ML-Based Course Objective Generation and Presentation Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Instructors face challenges in efficiently generating course learning objectives from course text content and evaluating student presentations against these objectives, leading to time-consuming and inconsistent results.
Innovation Solution
Utilizing a language model with task-specific prompting, including zero-shot template-based prompting, to analyze course text content and generate course learning objectives, and to evaluate student presentations against these objectives, thereby producing competency scores with supportive reasoning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual review and assessment of course text content is used to generate course learning objectives, then instructors can develop customized learning objectives, but the process becomes time consuming and leads to inconsistent results across student populations
Solution Approach 1:
The patent introduces machine learning models as an intermediary between course text content and learning objective generation. The ML models automatically analyze course materials and generate standardized learning objectives, eliminating the need for manual instructor review while ensuring consistent application across all courses and student populations.
Solution Approach 2:
The patent replaces the mechanical manual process of instructor review and assessment with automated machine learning-based systems. The ML models perform text analysis, learning objective generation, and presentation scoring automatically, substituting human manual labor with computational processes that provide consistent and reliable results.
2Productivity
If manual assessment of course text content is used to derive course learning objectives, then instructors can exercise judgment and adaptability, but the process is time consuming and variable based on the person performing the assessment
Solution Approach 1:
The patent introduces machine learning models as an intermediary between course text content and learning objective generation. The ML models automatically analyze course materials and generate standardized learning objectives, eliminating the need for manual instructor review while ensuring consistent application across all courses and student populations.
Solution Approach 2:
The patent transforms the assessment process from a human-centric variable process to a standardized computational process. By changing the parameters of assessment from human judgment (which varies by individual) to machine learning model parameters (which can be standardized and replicated), the system achieves both high productivity and reliable consistency.
3Measurement precision
If machine learning is used to generate course learning objectives and evaluate presentations, then time spent by instructors is reduced and accuracy is enhanced, but the system complexity increases
Solution Approach 1:
The patent creates a universal machine learning system that performs multiple functions: analyzing course text content, generating learning objectives, evaluating student presentations, and providing scoring. This multi-functional approach consolidates what would otherwise require separate systems into a single unified platform, managing complexity while delivering comprehensive automated assessment capabilities.
Data Source
AI summary
A computing device and methods of making and using a computing device having machine learning capabilities to analyze course text content based on prompting to generate a list of course learning objectives, and in particular embodiments, having machine learning capabilities to analyze presentation content text against each of the course learning objectives to generate a course competency score with supportive reasoning for each course learning objective and an overall presentation score.