CN112149940A - Knowledge point mastering degree online evaluation system and method - Google Patents
Knowledge point mastering degree online evaluation system and method Download PDFInfo
- Publication number
- CN112149940A CN112149940A CN201910583902.5A CN201910583902A CN112149940A CN 112149940 A CN112149940 A CN 112149940A CN 201910583902 A CN201910583902 A CN 201910583902A CN 112149940 A CN112149940 A CN 112149940A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- knowledge point
- online
- student
- mastery degree
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 238000012163 sequencing technique Methods 0.000 claims abstract description 6
- 230000003993 interaction Effects 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 230000001680 brushing effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 4
- 230000001737 promoting effect Effects 0.000 abstract description 2
- 238000000691 measurement method Methods 0.000 abstract 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000007547 defect Effects 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
- G06Q10/06—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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Educational Technology (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to the field of education technology and measurement method, in particular to an online evaluation system and method for knowledge point mastery degree, wherein the evaluation system comprises a student knowledge offline calculation module, a question sequencing module and an online updating module, and the method comprises the following steps: collecting historical behavior records of the evaluated object on the knowledge points to be tested, calculating the historical mastery degree of the evaluated object on each knowledge point by adopting a Bayesian algorithm according to the historical records, recommending test contents by combining a knowledge map with fine granularity and an exercise library, updating the mastery degree of the knowledge points to be tested on line according to a real-time test result, and performing iteration circularly until a preset threshold value is reached. The method is suitable for promoting proper evaluation content to the evaluated object and calculating the mastery degree on the knowledge point to be evaluated, and has the advantages of obtaining equal test effect by using less test content, obviously improving the user experience and the like.
Description
The technical field is as follows:
the invention relates to the field of education technology and measuring method, in particular to an online evaluation system and method for knowledge point mastery degree.
Background
The prior art discloses a method for measuring the mastery degree of students on certain knowledge by related education institutions, and generally adopts a mode of evaluating answer sheets no matter whether the students are online or offline. Generally, when a study subject includes a large number of knowledge points and a part of the knowledge points have a plurality of exercises for assessment, it becomes very difficult to comprehensively test the accurate grasping condition of a student by adopting a proper amount of test and evaluation questions, because the comprehensive, proper and accurate three are in competitive relationship; for example, in a given number of knowledge points to be examined, more topics need to be designed for comprehensive examination; or, under the condition of a given number of knowledge points and questions, how to evaluate more accurately according to the answering condition, and the like; in addition, for a student, the evaluation cannot completely and accurately evaluate the mastery level of the knowledge point, because even the simplest subject is carelessly wrong, and some difficulties may be temporarily masked, so that the method for uniquely determining the mastery level of the knowledge point by the student only through the evaluation score is not completely reliable. Even in the current big data era, the learning data of students obtained by online education institutions is very limited and biased, each test paper has a detected recognition point and a fixed number, and usually, one test only measures the grasping level of the students at the test points, and the test points which are not listed in the test paper cannot be calculated. How to utilize limited test data to evaluate the mastery conditions of students on more knowledge points becomes a problem to be solved urgently in the industry. In addition, the mastery degree of the knowledge points by the students does not need to be evaluated, comprehensive evaluation can be performed by considering more multidimensional information sources, an online education institution focuses on customizing a culture plan for the students, and besides online evaluation, a plurality of teaching modes are provided, so that the mastery condition of each knowledge point by each student needs to be uniformly and comprehensively recorded and managed.
Based on the current state of the prior art, the inventor of the application intends to provide an online evaluation system and method for knowledge point mastery degree, so as to evaluate the mastery condition of students on more knowledge points by using limited test data.
Disclosure of Invention
The invention aims to provide an online evaluation system and method based on the current situation of the prior art and overcoming the defects of the prior art, and particularly relates to an online evaluation system and method for knowledge point mastering degree.
More specifically, the technical problems to be solved by the present invention are: (1) a proper amount of evaluation questions are used for more comprehensively and accurately evaluating the mastering conditions of students on a given knowledge point; (2) considering the possibility that the student is mastered but wrongly done or not mastered but does a right in the evaluation; (3) evaluating more knowledge point mastering conditions by using limited evaluation data; (4) considering the mastery information of students on knowledge points except for evaluation; (5) and uniformly managing the mastery degree of each student at each knowledge point on line.
The purpose of the invention is realized by adopting the following technical scheme:
the invention provides an online evaluation system which comprises a student knowledge offline calculation module, a question sequencing module and an online updating module.
