CN101105854A - Students state on-line detection method based on decision-making tree remote-education environment - Google Patents
Students state on-line detection method based on decision-making tree remote-education environment Download PDFInfo
- Publication number
- CN101105854A CN101105854A CNA2007100451788A CN200710045178A CN101105854A CN 101105854 A CN101105854 A CN 101105854A CN A2007100451788 A CNA2007100451788 A CN A2007100451788A CN 200710045178 A CN200710045178 A CN 200710045178A CN 101105854 A CN101105854 A CN 101105854A
- Authority
- CN
- China
- Prior art keywords
- data
- decision tree
- student
- attribute
- tables
- 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.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An decision-making tree-based method for online checking of student status in distance education includes four steps: step 1: take out the data related to student learning from the original data collection of distance education database, and form the training collection after noise elimination; step 2: adopt ID3 algorithm to construct the corresponding decision-making tree, which is equal to a series of rules; step 3: introduce new data collection to the decision-making tree and calculate out the corresponding checking result; step 4: manifest the checking result to teaches in a graphic way, and the contents include each knowledge point's overall checking status and category fluctuation. The invention can support real-time checks on students with knowledge point as the center in large-scale learning environment, so as to provide teachers with real-time data of students.
Description
Technical field
What the present invention relates to is the method in a Computer Applied Technology field, specifically is a kind of remote-education environment middle school student situation online test method based on decision tree, is used at remote-education environment the aid when being provided at teaching for the teacher.
Background technology
In remote-education environment because student's quantity is huge, and teacher can not with the direct face-to-face exchange of student, thereby make the teacher be difficult to hold to student's study situation, therefore also just can't adjust teaching plan in real time.In this case, utilize data mining technology, student's study situation is judged, just become a kind of most important method.
Find through literature search prior art, chenn-Jung Huang etc. are in " computers andeducation " (" computing machine and education "), (" Anintelligent learning diagnosis system for web-based thematic learningplatform ") (intelligent diagnosis system that is used for WEB theme teaching platform) delivered on (48 (2007) 658-679), this article proposition utilizes the log file in student's past to carry out the analysis and the detection of study habit, thereby give the student some guidances, help the student to revise study habit, concrete grammar comprises: utilize the LOG file in the learning behavior in user's past to analyze, the sorting technique that adopts mainly comprises rough set and K-vicinity technology, and experimental result shows that this system has certain detectability for student's study situation.There are some shortcomings in this system: the rough set that adopt (1) and the efficiency ratio of K-neighbor method are lower, and real-time is not enough in large-scale remote-education environment; (2) do not create training data, make that the granularity of testing result is too coarse according to the knowledge point.
Summary of the invention
The objective of the invention is to overcome deficiency of the prior art, a kind of remote-education environment middle school student situation online test method based on decision tree is provided, it can be supported under the extensive academic environment, be that the center is carried out student's situation and detected in real time with the knowledge point, thereby provide instant student's situation data to the teacher, better solve the problem of the quality of education in the long-distance education.
The present invention is achieved by the following technical solutions, the present invention includes four steps:
First step is the generation of training dataset: concentrate the tables of data relevant with student's study situation to extract the raw data of long-distance education database, and through operations such as denoising, arrangements, form training set;
Second step is to make up decision tree according to training dataset: adopt the ID3 algorithm to construct corresponding decision trees, this decision tree is equivalent to series of rules;
Third step is to use decision tree to carry out the detection of student's situation: new data set is incorporated in the above-mentioned decision tree goes, and calculate the relevant detection result;
The 4th step is that testing result graphically shows: testing result is showed to the teacher in patterned mode, and displaying contents is included in the overall detection case and the classification fluctuation situation of each knowledge point.
The generation of described training dataset comprises that step is specific as follows:
A. from raw data base, the tables of data of Attendance Sheet, schedule work and examination table is extracted; Abstracting method adopts standard SQL sentence to get final product.
