CN111275239A - Multi-mode-based networked teaching data analysis method and system - Google Patents
Multi-mode-based networked teaching data analysis method and system Download PDFInfo
- Publication number
- CN111275239A CN111275239A CN201911329595.4A CN201911329595A CN111275239A CN 111275239 A CN111275239 A CN 111275239A CN 201911329595 A CN201911329595 A CN 201911329595A CN 111275239 A CN111275239 A CN 111275239A
- Authority
- CN
- China
- Prior art keywords
- learning
- data
- feature
- students
- online
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000007405 data analysis Methods 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 50
- 238000013210 evaluation model Methods 0.000 claims abstract description 43
- 230000000694 effects Effects 0.000 claims abstract description 38
- 230000006399 behavior Effects 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000012216 screening Methods 0.000 claims abstract description 21
- 238000005516 engineering process Methods 0.000 claims abstract description 20
- 238000007637 random forest analysis Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000007418 data mining Methods 0.000 claims abstract description 10
- 238000012800 visualization Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000003066 decision tree Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 15
- 238000002474 experimental method Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 5
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000007786 learning performance Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 abstract description 8
- 230000004927 fusion Effects 0.000 abstract description 4
- 230000000875 corresponding effect Effects 0.000 description 12
- 238000013461 design Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 7
- 238000013480 data collection Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002906 microbiologic effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008450 motivation Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000012925 biological evaluation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003867 tiredness Effects 0.000 description 1
- 208000016255 tiredness Diseases 0.000 description 1
- 208000016254 weariness Diseases 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Technology (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of data processing, and discloses a multi-mode-based networked teaching data analysis method and system, which adopt a maximum information coefficient MIC to carry out feature screening and remove irrelevant factors; after feature screening is carried out by using MIC analysis, the screened features are recombined into a feature space, and regression is carried out by using a random forest to obtain a final evaluation model; the method combines a learning analysis technology and a data mining algorithm, integrates and analyzes learning capacity data, physiological data and learning behavior data generated by students learning on a theoretical course online learning platform, establishes a theoretical online course learning effect evaluation model, evaluates the learning effect of the students, and outputs evaluation results in the forms of charts, numbers and the like by applying a visualization technology. The invention utilizes the machine learning technology to establish a theory course evaluation system of multi-mode information fusion and provides theory and technical method support for the online course learning process.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a multi-mode-based networked teaching data analysis method and system.
Background
Currently, the closest prior art: different from the traditional teachers and students face-to-face teaching mode, the network teaching method has important significance in constructing an effective evaluation system model aiming at the networked courses. At present, a great deal of research is carried out on collecting, measuring, analyzing and reporting learning behavior data of students by using learning analysis technologies such as correlation analysis, regression analysis and data mining algorithm, so as to understand and optimize teaching process and situation, provide support for teaching decision and academic early warning and improve teaching effect.
However, the prior art mainly relates to acquisition and analysis of learning behavior data of students, and meanwhile, the established evaluation model is relatively fixed, so that certain evaluation prediction errors exist in application of different batches and environments. In network online education, teachers and students are in a quasi-separation state, students mostly study independently geographically, emotional attention of teachers is lacked, deep communication with other students is difficult, and classroom presence and collective belonging feeling of traditional education cannot be realized, so that the loneness of students is strengthened, and learning tiredness is easily caused; the students cannot timely obtain the feedback, evaluation and excitation of teachers and classmates in the learning process, so that anxiety is easy to generate; in the process, along with the change of the physiological signal indexes of the body, the learning effect of students can be influenced. In addition, the learning abilities of students, such as intelligence factors, meta learning abilities, intrinsic factors, etc., of the students play an extremely important role in the whole learning process. Therefore, it is difficult to achieve a comprehensive and accurate evaluation of the learning effect of the theoretical course by simply relying on the learning behavior data or the learning ability data. Except for the problem that the evaluation standard is too single, a general course evaluation system is usually formed after the whole teaching process is finished, has hysteresis, and is difficult to realize active intervention on the learning process of students.
In summary, the problems of the prior art are as follows:
(1) the prior art mainly relates to the acquisition and analysis of learning behavior data of students, and meanwhile, an established evaluation model is relatively fixed, so that certain evaluation prediction errors exist in the application of different batches and environments.
(2) In the existing network online education, teachers and students are in a quasi-separation state, students mostly study alone geographically, the emotional attention of teachers is lacked, the students are difficult to deeply communicate with other students, the classroom presence and the body attribution of the traditional education are not realized, the loneness of the students is strengthened, and the learning weariness is easily caused; affecting the learning effect of students.
(3) The prior art mainly relates to the acquisition of student learning behavior data and the single analysis and evaluation standard, has hysteresis and is difficult to realize the active intervention on the learning process of students.
The difficulty of solving the technical problem is as follows:
the learning ability data of the learners are acquired in the form of questionnaires, which requires that the characteristics related to the questionnaires established by the learners are comprehensive and the subjective psychological factors of the respondents are considered.
The modeling is carried out according to the characteristics, the accuracy of the model is considered, the risk of overfitting is avoided, a strict research frame needs to be considered in the modeling process, the validity of the standard is ensured while the important degree of each factor in the learning and evaluation process is screened and quantified, the too harsh standard cannot be set, otherwise, the data overfitting to the sample is easy, and the data cannot be generalized to the outside of the sample in many times.
None of the machine learning models can win long, but we also face how to find the optimal solution for the current event. In general, model fusion can improve the final prediction capability more or less, and is generally not worse than the optimal submodel. This requires that we must consider a variety of modeling methods using machine learning and build a fused model on the basis of these models, which is ultimately used for prediction.
The application of the evaluation model constructed only based on the first batch of data to the evaluation of the subsequent students can directly cause the instability of the evaluation result, and as learners can continuously generate dynamic big data in the learning process, the generation of the data means the richness of characteristic data, but also brings the complexity of characteristic analysis, how to determine the influence factors of the same characteristics of different batches on the final model construction, the evaluation comparison between models combined by different batches in different combination modes, and how to screen quantitative characteristics according to the evaluation models constructed based on different combination modes, which all require that the learners have strict logic structures.