The off-line computation module receives four data sources: student-knowledge point interaction information, student figures, knowledge point related indexes and student-knowledge point mastering information;
the student-knowledge point interaction information refers to information which is left by a student at each knowledge point through various ways and can reflect the mastery or not of the student, and mainly comprises the following steps: (1) brushing question data on line; (2) online evaluation data; (3) online classroom assessment data; (4) online post-session job data; (5) evaluation by an online teacher; (6) evaluation of the student himself.
The student image comprises a priori value (probability which can be mastered by a student before any test is carried out, the probability reflects the easy mastering condition of a knowledge point to a certain extent), error-prone probability (mastered but wrongly done (related to the subject form and the like)), guess-prone probability (mastered but wrongly done (related to the subject form)), learning-prone probability (probability that the student cannot do any error after wrongly copying), forgetting probability and teaching indexes (such as the frequency of being checked and some comprehensive indexes). The student portrait provides fine-grained evaluation indexes of students in various disciplines, various knowledge modules and the like.
The related indexes of the knowledge points are provided by a set of comprehensive management system, and the indexes mainly comprise: (1) the prior value, namely the probability that a student can master before there is no test, reflects the easy-to-master situation of the knowledge point to a certain extent; (2) the probability of making mistakes is easy, namely the probability of mastering but making mistakes is particularly related to the form of the question and the like; (3) the guess probability is easy, namely the guess probability is not mastered but is right, and is particularly related to the question form; (4) the probability of easy learning, namely the probability of no error after error duplication; (5) a forgetting probability; (6) teaching indexes such as the frequency of being examined and some comprehensive indexes; (7) and so on.
The mastery information of the knowledge points of the students is provided by a set of comprehensive management system, and an evaluation system corresponding to the evaluation method also belongs to the comprehensive management system, and the comprehensive management system represents the mastery degree of each student on each knowledge point at present and generally represents the mastery degree by using a probability continuous value from 0 to 1.
In the invention, an off-line calculation module adopts a popularization algorithm of Bayesian Knowledge tracking to perform off-line calculation, combines partial characteristics in the four data sources, performs off-line training to obtain the parameter values with the maximum expectation, and iteratively updates the parameter values, wherein the parameter values are positioned in the related indexes of the Knowledge points and the student-Knowledge point grasping information.
In the invention, the question sequencing module receives three data sources, the question sequencing refers to sequencing according to the front-back relation of knowledge points in a map, and can be performed from front to back or from back to front, and then whether to skip the next question is selected according to the answer condition and the latest mastery degree of students; the three data sources comprise knowledge point-question associated information, a knowledge graph and student real-time answer conditions;
wherein the knowledge point-topic association information comprises: (1) each knowledge point corresponds to a question in a question bank; (2) the related indexes of the questions, such as examination frequency, comprehensive indexes and the like;
the knowledge graph comprises the front-rear order relation of all knowledge points.
The updating method adopted in the online updating module is a Bayes online inference mode of BKT, and a specific knowledge point set is updated according to the answering condition of students and by combining the associated knowledge points and the knowledge graph of the answering purpose; the knowledge point set comprises detected knowledge points, and the detected knowledge points or the post-knowledge point set are selected according to answer conditions.
On the other hand, the invention provides an online evaluation method for the mastery degree of the knowledge points.
The method comprises the following steps: step one, collecting historical behavior records of an evaluated object on a knowledge point to be tested; secondly, calculating the historical mastery degree of the evaluated object on each knowledge point by adopting a BKT algorithm according to the historical records; and thirdly, recommending test contents by combining the knowledge graph with fine granularity and the problem library, updating the mastery degree of the knowledge point to be tested on line according to a real-time test result, and performing iteration circularly until a preset threshold value is reached.
The invention provides an online evaluation system and method for knowledge point mastery degree, which are suitable for promoting proper evaluation content to an evaluated object and calculating the mastery degree of the knowledge point to be evaluated. Compared with the prior art, the method has the advantages of obtaining the same test effect by using less test contents, obviously improving the user experience and the like.
Through the knowledge point mastering degree online evaluation system and method, the following beneficial effects can be produced:
(1) according to the knowledge map relationship, the effect of updating a plurality of knowledge points for one question is achieved, the effect of researching the front knowledge points of the knowledge points can be omitted by mastering one knowledge point, more knowledge points are evaluated by using fewer questions, the question adaptability and the comprehensiveness of the knowledge points are improved, the same knowledge point is updated as much as possible, and the accuracy is improved.
(2) The calculation model of the BKT considers the situations of easiness in making mistakes, easiness in guessing pairs, learning conversion possibility, forgetting possibility and the like, and is more scientific.
(3) In off-line training, as many data sources as possible are considered, and not only question information is considered.
