A student attendance management system based on big data

Abstract

The present invention relates to the technical field of big data student management, and in particular to a student attendance management system based on big data, the system comprising: an information acquisition module for acquiring student attendance information and student grade information of past courses; an attendance analysis module for analyzing the attendance rate of students in past courses; an analysis optimization module for optimizing the analysis process of the attendance rate of students in past courses; a grade fluctuation analysis module for analyzing the volatility of the grades of students in past courses; a correlation analysis module for analyzing the correlation between student attendance rate and student grades; a management module for managing the attendance standards of students within a management cycle, and providing users with abnormal student attendance warnings based on the management results of the student attendance standards within the acquired management cycle, the number of absences of students, and the number of late arrivals of students. The present invention improves the efficiency of student attendance management and improves teaching performance at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of big data student management, and in particular to a student attendance management system based on big data. Background Art

[0002] With the in-depth development of educational informatization, student attendance management has become an important task in school management. Traditional attendance management methods mainly rely on manual recording and statistics, which have problems such as low efficiency and prone to errors. In order to solve these problems, we proposed a student attendance management system based on big data, aiming to use advanced technical means to improve the efficiency of attendance management, accurately record student attendance, and provide a scientific basis for school management.

[0003] Chinese Patent Publication No.: CN113469157A discloses a student attendance management system and method based on big data, the system includes a monitoring terminal, a student attendance analysis module, a student abnormal behavior analysis module and an attendance rate summary module; the monitoring terminal obtains the monitoring terminals distributed at different positions, retrieves student data information to adjust the shooting angle and set the shooting area size; the student attendance analysis module obtains the distribution number of student head areas in different time periods at the monitoring terminal, and then analyzes the student attendance rate; the student abnormal behavior analysis module obtains the difference number of student heads in different time periods, and analyzes the reason for the difference as the student abnormal behavior blocking the student head or the abnormal distribution of the queue resulting in a decrease in the number of student attendance; the attendance rate summary analysis module sends the compared attendance summary table to the teacher terminal and publishes the attendance score in a timely manner to prevent students from intentionally absent; it can be seen that when managing the student's attendance, the scheme only analyzes the attendance rate, and there is a problem of low efficiency in student attendance management. Summary of the invention

[0004] To this end, the present invention provides a student attendance management system based on big data to overcome the problem of low efficiency of student attendance management in the prior art.

[0005] To achieve the above-mentioned purpose, the present invention provides a student attendance management system based on big data, the system comprising: an information acquisition module for acquiring student past course attendance information and student past course grade information;

[0006] The attendance analysis module is used to analyze the attendance rate of students in previous courses based on the number of absences, the number of lateness and the length of lateness of previous courses obtained;

[0007] The grade fluctuation analysis module is used to analyze the fluctuation of students' grades in previous courses based on their grades in previous courses;

[0008] The correlation analysis module is used to analyze the correlation between student attendance rate and student grades based on the analysis results of student attendance rate of each past course and the analysis results of student grade fluctuation of each past course;

[0009] The management module is used to manage the attendance standards of students within the management period according to the analysis results of the correlation between student attendance rate and student grades. It is also used to obtain the number of student absences and the number of student lateness during the management period, and to issue abnormal attendance warnings to users based on the management results of student attendance standards, the number of student absences and the number of student lateness during the management period.

[0010] Furthermore, the attendance analysis module is provided with a lateness duration analysis unit and an attendance rate analysis unit, and the lateness duration analysis unit is used to compare the acquired lateness duration of the student's previous courses with the preset duration t1, and analyze the abnormality of the student's lateness duration according to the comparison result, wherein:

[0011] When Wtiz0≤t1, the lateness duration analysis unit determines that the zth lateness duration of the Wth student in the past course numbered i is normal;

[0012] When Wtiz0>t1, the lateness duration analysis unit determines that the zth lateness duration of the Wth student in the past course numbered i is abnormal;

[0013] Wherein, Wtiz0 is the zth lateness duration of the Wth student in the previous course numbered i, 0<i<I, I is the number of previous courses, 0<z≤ZWi, ZWi is the number of latenesses of the Wth student in the previous course numbered i, 0<W≤wq, wq is the number of students.

