students' interests when recommending physical education courses. The recommendation module is the core module of the entire system. It generates the optimal physical education course recommendation plan based on the comprehensive analysis results of physical fitness index, course intensity index, academic load index and interest index. Through multi-dimensional weight allocation, personalized physical education course recommendation is realized, and the balance of academic load, physical fitness status and interests and hobbies is considered, ensuring the reasonable coordination of sports and academics, and improving the efficiency of physical education course recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0031] Figure 1This is a structural diagram of the campus smart sports system of this embodiment.

[0032] Figure 2 Schematic diagram of the structure of the physical fitness analysis module of this embodiment.

[0033] Figure 3 Schematic diagram of the structure of the academic stress analysis module of this embodiment.

[0034] Figure 4 This is a schematic diagram of the structure of the module recommended in this embodiment. DETAILED DESCRIPTION

[0035] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0036] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0037] See also Figure 1 As shown, it is a schematic diagram of the structure of the campus smart sports system of this embodiment, and the system includes:

[0038] The data collection module is used to collect student learning course data, sports course data to be selected, student physical fitness data and questionnaire data. The learning course data includes the historical average score of the student's learning course, the full score threshold of the learning course, the number of students' learning courses, the number of class hours of students' learning courses and the total number of class hours of students' learning courses; the number of students' learning courses is the number of students' learning courses in the current semester, the number of class hours of students' learning courses is the number of class hours of each student's learning course in the current semester, and the total number of class hours of students' learning courses is the sum of the number of class hours of all learning courses of students during college. The learning courses include students' compulsory courses and elective courses except physical education courses. The sports course data to be selected include the number of class hours of sports courses to be selected and the types of sports courses to be selected. The sports courses to be selected are sports courses that students can choose this semester. The types of sports courses to be selected include individual projects and team projects, such as swimming, tennis, etc. are individual projects, and basketball, football, etc. are team projects; in this embodiment, the student learning course data and the number of sports courses to be selected are not compared. The method for collecting the physical fitness data and the questionnaire data is specifically limited, and those skilled in the art can freely set it, and it only needs to meet the collection requirements of the student's course data and the selected physical education course data, wherein the student's course data and the selected physical education course data can be obtained by importing the background data of the school's academic affairs system; the student's physical fitness data includes the student's maximum oxygen uptake, gender and resting heart rate, and the interest data includes the student's interest score for the selected physical education course, the student's intensity score for the selected physical education course, the student's daily free time and the student's social score, the student's interest score for the selected physical education course is the student's score for the interest in the selected physical education course, the intensity score for the selected physical education course is the student's score for the intensity of the selected physical education course, and the social score is defined as the student's preference score for teamwork sports; in this embodiment, the method for collecting the student's physical fitness data and the questionnaire data is not specifically limited, and those skilled in the art can freely set it, and it only needs to meet the collection requirements of the student's physical fitness data and the questionnaire data, wherein the student's physical fitness data and the questionnaire data can be obtained by means of questionnaire survey;

[0039] The physical fitness analysis module is used to analyze the physical fitness status of students based on the collected maximum oxygen uptake and resting heart rate of the students. The physical fitness analysis module is connected to the data acquisition module.

[0040] See also Figure 2 As shown, the physical fitness analysis module includes a first analysis unit, which is used to compare the collected maximum oxygen uptake a0 of the student with the preset oxygen uptake a1 to construct an oxygen uptake index SY, and set SY=(a0-a1) / a1; the first analysis unit constructs the oxygen uptake index by comparing the maximum oxygen uptake of the student with the preset oxygen uptake, so as to accurately evaluate the student's cardiopulmonary function and athletic ability, and adjusts the preset oxygen uptake according to the gender differences of the students, so that the physical fitness evaluation results are more personalized and accurate.

