Patent Drawing Reference Mapping for Faster Figure-Based Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for analyzing knowledge information contents, such as patent documents, are inefficient due to the lack of a drawing-oriented content analysis that links drawings and texts, making it difficult to quickly access relevant information.
Innovation Solution
A method and apparatus that utilize optical character recognition and machine learning to identify and replace drawing reference numbers with descriptions, enabling drawing-centered analysis by interlocking drawing reference numbers with their descriptions, and allowing for intuitive information retrieval.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If OCR technology is used to recognize characters on knowledge information contents, then the speed in accessing necessary information is improved, but it is difficult to quickly acquire information related to drawings
Solution Approach 1:
The patent segments the knowledge information contents into drawing elements and text elements, and establishes linkage relationships between them. This segmentation allows the system to process and search drawing-related information independently, resolving the contradiction between general character recognition speed and specific drawing information accessibility.
Solution Approach 2:
The patent introduces a drawing element information extraction module that acts as an intermediary between the OCR recognition system and the drawing information. This intermediary extracts drawing reference numbers and descriptions from the recognized text, creating a bridge that enables efficient drawing-oriented search while maintaining the speed benefits of OCR technology.
2Ease of operation
If drawing reference numbers are replaced with descriptions, then drawing-oriented content analysis is enabled, but the complexity of processing increases
Solution Approach 1:
The patent performs preliminary extraction of drawing element information (reference numbers and descriptions) from the knowledge information contents before the actual analysis or search operations. This preliminary action stores the extracted information in a structured format, reducing the complexity of subsequent processing while enabling easy drawing-oriented analysis.
Solution Approach 2:
The patent creates a copy of the drawing element information structure that includes reference numbers linked to their descriptions. This copied structure can be independently processed and searched without modifying the original contents, simplifying the processing complexity while enabling comprehensive drawing-oriented analysis capabilities.
3Measurement precision
If all drawings are processed to extract linkage information, then comprehensive drawing analysis is achieved, but the time and effort to process increases
Solution Approach 1:
The patent extracts only the essential drawing element information (reference numbers and their associated descriptions) from the complete knowledge information contents. This extraction approach maintains the precision of drawing analysis by capturing all necessary linkage information while significantly reducing the time and effort required to process the entire document set.
Solution Approach 2:
The patent applies partial action by processing only the drawing-related portions of the knowledge information contents rather than all contents uniformly. The system identifies and processes drawing elements selectively, achieving comprehensive drawing analysis precision while minimizing the overall processing time and effort through targeted rather than exhaustive processing.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables rapid and intuitive access to knowledge information by accurately recognizing and replacing drawing reference numbers, facilitating efficient filtering and analysis of drawings and texts, even in varying states like enlargement or rotation.
Implementation Method 1
a method is becoming available in which Optical Character Recognition (OCR) technology is used to precisely recognize characters and/or numbers on knowledge information contents
Data Source
AI summary
A method for outputting a drawing reference number description including recognizing a size of a patent drawing and a position of a drawing reference number included in the patent drawing and acquiring a relative position coordinate of the drawing reference number in the patent drawing; setting a relative position coordinate of the drawing reference number description corresponding to the drawing reference number based on the acquired relative position coordinate; and outputting the drawing reference number description on the set relative position coordinate, thereby outputting such that the drawing reference number description corresponds to the drawing reference number.