Data processing method based on big data Internet

What is AI technical title?
AI technical title is built by Patsnap AI team. It summarizes the technical point description of the patent document.
By applying data processing methods based on the Internet on the online education platform, the learning, learning and learning evaluation index are calculated, and a personalized learning evaluation report is generated, which solves the problem of insufficient utilization of student data in the existing technology and realizes an accurate assessment of students' learning status.

CN119671809AInactive Publication Date: 2025-03-21合肥理微大数据有限公司

View PDF 0 Cites 0 Cited by

Patent Information

Application Number: CN202510195480.X
Authority / Receiving Office: CN · China
Patent Type: Applications(China)
Current Assignee / Owner
Filing Date: 2025-02-21
Publication Date: 2025-03-21
Estimated Expiration: Not applicable · inactive patent

AI Technical Summary

Technical Problem

The data processing methods based on the Internet in the prior art are insufficiently utilized on online education platforms, lack effective data processing and analysis methods, cannot accurately understand students' learning status, and it is difficult to provide an evaluation report that meets the status of students.

Method used

A data processing method based on the Internet of big data is proposed, which can obtain students' learning behavior data, interactive communication data and learning outcome data through multi-source data, conduct data processing and evaluation, calculate learning, mutual learning and learning evaluation index, and generate personalized learning evaluation reports.

Benefits of technology

Through detailed data analysis and evaluation index calculation, students' learning investment, interactive activity and learning results can be clearly displayed, and comprehensive and objective learning evaluation can be provided, which solves the problem of insufficient data utilization in the existing technology.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN119671809A_ABST

Patent Text Reader

Abstract

The invention discloses a data processing method based on a big data internet, and relates to the technical field of big data processing. According to the method, in a data processing evaluation stage, a chemical product evaluation index, a chemical interaction evaluation index and a chemical fruit evaluation index are calculated respectively; learning duration and login times are extracted from learning records and combined with a weight coefficient to obtain a learning product evaluation index, the learning investment condition of students is clearly displayed, and the learning product evaluation index considers the interaction activeness, participation continuity and problem solving ability of the students through quantitative evaluation of each index of interaction data; the learning result evaluation index comprehensively considers the difference between the scores of the students in different types of courses and the average score, marks the course types, gives scores, converts into an assessment and evaluation ratio, comprehensively and objectively evaluates the learning results, also can reflect the difference between the course difficulty and the overall student level, and solves the problems that the data of the students is not fully utilized and the learning efficiency is high in the prior art. An effective data processing and analysis method is lacked, and the learning condition of the student cannot be accurately known.

Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to a data processing method based on big data Internet. Background Art

[0002] With the development of Internet technology and online education, a large amount of students' learning behavior data, performance data and online learning records have been generated and accumulated.

[0003] However, in the process of using the data processing method based on the big data Internet in the prior art to process these data using the online education platform, there are still the following deficiencies: When using the big data Internet to process data from online education platforms, there are problems with insufficient data processing and analysis methods, insufficient use of student data, a lack of effective data processing and analysis methods, an inability to accurately understand students’ learning status, and difficulty providing evaluation reports that are consistent with student status.

[0004] To this end, a data processing method based on the big data Internet is introduced. Summary of the invention

[0005] The purpose of the present invention is to solve the problems pointed out in the background technology and to propose a data processing method based on the big data Internet.

[0006] The purpose of the present invention can be achieved by the following technical solution: A data processing method based on big data Internet, comprising: Multi-source data acquisition: Acquire the learning behavior data, interactive communication data, and learning outcome data of each student user within a set period; learning behavior data includes learning records; interactive communication data includes the number of exchanges, participation frequency, number of questions raised, and number of questions solved; learning outcome data includes the grade data of various types of courses; Data processing and evaluation: Evaluate the learning behavior data, interactive communication data, and learning outcome data of each student user within a set period, so as to determine the academic performance evaluation index, mutual learning evaluation index, and learning outcome evaluation index of each student user within a set period; Specifically: Analyze the study time and login times in the learning records of each student user within the set period to obtain the academic performance evaluation index of each student user within the set period; Analyze the number of exchanges and participation frequencies of each numbered student within the set period to obtain the mutual evaluation index of each numbered student within the set period; Analyze the course performance data of each type of students with different numbers within a set period to obtain the academic performance evaluation index of each student with different numbers within the set period; Personalized push: Based on the academic performance evaluation index, mutual evaluation index and learning outcome evaluation index of each numbered student user in the current set period, a learning evaluation report for each numbered student user in the current set period is generated and pushed to each numbered student user.

