Metacognitive competence evaluation model based on online learning behaviors and deep neural network

A technology of deep neural network and cognitive ability, applied in the field of metacognitive ability evaluation model, can solve the problems that cannot satisfy learners' metacognitive ability precision, intelligent evaluation, lack of externalization of model building technology, metacognition It is not easy to observe and obtain problems, so as to achieve the effect of accurate metacognitive ability assessment

Active Publication Date: 2021-09-17
JIANGXI NORMAL UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Metacognition is not easy to observe and obtain, and the current research on metacognitive ability models is still a relatively new research field, basically in the theoretical research stage of the model, and there is a lack of effective model construction technology to make it explicit
Although some researchers have analyzed and studied learners' metacognitive strategies from the perspective of learning behavior analysis, they are mainly based on traditional machine learning techniques to mine behaviors, which cannot meet the needs of learners' metacognitive abilities. Accurate and intelligent evaluation of

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
  • Metacognitive competence evaluation model based on online learning behaviors and deep neural network
  • Metacognitive competence evaluation model based on online learning behaviors and deep neural network
  • Metacognitive competence evaluation model based on online learning behaviors and deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation.

[0030] Such as figure 2 As shown, the metacognitive ability evaluation model based on online learning behavior and deep neural network provided by the present invention is mainly composed of a dual-channel gated recurrent unit (BiGRU) that fuses self-attention mechanism (Self-Attention) Structure formation; this method can evaluate learners' metacognitive ability according to their online learning behavior, mainly dividing learners and metacognitive ability into those with higher metacognitive ability and those with lower metacognitive ability . Specifically, it consists of five layers of networks: input layer, vector layer, feature extraction layer, feature fusion layer and output layer. The specific implementation is as follows:

[0031] 1) Input layer: select a group of online learners, and extract the basic learning behavior...

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 metacognitive competence evaluation model based on online learning behaviors and a deep neural network. The method comprises the steps of constructing the deep neural network model; acquiring online learning behavior data and preprocessing the online learning behavior data; performing label labeling on the behavior data; training word vectors; training the deep neural network model; testing the deep neural network model; and evaluating the metacognitive competence of a learner and the like. The metacognitive competence of the learner can be evaluated automatically and intelligently based on the deep neural network model provided by the online learning behavior. Besides, an Item2Vec algorithm is adopted in the model to carry out vectorization representation on behavior sequence data, internal semantic information of the data can be reserved, metacognitive features are extracted from multiple online learning behavior data, and the metacognitive competence can be evaluated more accurately. On the basis of the method, the current metacognitive competence state of the online learner can be more accurately and intuitively represented, so that metacognition is explicated, and a guidance basis is provided for a teacher to better realize hierarchical teaching.

Description

technical field [0001] The invention belongs to the field of computer application technology, and in particular relates to a metacognitive ability evaluation model based on online learning behavior and deep neural network. Background technique [0002] Online learning has broken the inherent environment of traditional education walls and gradually developed into an important form of current education. In the online learning environment, learners and teachers are usually online asynchronously, which greatly reduces the teacher's effective supervision of learners' learning. Therefore, learners need to have a clear understanding of the individual and the environment, and be able to reasonably plan, monitor and adjust the learning process independently, so as to achieve effective online learning. Metacognition can make learners realize their own cognitive level and skill level, which is a key element for learners to carry out effective online learning. However, metacognition i...

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): G06Q10/06G06Q50/20G06N3/08
CPCG06Q10/06393G06Q50/205G06N3/08
Inventor 程艳蔡盈盈陈豪迈邹海锋
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