Mapping Model for Accurate System Behavior Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for modeling complex systems are inefficient due to high resource costs and limited sampling budgets, resulting in sub-optimal accuracy and decision-making when predicting system behaviors across various parameter combinations.
Innovation Solution
A computer-implemented method that generates a model by creating a mapping model based on authoritative data, which maps values from an existing model to new measured values, allowing for more accurate predictions with reduced resource expenditure by leveraging structural similarity between the authoritative and new behaviors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of samples is increased to improve model accuracy, then the accuracy of the model increases, but the time and resources required to generate the model increase
Solution Approach 1:
The patent creates a mapping model that copies the structural patterns from an authoritative model (trained on comprehensive data) and applies them to predict system behavior. Instead of gathering all possible samples directly, the system generates synthetic samples by transforming the authoritative model's structure through the mapping model, achieving high accuracy with fewer actual measurements.
Solution Approach 2:
The authoritative model is pre-trained on a comprehensive dataset covering the full parameter space. This preliminary action creates a rich structural foundation that can be transformed into predictions for specific queries, eliminating the need to collect all possible samples at query time and significantly reducing the sampling budget required.
2Loss of energy
If the sampling budget is constrained to reduce resource costs, then the resources required decrease, but the number of samples obtained decreases leading to sub-optimal model accuracy
Solution Approach 1:
The mapping model copies structural information from the authoritative model to generate accurate predictions without requiring proportional sampling resources. By leveraging the pre-trained authoritative model's comprehensive coverage, the system achieves high accuracy predictions at a fraction of the original sampling cost.
Solution Approach 2:
The system transforms the problem from directly sampling system behavior to sampling the mapping between authoritative model outputs and actual system behavior. This parameter transformation allows the use of fewer samples because the mapping model learns the transformation relationship rather than requiring exhaustive direct measurements.
3Loss of energy
If conventional modeling techniques are used with limited samples, then resource expenditure is reduced, but the accuracy of predictions decreases
Solution Approach 1:
The mapping model copies the robust structural patterns from the authoritative model, which was trained on comprehensive data. This copying mechanism allows the system to achieve high prediction accuracy with limited sampling resources, outperforming conventional techniques that would require proportionally more resources to achieve the same accuracy.
Solution Approach 2:
The mapping model serves as an intermediary between the authoritative model and the target system behavior. This intermediary transforms the authoritative model's comprehensive structural knowledge into accurate predictions for specific queries, achieving high accuracy with fewer direct samples than conventional methods would require.
Data Source
AI summary
In one embodiment, a model generator generates a new model for a behavior of a system based on an existing, authoritative model. First, a mapping generator generates a mapping model that maps authoritative values obtained via the authoritative model to measured values that represent the behavior of the system. Subsequently, the model generator creates the new model based on the authoritative model and the mapping model. In this fashion, the mapping model indirectly transforms the authoritative model to the new model based on the measured values. Advantageously, the authoritative model enables the model generator to increase a rate of accuracy improvement experienced while developing the new model compared to a rate of accuracy improvement that would be experienced were the new model to be generated based on conventional modeling techniques. In particular, for a given sampling budget, the model generator improves the accuracy of the new model.