[0014] Further, the attendance rate analysis unit is used to analyze the attendance rate of students in each past course according to the analysis result of the abnormality of the student's lateness duration and the number of absences in the student's past courses. The attendance rate analysis unit sets the attendance rate of the Wth student in the past course numbered i as Wic, and sets: Wic=1-Wiq / (Wiq+Wicq)-α×Wiy / (Wiq+Wicq);

[0015] Where α is the penalty coefficient, 0<α<0.5, and Wiy is the number of abnormal lateness durations of the Wth student in the previous courses numbered i.

[0016] Further, an analysis and optimization module is used to optimize the analysis process of the attendance rate of students in each past course according to the duration of lateness of students in each past course and the number of class hours of each past course; the analysis and optimization module is provided with a first optimization unit and a second optimization unit, the first optimization unit is used to calculate the total duration of lateness of students in each past course by the duration of lateness of students in each past course and the number of lateness of students, and compare the calculation result with the preset duration threshold value Y0, and optimize the analysis process of the attendance rate of students in each past course according to the comparison result, wherein:

[0017] when When , the first optimization unit determines that the total lateness time of the Wth student in the past course numbered i is normal, and no optimization is performed;

[0018] when When , the first optimization unit determines that the total lateness time of the Wth student in the past courses numbered i is abnormal, and optimizes the analysis process of the attendance rate of the Wth student in the past courses numbered i, and sets the optimized penalty coefficient as α', setting: .

[0019] Furthermore, the second optimization unit compares the number of class hours of each past course with the preset number of class hours k0, and performs secondary optimization on the analysis process of the student attendance rate of each past course according to the comparison result, wherein:

[0020] When Li≤k0, the second optimization unit determines that the number of class hours of the past course numbered i is normal and does not perform optimization;

[0021] When Li>k0, the second optimization unit determines that the number of class hours of the past course numbered i is abnormal, and performs secondary optimization on the analysis process of the student attendance rate of the past course numbered i, and sets the optimized preset duration threshold to Y0', and sets Y0'=Y0×[1+β×(Li-k0) / Li];

[0022] Among them, Li is the number of class hours of the previous course numbered i, and β is the preset adjustment coefficient.

[0023] Furthermore, the grade fluctuation analysis module analyzes the fluctuation of the student's grades in each past course according to the student's past course grades, wherein:

[0024] when When , the grade fluctuation analysis module determines that the grade fluctuation of the student in the previous course numbered i is normal;

[0025] when When , the score fluctuation analysis module determines that the score fluctuation of the student in the previous course numbered i is abnormal;

[0026] Among them, Wicj is the score obtained by the Wth student in the previous course numbered i, icj is the average score of the previous courses numbered i, and by is the preset fluctuation coefficient.

[0027] Furthermore, the correlation analysis module is provided with a first analysis unit and a second analysis unit, wherein the first analysis unit is used to analyze the correlation between the attendance rate of each past course and the grades of each past course according to the analysis results of the attendance rate of each past course and the grades of each past course, and the first analysis unit sets the correlation coefficient between the attendance rate of the past course numbered i and the grades of the past courses as ri, and sets:

[0028] Among them, Wic 均 is the average student attendance rate of the past courses numbered i.

[0029] Furthermore, the second analysis unit is used to analyze the correlation between the student attendance rate and the student's grades according to the analysis results of the correlation between the student attendance rate of each past course and the student's grades of each past course and the analysis results of the volatility of the student's grades of each past course. The second analysis unit sets the correlation coefficient between the student attendance rate and the student's grades as R, and sets:

[0030] Among them, Hi is the weight of the previous course numbered i. When the fluctuation of the student's grades in the previous course numbered i is normal, the value of Hi is h1; when the fluctuation of the student's grades in the previous course numbered i is abnormal, the value of Hi is h2.

[0031] Furthermore, the management module is provided with a first management unit and a second management unit, wherein the first management unit is used to manage the student attendance standard within the management period according to the analysis result of the correlation between the student attendance rate and the student performance, wherein:

[0032] When R≤R0, the first management unit determines that the correlation between the student's attendance rate and the student's grades is weak, and sets the student's absence threshold to U1 and the lateness threshold to E1 within the management period;

[0033] When R>R0, the first management unit determines that the student attendance rate is highly correlated with the student's grades, and sets the student's absence threshold to U2 and the lateness threshold to E2 within the management period;

[0034] Among them, R0 is the correlation threshold.

