Automated Curriculum Grading via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Grading software assignments in remote learning is challenging due to subjectivity, time-consuming manual testing, plagiarism concerns, and limited feedback, making it difficult to provide consistent and accurate grades while preventing cheating.
Innovation Solution
A computer-implemented method using a machine learning system to evaluate curriculum responses and generate scores based on curriculum material, providing automated grading and feedback that prefers solutions adhering to best practices and taught techniques, with parameter randomization to prevent copying.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual grading is used to evaluate software assignments, then detailed feedback can be provided, but the process becomes time-consuming and inconsistent
Solution Approach 1:
The patent introduces an automated grading system as an intermediary between students and instructors. This system uses machine learning models trained on curriculum materials to objectively evaluate code submissions, providing consistent and accurate grading without requiring manual review of each assignment. The intermediary handles the time-consuming evaluation task while maintaining grading quality.
Solution Approach 2:
The patent replaces the mechanical process of manual code review with an automated computational system. Instead of instructors manually examining and evaluating student submissions, the system uses automated testing, static analysis, and machine learning-based assessment to evaluate assignments, dramatically reducing grading time while maintaining consistency.
2Productivity
If automated grading systems are used to reduce time consumption, then grading speed increases, but subjectivity and plagiarism detection become challenging
Solution Approach 1:
The patent creates a universal grading system that performs multiple functions simultaneously: it evaluates code functionality through automated testing, assesses adherence to curriculum standards using machine learning models, detects potential plagiarism through code comparison, and provides detailed feedback. This multi-functional approach ensures consistent and reliable grading across all assignments.
Solution Approach 2:
The system implements comprehensive feedback mechanisms that provide students with detailed information about their performance. The automated grading system doesn't just assign scores but provides specific feedback on what was correct, what needs improvement, and how the submission compares to curriculum requirements, enhancing the reliability and educational value of automated grading.
3Object-generated harmful factors
If parameter randomization is implemented to prevent copying, then plagiarism is reduced, but the complexity of assignment generation increases
Solution Approach 1:
The patent implements parameter randomization as a preliminary action in the assignment generation process. Before presenting assignments to students, the system pre-randomizes parameters such as input values, test cases, and problem specifications. This prevents students from copying exact assignments and ensures each student receives a unique version, effectively reducing plagiarism before it can occur.
Solution Approach 2:
The system dynamically changes parameters of assignments and test cases to create unique variations for different students. By modifying numerical values, input data, test scenarios, and problem constraints, the system generates infinitely varied versions of the same learning objective, making plagiarism difficult while maintaining the core educational content.
Data Source
AI summary
Disclosed embodiments provide techniques for automated evaluation and scoring of curriculum challenges such as tests and quizzes. An automated score is provided to students, as well as prescriptive guidance on where the provided solution deviates from best practices and/or the taught curriculum. Curriculum material and challenge material are input to a machine learning system to create a grading model. The challenge material can include a software programming challenge. The grading model is used to evaluate curriculum responses and provide a score and feedback based on the evaluation. The evaluation can be based on the curriculum. There can be multiple ways to solve a programming (coding) challenge and disclosed embodiments give scoring preference to solutions that employ techniques covered in the curriculum.