Test question recommendation method combining neurocognitive diagnosis and neural collaborative filtering

A collaborative filtering algorithm and collaborative filtering technology, applied in the computer field, can solve problems such as mismatching difficulty levels of test questions

Pending Publication Date: 2022-02-25
JIANGXI NORMAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 1. In view of the above-mentioned shortcomings, the purpose of the present invention is to solve the problem of mismatching of the difficulty of the recommended test items in the existing test item recommendation technology, and propose a personalized test item recommendation combining neurocognitive diagnosis and neural collaborative filtering Method (NCD-NCF)

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
  • Test question recommendation method combining neurocognitive diagnosis and neural collaborative filtering
  • Test question recommendation method combining neurocognitive diagnosis and neural collaborative filtering
  • Test question recommendation method combining neurocognitive diagnosis and neural collaborative filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] See attached figure 1 As shown, the NCD-NCF method mainly includes three steps:

[0010] Step 1 (student cognitive diagnosis): Use the neurocognitive diagnosis model to model the practice process of each student's test questions, obtain the knowledge point mastery degree α of each student and the knowledge point difficulty information β of the test questions, and output the student The test questions master the level matrix A.

[0011] Step 2 (Student score prediction): Combined with the neural collaborative filtering algorithm, the cognitive diagnosis results of the previous step are introduced as the prior information of the neural collaborative filtering to obtain the student's score vector on the test questions.

[0012] Step 3 (output): According to the actual knowledge level of the students, set the difficulty range of the recommended test questions, and filter out the test questions whose predicted scores are within the range, so as to generate a personalized te...

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 test question recommendation method for cognitive diagnosis and a test question recommendation method based on collaborative filtering, implicit information in data cannot be fully mined out, and microscopic and macroscopic personality characteristics of students are ignored. The invention provides a personalized test question recommendation method (NCD-NCF) in combination with neurocognitive diagnosis and neural collaborative filtering. According to the method, learning personality of recommended students and learning generality of group students are considered at the same time, and personalized test questions are recommended to each student more accurately by using nonlinear modeling capability of the neural network. According to the method, firstly, knowledge point mastering degrees of students and knowledge point difficulty information of test questions are obtained by using a neurocognitive diagnosis model, and a test question mastering level matrix of the students is output; and then a neural collaborative filtering recommendation algorithm is combined to predict scores of the test questions of the students, and finally proper test questions are recommended to each student according to a difficulty threshold.

Description

technical field [0001] The invention belongs to the technical field of computers and is applied to test item recommendation tasks. 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. Knowledge point proficiency: a parameter indicating the student's mastery of knowledge points. 3. Q matrix: A matrix describing the relationship between test questions and 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. [0004] 2. Existing technologies: 1. Matrix Factorization (MF) technology solves the problem of predicting scores of test questions for students, thereby recommending test questions. It constructs a low-dimensional matr...

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): G06F16/9535G06F16/9536G06Q50/20G06N3/02
CPCG06F16/9535G06F16/9536G06Q50/205G06N3/02
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