Computer adaptive evaluation method based on learning topic selection strategy

A computer and self-adaptive technology, applied in the field of computer self-adaptive evaluation based on the learning topic selection strategy, to achieve the effect of accelerating convergence, improving performance and improving accuracy

Pending Publication Date: 2022-05-31
ANHUI UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the shortcomings of the above-mentioned prior art, the present invention proposes a computer adaptive evaluation method based on the learning topic selection strategy, in order to mine student ability and topic selection in a large a

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
  • Computer adaptive evaluation method based on learning topic selection strategy
  • Computer adaptive evaluation method based on learning topic selection strategy
  • Computer adaptive evaluation method based on learning topic selection strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0109] In order to verify the effectiveness of the method of the present invention, this method selects the data set of Assistment2009 for experimental verification, wherein the data set already disclosed by assistance2009 includes math test questions and student answer records.

[0110] 1. First, data cleaning is performed on the data set, mainly from the following aspects: in the training data 1) knowledge points: filter knowledge points with less than 10 related questions; 2) questions: these questions must be answered at least 50 times ; 3) Behavior records: students must have at least 10 behavior records; in the test data 1) students who answer at least 150 questions are divided into test data; the final Assistment2009 data set contains 903 questions, 1473 students (training students 1426 / test student 47), 22 knowledge points, 58472 behavior records;

[0111] 2. Secondly, compare the topic selection algorithms, including random topic selection (random), IRT-based maximum ...

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

The invention discloses a computer adaptive evaluation method based on a learning topic selection strategy, which is used for mining the relationship between students and selected topics in a Learning mode, and comprises the following steps of: 1, training a cognitive diagnosis model, obtaining initialization capability parameters and topic parameters, and constructing an input vector of a deep neural network; 2, constructing a deep neural network structure to obtain mapping of an input vector and an output topic selection probability; and 3, performing loss function design of the deep neural network, and updating parameters of the deep neural network. According to the invention, the potential relation between the ability of the students and the selected questions can be mined, so that the purpose of accurately evaluating the mastering degree of the students on the required subjects/fields by selecting fewest questions can be achieved, and the accuracy of question selection can be improved.

Description

technical field [0001] The invention relates to the technical fields of machine learning, artificial intelligence and intelligent education, in particular to a computer adaptive evaluation method based on learning topic selection strategies. Background technique [0002] Computer Adaptive Assessment (CAT) refers to a personalized test form for each student. Based on the student's answers to the previous question and the previous test questions, the next test exercise is adaptively selected. See figure 1 As shown in the CAT framework, according to the students' answers (correct / wrong answers), the cognitive diagnosis model (CDM) is used to diagnose the student's ability status (θ), and then combine the topic selection strategy to select a topic suitable for the current ability (qt) , and finally form a set of personalized test questions. [0003] In the traditional computer adaptive assessment (CAT), most of the algorithms are model-specific, such as the maximum information ...

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
IPC IPC(8): G06N3/04G06N3/08G06N20/00
CPCG06N3/04G06N3/08G06N20/00
Inventor 马海平曾毅张兴义
Owner ANHUI UNIVERSITY
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