CN111626372B - On-line teaching supervision and management method and system - Google Patents
On-line teaching supervision and management method and system Download PDFInfo
- Publication number
- CN111626372B CN111626372B CN202010477322.0A CN202010477322A CN111626372B CN 111626372 B CN111626372 B CN 111626372B CN 202010477322 A CN202010477322 A CN 202010477322A CN 111626372 B CN111626372 B CN 111626372B
- Authority
- CN
- China
- Prior art keywords
- index
- indexes
- teaching
- training
- learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 29
- 230000006399 behavior Effects 0.000 claims abstract description 118
- 238000012549 training Methods 0.000 claims abstract description 99
- 238000000034 method Methods 0.000 claims abstract description 54
- 230000000694 effects Effects 0.000 claims abstract description 13
- 238000012216 screening Methods 0.000 claims description 62
- 238000012360 testing method Methods 0.000 claims description 31
- 238000012937 correction Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Technology (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides an online teaching supervision and management method and system, wherein the method comprises the following steps: presetting an online teaching characteristic index of a teacher; presetting a learning behavior characteristic index of a student; collecting the historical learning behavior of students or the historical teaching behavior of teachers according to the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain sample data; constructing and training an early warning model according to the online teaching characteristic index, the learning behavior characteristic index and the sample data; acquiring real-time learning behaviors of students or real-time teaching behaviors of teachers, transmitting the real-time learning behaviors or the real-time teaching behaviors to a trained early warning model, and outputting classification results and corresponding index ranks by the early warning model; and calling corresponding intervention measures from a preset intervention system according to the classification result and the corresponding index ranking, and executing the intervention measures. The method gives early warning to student academic and carries out targeted teaching intervention, thereby guaranteeing the effect of online teaching.
Description
Technical Field
The invention belongs to the technical field of deep learning, and particularly relates to an online teaching supervision and management method and system.
Background
Along with the development of online teaching at present, the integration of artificial intelligence and online teaching becomes a necessary trend. The online teaching is imperative, the online teaching supervision and management system is matched with the online teaching resource construction to cooperatively develop, and the online teaching supervision and management system mainly comprises two major blocks of early warning of the academic industry and early warning of teaching intervention, wherein the early warning of the academic industry mainly comprises early warning of course examination results. The teaching intervention is used as an intervention means which affects the learning of a learner, can explain various factors and relations in the learning process, and can provide new ideas and views for improving the learning performance.
However, in the existing online teaching supervision and management system, most of the learning early warning models are universal prediction models, the complexity of all courses cannot be solved, and the learning early warning models are usually only aimed at student behaviors, so that teacher teaching behaviors are often ignored. The existing online teaching supervision and management system does not have a systematic teaching intervention method, so that the existing online teaching supervision and management system lacks supervision measures suitable for new technology in new era, and cannot guarantee that online teaching is substantially equivalent to offline teaching effects.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the on-line teaching supervision and management method and system, which realize early warning of student academic and pertinence teaching intervention, and ensure the on-line teaching effect.
In a first aspect, an online teaching supervision and management method includes the following steps:
presetting an online teaching characteristic index of a teacher;
presetting a learning behavior characteristic index of a student;
collecting the historical learning behavior of students or the historical teaching behavior of teachers according to the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain sample data;
constructing and training an early warning model according to the online teaching characteristic index, the learning behavior characteristic index and the sample data;
acquiring real-time learning behaviors of students or real-time teaching behaviors of teachers, transmitting the real-time learning behaviors or the real-time teaching behaviors to a trained early warning model, and outputting classification results and corresponding index ranks by the early warning model;
and calling corresponding intervention measures from a preset intervention system according to the classification result and the corresponding index ranking, and executing the intervention measures.
Preferably, the online teaching feature index comprises one or a combination of several indexes of:
the method comprises the steps of logging times, video resource numbers, teaching numbers, question numbers imported into a question bank, arrangement operation numbers, arrangement examination numbers, uploading video numbers, quoting other video numbers, correction operation numbers, correction examination numbers, classroom teaching scores and average online teaching check-in rate.
