User Proficiency Prediction via Similar User Intermediaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing learning systems struggle to accurately determine the difficulty level of questions for users based on their proficiency, relying on analysis of given questions which may not reflect the user's true learning level.
Innovation Solution
An information processing apparatus identifies similar users based on question-giving history and correctness determination results to derive the correct answer probability for not-yet-given questions, allowing for the selection of questions tailored to the user's learning level.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system analyzes user understanding based on given questions to predict correct answer probability, then the learning level can be judged, but the accuracy of difficulty level determination deteriorates because the analyzed questions may not reflect the user's true learning level
Solution Approach 1:
The patent introduces similar users as intermediaries to bridge the gap between the target user's limited question history and accurate proficiency assessment. By using correctness determination results from similar users who have answered the same questions, the system obtains more reliable proficiency indicators without directly analyzing the target user's limited performance data.
Solution Approach 2:
The patent copies correctness determination results from similar users to predict the target user's correct answer probability. Instead of relying solely on the target user's own answer history, the system replicates proficiency indicators from users with similar characteristics, thereby improving measurement accuracy when the target user's data is insufficient.
2Measurement precision
If the system uses correctness determination results from similar users to derive correct answer probability, then the accuracy of predicting user proficiency improves, but the complexity of the system increases due to additional user matching and data processing
Solution Approach 1:
The patent performs preliminary actions by pre-identifying similar users and storing their correctness determination results before the actual proficiency assessment is needed. This advance preparation reduces the computational burden during real-time operation, as the system can directly query pre-processed data rather than performing complex matching and analysis on-demand.
Solution Approach 2:
The system makes the complexity of finding and analyzing similar users' performance data transparent to the end user. The automated matching and probability derivation processes serve themselves without requiring user intervention, thereby managing system complexity internally while maintaining simple user interaction.
Data Source
AI summary
An information processing apparatus includes at least one processor. The processor is configured to, based on question-giving history information on questions, identify, among users, a similar user who is similar to a target user among the users in proficiency tendency of the questions. The question-giving history information includes results of determination as to whether the users have correctly answered given questions that have been given to the users. The processor is further configured to derive a probability of the target user correctly answering a question as a deriving target question among the questions, based on a result of determination as to whether the similar user has correctly answered the deriving target question. The deriving target question is a question for which the probability is derived, and is a given question for the similar user. The processor is further configured to perform a specific process based on the derived probability.