Rule-Based Machine Learning for Eligibility Criteria Migration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current HR systems face challenges in efficiently analyzing and updating eligibility criteria from Plan Administration Manual (PAM) documents, leading to inconsistencies and time-consuming manual processes, especially during system migrations and status changes, which can result in discrepancies and inaccurate eligibility rule migration.

Innovation Solution

A method and system using rule-based machine learning to extract and derive classification rules from documents and databases, employing natural language processing for variable extraction, filtering, and feature engineering to improve accuracy and efficiency in eligibility criteria analysis and migration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual analysis of PAM documents is used to update eligibility criteria, then administrators can review and configure criteria, but the process is time-consuming and leads to inconsistencies

Engineering Contradiction:

Improveaccuracy of eligibility criteriaVSAvoidtime for analyzing and updating criteria

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of analyzing PAM documents with an automated system using natural language processing and machine learning algorithms. The system automatically extracts eligibility criteria from documents, maps them to database fields, and derives classification rules, eliminating manual analysis while improving accuracy and reducing time consumption.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically performing tasks that previously required administrator intervention. The machine learning model autonomously extracts criteria from documents, identifies relevant database fields, and generates classification rules without human input, allowing the system to serve itself in the eligibility criteria management process.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If manual analysis and comparison of updated PAM documents is performed, then eligibility criteria can be updated, but inconsistencies and errors occur

Engineering Contradiction:

Improveability to update criteriaVSAvoidconsistency of eligibility criteria

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system implements feedback mechanisms where the machine learning model continuously learns from extracted criteria and improves its accuracy over time. The system validates extracted criteria against existing database schemas and provides feedback loops that refine the extraction and mapping processes, ensuring consistent and reliable eligibility criteria updates.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent replaces error-prone manual analysis with automated natural language processing and machine learning systems that consistently extract and map eligibility criteria. This substitution eliminates human errors and inconsistencies while maintaining the ability to adapt to updated PAM documents through automated processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If rule-based machine learning is used to derive classification rules, then accuracy and efficiency are improved, but system complexity increases

Engineering Contradiction:

Improveefficiency of criteria analysisVSAvoidcomplexity of processing system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the complex task of eligibility criteria management into distinct modules: document extraction using natural language processing, database field identification, rule derivation through machine learning, and validation. This segmentation reduces overall system complexity by breaking down the monolithic process into manageable, specialized components that can be developed and maintained independently.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces intermediary components such as the machine learning model that acts as a mediator between raw document text and database classification rules. This intermediary layer simplifies the complexity by handling the complex pattern recognition and rule derivation tasks, while presenting a simpler interface to administrators for configuration and validation.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12118478B2Systems and methods for machine learning based rule discovery for data migration

Publication Date: 2024.10.15 FMR CORP

AI summary

Systems and methods for deriving classification rules from documents and a database using rule-based machine learning. The method includes extracting first variables from documents corresponding to an organization. The method further includes extracting second variables from a database corresponding to the organization. The method also includes filtering the extracted second variables based on at least one of null values, repeat variables, location variables, ID variables, or data variables. The method further includes deriving first classification rules based on the first variables using a rule-based machine learning algorithm. The method also includes calculating an accuracy of the derived first classification rules. The method also includes deriving second classification rules based on the first variables and the filtered second variables. The method further includes determining a suggested additional variable based on the derived second classification rules and the calculated accuracy.