Learning Support Apparatus Using Viewing Time Weighted Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current English learning assistance systems fail to effectively check comprehension of unhighlighted learning targets, as they only provide support for highlighted portions, leaving overlooked material unchecked.
Innovation Solution
A system that records and analyzes learning history data to identify unhighlighted learning targets by calculating occurrence ratios and generating tailored confirmation questions based on viewing times and frequencies, ensuring comprehensive assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If confirmation questions are designed to be used by many children/students simultaneously, then the system can serve multiple learners, but the questions cannot be customized for individual learning states
Solution Approach 1:
The system performs preliminary analysis of learning history data before generating confirmation questions. By pre-processing viewing time records and identifying unhighlighted learning targets in advance, the system can create personalized questions without complex real-time processing, thus achieving customization while controlling system complexity
Solution Approach 2:
The system automatically generates personalized confirmation questions by analyzing each learner's own viewing history and highlighting patterns. The learner's interaction data serves as the input for generating their specific assessment questions, eliminating the need for manual question customization while achieving individualization
2Reliability
If questions are too easy, then learners can answer correctly, but motivation and confidence in teaching materials decrease
Solution Approach 1:
The system creates confirmation questions with locally optimized difficulty for each learner by analyzing their specific viewing patterns and highlighting behavior. Questions focus on unhighlighted portions that represent the learner's actual knowledge gaps, ensuring each question has appropriate difficulty tailored to that individual's learning state
Solution Approach 2:
The system dynamically adjusts question parameters including difficulty level, topic selection, and question type based on analyzed learning history data. By changing these parameters according to individual viewing times and highlighting patterns, the system maintains optimal challenge levels that preserve both assessment accuracy and learner motivation
3Measurement precision
If questions are too difficult, then learners may memorize answers without understanding, but comprehension cannot be properly assessed
Solution Approach 1:
The system uses learning history data as feedback to create appropriately-difficulty confirmation questions. By analyzing what portions learners chose to highlight versus overlook, the system infers comprehension levels and generates questions that truly test understanding rather than memorization, maintaining measurement precision while preventing answer guessing
Solution Approach 2:
The system focuses confirmation questions on specific unhighlighted portions rather than covering all material. This partial action approach concentrates assessment on the most critical knowledge gaps identified through learning history analysis, ensuring comprehensive comprehension checking without overwhelming learners with excessive difficult questions
4Productivity
If the system only provides support for highlighted portions, then it can focus on learner-identified important material, but overlooked portions remain unchecked
Solution Approach 1:
Instead of only assessing highlighted portions as traditional systems do, the patent inverts the approach by identifying and assessing unhighlighted portions. The system uses the absence of highlighting as the key indicator for generating confirmation questions, thereby checking comprehension of overlooked material that would otherwise remain unassessed
Solution Approach 2:
The system segments the learning material into highlighted and unhighlighted portions, then applies different assessment strategies to each segment. By separating the treatment of these two types of portions and focusing confirmation questions specifically on unhighlighted areas, the system achieves both efficient use of learner-identified priorities and comprehensive coverage of all learning targets
Data Source
AI summary
Provided is a learning assistance technology that uses a learning history to check the level of comprehension by a learner in relation to a learning target. Included are a score calculation unit that uses a first occurrence ratio α(n) of a learning target Q(n) calculated using an occurrence frequency R(n) of the learning target Q(n) in a document to be used as a basis for creating a confirmation question and a second occurrence ratio β(n) of the learning target Q(n) weighted by viewing time and calculated using the occurrence frequency R(n) of the learning target Q(n) and a viewing time for each page of the document included in a learning history to calculate one of the difference between the first occurrence ratio α(n) and the second occurrence ratio β(n), the absolute value of the difference, or the ratio as a score S(n) of the learning target Q(n), and a query generation unit that treats the learning target Q(n) corresponding to the n for which the score S(n) is maximized as a query, that is, the learning target with which to create a confirmation question for a learner.