B. the mistake in these tables of data, incompleteness, inconsistent data are rejected;
The data of described mistake are meant the data that exceed actual range, and for example: certain student's achievement has surpassed 100 fens.
The data of described incompleteness are meant the record of significant field data disappearance, for example: the record disappearance of certain student's name field.
Described inconsistent certain record field and the unmatched data of attribute specification that are meant in tables of data, for example, the input of ' name ' field is student number in certain record.
More than these several situations often because the operating mistake of the foundation of database and input data causes, such data can't be used for doing training dataset afterwards, need to reject.
C. according to metadata table pattern in these several tables of data is not matched and the data field of semantic conflict is unified, be incorporated in then in the tables of data;
Described metadata table is meant and write down the form that concerns between the different pieces of information table, and this table has illustrated the semanteme of each data sheet field and mutual relation, is used for doing the unification between the tables of data and the standard of merging in the present invention.
Described pattern does not match and the data field of semantic conflict, is meant in different forms, and the semanteme that certain numeric field is expressed is identical, but the title difference that is to use, thereby caused pattern not match.For example in Attendance Sheet, use " NO " to represent student number, in schedule work, adopt " ID " to represent student number.What these two fields were expressed is same content, the field name difference, thus caused pattern not match and semantic conflict.
Describedly be incorporated in a tables of data and be meant the data from Attendance Sheet, schedule work and LOG file, be stored in the training table, be convenient to training like this, concrete method can realize with SQL statement, also can realize with the method for program.
Then can get final product with SQL statement, for example insert into training_tableselect*from kaoshi_table with the insert order.
D. the field of examination result is appended in the tables of data after the merging;
The centesimal system method for expressing of examination result is converted to " A ", " B ", " C ", " D " four ranks, " 100-90 " is A, and " 89-75 " is B, and " 74-60 " is C, and " below 60 " are D.
In the training table, increase a field " record ", use SQL statement then, examination result is inserted in the corresponding field goes.
Described according to training dataset structure decision tree, comprise that step is specific as follows:
A. testing result is defined as A, B, C, D four classes, the examination result of corresponding front respectively;
B. the algorithm of decision tree structure adopts the ID3 algorithm, and this algorithm is a kind of mountain-climbing algorithm, promptly selects the detection attribute of an optimum attribute as next stage.
This algorithm detailed process is as follows:
B.1 according to the information gain formula, calculate current information gain maximum attribute;
Described information gain formula is:
Gain(F)＝I(s
1，s
2，…s
m)-E(F)
I(s
1，s
2，…s
m)＝-∑p
ilog2(p
i)
E(F)＝∑((s
1j+…..s
mj)/s)*I(s
1j，.....s
mj)
I(s
1j，.....s
mj)＝-∑P
ijlog2(p
ij)
Wherein, S is the set of s data sample, defines m inhomogeneity Ci.s
iBe C
iMiddle sample number, pi is that arbitrary sample belongs to C
iProbability.
F is certain attribute, has v value, and can with attribute F with S be divided into v subclass (S1 ... .S
v), S
IjBe subclass S
jMiddle class C
iSample number, P
IjBe that sample among the Sj belongs to class C
iProbability.
B.2 with the root node of this attribute as tree;
B.3 the number according to this property value is divided into corresponding branch with the data in the training table;
B.4 for each branch, repeat process b.1-b.3, till all data are all used up.
B.5 the attribute that will be b.1-b.4 finds in the process links up, and is exactly a decision tree.On the leaf node " A ", " B ", " C ", " D " these four values.
Described application decision tree carries out student's situation and detects, and comprises that step is specific as follows:
Record in student's situation tables of data that a. will need to detect extracts, and can realize with SQL statement;
B. retrieve out with the corresponding property value of decision-making tree root in will writing down, and compare, determine down the attribute of one deck take-off point according to result relatively with the value of decision-making tree root attribute;
C. value corresponding with one deck take-off point attribute under the decision tree in will writing down extracts, with the value comparison of this take-off point, according to the attribute of the more following one deck take-off point of comparative result decision;
D. repeat the process of c, all relatively finish, perhaps arrived the decision tree leaf node up to all property values;
E. the pairing numerical value of this decision tree leaf node is exactly testing result.As the process of certain student's record by above-mentioned a-d, the value of the leaf node that reaches is " A ", and then representing the testing result for this student is " A ".