[0035] Furthermore, the second management unit is used to provide the user with an abnormal student attendance warning according to the management result of the student attendance standard within the management period, the number of student absences and the number of student lateness, wherein:

[0036] When GMq≤Uu, if GMc≤Ee, the second management unit determines that the attendance of the Wth student is normal within the management period, and does not issue an abnormal attendance warning to the user; if GMc>Ee, the second management unit determines that the attendance of the Wth student is abnormal within the management period, and issues an abnormal attendance warning to the user;

[0037] When GMq>Uu, the second management unit determines that the Wth student has abnormal attendance during the management period, and issues an abnormal attendance warning to the user;

[0038] Among them, GMq is the number of absences of the Wth student in the management cycle, GMc is the number of lateness of the Wth student in the management cycle; Uu is the management result of the absence threshold, u=1,2; Ee is the management result of the lateness threshold, e=1,2.

[0039] Compared with the prior art, the beneficial effects of the present invention are that the attendance analysis module improves the accuracy of the abnormality analysis of the student's lateness duration by setting a preset time length, thereby improving the accuracy of the student's attendance rate analysis, and improves the accuracy of the analysis of the correlation between the student's attendance rate and the student's grade by setting a preset penalty coefficient to improve the accuracy of the analysis of the student's attendance rate, thereby improving the accuracy of the analysis of the correlation between the student's attendance rate and the student's grade, the analysis optimization module reduces the influence of the total length of student lateness on the attendance rate analysis by setting a preset time length threshold, thereby improving the accuracy of the analysis of the student's attendance rate, thereby improving the accuracy of the analysis of the correlation between the student's attendance rate and the student's grade, and reduces the influence of the excessive number of class hours of previous courses on the attendance rate analysis by setting a preset number of class hours and a preset adjustment coefficient, thereby improving the accuracy of the analysis of the student's attendance rate, thereby improving the accuracy of the analysis of the correlation between the student's attendance rate and the student's grade. The grade fluctuation analysis module improves the accuracy of the analysis of student grade fluctuations in each past course by setting a preset fluctuation coefficient, thereby improving the accuracy of the analysis of the correlation between student attendance rate and student grades. The correlation analysis module improves the accuracy of the analysis of the correlation between student attendance rate and student grades by analyzing the correlation between student attendance rate and student grades in each past course, and improves the accuracy of the analysis of the correlation between student attendance rate and student grades by setting the weight of each past course. The management module improves the accuracy of the analysis of student attendance standards within the management cycle by setting a correlation threshold, thereby improving the accuracy of abnormal student attendance warnings to users, and improves the accuracy of abnormal student attendance warnings to users by analyzing the abnormality of student attendance within the management cycle, thereby improving the efficiency of student attendance management and improving teaching results at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a structural diagram of the student attendance management system based on big data in this embodiment.

[0041] Figure 2 Schematic diagram of the structure of the attendance analysis module in this embodiment.

[0042] Figure 3 This is a schematic diagram of the structure of the analysis and optimization module of this embodiment.

[0043] Figure 4 Schematic diagram of the structure of the correlation analysis module in this embodiment.

[0044] Figure 5 It is a structural diagram of the management module of this embodiment. DETAILED DESCRIPTION

[0045] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0047] It should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0048] See also Figure 1 As shown, it is a structural diagram of the student attendance management system based on big data in this embodiment, and the system includes:

[0049] The information acquisition module is used to obtain the student's past course attendance information and the student's past course grade information; the past course attendance information includes the number of absences of the student in the past courses, the number of attendances of the student in the past courses, the number of lateness of the student in the past courses and the length of lateness of the student in the past courses; the student's past course grade information includes the grade of each past course of the student, the average grade of the students in each past course, and the number of class hours of each past course. The class hour is the teaching time unit set in the past courses. One class hour usually represents a standard time period for teaching activities. The number of class hours of past courses is the number of standard time periods included in the past courses. This implementation In the example, no specific limitation is made on the method of obtaining the student's previous course attendance information and the student's previous course grade information, and those skilled in the art can freely set it, and only need to meet the requirements for obtaining the student's previous course attendance information and the student's previous course grade information, wherein the student's previous course attendance information and the student's previous course grade information can be obtained by importing data from the educational management platform; it is worth noting that the student's previous course attendance information and the student's previous course grade information in this embodiment are information of the same group of students, and their previous course attendance information and previous course grade information in the school's historical semester can be used as the previous course attendance information and the student's previous course grade information;

