Information Processing Device for Accurate Distribution Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional calculation methods, such as convolutional and calculus calculations, are limited in accurately processing discrete data like distributions or histograms from big data, failing to provide accurate results for parameters with distribution.
Innovation Solution
An information processing device acquires and processes input distributions for multiple parameters, setting partial regions and generating output distributions by combining and modifying input distributions based on defined ranges and partial regions, enabling accurate calculation of output parameter distributions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If convolutional calculation is used to process parameters with distribution, then calculation can be performed based on distribution theory, but the method cannot be applied to discrete data such as histograms from actual big data
Solution Approach 1:
The patent transforms the continuous distribution parameters into discrete histogram parameters by introducing binning intervals and cumulative frequency concepts. This allows the calculation method to adapt from continuous mathematical functions to discrete data representations while preserving the essential distribution calculation logic.
Solution Approach 2:
The patent introduces an intermediary transformation process that converts discrete histogram data into a form suitable for distribution calculation. By using cumulative frequency distributions and differential calculations, the method bridges the gap between discrete data and continuous distribution theory.
2Measurement precision
If the number of data pieces of each parameter is increased to improve distribution accuracy, then more data is available for calculation, but the calculation complexity and computational burden increase significantly
Solution Approach 1:
The patent segments the continuous parameter range into discrete bins or intervals, transforming the continuous distribution problem into a discrete histogram problem. This segmentation reduces the infinite complexity of continuous data to a manageable number of discrete categories while preserving the essential distribution characteristics.
Solution Approach 2:
The patent uses differential calculations on cumulative frequency distributions to obtain probability density estimates. By calculating the difference between adjacent cumulative frequencies and dividing by the interval width, the method obtains accurate distribution information without requiring exhaustive processing of all individual data points.
3Productivity
If conventional arithmetic calculation is used for parameters with distribution, then calculation speed is maintained, but the distribution characteristics are lost and calculation accuracy deteriorates
Solution Approach 1:
The patent creates a copied representation of the original data in the form of histograms and cumulative frequency distributions. These copied structures preserve the distribution characteristics while enabling efficient calculation through discrete mathematical operations that maintain both speed and accuracy.
Data Source
AI summary
A result of calculation for a plurality of parameters with distribution is obtained with higher accuracy than conventional calculation in an information processor that acquires first and second input distributions of first and second input parameters. A first partial region is set in a range of an output distribution of an output parameter using the first and second input parameters. A value of a distribution for the first value is obtained, based on a value of a distribution of the first input parameter corresponding to the first value and a value of a distribution of the second input parameter corresponding to the first value within an input parameter range determined based on the first and second input distributions, and on a size of a second partial region that is included in the input parameter range and corresponds to the first partial region and a size of the first partial region.