The significance for solving the technical problems is as follows:
the characteristics are the basis of modeling, good characteristics can play a very positive role in establishing a final model, and poor characteristics can cause the result deviation of the model, so that the acquisition of learning characteristics is very important for the accuracy of modeling, and the analysis of research data and the application of research results. The characteristics are effectively screened and quantified, overfitting is avoided when the model is established, and the application accuracy of the model in data outside a sample can be effectively improved. The model is optimized in real time according to big data continuously generated by the learner in the learning process, so that the prediction capability of the model can be further improved.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a multi-mode-based networked teaching data analysis method and system.
The invention is realized in such a way that a multi-mode-based networked teaching data analysis method comprises the following steps:
firstly, performing feature screening by adopting a maximum information coefficient MIC to remove irrelevant factors; calculating correlation coefficients of the feature space X and the achievement space S column by column, and selecting a feature corresponding to the maximum value of the correlation coefficients as a first feature; calculating the feature f1MIC value with other characteristics, LmaxThe corresponding feature is selected as the second feature f2(ii) a Removing the first characteristic, and repeating the steps until the most characteristic quantity is obtained;
secondly, after feature screening is carried out by using MIC analysis, the screened features are recombined into a feature space, and regression is carried out by using a random forest to obtain a final evaluation model;
and thirdly, integrating and analyzing learning ability data, physiological data and learning behavior data generated by the students on the theoretical course online learning platform by adopting a method of combining a learning analysis technology and a data mining algorithm, establishing a theoretical online course learning effect evaluation model, evaluating the learning effect of the students, and outputting the evaluation result in the forms of graphs, numbers and the like by applying a visualization technology.
Further, the multi-modal data feature screening of the multi-modal based networked teaching data analysis method comprises: the on-line learning score of the student theoretical course gives specific quantitative data through on-line real practice and on-line test before the course is finished each time, physiological signal data finishes acquisition and data transmission through the intelligent bracelet, and the average value and variance of signal sequence acquisition are used as the characteristic xbio(ii) a Learning behavior data (x)bah) The collection is completed through a theoretical course online learning platform; learning ability data (x)iq) Before the first theoretical course begins, all the courses can be acquired in an electronic questionnaire form; the feature vector of each student is denoted Xi＝(xbio，xbah，xiq) The feature space of all students is expressed as X ═ (X)1，X2，...，Xn)TWhere n is the number of students and the corresponding score space is expressed as S ═ S (S)1，S2，...，Sn)T. All the characteristics are subjected to variance normalization, and then the relation between each factor and the learning performance of the theoretical course is analyzed.
Further, the multi-mode-based networked teaching data analysis method adopts the maximum information coefficient MIC to carry out feature screening and removes irrelevant factors, and comprises the following specific steps: first, the correlation coefficient P ═ of the feature space X and the achievement space S is calculated column by column (P)1，p2，...，pn) The maximum value P of the correlation coefficientmaxThe corresponding feature is selected as the first feature, assumed to be f1＝Xk(ii) a Then calculate the feature f1MIC value M ═ between other features (M)1，...，mk-1，mk+1，...，mn) Let L equal to 0.5 × P (i ≠ k) +0.5 × 1-M, and let L equal to 0.5 × P (i ≠ k) +0.5 × MmaxThe corresponding feature is selected as a second feature f 2; and removing the first feature, and repeating the steps until the most number of features is obtained or the maximum value of the current MIC is less than a certain threshold value.
Further, the multi-modal data initial evaluation model establishment of the multi-modal based networked teaching data analysis method comprises the following steps: the random forest is composed of N decision trees, the N decision trees are trained circularly during training, a training sample of each decision tree is obtained by Bootstrap sampling from an original training set, the used characteristic of each node of the training decision tree is also obtained by random sampling from a new characteristic space X, each decision tree is subjected to recursive splitting according to a judgment criterion, and after the training of the N decision trees is finished, the average value of leaf nodes where students are located is the final regression score;
bootstrap sampling is the extraction of n samples with a put back in a set of n samples to form a data set.
Further, the implementation method of the single decision tree by adopting the recursive splitting process is as follows: the extracted sample set D forms a root node, and the sample set is split into two parts, namely D1 and D2, according to a judgment criterion; establishing a left sub-tree by recursion of a sample set D1, and establishing a right sub-tree by a sample set D2; and setting a condition for stopping splitting, and marking the node as a leaf node when the splitting cannot be continued, and assigning values.
Further, the specific implementation method of the decision criterion is as follows: calculating the regression error of the root node, namely the mean square sum error of the label value and the regression value of all samples, and defining as follows:
randomly extracting features X from a new feature space XuSorting the extracted training samples D from small to large according to the values of the features; sequentially using the score of each student as a threshold value, dividing the sample into a left part and a right part, and then calculating the mean square sum error of a left sub-tree and a right sub-tree; the error index for splitting is defined as the regression error before splitting minus the regression error of the left and right subtrees after splitting:
E＝E(D)-E(D1)-E(D2)；
if the index is maximized, continuing splitting; when the depth of the artificially set decision tree is reached or the calculated regression error is larger than the artificially set threshold value, stopping splitting, setting the node as a leaf node, wherein the value of the leaf node is the mean value of the label values of the node sample set; thus, the training of a single decision tree is completed.
