Teaching data management system and method based on cloud computing

Abstract

The invention provides a teaching data management system and method based on cloud computing, and belongs to the field of data management. The problem of complex data management is solved; the data collection module is used for acquiring the number of students and examination scores to form student information; obtaining teaching data; the data processing module is used for averaging examination scores and teaching data in combination with the number of students; obtaining a correlation coefficient according to the obtained mean value in combination with the examination score; according to the correlation coefficient, calculating a total influence value of the teaching data on the student examination scores; the data prediction module is used for performing regression analysis on the examination scores and the total influence value, constructing a score prediction model, predicting student scores, comparing predicted scores with the examination scores, and providing teaching plans for the students with the scores lower than the predicted scores; according to the method, the data is acquired and predicted, and the predicted data is analyzed and judged, so that the data management difficulty is reduced.

Description

Technical Field

[0001] A teaching data management system and method based on cloud computing according to the present invention relates to the field of data management. Background Art

[0002] The existing teaching data management systems and methods have the following deficiencies: Single data scope: Most of the existing teaching data management systems manage students' grades, with less management data and limited system functions. Few processing methods: Most of the existing teaching data management systems sort students' grades or evaluate students' behaviors, with single processing methods and high limitations in data processing results. Weak privacy: The system contains students' privacy information, and security protection measures need to be strengthened to protect students' privacy and security. Summary of the Invention

[0003] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a teaching data management system and method based on cloud computing, aiming to solve the problem of complex data management.

[0004] To achieve the above purpose, the present invention is realized through the following technical solutions: A teaching data management system and method based on cloud computing includes: A teaching data management system based on cloud computing includes: Data collection module: Obtain the number of students and students' exam scores to form student information; obtain teaching data. Data processing module: Calculate the mean value of students' exam scores and teaching data in combination with the number of students; calculate the correlation coefficient according to the obtained mean value in combination with students' exam scores; calculate the total influence value of teaching data on students' exam scores according to the correlation coefficient. Data prediction module: Conduct a regression analysis on students' exam scores and the total influence value, construct a score prediction model, obtain students' predicted scores through teaching data and the score prediction model, compare the predicted scores with the exam scores, and provide teaching plans for students with scores lower than the predicted scores.

[0005] Further, the data processing module processes the data as follows: According to the teaching data, obtain the viewing progress, viewing times of students' online courses, the number of exchanges between students and teachers, students' attendance rate, and homework completion rate of students, obtain students' exam scores, and calculate the average value ksp of exam scores, the average value jdp of viewing progress, the average value gkp of the number of viewing times of online courses, the average value jlp of the number of exchanges, the average value cqp of students' attendance rate, and the average value wcp of students' homework completion rate in combination with the number of students. Based on the obtained mean value and combined with the students' exam scores, the correlation coefficients are obtained: the correlation coefficient sad between the students' exam scores and the viewing progress of the students' online courses, the correlation coefficient sak between the students' exam scores and the number of times the students view the online courses, the correlation coefficient sal between the students' exam scores and the number of times the students communicate with the teacher, the correlation coefficient saq between the students' exam scores and the attendance rate of the students, and the correlation coefficient sac between the students' exam scores and the homework completion rate of the students; the correlation coefficients are saved in the same list, denoted as the correlation coefficient list L, and the length of the list is cd; ; Based on the teaching data, the mean value of the teaching data, and the correlation coefficient list L, the total influence value YXZ is obtained; Based on the exam scores of each student and the total influence value, the data set Z of the students' exam scores and the total influence value is obtained; Z = (Z1, Z2, Z3,..., Z n ); n is the number of students, and Z i = (ks i , YXZ i ), where ks i represents the exam score of the i-th student.

[0006] Furthermore, the mean value of each data in the teaching data is obtained as follows: Based on the teaching data, the exam scores of the students are obtained; the mean value ksp of the exam scores is calculated; The specific calculation process of the mean value ksp of the exam scores is as follows: ; where: n is the number of students, and ks i is the exam score of the i-th student; Similarly, the mean value jdp of the viewing progress of the online courses, the mean value gkp of the number of times the online courses are viewed, the mean value jlp of the number of communication times, the mean value cqp of the attendance rate of the students, and the mean value wcp of the homework completion rate of the students are obtained.