Preferably, the learning behavior feature index includes one or a combination of several indexes of:
the method comprises the steps of login times, video resource learning progress, check-in number of each course, number of completed jobs, number of completed exams, number of participation of classroom activities, interaction scoring with teachers, classroom scoring, number of completed classroom questions and answers and number of classroom learning notes.
Preferably, the method for constructing and training the early warning model comprises the following steps:
coarse screening is carried out on the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain screening indexes, and the screening indexes are ordered;
forming training samples from all sample data;
extracting the training samples for k times to obtain k training sets; the extraction method comprises the steps of extracting n data in a training sample each time to form a training set, then putting the extracted data back into the training sample, extracting n data in the training sample to form another training set, and circulating until k training sets are extracted; training each training set to obtain k classifiers;
extracting part of data from the training sample as a test set, defining a first screening index as a target index, and executing an importance judging step;
ranking the importance of each screening index obtained in the importance judging step to obtain an index ranking;
the importance judging step comprises the following steps: calculating the accuracy of the test set to obtain the original accuracy; after adding interference data to the target index in the test set, calculating the accuracy of the test set again to obtain interference accuracy, and calculating the difference between the original accuracy and the interference accuracy to obtain the importance of the target index; judging whether the next screening index is empty, if so, exiting the importance judging step; if not, defining the next screening index as the target index, and repeatedly executing the importance judging step.
Preferably, the coarse screening of the online teaching feature index and the learning behavior feature index to obtain screening indexes specifically includes:
inputting indexes, wherein the indexes comprise online teaching characteristic indexes and learning behavior characteristic indexes;
calculating a correlation matrix between indexes to obtain the correlation of each index;
and removing indexes of which the correlation does not meet the preset screening conditions to obtain the screening indexes.
In a second aspect, an on-line teaching supervision and management system includes:
an index setting unit: the method comprises the steps of presetting online teaching characteristic indexes of teachers and learning behavior characteristic indexes of students;
the acquisition unit: the system comprises a learning behavior feature index and a learning behavior feature index, wherein the learning behavior feature index is used for acquiring the learning behavior of students or the learning behavior of teachers according to the online teaching feature index and the learning behavior feature index so as to obtain sample data;
the construction unit: the early warning model is used for building and training an early warning model according to the online teaching characteristic index, the learning behavior characteristic index and the sample data;
an early warning unit: the method comprises the steps of acquiring real-time learning behaviors of students or real-time teaching behaviors of teachers, transmitting the real-time learning behaviors or the real-time teaching behaviors to a trained early warning model, and outputting classification results and corresponding index ranks by the early warning model;
an intervention unit: and the method is used for calling the corresponding intervention measures from a preset intervention system according to the classification result and the corresponding index rank and executing the intervention measures.
Preferably, the online teaching feature index comprises one or a combination of several indexes of:
the method comprises the steps of logging times, video resource numbers, teaching numbers, question numbers imported into a question bank, arrangement operation numbers, arrangement examination numbers, uploading video numbers, quoting other video numbers, correction operation numbers, correction examination numbers, classroom teaching scores and average online teaching check-in rate.
Preferably, the learning behavior feature index includes one or a combination of several indexes of:
the method comprises the steps of login times, video resource learning progress, check-in number of each course, number of completed jobs, number of completed exams, number of participation of classroom activities, interaction scoring with teachers, classroom scoring, number of completed classroom questions and answers and number of classroom learning notes.
Preferably, the method for constructing and training the early warning model comprises the following steps:
coarse screening is carried out on the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain screening indexes, and the screening indexes are ordered;
forming training samples from all sample data;
extracting the training samples for k times to obtain k training sets; the extraction method comprises the steps of extracting n data in a training sample each time to form a training set, then putting the extracted data back into the training sample, extracting n data in the training sample to form another training set, and circulating until k training sets are extracted; training each training set to obtain k classifiers;
extracting part of data from the training sample as a test set, defining a first screening index as a target index, and executing an importance judging step;
ranking the importance of each screening index obtained in the importance judging step to obtain an index ranking;
the importance judging step comprises the following steps: calculating the accuracy of the test set to obtain the original accuracy; after adding interference data to the target index in the test set, calculating the accuracy of the test set again to obtain interference accuracy, and calculating the difference between the original accuracy and the interference accuracy to obtain the importance of the target index; judging whether the next screening index is empty, if so, exiting the importance judging step; if not, defining the next screening index as the target index, and repeatedly executing the importance judging step.