[0007] As a preferred implementation of the present invention, the specific steps of evaluating the learning behavior data of each numbered student user within a set period are: Extract the learning time and login times from the learning records of each numbered student user within the set period, calculate the ratio of the learning time of each numbered student user within the set period to the set period duration, and obtain the learning time proportion of each numbered student user, that is, calculate it by learning time / set period duration; Calculate the ratio of the number of logins of each numbered student user within the set period to the number of days in the set period, and obtain the login frequency of each numbered student user, that is, the number of logins / the number of days in the set period; Calculate the ratio of the study time of each numbered student user within the set period to the number of days in the set period, and get the average daily study time of each numbered student user, that is, study time / set number of days in the cycle.

[0008] As a preferred implementation of the present invention, the academic performance evaluation index of each numbered student user within a set period is determined, specifically: The preset learning time percentage, login frequency and average daily learning time correspond to the qualified learning time percentage, qualified login frequency and qualified average daily learning time respectively; The ratio of the study time proportion, login frequency and average daily study time of each numbered student user within the set period is calculated with the corresponding preset passing study time proportion, passing login frequency and passing average daily study time, so as to obtain the time evaluation value, frequency evaluation value and average daily evaluation value; that is, it is calculated by the study time proportion / passing study time proportion, login frequency / passing login frequency and average daily study time / passing average daily study time; The duration evaluation value, frequency evaluation value and daily average evaluation value of each numbered student user within the set period are multiplied by the corresponding preset weight coefficients, and then the sum is calculated to obtain the academic performance evaluation index of each numbered student within the set period.

[0009] As a preferred implementation of the present invention, the specific steps of evaluating the interactive communication data of each numbered student user within a set period are: Extract the number of exchanges and participation frequencies from the interactive communication data of each numbered student user within a set period; count the number of speeches of each numbered student user within the set period as the number of exchanges of each numbered student user within the set period; The intervals of the number of communication times corresponding to each group of times are set, and each interval of the number of communication times corresponds to an active evaluation value; the number of communication times of each numbered student user within the set period is converted into an active evaluation value; Identify the number of days that each student user with a number participates in interactive communication within a set period, and calculate the ratio between the number of days in the set period to obtain the participation frequency of each student user with a number within the set period, that is, calculate by the number of days participating in interactive communication / the number of days in the set period; The number of questions raised and the number of questions solved are extracted from the interactive communication data of each numbered student user within a set period, and the ratio is calculated to obtain the ability ratio of each numbered student user within the set period, that is, calculated by number of problems solved / number of questions raised.

[0010] As a preferred implementation of the present invention, the mutual evaluation index of each numbered student user within a set period is determined as follows: The preset activity assessment value, participation frequency and ability ratio correspond to the moderate activity assessment value, normal participation frequency and passing ability ratio respectively; The activity evaluation value, participation frequency and ability ratio of each numbered student user within the set period are calculated with the corresponding preset moderate activity evaluation value, normal participation frequency and passing ability ratio, so as to obtain the communication evaluation value, participation evaluation value and ability evaluation value; that is, calculated by active evaluation value / moderate activity evaluation value, participation frequency / normal participation frequency and ability ratio / passing ability ratio; The communication evaluation value, participation evaluation value and ability evaluation value of each numbered student user within the set period are multiplied by the corresponding preset weight coefficients, and then the sum is obtained to obtain the mutual evaluation index of each numbered student within the set period.

[0011] As a preferred implementation of the present invention, the specific steps of evaluating the learning achievement data of each numbered student user within a set period are: Extract various types of course performance data from the learning achievement data of each numbered student user within a set period; Count the number of grade data of each type of course for each numbered student user within the set period. If the number of grade data of a certain type of course is greater than one, take the average of the grade data of each group of the corresponding type of course as the grade data of the corresponding type of course within the set period; Extract the average scores corresponding to each type of course score data; the average score is the average score of all students in the corresponding type of course; calculate the difference between each type of course score data of each numbered student user and the corresponding average score to obtain the score performance value; that is, the average score of each type of course score data minus the corresponding average score; If the calculation result of a set of performance values is a negative value, the type of course corresponding to the negative value will be marked as an abnormal course; if the calculation result of a set of performance values is a positive value, the positive value will be compared with the preset performance cutoff value. If the positive value is lower than the preset performance cutoff value, the type of course corresponding to the positive value will be marked as a passing course; if the positive value is higher than the preset performance cutoff value, the type of course corresponding to the positive value will be marked as an excellent course.

