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

A topic recommendation system based on statistical characteristics of answers

A statistical feature and recommendation system technology, applied in computing, computer parts, special data processing applications, etc., can solve problems such as typical topics that cannot be recommended by users, similar problems, and achieve the effect of solving the problem of inaccurate difficulty labeling

Active Publication Date: 2022-04-19
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the defect that a large number of topics in the current auxiliary teaching platform are similar in content and cannot recommend more typical topics according to user needs, this invention proposes a topic recommendation system based on the statistical characteristics of answers

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 topic recommendation system based on statistical characteristics of answers
  • A topic recommendation system based on statistical characteristics of answers
  • A topic recommendation system based on statistical characteristics of answers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0071] Tables 1 and 2 show some output results of the above specific implementation process under the knowledge point of "binary tree and its traversal" in the background data set of the PTA platform:

[0072] There are a total of 262 questions for this knowledge point. The algorithm divides the questions into 9 categories, and some of the questions with high typical scores are as follows:

[0073] Table 1 Topics with high scores

[0074]

[0075] Table 2 Topics with low scores

[0076]

[0077]

[0078] It can be seen that most of the typical questions are more intuitive, and the inspection of knowledge points in the questions is straightforward. On the other hand, the less typical topics have relatively little correlation with knowledge points, or the way of examining knowledge points is more obscure.

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 topic recommendation system based on statistical characteristics of answers, belonging to the field of computer-aided teaching and data mining, including a topic acquisition module, a preprocessing module, a query feature configuration module, a user interface, a feature processing module, and a clustering calculation module and topic recommendation modules. This recommendation system uses the method of secondary clustering to efficiently screen out the test questions that can best meet the needs of users from any given questions obtained from the background of the teaching platform, and adopts a combination of multiple evaluation methods, based on answer statistics The feature can strongly represent the user's mastery of each question within a certain period of time, and the value of the feature value will be dynamically updated with the improvement of the mastery level and the improvement of the education quality. In the recommendation, the intra-class information and inter-class information in the clustering results are combined to ensure that the recommended test questions have strong representativeness. It makes up for the defects that there are too many similar questions on the auxiliary teaching platform and there is no screening mechanism for typical questions.

Description

technical field [0001] The invention relates to the fields of computer-aided teaching and data mining, in particular to a topic recommendation system based on statistical characteristics of answers. Background technique [0002] With the popularization and popularity of computer and Internet technology, the importance and necessity of online assisted teaching platform are becoming more and more obvious. Nowadays, there are many platforms, such as Homework Help, Puzzle A, Chinese University MOOC, etc., which are dedicated to the research of data-driven digital teaching personalized services, personalized intelligent guidance, etc., and generally provide fill-in-the-blank questions, multiple-choice questions, judgment questions, etc. Question type automatic judgment function. [0003] After long-term operation, some online auxiliary teaching platforms have a large number of original question banks and student practice records, and have accumulated a large amount of structured...

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): G06F16/2457G06F16/2458G06K9/62G06Q50/20G06V10/762
CPCG06F16/2457G06F16/2462G06Q50/205G06F18/23
Inventor 陈建海马万腾沈睿周瑞祺余林恩何钦铭
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