Preferably, the construction unit is specifically configured to:
inputting indexes, wherein the indexes comprise online teaching characteristic indexes and learning behavior characteristic indexes;
calculating a correlation matrix between indexes to obtain the correlation of each index;
and removing indexes of which the correlation does not meet the preset screening conditions to obtain the screening indexes.
According to the technical scheme, the on-line teaching supervision and management method and system provided by the invention are used for constructing the early warning model by using the machine learning technology and the acquired teacher teaching behaviors and student learning behaviors so as to predict the academic achievements, and then the early warning model is continuously trained and tested, so that the accuracy of the early warning model is improved. And performing intervention after obtaining classification results and corresponding index ranks of students or teachers. The intervention comprises the intervention aiming at the teacher condition, the intervention aiming at the student condition or the intervention aiming at the course so as to monitor the teacher and warn the students, thereby forming intelligent early warning, intervention teaching and student behavior, realizing online teaching supervision closed loop of the intelligent early warning.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
Fig. 1 is a flowchart of an on-line teaching supervision and management method according to an embodiment of the invention.
Fig. 2 is a flowchart of a method for constructing and training an early warning model according to a third embodiment of the present invention.
Fig. 3 is a flowchart of a screening indicator obtaining method according to a third embodiment of the present invention.
Fig. 4 is a block diagram of an on-line teaching supervision and management system according to a fourth embodiment of the present invention.
Detailed Description
Embodiments of the technical scheme of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and thus are merely examples, and are not intended to limit the scope of the present invention. It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Embodiment one:
an online teaching supervision and management method, see fig. 1, comprises the following steps:
s1: presetting an online teaching characteristic index of a teacher;
s2: presetting a learning behavior characteristic index of a student;
specifically, the online teaching characteristic index and the learning behavior characteristic index are set by the user, can be set according to courses, can be set according to teaching requirements, and the like.
S3: collecting the historical learning behavior of students or the historical teaching behavior of teachers according to the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain sample data;
specifically, the method collects corresponding data to form sample data according to the online teaching characteristic index and the learning behavior characteristic index.
S4: constructing and training an early warning model according to the online teaching characteristic index, the learning behavior characteristic index and the sample data;
s5: acquiring real-time learning behaviors of students or real-time teaching behaviors of teachers, transmitting the real-time learning behaviors or the real-time teaching behaviors to a trained early warning model, and outputting classification results and corresponding index ranks by the early warning model;
s6: according to the classification result and the corresponding index ranking, corresponding intervention measures are called from a preset intervention system, and the intervention measures are executed;
specifically, the method performs accurate intervention according to the output classification result of the early warning model and the corresponding index ranking, for example, if the output classification result of the early warning model is failed, the index with larger importance in the corresponding index ranking is obtained, and the interference measures of the indexes are executed. If the index with higher importance is an on-line teaching feature index, executing the intervention measure formulated based on teacher behavior data, if the index with higher importance is a learning behavior feature index, executing the intervention measure formulated based on student behavior data, and if the early warning model output classification result is excellent, executing the intervention measure may include the top-up and the like.
The method not only analyzes the cause of the possibly caused early warning of the academic industry in the teaching behaviors of teachers and the learning behaviors of students through accurate monitoring early warning, but also performs targeted intervention so as to improve the efficiency and effect of online learning. The intervention method comprises the steps of timely adopting an administrative intervention method in teaching supervision and management when the characteristics of the teacher group change, and preventing the early warning phenomenon of the group academic due to the teacher factor. And also comprises the step of notifying teachers or coaches and the like to take corresponding interventions when the student groups are found to have strong changes. The method provides three measures aiming at two behaviors, wherein the two behaviors comprise teacher behaviors and student behaviors, and the three measures comprise teaching management intervention measures, student consciousness intervention measures and platform technology intervention measures, and the specific is shown in table 1.
