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

Student class termination prediction method based on Attention deep learning model

A technology of deep learning and prediction methods, which is applied in neural learning methods, predictions, biological neural network models, etc., and can solve problems such as low accuracy

Active Publication Date: 2020-06-16
GUILIN UNIV OF ELECTRONIC TECH
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a student dropout prediction method based on the Attention deep learning model, aiming to solve the problem of low accuracy of the traditional dropout prediction method

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
  • Student class termination prediction method based on Attention deep learning model
  • Student class termination prediction method based on Attention deep learning model
  • Student class termination prediction method based on Attention deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0041] see figure 1 , figure 1 It is a schematic flowchart of a student dropout prediction method based on the Attention deep learning model provided by the present invention. Specifically, the student dropout prediction method based on the Attention deep learning model may include the following steps:

[0042] S101. Obtain a dataset of original online learning behavior-related data for screening and preprocessing;

[0043] In the embodiment of the present invention, please refer to figure 2, to obtain the dataset of the KDD...

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 student class stop prediction method based on an Attention deep learning model, and the method comprises the steps: carrying out the coding and time window score processing of a behavior record, and generating a plurality of time slice behavior vector matrixes; processing the plurality of time slice behavior vector matrixes based on an improved convolution layer of the CNN network to obtain a plurality of feature vector matrixes with a local association relationship; based on a BI-GRU model, carrying out feature extraction of time series features on the plurality of feature vector matrixes with the local association relationship to generate a plurality of behavior feature vector matrixes with the time series relationship; and giving different weights to the hiddenlayer features at each moment based on an Attention mechanism, performing weighted summation on the hidden layer states and the weights at different moments to generate a behavior feature representation vector, inputting the behavior feature representation vector into a classification layer, and performing prediction through a Sigmoid function to obtain a prediction result. By considering the relationship between the learning behaviors of the students and the degree of influence of different behavior characteristics on class termination prediction, prediction is realized, and the precision ofclass termination prediction is improved.

Description

technical field [0001] The invention relates to the technical fields of machine learning, deep learning and data mining, in particular to a method for predicting student dropouts based on an Attention deep learning model. Background technique [0002] With the rapid development of the Internet, the education model has begun to change, and more and more different groups of people have different needs for education quality and educational content. Therefore, a large number of online course learning platforms have emerged as the times require. MOOC, a large-scale online learning platform, has appeared since 2012, including famous schools from all over the world publishing courses on MOOC. The learning platform transcends the limitations of time, space and even identity. Anyone who is willing to learn, regardless of their profession, can register for online learning through a registered account. However, this also brings serious problems. The dropout rate is very high, as high a...

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): G06Q10/04G06Q50/20G06N3/04G06N3/08
CPCG06Q10/04G06Q50/205G06N3/08G06N3/045
Inventor 常亮张艳刘铁园古天龙
Owner GUILIN UNIV OF ELECTRONIC TECH
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