[0012] As a preferred implementation of the present invention, the learning evaluation index of each numbered student user within a set period is determined, specifically: Set the corresponding grades for abnormal courses, passing courses and excellent courses respectively; convert the abnormal courses, passing courses and excellent courses of each numbered student user into grade scores respectively, and accumulate them to obtain the abnormal course score, passing course score and excellent course score respectively; The passing course scores and excellent course scores of each numbered student user are accumulated, and the abnormal course scores are subtracted from the accumulated value to obtain the comprehensive score of each numbered student user; Set the interval of each group score corresponding to the comprehensive score; each group score interval corresponds to an assessment ratio; After converting the comprehensive performance score of each numbered student user into an assessment evaluation ratio, the obtained assessment evaluation ratio is used as the academic achievement evaluation index of each numbered student user within the set period.

[0013] As a preferred implementation of the present invention, a learning evaluation report is generated for each numbered student user within the current set period, specifically: A three-dimensional space is pre-constructed, and each group of historical three-dimensional coordinate points is marked in the three-dimensional space; each group of historical three-dimensional coordinate points corresponds to a learning evaluation report; With the academic performance evaluation index in the current set period as the x-axis, the mutual evaluation index as the y-axis, and the academic achievement evaluation index as the z-axis, the three index values corresponding to each numbered student user are plotted as a three-dimensional coordinate point in the pre-constructed three-dimensional space; Divide the three-dimensional space into voxel regions according to the range, and locate the voxel region to which the three-dimensional coordinate point of each numbered student user belongs; Find the historical three-dimensional coordinate point in the located voxel area, and calculate the similarity between the current three-dimensional coordinate point and each historical three-dimensional coordinate point through a similarity measurement method, and select the historical three-dimensional coordinate point with the smallest distance according to the similarity; The learning evaluation report corresponding to the selected historical three-dimensional coordinate point is extracted as the learning evaluation report of each numbered student user within the current set period.

[0014] As a preferred embodiment of the present invention, it also includes: Processing cycle adjustment: Based on the academic performance evaluation index, peer evaluation index and academic achievement evaluation index of each student user within the set period, adjust the specific duration of the next set period for each student user.

