Document Entity Comparison for Patentability Assessment Accuracy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing document comparison systems struggle to accurately assess the patentability of claims by effectively identifying and correlating entities across different documents, particularly in the context of patent documents, which can impact the evaluation of novelty and inventive step.

Innovation Solution

A document comparison system that utilizes entity recognition, natural language processing, and hierarchical modeling to identify and correlate claim and description entities across documents, employing custom dictionaries and associative links to enhance the accuracy of patentability assessments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional search algorithms are used to identify entities in documents, then the search process is simple and fast, but the accuracy of entity identification and correlation across documents is insufficient

Engineering Contradiction:
Improveentity identification accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary layer of entity recognition and hierarchical modeling between traditional search algorithms and document comparison. This intermediary processes documents to extract structured entity information, which then feeds into the comparison system, improving accuracy without requiring complete system redesign

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system segments documents into discrete entities and organizes them in hierarchical structures. By breaking down complex documents into identifiable entity components and their relationships, the system can accurately compare specific elements across documents rather than treating entire documents as monolithic units

Inventive Principle:
Principle #1Segmentation

2Reliability

If entity recognition and hierarchical modeling are employed to improve patentability assessment accuracy, then the assessment quality improves, but the processing time and computational resources increase

Engineering Contradiction:
Improvepatentability assessment reliabilityVSAvoiddocument processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary entity recognition and hierarchical modeling on documents during indexing or pre-processing stages. This preliminary action creates structured entity representations that can be quickly queried and compared later, reducing processing time during actual patentability assessments while maintaining high accuracy

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system changes parameters such as entity extraction depth, hierarchical model granularity, and correlation threshold levels to balance assessment accuracy with processing time. By adjusting these parameters based on specific assessment needs, the system can optimize the trade-off between reliability and time consumption

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3750080B1Document analysis method and apparatus
Publication Date: 2026.04.08 THOMPSON TREVOR GEORGE
  • EP3750080B1 patent drawingFigure 1
  • EP3750080B1 patent drawingFigure 2~3
  • EP3750080B1 patent drawingFigure 4A~4C

AI summary

The present disclosure relates to a document comparison system (100) for comparing a first document (D1) with a second document (D2). The first document (D1) includes at least a first section having at least one first section entity (CEn), and the second document (D2) includes at least one second document entity (CEn). The document comparison system includes a processor (110) and a memory device (120). The processor is configured to identify the at least one first section entity (CEn ) in the first section of the first document (D1). The processor conducts a search of the second document (D2) to identify the presence or absence of one or more second document entity (CEn) corresponding to or equivalent to each first section entity (CEn) identified in the first section. The present disclosure also relates to a dictionary generating system; a document comparison method; a dictionary populating method; and non-transitory computer-readable medium.