Learning Material Recommendation via Concentration and Comprehension
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing learning material recommendation methods fail to accurately recommend the next learning material for learners based on their comprehension and concentration degree, as high comprehension may indicate either optimal or easy material, and low comprehension may indicate low motivation or difficulty.
Innovation Solution
A learning material recommendation method and device that estimate a learner's concentration degree using learner and learning material data, and select the next material based on the specified learning state, adjusting the difficulty level accordingly to improve motivation and comprehension.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If learning material recommendation is based only on comprehension measurement, then the recommendation system is simple to implement, but it cannot distinguish whether high comprehension indicates optimal or easy material, and cannot distinguish whether low comprehension indicates difficulty or low motivation
Solution Approach 1:
The patent combines multiple measurement dimensions (comprehension, concentration degree, and their interaction) into a unified learning state assessment system. By merging these measurements and analyzing their relationships, the system can distinguish between different learning scenarios (e.g., high comprehension with high concentration indicates optimal material, while high comprehension with low concentration may indicate easy material), thereby improving measurement precision without excessively increasing system complexity.
Solution Approach 2:
The system implements feedback mechanisms that continuously monitor both comprehension and concentration degree, then use this feedback to adjust learning material recommendations. The feedback loop allows the system to learn from patterns in the data and improve its ability to distinguish between different learning states over time, enhancing measurement precision through iterative refinement.
2Productivity
If the system recommends learning material based on high comprehension alone, then the recommendation process is simple, but it may recommend difficult material to learners who are actually motivated but struggling, or easy material to learners who are disengaged
Solution Approach 1:
The patent introduces dynamic adjustment of learning material difficulty based on the interplay between comprehension and concentration degree. Rather than using static recommendation rules, the system dynamically adapts recommendations by analyzing how these two metrics interact, allowing it to respond appropriately to different learner states and improve recommendation accuracy while maintaining efficiency.
Solution Approach 2:
The system changes the parameters used for recommendation from a single comprehension metric to a multi-parameter model that includes both comprehension and concentration degree. By changing these parameters and analyzing their relationships, the system can more accurately determine the appropriate difficulty level for recommended materials, improving reliability without significantly reducing productivity.
3Device complexity
If the system tracks only comprehension through tests and questionnaires, then the data collection process is simple, but it loses valuable information about learner engagement and motivation that could improve recommendations
Solution Approach 1:
The patent makes the learning management system multi-functional by integrating concentration degree measurement capabilities alongside existing comprehension assessment functions. This universal approach allows the system to collect both types of data through a unified platform, reducing the need for separate specialized systems and minimizing the increase in device complexity while preventing information loss.
Solution Approach 2:
The system implements self-service mechanisms for data collection, such as automated concentration monitoring through interaction patterns and optional self-reporting by learners. These self-service approaches reduce the burden on instructors and system administrators, keeping the data collection process relatively simple while still gathering valuable engagement information that would otherwise be lost.
Data Source
AI summary
A learning material recommendation device recommends a learning material that should be learned next by a learner on the basis of the learner's comprehension and concentration degree. The learning material recommendation device includes estimation means for estimating a concentration degree indicating the degree of concentration of a learner on a learning material, on the basis of learner data including a feature related to the learner and learning material data including a feature related to the learning material, and learning material selection means for selecting one from among next learning material candidates associated with the learning material, on the basis of a learning state that is specified on the basis of the concentration degree and a comprehension of the learning material by the learner.