Described testing result graphically shows, comprises that step is specific as follows:
A. travel through test data set, all detection finishes according to the flow process in (3) up to all records;
B. testing result is write among the result data table result_table;
C. according to the knowledge point stage, testing result is divided into A, B, C, four groups of D, and with graphically showing; What show in each group is student's student number in this detection;
D. according to the testing result of a last knowledge point, student's study testing result change conditions is graphically shown, have respectively rise 3, rise 2, rise 1, constant, descend 1, descend 27 kinds of situations of 3 grades that descend.
Remote-education environment middle school student based on decision tree technique provided by the invention learn the situation online test method, the student's situation testing result that provides in each knowledge point to the teacher, allow the teacher can understand overall study distribution situation and student change in different knowledge points study situations, thereby help the teacher to carry out corresponding teaching process adjustment and personalized the guidance, can be used to improve the quality of instruction under the Web education environment.
Embodiment
Below embodiments of the invention are elaborated: present embodiment is being to implement under the prerequisite with the technical solution of the present invention, provided detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
Carry out the implementation procedure that the on-line study situation detects with place, ' linear list ' knowledge point below, the concrete application of this method is described at " data structure " course.For the student that can detect place, ' linear list ' knowledge point learns situation, need carry out the work of two key steps, first is to make up detection model, second is to utilize model to detect.The step that wherein makes up detection model is general, and for all knowledge points, model all is unified.
The process that makes up model is divided into the generation training dataset and makes up two parts of decision tree, and these two parts are irrelevant with concrete knowledge point.
The tables of data relevant with this method is Attendance Sheet, schedule work and the examination table relevant with " data structure " course, uses kaoqin_table respectively, zouye_table, and kaoshi_table represents
(1) the training dataset generative process is specific as follows:
A. from raw data base, the content of Attendance Sheet, schedule work and the examination table of " data structure " this subject is extracted from database;
As follows with SQL statement: Select*from kaoqin_table where course name=' data structure '
Other the also similar processing of two tables.
B. the mistake in these tables of data, incompleteness, inconsistent data are rejected;
For example: find to have in kaoqin_table ' time ' field data disappearance of a record, such record is directly deletion just.Discovery has the achievement of a record in zuoye_table be ' 120 ' branch, and this obviously is inconsistent data, also needs to reject.
C. according to metadata table pattern in these several databases is not matched and the data field of semantic conflict is unified, be incorporated in then in the tables of data.
Discovery is represented student number with ' NO ' in kaoqin_table, represent student number with ' ID ' in kaoshi_table, and this is a semantic conflict, and is then that the student number field in two tables is unified with ' ID ' expression.
Set up a training table training_table, then the data of other three tables are inserted in this table, for example: insert into training table select*from kaoshi_table, the also similar processing of other two tables.
D. the field of examination result is appended in the tables of data after the merging;
In training_table, increase ' record ' field, from kaoshi_table, achievement is read out then, insert respectively in the corresponding record and go.
(2) the decision tree building process is specific as follows:
A. the result that will detect is defined as A in advance, B, C, D four classes, the examination result of corresponding front respectively
B. the algorithm of decision tree structure is the ID3 algorithm, and this algorithm is a kind of mountain-climbing algorithm, promptly selects the detection attribute of an optimum attribute as next stage.
This algorithm detailed process is as follows:
B.1 according to ' information gain ' formula, calculate current information gain maximum attribute among the training_table.
B.2 with the root node of this attribute as tree, for example calculate the information gain maximum of ' enquirement number of times ' this attribute, then the root node of this decision tree is ' an enquirement number of times '.