(4) The knowledge point mastery degree of students is uniformly managed in a plurality of scenes.
Description of the drawings:
FIG. 1 is a schematic view of the flow structure of the knowledge point mastery degree online evaluation method of the present invention.
Detailed Description
Example 1 student knowledge Point grasping degree on-line evaluation
Collecting historical behavior records of the evaluated object on the knowledge points to be tested, combining student portrait information, knowledge point portrait information and historical mastery degree of students to the knowledge points, calculating the current mastery degree of the evaluated object on each knowledge point in an off-line manner by adopting a BKT algorithm and updating the current relevant indexes of each knowledge point; the offline task can define the execution period by user;
the online task comprises two modules of task ordering and online calculation and runs in real time;
in the embodiment, the questions are sorted according to the sequence from back to front and are combined with the current mastery degree to determine whether to push the questions to students, if the current mastery degree of the students reaches a preset threshold value, the students know the knowledge points, do not push the knowledge points, and simultaneously do not push the related preposed knowledge points of the knowledge points;
the students receive the pushed questions in sequence, answer and submit in real time, submit one question and then receive the next question, but not generate all questions at one time; according to the answering condition: if the student answers to the pair, combining the historical mastery degree and the related indexes of the student to the knowledge point, calculating and updating the mastery degree of the student at the knowledge point and all the preposed knowledge points on line, and supposing that the student makes a pair on all the preposed knowledge points of the knowledge point; if the student makes a mistake, only updating the mastery degree of the student on the knowledge point;
at this time, there are two boundaries possible: (1) if the knowledge point has not been tested for records, then the default parameters given by the person are taken; (2) if the student does not have a relevant test record on the knowledge point, namely, does not have a corresponding parameter value, the corresponding parameter value of the knowledge point is taken; the parameters of the knowledge points are equivalent to the centralized statistics obtained according to the test data of all students.
Claims (10)
1. The utility model provides a knowledge point mastery degree on-line evaluation system which characterized in that: the online evaluation system comprises a student knowledge offline calculation module, a question sequencing module and an online updating module.
2. The system for online evaluation of knowledge point mastery degree according to claim 1, wherein: the student knowledge offline calculation module comprises four data sources, namely: student-knowledge point interaction information, student figures, knowledge point related indexes and student-knowledge point mastering information.
3. The system for online evaluation of knowledge point mastery degree according to claim 2, wherein: the student-knowledge point interaction information comprises online question brushing data, online evaluation data, online classroom assessment data, online post-class operation data, online teacher evaluation and student evaluation information.
4. The system for online evaluation of knowledge point mastery degree according to claim 2, wherein: the student image comprises a priori value, probability of error, probability of guess, probability of learning, forgetting probability and teaching indexes.
5. The system for online evaluation of knowledge point mastery degree according to claim 1, wherein: the title sorting module comprises three data sources, namely: knowledge point-question associated information, a knowledge graph and student real-time answering conditions.
6. The point of knowledge mastery online evaluation system according to claim 5, wherein: the knowledge point-question associated information comprises the question in the question bank corresponding to each knowledge point and the relevant indexes of the question.
7. The point of knowledge mastery online evaluation system according to claim 5, wherein: the knowledge graph comprises the front-rear order relation of all knowledge points.
8. The system for online evaluation of knowledge point mastery degree according to claim 1, wherein: the online updating module comprises an online calculation and updating method, and the updating method is a Bayesian online inference mode of BKT.
9. The point of knowledge mastery online evaluation system according to claim 1 or 2, characterized in that: the off-line calculation module adopts an off-line calculation method, and the off-line calculation method is a popularization algorithm adopting Bayesian Knowledge tracking algorithm (Bayesian Knowledge tracking).