[0041] Please continue reading Figure 2 As shown, the physical fitness analysis module further includes the second analysis unit, which is used to construct a heart rate index to reflect the student's cardiovascular health, physical recovery and endurance, and the second analysis unit is connected to the first analysis unit;

[0042] The process of constructing the heart rate index is as follows:

[0043] The second analysis unit compares the collected student's resting heart rate b0 with the preset heart rate b1 to construct a heart rate index. If b0≤b1, the physical fitness analysis module sets the heart rate index to XL1, setting XL1=[(b1-b0) / b1] 0.5 If b0>b1, the physical fitness analysis module sets the heart rate index to XL2, setting XL2=-[(b1-b0) / b1] 0.5 The second analysis unit can distinguish different situations of too high and too low heart rate by performing different analyses on different situations, so as to improve the accuracy of constructing the heart rate index.

[0044] Please continue reading Figure 2 As shown, the physical fitness analysis module further includes a physical fitness analysis unit, which is used to construct a physical fitness index of the student to accurately analyze the physical fitness status of the student, and the physical fitness analysis unit is connected to the second analysis unit;

[0045] The process of constructing the student's physical fitness index is as follows:

[0046] The physical fitness analysis unit constructs the student's physical fitness index TN according to the construction results of the oxygen uptake index and the heart rate index, and sets TN=w1×oxygen uptake index+w2×heart rate index, where w1 is the oxygen uptake weight, w2 is the heart rate weight, w1+w2=1, w1>w2; the physical fitness analysis unit evaluates physical fitness through two indicators of oxygen uptake and resting heart rate, which is more comprehensive than a single indicator and helps to evaluate the student's physical fitness status more scientifically.

[0047] Specifically, in this embodiment, there is no specific limitation on the setting of each weight, preset oxygen uptake and preset heart rate. Those skilled in the art can set them freely as long as the setting requirements of each weight, preset oxygen uptake and preset heart rate are met. Among them, when the student is male, the best value of a1 is 50 ml / kg / min, and the best value of b1 is 80 times / minute. When the student is female, the best value of a1 is 40 ml / kg / min, and the best value of b1 is 80 times / minute. The best value of w1 is 0.55, and the best value of w2 is 0.45.

[0048] Please continue reading Figure 1As shown, the system further includes a course intensity analysis module, which is used to construct an intensity index of the selected physical education course according to the intensity score of the selected physical education course and the number of class hours of the selected physical education course, so as to provide students with appropriate physical education course suggestions and flexibly handle the adaptability of different students to different course intensities. The course intensity analysis module is connected to the physical fitness analysis module;

[0049] The course intensity analysis module constructs an intensity index of the physical education course to be selected according to the intensity score of the physical education course to be selected and the number of class hours of the physical education course to be selected, wherein:

[0050] The course intensity analysis module sets the intensity index of the ith physical education course to be selected as Qi, and sets Qi=x1×di / dmax+x2×ln(si / smax+1), where di is the intensity score of the ith physical education course to be selected, dmax is the maximum threshold of the intensity score of the physical education course to be selected, si is the number of class hours of the ith physical education course to be selected, smax is the maximum value of the physical education class hours, x1 is the intensity weight, x2 is the class hour weight, x1+x2=1, x1>x2; the course intensity analysis module constructs the intensity index through the intensity score and the number of class hours of the course, and can provide students with appropriate physical education course recommendations, avoid excessive or insufficient exercise, and promote the continuous improvement of students' physical fitness.

[0051] Specifically, in this embodiment, there is no specific limitation on the setting of each weight, and technical personnel in this field can set it freely as long as the setting requirements of each weight are met. Among them, the optimal value of x1 is 0.7, and the optimal value of x2 is 0.3; the maximum value of the physical education course hours described in this embodiment is the maximum value of the number of hours in the selected physical education courses, which can be obtained by importing from the background of the academic affairs system.