[0050] An attendance analysis module, used to analyze the attendance rate of students in each past course according to the acquired number of absences, number of lateness and duration of lateness of students in past courses, and the attendance analysis module is connected to the information acquisition module;

[0051] An analysis and optimization module, used to optimize the analysis process of the attendance rate of students in each past course according to the length of time that students were late for each past course and the number of class hours of each past course, and the analysis and optimization module is connected to the attendance analysis module;

[0052] A grade fluctuation analysis module, used to analyze the fluctuation of students' grades in previous courses according to their grades in previous courses, and the grade fluctuation analysis module is connected to the information acquisition module;

[0053] A correlation analysis module, used to analyze the correlation between student attendance rate and student grades according to the analysis results of student attendance rate of each past course and the analysis results of student grade fluctuation of each past course, and the correlation analysis module is connected with the attendance analysis module and the grade fluctuation analysis module;

[0054] A management module is used to manage the attendance standards of students within a management period according to the analysis results of the correlation between student attendance rate and student grades, and is also used to obtain the number of student absences and the number of student tardiness within the management period, and to issue abnormal student attendance warnings to users according to the management results of the student attendance standards, the number of student absences and the number of student tardiness within the management period. The management module is connected to the correlation analysis module; the attendance standards described in this embodiment include an absence threshold and a tardiness threshold, the absence threshold is the maximum number of absences allowed for students within the management period, and the tardiness threshold is the maximum number of tardiness allowed for students within the management period; the management period is the semester period that students are currently attending in the school year; in this embodiment, no specific limitation is made on the method for obtaining the number of student absences and the number of student tardiness within the management period, and those skilled in the art can freely set it, as long as the requirements for obtaining the number of student absences and the number of student tardiness within the management period are met, wherein the number of student absences and the number of student tardiness within the management period can be obtained through interaction.

[0055] Specifically, the student attendance management system based on big data described in this embodiment is applied to the management of attendance standards for students who have taken the same past courses. By analyzing the historical attendance rates of students in each past course and analyzing the volatility of their historical grades in each past course, the correlation between student attendance rates and student grades is analyzed based on the analysis results of attendance rate and grade volatility. The student attendance standards are managed based on the analysis results, which improves the efficiency of student attendance management and improves teaching results at the same time.

[0056] See also Figure 2 As shown, it is a schematic diagram of the structure of the attendance analysis module of this embodiment, and the attendance analysis module includes:

[0057] The lateness time analysis unit is used to analyze the abnormality of students' lateness time based on the acquired lateness time of students' previous courses;

[0058] The attendance rate analysis unit is used to analyze the attendance rate of students in each previous course according to the analysis result of the abnormality of the student's lateness duration and the number of absences in the student's previous courses. The attendance rate analysis unit is connected to the lateness duration analysis unit.

[0059] See also Figure 3 As shown, it is a schematic diagram of the structure of the analysis and optimization module of this embodiment, and the analysis and optimization module includes:

[0060] The first optimization unit is used to optimize the analysis process of the attendance rate of students in each past course according to the length of time the students were late for each past course and the number of times the students were late for each past course;

[0061] The second optimization unit is used to perform secondary optimization on the analysis process of the student attendance rate of each past course according to the acquired number of class hours of each past course. The second optimization unit is connected to the first optimization unit.

[0062] See also Figure 4 As shown, it is a schematic diagram of the structure of the correlation analysis module of this embodiment, and the correlation analysis module includes:

[0063] The first analysis unit is used to analyze the correlation between the attendance rate of students in each past course and the grades of students in each past course according to the analysis results of the attendance rate of students in each past course and the grades of students in each past course;

[0064] The second analysis unit is used to analyze the correlation between student attendance rate and student grades according to the analysis results of the correlation between student attendance rate and student grades of each past course and the analysis results of the volatility of student grades of each past course. The second analysis unit is connected to the first analysis unit.

[0065] See also Figure 5 As shown, it is a schematic diagram of the structure of the management module of this embodiment, and the management module includes:

[0066] The first management unit is used to manage the attendance standards of students within the management cycle according to the analysis results of the correlation between the student attendance rate and the student performance;

[0067] An acquisition unit is used to obtain the number of absences and tardiness of students within a management period;

[0068] The second management unit is used to issue abnormal attendance warnings to users based on the management results of the student attendance standards within the management period, the number of student absences and the number of student lateness. The second management unit is connected to the first management unit and the acquisition unit.

