Open Access

Strategies for Sharing and Utilizing Internet-Based Curriculum Resources in Teaching Higher Mathematics

Xiaohui Zhang

Xiaohui Zhang

School of Mathematics and Statistic, Zhengzhou Normal UniversityZhengzhou, China
Search for this author on
Sciendo|Google Scholar
Zhang, Xiaohui
 and 
Weiqiang Niu

Weiqiang Niu

School of Mathematics and Statistic, Zhengzhou Normal UniversityZhengzhou, China
Search for this author on
Sciendo|Google Scholar
Niu, Weiqiang
  
Mar 19, 2025
Strategies for Sharing and Utilizing Internet-Based Curriculum Resources in Teaching Higher Mathematics's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Mar 19, 2025
Received: Nov 02, 2024
Accepted: Feb 14, 2025
DOI: https://doi.org/10.2478/amns-2025-0450
Keywords
© 2025 Xiaohui Zhang et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Teaching repository framework
Teaching repository framework

Figure 2.

The function of the teaching resource library is composed
The function of the teaching resource library is composed

Figure 3.

DKVMN-FMF model structure
DKVMN-FMF model structure

Figure 4.

A multi-task learning course recommendation model
A multi-task learning course recommendation model

Figure 5.

Candidate course examples
Candidate course examples

Figure 6.

The accuracy of the data set in different recommendations
The accuracy of the data set in different recommendations

Figure 7.

Students have a sense of knowledge at k1
Students have a sense of knowledge at k1

Figure 8.

Students have a sense of knowledge at k2
Students have a sense of knowledge at k2

Figure 9.

Students have a sense of knowledge at k3
Students have a sense of knowledge at k3

Figure 10.

Students have a sense of knowledge at k4
Students have a sense of knowledge at k4

Figure 11.

Students have a sense of knowledge at k5
Students have a sense of knowledge at k5

Figure 12.

Different class knowledge points master the situation
Different class knowledge points master the situation

Figure 13.

The students’ knowledge points are compared
The students’ knowledge points are compared

Figure 14.

Student knowledge
Student knowledge

Figure 15.

Student mathematical performance
Student mathematical performance

Symbols and their meanings

Symbol Meaning
qt The embedded vector of problem q
countt The embedded vector of the attempt_count number
hintt Whether to request the embedded vector of the first _action
difft Difficulty embedding vector
typet The embedded vector of the problem type
ct The combination eigenvectors that contain problem sets and multiple features
Mk The static matrix key, which contains the knowledge concept of the study
Mv The dynamic matrix value, which contains the mastery of the concept of knowledge
wt The relevant weights of problem sets and knowledge concepts
rt Read the vector, which means the student’s degree of mastery of the problem set
ret The degree of mastery of the problem of forgetting
ft Summarize the vector, including the student’s degree of mastery and the difficulty of the problem
pt Predicting the probability of students answering correctly
et Erase vector
at Plus vector

Indicators of the four recommended models

Data set ASST2023 ASST2017 KDD2010 Bean cloud
Index Model 60 70 80 60 70 80 60 70 80 60 70 80
PR UB-CF 46.2 54.5 64.2 44.2 51 61.6 35.4 43.2 55.7 43.8 51 58.7
IB-CF 58.8 63.2 67.8 56.2 61.5 64 37.2 47.6 57.7 40.3 47.5 64.7
DKT-CF 82.1 85.7 88.2 78.4 80.1 83.9 73.7 75.5 78.2 76.5 80 81.9
Ours 88.9 89.5 93 83.3 84.9 86.7 76.1 80.9 82.4 80.1 83.4 85.1
RR UB-CF 15.5 20.6 24.7 12.3 15.5 16.4 12.9 13 12 12.8 13.7 13.7
IB-CF 18.1 22.3 26.5 15 16.6 18.8 11.9 12.9 14.6 11.9 16.3 17.5
DKT-CF 31.3 34 35.2 29.3 29.6 30.9 25.1 27.3 28.7 27.1 28.9 29.8
Ours 36.2 38.4 38.3 31.4 32.9 33.2 28.1 29 30.3 30.4 31 32.1
F1 UB-CF 23.3 30.7 35.1 19.4 23.8 26.3 19.1 19.4 20.8 20.4 21.2 22.5
IB-CF 27 32 38.8 22.9 26.5 29 18.2 21.5 23.3 19.4 24.5 28.7
DKT-CF 45 48.5 50.4 42.2 43.1 45.5 37.1 39 42.4 38.8 42.7 44
Ours 52.5 53.5 54.9 46 47.5 47.8 41.3 42.8 44.1 43.5 45.1 46.9

Data collection statistics

POJ LLS
Number of learners 13,289 2,063
Number of learning items 2,030 1,198
Number of interactions 424,004 312.379
Data collection time 2022/05/29-2023/04/17 2022/5/29-2023/04/17
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Life Sciences, Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics, Physics, other
Journal RSS Feed