Composite Classification Scenario Scoring Machine Learning Model

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing predictive data analysis systems face computational inefficiencies when performing composite classification of classification inputs, requiring O(x*s) operations to determine optimal composite classification scenarios, leading to high computational complexity.

Innovation Solution

The method involves distributing the largest per-input individual cost measure for a composite class to all associated classification inputs, simplifying the optimization process and reducing computational complexity to linear, allowing for efficient composite classification scenario determination using composite classification scenario scoring machine learning models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional optimization methods are used to determine composite classification scenarios, then measurement precision is improved, but computational complexity increases to O(x*s) operations

Engineering Contradiction:

Improvecomposite classification scenario determination accuracyVSAvoidcomputational complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical optimization algorithms with a machine learning model (composite classification scenario scoring model) that automatically scores and ranks composite classification scenarios. This substitution transforms the computational approach from iterative optimization to direct prediction, significantly reducing computational complexity while maintaining determination accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent performs preliminary actions by pre-training the machine learning model on historical classification data and scenario outcomes. The model learns optimal scoring patterns in advance, enabling it to quickly evaluate new composite classification scenarios without requiring complex real-time optimization calculations

Inventive Principle:

Principle #10Preliminary action

2Reliability

If comprehensive composite classification analysis is performed, then reliability is improved, but productivity decreases due to high computational requirements

Engineering Contradiction:

Improvepredictive data analysis reliabilityVSAvoidcomposite classification processing speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces computationally intensive traditional analysis methods with a machine learning-based scoring system that maintains reliability through learned patterns from training data while achieving significantly faster processing speeds for composite classification scenarios

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses the machine learning model to create a computational copy of the complex optimization process, capturing the essential decision-making patterns during training and reproducing them efficiently during inference, thereby maintaining reliability without the original computational burden

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20230065947A1Machine learning techniques for composite classification

Publication Date: 2023.03.02 UNITEDHEALTH GROUP INC

AI summary

Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive data analysis. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis operations by utilizing at least one of composite classification scenarios and composite classification scenario scoring machine learning models.