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

Knowledge tracking method based on heterogeneous graph learning and fusion learning participation state

A heterogeneous graph and knowledge technology, applied in the field of knowledge tracking, can solve problems such as ignoring student participation status, achieve the effects of overcoming long sequence dependencies, improving efficiency, and high accuracy

Pending Publication Date: 2022-01-18
SHAANXI NORMAL UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When modeling, the above model only considers the state of students' knowledge to predict the learning effect, ignoring the crucial factor of students' participation state

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
  • Knowledge tracking method based on heterogeneous graph learning and fusion learning participation state
  • Knowledge tracking method based on heterogeneous graph learning and fusion learning participation state
  • Knowledge tracking method based on heterogeneous graph learning and fusion learning participation state

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] The knowledge tracking method based on heterogeneous graph learning fusion learning participation status of this embodiment consists of the following steps (see figure 1 ):

[0083] (1) Obtain training data set

[0084] In the public data set Assistment2009, select the students who answered more than 3 questions, and divide them into a test set and a training set. The ratio of the training set to the test set is 4:1, and the answer sequence of student i is X i for:

[0085]

[0086]

[0087] in, For student i's answer to the question at time t, is the knowledge point that student i answers the question at time t, It is student i's answer to the question at time t is correct or not, t∈[4,200], the value of t in this embodiment is 100.

[0088] (2) Construct a bipartite graph of problem knowledge points

[0089] The structure of the problem knowledge point bipartite graph G is as follows:

[0090] exist figure 2 Among them, the problem knowledge point bi...

Embodiment 2

[0149] The knowledge tracking method based on heterogeneous graph learning fusion learning participation status in this embodiment consists of the following steps:

[0150] (1) Obtain training data set

[0151] In the public data set Assistment2009, select the students who answered more than 3 questions, and divide them into a test set and a training set. The ratio of the training set to the test set is 4:1, and the answer sequence of student i is X i for:

[0152]

[0153]

[0154] in, For student i's answer to the question at time t, is the knowledge point that student i answers the question at time t, It is student i's answer to the question at time t is correct or not, t∈[4,200], the value of t in this embodiment is 4.

[0155] (2) Construct a bipartite graph of problem knowledge points

[0156] The structure of the problem knowledge point bipartite graph G is as follows:

[0157] The problem knowledge point bipartite graph G consists of the knowledge point ...

Embodiment 3

[0187] The knowledge tracking method based on heterogeneous graph learning fusion learning participation status in this embodiment consists of the following steps:

[0188] (1) Obtain training data set

[0189] In the public data set Assistment2009, select the students who answered more than 3 questions, and divide them into a test set and a training set. The ratio of the training set to the test set is 4:1, and the answer sequence of student i is X i for:

[0190]

[0191]

[0192] in, For student i's answer to the question at time t, is the knowledge point that student i answers the question at time t, It is student i's answer to the question at time t is correct or not, t∈[4,200], the value of t in this embodiment is 200.

[0193] (2) Construct a bipartite graph of problem knowledge points

[0194] The structure of the problem knowledge point bipartite graph G is as follows:

[0195] The problem knowledge point bipartite graph G consists of the knowledge point...

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 knowledge tracking method based on heterogeneous graph learning and fusion learning participation state. The method comprises the steps of obtaining a training data set, constructing a question and knowledge point bipartite graph, constructing a knowledge tracking model, generating a question tensor and a knowledge point tensor, encoding a student knowledge state, encoding a student learning participation state, predicting a student answering condition, training a model and testing the model. According to the method, adaptive heterogeneous graph learning is adopted, the length of random walk can be adaptively adjusted according to the size of the bipartite graph formed by problems and knowledge points, the efficiency of the bipartite graph is improved, and the information can be introduced more comprehensively and accurately when the knowledge state of the student is modeled. By modeling the learning participation state of the student, the modeling of the whole learning process of the student is more comprehensive, the accuracy of predicting the answering condition of the student is improved, the operation efficiency of the model is effectively improved, and the problem of long sequence dependence of the recurrent neural network is overcome.

Description

technical field [0001] The invention belongs to the field of wisdom education and education data technology, and in particular relates to a knowledge tracking method. Background technique [0002] The knowledge tracking model based on the attention mechanism overcomes the technical problems of long sequence dependence and low operational efficiency based on the cyclic neural network model. Because only the questions and the students' answers are considered when modeling the students' knowledge status, there is no simultaneous Considering the questions and the knowledge points covered by the questions, the model cannot accurately and comprehensively model the students' knowledge status, resulting in low prediction accuracy for students' answers. The pre-training method based on question graphs and knowledge point graphs makes the vector representations of questions covering the same knowledge points similar by adding constraints when training the vector representations of que...

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
CPCG06Q10/04G06Q50/205G06N3/084G06N3/047G06N3/048G06N3/045
Inventor 肖冰蒋华马君亮何聚厚
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