Hierarchical Simulation Using Sample Data for Accurate Fast Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for simulating hierarchical processes struggle to balance prediction accuracy and processing load, with higher-level simulations providing fast results but low accuracy, and lower-level simulations offering high accuracy but at the cost of increased processing time and load.
Innovation Solution
An information processing device that stores sample data associated with each parameter representing work, using higher-level simulation with similar parameters to predict indicators efficiently and lower-level simulation to generate complementary data when necessary, thereby achieving accurate and efficient predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If higher-level simulation is used, then processing speed is improved, but prediction accuracy deteriorates
Solution Approach 1:
The patent segments the simulation process into two distinct levels: higher-level simulation for fast processing and lower-level simulation for high accuracy. By dividing the simulation task into hierarchical segments, the system can selectively apply appropriate simulation levels to different scenarios, achieving both speed and accuracy where needed.
Solution Approach 2:
The patent applies partial action by using lower-level simulation only when necessary (when sample data is insufficient or high accuracy is required), rather than always applying the most accurate but computationally expensive method. This selective approach optimizes the balance between processing speed and prediction accuracy.
2Measurement precision
If lower-level simulation is used, then prediction accuracy is improved, but processing load increases
Solution Approach 1:
The patent performs preliminary action by pre-collecting and storing sample data from lower-level simulations for various parameter combinations. This pre-computed sample data serves as a reference database, allowing the higher-level simulation to make accurate predictions without repeatedly executing computationally expensive lower-level simulations, thus improving processing efficiency.
Solution Approach 2:
The patent creates copies of lower-level simulation results in the form of sample data stored in association with parameter values. These copied results can be quickly retrieved and applied during higher-level simulation, avoiding the need to re-run lower-level simulations and significantly reducing processing load while maintaining accuracy.
3Measurement precision
If lower-level simulation is used, then prediction accuracy is improved, but execution time increases
Solution Approach 1:
The patent performs preliminary lower-level simulations to generate sample data that is stored for future use. When performing higher-level simulation, the system retrieves pre-computed sample data instead of executing time-consuming lower-level simulations in real-time, significantly reducing execution time while maintaining prediction accuracy.
Solution Approach 2:
The patent creates and stores copies of lower-level simulation results as sample data associated with specific parameter values. These copied results can be quickly accessed during higher-level simulation, eliminating the need to re-execute time-consuming lower-level simulations and thus reducing overall execution time.
Data Source
AI summary
An indicator related to work performed through a plurality of hierarchical processes is predicted efficiently with high accuracy. The information processing device stores sample data in association with each parameter representing work, the sample data including an indicator generated by execution of lower-level simulation based on a lower-level model set for a lower-level process, and the information processing device predicts an indicator related to predicted work by performing higher-level simulation using the sample data associated with a parameter similar to a parameter representing the predicted work, the higher-level simulation being based on a higher-level model which is set for a higher-level process. If sample data associated with a parameter similar to the parameter representing the predicted work is not stored, the information processing device complements sample data by performing lower-level simulation and performs higher-level simulation using the complemented sample data.