TABLE 1 intervention
According to the on-line teaching supervision and management method provided by the embodiment, the machine learning technology, the acquired teacher teaching behaviors and student learning behaviors are utilized to construct an early warning model for predicting academic achievements, and then training and testing are continuously carried out on the early warning model, so that the accuracy of the early warning model is improved. And performing intervention after obtaining classification results and corresponding index ranks of students or teachers. The intervention comprises the intervention aiming at the teacher condition, the intervention aiming at the student condition or the intervention aiming at the course so as to monitor the teacher and warn the students, thereby forming intelligent early warning, intervention teaching and student behavior, realizing online teaching supervision closed loop of the intelligent early warning.
Embodiment two:
embodiment two adds the following to the embodiment one:
the online teaching characteristic index comprises one or a combination of several indexes:
the method comprises the steps of logging times, video resource numbers, teaching numbers, question numbers imported into a question bank, arrangement operation numbers, arrangement examination numbers, uploading video numbers, quoting other video numbers, correction operation numbers, correction examination numbers, classroom teaching scores and average online teaching check-in rate.
Specifically, the method aims at analyzing the relation between the online teaching of a teacher and the assessment results of the courses of students and early warningThe model is used for monitoring the online teaching activities of the teacher, intervening in the behaviors which possibly affect the assessment results of the courses of the students, and collecting the online teaching feature data of the teacher according to the online teaching feature indexes. Referring to table 2, the method sets 13 online teaching feature index sets x= { X 1 ,x 2 ,x 3 ,···,x n },n=13:
Table 2 on-line teaching characteristic index table:
preferably, the learning behavior feature index includes one or a combination of several indexes of:
the method comprises the steps of login times, video resource learning progress, check-in number of each course, number of completed jobs, number of completed exams, number of participation of classroom activities, interaction scoring with teachers, classroom scoring, number of completed classroom questions and answers and number of classroom learning notes.
Specifically, in order to analyze the relationship between the online learning condition of the student and the course assessment score, monitor the student with abnormal learning behavior, intervene the learning behavior possibly generated by the student score, and collect the learning behavior feature data of the student according to the learning behavior feature index. Referring to table 3, the method sets 11 learning behavior feature index sets y= { Y 1 ,y 2 ,y 3 ,···,y n },n=11:
TABLE 3 learning behavior characteristics index Table
Characteristic index | Index name | Index description |
Number of logins | y 1 | Number of logins |
Progress of learning | y 2 | Student video resource learning progress |
Number of check-ins | y 3 | Number of check-ins per class for students |
Work is carried out | y 5 | Number of completed jobs |
Examination method | y 6 | Number of times of completing examination |
Number of classroom activities | y 7 | Number of classroom activities participation |
Interaction scoring with teacher | y 8 | Student scoring teacher interactions with conversion scores |
Classroom scoring | y 9 | Student evaluation teacher score |
Question and answer | y 10 | Complete the number of questions and answers in teacher class |
Note-book | y 11 | Number of notes recorded in classroom learning |
For a brief description of the method provided in the embodiments of the present invention, reference may be made to the corresponding content in the foregoing method embodiments where the description of the embodiments is not mentioned.
Embodiment III:
the third embodiment defines a specific construction method of the early warning model based on the above embodiment.
Referring to fig. 2, the method for constructing and training the early warning model includes:
s11: coarse screening is performed on the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain screening indexes, and the screening indexes are ranked, see fig. 3, and specifically include:
s21: inputting indexes, wherein the indexes comprise online teaching characteristic indexes and learning behavior characteristic indexes;
s22: calculating a correlation matrix between indexes to obtain the correlation of each index;
s23: and removing indexes of which the correlation does not meet the preset screening conditions to obtain the screening indexes.
Specifically, the method comprises the steps of firstly inputting an index set X, calculating a correlation matrix W between indexes, and obtaining the correlation of an ith indexWherein w is ij As index weight, P ij As j index, ε ij Is a bias parameter. The method firstly carries out preliminary screening on indexes, for example, N indexes in total are assumed, and m optimal indexes are selected from N indexes to serve as screening indexes, wherein m is more than or equal to 0 and less than or equal to N. The screening condition may be set by itself according to a specific situation, for example, to remove an index whose correlation is lower than a certain set value.