10. An online evaluation method for knowledge point mastery degree is characterized by comprising the following steps:
step one, collecting historical behavior records of an evaluated object on a knowledge point to be tested;
secondly, calculating the historical mastery degree of the evaluated object on each knowledge point by adopting a BKT algorithm according to the historical records;
and thirdly, recommending test contents by combining the knowledge graph with fine granularity and the problem library, updating the mastery degree of the knowledge point to be tested on line according to a real-time test result, and performing iteration circularly until a preset threshold value is reached.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910583902.5A CN112149940A (en) | 2019-06-28 | 2019-06-28 | Knowledge point mastering degree online evaluation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910583902.5A CN112149940A (en) | 2019-06-28 | 2019-06-28 | Knowledge point mastering degree online evaluation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112149940A true CN112149940A (en) | 2020-12-29 |
Family
ID=73891380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910583902.5A Pending CN112149940A (en) | 2019-06-28 | 2019-06-28 | Knowledge point mastering degree online evaluation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149940A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117648934A (en) * | 2024-01-30 | 2024-03-05 | 青岛培诺教育科技股份有限公司 | Knowledge point determining method, device, equipment and medium based on error test questions |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140024008A1 (en) * | 2012-07-05 | 2014-01-23 | Kumar R. Sathy | Standards-based personalized learning assessments for school and home |
| CN106599999A (en) * | 2016-12-09 | 2017-04-26 | 北京爱论答科技有限公司 | Evaluation method and system for using small amount of questions to accurately detect segmented weak knowledge points of student |
| CN107122452A (en) * | 2017-04-26 | 2017-09-01 | 中国科学技术大学 | Student's cognitive diagnosis method of sequential |
| CN109598995A (en) * | 2019-01-08 | 2019-04-09 | 上海健坤教育科技有限公司 | Intelligent tutoring system based on Bayes's knowledge trace model |
| CN109902298A (en) * | 2019-02-13 | 2019-06-18 | 东北师范大学 | Domain Modeling and know-how estimating and measuring method in a kind of adaptive and learning system |
-
2019
- 2019-06-28 CN CN201910583902.5A patent/CN112149940A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140024008A1 (en) * | 2012-07-05 | 2014-01-23 | Kumar R. Sathy | Standards-based personalized learning assessments for school and home |
| CN106599999A (en) * | 2016-12-09 | 2017-04-26 | 北京爱论答科技有限公司 | Evaluation method and system for using small amount of questions to accurately detect segmented weak knowledge points of student |
| CN107122452A (en) * | 2017-04-26 | 2017-09-01 | 中国科学技术大学 | Student's cognitive diagnosis method of sequential |
| CN109598995A (en) * | 2019-01-08 | 2019-04-09 | 上海健坤教育科技有限公司 | Intelligent tutoring system based on Bayes's knowledge trace model |
| CN109902298A (en) * | 2019-02-13 | 2019-06-18 | 东北师范大学 | Domain Modeling and know-how estimating and measuring method in a kind of adaptive and learning system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117648934A (en) * | 2024-01-30 | 2024-03-05 | 青岛培诺教育科技股份有限公司 | Knowledge point determining method, device, equipment and medium based on error test questions |
| CN117648934B (en) * | 2024-01-30 | 2024-04-26 | 青岛培诺教育科技股份有限公司 | Knowledge point determining method, device, equipment and medium based on error test questions |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919810B (en) | Student modeling and personalized course recommendation method in online learning system | |
| Kurt | Intelligent tutoring systems for continuous, embedded assessment | |
| KR100978091B1 (en) | Management system for online test assessment and method thereof | |
| CN112131349B (en) | Method for measuring knowledge point mastering state | |
| CN108694501A (en) | A kind of individualized learning effect analysis system and method towards xAPI | |
| CN112508334B (en) | Personalized paper grouping method and system integrating cognition characteristics and test question text information | |
| Abdi et al. | A multivariate Elo-based learner model for adaptive educational systems | |
| CN107067849A (en) | Parent's end system based on cloud teaching platform | |
| Veerasamy et al. | Using early assessment performance as early warning signs to identify at-risk students in programming courses | |
| CN109214965B (en) | Data sorting method, system and device | |
| CN114429212A (en) | Intelligent learning knowledge ability tracking method, electronic device and storage medium | |
| CN115455186A (en) | Learning situation analysis method based on multiple models | |
| CN112116506A (en) | Method for measuring mastery degree of knowledge point | |
| CN112015783B (en) | Interactive learning process generation method and system | |
| CN114049240A (en) | Method for intelligently recommending questions and learning paths based on student online learning data | |
| CN114065031A (en) | Personalized learning path recommendation method based on fuzzy cognitive map | |
| CN112149940A (en) | Knowledge point mastering degree online evaluation system and method | |
| Cheng et al. | To implement computerized adaptive testing by automatically adjusting item difficulty index on adaptive English learning platform | |
| CN117313947A (en) | Learning early warning method based on random forest and tuna group optimization algorithm | |
| CN111259305A (en) | Online intelligent education method | |
| CN105678663A (en) | Question bank management system based on tree-structure knowledge tree model | |
| CN115409257A (en) | Score distribution prediction method and system based on condition density estimation model | |
| CN115100912A (en) | Teaching activity design system based on big data | |
| CN108921434A (en) | A method of user capability prediction is completed by human-computer interaction | |
| CN111178770B (en) | Answer data evaluation and learning image construction method, device and storage medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201229 |