B.3 the number according to this property value is divided into corresponding branch with the data in the training table, is recorded into right subtree branch as what ' put question to the record of number of times＜3 ' to put into left subtree branch, ' putd question to number of times＞3 '
B.4 by the computing information gain, the attribute of next level is ' program request time '.Left subtree put in the record of ' program request time＜30 hour ', and right subtree put in the record of ' program request time＞30 hour '.
B.5 the attribute that will be b.1-b.5 finds in the process links up, and is exactly a decision tree.On the leaf node " A ", " B ", " C ", " D " these four values are wherein with ' the node corresponding class of program request time＞30 ' is ' A '.
When utilizing model to detect, then be relevant with the knowledge point of ' linear list ', test data set needs to integrate according to ' linear list ' this knowledge point, and the input decision-tree model.Specify below
(3) using decision tree detects specific as follows in the study situation process of ' linear list ' this knowledge point:
A. will need the student " Zhang San " that detects situation, comprise that data such as work attendance, operation, examination extract from entire database, form the test data table in ' linear list ' this knowledge point
For example use SQL statement: select*from kaoshi_table where name=' Zhang San '
B. in will writing down Zhang San the record value of ' enquirement number of times ' and root directory relatively, find that Zhang San's enquirement number of times is ' 2 ', then enter right subtree; ' program request time ' second layer with decision tree is compared, the program request time of finding Zhang San then enters right subtree greater than 30 again.The value of the leaf node corresponding with this subtree is ' A ', and Zhang San's testing result is exactly ' A ' so.
C. the testing result with Zhang San writes among the corresponding result_table, and the knowledge point property value assignment with table is ' linear list ' simultaneously;
Update result_table set knowpoint=' linear list ' where name=' Zhang San '.
(4) the graphical procedure for displaying of testing result is as follows:
A. after the flow process in the basis (3) of all students in the tables of data being walked one time, obtain the data recording among the result_table
C. with the student name in the testing result or student number according to A, B, C, the demonstration of D separated graphics, patterned knowledge point is labeled as ' linear list '.Each grouping middle school student's quantity also comes out, and is presented on the figure.
D. according to the testing result of a last knowledge point, student's study testing result change conditions is graphically shown, have respectively rise 3, rise 2, rise 1, constant, descend 1, descend 27 kinds of situations of 3 grades that descend.
Implementation result: the inventive method utilizes decision tree technique to carry out the detection of student in the study situation of ' linear list ' knowledge point of " data mining " course, the instrument of judging current study situation at this knowledge point point is provided for the teacher who imparts knowledge to students in the Web education environment.The teacher can see in ' linear list ' knowledge point student's study situation and detecting, and the student is in different knowledge points results of learning change conditions, and the teacher can adjust teaching programme targetedly like this, perhaps carries out the personalization guidance.
Claims (9)
1. the remote-education environment middle school student situation online test method based on decision tree is characterized in that, comprises four steps:
First step is the generation of training dataset: concentrate the tables of data relevant with student's study situation to extract the raw data of long-distance education database, and through denoising, housekeeping operation, form training set;
Second step is to make up decision tree according to training dataset: adopt the ID3 algorithm to construct corresponding decision trees, this decision tree is equivalent to series of rules;
Third step is to use decision tree to carry out the detection of student's situation: new data set is incorporated in the above-mentioned decision tree goes, and calculate the relevant detection result;
The 4th step is that testing result graphically shows: testing result is showed to the teacher in patterned mode, and displaying contents is included in the overall detection case and the classification fluctuation situation of each knowledge point.
2. the remote-education environment middle school student situation online test method based on decision tree according to claim 1 is characterized in that the generation of described training dataset comprises that step is specific as follows:
A. from raw data base the tables of data of Attendance Sheet, schedule work and examination table is extracted, abstracting method adopts standard SQL sentence;
B. the mistake in the tables of data that extracts, incompleteness, inconsistent data are rejected;
C. according to metadata table pattern in these several tables of data is not matched and the data field of semantic conflict is unified, be incorporated in then in the tables of data;
D. the field of examination result is appended in the tables of data after the merging.
3. the remote-education environment middle school student situation online test method based on decision tree according to claim 2 is characterized in that the data of described mistake are meant the data that exceed actual range; The data of described incompleteness are meant the record of significant field data disappearance; Described inconsistent certain record field and the unmatched data of attribute specification that are meant in tables of data.
