CN110727788A - Self-adaptive teaching scheme adjusting method based on knowledge point similarity - Google Patents
Self-adaptive teaching scheme adjusting method based on knowledge point similarity Download PDFInfo
- Publication number
- CN110727788A CN110727788A CN201910992611.1A CN201910992611A CN110727788A CN 110727788 A CN110727788 A CN 110727788A CN 201910992611 A CN201910992611 A CN 201910992611A CN 110727788 A CN110727788 A CN 110727788A
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- similarity
- knowledge
- ability value
- points
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The invention discloses a self-adaptive teaching scheme adjusting method based on knowledge point similarity, which comprises the following steps: s1: calling historical detection data of each knowledge point; s2: acquiring a learning ability value vector of each knowledge point according to historical detection data; s3: combining every two knowledge points to form a knowledge point combination list, and respectively inputting learning ability value vectors corresponding to the knowledge points in the knowledge point combination list; s4: calculating the cosine similarity of each group of knowledge point pairs in the knowledge point combination list; s5: carrying out data screening on the knowledge point combination list, and finding out a knowledge point pair consisting of a target knowledge point and knowledge points which have been learned by the target student; s6: calculating the similarity of the average capability values of the screened groups of knowledge point pairs; s7: and correspondingly adjusting the teaching scheme based on the average ability value similarity. The invention can mine the similarity between the knowledge points according to the detection data records of the past students and predict the learning performance of the students on the new knowledge points according to the similarity, thereby adjusting the teaching scheme.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a self-adaptive teaching scheme adjusting method based on knowledge point similarity.
Background
With the rapid development of network technology, online teaching systems have been widely used on networks in recent years. At present, many conventional online teaching systems prepare knowledge point maps in the system according to the logical relevance of each knowledge point. Meanwhile, the teaching scheme of the subsequent knowledge point is correspondingly adjusted along the knowledge point atlas according to the learning condition of each student on the prior knowledge point, so that the teaching scheme is matched with the learning ability expressed by the student in the previous stage. So as to ensure the teaching quality of different students and improve the learning confidence of the students. However, at the 2019LAK (International Learning Analytics & Knowledge Conference) Conference in 3 rd year, Jinseok Lee and Dit-Yan Yeung propose an academic paper with Knowledge tracing as a subject, which notes: in the practice of the institution, teachers found: it is often not accurate to predict the learning receptivity of a subsequent knowledge point based on the student's performance of a previous knowledge point on the knowledge point map. The paper therefore introduces a model of a Knowledge query network. The model further introduces the concept of knowledge point similarity by quantifying two dimensions of knowledge State (knowledge State) and knowledge points of students. The article states that: the results of the sampling survey of the big data show: when the similarity of the two knowledge points is high, the learning performances of the students in the two knowledge points are consistent. Therefore, how to develop a teaching scheme for purposefully adjusting teaching schemes of different students by acquiring the similarity between different knowledge points and predicting the learning performance of the knowledge points to be learned by different students based on the similarity is a direction in which the skilled person needs to research.
Disclosure of Invention
The invention aims to provide a self-adaptive teaching scheme adjusting method based on the similarity of knowledge points, which can be used for recording and mining the similarity between the knowledge points according to the detection data of the current students and predicting the learning performance of the students on new knowledge points according to the similarity so as to adjust the teaching scheme.
The technical scheme is as follows:
a self-adaptive teaching scheme adjusting method based on knowledge point similarity comprises the following steps: s1: calling historical detection data of each lead student on each knowledge point; s2: substituting the historical detection data obtained in the step S1 into a prestored operation model to obtain the learning ability value vector of each past student at each knowledge point; s3: combining every two knowledge points to form a knowledge point pair, forming a knowledge point combination list by using each group of knowledge point pairs, and respectively inputting learning ability value vectors corresponding to each knowledge point by each lead student in the knowledge point combination list; s4: calculating cosine similarity between two knowledge points in each group of knowledge point pairs in the knowledge point combination list based on the learning ability value vector obtained in the step S3, and taking the cosine similarity as the ability value similarity between the two knowledge points; s5: carrying out data screening on the knowledge point combination list, and finding out a knowledge point pair consisting of a target knowledge point and a learned knowledge point of a target object; s6: calculating the average ability value similarity of each group of knowledge point pairs screened out in S5; s7: screening out the previous N groups of knowledge points with higher average capacity value similarity, and acquiring historical detection data of a target object on learned knowledge points in the N groups of knowledge points; s8: and correspondingly adjusting the teaching scheme based on the historical detection data obtained in the step S7.