[0069] Specifically, the lateness time analysis unit compares the acquired lateness time of the student's previous courses with the preset time t1, and analyzes the abnormality of the student's lateness time according to the comparison result, wherein:

[0070] When Wtiz0≤t1, the lateness duration analysis unit determines that the zth lateness duration of the Wth student in the past course numbered i is normal;

[0071] When Wtiz0>t1, the lateness duration analysis unit determines that the zth lateness duration of the Wth student in the past course numbered i is abnormal;

[0072] Wherein, Wtiz0 is the zth lateness duration of the Wth student in the previous course numbered i, 0<i<I, I is the number of previous courses, 0<z≤ZWi, ZWi is the number of latenesses of the Wth student in the previous course numbered i, 0<W≤wq, wq is the number of students.

[0073] Specifically, the tardiness duration analysis unit improves the accuracy of the abnormality analysis of students' tardiness duration by setting a preset duration, thereby improving the accuracy of the analysis of students' attendance rate, thereby improving the accuracy of the analysis of the correlation between students' attendance rate and students' grades, and ultimately improving the efficiency of students' attendance management while improving teaching results; in this embodiment, there is no specific limitation on the setting of the preset duration, and technical personnel in this field can set it freely as long as the setting requirements of the preset duration are met, where the optimal value of t1 is 6 minutes; it is worth noting that in this embodiment, the numbers of previous courses are positive integers from 1 to I, and each previous course has a unique number.

[0074] Specifically, the attendance rate analysis unit analyzes the attendance rate of students in each past course according to the analysis result of the abnormality of the student's lateness duration and the number of absences in the student's past courses. The attendance rate analysis unit sets the attendance rate of the Wth student in the past course numbered i as Wic, and sets: Wic=1-Wiq / (Wiq+Wicq)-α×Wiy / (Wiq+Wicq);

[0075] Among them, Wiq is the number of historical absences of the Wth student in the previous courses numbered i, Wicq is the number of historical attendances of the Wth student in the previous courses numbered i, α is the penalty coefficient, 0<α<0.5, and Wiy is the number of abnormal lateness durations of the Wth student in the previous courses numbered i.

[0076] Specifically, the attendance analysis unit improves the accuracy of student attendance analysis by setting a preset penalty coefficient, thereby improving the accuracy of the analysis of the correlation between student attendance and student performance, thereby improving the efficiency of student attendance management and improving teaching performance at the same time; in this embodiment, there is no specific limitation on the setting of the preset penalty coefficient, and technical personnel in this field can set it freely, as long as the setting requirements of the preset penalty coefficient are met, where the optimal value of α is 0.2.

[0077] Specifically, the first optimization unit calculates the total time that students were late for each past course by combining the time that students were late for each past course and the number of times that students were late, and compares the calculation result with the preset time threshold Y0, and optimizes the analysis process of the attendance rate of students in each past course according to the comparison result, wherein:

[0078] when When , the first optimization unit determines that the total lateness time of the Wth student in the past course numbered i is normal, and no optimization is performed;

[0079] when When , the first optimization unit determines that the total lateness time of the Wth student in the past courses numbered i is abnormal, and optimizes the analysis process of the attendance rate of the Wth student in the past courses numbered i, and sets the optimized penalty coefficient as α', setting: .

[0080] Specifically, the first optimization unit sets a preset time threshold to reduce the impact of the total duration of students' tardiness on the attendance analysis, thereby improving the accuracy of the student attendance analysis, and further improving the accuracy of the analysis of the correlation between student attendance and student performance, ultimately improving the efficiency of student attendance management, while improving teaching performance; in this embodiment, there is no specific limitation on the setting of the preset time threshold, and technical personnel in this field can set it freely, as long as the setting requirements of the preset time threshold are met, where the optimal value of Y0 is 45min.

[0081] Specifically, the second optimization unit compares the number of class hours of each past course with the preset number of class hours k0, and performs secondary optimization on the analysis process of the student attendance rate of each past course according to the comparison result, wherein:

[0082] When Li≤k0, the second optimization unit determines that the number of class hours of the past course numbered i is normal and does not perform optimization;

[0083] When Li>k0, the second optimization unit determines that the number of class hours of the past course numbered i is abnormal, and performs secondary optimization on the analysis process of the student attendance rate of the past course numbered i, and sets the optimized preset duration threshold to Y0', and sets Y0'=Y0×[1+β×(Li-k0) / Li];

[0084] Among them, Li is the number of class hours of the previous course numbered i, β is the preset adjustment coefficient, 0<β<0.6.