Further, the multi-modal networked teaching data analysis method based on the multi-modal evaluation model verification method comprises the following steps: firstly, grading the learning effect of students: setting the rate lower than 60 as 5 grades; the score of 60-70 is determined as 4 grades; the score of 70-80 is determined as 3 grades; the score of 80-90 is defined as 2 grades; the score of 90-100 is defined as 1 grade; secondly, predicting the final scoring result of the student by using a final model obtained by the multi-modal data, and grading according to the grading method; comparing the result with the final grading results of the four classes of students, and calculating the accuracy to verify the accuracy of the final model; the method comprises the steps of setting scores predicted by a model to be 5, 4, 3, 2 and 1 respectively according to a preset grading interval of <60, 60-70, 70-80, 80-90 and 90-100, setting final scores actually obtained by students to be 5, 4, 3, 2 and 1 according to grading, marking the scores of the students as 1 when the grades are consistent, marking the scores of the students as 0 when the grades are inconsistent, and calculating the probability marked as 1, namely the accuracy rate of model prediction.
Furthermore, the LSTM network structure of the multi-modal evaluation model based on the multi-modal networked teaching data analysis method is an LSTM layer behind an input layer, the number of hidden layer units can be optimized through experiments, then two full-connection layers are connected, dropout is added between the two full-connection layers to improve the trainability, and finally the student performance is predicted through a regression layer.
Another object of the present invention is to provide a multimodal-based networked teaching data analysis system implementing the multimodal-based networked teaching data analysis method, the multimodal-based networked teaching data analysis system including:
the characteristic screening module is used for adopting the maximum information coefficient MIC to carry out characteristic screening and removing irrelevant factors;
the evaluation model acquisition module is used for reconstructing the screened features into a feature space after the features are screened by utilizing MIC analysis, and performing regression by utilizing a random forest to obtain a final evaluation model;
and the evaluation result output module is used for integrating and analyzing learning ability data, physiological data and learning behavior data generated by the students in the online learning platform of the theoretical course by adopting a method of combining a learning analysis technology and a data mining algorithm, establishing a theoretical online course learning effect evaluation model, evaluating the learning effect of the students, and outputting the evaluation result in a chart and digital form by applying a visualization technology.
Another object of the present invention is to provide an information data processing terminal applying the multimodal-based networked teaching data analysis method.
In summary, the advantages and positive effects of the invention are: according to the invention, through various learning behavior data provided by a theoretical course learning platform, physiological signals acquired by an intelligent bracelet and learning ability information of students are fused, and a multi-mode information database of the learning process of the students is established; a theory course evaluation system of multi-mode information fusion is established by utilizing a machine learning technology, and theory and technical method support is provided for the precision, individualized real-time evaluation and dynamic adjustment of a teaching scheme in the online course learning process.
Drawings
Fig. 1 is a flowchart of a multimodal-based networked teaching data analysis method according to an embodiment of the present invention.
FIG. 2 is a schematic structural diagram of a multi-modal-based networked instructional data analysis system according to an embodiment of the present invention;
in the figure: 1. a feature screening module; 2. an evaluation model acquisition module; 3. and an evaluation result output module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a multi-mode-based networked teaching data analysis method and system, and the invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for analyzing networked teaching data based on multiple modalities according to the embodiment of the present invention includes the following steps:
s101: performing characteristic screening by adopting a maximum information coefficient MIC, and removing irrelevant factors; calculating correlation coefficients of the feature space X and the achievement space S column by column, and selecting a feature corresponding to the maximum value of the correlation coefficients as a first feature; calculating the feature f1MIC value with other characteristics, LmaxThe corresponding feature is selected as the second feature f2(ii) a Removing the first characteristic, and repeating the steps until the most characteristic quantity is obtained;
s102: after feature screening is carried out by using MIC analysis, the screened features are recombined into a feature space, and regression is carried out by using a random forest to obtain a final evaluation model;
s103: the method combines a learning analysis technology and a data mining algorithm, integrates and analyzes learning capacity data, physiological data and learning behavior data generated by students learning on a theoretical course online learning platform, establishes a theoretical online course learning effect evaluation model, evaluates the learning effect of the students, and outputs evaluation results in the forms of charts, numbers and the like by applying a visualization technology.
As shown in fig. 2, the multi-modal based networked instructional data analysis system provided by the embodiment of the present invention includes:
the characteristic screening module 1 is used for adopting a maximum information coefficient MIC to carry out characteristic screening and removing irrelevant factors;
the evaluation model acquisition module 2 is used for reconstructing the screened features into a feature space after the features are screened by using MIC analysis, and performing regression by using a random forest to obtain a final evaluation model;
and the evaluation result output module 3 is used for integrating and analyzing learning capacity data, physiological data and learning behavior data generated by the students in the online learning platform of the theoretical course by adopting a method of combining a learning analysis technology and a data mining algorithm, establishing a learning effect evaluation model of the theoretical online course, evaluating the learning effect of the students, and outputting the evaluation result in the forms of charts, numbers and the like by applying a visualization technology.
The technical solution of the present invention is further described with reference to the following specific examples.
1. Theoretical course teaching design and multi-mode data acquisition
1.1 teaching activity design:
teaching activities are carried out by relying on provincial virtual simulation demonstration course items 'microbiology virtual simulation experiments' self-built by applicant teams. The whole online learning period is 10 weeks. Weeks 1-3: professional basic experiments, online theoretical tests, online actual operation tests and self-evaluation; week 4-6: professional experiments, online theoretical tests, online actual operation tests and self evaluation; in 7-9 weeks, comprehensive innovation experiments (grouping), online theoretical tests, online practical tests, self-evaluation and companion evaluation; week 10: the method comprises the following steps of end-of-term online theoretical evaluation, end-of-term online actual operation evaluation, self evaluation, companion evaluation and teacher evaluation. The teaching activity design is used for collecting four-dimensional theoretical course score data and learning behavior data.
