Learning Apparatus for Multi-Format Device Data Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current machine learning models require separate learning and estimation processes for different device types due to varying data formats, limiting the use of collected data for a single model.
Innovation Solution
A learning apparatus and method that acquires first-type device data, generates second-type device data with a different format, and performs learning on both models, enabling estimation using the second-type device data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If separate learning processes are performed for each device type, then estimation accuracy for specific device data is improved, but system complexity and data utilization efficiency deteriorate
Solution Approach 1:
The patent creates a universal learning system where a single learning apparatus can process multiple device types through data format conversion. The generating section converts first-type device data into second-type device data, allowing one model to serve multiple device types, thereby reducing system complexity while maintaining estimation accuracy through unified processing
Solution Approach 2:
The generating section acts as an intermediary that bridges different device data formats. It converts first-type device data into the format required by the second model, enabling seamless integration of multiple data sources without requiring separate learning processes for each device type
2Adaptability or versatility
If data format conversion is performed, then data utilization from multiple devices is improved, but processing complexity increases
Solution Approach 1:
The system performs preliminary data format conversion by generating second-type device data from first-type device data before model processing. This advance preparation ensures that data from multiple devices can be uniformly processed, improving adaptability while managing processing complexity through structured conversion operations
Solution Approach 2:
The generating section changes data format parameters by converting first-type device data into second-type device data. This parameter transformation enables diverse device data to be processed by unified models, enhancing data utilization across different device types through systematic format standardization
Data Source
AI summary
There are provided a learning apparatus, a learning method, and a program that enable, by using one type of device data, learning of a plurality of models using different data formats. A learning data acquiring section (36) acquires first data that is first-type device data. A first learning section (42) performs learning of a first model (34(1)) in which an estimation using the first-type device data is executed by using the first data. A learning data generating section (40) generates second data that is second-type device data the format of which differs from the format of the first-type device data on the basis of the first data. A second learning section (44) performs learning of a second model (34(2)) in which an estimation using the second-type device data is executed by using the second data.