[0007] Furthermore, the correlation coefficients are calculated as follows: Based on the exam scores ks i of the students, the mean value ksp of the exam scores, the viewing progress jd i of the students' online courses, and the mean value jdp of the viewing progress, the correlation coefficient sad between the students' exam scores and the viewing progress of the students' online courses is calculated; The specific calculation process of the correlation coefficient sad is as follows: ; n is the number of students; similarly, the correlation coefficients sak between the students' exam scores and the number of times they watched online courses, sal between the students' exam scores and the number of times they communicated with the teacher, saq between the students' exam scores and their attendance rate, and sac between the students' exam scores and their homework completion rate are calculated.

[0008] Furthermore, the total influence value is calculated as follows: Based on the correlation coefficient sad between the students' exam scores and their viewing progress, the correlation coefficient sak between the students' exam scores and the number of times they watched, and the correlation coefficient sal between the students' exam scores and the number of times they communicated, combined with the viewing progress jd, the number of times watched gk, the number of times the students communicated with the teacher jl and their corresponding means of the students' online courses; the influence of the students' online learning situation on their exam scores is calculated to obtain the online influence value Syx. The specific calculation process is as follows: ; Among them: jdp is the mean of the viewing progress of the students' online courses, gkp is the mean of the number of times watched, and jlp is the mean of the number of times communicated. Based on the correlation coefficient saq between the students' exam scores and their attendance rate, and the correlation coefficient sac between the students' exam scores and their homework completion rate, combined with the students' attendance rate cq, the mean attendance rate cqp of the students, the homework completion rate wc and the mean wcp of the homework completion rate, the influence of the students' offline learning situation on their exam scores is calculated to obtain the offline influence value Xyx. The specific calculation process is as follows: ; Based on the students' exam scores, the value range t of the exam scores is obtained; t is used as the weight to calculate the online influence value Syx and the offline influence value Xyx to obtain the total influence value YXZ. ; Among them: L j represents the j-th correlation coefficient in the correlation coefficient list, and cd is the length of the list.

[0009] Furthermore, the scores are predicted as follows: Based on the data set Z, the students' exam scores and the total influence value are calculated to obtain the first parameter k of the score prediction model. Based on the students' exam scores and the total influence value, combined with the first parameter k, the second parameter v of the score prediction model is calculated. Based on the first parameter k and the second parameter v, the score prediction model is constructed. The score prediction model is as follows: ; ks is the student's test score, and YXZ is the total impact value; Get the student's online course viewing progress, viewing times, communication times between students and teachers, student attendance rate, and homework completion rate for one month. Use the data processing module to get the total impact value for one month. Substitute the total impact value for one month into the score prediction model to get the predicted value ks of the test score. Compare the predicted value with the test score: When ks>ks i , indicating that students’ academic performance has improved and their current learning plan is reasonable; When ks<ks i , indicating that the student’s academic performance has declined, intervene in his current learning habits, and arrange a targeted learning plan for him.

[0010] Furthermore, students are provided with a learning plan, as follows: Get ks<ks i The students’ one-month online course viewing progress, viewing times, number of exchanges between students and teachers, students’ attendance rate, and homework completion rate are used as analytical data; Obtain the correlation coefficient of the student's test score; obtain the mean of the viewing progress, the mean of the number of views, the mean of the number of exchanges, the mean of the student's attendance rate, and the mean of the homework completion rate of the online course in the teaching data as judgment data; Calculate based on judgment data and analysis data to obtain the improvement priority of students' online course viewing progress, viewing times, number of exchanges between students and teachers, students' attendance rate, and homework completion rate; The specific calculation steps are as follows: According to the students' online course viewing progress, the mean jdp of the online course viewing progress in the teaching data and the correlation coefficient sad between the students' test scores and the students' online course viewing progress, the improvement priority G1 of the online course viewing progress is obtained; ; DJD is the student’s online course viewing progress in the past month; Similarly, the improvement priority G2 of the number of views, the improvement priority G3 of the number of exchanges between students and teachers, the improvement priority G4 of the student's attendance rate, and the improvement priority G5 of the homework completion rate are obtained; Sort the improvement priorities in descending order to obtain the students’ improvement list, and the teacher supervises the students’ learning based on the improvement list.