[0015] As a preferred implementation of the present invention, the specific duration of the next set period corresponding to each numbered student user is adjusted, specifically: The weight coefficients corresponding to the academic performance evaluation index, the mutual evaluation index and the academic achievement evaluation index are set respectively, and the academic performance evaluation index, the mutual evaluation index and the academic achievement evaluation index of each numbered student user are multiplied by the corresponding weight coefficients respectively, and then the sum is calculated to obtain the academic status comprehensive index of each numbered student user; The comprehensive index of the academic status of each numbered student user is compared with the corresponding set reference index. If the comprehensive index of the academic status of a certain numbered student user is higher than the corresponding set reference index, the difference between the two is calculated to obtain the time increment; If the overall academic index of a student user with a certain ID is lower than the corresponding reference index, the difference between the two is calculated to obtain the duration deduction; Preset the intervals of each group of depreciation and each group of value-added corresponding to the depreciation and value-added of the duration, and each group of depreciation interval and each group of value-added interval respectively corresponds to a duration adjustment ratio; If a student user with a certain ID has a time reduction, the time adjustment ratio will be determined and then the set period time will be reduced accordingly based on the current set period time. If a student user with a certain number increases the duration, the duration adjustment ratio is determined and then, based on the current set period duration, the set period duration is extended accordingly according to the duration adjustment ratio.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention calculates the learning accumulation, learning interaction and learning result evaluation indexes respectively in the data processing and evaluation stage; extracts the learning time and login times from the learning records and combines them with the weight coefficient to obtain the learning accumulation evaluation index, which clearly shows the students' learning input; the learning interaction evaluation index quantitatively evaluates each indicator of the interactive communication data, taking into account the students' interactive activity, participation continuity and problem-solving ability; the learning result evaluation index comprehensively considers the difference between the students' scores and average scores in different types of courses, marks the course categories and assigns scores, and converts them into assessment evaluation ratios, which comprehensively and objectively evaluates the learning results, and can also reflect the course difficulty and overall student level differences, solving the problems in the prior art that the students' data is not fully utilized, there is a lack of effective data processing and analysis methods, and it is impossible to accurately understand the students' learning status; The present invention constructs a three-dimensional space based on three evaluation indexes, locates the current student coordinate point, finds the most similar historical coordinate point, extracts the corresponding learning evaluation report and pushes it to the student. This method combined with historical data evaluation improves the efficiency and accuracy of data processing. The present invention calculates a comprehensive learning status index, compares it with a reference index, obtains an increase or decrease in duration, and presets a duration adjustment ratio corresponding to the increase or decrease interval. For students with good learning status, the learning cycle is extended to reduce the waste of data processing resources; for students whose learning status needs to be improved, the cycle is shortened to encourage them to improve their learning efficiency. This personalized duration adjustment fully respects individual differences among students and adapts to different learning needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] See also Figure 1 As shown, the data processing method based on the big data Internet includes: Multi-source data acquisition: Through the learning system of the online education platform, the learning behavior data, interactive communication data and learning outcome data of each numbered student user within the set period are obtained; the set period is initially set to two weeks, that is, the learning behavior data, interactive communication data and learning outcome data of each numbered student user within these two weeks are obtained every two weeks; and the learning behavior data, interactive communication data and learning outcome data of each numbered student user are transmitted to the data processing center through a secure network transmission protocol; the learning behavior data includes learning records; the interactive communication data includes the number of exchanges, participation frequency, number of questions raised and number of questions solved; the learning outcome data includes the grade data of various types of courses; Data processing and evaluation: After receiving the learning behavior data, interactive communication data and learning outcome data of each numbered student user within the set period, the data processing center will evaluate the learning behavior data, interactive communication data and learning outcome data of each numbered student user within the set period, so as to determine the academic achievement evaluation index, mutual learning evaluation index and learning outcome evaluation index of each numbered student user within the set period; Determine the academic performance evaluation index of each student user within the set period, specifically: Extract the learning time and login times from the learning records of each numbered student user within the set period, calculate the ratio of the learning time of each numbered student user within the set period to the set period duration, and obtain the learning time proportion of each numbered student user, that is, calculate it by learning time / set period duration; For example, if the period is set to two weeks (a total of 14×24=336 hours), and a student studies for 33.6 hours, then the proportion of study time is 33.6÷336=0.1; this indicator reflects the proportion of time that students spend on study during the entire period; Calculate the ratio of the number of logins of each numbered student user within the set period to the number of days in the set period, and obtain the login frequency of each numbered student user, that is, the number of logins / the number of days in the set period; For example, if the student logged in 10 times, a total of 14 days in two weeks, then the login frequency is 10÷14≈0.71 times / day. This indicator measures how frequently students access the learning platform; Calculate the ratio of the study time of each numbered student user within the set period to the number of days in the set period, and obtain the average daily study time of each numbered student user, that is, by studying time / the number of days in the set period; If a student studies for 7 days in two weeks, the average daily study time is 33.6÷14=2.4 hours. This indicator reflects the intensity of the student's daily study. Based on the duration of the current set cycle, the preset learning time percentage, login frequency and average daily learning time correspond to the passing learning time percentage, passing login frequency and passing average daily learning time respectively; The ratio of the study time proportion, login frequency and average daily study time of each numbered student user within the set period is calculated with the corresponding preset passing study time proportion, passing login frequency and passing average daily study time, so as to obtain the time evaluation value, frequency evaluation value and average daily evaluation value; that is, it is calculated by the study time proportion / passing study time proportion, login frequency / passing login frequency and average daily study time / passing average daily study time; Multiply the duration evaluation value, frequency evaluation value and daily average evaluation value of each numbered student user in the set period by the corresponding preset weight coefficient, and then sum them up to obtain the academic performance evaluation index of each numbered student in the set period; It should be noted that through multiple quantitative indicators such as the proportion of study time, login frequency and average daily study time, we can clearly understand the learning input of each student within the set period.