Preferably, in the adaptive teaching scheme adjusting method based on similarity of knowledge points: in step S2, the operation model adopts an IRT single parameter model.
More preferably, in the adaptive teaching plan adjusting method based on similarity of knowledge points: in step S4, the cosine similarity is calculated based on the Python sklern model.
More preferably, in the adaptive teaching plan adjusting method based on similarity of knowledge points: in step S5, data screening is performed on the knowledge point combination list based on the Python pandas model.
More preferably, in the adaptive teaching plan adjusting method based on similarity of knowledge points: in step S6, the average ability value similarity is obtained for each group of knowledge point pairs based on the Python numpy model.
By adopting the technical scheme, the working process is as follows: and solving the similarity degree between all knowledge points through cosine similarity based on the question-making test result of the current student user. And extracting knowledge points with high similarity with the target knowledge points as prediction bases, pre-judging the ability expression of the target student users when learning the target knowledge points according to the learning feedback condition of the target student users on each knowledge point as the prediction bases, and correspondingly adjusting the teaching scheme output to the target student users.
Compared with the prior art: the similar degree of knowledge point is compared to the output of the effect of making a question through the student actual use system to this scheme of adoption, and the evaluation process is comparatively objective true. The similarity of the capability value sequence vectors of the knowledge points is calculated through cosine similarity, and the method accords with the conclusion of a paper made by Jinseok Lee and Dit-Yan Yeung in 2019LAK, and the theoretical basis is firm. In addition, a knowledge point map does not need to be additionally constructed for each knowledge point according to the logical sequence of the knowledge points, and program resources are greatly saved. The scheme can record and mine the similarity between the knowledge points according to the detection data of the students and predict the learning performance of the students on the new knowledge points according to the similarity, so that the teaching scheme is adjusted. Therefore, the teaching scheme aiming at different students is adjusted, the learning efficiency of the students is improved, and the learning enthusiasm of the students is ensured.
Drawings
The invention will be described in further detail with reference to the following detailed description and accompanying drawings:
FIG. 1 is a flow chart of the operation of the present invention.
Detailed Description
In order to more clearly illustrate the technical solution of the present invention, the following will be further described with reference to various embodiments.
FIG. 1 shows example 1 of the present invention:
forecasting and adjusting a teaching scheme aiming at a knowledge point sine function to be learned by a student A;
the process is as follows:
s1: calling historical detection data of all the past students on all teaching knowledge points in the database;
s2: substituting the historical detection data obtained in the step S1 into a prestored IRT single-parameter operation model to obtain the learning capacity value vector of each past student at each knowledge point;
s3: combining every two knowledge points to form a knowledge point pair, forming a knowledge point combination list by using each group of knowledge point pairs, and respectively inputting learning ability value vectors corresponding to each knowledge point by each lead student in the knowledge point combination list;
s4: calculating cosine similarity between two knowledge points in each group of knowledge point pairs in the knowledge point combination list by adopting a Python sklern model based on the learning ability value vector obtained in the S3, and taking the cosine similarity as the ability value similarity between the two knowledge points;
s5: carrying out data screening on the knowledge point combination list based on a Python pandas model, and finding out a knowledge point pair which simultaneously contains a sine function and a learned knowledge point of student A;
s6: calculating the average ability value similarity of each group of knowledge point pairs screened out in S5 based on a Python numpy model;
s7: screening the first 3 (in the example, N takes 3) groups of knowledge points with higher similarity of the average ability value, wherein the knowledge points are respectively (cubic root, sine function), (rational number, sine function), (factorization and sine function);
s8: and respectively obtaining historical detection data of the student A on the root of the opposite square, the rational number and the factorization, wherein the learning ability values of the student A are respectively good, excellent and excellent on the three knowledge points.