S12: forming training samples from all sample data;
s13: extracting the training samples for k times to obtain k training sets; the extraction method comprises the steps of extracting n data in a training sample each time to form a training set, then putting the extracted data back into the training sample, extracting n data in the training sample to form another training set, and circulating until k training sets are extracted;
s14: training each training set to obtain k classifiers;
specifically, the classification result is set according to a specific case, for example, if set to 2 kinds, the classification result includes pass and fail. If set to class 3, the classification result includes excellent, pass and fail. The N classes can also be set according to different conditions. The method may manually add classification results based on each sample data. And training the sample data and the corresponding classification result by using the classification model to obtain a classifier. The method comprises generating k training sets T based on training samples at random 1 ,T 2 ,...T k Then training each training set to obtain k classifiers, for example, the k classifiers are C 1 (X),C 2 (X),...C k (X). The training set generation method comprises the following steps: firstly, randomly selecting n data from all training samples as one training set, then putting the n data back into the original training samples, and randomly extracting the n data to form another training set, thus finally randomly generating k training sets.
S15: extracting part of data from the training sample as a test set, defining a first screening index as a target index, and executing an importance judging step;
s16: ranking the importance of each screening index obtained in the importance judging step to obtain an index ranking;
the importance judging step comprises the following steps: calculating the accuracy of the test set to obtain the original accuracy; after adding interference data to the target index in the test set, calculating the accuracy of the test set again to obtain interference accuracy, and calculating the difference between the original accuracy and the interference accuracy to obtain the importance of the target index; judging whether the next screening index is empty, if so, exiting the importance judging step; if not, defining the next screening index as the target index, and repeatedly executing the importance judging step.
Specifically, the test set may be composed of data that does not participate in the training of the early warning model, or may be composed of randomly extracting a certain proportion of data. The test set may be used to evaluate model generalization performance while evaluating index importance.
The method extracts partial data from the training sample as a test set L, and calculates the accuracy Acc of the test set L L1 For interference index x in test set L i After adding the interference data, retesting the accuracy Acc of the set L L2 Calculate importance score=acc L1 -Acc L2 . If score is greater than 0, this indicates that accuracy is reduced after the addition of the interference data, indicating that the feature is of higher importance. Conversely, if score is less than 0, this indicates that accuracy increases after the interference data is added, indicating that the feature is of less importance. Therefore, the importance index in the characteristic system can be calculated, and accurate intervention is performed for students and teachers.
For a brief description of the method provided in the embodiments of the present invention, reference may be made to the corresponding content in the foregoing method embodiments where the description of the embodiments is not mentioned.
Embodiment four:
an on-line teaching supervision and management system, see fig. 4, comprising:
an index setting unit: the method comprises the steps of presetting online teaching characteristic indexes of teachers and learning behavior characteristic indexes of students;
the acquisition unit: the system comprises a learning behavior feature index and a learning behavior feature index, wherein the learning behavior feature index is used for acquiring the learning behavior of students or the learning behavior of teachers according to the online teaching feature index and the learning behavior feature index so as to obtain sample data;
the construction unit: the early warning model is used for building and training an early warning model according to the online teaching characteristic index, the learning behavior characteristic index and the sample data;
an early warning unit: the method comprises the steps of acquiring real-time learning behaviors of students or real-time teaching behaviors of teachers, transmitting the real-time learning behaviors or the real-time teaching behaviors to a trained early warning model, and outputting classification results and corresponding index ranks by the early warning model;
an intervention unit: and the method is used for calling the corresponding intervention measures from a preset intervention system according to the classification result and the corresponding index rank and executing the intervention measures.
Preferably, the online teaching feature index comprises one or a combination of several indexes of:
the method comprises the steps of logging times, video resource numbers, teaching numbers, question numbers imported into a question bank, arrangement operation numbers, arrangement examination numbers, uploading video numbers, quoting other video numbers, correction operation numbers, correction examination numbers, classroom teaching scores and average online teaching check-in rate.