[0021] Determine the peer evaluation index of each student user within the set period, specifically: Extract the number of exchanges and participation frequencies from the interactive communication data of each numbered student user within a set period; count the number of speeches of each numbered student user within the set period as the number of exchanges of each numbered student user within the set period; the number of speeches includes speeches in various interactive scenarios such as forums on the online education platform, private messages with teachers, and group discussions; The intervals of the number of communication times corresponding to each group of times are set, and each interval of the number of communication times corresponds to an active evaluation value; the number of communication times of each numbered student user within the set period is converted into an active evaluation value; Set the intervals of the number of exchanges corresponding to each group, and assign an active evaluation value to each interval. The number of exchanges is converted into an active evaluation value, thus realizing a quantitative evaluation of the students' interactive activity. Identify the number of days that each student user with a number participates in interactive communication within a set period, and calculate the ratio between the number of days in the set period to obtain the participation frequency of each student user with a number within the set period, that is, calculate by the number of days participating in interactive communication / the number of days in the set period; The participation frequency is obtained by calculating the ratio of the number of days of participation in interactive communication to the number of days in the set period. It can measure the continuity and stability of students' participation in interactive communication within the set period. A student with a high participation frequency indicates that he or she has maintained an active participation in interactive communication activities over a long period of time, rather than doing it occasionally. Extract the number of questions raised and the number of problems solved from the interactive communication data of each numbered student user within a set period, and calculate the ratio to obtain the ability ratio of each numbered student user within the set period, that is, calculate by the number of problems solved / the number of questions raised; The ability evaluation value is obtained by calculating the ratio of the number of problems solved to the number of problems raised, which directly reflects the students' ability to solve problems in the learning process; Based on the duration of the current set period, the preset activity assessment value, participation frequency and ability ratio correspond to the moderate activity assessment value, normal participation frequency and passing ability ratio respectively; The activity evaluation value, participation frequency and ability ratio of each numbered student user within the set period are calculated with the corresponding preset moderate activity evaluation value, normal participation frequency and passing ability ratio, so as to obtain the communication evaluation value, participation evaluation value and ability evaluation value; that is, calculated by active evaluation value / moderate activity evaluation value, participation frequency / normal participation frequency and ability ratio / passing ability ratio; The communication evaluation value, participation evaluation value and ability evaluation value of each numbered student user in the set period are multiplied by the corresponding preset weight coefficients respectively, and then the sum is obtained to obtain the mutual learning evaluation index of each numbered student in the set period; It should be noted that the introduction of the peer evaluation index has enriched the education evaluation system. Students are no longer measured solely by their grades, but the ability to interact and communicate is included in the evaluation scope, which makes data processing more comprehensive.

[0022] Determine the learning evaluation index of each student user number within the set period, specifically: Extract various types of course performance data from the learning achievement data of each numbered student user within a set period; Count the number of grade data of each type of course for each numbered student user within the set period. If the number of grade data of a certain type of course is greater than one, it means that the number of examinations for this type of course within the set period is greater than one. Then take the average of the grade data of each group of the corresponding type of course as the grade data of the corresponding type of course within the set period; Extract the average scores corresponding to each type of course score data; the average score is the average score of all students in the corresponding type of course; calculate the difference between each type of course score data of each numbered student user and the corresponding average score to obtain the score performance value; that is, the average score of each type of course score data minus the corresponding average score; If the result of calculating a set of performance values is a negative value, the type of course corresponding to the negative value is marked as an abnormal course; if the result of calculating a set of performance values is a positive value, the positive value is compared with the preset performance cutoff value. If the positive value is lower than the preset performance cutoff value, the type of course corresponding to the positive value is marked as a passing course; if the positive value is higher than the preset performance cutoff value, the type of course corresponding to the positive value is marked as an excellent course; Set the corresponding grades for abnormal courses, passing courses and excellent courses respectively; the grade of excellent courses is set to 3, the grade of passing courses is set to 1, and the grade of abnormal courses is set to 2; The abnormal courses, passing courses and excellent courses of each numbered student user are converted into grade scores, and the abnormal course scores, passing course scores and excellent course scores are accumulated respectively; The passing course scores and excellent course scores of each numbered student user are accumulated, and the abnormal course scores are subtracted from the accumulated value to obtain the comprehensive score of each numbered student user; Set the interval of each group score corresponding to the comprehensive score; each group score interval corresponds to an assessment ratio; the range of the assessment ratio is set at 0.896-1.237. If the comprehensive score is a negative value, the assessment ratio matching range is below 1, and the greater the negative value, the greater the possibility of matching 0.896. If the comprehensive score is a positive value, the assessment ratio matching range is above 1, and the greater the positive value, the greater the possibility of matching 1.237. After converting the comprehensive score of each student user into an assessment ratio, the obtained assessment ratio is used as the academic achievement assessment index of each student user within the set period; It should be noted that the learning outcome evaluation index comprehensively considers students' performance in different types of courses, avoiding the one-sidedness of single course performance evaluation and being able to evaluate students' learning outcomes more comprehensively and objectively. At the same time, by comparing with the average course performance, it also takes into account the differences in course difficulty and overall student level, making the evaluation more fair and reasonable.