[0011] A teaching data management method based on cloud computing includes: Step S1: Obtain the student ID numbers, the number of students, and the students' exam scores to form student information; obtain the viewing progress, the number of views, the number of exchanges between students and teachers, the students' attendance rate, and the homework completion rate of the students' online courses to form teaching data; Step S2: Calculate the mean value of each data in the teaching data according to the number of students in the student information; obtain the correlation coefficients between the students' exam scores and the viewing progress, the number of views, the number of exchanges between students and teachers, the students' attendance rate, and the homework completion rate of the students' online courses based on the mean values of each data; obtain the total influence value of the teaching data on the students' exam scores according to the correlation coefficients; Step S3: Obtain the teaching data and the total influence value; conduct a regression analysis on the students' exam scores and the total influence value to construct a performance prediction model, predict the students' performance through the teaching data and the performance prediction model, compare the predicted performance with the students' actual performance, and provide a teaching plan for students whose performance is lower than the predicted performance.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: Expand the data scope: The present invention obtains multi-faceted data and analyzes the students' exam scores through multi-faceted data to improve the accuracy of the analysis; Improve the processing method: The present invention obtains the influence value of the performance according to the correlation between each data and the performance, constructs a model based on the influence value, and predicts the performance; Supplement the management method: According to the prediction results of the prediction model, plan teaching for students, reduce the work intensity of teachers, and provide customized teaching for students; Strengthen security and privacy: Control the access scope of students, and at the same time encrypt the students' privacy information to protect the privacy and security of students; BRIEF DESCRIPTION OF THE DRAWINGS

[0013] By reading the following detailed description of the non-limiting embodiments with reference to the accompanying drawings, other features, objectives, and advantages of the present invention will become more apparent: Figure 1 It is a schematic diagram of the system of the present invention; Figure 2 It is a schematic diagram of the regression analysis of the present invention; Figure 3 It is a schematic diagram of the method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0014] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] Example 1, please refer to Figure 1, A teaching data management system based on cloud computing includes: a data collection module, a data processing module, a data prediction module, a data storage module, a database, and a cloud server; It should be noted that: the cloud server provides online courses. Students can access the cloud server to take courses, and at the same time, students can communicate with teachers through the cloud server; the cloud server records and saves the learning situation of students.

[0016] The data collection module mainly collects teaching data and saves the teaching data into the database; the working process of the data collection module is as follows: Obtain the student ID numbers, the number of students, and the exam scores of students to form student information; Access the cloud server. According to the student information, obtain the viewing progress and viewing times of all students' online courses, and obtain the communication times between students and teachers to form the online learning situation of students; Obtain the attendance rate and homework completion rate of students to form the offline learning situation of students; It should be noted that: in the present invention, the online learning situation of students and the offline learning situation of students are the learning situations for one semester. For example, the attendance rate is the number of times students attend classes in one semester, and the exam scores of students are the exam scores at the end of the semester.

