Pattern-Based Multi-Stage Data Classification System

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data classification methods, particularly those relying on AI and stochastic processes, are inefficient and costly when dealing with unpredictable client or customer input data sets, often resulting in inaccurate or undesirable outcomes.

Innovation Solution

A pattern-based multi-stage deterministic data classification system that identifies data parameters without immediate extraction, using descriptive data to conduct classification analysis, and only extracting values after classification or for specific classifications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If AI and stochastic processes are used for data classification, then automation extent is improved, but productivity deteriorates due to inefficiency and high costs

Engineering Contradiction:

Improveautomation of data classificationVSAvoidclassification efficiency

Core Design Contradiction:

Extent of automationVSProductivity

Solution Approach 1:

The classification system is divided into multiple stages: initial filtering stage and detailed classification stage. The system segments data processing by applying different levels of analysis to different data subsets, thereby improving overall efficiency while maintaining automation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies full classification analysis only to data that requires it, while using simplified filtering for other data. This partial action approach avoids the inefficiency of applying complex AI methods to all data uniformly, thereby improving productivity.

Inventive Principle:

Principle #16Partial or excessive action

2Measurement precision

If immediate data extraction is performed for all input data, then measurement precision is improved, but loss of time and energy increases

Engineering Contradiction:

Improvedata extraction accuracyVSAvoiddata processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary filtering and analysis before full data extraction. By conducting initial classification on summarized data first, the system identifies which data requires detailed extraction, thereby reducing overall processing time while maintaining accuracy for relevant data.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system extracts data selectively rather than immediately extracting all data. Full data extraction is performed only on data that passes initial filtering and requires detailed classification, removing unnecessary extraction operations and reducing time loss.

Inventive Principle:

Principle #2Taking out (Extraction)

3Reliability

If comprehensive data processing is applied to all datasets, then reliability is improved, but use of energy and processing resources increases

Engineering Contradiction:

Improveclassification accuracyVSAvoidprocessing resource consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system applies different processing qualities to different data subsets. High-resource comprehensive processing is applied only where needed for reliable classification, while simplified processing is used for other data, optimizing energy usage while maintaining reliability for critical classifications.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12216685B2Systems and methods for pattern-based multi-stage deterministic data classification

Publication Date: 2025.02.04 THE TRAVELERS INDEMNITY

AI summary

Systems and methods for pattern-based multi-stage deterministic data classification that may reduce processing and memory overhead while providing more accurate data classifications.