Area-Adaptive Learning Model Updates for Mobile Equipment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Learning models mounted on mobile or portable equipment, such as vehicles and smartphones, lose precision when used in areas different from their usual usage areas, as they are optimized for specific properties and lack training data from other regions.
Innovation Solution
A learning apparatus and model learning system that enables communication between equipment and a server, allowing the server to relearn the learning model using training data sets acquired in the new area when the equipment is used outside its usual area, ensuring the model remains precise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a learning model is optimized for a specific usage area using training data from that area, then the precision of the learning model is improved in that area, but the precision deteriorates when the equipment is used in a different area
Solution Approach 1:
The learning model is made dynamic by enabling it to be relearned and updated based on the current usage area. The system detects when equipment moves to a different area and triggers relearning with local training data, allowing the model to adapt its parameters dynamically rather than remaining static
Solution Approach 2:
The system changes the parameters of the learning model by relearning with area-specific training data. When equipment is used in a different area, the training data and model parameters are updated to reflect the new area's characteristics, thereby maintaining precision across different locations
2Measurement precision
If training data is collected specifically for each usage area, then the precision of the learning model in that area is improved, but the complexity of the system increases
Solution Approach 1:
A server acts as an intermediary to manage the complexity of collecting, storing, and managing training data from multiple usage areas. The server centralizes these functions, allowing individual equipment to benefit from area-specific training data without each device needing to independently manage the complex data infrastructure
Solution Approach 2:
The server provides universal functionality by serving multiple equipment across different usage areas. It consolidates the function of data collection, storage, and model relearning into a single multi-functional system that benefits all connected equipment regardless of their specific usage areas
Data Source
AI summary
A learning apparatus configured to be able to communicate with a plurality of equipment in which learning models are mounted, wherein when first equipment among the plurality of equipment in which a learning model trained using training data sets acquired in a predetermined first area is mounted and which is controlled by the same is used in a predetermined second area, the learning apparatus uses training data sets acquired in the second area to relearn the learning model mounted in the first equipment.