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

Subjective question intelligent marking method, system and device based on transfer learning

A technology of transfer learning and subjective questions, applied in the field of educational examination evaluation, to achieve the effect of highlighting substantive features, increasing diversity, and good explanatory

Active Publication Date: 2021-01-08
山东山大鸥玛软件股份有限公司
View PDF13 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the object of the present invention is to provide a method, system and equipment for intelligent marking of subjective questions based on transfer learning, which can solve the problem of small-sample learning. The intelligent marking system constructed according to the method of the present invention has high accuracy. rate and high review efficiency, while having a certain degree of interpretability

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
  • Subjective question intelligent marking method, system and device based on transfer learning
  • Subjective question intelligent marking method, system and device based on transfer learning
  • Subjective question intelligent marking method, system and device based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060]The specific embodiments of the present invention will be described below in conjunction with the drawings.

[0061]Such asfigure 1 The intelligent marking method for subjective questions based on transfer learning shown here includes the following steps:

[0062]S1: Based on the occlusion language model, construct a semantic feature extraction network, and use self-supervised learning to pre-train the semantic feature extraction network.

[0063]Specifically, S1 includes the following steps:

[0064]S11: Unsupervised task modeling. The self-supervised learning task is constructed by occluding some words in the text data and predicting the occluded words.

[0065]S12: Neural network model design. It is preferable to adopt a multi-head self-attention mechanism network model as the backbone layer of the semantic feature extraction network. The model includes an input layer, a word embedding layer, a position embedding layer, a semantic feature extraction layer, and a classification prediction ...

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 provides an intelligent subjective question marking method, system and device based on transfer learning, and the method comprises the steps: constructing a semantic feature extraction network based on an occlusion language model, and carrying out pre-training of the semantic feature extraction network in a self-supervised learning mode; constructing a multi-score evaluation model onthe basis of the pre-trained semantic feature extraction network, selecting examinee data evaluated by experts, and performing supervised fine adjustment training on the multi-score evaluation model;and scoring the examinee data to be scored by using the multi-score-point scoring model after fine adjustment training. According to the method, the problem of small sample learning can be solved, and the intelligent marking system constructed according to the method has high accuracy, high marking efficiency and certain interpretability.

Description

Technical field[0001]The invention relates to the technical field of educational examination evaluation, and more specifically to a method, system and equipment for intelligently marking subjective questions based on transfer learning.Background technique[0002]In recent years, with the development of natural language processing, computer-assisted intelligent marking technology based on deep learning has become a research hotspot in the field of educational examination evaluation. Computer-aided intelligent marking technology is the use of computer technology to evaluate and score candidates' answers. Compared with manual marking, computer-aided intelligent marking technology has obvious advantages. First of all, the reproducibility, consistency, and objectivity of the marking process. There are no physiological factors in the computer system. On the one hand, it avoids the negligence caused by fatigue, and on the other hand, it avoids the deviation caused by different personal cogni...

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): G06F16/33G06N3/04G06N3/08
CPCG06F16/334G06N3/084G06N3/045
Inventor 马磊郭成锋袁峰薛勇韩百龙
Owner 山东山大鸥玛软件股份有限公司
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