Expert Reliability Scaling for Adaptive Decision Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing decision-making techniques fail to adapt appropriately to changes in the environment by adding or removing experts, as seen in the elevator traffic demand prediction apparatus.
Innovation Solution
An information processing apparatus that sets, normalizes, and scales the reliability of multiple experts using a setting process, a first calculation process, and a second calculation process to handle additions and removals of experts effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of experts is increased to improve prediction accuracy, then the prediction performance is improved, but the device complexity increases
Solution Approach 1:
The patent changes the parameter of expert reliability from fixed to dynamic by introducing normalization and scaling processes. The reliability of each expert is adjusted based on their performance (loss value) and the total number of experts, allowing the system to adaptively optimize prediction accuracy without manually increasing the number of experts.
2Measurement precision
If the reliability weighting is adjusted to improve decision quality, then the decision making accuracy is improved, but the calculation complexity increases
Solution Approach 1:
The patent transforms the reliability parameter through normalization (dividing by sum of all reliabilities) and scaling (multiplying by total number of experts). This systematic parameter transformation improves decision quality while keeping the calculation process structured and manageable.
Solution Approach 2:
The patent implements feedback by updating expert reliabilities based on loss values obtained from prediction results. Experts with lower loss values (better performance) receive higher reliability weights in subsequent predictions, creating a continuous improvement loop that enhances decision accuracy.
Data Source
AI summary
An information processing apparatus includes at least one processor that carries out: a setting process of setting a reliability for an expert; a first calculation process of normalizing the reliability to calculate a normalized reliability; an updating process of updating the normalized reliability with reference to a loss value; and a second calculation process of subjecting the updated normalized reliability to scaling. In the setting process, as a reliability of a new expert, the at least one processor sets a predetermined value, and as a reliability of an existing expert, the at least one processor set the scaled reliability.