4. the remote-education environment middle school student situation online test method based on decision tree according to claim 2, it is characterized in that, described metadata table is meant and has write down the form that concerns between the different pieces of information table, this table has illustrated the semanteme of each data sheet field and mutual relation, is used for doing the unification between the tables of data and the standard of merging; Described pattern does not match and the data field of semantic conflict, is meant in different forms, and the semanteme that certain numeric field is expressed is identical, but the title difference that is to use, thereby caused pattern not match; Describedly be incorporated in a tables of data and be meant, be stored in the training table, be convenient to training like this data from Attendance Sheet, schedule work and LOG file.
5. the remote-education environment middle school student situation online test method based on decision tree according to claim 2, it is characterized in that, described field with examination result is appended in the tables of data after the merging, is meant: the centesimal system method for expressing of examination result is converted to " A ", " B ", " C ", " D " four ranks, " 100-90 " is A, " 89-75 " is B, " 74-60 " is C, and " below 60 " are D; In the training table, increase a field " record ", use SQL statement then, examination result is inserted in the corresponding field goes.
6. the remote-education environment middle school student situation online test method based on decision tree according to claim 1 is characterized in that, and is described according to training dataset structure decision tree, comprises that step is specific as follows:
A. testing result is defined as A, B, C, D four classes, the examination result of corresponding front respectively;
B. the algorithm that makes up of decision tree adopts the ID3 algorithm, and this algorithm is a kind of mountain-climbing algorithm, promptly selects an optimum attribute as the detection attribute of next stage, and is specific as follows:
B.1 according to the information gain formula, calculate current information gain maximum attribute;
B.2 with the root node of this attribute as tree;
B.3 the number according to this property value is divided into corresponding branch with the data in the training table;
B.4 for each branch, repeat process b.1-b.3, till all data are all used up;
B.5 the attribute that will be b.1-b.4 finds in the process links up, and is exactly a decision tree, is " A " on the leaf node, " B ", " C ", " D " these four values.
7. the remote-education environment middle school student situation online test method based on decision tree according to claim 6 is characterized in that described information gain formula is:
Gain(F)＝I(s
1，s
2，…s
m)-E(F)
I(s
1，s
2，…s
m)＝-∑p
ilog2(p
i)
E(F)＝∑((s
1j+…..s
mj)/s)*I(s
1j，.....s
mj)
I(s
1j，.....s
mj)＝-∑p
ijlog2(p
ij)
Wherein, S is the set of s data sample, defines m inhomogeneity Ci, s
iBe C
iMiddle sample number, pi is that arbitrary sample belongs to C
iProbability, F is certain attribute, has v value, and can with attribute F with S be divided into v subclass (S1 ... .S
v), S
IjBe subclass S
jMiddle class C
iSample number, p
IjBe that sample among the Sj belongs to class C
iProbability.
8. the remote-education environment middle school student situation online test method based on decision tree according to claim 1 is characterized in that, described application decision tree carries out student's situation and detects, and comprises that step is specific as follows:
Record in student's situation tables of data that a. will need to detect extracts;
B. retrieve out with the corresponding property value of decision-making tree root in will writing down, and compare, determine down the attribute of one deck take-off point according to result relatively with the value of decision-making tree root attribute;
C. value corresponding with one deck take-off point attribute under the decision tree in will writing down extracts, with the value comparison of this take-off point, according to the attribute of the more following one deck take-off point of comparative result decision;
D. repeat the process of c, all relatively finish, perhaps arrived the decision tree leaf node up to all property values;