[0085] Specifically, the second optimization unit reduces the impact of the excessive number of class hours in previous courses on the attendance rate analysis by setting a preset number of class hours and a preset adjustment coefficient, thereby improving the accuracy of the student attendance rate analysis, and further improving the accuracy of the correlation analysis between the student attendance rate and the student performance, ultimately improving the student attendance management efficiency, while improving the teaching performance; in this embodiment, there is no specific limitation on the setting of the preset number of class hours and the preset adjustment coefficient, and technical personnel in this field can set them freely, as long as the setting requirements of the preset number of class hours and the preset adjustment coefficient are met, where the optimal value of k0 is 60, and the optimal value of β is 0.4.

[0086] Specifically, the grade fluctuation analysis module analyzes the fluctuation of students' grades in previous courses according to their previous course grades, where:

[0087] when When , the grade fluctuation analysis module determines that the grade fluctuation of the student in the previous course numbered i is normal;

[0088] when When , the score fluctuation analysis module determines that the score fluctuation of the student in the previous course numbered i is abnormal;

[0089] Among them, Wicj is the score obtained by the Wth student in the previous course numbered i, icj is the average score of the previous courses numbered i, and by is the preset fluctuation coefficient, 0.1<by<1.

[0090] Specifically, the grade fluctuation analysis module improves the accuracy of the analysis of student grade fluctuations in previous courses by setting a preset fluctuation coefficient, thereby improving the accuracy of the analysis of the correlation between student attendance rate and student grades, ultimately improving the efficiency of student attendance management and improving teaching results at the same time; in this embodiment, no specific limitation is made to the setting of the preset fluctuation coefficient, and technical personnel in this field can set it freely, as long as the setting requirements of the preset fluctuation coefficient are met, where the optimal value of by is 0.2.

[0091] Specifically, the first analysis unit analyzes the correlation between the attendance rate of each past course and the grades of each past course according to the analysis results of the attendance rate of each past course and the grades of each past course. The first analysis unit sets the correlation coefficient between the attendance rate of the past course numbered i and the grades of the past courses as ri, and sets:

[0092] Among them, Wic 均 is the average student attendance rate of the past courses numbered i, .

[0093] Specifically, the first analysis unit analyzes the correlation between student attendance rate and student grades in each previous course to improve the accuracy of the analysis of the correlation between student attendance rate and student grades, thereby improving the efficiency of student attendance management and improving teaching results.

[0094] Specifically, the second analysis unit analyzes the correlation between the student attendance rate and the student's grades according to the analysis results of the correlation between the student attendance rate and the student's grades of each past course and the analysis results of the fluctuation of the student's grades of each past course. The second analysis unit sets the correlation coefficient between the student attendance rate and the student's grades as R, and sets:

[0095] Among them, Hi is the weight of the previous course numbered i. When the fluctuation of the student's grades in the previous course numbered i is normal, the value of Hi is h1; when the fluctuation of the student's grades in the previous course numbered i is abnormal, the value of Hi is h2; 0<h2

[0096] Specifically, the second analysis unit improves the accuracy of the correlation analysis between student attendance rate and student performance by setting the weight of each past course, thereby improving the efficiency of student attendance management and improving teaching performance at the same time; in this embodiment, there is no specific limitation on the setting of the weight of past courses, and technicians in this field can set it freely, as long as the setting requirements of the weight of each past course are met, among which the best value of h1 is 1, and the best value of h2 is 0.7.

[0097] Specifically, the first management unit manages the student attendance standard within the management period according to the analysis result of the correlation between the student attendance rate and the student performance, wherein:

[0098] When R≤R0, the first management unit determines that the correlation between the student's attendance rate and the student's grades is weak, and sets the student's absence threshold to U1 and the lateness threshold to E1 within the management period;

[0099] When R>R0, the first management unit determines that the student attendance rate is highly correlated with the student's grades, and sets the student's absence threshold to U2 and the lateness threshold to E2 within the management period;

[0100] Among them, R0 is the correlation threshold, 0.3<R0<1.

