Unstructured Data Extraction via Dynamic Template Rules

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual review of unstructured data for claim processing is time-consuming and expensive due to the lack of semantic context in existing data extraction methods, which often rely on hardcoded and non-transparent algorithms, limiting flexibility and transparency.

Innovation Solution

A system and method for generating a structured report from unstructured data using customizable template rules, where predefined templates define extraction rules for identifying relevant data, allowing users to refine and modify these rules dynamically to improve data extraction accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual review of unstructured data is performed, then data extraction can be done, but the process is time-consuming and expensive

Engineering Contradiction:
Improvedata extraction accuracyVSAvoidreview time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical review processes with an automated computer-based system that uses extraction rules and templates to identify and extract relevant data from unstructured documents, eliminating the need for human reviewers to manually parse through documents

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service data extraction by allowing users to define their own extraction rules and templates, making the system adaptable to different data extraction needs without requiring manual reconfiguration or expert intervention for each new extraction task

Inventive Principle:
Principle #25Self-service

2Productivity

If hardcoded extraction algorithms are used, then data extraction can be automated, but the system lacks flexibility and transparency

Engineering Contradiction:
Improveextraction automationVSAvoidrule flexibility
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic extraction rules that can be modified and adjusted by users based on changing requirements. The system allows rules to be updated without reprogramming, enabling adaptive extraction across different document types and data requirements while maintaining automation

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms where extraction results can be reviewed and used to refine extraction rules. This allows the system to learn from actual extraction outcomes and improve its performance over time while maintaining transparency in the extraction process

Inventive Principle:
Principle #23Feedback

3Measurement precision

If sophisticated data extraction methods are used, then extraction capability is improved, but the system becomes a black box without transparency

Engineering Contradiction:
Improveextraction accuracyVSAvoidprocess transparency
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent segments the extraction process into distinct, understandable components including templates, extraction rules, and data fields. This segmentation makes the extraction process transparent and interpretable while maintaining high extraction accuracy through structured rule application

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS12182186B2Systems and method for generating a structured report from unstructured data
Publication Date: 2024.12.31 THOMSON REUTERS ENTERPRISE CENTRE GMBH
  • US12182186B2 patent drawing
  • US12182186B2 patent drawing
  • US12182186B2 patent drawing

AI summary

Methods and systems for providing computer-assisted guided review of unstructured data to generate a structured data output based on customizable template rules. In embodiments, an unstructured file is received, and a predefined template is selected. The predefined template includes a plurality of fields, each field corresponding to a field of the structured report. The predefined template also defines extraction rules for each field of the predefined template, and the extraction rules define parameters for identifying unstructured data relevant to the associated field. The extraction rules are applied to the unstructured file to identify data relevant to the field associated with the corresponding extraction rule, and the data identified as relevant is confirmed. Confirming the relevant data includes determining to refine the relevant data based on a condition, and modifying the extraction rule associated with the field to refine the relevant data.