E. the pairing numerical value of this decision tree leaf node is exactly testing result.
9. the remote-education environment middle school student situation online test method based on decision tree according to claim 1 is characterized in that described testing result graphically shows, comprises that step is specific as follows:
A. travel through test data set, the flow process detection of all having carried out in the detection of student's situation according to the application decision tree up to all records finishes;
B. testing result is write among the result data table result_table;
C. according to the knowledge point stage, testing result is divided into A, B, C, four groups of D, and show with graphical, what show in each group is student's student number in this detection;
D. according to the testing result of a last knowledge point, student's study testing result change conditions is graphically shown, have respectively rise 3, rise 2, rise 1, constant, descend 1, descend 2,37 kinds of situations descend.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2007100451788A CN101105854A (en) | 2007-08-23 | 2007-08-23 | Students state on-line detection method based on decision-making tree remote-education environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2007100451788A CN101105854A (en) | 2007-08-23 | 2007-08-23 | Students state on-line detection method based on decision-making tree remote-education environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101105854A true CN101105854A (en) | 2008-01-16 |
Family
ID=38999737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2007100451788A Pending CN101105854A (en) | 2007-08-23 | 2007-08-23 | Students state on-line detection method based on decision-making tree remote-education environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101105854A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951472A (en) * | 2014-03-29 | 2015-09-30 | 华为技术有限公司 | Data statistics method based on distribution |
| CN105303492A (en) * | 2015-10-27 | 2016-02-03 | 中国疾病预防控制中心环境与健康相关产品安全所 | Cleaning method of health data for atmospheric pollution health risk assessment |
| CN105677854A (en) * | 2016-01-04 | 2016-06-15 | 安徽大学 | Student single-subject score decision analysis method and analyzer based on rough set |
| CN106843941A (en) * | 2016-12-31 | 2017-06-13 | 广东欧珀移动通信有限公司 | Information processing method, device and computer equipment |
| CN106909682A (en) * | 2017-03-03 | 2017-06-30 | 盐城工学院 | Test library design method and system |
| CN107680018A (en) * | 2017-09-27 | 2018-02-09 | 杭州铭师堂教育科技发展有限公司 | A kind of college entrance will based on big data and artificial intelligence makes a report on system and method |
| CN108121785A (en) * | 2017-12-15 | 2018-06-05 | 华中师范大学 | A kind of analysis method based on education big data |
| CN108241632A (en) * | 2016-12-23 | 2018-07-03 | 航天星图科技（北京）有限公司 | A kind of data verification method of data base-oriented Data Migration |
| CN108597280A (en) * | 2018-04-27 | 2018-09-28 | 中国人民解放军国防科技大学 | Teaching system and teaching method based on learning behavior analysis |
| RU2669508C1 (en) * | 2017-10-12 | 2018-10-11 | Частное образовательное учреждение высшего образования "Московский Университет им. С.Ю. Витте" | Method of automated formation of decisions on electronic education parameters selection |
| CN112860851A (en) * | 2021-01-22 | 2021-05-28 | 平安科技（深圳）有限公司 | Course recommendation method, device, equipment and medium based on root cause analysis |
-
2007
- 2007-08-23 CN CNA2007100451788A patent/CN101105854A/en active Pending
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015149497A1 (en) * | 2014-03-29 | 2015-10-08 | 华为技术有限公司 | Distributed data statistical method |
| CN104951472A (en) * | 2014-03-29 | 2015-09-30 | 华为技术有限公司 | Data statistics method based on distribution |
| CN105303492A (en) * | 2015-10-27 | 2016-02-03 | 中国疾病预防控制中心环境与健康相关产品安全所 | Cleaning method of health data for atmospheric pollution health risk assessment |
| CN105677854A (en) * | 2016-01-04 | 2016-06-15 | 安徽大学 | Student single-subject score decision analysis method and analyzer based on rough set |