[0023] Personalized push: Based on the academic performance evaluation index, peer evaluation index and academic achievement evaluation index of each student user in the current set period, a learning evaluation report for each student user in the current set period is generated and pushed to each student user; Specifically: A three-dimensional space is pre-constructed, and each group of historical three-dimensional coordinate points are marked in the three-dimensional space; the historical three-dimensional coordinate points are collected by collecting a large number of students' academic performance evaluation indexes, academic peer evaluation indexes and academic achievement evaluation indexes in the past set period, and are also converted into three-dimensional coordinate points for marking; Each group of historical three-dimensional coordinate points corresponds to a learning evaluation report; the learning evaluation report of each group of historical three-dimensional coordinate points is commented on by professional teachers in their spare time; With the academic performance evaluation index in the current set period as the x-axis, the mutual evaluation index as the y-axis, and the academic achievement evaluation index as the z-axis, the three index values corresponding to each numbered student user are plotted as a three-dimensional coordinate point in the pre-constructed three-dimensional space; Divide the three-dimensional space into voxel regions according to the range, and locate the voxel region to which the three-dimensional coordinate point of each numbered student user belongs; Find the historical three-dimensional coordinate point in the located voxel area, and calculate the similarity between the current three-dimensional coordinate point and each historical three-dimensional coordinate point through a similarity measurement method, and select the historical three-dimensional coordinate point with the smallest distance according to the similarity; Extract the learning evaluation report corresponding to the selected historical three-dimensional coordinate point as the learning evaluation report of each numbered student user in the current set period; the learning evaluation report includes a description of the learning input status, the learning interaction status and the learning performance status; Processing cycle adjustment: Based on the academic performance evaluation index, peer evaluation index, and academic achievement evaluation index of each student user within the set period, adjust the specific duration of the next set period for each student user; Specifically: The weight coefficients corresponding to the academic performance evaluation index, the mutual evaluation index and the academic achievement evaluation index are set respectively, and the academic performance evaluation index, the mutual evaluation index and the academic achievement evaluation index of each numbered student user are multiplied by the corresponding weight coefficients respectively, and then the sum is calculated to obtain the academic status comprehensive index of each numbered student user; The comprehensive index of the academic status of each numbered student user is compared with the corresponding set reference index. If the comprehensive index of the academic status of a certain numbered student user is higher than the corresponding set reference index, the difference between the two is calculated to obtain the time increment; If the overall academic index of a student user with a certain ID is lower than the corresponding reference index, the difference between the two is calculated to obtain the duration deduction; Preset the intervals of each group of depreciation and each group of value-added corresponding to the depreciation and value-added of the duration, and each group of depreciation interval and each group of value-added interval respectively corresponds to a duration adjustment ratio; If a student user with a certain ID has a time reduction, the time adjustment ratio will be determined and then the set period time will be reduced accordingly based on the current set period time. If a student user with a certain ID increases the duration, the duration adjustment ratio is determined and then the duration of the set period is correspondingly extended based on the current set period duration according to the duration adjustment ratio; It should be noted that, based on the comparison results of the comprehensive academic status index and the reference index, different time adjustment strategies are given to students in different learning status. For students with better learning status (comprehensive academic status index higher than the reference index), the learning cycle duration is extended to reduce the waste of data processing resources; while for students whose learning status needs to be improved (comprehensive academic status index lower than the reference index), the learning cycle duration is shortened. The students' status is continuously analyzed and adjustments are reminded. This personalized time adjustment fully takes into account the individual differences of students and meets the learning needs of different students.