[0052] Please continue reading Figure 1 As shown, the system also includes a learning pressure analysis module, which is used to construct a learning course difficulty coefficient based on the collected historical scores of students' learning courses, and to construct an academic load index based on the construction result of the course difficulty coefficient and the number of students' learning courses and the number of class hours of students' learning courses. The academic pressure analysis module is connected to the course intensity analysis module;

[0053] See also Figure 3 As shown, the academic stress analysis module includes a difficulty coefficient analysis unit, which is used to construct the difficulty coefficient of the learning course;

[0054] The process of constructing the difficulty coefficient of the learning course is as follows:

[0055] The difficulty coefficient analysis unit constructs the difficulty coefficient of the learning course according to the collected historical scores of the students in the learning course, so as to balance the time allocation between physical learning and academic learning, wherein:

[0056] The difficulty coefficient analysis unit sets the difficulty coefficient of the jth course of the student's course as Rj, and sets Mrj is the rj-th historical average score data of the j-th course in the student's study course, mj is the number of historical average score data of the j-th course in the student's study course, and Mj is the full score threshold of the j-th course in the student's study course; the difficulty coefficient analysis unit constructs the course difficulty coefficient through historical scores, and combines the academic load index to help analyze the student's academic burden and balance the time allocation between physical education learning and academic learning.

[0057] Please continue reading Figure 3 As shown, the academic stress analysis module includes an academic load analysis unit, which is used to construct an academic load index to provide students with a more scientific and reasonable course arrangement. The academic load analysis unit is connected to the difficulty coefficient analysis unit;

[0058] The construction process of the academic load index is as follows:

[0059] The academic load analysis unit constructs an academic load index according to the construction result of the course difficulty coefficient and the collected number of courses studied by the students and the number of class hours of the courses studied by the students. The academic load analysis unit sets the student's academic load index to F, and sets:

[0060] Hj is the number of class hours for the jth course in the student's study course, C is the number of courses studied by the student, Z is the total number of class hours for the student's study courses, f0 is the preset difficulty coefficient threshold, α1 is the course quantity weight, α2 is the course difficulty weight, α1+α2=1, α1>α2; the academic load analysis unit not only considers the number of courses, but also combines the course difficulty and class hours. The generated academic load index is more comprehensive. By dynamically adjusting the difficulty coefficient threshold, the scientific nature of academic stress assessment is improved.

[0061] Specifically, in this embodiment, there is no specific limitation on the values ​​of each weight and the preset difficulty coefficient threshold. Technical personnel in this field can set them freely as long as the value requirements of each weight and the preset difficulty coefficient threshold are met. Among them, the best value of α1 is 0.65, the best value of α2 is 0.35, and the best value of f0 is 0.4.

[0062] Please continue reading Figure 1As shown, the system further includes an interest analysis module, which is used to construct the interest index of students so as to recommend sports courses that students are interested in according to their interest tendencies, and the interest analysis module is connected to the academic stress analysis module;

[0063] The process of constructing the student's interest index is as follows:

[0064] The interest analysis module constructs the student interest index according to the collected student interest scores for physical education courses, wherein:

[0065] The interest analysis module sets the student's interest index for the i-th selected physical education course as Pi, setting Pi = 3 × (ui / u0) 2 +2×(ui / u0) 3 , where ui is the student's interest score for the i-th physical education course to be selected, and u0 is the preset score threshold; the interest analysis module constructs an interest index by collecting students' interest scores for physical education courses, so as to recommend content of interest to students based on their interest tendencies, thereby improving students' sports participation and learning interest. At the same time, the construction process of the interest index adopts a refined evaluation based on the preferences of each student, so that the course recommendation is more in line with the students' interests and increases the students' active participation.

[0066] Specifically, the preset score threshold in this embodiment is the maximum value of the interest scoring system. For example, if the scoring system is 10 points, the value of u0 is 10.

[0067] Please continue reading Figure 1 As shown, the system also includes a recommendation module, which is used to recommend physical education courses to students based on the analysis results of the students' physical fitness status, the intensity index of the selected physical education courses, and the construction results of the academic load index and the interest index, and adjust the recommendation process based on the collected student social scores and the students' daily free time. The recommendation module is connected to the interest analysis module.