Learning capacity data collection is completed based on the questionnaire table:
the first-time repair related course score data is directly connected with a school teaching department score system through a project database. Learning ability data acquisition is mainly through independently designing the questionnaire system, and data collection before the student first course begins: the intelligence evaluation depends on a global authoritative intelligence quotient test, namely a Wechsler intelligence test (Wechsler Adult Intelligent Scale) and a relevant Scale thereof, big data analysis is carried out on intelligence evaluation data based on an online test platform, the scores of partial test questions in the intelligent evaluation data are weighted and calculated, and a deviation intelligence quotient algorithm (relative intelligence quotient obtained by taking average intelligence quotient as reference and standard deviation as unit) is introduced, so that the intelligence evaluation result is more accurate. The PC/mobile terminal electronic questionnaire used by the survey data of the intrinsic factors and the meta learning ability factors is compiled by combining the condition modification of actual colleges and universities on the basis of the reference of mature measuring tools and early-stage series surveys at home and abroad. Questionnaire survey contents are mainly divided into: gender (male and female), grade (1-4), specialty (philosophy, economics, law, education, literature, histology, history, science, engineering, agriculture, medicine, military science, management, art), household (one, two, three, four-line city, county/town, county/village), parental study (literary blind, primary school, junior school, high school/middle school, college, basic subject, student), teaching environment (very good, general, poor, extraordinary poor), achievement motivation (scale assignment), self-efficiency (scale assignment), meta-cognition (scale assignment), achievement attribution (scale assignment), personal inheritance (scale assignment) and the like, and has strong comprehensiveness. And meanwhile, the meta-learning ability factors (achievement motivation, self efficiency, meta-cognition, achievement attribution and personal inheritability) are assigned (0-100) according to the questionnaire quantity table, so that the subsequent analysis modeling of the quantifiable data is facilitated.
1.2 learning behavior data collection is completed based on the theoretical course online platform:
learning behavior factors depend on the early-stage research result, 18 relevant variables of the final learning achievement, such as the use time of the virtual simulation module, the use times of the virtual simulation module, the pre-experiment pre-study time, the discussion times of the experiment process, the review times after the experiment, the completion times of the tasks under class, self-evaluation, the experimental omics biological evaluation, the experimental comprehensive evaluation (teacher), the access to the learning website, the reading and discussion times, the platform posting times, the online testing times, the course dynamic checking, the knowledge learning expansion times, the use times of the search tool and the like, are preliminarily selected. Because the learning behavior big data platform is a system platform which is established and completed by a project principal in the early period, an open data transmission interface exists in the learning behavior big data platform, variables required by the project can be automatically introduced into the multi-mode database, and simultaneously can be output in various file forms such as excel, word and the like.
2. Multi-modal evaluation model construction based on machine learning method
2.1 multimodal data feature screening based on maximum information coefficients:
the online learning achievement of the student theoretical course gives specific quantitative data through online real practice and online test before each (10 times in total) course is finished. Physiological signal data are collected and transmitted through the intelligent bracelet, and the average value and variance of signal sequence collection are used as the characteristic xbio(ii) a Learning behavior data (x)bah) The collection is completed through a theoretical course on-line learning platform; learning ability data (x)iq) Before the first theoretical course begins, all the data can be acquired in the form of electronic questionnaires. The feature vector of each student is denoted Xi＝(xbio，xbah，xiq) The feature space of all students is expressed as X ═ (X)1，X2，...，Xn)TWhere n is the number of students and the corresponding score space is expressed as S ═ S (S)1，S2，...，Sn)T. All the characteristics are subjected to variance normalization, and then the relation between each factor and the learning performance of the theoretical course is analyzed.
The invention adopts the maximum information coefficient MIC to carry out feature screening and removes irrelevant factors. The method comprises the following specific steps: first, bits are calculated column by columnThe correlation coefficient P between the feature space X and the achievement space S is (P)1，p2，...，pn) The maximum value P of the correlation coefficientmaxThe corresponding feature is selected as the first feature, assumed to be f1＝Xk(ii) a Then calculate the feature f1MIC value M ═ between other features (M)1，...，mk-1，mk+1，...，mn) Let L equal to 0.5 × P (i ≠ k) +0.5 × 1-M, and let L equal to 0.5 × P (i ≠ k) +0.5 × MmaxThe corresponding feature is selected as the second feature f2(ii) a The first feature is removed and the above steps are repeated until the maximum number of features is obtained (empirical value, which can be determined experimentally), or the current maximum MIC value is less than a certain threshold, such as the mean value of the MIC values corresponding to the first feature.
3. Establishing a multi-modal data initial evaluation model based on random forests:
the method combines a learning analysis technology and a data mining algorithm, integrates and analyzes learning capacity data, physiological data and learning behavior data generated when students learn microbiological virtual simulation experiments on a theoretical course online learning platform, establishes a theoretical online course learning effect evaluation model, evaluates the learning effect of the students, and outputs evaluation results in the forms of charts, numbers and the like by applying a visualization technology. And after the characteristics are screened by utilizing MIC analysis, the screened characteristics are recombined into a characteristic space, and then a random forest is utilized for regression to obtain a final evaluation model. The specific method comprises the following steps:
the random forest is composed of N (artificially set) decision trees, the N decision trees are trained circularly during training, training samples of each decision tree are obtained by Bootstrap sampling from an original training set (all students), features used when each node of the decision trees is trained are also obtained by random sampling from a new feature space X, each decision tree is subjected to recursive splitting according to a judgment criterion, and after the training of the N decision trees is completed, the mean value of leaf nodes where each student is located is the final regression achievement.
Bootstrap sampling is to extract n samples in a set of n samples to form a data set, and one sample in the original sample set may or may not appear many times in the new data set.
The single decision tree adopts a recursion splitting process, and the specific implementation method is as follows: the extracted sample set D forms a root node, and the sample set is split into two parts, namely D1 and D2, according to a judgment criterion; recursively building a left sub-tree with a sample set D1, and building a right sub-tree with a sample set D2; and setting a condition for stopping splitting, and marking the node as a leaf node when the splitting cannot be continued, and assigning a value to the node.
