Dynamic Rule-Based Matching Engine for Unstructured Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional computer matching engines rely on predefined rules and rigid structures, which are inadequate for handling unstructured inputs and dynamically changing rules, limiting their ability to identify matches in less-than-structured data environments.

Innovation Solution

A computer-implemented method and system that dynamically modifies a rule-based matching system by receiving a rule set, a source data entity, and a rater assessment, revising the rule set in real-time based on the assessment, and using the revised rules to locate matching data entities, enabling flexible and dynamic matching and prioritization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional predefined rules are used for matching, then the system is simple and easy to operate, but it cannot handle unstructured inputs and dynamically changing rules

Engineering Contradiction:

Improveability to handle unstructured inputs and dynamically changing rulesVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic rule modification by allowing the rule set to be updated in real-time based on rater assessments and machine learning outputs. The system transitions from static predefined rules to dynamic rules that adapt to changing data patterns and user feedback, enabling the matching engine to handle unstructured inputs effectively while maintaining operational simplicity through automated updates.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback loops where rater assessments of match quality are fed back into the machine learning model, which then generates revised rules for the matching engine. This closed-loop feedback mechanism allows the system to continuously improve its matching accuracy for unstructured data while maintaining ease of operation through automated learning and adaptation.

Inventive Principle:

Principle #23Feedback

2Measurement precision

If rigid structured elements are used for matching, then parsing is easy, but the system cannot match less-than-structured data effectively

Engineering Contradiction:

Improvematching accuracy for unstructured dataVSAvoidparsing ease

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces traditional mechanical parsing methods with machine learning-based semantic analysis. Instead of relying on rigid structural parsing, the system uses natural language processing and semantic understanding to identify and match entities in unstructured data, achieving high matching accuracy while maintaining ease of operation through automated linguistic analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system dynamically adjusts matching parameters based on the structure and characteristics of the input data. For unstructured data, the machine learning model modifies extraction and matching parameters in real-time, allowing the system to adapt to varying data formats and structures while maintaining parsing ease through automated parameter optimization.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If the rule set is fixed, then the system is stable and reliable, but it cannot dynamically adapt to changing matching criteria

Engineering Contradiction:

Improvedynamic rule adaptationVSAvoidsystem stability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system implements self-service through automated machine learning models that continuously learn from rater assessments and independently generate rule revisions. This self-learning mechanism allows the system to dynamically adapt to changing matching criteria while maintaining stability through automated validation and gradual rule evolution, eliminating the need for manual rule management.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary analysis of rater assessments and data patterns to predict optimal rule modifications before implementing changes. This preliminary action ensures that dynamic rule adaptations are based on充分的 analysis and validation, maintaining system reliability while enabling adaptability to changing matching criteria.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11620538B1Machine learning integration for a dynamically scaling matching and prioritization engine

Publication Date: 2023.04.04 WELLS FARGO BANK NA

AI summary

A system and related method are provided for dynamically modifying a rule-based matching system. A processor receives a source data entity, and then locates a matching data entity by a search based on the source data entity and a rule set. A rater assessment is provided by a rater that utilizes at least one factor that is independent of the rule set and comprises a degree of matching between the source and matching data entity. A revised rule set is dynamically created based on an output of the analyzer, which in turn is based on the source data entity, the matching data entity, the rater assessment, and the rule set. Once this is complete, a second matching data entity is located by searching for the second matching data entity based on the source data entity and the revised rule set.