[0068] See also Figure 4 As shown, the recommendation module includes a recommendation unit, which is used to recommend physical education courses to students based on the construction results of the students' physical fitness index, physical education course intensity index, academic load index and interest index, so as to ensure that the recommended courses meet the students' personal physical fitness level, study pressure and interests and hobbies;

[0069] The process for making a physical education course referral to a student is as follows:

[0070] The recommendation unit recommends physical education courses to students based on the results of constructing the student's physical fitness index, physical education course intensity index, academic load index and interest index, wherein:

[0071] The recommendation unit sets the recommendation coefficient of the i-th selected physical education course as Ti, and sets: Ti = -|[t1×TN-t2×ln(F+1) / ln2+t3×(e Pi -1) / (e-1)]-γ×Qi|, where t1 is the physical fitness weight, t2 is the academic load weight, t3 is the interest weight, t1+t2+t3=1, t1>t3≥t2, and γ is the preset adjustment coefficient;

[0072] The recommendation unit ranks the recommendation coefficients of various physical education courses, and pushes the physical education courses with the largest recommendation coefficients to users as recommended courses; the recommendation unit integrates the physical fitness index, academic load index, interest index and course intensity index to ensure that the recommended courses fully meet the students' needs in all aspects and provide the best course selection. At the same time, the complex weight distribution of physical fitness, academic load, interest and course intensity ensures that the recommendations are reasonable, which not only ensures that the course difficulty is moderate, but also fully encourages students' interests.

[0073] Specifically, this embodiment does not make any specific limitations on the setting of each weight and the preset adjustment coefficient. Those skilled in the art can set it freely, and it is only necessary to meet the setting requirements of each weight and the preset adjustment coefficient. Among them, the best value of t1 is 0.6, the best value of t2 is 0.2, the best value of t3 is 0.2, and the best value of γ is 0.7. This embodiment does not make any specific limitations on the sorting method. Those skilled in the art can set it freely, and it is only necessary to meet the sorting requirements. Among them, sorting can be performed by bubble sort.

[0074] Please continue reading Figure 4 As shown, the recommendation module also includes a social analysis unit, which is used to construct social factors and adjust the sports course recommendation process. The social situation is dynamically adjusted to the coefficient of the recommended course. The social analysis unit is connected to the recommendation unit;

[0075] The process for making adjustments to the physical education course recommendation process is as follows:

[0076] The social analysis unit constructs the social factor Y0 with the collected student social score y0, and sets: Y0=y0 / y1, where y1 is the social score threshold;

[0077] The social analysis unit compares the social factor with the preset social factor threshold value Y1 to adjust the sports course recommendation process. If Y0≤Y1 and the i-th sports course type to be selected is a team project, the social analysis unit sets the recommendation coefficient of the i-th sports course to be selected to Ti1, and sets Ti1=Ti-η×(Y1-Y0) / Y1. If Y0>Y1 and the i-th sports course type to be selected is an individual project, the social analysis unit does not make any adjustments. If Y0>Y1 and the i-th sports course type to be selected is a team project, the social analysis unit does not make any adjustments. If Y0>Y1 and the i-th sports course type to be selected is an individual project, the social analysis unit sets the recommendation coefficient of the i-th sports course to be selected to Ti2, and sets Ti2=Ti-η×(Y1-Y0) / Y1. i2=Ti-η×(Y0-Y1) / Y1, η is a preset correction ratio coefficient; the social analysis unit recommends more suitable social or non-social physical education courses by analyzing social factors, helping students to choose appropriate activities based on their social abilities, enhance their social abilities or avoid social fatigue. At the same time, the coefficients of recommended courses are dynamically adjusted according to the social situation, helping students with high or low sociality to choose activities that meet their social needs in a balanced manner.

[0078] Specifically, this embodiment does not impose any specific limitation on the setting of the preset social factor threshold and the preset correction ratio coefficient. Those skilled in the art can set them freely as long as the setting requirements of the preset social factor threshold and the preset correction ratio coefficient are met, where the optimal value of Y1 is 0.6, and the optimal value of η is 0.21; in this embodiment, the social score threshold is the maximum value of the social score, which is the same as the setting process of the preset score threshold.

