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

Intelligent marking method for computational analysis type non-choice questions

A multiple-choice, intelligent technology, applied in computing, data processing applications, instruments, etc., can solve problems such as not given, unable to verify the correctness of complex calculation expressions, etc., to increase accuracy, eliminate manual marking bias, and easy to explain sexual effect

Active Publication Date: 2021-01-15
山东山大鸥玛软件股份有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for calculation and analysis problems that contain calculation expressions, deep learning models are not the only choice. Currently, deep learning models cannot verify the correctness of complex calculation expressions.
Calculation and analysis questions cannot be judged solely by the calculation results. For example, the calculation expression in the candidate's answer is correct, but the test taker did not give the calculation result. According to the scoring rules, such cases may get some points. The unit of the calculation result is inconsistent with the unit of the calculation result in the reference answer. At this time, a unit conversion is required. This type of unit conversion requires prior knowledge

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
  • Intelligent marking method for computational analysis type non-choice questions
  • Intelligent marking method for computational analysis type non-choice questions
  • Intelligent marking method for computational analysis type non-choice questions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Specific embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0049] Such as figure 1 An intelligent marking method for calculation and analysis non-choice questions is shown, including the following steps:

[0050] S1: Perform text processing on the reference answer text and the examinee answer text.

[0051] For each character in the reference answer text and the examinee’s answer text, convert rounded characters into half-width characters, convert Chinese symbols in mathematical expressions into English symbols, and convert percent values ​​into decimal values.

[0052] S2: Extract structured information from the reference answer text and set scoring rules to form an answer template.

[0053] First of all, it needs to be explained that the calculation steps of the calculation and analysis non-choice questions in this embodiment adopt the form of structured information, and the form of structured information is ...

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 test paper marking method for computational analysis type non-selective questions. The method comprises the steps: carrying out text preprocessing on a referenceanswer text and an examinee answer text; performing structured information extraction on the reference answer text and setting a score rule to form an answer template; performing structured information extraction on the examinee answers to form alternative answers; and scoring the alternative answers based on the answer template, and summarizing scores of the alternative answers according to the calculation steps to form scoring data. According to the invention, automatic paper marking of computational analysis questions can be achieved, manual paper marking deviation is eliminated, and the paper marking efficiency is greatly improved.

Description

technical field [0001] The invention relates to the technical field of examination evaluation, and more specifically relates to an intelligent marking method for calculation and analysis non-choice questions. Background technique [0002] In recent years, with the development of natural language processing, computer-aided intelligent marking technology based on deep learning has become a research hotspot in the field of examination evaluation. However, for calculation and analysis topics that contain calculation expressions, deep learning models are not the only choice. Currently, deep learning models cannot verify the correctness of complex calculation expressions. Calculation and analysis questions cannot be judged solely by the calculation results. For example, the calculation expression in the candidate's answer is correct, but the test taker did not give the calculation result. According to the scoring rules, such cases may get some points. The unit of the calculation ...

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): G06Q10/06G06F40/194G06F40/289G06F40/205G06F40/151
CPCG06Q10/06393G06F40/194G06F40/289G06F40/205G06F40/151
Inventor 马磊郭成锋袁峰薛勇张宝京
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