[0017] Obtain the online learning situation and offline learning situation of students to form teaching data; save the teaching data into the database; The data processing module accesses the database, obtains the teaching data, processes the teaching data, and saves the processing results into the database; The specific processing process of the data processing module is as follows: According to the student information, obtain the exam scores of students; calculate the average value ksp of the exam scores; The specific calculation process of the average value ksp of the exam scores is as follows: ; Where: n is the number of students, ks i is the exam score of the i-th student; According to the teaching data, obtain the viewing progress of students' online courses; calculate the average value jdp of the viewing progress; The specific calculation process of the average value jdp of the viewing progress is as follows: ; Where: jd i is the viewing progress of the i-th student's online course; According to the teaching data, obtain the viewing times of students' online courses; calculate the average value gkp of the viewing times; The specific calculation process of the average value gkp of the viewing times is as follows: ; where: gk i is the number of views of the online course for the i-th student; Based on the teaching data, obtain the number of exchanges between students and teachers; calculate the average value jlp of the number of exchanges; The specific process of calculating the average value jlp of the number of exchanges is as follows: ; where: jl i is the number of exchanges between the i-th student and the teacher; Based on the teaching data, obtain the attendance rate of students; calculate the average value cqp of the attendance rate of students; The specific process of calculating the average value cqp of the attendance rate of students is as follows: ; where: cq i is the attendance rate of the i-th student; Based on the teaching data, obtain the homework completion rate of students; calculate the average value wcp of the homework completion rate of students; The specific process of calculating the average value wcp of the homework completion rate of students is as follows: ; where: wc i is the homework completion rate of the i-th student; Based on the exam score ks of the student, the average value ksp of the exam scores, the viewing progress jd of the student's online course, and the average value jdp of the viewing progress, calculate the correlation coefficient sad between the student's exam score and the viewing progress of the student's online course; The specific process of calculating the correlation coefficient sad is as follows: ; It should be noted that: the value range of sad is [-1, 1]. When sad > 0, it is judged that there is a positive correlation between the student's exam score and the viewing progress of the student's online course. When sad < 0, it is judged that there is a negative correlation between the student's exam score and the viewing progress of the student's online course. The larger the absolute value of sad, the higher the correlation between the student's exam score and the viewing progress of the student's online course.

[0018] Based on the exam score ks of the student, the average value ksp of the exam scores, the number of views gk of the student's online course, and the average value gkp of the number of views of the online course, calculate the correlation coefficient sak between the student's exam score and the number of views of the student's online course; The specific process of calculating the correlation coefficient sak is as follows: ; According to the student's exam score ks, the average value of the exam scores ksp, the number of communications jl between the student and the teacher, and the average value of the number of communications jlp, calculate the correlation coefficient sal between the student's exam score and the number of communications between the student and the teacher; The specific process of calculating the correlation coefficient sal is as follows: ; According to the student's exam score ks, the average value of the exam scores ksp, the student's attendance rate cq, and the average value of the attendance rates cqp, calculate the correlation coefficient saq between the student's exam score and the student's attendance rate; The specific process of calculating the correlation coefficient saq is as follows: ; According to the student's exam score ks, the average value of the exam scores ksp, the student's homework completion rate wc, and the average value of the homework completion rates wcp, calculate the correlation coefficient sac between the student's exam score and the student's homework completion rate; The specific process of calculating the correlation coefficient sac is as follows: ; Save the correlation coefficients in the same list, denoted as the correlation coefficient list L, and the length of the list is cd; ; Based on the correlation coefficient sad between the student's exam score and the viewing progress, the correlation coefficient sak between the student's exam score and the number of views, and the correlation coefficient sal between the student's exam score and the number of communications, combined with the viewing progress and the number of views of the student's online courses, the number of communications between the student and the teacher and the corresponding average values; calculate the impact of the student's online learning situation on the student's exam score to obtain the online impact value Syx; The specific calculation process of the impact value Syx is as follows: ; Where: jd is the viewing progress of the student's online course, gk is the number of views, jl is the number of communications between the student and the teacher, jdp is the average value of the viewing progress of the student's online course, gkp is the average value of the number of views, and jlp is the average value of the number of communications; Based on the correlation coefficient saq between the student's exam score and the student's attendance rate, the correlation coefficient sac between the student's exam score and the student's homework completion rate, combined with the student's attendance rate cq, the average value of the attendance rates cqp, the student's homework completion rate wc and the average value of the homework completion rates wcp, calculate the impact of the student's offline learning situation on the student's exam score to obtain the offline impact value Xyx; ; Obtain the value range t of the exam scores; use t as the weight to calculate the online influence value Syz and the offline influence value Xyz to obtain the total influence value YXZ; ; where: L j represents the j-th correlation coefficient in the correlation coefficient list, and cd is the length of the list; Obtain the exam scores and total influence values of each student to obtain the data set Z of the exam scores and total influence values of the students; Z = (Z1, Z2, Z3,..., Z n ), where Z i = (ks i , YXZ i ), 1 ≤ i ≤ n; and save the data set Z to the database; It should be noted that: Z i represents the i-th data in the data set; ks i represents the exam score of the i-th student; YXZ i represents the total influence value of the i-th student.