[0024] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A data processing method based on big data Internet, characterized in that: include: Multi-source data acquisition: obtain the learning behavior data, interactive communication data and learning achievement data of each student user within a set period; The learning behavior data includes learning records; the interactive communication data includes the number of exchanges, participation frequency, number of questions raised, and number of questions solved; the learning outcome data includes the grade data of various types of courses; Data processing and evaluation: Evaluate the learning behavior data, interactive communication data, and learning outcome data of each student user within a set period, so as to determine the academic performance evaluation index, mutual learning evaluation index, and learning outcome evaluation index of each student user within a set period; Specifically: Analyze the study time and login times in the learning records of each student user within the set period to obtain the academic performance evaluation index of each student user within the set period; Analyze the number of exchanges and participation frequencies of each numbered student within the set period to obtain the mutual evaluation index of each numbered student within the set period; Analyze the course performance data of each type of students with different numbers within a set period to obtain the academic performance evaluation index of each student with different numbers within the set period; Personalized push: Based on the academic performance evaluation index, mutual evaluation index and learning outcome evaluation index of each numbered student user in the current set period, a learning evaluation report for each numbered student user in the current set period is generated and pushed to each numbered student user.

2. The data processing method based on big data Internet according to claim 1 is characterized in that: The specific steps for evaluating the learning behavior data of each student user number within the set period are: Extract the learning time and login times from the learning records of each numbered student user within the set period, calculate the ratio of the learning time of each numbered student user within the set period to the set period duration, and obtain the learning time proportion of each numbered student user, that is, calculate it by learning time / set period duration; Calculate the ratio of the number of logins of each numbered student user within the set period to the number of days in the set period, and obtain the login frequency of each numbered student user, that is, the number of logins / the number of days in the set period; Calculate the ratio of the study time of each numbered student user within the set period to the number of days in the set period, and get the average daily study time of each numbered student user, that is, study time / set number of days in the cycle.

3. The data processing method based on big data Internet according to claim 2 is characterized in that: Determine the academic performance evaluation index of each student user within the set period, specifically: The preset learning time percentage, login frequency and average daily learning time correspond to the qualified learning time percentage, qualified login frequency and qualified average daily learning time respectively; The ratio of the study time proportion, login frequency and average daily study time of each numbered student user within the set period is calculated with the corresponding preset passing study time proportion, passing login frequency and passing average daily study time, so as to obtain the time evaluation value, frequency evaluation value and average daily evaluation value; that is, it is calculated by the study time proportion / passing study time proportion, login frequency / passing login frequency and average daily study time / passing average daily study time; The duration evaluation value, frequency evaluation value and daily average evaluation value of each numbered student user within the set period are multiplied by the corresponding preset weight coefficients, and then the sum is calculated to obtain the academic performance evaluation index of each numbered student within the set period.

4. The data processing method based on big data Internet according to claim 3 is characterized in that: The specific steps for evaluating the interactive communication data of each numbered student user within a set period are: Extract the number of exchanges and participation frequencies from the interactive communication data of each numbered student user within a set period; count the number of speeches of each numbered student user within the set period as the number of exchanges of each numbered student user within the set period; The intervals of the number of communication times corresponding to each group of times are set, and each interval of the number of communication times corresponds to an active evaluation value; the number of communication times of each numbered student user within the set period is converted into an active evaluation value; Identify the number of days that each student user with a certain number participates in interactive communication within a set period, and calculate the ratio between the number of days in the set period to obtain the participation frequency of each student user with a certain number within the set period, that is, calculate by the number of days participating in interactive communication / the number of days in the set period; The number of questions raised and the number of questions solved are extracted from the interactive communication data of each numbered student user within a set period, and the ratio is calculated to obtain the ability ratio of each numbered student user within the set period, that is, calculated by number of problems solved / number of questions raised.

5. The data processing method based on big data Internet according to claim 4 is characterized in that: Determine the peer evaluation index of each student user within the set period, specifically: The preset activity assessment value, participation frequency and ability ratio correspond to the moderate activity assessment value, normal participation frequency and passing ability ratio respectively; The activity evaluation value, participation frequency and ability ratio of each numbered student user within the set period are calculated with the corresponding preset moderate activity evaluation value, normal participation frequency and passing ability ratio, so as to obtain the communication evaluation value, participation evaluation value and ability evaluation value; that is, calculated by active evaluation value / moderate activity evaluation value, participation frequency / normal participation frequency and ability ratio / passing ability ratio; The communication evaluation value, participation evaluation value and ability evaluation value of each numbered student user within the set period are multiplied by the corresponding preset weight coefficients, and then the sum is obtained to obtain the mutual evaluation index of each numbered student within the set period.

