Discrimination Result Apparatus Resource Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the medical field, there is a challenge in collecting a large amount of high-quality learning data necessary for deep learning, as the process of assigning correct solution data is burdensome, lacking direct merit for users, which discourages motivation for data creation and collection.
Innovation Solution
A discrimination result providing apparatus and system that receives identification information and image correct solution data from multiple terminals, uses this data to learn and terminate discriminators, and distributes resources based on the number and quality of data received, enabling efficient discrimination and improving performance by utilizing distributed resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large amount of learning data is collected for deep learning, then discrimination performance is improved, but the operation of assigning correct solution data becomes burdensome and motivation for data creation decreases
Solution Approach 1:
The system implements a feedback mechanism where organizations that contribute learning data receive discrimination results as回报. The discrimination result providing apparatus transmits discrimination results back to contributing organizations, creating a closed-loop feedback system that motivates continued data contribution while maintaining high discrimination performance through accumulated learning data
Solution Approach 2:
The system enables organizations to serve themselves by allowing them to contribute their own learning data and receive discrimination results automatically. The discrimination result providing apparatus autonomously manages the collection, learning, and distribution process, reducing the operational burden on individual organizations while improving discrimination performance through aggregated data
2Quantity of substance
If learning data is collected from multiple organizations, then the amount of learning data increases, but resource management and distribution complexity increases
Solution Approach 1:
The discrimination result providing apparatus serves multiple functions: it collects learning data from multiple organizations, performs deep learning to improve discrimination performance, manages resource distribution automatically, and provides discrimination results back to contributing organizations. This multi-functional system handles diverse organizational inputs through a unified platform, increasing data quantity while managing complexity through universal resource management
Solution Approach 2:
The discrimination result providing apparatus acts as an intermediary between multiple organizations contributing learning data and the deep learning process. It centralizes resource management and distribution, mediating between data contributors and the learning system, thereby increasing the amount of learning data from multiple sources while simplifying resource management through centralized control
Data Source
AI summary
Image correct data is received from a plurality of terminals that belong to a plurality of organizations, a learning-terminated discriminator that is a learning discriminator that has performed learning using the image correct solution data is obtained, distribution of resources capable of being used by each discriminator is determined in accordance with the number of pieces of the received image correct solution data or the degree of performance improvement of the learning-terminated discriminator, and a discrimination result “Output” obtained by performing discrimination of a discrimination target image “Input” received from the terminal using the determined resources of the distribution is transmitted to the terminal that is a transmission source.