[0019] The data prediction module accesses the database, obtains teaching data, and obtains the data set Z of the exam scores and total influence values of the students; performs a regression analysis on the exam scores and total influence values of the students according to the data set Z, constructs a performance prediction model, and predicts the students' scores through the teaching data and the performance prediction model, compares the predicted scores with the students' scores, and conducts targeted teaching for students with scores lower than the predicted scores; The specific process is as follows: Please refer to Figure 2 , obtain the data set Z of the exam scores and total influence values of the students, perform a regression analysis on the data set Z, process the data through least squares, obtain the relevant parameters of the performance prediction model, and construct the performance prediction model according to the relevant parameters; The construction process of the performance prediction model is as follows: Obtain the data set Z, and calculate according to the exam scores and total influence values of the students to obtain the first parameter k of the performance prediction model; The specific calculation process of the first parameter k is as follows: ; According to the exam scores and total influence values of the students, combined with the first parameter k, calculate the second parameter v of the performance prediction model; The specific calculation process of the second parameter v is as follows: ; Obtain the first parameter k and the second parameter v, and construct the performance prediction model. The performance prediction model is as follows: ; Where: ks refers to the student's exam score, YXZ refers to the total impact value on the exam score, and the score prediction model predicts the student's exam score based on the total impact value of the exam score.

[0020] Obtain the viewing progress, number of views, number of exchanges between the student and the teacher, student attendance rate, and homework completion rate of the student's online courses in a month. Through the data processing module, obtain the total impact value in a month, substitute the total impact value in a month into the score prediction model to obtain the predicted value ks of the student's exam score, compare the predicted value with the student's exam score, and according to the comparison result, when ks > ks i , it indicates that the student's academic performance has improved and the current learning plan is reasonable; when ks < ks i , it indicates that the student's grades have regressed, and the teacher needs to intervene in the student's current learning habits and arrange a targeted learning plan to help the student make a reasonable learning arrangement; The specific steps are as follows: Obtain the viewing progress, number of views, number of exchanges between the student and the teacher, student attendance rate, and homework completion rate of the student's online courses in a month with ks < ks i as the analysis data; According to the correlation coefficient list L, obtain the correlation coefficient sad between the student's exam score and the viewing progress of the student's online courses, the correlation coefficient sak between the student's exam score and the number of views of the student's online courses, the correlation coefficient sal between the student's exam score and the number of exchanges between the student and the teacher, the correlation coefficient saq between the student's exam score and the student attendance rate, and the correlation coefficient sac between the student's exam score and the student homework completion rate; obtain the mean value of the viewing progress of the online courses, the mean value of the number of views, the mean value of the number of exchanges, the mean value of the student attendance rate, and the mean value of the homework completion rate in the teaching data as the judgment data; Calculate according to the judgment data and the analysis data to obtain the improvement priorities of the student for the viewing progress, number of views, number of exchanges between the student and the teacher, student attendance rate, and homework completion rate of the online courses; The specific calculation steps are as follows: According to the viewing progress of the student's online courses in a month, the mean value jdp of the viewing progress of the online courses in the teaching data, and the correlation coefficient sad between the student's exam score and the viewing progress of the student's online courses, obtain the improvement priority G1 of the viewing progress of the online courses; ; Where: djd is the viewing progress of the student's online courses in a month; According to the number of online course views of students in one month, the mean value gkp of the number of online course views in the teaching data and the correlation coefficient sak between the student's test score and the student's online course viewing progress, the improvement priority G2 of the number of online course views is obtained; ; Among them: dgk is the number of online course views of students in one month; According to the number of exchanges between students and teachers in a month, the mean value of the number of exchanges in the teaching data jlp and the correlation coefficient sal between the students' test scores and the number of exchanges between students and teachers, the improvement priority G3 of the number of exchanges between students and teachers is obtained; ; Among them: djl is the number of exchanges between students and teachers in one month; According to the attendance rate of students in one month, the mean value cqp of the attendance rate of students in the teaching data, and the correlation coefficient saq between the test scores of students and the attendance rate of students, the improvement priority G4 of the attendance rate of students is obtained; ; Among them: dcq is the attendance rate of students in one month; According to the homework completion rate of students in one month, the mean value wcp of the homework completion rate of students in the teaching data, and the correlation coefficient sac between the test scores of students and the homework completion rate of students, the improvement priority G5 of the homework completion rate of students is obtained; ; Among them: dwc is the homework completion rate of students in one month; Sort the improvement priorities G1, G2, G3, G4, and G5 in descending order to obtain the student's improvement list. The teacher supervises the student's learning based on the improvement list and formulates a corresponding teaching plan; and the teaching plan is saved in the database.

