Enhanced neurocognitive diagnostic model

A convolutional neural network and knowledge point technology, applied in the field of educational data mining, can solve problems such as not considering the importance of knowledge points, failing to capture the complex relationship between students and exercises, and affecting the diagnosis effect

Pending Publication Date: 2021-07-23
JIANGXI NORMAL UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 3. Technical issues: Existing cognitive diagnosis models usually use artificially designed functions to mine students’ practice process. These functions are usually relatively simple and cannot capture the complex relationship between students and exercises well, which affects the diagnosis effect
It does not consider the importance of knowledge point proficiency and knowledge point difficulty itself to the answer prediction results, which in turn affects the diagnosis effect

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Enhanced neurocognitive diagnostic model
  • Enhanced neurocognitive diagnostic model
  • Enhanced neurocognitive diagnostic model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] See attached figure 1 As shown, the ENeuralCD model mainly consists of 4 parts:

[0010] 1. Vector representation of diagnostic factors:

[0011] In terms of students, this paper uses knowledge point proficiency vector α to represent students. α is obtained by multiplying the student one-hot encoded vector x with the trainable matrix A, namely

[0012] α=sigmoid(x×A)

[0013] where, α∈(0,1) 1×J ,x∈{0,1} 1×U ,A∈R U×J .

[0014] In terms of test questions, the knowledge point association vector p directly comes from the pre-given Q matrix:

[0015] p=z×Q

[0016] where p∈{0,1} 1×J , z∈{0,1} 1×V , Q∈{0,1} V×J , z is the one-hot encoded vector of the test item.

[0017] For other optional factors, use knowledge point difficulty vector β and test item discrimination γ. β=[β 1 ,β 1 ,...,β J ] indicates the difficulty of each knowledge point tested by the test questions. γ is used in test questions to distinguish students with high knowledge mastery from stude...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

According to an existing cognitive diagnosis model, manually designed functions are generally used for mining the exercise process of students, and the functions are generally simple and cannot well capture the complex relation between the students and exercises, so that the diagnosis effect is affected. The invention provides an enhanced neural cognitive diagnosis (ENeuralCD) model on the basis of a neural cognitive diagnosis (NeuralCD) framework, and the enhanced neural cognitive diagnosis (ENeuralCD) model is provided on the basis of the neural cognitive diagnosis (NeuralCD) framework. The model not only considers the influence of the importance (namely the importance degree of the knowledge points) factors of the knowledge points examined by the test questions on the diagnosis effect, but also considers the influence of the knowledge point proficiency degree of students and the knowledge point difficulty of the test questions on the importance degree of answer prediction on the diagnosis effect; and the fitting degree of the complex relationship between the student and the exercises is improved, so that the diagnosis effect is improved. According to the method, a real data set is compared with an existing typical model, and it is proved that the model has a good diagnosis effect and interpretability.

Description

technical field [0001] The invention relates to the technical field of educational data mining, and relates to a cognitive diagnosis method for students. Background technique [0002] 1. Explanation of terms: [0003] 1. Difficulty of test questions: Indicates the difficulty of each knowledge point of the test questions. 2. Examination item differentiation degree: It indicates the parameter that the examination item distinguishes students of different levels. 3. Knowledge point proficiency: a parameter indicating the student's mastery of knowledge points. 4. Q matrix: A matrix describing the relationship between test items (test questions) and attributes (knowledge points), generally composed of a 0-1 matrix of J (number of test questions) rows and K (number of knowledge points) columns. Q jk If it is 1, it means that question j examines knowledge point k; Q jk If it is 0, it means that the knowledge point k is not examined in question j. 5. Student factors: Indicates ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q50/20G06N3/08
CPCG06Q50/205G06N3/08
Inventor 程艳李猛陈豪迈
Owner JIANGXI NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap