Document Translation Apparatus Excluding Non-Target Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current information processing systems face challenges in efficiently translating documents while excluding specific regions, such as logos or images, from the translation process, leading to potential mistranslation and increased operator effort in designating non-target regions.
Innovation Solution
An information processing apparatus with a receiving unit, an obtaining unit, and a translating unit, which receives a document, identifies and excludes non-target regions through layout analysis and user designation, and performs translation only on the target regions, maintaining the original document layout.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the translating unit performs translation on the entire document without excluding non-target regions, then the translation process is simple and fast, but mistranslation occurs in regions such as logos or images that should not be translated
Solution Approach 1:
The patent segments the document into target regions (text to be translated) and non-target regions (logos, images, etc. to be excluded). The obtaining unit extracts non-target regions, and the translating unit processes only the remaining target regions. This segmentation resolves the contradiction by enabling accurate translation while maintaining manageable process complexity through automated region identification.
Solution Approach 2:
The patent extracts non-target regions from the document before translation. The obtaining unit identifies and removes logos, images, and other non-translatable elements from the document structure. This extraction ensures that the translating unit only processes appropriate text regions, preventing mistranslation while keeping the overall process straightforward through automated extraction.
2Reliability
If the operator manually designates non-target regions for exclusion, then translation accuracy can be improved, but the operator effort and time required increase significantly
Solution Approach 1:
The patent implements self-service by having the obtaining unit automatically identify and extract non-target regions without operator intervention. The system uses automated detection methods to recognize logos, images, and other non-translatable elements, then excludes them from the translation process. This eliminates the need for manual operator designation while maintaining high translation accuracy.
Solution Approach 2:
The patent performs preliminary action by having the obtaining unit identify and extract non-target regions before the translation process begins. This preliminary extraction of non-translatable elements ensures that the translating unit only processes appropriate text regions, achieving accurate translation without requiring operator time for region designation.
3Ease of manufacture
If the translation result is superimposed on the original document layout, then the translation process is simple, but the translation result may be incorrectly positioned on non-target regions such as logos or images
Solution Approach 1:
The patent segments the document into target regions (text to be translated) and non-target regions (logos, images). By excluding non-target regions from the translation process, the system ensures that translation results are only generated for appropriate text areas, preventing incorrect positioning on logos or images while maintaining simple superposition of results on the original layout.
Solution Approach 2:
The patent extracts non-target regions from the document before translation. This extraction ensures that the translating unit only generates translation results for text regions, not for logos or images. Consequently, the translation results are automatically positioned correctly on the original document layout without overlapping or distorting non-translatable elements.
Data Source
AI summary
An information processing apparatus includes a receiving unit, an obtaining unit, and a translating unit. The receiving unit receives a document as a target to be translated. The obtaining unit obtains a non-target region from the document, the non-target region being a region that is not a target to be translated. The translating unit does not perform translation on the non-target region but performs translation on a portion other than the non-target region.