Preferably, the learning behavior feature index includes one or a combination of several indexes of:
the method comprises the steps of login times, video resource learning progress, check-in number of each course, number of completed jobs, number of completed exams, number of participation of classroom activities, interaction scoring with teachers, classroom scoring, number of completed classroom questions and answers and number of classroom learning notes.
Preferably, the method for constructing and training the early warning model comprises the following steps:
coarse screening is carried out on the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain screening indexes, and the screening indexes are ordered;
forming training samples from all sample data;
extracting the training samples for k times to obtain k training sets; the extraction method comprises the steps of extracting n data in a training sample each time to form a training set, then putting the extracted data back into the training sample, extracting n data in the training sample to form another training set, and circulating until k training sets are extracted;
training each training set to obtain k classifiers;
extracting part of data from the training sample as a test set, defining a first screening index as a target index, and executing an importance judging step;
ranking the importance of each screening index obtained in the importance judging step to obtain an index ranking;
the importance judging step comprises the following steps: calculating the accuracy of the test set to obtain the original accuracy; after adding interference data to the target index in the test set, calculating the accuracy of the test set again to obtain interference accuracy, and calculating the difference between the original accuracy and the interference accuracy to obtain the importance of the target index; judging whether the next screening index is empty, if so, exiting the importance judging step; if not, defining the next screening index as the target index, and repeatedly executing the importance judging step.
Preferably, the construction unit is specifically configured to:
inputting indexes, wherein the indexes comprise online teaching characteristic indexes and learning behavior characteristic indexes;
calculating a correlation matrix between indexes to obtain the correlation of each index;
and removing indexes of which the correlation does not meet the preset screening conditions to obtain the screening indexes.
The online teaching supervision and management system utilizes the machine learning technology and the acquired teacher teaching behaviors and student learning behaviors to construct an early warning model for predicting academic achievements, and then continuously trains and tests the early warning model to improve the accuracy of the early warning model. And performing intervention after obtaining classification results and corresponding index ranks of students or teachers. The intervention comprises the intervention aiming at the teacher condition, the intervention aiming at the student condition or the intervention aiming at the course so as to monitor the teacher and warn the students, thereby forming intelligent early warning, intervention teaching and student behavior, realizing online teaching supervision closed loop of the intelligent early warning.
For a brief description of the system provided by the embodiments of the present invention, reference may be made to the corresponding content in the foregoing method embodiments where the description of the embodiments is not mentioned.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (8)
1. The on-line teaching supervision and management method is characterized by comprising the following steps of:
presetting an online teaching characteristic index of a teacher;
presetting a learning behavior characteristic index of a student;
collecting the historical learning behavior of students or the historical teaching behavior of teachers according to the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain sample data;
constructing and training an early warning model according to the online teaching characteristic index, the learning behavior characteristic index and the sample data;
acquiring real-time learning behaviors of students or real-time teaching behaviors of teachers, transmitting the real-time learning behaviors or the real-time teaching behaviors to a trained early warning model, and outputting classification results and corresponding index ranks by the early warning model;
according to the classification result and the corresponding index ranking, corresponding intervention measures are called from a preset intervention system, and the intervention measures are executed;
the construction and training method of the early warning model comprises the following steps:
coarse screening is carried out on the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain screening indexes, and the screening indexes are ordered;
forming training samples from all sample data;
extracting the training samples for k times to obtain k training sets; the extraction method comprises the steps of extracting n data in a training sample each time to form a training set, then putting the extracted data back into the training sample, extracting n data in the training sample to form another training set, and circulating until k training sets are extracted;
training each training set to obtain k classifiers;
extracting part of data from the training sample as a test set, defining a first screening index as a target index, and executing an importance judging step;
ranking the importance of each screening index obtained in the importance judging step to obtain an index ranking;
the importance judging step comprises the following steps: calculating the accuracy of the test set to obtain the original accuracy; after adding interference data to the target index in the test set, calculating the accuracy of the test set again to obtain interference accuracy, and calculating the difference between the original accuracy and the interference accuracy to obtain the importance of the target index; judging whether the next screening index is empty, if so, exiting the importance judging step; if not, defining the next screening index as the target index, and repeatedly executing the importance judging step.
