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

Model detection method based on deep learning student online learning efficiency prediction

A model detection and deep learning technology, which is applied in the field of model detection for students' online learning efficiency prediction, can solve problems such as time lag, and achieve the effect of simple method, fast operation speed, and simplified construction steps

Active Publication Date: 2021-07-16
SHAANXI NORMAL UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the learning quality results obtained through examinations are very lagging in terms of time.

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
  • Model detection method based on deep learning student online learning efficiency prediction
  • Model detection method based on deep learning student online learning efficiency prediction
  • Model detection method based on deep learning student online learning efficiency prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Taking 1000 images from the image database as an example, the model detection method based on deep learning students' online learning efficiency prediction of this embodiment consists of the following steps (see figure 1 ):

[0034] (1) Obtain raw data and features

[0035] Take 1000 images from the image library and divide them into training set and test set, of which 700 are training sets and 300 are test sets. The convolutional neural network model is trained, and the test set is used for testing. After the test, the feature set and feature set are obtained. Add the state label as the Bayesian training set, put the Bayesian training set into the naive Bayesian model, obtain the state prediction model, intercept the user's use image, convert it into a picture set by frame, and use the convolutional neural network to obtain the user's image The eigenvector F, the eigenvector F is F 1 , F 2 , F 3 , F 4 , F 5 , F 6 A collection of vectors, that is, F ∈ {F 1 , F ...

Embodiment 2

[0058] Taking 1000 images from the image library as an example, the model detection method based on deep learning students' online learning efficiency prediction in this embodiment consists of the following steps:

[0059] (1) Obtain raw data and features

[0060] This step is the same as in Example 1.

[0061] (2) Determine the student's learning status

[0062] This step is the same as in Example 1.

[0063] (3) Determine the action state trajectory sequence

[0064] Connect the states at each moment by moment to obtain the state sequence of each action. The state sequence is:

[0065]

[0066] Among them, S∈{S 1 , S 2 ,...,S n} is the state, A∈{A 1 、A 2 ,...,A m} is an action, n and m are finite positive integers, the value of n in this embodiment is 32, and the value of m is 5, the described actions are: talking, yawning, not looking at the screen, closing eyes, sitting Not correct.

[0067] Other steps are the same as in Example 1.

[0068] Complete the mod...

Embodiment 3

[0070] Taking 1000 images from the image library as an example, the model detection method based on deep learning students' online learning efficiency prediction in this embodiment consists of the following steps:

[0071] (1) Obtain raw data and features

[0072] This step is the same as in Example 1.

[0073] (2) Determine the student's learning status

[0074] This step is the same as in Example 1.

[0075] (3) Determine the action state trajectory sequence

[0076] Connect the states at each moment by moment to obtain the state sequence of each action. The state sequence is:

[0077]

[0078] Among them, S∈{S 1 , S 2 ,...,S n} is the state, A∈{A 1 、A 2 ,...,A m} is an action, n and m are finite positive integers, the value of n in this embodiment is 64, and the value of m is 5, the described actions are: talking, yawning, not looking at the screen, closing eyes, sitting Not correct.

[0079] Other steps are the same as in Example 1.

[0080] Complete the mod...

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 model detection method based on deep learning student online learning efficiency prediction. The method comprises the steps of obtaining original data and features, determining a student learning state, determining an action state track sequence, constructing a Markov decision process model, generating a PRISM code, determining action state transition and processing a migration action result. In the construction of the Markov decision process model, the transition probability Pi, j is used to construct the Markov decision process model, so that the construction steps are simplified, the complex calculation process is reduced, and the operation speed is improved; the Markov decision process model detection is used for student online learning efficiency prediction, so that the change of the learning efficiency of students can be accurately predicted. The method has the advantages of being simple, high in operation speed and the like, and can be used for predicting the online learning efficiency of students in network education.

Description

technical field [0001] The invention belongs to the field of model detection in computer technology, and in particular relates to a model detection method for predicting students' online learning efficiency based on deep learning. Background technique [0002] In the online learning industry, the most important thing is to evaluate the quality of students' learning. Existing software mainly uses exams to evaluate the quality of students' learning. However, the learning quality results obtained through examinations lag behind in terms of time. Therefore, there is a need for real-time assessment of learning quality methods to improve the educational quality and student acceptance of online education. [0003] At present, many schools choose online teaching, and the effect of online learning is uneven. It is necessary to use the prediction method of students' online learning efficiency to improve the learning quality of students' online learning. Contents of the invention ...

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): G06K9/62G06K9/00G06Q10/04G06Q10/06G06Q50/20
CPCG06Q10/04G06Q10/06395G06Q50/205G06V40/20G06V20/53G06F18/24155G06F18/214
Inventor 雷丽晖李梦洋
Owner SHAANXI NORMAL 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