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

Pre-training model method for mathematical problem classification

A problem classification and pre-training technology, which is applied in the field of pre-training models for mathematical problem classification, can solve problems such as inaccurate prediction results, and achieve the effect of enhancing knowledge point representation, improving accuracy, and accurate prediction results

Pending Publication Date: 2020-08-21
浙江学海教育科技有限公司
View PDF9 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the prior art, one of the purposes of the present invention is to provide a pre-training model method for mathematical problem classification, which can solve the problem of inaccurate prediction

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
  • Pre-training model method for mathematical problem classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Such as figure 1 As shown, a pre-training model method for mathematical problem classification includes the following steps:

[0037] Construct a knowledge map of the relationship between mathematical knowledge points, and generate a knowledge point vector for each knowledge point in the knowledge map according to the relationship between each knowledge point;

[0038] Generate text vectors according to the mathematical problems in the training set and verification set respectively, import the text vectors and knowledge point vectors and build a text pre-training model, including semantic mask language model training, related question prediction model training and question relevance ranking training;

[0039] Import the test set into the pre-trained model, predict and output the processed math questions.

[0040] The invention integrates the knowledge map, and proposes a novel masking and prediction strategy to enhance the representation of knowledge points, so that th...

Embodiment 2

[0042] A pre-training model method for classification of mathematical problems, comprising the following steps:

[0043] Construct a knowledge map of the relationship between mathematical knowledge points, and generate a knowledge point vector for each knowledge point in the knowledge map according to the relationship between each knowledge point; where the knowledge map is a graph used to describe the relationship between various knowledge points , the relationship between knowledge points is represented by triples (knowledge point-relationship-knowledge point), and there are three kinds of relationships: containment, belonging, and correlation. In the knowledge graph, each node is a knowledge point, and each edge is a relationship. It can understand various relationships in practical problems from the semantic level, and the description ability is relatively strong. In order to solve multi-relational data, triplet relations in knowledge graphs can be transformed into vector ...

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 pre-training model method for mathematic problem classification, and the method comprises the following steps: constructing a knowledge graph of mathematic knowledge point relations, and generating a knowledge point vector for each knowledge point in the knowledge graph according to the relation between the knowledge points; generating text vectors according to mathematical problems in the training set and the verification set, importing the text vectors and knowledge point vectors and creating a text pre-training model, wherein the model comprises semantic mask language model training, related problem prediction model training and problem correlation sorting training; and importing the test set into a pre-training model, predicting the processed mathematical questions, and outputting a result. The knowledge graph is integrated, and a novel masking and prediction strategy is provided to enhance knowledge point representation, so that prediction effect is moreaccurate; the model uses a knowledge embedding algorithm to encode a graph structure of a knowledge graph, and multi-information embedding is used as input of the model, so that the accuracy of pre-training is greatly improved.

Description

technical field [0001] The invention relates to a mathematical problem prediction technology, in particular to a pre-training model method for classification of mathematical problems. Background technique [0002] How to teach conceptual and procedural knowledge in mathematics is a hot spot in teaching. Procedural knowledge is "learning that involves mere memory operations without understanding the underlying meaning"; conceptual knowledge is "an explicit or implicit understanding of the principles governing the domain and the interrelationships between knowledge in the domain". Based on mathematical knowledge, we can design problems based on process knowledge or concept knowledge. Therefore, in terms of teaching and learning, knowledge points have many advantages, such as developing automatic generation test systems, measuring students' learning ability or influencing practice-based mathematical knowledge teaching theory (MKT). [0003] Predicting suitable knowledge point...

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): G06F16/35G06F16/36G06Q10/04G06Q50/20
CPCG06F16/355G06F16/367G06Q10/04G06Q50/205
Inventor 王伟松于业江郑欢阮涛
Owner 浙江学海教育科技有限公司
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