Neural Network Model for User Learning Ability Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current learning ability assessment methods are costly and time-consuming due to the need for domain expert intervention and data collection in designing assessment models, especially in formative assessment systems.
Innovation Solution
A method using a neural network model trained with data from a summative assessment system to assess learning ability in a formative assessment system, eliminating the need for expert intervention and reducing data collection time by generating an answer sequence and adjusting weights based on user answers and scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If domain experts design assessment models manually and collect data through designed models, then assessment accuracy is improved, but cost and time consumption increase
Solution Approach 1:
The patent applies preliminary action by pre-training the neural network model using assessment data from a second assessment system before deploying it in the first assessment system. This pre-training phase collects and processes data in advance, so that when the model is deployed, it can immediately provide accurate assessments without requiring time-consuming data collection and model design in the target system.
Solution Approach 2:
The patent uses copying by transferring the trained neural network model from the second assessment system to the first assessment system. Instead of manually designing and training a new model in each system, the assessment capability is copied through the trained model, which can then be applied to different assessment contexts with minimal additional data collection.
2Reliability
If domain experts design assessment models manually, then assessment reliability is improved, but cost increases
Solution Approach 1:
The patent replaces the mechanical system of manual expert model design with an automated neural network-based system. The neural network automatically learns assessment patterns from training data, substituting the need for domain experts to manually design assessment models, thereby reducing costs while maintaining or improving reliability through data-driven insights.
Solution Approach 2:
The neural network model performs self-service by automatically training itself on assessment data from the second assessment system and then autonomously providing assessment capabilities in the first assessment system. This self-training and self-deployment process eliminates the need for continuous expert intervention, reducing costs while maintaining reliability.
3Productivity
If neural network is trained with data from second assessment system, then productivity is improved, but data quality transferability becomes challenging
Solution Approach 1:
The patent applies parameter changes by adapting the neural network model's parameters and weights when transferring from the second assessment system to the first assessment system. The model's internal parameters are adjusted to accommodate differences in data characteristics between the two systems, enabling efficient productivity improvement while maintaining data quality transferability through parameter optimization.
Data Source
AI summary
Provided are a method of training a neural network for calculating a learning ability and a method of calculating a user's learning ability. The method of training a neural network includes acquiring an assessment database including data, which includes question information answered by a user at a second time point earlier than a first time point, the user's answer information to the question information, and the user's score information in a second assessment system, acquired from the second assessment system different from a first assessment system, generating an answer sequence from the assessment database by matching the answer information with the score information to prepare a training set, preparing a neural network for calculating the user's score information in the second assessment system on the basis of the answer information in the second assessment system, and training the neural network with the training set.