[0101] Specifically, the first management unit sets a correlation threshold to improve the accuracy of the analysis of student attendance standards within the management cycle, thereby improving the accuracy of abnormal student attendance warnings to users, thereby improving the efficiency of student attendance management and improving teaching performance. In this embodiment, no specific limitation is made on the setting of correlation thresholds, absence thresholds and lateness thresholds, and those skilled in the art may set them freely as long as the setting requirements of the correlation thresholds, absence thresholds and lateness thresholds are met. Among them, the optimal value of R0 is 0.6, the optimal value of U1 is 7 times, the optimal value of U2 is 5 times, the optimal value of E1 is 10 times, and the optimal value of E2 is 6 times.

[0102] Specifically, the second management unit issues an abnormal student attendance warning to the user based on the management results of the student attendance standard within the management period, the number of student absences and the number of student lateness, wherein:

[0103] ​When GMq≤Uu, if GMc≤Ee, the second management unit determines that the attendance of the Wth student is normal within the management period, and does not issue an abnormal attendance warning to the user; if GMc>Ee, the second management unit determines that the attendance of the Wth student is abnormal within the management period, and issues an abnormal attendance warning to the user;

[0104] When GMq>Uu, the second management unit determines that the Wth student has abnormal attendance during the management period, and issues an abnormal attendance warning to the user;

[0105] Among them, GMq is the number of absences of the Wth student in the management cycle, GMc is the number of lateness of the Wth student in the management cycle; Uu is the management result of the absence threshold, u=1,2; Ee is the management result of the lateness threshold, e=1,2.

[0106] Specifically, the second management unit analyzes the abnormality of the student's attendance within the management period to improve the accuracy of the abnormal student attendance warning to the user, thereby improving the efficiency of student attendance management and improving teaching results.

[0107] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A student attendance management system based on big data, characterized in that: include, Information acquisition module, used to obtain students' past course attendance information and past course grade information; The attendance analysis module is used to analyze the attendance rate of students in previous courses based on the number of absences, the number of lateness and the length of lateness of previous courses obtained; The grade fluctuation analysis module is used to analyze the fluctuation of students' grades in previous courses based on their grades in previous courses; The correlation analysis module is used to analyze the correlation between student attendance rate and student grades based on the analysis results of student attendance rate of each past course and the analysis results of student grade fluctuation of each past course; The management module is used to manage the attendance standards of students within the management period according to the analysis results of the correlation between student attendance rate and student grades, and is also used to obtain the number of student absences and the number of student tardiness within the management period, and to issue abnormal student attendance warnings to users according to the management results of student attendance standards within the management period, the number of student absences and the number of student tardiness; The attendance analysis module is provided with a lateness duration analysis unit and an attendance rate analysis unit. The lateness duration analysis unit is used to compare the acquired lateness duration of the student's previous courses with the preset duration t1, and analyze the abnormality of the student's lateness duration according to the comparison result, wherein: When Wtiz0≤t1, the lateness duration analysis unit determines that the zth lateness duration of the Wth student in the past course numbered i is normal; When Wtiz0>t1, the lateness duration analysis unit determines that the zth lateness duration of the Wth student in the past course numbered i is abnormal; Where Wtiz0 is the zth lateness duration of the Wth student in the previous course numbered i, 0<i<I, I is the number of previous courses, 0<z≤ZWi, ZWi is the number of lateness of the Wth student in the previous course numbered i, 0<W≤wq, wq is the number of students; The grade fluctuation analysis module analyzes the fluctuation of students' grades in previous courses according to their previous course grades, where: when When , the grade fluctuation analysis module determines that the grade fluctuation of the student in the previous course numbered i is normal; when When , the score fluctuation analysis module determines that the score fluctuation of the student in the previous course numbered i is abnormal; Where Wicj is the score of the Wth student in the previous course numbered i, icj is the average score of the previous courses numbered i, and by is the preset fluctuation coefficient; The correlation analysis module is provided with a first analysis unit and a second analysis unit. The first analysis unit is used to analyze the correlation between the attendance rate of each past course and the grades of each past course according to the analysis results of the attendance rate of each past course and the grades of each past course. The first analysis unit sets the correlation coefficient between the attendance rate of the past course numbered i and the grades of the past courses as ri, and sets: Among them, Wic is the average student attendance rate of the past courses numbered i, and Wic is the attendance rate of the Wth student in the past courses numbered i; The second analysis unit is used to analyze the correlation between the student attendance rate and the student's grades according to the analysis results of the correlation between the student attendance rate of each past course and the student's grades of each past course and the analysis results of the fluctuation of the student's grades of each past course. The second analysis unit sets the correlation coefficient between the student attendance rate and the student's grades as R, and sets: Among them, Hi is the weight of the previous course numbered i. When the fluctuation of the student's grades in the previous course numbered i is normal, the value of Hi is h1; when the fluctuation of the student's grades in the previous course numbered i is abnormal, the value of Hi is h2.