The specific implementation of the decision criterion (assumed to start from the root node) is as follows: calculating the regression error of the root node, i.e. the mean square sum error of the label values of all samples and the regression value (the mean value of the label values of all samples at this node), and defining as:
randomly extracting features X from a new feature space XuSorting the extracted training samples D (student achievements) from small to large according to the values of the features; sequentially using the score of each student as a threshold value, dividing the sample into a left part and a right part, and then calculating the mean square sum error of a left sub-tree and a right sub-tree; the error index for splitting is defined as the regression error before splitting minus the regression error of the left and right subtrees after splitting:
E＝E(D)-E(D1)-E(D2)；
if the index is maximized, continuing splitting; and when the depth of the artificially set decision tree is reached or the calculated regression error is larger than the artificially set threshold value, stopping splitting, setting the node as a leaf node, wherein the value of the leaf node is the mean value of the label values of the node sample set. Thus, the training of a single decision tree is completed.
4. Practice verification of a multi-mode evaluation model, grading of model prediction results and verification of prediction accuracy of an online course learning evaluation model:
and (3) applying and verifying the accuracy of the online course learning evaluation fusion model based on the physiological indexes, learning behaviors and learning capacity data of the students in the virtual simulation course of the second batch (the first batch of data is used for constructing the evaluation model) of the microbiological virtual simulation true test. And collecting various data of students in the virtual simulation learning platform according to a plurality of key data in the model.
The steps for verifying the feasibility and the effectiveness of the online course learning evaluation model are as follows. Firstly, grading the learning effect of students: setting the rate lower than 60 as 5 grades; the score of 60-70 is determined as 4 grades; the score of 70-80 is defined as 3 grades; the score of 80-90 is defined as 2 grades; the score of 90-100 is defined as 1 st gear. And secondly, predicting the final scoring result of the student by using a final model obtained by the multi-modal data, and grading according to the grading method. And comparing the result with the final grading results of four classes of students, and calculating the accuracy to verify the accuracy of the final model. The method comprises the steps of setting scores predicted by a model to be 5, 4, 3, 2 and 1 respectively according to a preset grading interval (<60, 60-70, 70-80, 80-90 and 90-100), setting final scores actually obtained by students to be 5, 4, 3, 2 and 1 according to grading, marking the scores with the same grade as 1 and marking the scores with different grades as 0, and calculating the probability marked as 1, namely the accuracy of model prediction so as to verify the accuracy of the final model. The consistency of the activity variable finally determined by regression with the determined online lesson learning effect evaluation index is demonstrated by the above expression.
4.1 designing a data feedback system based on the WeChat program:
the student data acquired based on the mobile equipment and the questionnaire are matched with student personal information (school number) and are arranged into a data list; designing a login interface in the WeChat small program, and acquiring personal information (student number) of a student to be matched with a data list; and displaying the corresponding performance prediction in the WeChat applet interface. Designing a data feedback system by using a WeChat small program development tool, realizing interface design by using a WXML program file, and finishing the design of components such as pictures, buttons and the like; realizing content design such as characters, sizes and the like by utilizing the WXSS program file; and the JS program file is utilized to realize the user interaction design and realize the button function. After the program is designed, debugged and on-line, the contents of content push, four-class score push, data bar chart generation statistics, learning scheme push, teaching strategy suggestion and the like are finally embodied on WeChat interfaces of student terminals and teacher ports by matching with background multi-mode database information and multi-mode evaluation model calculation, and the method is convenient to interact and clear at a glance.
5. Optimizing an evaluation model based on deep learning:
in the initial stage of the experiment, the number of the accumulated students is small, the data volume is small, the training of the model is completed by adopting the random forest, the prediction and evaluation of the student score are carried out, and under the condition that the data volume gradually changes, the training of the evaluation model can be carried out by adopting a deep learning method, so that the more accurate prediction and evaluation of the student score are realized. The invention adopts a Long Short-Term Memory network model (LSTM), wherein a forgetting mechanism and a storing mechanism can more effectively model the student learning state information recorded in each course, and compared with a random forest method, the invention can obtain a more accurate evaluation model. The LSTM network structure designed by the invention is characterized in that an LSTM layer is arranged behind an input layer, the number selection of hidden layer units can be optimized through experiments, then two full-connection layers are connected, dropout is added between the two full-connection layers to improve the trainability, and finally the student performance is predicted through a regression layer.
6. Evaluation results
6.1 Multi-modal modeling
Effective characteristics of online virtual simulation learning are integrated and summarized based on multi-modal data, and are specifically shown in the following table 1 (name is hidden for privacy protection):
table 1: data collection of 20 model online virtual simulation experiment (sample number 86)
The learning traces of the students are stored in a database log by a technical means, and huge log data are screened, so that an initial data set of online learning activity variables of the students is preliminarily determined. The number of data features is 20. In order to prove that the 20 indexes are positively correlated with the online learning effect of the students, based on data generated by 237 family students by using virtual simulation experiment learning, a scatter diagram is drawn for verification, and whether correlation exists between each learning ability factor and the learning effect is verified. In order to determine whether the 20 indexes are core indexes for finally evaluating the learning effect of the student on-line course, the 20 indexes and the learning effect of the student on-line course are subjected to binary correlation analysis. The analysis result shows that the significance values of the initially selected 20 indexes are all less than 0.05, and the significance values are in significant positive correlation with the evaluation of the learning effect of students. In order to make the evaluation indexes of the learning effect of the online virtual simulation experiment course more reliable, 20 index data sets are further analyzed by using a machine learning method, and the 20 learning behavior indexes all affect the learning effect of the virtual simulation experiment to a certain extent, which is shown in table 2.