[0079] Please continue reading Figure 4 As shown, the recommendation module further includes an idle analysis unit, which is used to optimize the recommendation process of physical education courses, and the idle analysis unit is connected to the social analysis unit;

[0080] The process of optimizing the recommendation process for physical education courses is as follows:

[0081] The idle analysis unit compares the collected daily idle time g0 of the students with the preset idle time g1 to optimize the recommendation process of physical education courses. If g0≤g1, the idle analysis unit determines that the student's idle time is normal and does not perform optimization. If g0≥g1, the idle analysis unit determines that the student's idle time is abnormal and optimizes the physical education course recommendation process. The optimized preset adjustment coefficient is set to γ1, and γ1 is set to γ×{1+exp[3(g0-g1) / (g0+g1)-3]}. When γ1≥γ0, γ1 takes γ0, and γ0 is the preset adjustment threshold. For students with too much or too little free time, the idle analysis unit can reasonably adjust the course recommendations to ensure that the recommended courses are more in line with the students' actual life rhythm, avoid time management problems, and ultimately improve the recommendation efficiency of physical education courses.

[0082] Specifically, in this embodiment, there is no specific limitation on the setting of the preset idle time and the preset adjustment threshold. Technical personnel in this field can set them freely as long as the setting requirements of the preset idle time and the preset adjustment threshold are met. Among them, the optimal value of g1 is 3h, and the optimal value of γ0 is 0.85.

[0083] Specifically, the campus smart sports system described in this embodiment is applied to the recommendation of school physical education courses. Through multi-angle analysis of students' physical fitness, academic load, interests, social and free time, the system can intelligently avoid the deviation of a single factor, provide comprehensive and scientific course recommendations, and improve the efficiency of physical education course recommendations.

[0084] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. A campus smart sports system, characterized in that: include, Data collection module, used to collect students' learning course data, selected physical education course data, students' physical fitness data and questionnaire data; Physical fitness analysis module, used to analyze students' physical fitness status based on the collected maximum oxygen uptake and resting heart rate of students; A course intensity analysis module is used to construct an intensity index of the selected physical education course according to the intensity score of the selected physical education course and the number of class hours of the selected physical education course; The academic stress analysis module is used to construct the difficulty coefficient of the learning course according to the collected historical scores of the students' learning courses, and to construct the academic load index according to the construction results of the course difficulty coefficient and the number of courses studied by the students and the number of class hours of the courses studied by the students; The interest analysis module is used to construct the student interest index based on the collected student interest scores for physical education courses; The recommendation module is used to recommend physical education courses to students based on the analysis results of the students' physical fitness status, the intensity index of the selected physical education courses, the construction results of the academic load index and the interest index, and adjust the recommendation process based on the collected student social scores and the students' daily free time.

2. The campus smart sports system according to claim 1, characterized in that: The physical fitness analysis module is provided with a first analysis unit, a second analysis unit and a physical fitness analysis unit, wherein the first analysis unit is used to compare the collected maximum oxygen uptake a0 of the student with the preset oxygen uptake a1 to construct an oxygen uptake index; The second analysis unit compares the collected student's resting heart rate b0 with the preset heart rate b1 to construct a heart rate index. If b0≤b1, the physical fitness analysis module sets the heart rate index to XL1, setting XL1=[(b1-b0) / b1] 0.5 If b0>b1, the physical fitness analysis module sets the heart rate index to XL2, setting XL2=-[(b1-b0) / b1] 0.5 .

3. The campus smart sports system according to claim 2 is characterized in that: The physical fitness analysis unit is used to construct the student's physical fitness index TN according to the construction results of the oxygen uptake index and the heart rate index, and set TN=w1×oxygen uptake index+w2×heart rate index, where w1 is the oxygen uptake weight and w2 is the heart rate weight.

4. The campus smart sports system according to claim 3 is characterized in that: The course intensity analysis module sets the intensity index of the i-th selected physical education course as Qi, and sets Qi=x1×di / dmax+x2×ln(si / smax+1), where di is the intensity score of the i-th selected physical education course, dmax is the maximum threshold of the intensity score of the selected physical education course, si is the number of class hours of the i-th selected physical education course, smax is the maximum value of the physical education course class hours, x1 is the intensity weight, and x2 is the class hour weight.