2. The student attendance management system based on big data according to claim 1 is characterized in that: The attendance rate analysis unit is used to analyze the attendance rate of students in each past course according to the analysis result of the abnormality of the student's lateness duration and the number of absences in the student's past courses. The attendance rate analysis unit sets the attendance rate of the Wth student in the past course numbered i as Wic, and sets: Wic=1-Wiq / (Wiq+Wicq)-α×Wiy / (Wiq+Wicq); Among them, Wiq is the number of historical absences of the Wth student in the previous courses numbered i, Wicq is the number of historical attendances of the Wth student in the previous courses numbered i, α is the penalty coefficient, α is the penalty coefficient, 0<α<0.5, and Wiy is the number of abnormal lateness durations of the Wth student in the previous courses numbered i.

3. The student attendance management system based on big data according to claim 2 is characterized in that: It also includes an analysis and optimization module, which is used to optimize the analysis process of the attendance rate of students in each past course according to the duration of students' lateness in each past course and the number of class hours in each past course; the analysis and optimization module is provided with a first optimization unit and a second optimization unit, the first optimization unit is used to calculate the total duration of students' lateness in each past course by the duration of students' lateness in each past course and the number of students' lateness, and compare the calculation result with the preset duration threshold value Y0, and optimize the analysis process of the attendance rate of students in each past course according to the comparison result, wherein: when When , the first optimization unit determines that the total lateness time of the Wth student in the past course numbered i is normal, and no optimization is performed; when When , the first optimization unit determines that the total lateness time of the Wth student in the past courses numbered i is abnormal, and optimizes the analysis process of the attendance rate of the Wth student in the past courses numbered i, and sets the optimized penalty coefficient as α', setting:

4. The student attendance management system based on big data according to claim 3 is characterized in that: The second optimization unit compares the number of class hours of each past course with the preset number of class hours k0, and performs secondary optimization on the analysis process of the student attendance rate of each past course according to the comparison result, wherein: When Li≤k0, the second optimization unit determines that the number of class hours of the past course numbered i is normal and does not perform optimization; When Li>k0, the second optimization unit determines that the number of class hours of the past course numbered i is abnormal, and performs secondary optimization on the analysis process of the student attendance rate of the past course numbered i, and sets the optimized preset duration threshold to Y0', and sets Y0'=Y0×[1+β×(Li-k0) / Li]; Among them, Li is the number of class hours of the previous course numbered i, and β is the preset adjustment coefficient.

5. The student attendance management system based on big data according to claim 4 is characterized in that: The management module is provided with a first management unit and a second management unit, wherein the first management unit is used to manage the student attendance standard within the management period according to the analysis result of the correlation between the student attendance rate and the student performance, wherein: When R≤R0, the first management unit determines that the correlation between the student's attendance rate and the student's grades is weak, and sets the student's absence threshold to U1 and the lateness threshold to E1 within the management period; When R>R0, the first management unit determines that the student attendance rate is highly correlated with the student's grades, and sets the student's absence threshold to U2 and the lateness threshold to E2 within the management period; Among them, R0 is the correlation threshold.

6. The student attendance management system based on big data according to claim 5 is characterized in that: The second management unit is used to provide a user with an abnormal student attendance warning according to the management result of the student attendance standard within the management period, the number of student absences and the number of student lateness, wherein: When GMq≤Uu, if GMc≤Ee, the second management unit determines that the attendance of the Wth student is normal within the management period, and does not issue an abnormal attendance warning to the user; if GMc>Ee, the second management unit determines that the attendance of the Wth student is abnormal within the management period, and issues an abnormal attendance warning to the user; When GMq>Uu, the second management unit determines that the Wth student has abnormal attendance during the management period, and issues an abnormal attendance warning to the user; Among them, GMq is the number of absences of the Wth student in the management cycle, GMc is the number of lateness of the Wth student in the management cycle; Uu is the management result of the absence threshold, u=1,2; Ee is the management result of the lateness threshold, e=1,2.

Images