S9: and the teacher reads historical detection data of the student A on the basis of the cubic root, rational number and factorization obtained in the step S8, judges that the student A approximately shows excellence when learning the sine function, and adjusts the teaching scheme to output high-difficulty teaching materials for the student A.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. The protection scope of the present invention is subject to the protection scope of the claims.
Claims (5)
1. A self-adaptive teaching scheme adjusting method based on knowledge point similarity is characterized by comprising the following steps:
s1: calling historical detection data of each lead student on each knowledge point;
s2: substituting the historical detection data obtained in the step S1 into a prestored operation model to obtain the learning ability value vector of each past student at each knowledge point;
s3: combining every two knowledge points to form a knowledge point pair, forming a knowledge point combination list by using each group of knowledge point pairs, and respectively inputting learning ability value vectors corresponding to each knowledge point by each lead student in the knowledge point combination list;
s4: calculating cosine similarity between two knowledge points in each group of knowledge point pairs in the knowledge point combination list based on the learning ability value vector obtained in the step S3, and taking the cosine similarity as the ability value similarity between the two knowledge points;
s5: carrying out data screening on the knowledge point combination list, and finding out a knowledge point pair consisting of a target knowledge point and a learned knowledge point of a target object;
s6: calculating the average ability value similarity of each group of knowledge point pairs screened out in S5;
s7: screening out the previous N groups of knowledge points with higher average capacity value similarity, and acquiring historical detection data of a target object on learned knowledge points in the N groups of knowledge points;
s8: and correspondingly adjusting the teaching scheme based on the historical detection data obtained in the step S7.
2. The adaptive teaching scheme adjustment method based on knowledge point similarity as claimed in claim 1, characterized in that: in step S2, the operation model adopts an IRT single parameter model.
3. The adaptive teaching scheme adjustment method based on knowledge point similarity as claimed in claim 1, characterized in that: in step S4, the cosine similarity is calculated based on the Python sklern model.
4. The adaptive teaching scheme adjustment method based on knowledge point similarity as claimed in claim 1, characterized in that: in step S5, data screening is performed on the knowledge point combination list based on the Python pandas model.
5. The adaptive teaching scheme adjustment method based on knowledge point similarity as claimed in claim 1, characterized in that: in step S6, the average ability value similarity is obtained for each group of knowledge point pairs based on the Python numpy model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910992611.1A CN110727788B (en) | 2019-10-17 | 2019-10-17 | Self-adaptive teaching scheme adjusting method based on knowledge point similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910992611.1A CN110727788B (en) | 2019-10-17 | 2019-10-17 | Self-adaptive teaching scheme adjusting method based on knowledge point similarity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110727788A true CN110727788A (en) | 2020-01-24 |
| CN110727788B CN110727788B (en) | 2020-11-10 |
Family
ID=69221494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910992611.1A Active CN110727788B (en) | 2019-10-17 | 2019-10-17 | Self-adaptive teaching scheme adjusting method based on knowledge point similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110727788B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007112216A2 (en) * | 2006-03-24 | 2007-10-04 | Massie Robert K | Method and system for evaluating and matching educational content to a user |
| CN105138624A (en) * | 2015-08-14 | 2015-12-09 | 北京矩道优达网络科技有限公司 | Personalized recommendation method based on user data of on-line courses |
| CN106097204A (en) * | 2016-06-24 | 2016-11-09 | 北京航空航天大学 | A kind of work commending system towards cold start-up User and recommendation method |
| CN107122452A (en) * | 2017-04-26 | 2017-09-01 | 中国科学技术大学 | Student's cognitive diagnosis method of sequential |
