Document Role Identification Using Proper Noun and Seal Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information processing systems fail to accurately determine whether a user or their company is a provider or receiver of a document, especially in forms like invoices and cost estimates, leading to inefficiencies in processing and management.
Innovation Solution
An information processing apparatus that extracts proper nouns from documents and uses OCR technology to analyze the presence of honorifics, words accompanying addressees, and seal impressions to determine the role of the company within the document, utilizing a processor to differentiate between providers and receivers based on positional relationships and attribute information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic extraction of information from scanned forms is implemented, then processing efficiency is improved, but accuracy in determining provider/receiver roles deteriorates
Solution Approach 1:
The document analysis is divided into multiple segments: extracting proper nouns, identifying honorifics, detecting seal impressions, and analyzing positional relationships. Each segment processes specific features independently, then combines results to determine provider/receiver roles accurately while maintaining efficient automated processing
Solution Approach 2:
The system introduces intermediary elements such as honorific detection, seal impression recognition, and positional relationship analysis as mediators between the extracted text and the final provider/receiver determination. These intermediaries provide additional contextual clues that improve accuracy without significantly increasing processing complexity
2Speed
If simple OCR processing is used, then processing speed is improved, but ability to determine document roles deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-identifying proper nouns, honorifics, and seal impressions before the final provider/receiver determination. This preliminary processing prepares structured data that speeds up the subsequent role determination while enhancing the system's ability to accurately identify document roles through multiple pre-analyzed features
Data Source
AI summary
An information processing apparatus includes a processor programmed to: extract from a document a proper noun that is likely to represent a provider of the document or a receiver of the document; and determine whether an attribute of the proper noun is the provider or the receiver by referring to information obtained from the proper noun or information obtained from a vicinity of the proper noun on the document.


