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

Automatic labeling method and device for mathematic question knowledge points

A technology of knowledge points and mathematics, applied in the field of teaching, can solve problems such as the inability to automatically mark knowledge points in test questions, achieve the effect of eliminating manual marking work, realizing intelligence, and improving work efficiency and accuracy

Inactive Publication Date: 2018-06-19
谢德刚
View PDF4 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Embodiments of the present invention provide a method and device for automatically labeling knowledge points of math test questions based on deep learning technology, with the purpose of solving the problem that the existing math test bank cannot automatically mark knowledge points for test questions

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
  • Automatic labeling method and device for mathematic question knowledge points
  • Automatic labeling method and device for mathematic question knowledge points
  • Automatic labeling method and device for mathematic question knowledge points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Example as figure 1 As shown, an automatic labeling method for mathematical knowledge points based on deep learning includes the following steps:

[0027] S1: Prepare a training sample set with knowledge points marked, and preprocess the mathematical text;

[0028] S2: Prepare the corpus in the field of mathematics, train the word vectors in the field of mathematics according to the character level and word level respectively, and save the result as a dictionary form of {word / character: word vector}, which will be used for future training of the neural network model; S3: Build two layers of TextCNN Neural network model, input the labeled training sample set, and train the model.

[0029] The specific work includes model framework design. The present invention uses a two-layer TextCNN network with a structure of word embedding-convolution-pooling-convolution-pooling-dropout. Among them, multiple convolution kernels with different fields of view are designed to collect ...

Embodiment 2

[0038] An automatic labeling method for mathematical knowledge points based on deep learning, including:

[0039] S1: Mathematics text preprocessing, respectively standardize, word segmentation and stop word processing;

[0040] S2: Prepare the corpus in the field of mathematics, and train word vectors in the field of mathematics according to the character level and word level respectively;

[0041] S3: Build a two-layer TextCNN neural network model, input a labeled training sample set, and train the model;

[0042] The step S1 specifically includes the following steps:

[0043] S11: Standardize the mathematical text, mainly for text normalization and synonym replacement. For example: "image" is replaced with "image", "°|circ|degree" is replaced with "degree", " / / |parallel" is replaced with "parallel", etc. To remove stop words is to remove high-frequency and meaningless words, such as "的", ",", "!", "\" and so on.

[0044] S12: Use tf-idf to filter keywords for each type ...

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

Disclosed is an automatic labeling method for mathematic question knowledge points. The labeling method is based on a depth learning model. The labeling method comprises the steps of S1, preprocessinga mathematic question text, wherein standardization, word segmentation and stop word removal processing are performed separately; S2, preparing a mathematic field corpus, and training a mathematic field word vector according to the character level and the word level; S3, setting up a two-layer Text CNN neural network model, inputting a mathematic question training sampling set with labels, and training the neural network model. The knowledge points of mathematic question in a novel question bank can be automatically labeled by means of the model.

Description

technical field [0001] The invention belongs to the field of teaching technology, in particular to a method and device for automatically marking knowledge points of mathematics test questions. Background technique [0002] With the continuous development of artificial intelligence technology, deep learning is increasingly being used in speech recognition, image recognition, natural language processing and other aspects. The concept of deep learning originated from the research of artificial neural networks, and the multi-layer perceptron with multiple hidden layers is a deep learning structure. The deep learning framework can learn the underlying data feature representation, so as to find the intrinsic relationship between the feature data and the target data. In the field of Internet education, the establishment and maintenance of online question bank is the "cornerstone". In the process of entering the new question catalog into the question bank, it relies on manual entr...

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
IPC IPC(8): G06F17/27G06F17/30
CPCG06F16/35G06F40/242G06F40/289
Inventor 谢德刚姚志峰
Owner 谢德刚
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