| CN107274020A (en) * | 2017-06-15 | 2017-10-20 | 北京师范大学 | A kind of learner's subject based on collaborative filtering thought always surveys result prediction system and method |
| CN109388744A (en) * | 2017-08-11 | 2019-02-26 | 北京龙之门网络教育技术股份有限公司 | A kind of adaptive learning recommended method and device |
-
2019
- 2019-10-17 CN CN201910992611.1A patent/CN110727788B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007112216A2 (en) * | 2006-03-24 | 2007-10-04 | Massie Robert K | Method and system for evaluating and matching educational content to a user |
| CN105138624A (en) * | 2015-08-14 | 2015-12-09 | 北京矩道优达网络科技有限公司 | Personalized recommendation method based on user data of on-line courses |
| CN106097204A (en) * | 2016-06-24 | 2016-11-09 | 北京航空航天大学 | A kind of work commending system towards cold start-up User and recommendation method |
| CN107122452A (en) * | 2017-04-26 | 2017-09-01 | 中国科学技术大学 | Student's cognitive diagnosis method of sequential |
| CN107274020A (en) * | 2017-06-15 | 2017-10-20 | 北京师范大学 | A kind of learner's subject based on collaborative filtering thought always surveys result prediction system and method |
| CN109388744A (en) * | 2017-08-11 | 2019-02-26 | 北京龙之门网络教育技术股份有限公司 | A kind of adaptive learning recommended method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110727788B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110519128B (en) | Random forest based operating system identification method | |
| CN109360183A (en) | A kind of quality of human face image appraisal procedure and system based on convolutional neural networks | |
| CN107545000A (en) | The information-pushing method and device of knowledge based collection of illustrative plates | |
| Zhang et al. | A brief analysis of the key technologies and applications of educational data mining on online learning platform | |
| CN104573130A (en) | Entity resolution method based on group calculation and entity resolution device based on group calculation | |
| CN110110063A (en) | A kind of question answering system construction method based on Hash study | |
| CN114168906A (en) | Mapping geographic information data acquisition system based on cloud computing | |
| CN115456695A (en) | Method, device, system and medium for analyzing shop address selection | |
| CN110544047A (en) | Bad data identification method | |
| CN110084291A (en) | A kind of students ' behavior analysis method and device based on the study of the big data limit | |
| CN110727788B (en) | Self-adaptive teaching scheme adjusting method based on knowledge point similarity | |
| CN108563720A (en) | Big data based on AI recommends learning system and recommends method | |
| CN112380906A (en) | Method for determining user address based on driving data | |
| CN111626324A (en) | Seabed observation network data heterogeneous analysis integration method based on edge calculation | |
| JP4780668B2 (en) | Traffic analysis model construction method, apparatus, construction program, and storage medium thereof | |
| CN108055638A (en) | Obtain method, apparatus, computer-readable medium and the equipment of target location | |
| CN114821322A (en) | Small sample remote sensing image classification method and system based on attention mechanism | |
| CN114492569A (en) | Typhoon path classification method based on width learning system | |
| Jiang et al. | Evolving hard and easy traveling salesman problem instances: a multi-objective approach | |
| CN111881125A (en) | Real-time cleaning method and system for non-operational targets on sea | |
| CN108986217B (en) | Multipoint geostatistical modeling method based on pattern vector distance | |
| CN105260448A (en) | Big data information analysis method | |
| CN110311991A (en) | Street-level terrestrial reference acquisition methods based on svm classifier model | |
| CN114936203B (en) | Method based on time sequence data and business data fusion analysis | |
| CN112040414B (en) | Similar track calculation method and device and electronic equipment |
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 | ||
| CB02 | Change of applicant information |
Address after: Room B381, 588 Tianlin East Road, Xuhui District, Shanghai 200000 Applicant after: Shanghai squirrel classroom Artificial Intelligence Technology Co., Ltd Address before: Room B381, 588 Tianlin East Road, Xuhui District, Shanghai 200000 Applicant before: SHANGHAI YIXUE EDUCATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |