Information Processing Apparatus for Document Annotation via Machine Translation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing techniques for annotating document images require high work costs, especially when the annotator is not familiar with the document language, as they necessitate manual translation and annotation processes, increasing operational expenses.

Innovation Solution

An information processing apparatus that translates input text, allows users to select and label consecutive characters in the translated text, and stores the labeled text, reducing the need for language familiarity and manual annotation efforts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual translation and annotation operations are performed by annotators, then annotation accuracy can be maintained, but work costs and operational expenses greatly increase

Engineering Contradiction:

Improveannotation accuracyVSAvoidwork cost

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent introduces machine translation as an intermediary tool between the document and the annotator. The system automatically translates foreign language documents into the annotator's native language, eliminating the need for annotators to directly understand and translate the source language while maintaining annotation accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables self-service by allowing annotators to work with translated documents independently without requiring native language expertise or manual translation skills. The automated translation service handles the language barrier, enabling annotators to focus solely on the annotation task.

Inventive Principle:

Principle #25Self-service

2Ease of operation

If annotators work with foreign language documents without translation support, then workflow simplicity is maintained, but annotation quality deteriorates due to language unfamiliarity

Engineering Contradiction:

Improveworkflow simplicityVSAvoidannotation quality

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If translation operations are performed manually by annotators, then language accuracy can be ensured, but operational expenses and work costs greatly increase

Engineering Contradiction:

Improvelanguage accuracyVSAvoidoperational expense

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical process of manual translation with an automated machine translation system. This substitution eliminates the need for annotators to perform translation operations manually, thereby reducing operational expenses while maintaining language accuracy through automated translation services.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20240202465A1Information processing apparatus, controlling method of information processing apparatus, and storage medium

Publication Date: 2024.06.20 CANON KK

AI summary

An information processing apparatus according to the present disclosure acquires a translation text by executing a translation process on an input text; selects one or more consecutive characters in the translation text as a selection text, based on a user operation; assigns a label selected based on a user operation, to a character string corresponding to the selection text in the input text; and stores the input text to which the label has been assigned, in a storage unit.