Multi-dimensional Industrial Knowledge Graph for Complex Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial operations face challenges in organizing and extracting entities and relationships from scattered, diverse data sources to build a customized knowledge base for efficient data services, as traditional relational databases are inadequate for handling complex industrial data.
Innovation Solution
A customized industrial graph knowledge base is built using a graph database, where entities and relationships are extracted from baseline, domain-specific, and implementation-specific data sources using machine learning and natural language processing, and organized into predetermined dimensions, with filtering parameters estimating importance for efficient querying.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional relational databases are used to store industrial data, then data storage is simple and well-established, but the database cannot efficiently handle complex industrial data relationships and entity extraction
Solution Approach 1:
The patent transitions from traditional relational database models to a graph database model, adding a new dimensional perspective for representing data. The graph database uses nodes and edges to represent entities and relationships, enabling multi-dimensional queries and complex relationship traversals that are inefficient in relational databases. This dimensional change allows the system to handle complex industrial data relationships while maintaining manageable structure through standardized graph operations.
2Loss of information
If entities and relationships are extracted from scattered data sources, then comprehensive industrial knowledge is captured, but data organization and processing become complex and time-consuming
Solution Approach 1:
The patent implements preliminary action by pre-defining entity types, relationship types, and dimension schemas before data extraction. The system establishes a standardized graph database schema with predefined nodes (equipment, processes, materials) and edges (connections, flows, relationships) in advance. This preliminary structuring enables automated extraction and organization of scattered industrial data without manual intervention, capturing comprehensive knowledge while minimizing organization time through template-based population of the graph structure.
3Measurement precision
If a customized industrial knowledge base is built with multiple data sources, then data service intelligence and accuracy improve, but system complexity and implementation difficulty increase
Solution Approach 1:
The patent segments the industrial knowledge base into distinct dimensional layers: equipment dimension, process dimension, material dimension, and performance dimension. Each dimension is represented as separate node types and relationship types in the graph database. This segmentation allows the system to integrate multiple scattered data sources by mapping them to specific dimensional schemas, improving data service accuracy through structured organization while reducing implementation complexity through modular, repeatable integration patterns for each dimension.
Data Source
AI summary
A customized industrial graph knowledge base for an industrial operation includes a graph database storing nodes of multiple dimensions predefined according to the nature and characteristics of the industrial operation. The nodes are extracted from baseline, domain-specific, and implementation specific industrial knowledge data sources using various analytics for structured and unstructured data. The customized industrial graph knowledge base further includes edges representing relationships between nodes that are either inter-dimensional or intra-dimensional. The importance of each node to the industrial operation is further quantified using a graph model and is included in the graph database as a composite filtering parameter.