[0021] It should be noted that the improvement priority indicates that students have a lot of room for improvement in the corresponding aspects and it has a great impact on their academic performance. The improvement list sorts the improvement priorities, and teachers can provide corresponding teaching to students through the improvement list.

[0022] The data storage module obtains the data in the database and uploads all the data to the cloud server for storage and backup; the students' private information is encrypted according to their student ID number; It should be noted that students’ private information refers to information that does not need to be known by others, such as teaching plans.

[0023] Provide students with student accounts through their student IDs. The passwords of the accounts are chosen by the students themselves. Set access permissions for the student accounts to access the cloud server, and the access permissions only allow them to view personal information and public information. Specifically as follows: Obtain the student ID as the encryption key; perform binary conversion on the encryption key to obtain the binary data of the encryption key; obtain the privacy information of the student as the encrypted data; perform binary conversion on the encrypted data to obtain the binary data of the encrypted data. Perform an exclusive OR operation on the binary data of the encrypted data and the encryption key to encrypt the encrypted data, obtain the ciphertext, and store the ciphertext. When the student logs in through the account, the background performs an exclusive OR operation on the account to decrypt the ciphertext again, enabling the student to view their relevant information. The public information is controlled by the school administrator and can be accessed by all accounts.

[0024] It should be noted that: the exclusive OR operation has the properties of zeroing and identity. The result of any value XOR with itself is 0, and the result of any value XOR with 0 is itself.

[0025] Example 2, please refer to Figure 3 , A teaching data management method based on cloud computing includes: Step S1: Obtain the student ID, the number of students, and the exam scores of the students to form student information; obtain the viewing progress, the number of viewings, the number of exchanges between students and teachers, the attendance rate, and the homework completion rate of the students' online courses to form teaching data. Step S2: According to the number of students in the student information, calculate the mean value of each data in the teaching data; obtain the correlation coefficient between the exam scores of the students and the viewing progress, the number of viewings, the number of exchanges between students and teachers, the attendance rate, and the homework completion rate of the students' online courses based on the mean value of each data; obtain the total influence value of the teaching data on the exam scores of the students according to the correlation coefficient. Step S3: Obtain the teaching data and the total influence value; perform a regression analysis on the exam scores of the students and the total influence value to construct a score prediction model. Through the teaching data and the score prediction model, predict the students' scores, compare the predicted scores with the students' actual scores, and provide teaching plans for students whose scores are lower than the predicted scores. Step S4: Provide students with student accounts according to the student IDs in the student information; encrypt and store the teaching plans by student ID, and students can view relevant information according to their student IDs; store the overall teaching data and restrict access through permissions. The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation. For example, if there are weight coefficients and proportionality coefficients, the values set are for quantifying each parameter to obtain a specific numerical value for subsequent comparison. Regarding the magnitudes of the weight coefficients and proportionality coefficients, as long as they do not affect the proportional relationship between the parameters and the quantified numerical values, it is acceptable.