2. The on-line teaching supervision and management method according to claim 1, wherein,
the online teaching characteristic index comprises one or a combination of several indexes:
the method comprises the steps of logging times, video resource numbers, teaching numbers, question numbers imported into a question bank, arrangement operation numbers, arrangement examination numbers, uploading video numbers, quoting other video numbers, correction operation numbers, correction examination numbers, classroom teaching scores and average online teaching check-in rate.
3. The on-line teaching supervision and management method according to claim 1, wherein,
the learning behavior characteristic index comprises one or a combination of several indexes:
the method comprises the steps of login times, video resource learning progress, check-in number of each course, number of completed jobs, number of completed exams, number of participation of classroom activities, interaction scoring with teachers, classroom scoring, number of completed classroom questions and answers and number of classroom learning notes.
4. The on-line teaching supervision and management method according to claim 1, wherein the performing coarse screening on the on-line teaching feature index and the learning behavior feature index to obtain screening indexes specifically includes:
inputting indexes, wherein the indexes comprise online teaching characteristic indexes and learning behavior characteristic indexes;
calculating a correlation matrix between indexes to obtain the correlation of each index;
and removing indexes of which the correlation does not meet the preset screening conditions to obtain the screening indexes.
5. An on-line teaching supervision and management system, comprising:
an index setting unit: the method comprises the steps of presetting online teaching characteristic indexes of teachers and learning behavior characteristic indexes of students;
the acquisition unit: collecting the historical learning behavior of students or the historical teaching behavior of teachers according to the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain sample data;
the construction unit: the early warning model is used for building and training an early warning model according to the online teaching characteristic index, the learning behavior characteristic index and the sample data;
an early warning unit: the method comprises the steps of acquiring real-time learning behaviors of students or real-time teaching behaviors of teachers, transmitting the real-time learning behaviors or the real-time teaching behaviors to a trained early warning model, and outputting classification results and corresponding index ranks by the early warning model;
an intervention unit: the method comprises the steps of acquiring corresponding intervention measures from a preset intervention system according to the classification result and the corresponding index rank, and executing the intervention measures;
the construction and training method of the early warning model comprises the following steps:
coarse screening is carried out on the online teaching characteristic indexes and the learning behavior characteristic indexes to obtain screening indexes, and the screening indexes are ordered;
forming training samples from all sample data;
extracting the training samples for k times to obtain k training sets; the extraction method comprises the steps of extracting n data in a training sample each time to form a training set, then putting the extracted data back into the training sample, extracting n data in the training sample to form another training set, and circulating in such a way until k training sets are extracted to respectively train each training set so as to obtain k classifiers;
extracting part of data from the training sample as a test set, defining a first screening index as a target index, and executing an importance judging step;
ranking the importance of each screening index obtained in the importance judging step to obtain an index ranking;
the importance judging step comprises the following steps: calculating the accuracy of the test set to obtain the original accuracy; after adding interference data to the target index in the test set, calculating the accuracy of the test set again to obtain interference accuracy, and calculating the difference between the original accuracy and the interference accuracy to obtain the importance of the target index; judging whether the next screening index is empty, if so, exiting the importance judging step; if not, defining the next screening index as the target index, and repeatedly executing the importance judging step.
6. The on-line teaching supervision and management system according to claim 5,
the online teaching characteristic index comprises one or a combination of several indexes:
the method comprises the steps of logging times, video resource numbers, teaching numbers, question numbers imported into a question bank, arrangement operation numbers, arrangement examination numbers, uploading video numbers, quoting other video numbers, correction operation numbers, correction examination numbers, classroom teaching scores and average online teaching check-in rate.
7. The on-line teaching supervision and management system according to claim 5,
the learning behavior characteristic index comprises one or a combination of several indexes:
the method comprises the steps of login times, video resource learning progress, check-in number of each course, number of completed jobs, number of completed exams, number of participation of classroom activities, interaction scoring with teachers, classroom scoring, number of completed classroom questions and answers and number of classroom learning notes.
