An automatic scoring method for programming questions based on machine learning

A machine learning and automatic scoring technology, applied in software testing/debugging, etc., can solve problems such as the non-unique influence of model programs and increase the workload of teachers, and achieve the effect of high practicability and saving teaching resources

Active Publication Date: 2021-03-30
SOUTH CHINA UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This increases the workload of teachers, and the non-uniqueness of the model program has a certain impact on the similarity comparison results

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
  • An automatic scoring method for programming questions based on machine learning
  • An automatic scoring method for programming questions based on machine learning
  • An automatic scoring method for programming questions based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with specific examples.

[0036] like figure 1 As shown, the machine learning-based automatic scoring method for program questions provided in this embodiment includes the following steps:

[0037] 1) Obtain student program coursework data, including student homework and homework score information; the student homework refers to the student homework obtained from the programming course of the online learning platform; the homework score information refers to the online learning platform. A course teacher or teaching assistant gives a grade for judging assignments submitted by students.

[0038] 2) Perform data preprocessing on the acquired homework, specifically, use text processing technology for the program homework submitted by the students to remove comments and parts that have nothing to do with the program structure.

[0039] 3) Dynamically test the program, enter the program questions into the...

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 an automatic program question scoring method based on machine learning, which comprises the following steps: 1) acquiring student program course homework data including studenthomework and homework score information; 2) carrying out data preprocessing on the obtained operation; 3) carrying out dynamic testing on the program; 4) extracting program characteristics; 5) applying a machine learning algorithm to perform static analysis on the program; And 6) integrating dynamic operation and static analysis results, and returning a final score of the program. According to the method, dynamic testing and static analysis are combined, that is, dynamic testing data of the program are used, and the program is analyzed; A machine learning algorithm is adopted for static analysis, a teacher does not need to provide a correct reference program for similarity comparison, the teaching burden is reduced, and the influence of non-uniqueness of a template program on a correctionresult is avoided; Static analysis is carried out on all programs, and the misjudgment phenomenon caused by the fact that all dynamic tests pass but programs are not compiled according to topic requirements is reduced.

Description

technical field [0001] The present invention relates to the technical field of automatic grading of procedural questions, in particular to an automatic grading method for procedural questions based on machine learning. Background technique [0002] In the teaching of computer programming courses, grading program questions is a complex, non-mechanical and time-consuming process. With the development of online learning platforms such as MOOC, how to efficiently, quickly and automatically grade and give feedback to the assignments submitted by students in computer programming related courses has become a hot spot that has attracted much attention. [0003] Currently, there are two common types of scoring methods: 1) Dynamic testing: run the program to be corrected, and use dynamic testing if it can be compiled, and return zero points directly if it cannot be compiled. The dynamic testing process requires a set of test cases that are as complete as possible, including input tes...

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 Patents(China)
IPC IPC(8): G06F11/36
Inventor 张凌张美丽
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products