Multiple-Choice Quiz Generation Using Lesson Consistency Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to generate multiple-choice quizzes that effectively include false options, making it difficult to efficiently learn from failures.
Innovation Solution
A learning support apparatus that stores failures and lessons, computes evaluation values for text inputs, and determines correct and incorrect options based on these values, allowing for the automatic creation of multiple-choice quizzes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single answer sentence is generated from a question sentence, then the system can provide a simple answer, but it cannot create effective multiple-choice quizzes with false options
Solution Approach 1:
The patent segments the lesson content into multiple candidate sentences, then evaluates and selects the most appropriate one as the correct option while others serve as false options. This segmentation allows the system to create multiple-choice quizzes from a single lesson without requiring complex manual quiz design
Solution Approach 2:
The patent introduces an evaluation value computation mechanism as an intermediary between the question sentence and the answer selection. This intermediary evaluates the consistency between the question and each candidate answer sentence, automatically determining which sentences should be correct or false options, thereby resolving the complexity of manual quiz creation
2Measurement precision
If manual creation of multiple-choice quizzes is performed, then accurate false options can be designed, but the user burden and time consumption increase significantly
Solution Approach 1:
The patent enables the system to automatically generate accurate false options by evaluating the consistency between the question sentence and candidate answer sentences. The system selects sentences with low consistency values as false options, ensuring they are plausibly related to the question but clearly incorrect, thereby maintaining accuracy while eliminating manual quiz creation time
3Ease of operation
If evaluation values are computed for all lessons against the question text, then appropriate correct and incorrect options can be determined, but the computational complexity increases
Solution Approach 1:
The patent extracts key features from both the question sentence and candidate answer sentences, then computes evaluation values based on these extracted features rather than comparing entire sentences. This extraction approach reduces computational complexity while maintaining the ability to accurately determine correct and incorrect options
Data Source
AI summary
A storage device stores failures and lessons. A processor accepts input of text serving as a question sentence in a multiple-choice quiz, computes an evaluation value for a consistency between the text and each of lessons stored in the storage device, and determines one lesson to serve as a correct option in the multiple-choice quiz and at least one lesson to serve as an incorrect option in the multiple-choice quiz, based on the evaluation value for each of the plurality of lessons computed in the computing operation.