[0026] Finally, it should be noted that the above-described embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments or can easily think of changes, or perform equivalent replacements for some of the technical features; and these modifications, changes or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A teaching data management system based on cloud computing, characterized in that, The management system includes: Data collection module: Obtain the number of students and the exam scores of students to form student information; obtain teaching data; Data processing module: Calculate the average value of the exam scores and teaching data in combination with the number of students; calculate the correlation coefficient based on the obtained average value and the exam scores of students; calculate the total influence value of teaching data on students' exam scores according to the correlation coefficient; Data prediction module: Conduct a regression analysis on the students' exam scores and the total influence value, construct a score prediction model, obtain the predicted scores of students through the teaching data and the score prediction model, compare the predicted scores with the exam scores, and provide a teaching plan for students with scores lower than the predicted scores.

2. The teaching data management system based on cloud computing according to claim 1, wherein The data processing module processes the data as follows: According to the teaching data, obtain the viewing progress, viewing times of students' online courses, the number of exchanges between students and teachers, the attendance rate of students, and the homework completion rate of students; obtain the exam scores of students; calculate the average value ksp of the exam scores, the average value jdp of the viewing progress, the average value gkp of the viewing times of online courses, the average value jlp of the number of exchanges, the average value cqp of the attendance rate of students, and the average value wcp of the homework completion rate of students in combination with the number of students. Based on the obtained average values and the exam scores of students, obtain the correlation coefficient sad between the exam scores of students and the viewing progress of students' online courses, the correlation coefficient sak between the exam scores of students and the viewing times of students' online courses, the correlation coefficient sal between the exam scores of students and the number of exchanges between students and teachers, the correlation coefficient saq between the exam scores of students and the attendance rate of students, and the correlation coefficient sac between the exam scores of students and the homework completion rate of students; save the correlation coefficients in the same list, denoted as the correlation coefficient list L, and the length of the list is cd. ； Obtain the total influence value YXZ based on the teaching data, the average value of the teaching data, and the correlation coefficient list L. According to the examination scores and total influence values of each student, a data set Z of the examination scores and total influence values of the students is obtained; Z = (Z1, Z2, Z3, ……, Z n ); n is the number of students, and Z i = (ks i , YXZ i ), where ks i represents the examination score of the i-th student.

3. A teaching data management system based on cloud computing according to claim 2, characterized in that, Calculate the average value of each data in the teaching data as follows: According to the teaching data, obtain the exam scores of students; calculate the average value ksp of the exam scores. The specific process of calculating the average value ksp of the exam scores is as follows: ； Where: n is the number of students, and ks i is the exam score of the i-th student; Similarly, obtain the average value jdp of the viewing progress of online courses, the average value gkp of the viewing times of online courses, the average value jlp of the number of exchanges, the average value cqp of the attendance rate of students, and the average value wcp of the homework completion rate of students.

4. A teaching data management system based on cloud computing according to claim 2, characterized in that, Calculate the correlation coefficient as follows: According to the student's exam score ks i , the average value ksp of the exam scores, and the viewing progress jd of the student's online courses i , the average value jdp of the viewing progress, calculate the correlation coefficient sad between the student's exam score and the viewing progress of the student's online courses; The specific process of calculating the correlation coefficient sad is as follows: ； n is the number of students; similarly, calculate the correlation coefficient sak between the exam scores of students and the viewing times of students' online courses, the correlation coefficient sal between the exam scores of students and the number of exchanges between students and teachers, the correlation coefficient saq between the exam scores of students and the attendance rate of students, and the correlation coefficient sac between the exam scores of students and the homework completion rate of students.