Table 2: coefficient relation of influence of online virtual simulation learning core characteristics on learning efficiency
6.2 multimodal model application
Based on the model constructed above, learning effect prediction based on multi-modal big data is carried out in parallel teaching classes, and specific results are shown in table 3 below. According to results, the final result predicted by the intelligent evaluation model based on deep learning and the final result of the examination of the student are high in matching degree and reach%. According to the method, various learning behavior data of students in the online learning process are relied on, and based on early-stage biology education informatization research theory research and big data mining and analyzing related achievements, learning ability information of the students is fused, and a multi-mode information database of the learning process of the students is established; establishing a virtual simulation experiment course evaluation system model of three modes (meta cognition, learning ability and learning behavior) by using a machine learning method; the evaluation model is utilized to dynamically monitor and evaluate the learning effect of students in real time in the subsequent virtual simulation experiment learning process of a large number of students, and meanwhile, the machine learning technology is utilized to continuously optimize the evaluation model, so that the accuracy, the personalized real-time evaluation, the monitoring, the early warning and the dynamic adjustment of the learning scheme in the whole online learning process are realized.
Table 3: parallel virtual simulation experiment result examination result and intelligent prediction comparison result (sample number 109)
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A multi-mode-based networked teaching data analysis method is characterized by comprising the following steps:
firstly, performing feature screening by adopting a maximum information coefficient MIC to remove irrelevant factors; calculating correlation coefficients of the feature space X and the achievement space S column by column, and selecting a feature corresponding to the maximum value of the correlation coefficients as a first feature; calculating the feature f1MIC value with other characteristics, LmaxThe corresponding feature is selected as the second feature f2(ii) a Removing the first characteristic, and repeating the steps until the most characteristic quantity is obtained;
secondly, after feature screening is carried out by using MIC analysis, the screened features are recombined into a feature space, and regression is carried out by using a random forest to obtain a final evaluation model;
and thirdly, integrating and analyzing learning ability data, physiological data and learning behavior data generated by the students on the theoretical course online learning platform by adopting a method of combining a learning analysis technology and a data mining algorithm, establishing a theoretical online course learning effect evaluation model, evaluating the learning effect of the students, and outputting the evaluation result in a chart and digital form by applying a visualization technology.
2. The multimodal-based networked instructional data analysis method of claim 1 wherein the multimodal data feature screening of the multimodal-based networked instructional data analysis method comprises:
the online learning score of the student theory course gives specific quantitative data and physiological signals through online practice and online test before the end of each courseData acquisition and data transmission are completed through the intelligent bracelet, and the average value and variance of signal sequence acquisition are used as the characteristic xbio(ii) a Learning behavior data (x)bah) Completing acquisition through a theoretical course online learning platform; learning ability data (x)iq) Before the first theoretical course begins, all the courses can be acquired in an electronic questionnaire form; the feature vector of each student is denoted Xi＝(xbio，xbah，xiq) The feature space of all students is expressed as X ═ (X)1，X2，...，Xn)YWhere n is the number of students and the corresponding score space is expressed as S ═ S (S)1，S2，…，Sn)TFirstly, all the characteristics are subjected to variance normalization, and then the relation between each factor and the learning performance of the theoretical course is analyzed.
3. The multi-modality-based networked teaching data analysis method according to claim 1, wherein the multi-modality-based networked teaching data analysis method adopts a maximum information coefficient MIC for feature screening to remove irrelevant factors, and comprises the following specific steps: first, a correlation coefficient P ═ P { P } between the feature space X and the achievement space S is calculated column by column1，p2，...，pnH, dividing the maximum value P of the correlation coefficientmaxThe corresponding feature is selected as the first feature, assumed to be f1＝Xk(ii) a Then calculate the feature f1MIC value M ═ between other features (M)1，...，mk-1，mk+1，...，mn) Let L equal to 0.5 × P (i ≠ k) +0.5 × 1-M, and let L equal to 0.5 × P (i ≠ k) +0.5 × MmaxThe corresponding feature is selected as the second feature f2(ii) a And removing the first feature, and repeating the steps until the most number of features is obtained or the maximum value of the current MIC is less than a certain threshold value.
4. The multimodal-based networked instructional data analysis method of claim 1, wherein the multimodal-based networked instructional data analysis method initial evaluation model building comprises: the random forest is composed of N decision trees, the N decision trees are trained circularly during training, a training sample of each decision tree is obtained by Bootstrap sampling from an original training set, the used characteristic is obtained by random sampling from a new characteristic space X during training of each node of the decision trees, each decision tree is subjected to recursive splitting according to a judgment criterion, and after the training of the N decision trees is finished, the mean value of leaf nodes where each student is located is the final regression score;
bootstrap sampling is the extraction of n samples with a put back in a set of n samples to form a data set.
5. The method for analyzing networked teaching data based on multiple modalities of claim 4, wherein a single decision tree is implemented by a recursive splitting process as follows: the extracted sample set D forms a root node, and the sample set is split into two parts, namely D1 and D2, according to a judgment criterion; recursively building a left sub-tree with a sample set D1, and building a right sub-tree with a sample set D2; and setting a condition for stopping splitting, and marking the node as a leaf node when the splitting can not be continued, and assigning values.
6. The method for analyzing networked teaching data based on multiple modalities of claim 4, wherein the decision criteria is implemented as follows: calculating the regression error of the root node, namely the mean square sum error of the label value and the regression value of all samples, and defining as follows:
randomly extracting features X from a new feature space XuSorting the extracted training samples D from small to large according to the values of the features; sequentially using the score of each student as a threshold value, dividing the sample into a left part and a right part, and then calculating the mean square sum error of a left sub-tree and a right sub-tree; the error index for splitting is defined as the regression error before splitting minus the regression error of the left and right subtrees after splitting:
E＝E(D)-E(D1)-E(D2)；
if the index is maximized, continuing splitting; when the depth of an artificially set decision tree is reached or the calculated regression error is larger than an artificially set threshold value, stopping splitting, setting the node as a leaf node, wherein the value of the leaf node is the mean value of the label values of the node sample set; thus, the training of a single decision tree is completed.