6. The data processing method based on big data Internet according to claim 5 is characterized in that: The specific steps for evaluating the learning achievement data of each student user within the set period are: Extract various types of course performance data from the learning achievement data of each numbered student user within a set period; Count the number of grade data of each type of course for each numbered student user within the set period. If the number of grade data of a certain type of course is greater than one, take the average of the grade data of each group of the corresponding type of course as the grade data of the corresponding type of course within the set period; Extract the average scores corresponding to each type of course score data; the average score is the average score of all students in the corresponding type of course; calculate the difference between each type of course score data of each numbered student user and the corresponding average score to obtain the score performance value; that is, the average score of each type of course score data minus the corresponding average score; If the calculation result of a set of performance values is a negative value, the type of course corresponding to the negative value will be marked as an abnormal course; if the calculation result of a set of performance values is a positive value, the positive value will be compared with the preset performance cutoff value. If the positive value is lower than the preset performance cutoff value, the type of course corresponding to the positive value will be marked as a passing course; if the positive value is higher than the preset performance cutoff value, the type of course corresponding to the positive value will be marked as an excellent course.

7. The data processing method based on big data Internet according to claim 6 is characterized in that: Determine the learning evaluation index of each student user number within the set period, specifically: Set the corresponding grades for abnormal courses, passing courses and excellent courses respectively; convert the abnormal courses, passing courses and excellent courses of each numbered student user into grade scores respectively, and accumulate them to obtain the abnormal course score, passing course score and excellent course score respectively; The passing course scores and excellent course scores of each numbered student user are accumulated, and the abnormal course scores are subtracted from the accumulated value to obtain the comprehensive score of each numbered student user; Set the interval of each group score corresponding to the comprehensive score; each group score interval corresponds to an assessment ratio; After converting the comprehensive performance score of each numbered student user into an assessment evaluation ratio, the obtained assessment evaluation ratio is used as the academic achievement evaluation index of each numbered student user within the set period.

8. The data processing method based on big data Internet according to claim 7 is characterized in that: Generate a learning evaluation report for each student user within the current set period, specifically: A three-dimensional space is pre-constructed, and each group of historical three-dimensional coordinate points is marked in the three-dimensional space; each group of historical three-dimensional coordinate points corresponds to a learning evaluation report; With the academic performance evaluation index in the current set period as the x-axis, the mutual evaluation index as the y-axis, and the academic achievement evaluation index as the z-axis, the three index values corresponding to each numbered student user are plotted as a three-dimensional coordinate point in the pre-constructed three-dimensional space; Divide the three-dimensional space into voxel regions according to the range, and locate the voxel region to which the three-dimensional coordinate point of each numbered student user belongs; Find the historical three-dimensional coordinate point in the located voxel area, and calculate the similarity between the current three-dimensional coordinate point and each historical three-dimensional coordinate point through a similarity measurement method, and select the historical three-dimensional coordinate point with the smallest distance according to the similarity; The learning evaluation report corresponding to the selected historical three-dimensional coordinate point is extracted as the learning evaluation report of each numbered student user within the current set period.

9. The data processing method based on big data Internet according to claim 8 is characterized in that: Also includes: Processing cycle adjustment: Based on the academic performance evaluation index, peer evaluation index and academic achievement evaluation index of each student user within the set period, adjust the specific duration of the next set period for each student user.

10. The data processing method based on big data Internet according to claim 9 is characterized in that: Adjust the specific duration of the next set cycle for each student user number, specifically: The weight coefficients corresponding to the academic performance evaluation index, the mutual evaluation index and the academic achievement evaluation index are set respectively, and the academic performance evaluation index, the mutual evaluation index and the academic achievement evaluation index of each numbered student user are multiplied by the corresponding weight coefficients respectively, and then the sum is calculated to obtain the academic status comprehensive index of each numbered student user; The comprehensive index of the academic status of each numbered student user is compared with the corresponding set reference index. If the comprehensive index of the academic status of a certain numbered student user is higher than the corresponding set reference index, the difference between the two is calculated to obtain the time increment; If the overall academic index of a student user with a certain ID is lower than the corresponding reference index, the difference between the two is calculated to obtain the duration deduction; Preset the intervals of each group of depreciation and each group of value-added corresponding to the depreciation and value-added of the duration, and each group of depreciation interval and each group of value-added interval respectively corresponds to a duration adjustment ratio; If a student user with a certain ID has a time reduction, the time adjustment ratio will be determined and then the set period time will be reduced accordingly based on the current set period time. If a student user with a certain number increases the duration, the duration adjustment ratio is determined and then, based on the current set period duration, the set period duration is extended accordingly according to the duration adjustment ratio.