5. The teaching data management system based on cloud computing according to claim 2, characterized in that, Calculate the total influence value as follows: According to the correlation coefficient sad between the student's exam score and viewing progress, the correlation coefficient sak between the student's exam score and the number of views, and the correlation coefficient sal between the student's exam score and the number of exchanges, combined with the viewing progress jd and the number of views gk of the student's online courses, the number of exchanges jl between the student and the teacher, and the corresponding means; calculate the impact of the student's online learning situation on the student's exam score to obtain the online impact value Syx; The specific calculation process is as follows: ； Where: jdp is the mean of the viewing progress of the student's online courses, gkp is the mean of the number of views, and jlp is the mean of the number of exchanges; According to the correlation coefficient saq between the student's exam score and the student's attendance rate, and the correlation coefficient sac between the student's exam score and the student's homework completion rate, combined with the student's attendance rate cq, the mean cqp of the student's attendance rate, the homework completion rate wc of the student, and the mean wcp of the student's homework completion rate, calculate the impact of the student's offline learning situation on the student's exam score to obtain the offline impact value Xyx; The specific calculation process is as follows: ； According to the student's exam score, obtain the value range t of the exam score; use t as the weight to calculate the online impact value Syx and the offline impact value Xyx to obtain the total impact value YXZ; ； Where: L j represents the j-th correlation coefficient in the correlation coefficient list, and cd is the list length.

6. The teaching data management system based on cloud computing according to claim 2, wherein, Predict the score, specifically as follows: According to the data set Z, calculate the student's exam score and the total impact value to obtain the first parameter k of the score prediction model; According to the student's exam score and the total impact value, combined with the first parameter k, calculate the second parameter v of the score prediction model; According to the first parameter k and the second parameter v, construct the score prediction model, and the score prediction model is as follows: ； ks is the student's exam score, and YXZ is the total impact value; Obtain the viewing progress, the number of views, the number of exchanges between the student and the teacher, the student's attendance rate, and the homework completion rate of the student's online courses in a month. Through the data processing module, obtain the total impact value in a month, substitute the total impact value in a month into the score prediction model to obtain the predicted value ks of the exam score, and compare the predicted value with the exam score: When ks > ks i , it indicates that the current learning plan is reasonable; When ks < ks i , it indicates that the current learning plan is unreasonable, intervenes in its current learning habits, and arranges a targeted learning plan for it.

7. An instructional data management system based on cloud computing according to claim 6, characterized in that, Provide a learning plan for the student, specifically as follows: Obtain students with ks < ks i The viewing progress, number of views, number of exchanges between students and teachers, student attendance rate, and homework completion rate of the one-month online courses of these students are used as analysis data; Obtain the correlation coefficient of the student's exam score; obtain the means of the viewing progress, the number of views, the number of exchanges, the student's attendance rate, and the homework completion rate of the online courses in the teaching data as the judgment data; According to the judgment data and the analysis data, calculate the improvement priorities of the student's viewing progress, the number of views, the number of exchanges between the student and the teacher, the student's attendance rate, and the homework completion rate for the online courses; The specific calculation steps are as follows: According to the viewing progress of the student's online courses, the mean jdp of the viewing progress of the online courses in the teaching data, and the correlation coefficient sad between the student's exam score and the viewing progress of the student's online courses, obtain the improvement priority G1 of the viewing progress of the online courses; ； djd is the viewing progress of the student's online courses in the recent month; Similarly, obtain the improvement priorities G2 for the number of views, G3 for the number of exchanges between students and teachers, G4 for the student attendance rate, and G5 for the homework completion rate; Sort the improvement priorities in descending order to obtain a student improvement list, and urge students to study according to the improvement list.

8. A teaching data management method based on cloud computing, applicable to a teaching data management system based on cloud computing according to any one of claims 1-7, characterized in that, The management method includes: Step S1: Obtain the student ID numbers, the number of students, and the exam scores of the students to form student information; obtain the viewing progress, the number of views, the number of exchanges between students and teachers, the student attendance rate, and the homework completion rate of the students' online courses to form teaching data; Step S2: Calculate the average value of each data in the teaching data according to the number of students in the student information; obtain the correlation coefficients between the exam scores of the students and the viewing progress, the number of views, the number of exchanges between students and teachers, the student attendance rate, and the homework completion rate of the students' online courses based on the average values of each data; obtain the total influence value of the teaching data on the exam scores of the students according to the correlation coefficients; Step S3: Obtain the teaching data and the total influence value; conduct a regression analysis on the exam scores of the students and the total influence value to construct a performance prediction model. Predict the students' scores through the teaching data and the performance prediction model, compare the predicted scores with the students' actual scores, and provide a teaching plan for students whose scores are lower than the predicted scores.

Images