Technical Diagram Knowledge Graphs for Searchable Information Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technical diagrams, particularly those in print or scanned form, lack searchable formats, making it difficult to retrieve relevant information efficiently.
Innovation Solution
A computing system utilizing machine learning logic to identify features in technical diagrams, generate knowledge graphs that define relationships between these features, and facilitate high-quality searching based on user requests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If technical diagrams are stored in print or scanned form, then they can be preserved and archived, but the information cannot be searched efficiently
Solution Approach 1:
The patent creates digital copies of technical diagrams and their associated data, transforming physical print or scanned documents into searchable digital formats. This allows the original diagrams to be preserved in their existing form while creating a searchable digital representation that enables efficient information retrieval without requiring manual searching through physical archives.
Solution Approach 2:
The patent introduces a characteristic data table as an intermediary structure that bridges the gap between visual diagram information and searchable text data. This intermediary captures key features, dimensions, and properties from the diagrams in a structured format, enabling efficient searching while the original diagrams remain preserved for reference.
2Measurement precision
If information is extracted and structured for searching, then search accuracy improves, but processing complexity increases
Solution Approach 1:
The patent segments the information extraction process into distinct components: identifying articles, extracting features, capturing dimensions, and organizing data into characteristic data tables. This segmentation allows each aspect to be processed independently and systematically, improving search accuracy while managing processing complexity through modular organization of the extraction tasks.
Solution Approach 2:
The patent creates a universal characteristic data table structure that can accommodate multiple types of technical diagrams and their various features. This multi-functional template system handles different article types, features, and dimensions through a consistent framework, reducing processing complexity by avoiding the need for separate extraction logic for each diagram type.
3Loss of information
If multiple data sources are integrated into a unified search system, then information completeness improves, but system complexity increases
Solution Approach 1:
The patent merges multiple data sources including visual diagram information, characteristic data tables, and dimension data into a unified searchable system. This integration ensures that information from disparate sources is consolidated and can be searched together, improving information completeness while the unified structure manages system complexity through centralized organization.
Data Source
AI summary
A computer-implemented method for extracting information from a diagram comprises identifying, via first machine learning logic implemented by a computer, features associated with an article illustrated in the diagram. A knowledge graph that defines relationships between the features is generated via second machine learning logic implemented by the computer and based on the features. The knowledge graph specifies nodes associated with the features and edges between the nodes that specify the relationships between the features. A request for information associated with the diagram is received by the computer and from a user. The computer searches the knowledge graph for the information associated with the request and communicates the information associated with the request to the user.