MOOC learner cognitive behavior recognition method based on BERT model

A recognition method, MOOC-BERT technology, applied in the direction of instruments, electrical digital data processing, calculation, etc., can solve the problems that the effect needs to be further improved, and achieve the effect of good generalization and high recognition effect

Pending Publication Date: 2021-10-15
HUAZHONG NORMAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the field of education contains a large number of abstract concepts, nouns, etc., the effect of the BERT model trained with general corpus needs to be further improved when it involves learners' cognitive behavior recognition tasks.

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
  • MOOC learner cognitive behavior recognition method based on BERT model
  • MOOC learner cognitive behavior recognition method based on BERT model
  • MOOC learner cognitive behavior recognition method based on BERT model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to more clearly illustrate the purpose, technical solution, process and advantages of the present invention, the details of the invention will be further described below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that the embodiments described here are for better explaining the present invention rather than limiting the present invention.

[0031] The embodiment described in the present invention is a BERT model-based MOOC learner cognitive behavior recognition method, combined below figure 1 The present invention is further described, which includes the following steps:

[0032] (1) Obtain large-scale learner forum discussion data from Chinese university MOOC forums to form BERT model pre-training corpus:

[0033] (1-1) The Chinese MOOC course discussion area records a large amount of text data generated when learners discuss and communicate with peers and teachers. In order to obtain the...

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 provides an MOOC learner cognitive behavior recognition method based on a BERT model, and the method comprises the steps of obtaining learner discussion text data in an MOOC forum, and generating a professional corpus in the field of MOOC comments; preprocessing the corpus, and forming pre-training data containing the professional knowledge in the MOOC field; in combination with the pre-training data, using an MLM strategy and an NSP strategy to re-train the BERT model to obtain MOOC-BERT; constructing an MOOC learner cognitive behavior annotation data set; and performing fine adjustment on parameters and weights in the MOOC-BERT by using the annotation data set, and generating a cognitive behavior recognition model oriented to the MOOC learner. The MOOC learner cognitive behavior recognition method based on the BERT model is used for improving the recognition ability of learner cognitive behaviors in an online learning environment and effectively helping teachers to analyze the cognitive behavior types of MOOC learners in a large-scale scene.

Description

technical field [0001] The invention belongs to the fields of natural language processing technology and educational data mining, and in particular relates to a method for recognizing cognitive behavior of MOOC learners based on a BERT model. Background technique [0002] Learner cognitive behavior refers to a behavior tendency abstracted from interactive discourse, which is used to represent the thinking activities in the brain during learning interaction, such as the use of cognitive skills such as analysis, disassembly, and reconstruction when solving problems . Discussion forums, instant dialogues, etc. are the main carriers to promote learners to achieve cognitive processing through collaborative discussions, and the rich cognitive behavioral information generated during the interaction process is recorded in the discussion text. By identifying and analyzing the cognitive behaviors covered in these discussion texts, teachers can better understand learners' cognitive pr...

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): G06F40/279G06F40/166
CPCG06F40/279G06F40/166
Inventor 刘智刘三女牙杨宗凯孔玺陈浩戴志诚
Owner HUAZHONG 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