7. The multi-modal-based networked teaching data analysis method according to claim 1, wherein the multi-modal-based networked teaching data analysis method multi-modal evaluation model verification method comprises: firstly, grading the learning effect of students: setting the rate lower than 60 as 5 grades; the score of 60-70 is determined as 4 grades; the score of 70-80 is determined as 3 grades; the score of 80-90 is defined as 2 grades; the score of 90-100 is defined as 1 grade; secondly, predicting the final scoring result of the student by using a final model obtained by the multi-modal data, and grading according to the grading method; comparing the result with the final grading results of the four classes of students, and calculating the accuracy to verify the accuracy of the final model; the method comprises the steps of setting scores predicted by a model to be 5, 4, 3, 2 and 1 respectively according to a preset grading interval of <60, 60-70, 70-80, 80-90 and 90-100, setting final scores actually obtained by students to be 5, 4, 3, 2 and 1 according to grading, marking the scores with the same grade as 1 and marking the scores with different grades as 0, and calculating the probability marked as 1, namely the accuracy rate of model prediction.
8. The multi-modal-based networked teaching data analysis method according to claim 1, wherein an LSTM network structure of a multi-modal evaluation model of the multi-modal-based networked teaching data analysis method is an LSTM layer behind an input layer, the number of hidden layer units can be optimized through experiments, two full connection layers are connected, dropout is added between the two full connection layers to improve the trainability, and finally, the student performance is predicted through a regression layer.
9. A multimodal-based networked teaching data analysis system for implementing the multimodal-based networked teaching data analysis method according to any one of claims 1 to 8, wherein the multimodal-based networked teaching data analysis system comprises:
the characteristic screening module is used for adopting the maximum information coefficient MIC to carry out characteristic screening and removing irrelevant factors;
the evaluation model acquisition module is used for reconstructing the screened features into a feature space after the features are screened by utilizing MIC analysis, and performing regression by utilizing a random forest to obtain a final evaluation model;
and the evaluation result output module is used for integrating and analyzing learning ability data, physiological data and learning behavior data generated by the students in the online learning platform of the theoretical course by adopting a method of combining a learning analysis technology and a data mining algorithm, establishing a theoretical online course learning effect evaluation model, evaluating the learning effect of the students, and outputting the evaluation result in a chart and digital form by applying a visualization technology.
10. An information data processing terminal applying the multi-modal based networked teaching data analysis method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911329595.4A CN111275239B (en) | 2019-12-20 | 2019-12-20 | Multi-mode-based networked teaching data analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911329595.4A CN111275239B (en) | 2019-12-20 | 2019-12-20 | Multi-mode-based networked teaching data analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111275239A true CN111275239A (en) | 2020-06-12 |
| CN111275239B CN111275239B (en) | 2023-09-29 |
Family
ID=71111831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911329595.4A Active CN111275239B (en) | 2019-12-20 | 2019-12-20 | Multi-mode-based networked teaching data analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111275239B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882247A (en) * | 2020-08-07 | 2020-11-03 | 成都理工大学 | Online learning system evaluation method based on comprehensive fuzzy evaluation model |
| CN112699933A (en) * | 2020-12-28 | 2021-04-23 | 华中师范大学 | Automatic identification method and system for processing capacity of user teaching material |
| CN113743271A (en) * | 2021-08-27 | 2021-12-03 | 中国科学院软件研究所 | Video content effectiveness visual analysis method and system based on multi-modal emotion |
| CN117455126A (en) * | 2023-12-26 | 2024-01-26 | 广州市锐星信息科技有限公司 | Ubiquitous practical training teaching and evaluation management system and method |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201040898A (en) * | 2009-05-01 | 2010-11-16 | Yourfamily Education Group | Visual perception evaluation learning system |
| US20130073387A1 (en) * | 2011-09-15 | 2013-03-21 | Stephan HEATH | System and method for providing educational related social/geo/promo link promotional data sets for end user display of interactive ad links, promotions and sale of products, goods, and/or services integrated with 3d spatial geomapping, company and local information for selected worldwide locations and social networking |
| US20140227675A1 (en) * | 2013-02-13 | 2014-08-14 | YourLabs, LLC | Knowledge evaluation system |
| CN105447525A (en) * | 2015-12-15 | 2016-03-30 | 中国科学院软件研究所 | Data prediction classification method and device |
| CN105844562A (en) * | 2016-05-23 | 2016-08-10 | 华中师范大学 | Learner learning performance analysis method based on curriculum teaching model |
| CN107123068A (en) * | 2017-04-26 | 2017-09-01 | 北京航空航天大学 | A kind of programming-oriented language course individualized learning effect analysis system and method |
| US20170256172A1 (en) * | 2016-03-04 | 2017-09-07 | Civitas Learning, Inc. | Student data-to-insight-to-action-to-learning analytics system and method |
| CN108460139A (en) * | 2018-03-09 | 2018-08-28 | 上海开放大学 | Based on web crawlers data mining online course Management System for Evaluation Teaching Quality |
| CN109377078A (en) * | 2018-11-12 | 2019-02-22 | 重庆靶向科技发展有限公司 | A kind of student's study quality evaluation method based on big data |
| CN109657721A (en) * | 2018-12-20 | 2019-04-19 | 长沙理工大学 | A kind of multi-class decision-making technique of combination fuzzy set and random forest tree |
| CN109726366A (en) * | 2018-12-07 | 2019-05-07 | 上海机电工程研究所 | Infrared Imaging Seeker anti-jamming performance evaluation method, system and medium based on random forest |
| KR102009713B1 (en) * | 2019-03-07 | 2019-08-12 | 주식회사 엠에이유니타스 | Online marketing education system |
