ML Content Comparison Extraction for Faster Document Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing content analysis technologies, such as the search apparatus in Patent Literature 1, are limited in versatility and require manual effort for identifying and comparing relevant parts across multiple documents, making the process time-consuming.

Innovation Solution

An information processing apparatus and method utilizing machine learning to automatically acquire and extract comparison target portions from a plurality of content pieces using an extraction model, reducing the need for manual reading and identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual reading and identification of related parts in content is performed, then accuracy of identifying relevant information is improved, but time consumption and labor effort increase significantly

Engineering Contradiction:

Improveaccuracy of identifying relevant informationVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of reading and identifying relevant parts with an automated information processing system using machine learning models. The extraction model automatically identifies and extracts comparison target portions from content, substituting human cognitive effort with computational processes while maintaining high accuracy through trained algorithms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the extraction model to autonomously identify and extract relevant information without human intervention. The model processes content independently, automatically determining comparison target portions based on learned patterns, thereby eliminating the need for manual reading and identification while preserving accuracy.

Inventive Principle:

Principle #25Self-service

2Reliability

If existing search apparatus technology is used to detect specific documents predicting the future, then the function is specialized for specific purposes, but versatility for other tasks is reduced

Engineering Contradiction:

Improvespecialization for specific purposeVSAvoidversatility

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements universality by designing an extraction model that can handle multiple types of content and tasks through a unified framework. The model extracts comparison target portions from various content types (text, images, tables) and applies to different analysis scenarios, making the system versatile while maintaining reliable performance across diverse applications through consistent machine learning-based extraction.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250378379A1Information processing apparatus, analysis method, and storage medium

Publication Date: 2025.12.11 NEC CORP

AI summary

In order to make use of content easier, an information processing apparatus includes: an acquisition unit that acquires a plurality of pieces of content which are comparison targets; and an extraction unit that extracts, with use of an extraction model which has been generated by machine learning so as to be capable of extracting a comparison target portion in content, a comparison target portion in the plurality of pieces of content that have been acquired by the acquisition unit. It is possible to use, for decision making based on the pieces of content which were used as comparison targets, a result of extraction by the extraction unit.