Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A system and method for grouping test questions of the same knowledge point based on question meaning text

A technology of grouping system and knowledge points, which is applied in text database clustering/classification, unstructured text data retrieval, character and pattern recognition, etc. It can solve problems such as accumulation of questions that are difficult to further divide, and achieve high accuracy.

Active Publication Date: 2022-05-03
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that a large number of questions in the current online teaching platform are similar in content and difficult to further divide the accumulation of questions under the same knowledge point, the present invention proposes a system and method for grouping test questions of the same knowledge point based on the text of the question meaning to meet the different needs of users. The multifunctional grouping module in includes unsupervised learning-based clustering model WSD-LDA and supervised learning-based one-hot random forest classification model

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
  • A system and method for grouping test questions of the same knowledge point based on question meaning text
  • A system and method for grouping test questions of the same knowledge point based on question meaning text
  • A system and method for grouping test questions of the same knowledge point based on question meaning text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0086] Table 1 shows the specific implementation process of the above WSD-LDA model in the "stack" knowledge point in the background data set of the PTA platform.

[0087] This knowledge point has a total of 155 short questions. The algorithm divides the questions into 5 categories. The specific clustering results obtained by the algorithm are as follows:

[0088] Table 1 Classification results of WSD-LDA model

[0089]

[0090]

[0091] Also based on the grouping consideration of the stack, the short questions under the knowledge point are labeled with the definition, storage, properties, application, algorithm, and combination with other knowledge points of the stack, and the training of the one-hot random forest model is carried out. , with an accuracy rate of 87% under cross-validation, meeting the accuracy requirement for classifying newly uploaded questions.

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 system and method for grouping test questions of the same knowledge point based on question meaning texts, belonging to the field of online test question learning. This system includes two method models of unsupervised model WSD-LDA clustering and supervised learning one-hot random forest. Using artificial intelligence and natural language processing related technologies, the online platform question bank is similar to the subject or knowledge point. Carry out subdivision and present similar questions in groups, which is convenient for users to select, deduplicate, simplify, and typicalize similar questions according to their own needs. It solves the problem of too many similar questions on the platform and complicated questions under the same knowledge point. It is difficult for teachers to optimize test questions, and users' learning and training are inefficient.

Description

technical field [0001] The invention relates to the field of online test question learning, in particular to a system and method for grouping test questions of the same knowledge point based on question meaning texts. Background technique [0002] Compared with traditional paper test questions, online test questions have more real-time feedback, more flexible interaction, smarter evaluation and wider scope. As a result, more and more course teaching and training are moving to the Internet. Some courses put assignments and assessments online, and some even directly transform into online courses. The popularity of online teaching platforms has brought about the popularity of online exercises and online exams. Therefore, most online teaching platforms (such as homework help, puzzle A, Chinese University MOOC, etc.) have their own fill-in-the-blank and multiple-choice questions. , true or false questions and other types of questions automatically judge function question bank. ...

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 Patents(China)
IPC IPC(8): G06F16/35G06K9/62
CPCG06F16/35G06F18/2321G06F18/24323
Inventor 陈建海杨楠沈睿何钦铭荣大中
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com