| CN110135494A (en) * | 2019-05-10 | 2019-08-16 | 南京工业大学 | Feature selection approach based on maximum information coefficient and Geordie index |
| CN110322134A (en) * | 2019-06-26 | 2019-10-11 | 刘玉静 | Learn the teachers ' teaching quality assessment system of harvest based on student |
-
2019
- 2019-12-20 CN CN201911329595.4A patent/CN111275239B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201040898A (en) * | 2009-05-01 | 2010-11-16 | Yourfamily Education Group | Visual perception evaluation learning system |
| US20130073387A1 (en) * | 2011-09-15 | 2013-03-21 | Stephan HEATH | System and method for providing educational related social/geo/promo link promotional data sets for end user display of interactive ad links, promotions and sale of products, goods, and/or services integrated with 3d spatial geomapping, company and local information for selected worldwide locations and social networking |
| US20140227675A1 (en) * | 2013-02-13 | 2014-08-14 | YourLabs, LLC | Knowledge evaluation system |
| CN105447525A (en) * | 2015-12-15 | 2016-03-30 | 中国科学院软件研究所 | Data prediction classification method and device |
| US20170256172A1 (en) * | 2016-03-04 | 2017-09-07 | Civitas Learning, Inc. | Student data-to-insight-to-action-to-learning analytics system and method |
| CN105844562A (en) * | 2016-05-23 | 2016-08-10 | 华中师范大学 | Learner learning performance analysis method based on curriculum teaching model |
| CN107123068A (en) * | 2017-04-26 | 2017-09-01 | 北京航空航天大学 | A kind of programming-oriented language course individualized learning effect analysis system and method |
| CN108460139A (en) * | 2018-03-09 | 2018-08-28 | 上海开放大学 | Based on web crawlers data mining online course Management System for Evaluation Teaching Quality |
| CN109377078A (en) * | 2018-11-12 | 2019-02-22 | 重庆靶向科技发展有限公司 | A kind of student's study quality evaluation method based on big data |
| CN109726366A (en) * | 2018-12-07 | 2019-05-07 | 上海机电工程研究所 | Infrared Imaging Seeker anti-jamming performance evaluation method, system and medium based on random forest |
| CN109657721A (en) * | 2018-12-20 | 2019-04-19 | 长沙理工大学 | A kind of multi-class decision-making technique of combination fuzzy set and random forest tree |
| KR102009713B1 (en) * | 2019-03-07 | 2019-08-12 | 주식회사 엠에이유니타스 | Online marketing education system |
| CN110135494A (en) * | 2019-05-10 | 2019-08-16 | 南京工业大学 | Feature selection approach based on maximum information coefficient and Geordie index |
| CN110322134A (en) * | 2019-06-26 | 2019-10-11 | 刘玉静 | Learn the teachers ' teaching quality assessment system of harvest based on student |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882247A (en) * | 2020-08-07 | 2020-11-03 | 成都理工大学 | Online learning system evaluation method based on comprehensive fuzzy evaluation model |
| CN112699933A (en) * | 2020-12-28 | 2021-04-23 | 华中师范大学 | Automatic identification method and system for processing capacity of user teaching material |
| CN112699933B (en) * | 2020-12-28 | 2023-07-07 | 华中师范大学 | Automatic identification method and system for processing capability of user teaching materials |
| CN113743271A (en) * | 2021-08-27 | 2021-12-03 | 中国科学院软件研究所 | Video content effectiveness visual analysis method and system based on multi-modal emotion |
| CN113743271B (en) * | 2021-08-27 | 2023-08-01 | 中国科学院软件研究所 | Video content effectiveness visual analysis method and system based on multi-modal emotion |
| CN117455126A (en) * | 2023-12-26 | 2024-01-26 | 广州市锐星信息科技有限公司 | Ubiquitous practical training teaching and evaluation management system and method |
| CN117455126B (en) * | 2023-12-26 | 2024-04-02 | 广州市锐星信息科技有限公司 | Ubiquitous practical training teaching and evaluation management system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111275239B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378818B (en) | Personalized exercise recommendation method, system and medium based on difficulty | |
| CN111275239B (en) | Multi-mode-based networked teaching data analysis method and system | |
| Kotsiantis et al. | Using learning analytics to identify successful learners in a blended learning course | |
| CN112287037B (en) | Multi-entity mixed knowledge graph construction method, device and storage medium | |
| CN111950708B (en) | Neural network structure and method for finding daily life habits of college students | |
| CN111143750B (en) | University computer class course management platform based on fragmented learning | |
| Misiejuk et al. | State of the field report on learning analytics | |
| CN110232343B (en) | Child personalized behavior statistical analysis system and method based on latent variable model | |
| Wu | Effect of online and offline blended teaching of college English based on data mining algorithm | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| Krikun | Applying learning analytics methods to enhance learning quality and effectiveness in virtual learning environments | |
| CN114372155A (en) | Personalized learning platform based on self-expansion knowledge base and multi-mode portrait | |
| CN116756340A (en) | Test question automatic generation method, system and equipment | |
| Mamcenko et al. | On using learning analytics to personalise learning in virtual learning environments | |
| Kang et al. | Investigating navigational behavior patterns of students across at-risk categories within an open-ended serious game | |
| Dogan et al. | Association rule mining from an intelligent tutor | |
| Hu et al. | A multivariate learning evaluation model for programming course in online learning environment | |
| Dipace et al. | From Big Data to Learning Analytics for a personalized learning experience | |
| Ogunkunle et al. | A data mining based optimization of selecting learning material in an intelligent tutoring system for advancing STEM education | |
| Wu | Study on the differences in behaviour characteristics of distance online autonomous learning in different network virtual environments | |
| Troussas et al. | Automatic predictions using LDA for learning through social networking services | |
| Gu | [Retracted] Evaluation of Teaching Quality on IP Environment Driven by Multiple Values Theory Based on Big Data | |
| Marigowda et al. | A comprehensive examination assessment model using machine learning | |
| Yang | English scores by distributed ID3 algorithm of computer network | |
| Poitras et al. | Preservice teacher disengagement with computer-based learning environments |
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 |