5. The campus smart sports system according to claim 4 is characterized in that: The academic stress distraction module is provided with a difficulty coefficient analysis unit and an academic load analysis unit. The difficulty coefficient analysis unit constructs the difficulty coefficient of the learning course according to the collected historical scores of the students in the learning course, wherein: The difficulty coefficient analysis unit sets the difficulty coefficient of the jth course of the student's course as Rj, and sets Mrj is the rj-th historical average score data of the j-th course in the student's course, mj is the number of historical average score data of the j-th course in the student's course, and Mj is the full score threshold of the j-th course in the student's course.

6. The campus smart sports system according to claim 5, characterized in that: The academic load analysis unit is used to construct an academic load index according to the construction result of the course difficulty coefficient and the collected number of students' learning courses and the number of class hours of students' learning courses. The academic load analysis unit sets the student's academic load index to F, and sets: Hj is the number of hours of the jth course studied by the student, C is the number of courses studied by the student, Z is the total number of hours of courses studied by the student, f0 is the preset difficulty coefficient threshold, α1 is the course quantity weight, α2 is the course difficulty weight, α1+α2=1.

7. The campus smart sports system according to claim 6, characterized in that: The interest analysis module constructs the student interest index according to the collected student interest scores for physical education courses, wherein: The interest analysis module sets the student's interest index for the i-th selected physical education course as Pi, setting Pi = 3 × (ui / u0) 2 +2×(ui / u0) 3 , where ui is the student’s interest score for the i-th physical education course to be selected, and u0 is the preset score threshold.

8. The campus smart sports system according to claim 7, characterized in that: The recommendation module is provided with a recommendation unit, a social analysis unit and a free time analysis unit. The recommendation unit is used to recommend physical education courses to students according to the construction results of the students' physical fitness index, physical education course intensity index, academic load index and interest index, wherein: The recommendation unit sets the recommendation coefficient of the i-th selected physical education course as Ti, and sets: Ti = -|[t1×TN-t2×ln(F+1) / ln2+t3×(ePi-1) / (e-1)]-γ×Qi|, where t1 is the physical fitness weight, t2 is the academic load weight, t3 is the interest weight, t1+t2+t3=1, t1>t3≥t2, and γ is the preset adjustment coefficient; The recommendation unit sorts the recommendation coefficients of the physical education courses, and pushes the physical education course with the largest recommendation coefficient to the user as a recommended course.

9. The campus smart sports system according to claim 8, characterized in that: The social analysis unit constructs the social factor Y0 with the collected student social score y0, and sets: Y0=y0 / y1, where y1 is the social score threshold; The social analysis unit compares the social factor with the preset social factor threshold Y1 to adjust the sports course recommendation process. If Y0≤Y1 and the i-th sports course type to be selected is a team project, the social analysis unit sets the recommendation coefficient of the i-th sports course to be selected to Ti 1, and sets Ti 1=Ti-η×(Y1-Y0) / Y1. If Y0>Y1 and the i-th sports course type to be selected is an individual project, the social analysis unit does not make any adjustment. If Y0>Y1 and the i-th sports course type to be selected is a team project, the social analysis unit does not make any adjustment. If Y0>Y1 and the i-th sports course type to be selected is an individual project, the social analysis unit sets the recommendation coefficient of the i-th sports course to be selected to Ti2, and sets Ti2=Ti-η×(Y0-Y1) / Y1, where η is a preset correction proportional coefficient.

10. The campus smart sports system according to claim 9, characterized in that: The idle analysis unit compares the collected daily idle time g0 of the students with the preset idle time g1 to optimize the adjustment process of the physical education course recommendation process. If g0≤g1, the idle analysis unit determines that the student's idle time is normal and does not perform optimization. If g0≥g1, the idle analysis unit determines that the student's idle time is abnormal and optimizes the physical education course recommendation process, and sets the optimized preset adjustment coefficient to γ1.

Images