Character Graph Representation for Substructure Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Searching for specific characters in complex written language systems, such as Chinese Hanzi, is challenging due to the large number of characters and their structural complexity, making it difficult to efficiently find and understand their meanings.
Innovation Solution
Representing characters as nodes and edges in a graph, enabling a searchable and decomposable database with substructure analysis to facilitate efficient searching and meaning prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional character-by-character searching methods are used, then searching accuracy is maintained, but searching time increases significantly
Solution Approach 1:
The patent segments characters into radicals and phonetic components, allowing the search system to break down complex characters into smaller searchable units. This segmentation enables the system to search for characters containing specific substructures without examining every character individually, thereby reducing searching time while maintaining accuracy.
Solution Approach 2:
The patent introduces an intermediary indexing system that maps radicals and phonetic components to characters. This intermediary structure allows the search to proceed through components rather than directly through characters, significantly improving searching efficiency while preserving the ability to accurately retrieve target characters.
2Measurement precision
If characters are represented in detailed graphical form, then visual accuracy is maintained, but data complexity and storage requirements increase
Solution Approach 1:
The patent segments character images into radical components and phonetic components, representing each segment with simplified graphical features rather than complete high-resolution images. This segmentation maintains visual accuracy for recognition purposes while reducing overall data complexity and storage requirements.
Solution Approach 2:
The patent creates simplified graphical representations (copies) of character components that capture essential visual features without preserving all details of the original high-resolution images. These simplified copies maintain sufficient accuracy for visual recognition and structure analysis while significantly reducing data complexity.
Data Source
AI summary
Methods and supporting systems for representing and searching characters, comprising: obtaining an image of a character, labelling a structure of the character by defining a plurality of nodes and a plurality of edges on the character in the image, and generating a representation of the character by extracting a set of two-dimensional coordinates to represent the plurality of nodes and by extracting a matrix to represent the plurality of edges, and providing the representation in a searchable database.