8. The on-line teaching supervision and management system according to claim 5, wherein the construction unit is specifically configured to:
inputting indexes, wherein the indexes comprise online teaching characteristic indexes and learning behavior characteristic indexes;
calculating a correlation matrix between indexes to obtain the correlation of each index;
and removing indexes of which the correlation does not meet the preset screening conditions to obtain the screening indexes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010477322.0A CN111626372B (en) | 2020-05-29 | 2020-05-29 | On-line teaching supervision and management method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010477322.0A CN111626372B (en) | 2020-05-29 | 2020-05-29 | On-line teaching supervision and management method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111626372A CN111626372A (en) | 2020-09-04 |
CN111626372B true CN111626372B (en) | 2023-06-23 |
Family
ID=72271972
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010477322.0A Active CN111626372B (en) | 2020-05-29 | 2020-05-29 | On-line teaching supervision and management method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111626372B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112149884A (en) * | 2020-09-07 | 2020-12-29 | 南京莱斯网信技术研究院有限公司 | Academic early warning monitoring method for large-scale students |
CN115086363B (en) * | 2022-05-23 | 2024-02-13 | 北京声智科技有限公司 | Early warning method and device for learning task, electronic equipment and storage medium |
WO2024006154A1 (en) * | 2022-06-28 | 2024-01-04 | HonorEd Technologies, Inc. | Comprehension modeling and ai-sourced student content recommendations |
CN116227729B (en) * | 2023-03-20 | 2023-10-10 | 广州工程技术职业学院 | Learning evaluation method, device and equipment based on machine learning |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106485964B (en) * | 2016-10-19 | 2019-04-02 | 深圳市鹰硕技术有限公司 | A kind of recording of classroom instruction and the method and system of program request |
CN109658004A (en) * | 2018-12-28 | 2019-04-19 | 杭州博世数据网络有限公司 | Intelligent task management and early warning push educational administration management system |
CN110910038A (en) * | 2019-12-02 | 2020-03-24 | 成都中医药大学 | Method for constructing teacher teaching portrait model based on network course |
-
2020
- 2020-05-29 CN CN202010477322.0A patent/CN111626372B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN111626372A (en) | 2020-09-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111626372B (en) | On-line teaching supervision and management method and system | |
Gadhavi et al. | Student final grade prediction based on linear regression | |
CN109345101A (en) | Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method | |
Verma et al. | National identity predictive models for the real time prediction of European school’s students: preliminary results | |
Ashenafi et al. | Predicting Student Progress from Peer-Assessment Data. | |
CN114388103A (en) | Algorithm for teenager psychological early warning analysis | |
Hadzhikolev et al. | Models for multicomponent fuzzy evaluation, with a focus on the assessment of higher-order thinking skills | |
CN111553581B (en) | Equipment maintainability evaluation model based on entropy value | |
CN116664001B (en) | Student skill assessment method and system based on artificial intelligence | |
CN111369140A (en) | Teaching evaluation system and method | |
CN117313947A (en) | Learning early warning method based on random forest and tuna group optimization algorithm | |
CN111126812A (en) | Comprehensive learning ability monitoring method and device, electronic equipment and storage medium | |
CN115409257A (en) | Score distribution prediction method and system based on condition density estimation model | |
CN112015830B (en) | Question storage method suitable for adaptive learning | |
CN112184040A (en) | Platform for evaluating software engineering capability based on behavior and learning data | |
CN113537738A (en) | Multi-cycle and multi-constraint fused aviation emergency rescue efficiency evaluation method | |
Wu et al. | Analysis of students' learning behavior under network learning environment | |
Bendjebar et al. | An improvement of a data mining technique for early detection of at-risk learners in distance learning environments | |
CN112766765A (en) | Professional learning ability evaluation method and system based on interval middle intelligence theory | |
Tan et al. | Predicting dropout from online education based on neural networks | |
Noskov et al. | Mathematical model for early prediction of learning success | |
Jing | Continuous improvement of college english teaching based on quantitative analysis of course objective achievement | |
CN116109456B (en) | Comprehensive evaluation method and system for intelligent education, electronic equipment and storage medium | |
Ratnaningsih et al. | Identifying Students’ Behavioral Online Learning Patterns Through Learning Analytics: a Case of Universitas Terbuka | |
Murad et al. | Student Assessment Factors in Study Success Using the Decision Tree Algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |