Information Processing Device for Prediction Error Investigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning prediction models struggle to efficiently address prediction errors caused by special circumstances, leading to time-consuming and costly investigations.
Innovation Solution
An information processing device and method that acquire, interpret, and output natural language prompts to identify special factors affecting prediction tasks, and propose suitable predictive models for these factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual investigation of prediction errors is performed by model designers and managers, then prediction accuracy can be improved by identifying special factors, but time consumption and costs increase significantly
Solution Approach 1:
The system enables self-service by automatically investigating prediction errors through the error investigation unit, which autonomously identifies special factors and determines their influence degrees without requiring manual intervention from model designers and managers, thus resolving the contradiction between maintaining high prediction accuracy and reducing time consumption
Solution Approach 2:
The patent replaces the mechanical manual investigation process with an automated computational system that uses machine learning models to analyze prediction errors, identify special factors, and assess their influence degrees, thereby eliminating the time-consuming manual work while preserving the ability to improve prediction accuracy
2Measurement precision
If manual investigation of prediction errors is performed by model designers and managers, then prediction accuracy can be improved by identifying special factors, but costs increase significantly
Solution Approach 1:
The system performs self-service by automatically investigating prediction errors and identifying special factors through the error investigation unit, eliminating the need for expensive manual labor by model designers and managers while maintaining the capability to improve prediction accuracy
Solution Approach 2:
The patent substitutes the expensive manual investigation process with an automated machine learning-based system that can efficiently identify special factors and their influence degrees, thereby reducing the costs associated with manual expert intervention while preserving prediction accuracy improvement
3Productivity
If existing machine learning prediction models are used without considering special factors, then processing speed is maintained, but prediction accuracy deteriorates due to inability to handle special circumstances
Solution Approach 1:
The system segments the prediction process into two parts: the base machine learning model for regular predictions and the error investigation unit for handling special factors. This segmentation allows the system to maintain fast processing for normal cases while automatically investigating and adjusting for special circumstances that affect accuracy
Solution Approach 2:
The system dynamically adjusts the prediction process by automatically investigating prediction errors and identifying special factors when needed. The error investigation unit activates selectively based on prediction performance, allowing the system to maintain high processing speed for normal operations while improving accuracy when special circumstances are detected
Data Source
AI summary
A prompt acquisition means acquires a prompt described in natural language which includes a designation of a prediction task and a request for information concerning a special factor which may affect the prediction task. A special factor acquisition means interprets the prompt using natural language, and acquires information concerning the special factor which may affect the prediction task designated. A model information acquisition means acquires model information concerning a model which can be used in a case of corresponding to the special factor. An output means outputs an answer including information concerning the special factor and the model information acquired.