| CN108241632B (en) * | 2016-12-23 | 2022-01-14 | 中科星图股份有限公司 | Data verification method oriented to database data migration |
| CN108241632A (en) * | 2016-12-23 | 2018-07-03 | 航天星图科技（北京）有限公司 | A kind of data verification method of data base-oriented Data Migration |
| CN106843941B (en) * | 2016-12-31 | 2019-02-05 | Oppo广东移动通信有限公司 | Information processing method, device and computer equipment |
| CN106843941A (en) * | 2016-12-31 | 2017-06-13 | 广东欧珀移动通信有限公司 | Information processing method, device and computer equipment |
| CN106909682A (en) * | 2017-03-03 | 2017-06-30 | 盐城工学院 | Test library design method and system |
| CN107680018A (en) * | 2017-09-27 | 2018-02-09 | 杭州铭师堂教育科技发展有限公司 | A kind of college entrance will based on big data and artificial intelligence makes a report on system and method |
| RU2669508C1 (en) * | 2017-10-12 | 2018-10-11 | Частное образовательное учреждение высшего образования "Московский Университет им. С.Ю. Витте" | Method of automated formation of decisions on electronic education parameters selection |
| CN108121785A (en) * | 2017-12-15 | 2018-06-05 | 华中师范大学 | A kind of analysis method based on education big data |
| CN108597280A (en) * | 2018-04-27 | 2018-09-28 | 中国人民解放军国防科技大学 | Teaching system and teaching method based on learning behavior analysis |
| CN112860851A (en) * | 2021-01-22 | 2021-05-28 | 平安科技（深圳）有限公司 | Course recommendation method, device, equipment and medium based on root cause analysis |
| CN112860851B (en) * | 2021-01-22 | 2022-05-06 | 平安科技（深圳）有限公司 | Course recommendation method, device, equipment and medium based on root cause analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101105854A (en) | Students state on-line detection method based on decision-making tree remote-education environment | |
| Chen et al. | Using author co-citation analysis to examine the intellectual structure of e-learning: A MIS perspective | |
| CN102201085A (en) | Online learning system | |
| Nicolaisen | The scholarliness of published peer reviews: A bibliometric study of book reviews in selected social science fields | |
| Zhou et al. | Application analysis of data mining technology in ideological and political education management | |
| Smallbone et al. | A three-stage framework for teaching literature reviews: A new approach. | |
| Aher et al. | Best combination of machine learning algorithms for course recommendation system in e-learning | |
| Ganesh et al. | Applications of educational data mining: a survey | |
| CN112487290A (en) | Internet precision teaching method and system based on big data and artificial intelligence | |
| Veeramuthu et al. | Application of higher education system for predicting student using data mining techniques | |
| Abazeed et al. | A Classification and Prediction Model for Student's Performance in University Level. | |
| IGREȚ et al. | INTERNSHIPS, SKILLS AND EMPLOYABILITY: MAPPING THE FIELD THROUGH A BIBLIOMETRIC ANALYSIS. | |
| Long et al. | Application of decision tree in student achievement evaluation | |
| Zhou | Data mining and student e-learning profiles | |
| Zhou et al. | Design of online education big data platform based on data mining and data collection technology | |
| Kuzminska et al. | Artificial Intelligence in Education: A Study on Using Bibliometric Systems | |
| CN112699933A (en) | Automatic identification method and system for processing capacity of user teaching material | |
| Jiang et al. | An evaluation model of polytechnic teaching quality based on ID3 decision making tree | |
| Zhang et al. | Applications of association rule mining in Teaching Evaluation | |
| Le | Industry-university-research cooperation education of tourism english under big data technology | |
| Abdulaziz et al. | A survey on Big Data Analytics for Education | |
| Mahboob et al. | A comparative study of engineering students pedagogical progress | |
| Walsh et al. | Supporting Learner Model Exchange in Educational Web Systems. | |
| Rawat et al. | Ascertaining the Factors Influencing Students' Performance for Engineering Pedagogy | |
| Yin et al. | Building a search engine for scientific projects survey |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20080116 |