Knowledge Graph Construction via Partial Topology Translation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in formulating data flows to build knowledge graphs due to their procedural nature, making it challenging to create knowledge graphs effectively.
Innovation Solution
A method that converts user-provided partial knowledge graph topologies into initial nodes with natural language descriptions, interprets these using natural language processing to match against reference data, and generates a valid topology and data flow to build an executable knowledge graph.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If users manually formulate data flows to build knowledge graphs, then the knowledge graph can be constructed with precise control, but the process becomes complex and difficult for users to master
Solution Approach 1:
The patent introduces an intermediary system that translates user-friendly partial topology specifications into complete data flows. Users specify only the essential graph structure (nodes and edges), and the system automatically generates the procedural data flow code needed to construct the knowledge graph, eliminating the need for users to manually write complex data flow formulations.
Solution Approach 2:
The system performs preliminary actions by pre-defining templates and structures for data flows. Instead of requiring users to create data flows from scratch, the system prepares reusable data flow templates that can be automatically instantiated based on the user's partial topology specification, reducing the cognitive load and complexity for users.
2Reliability
If users specify complete data flows manually, then the knowledge graph construction is precise, but the process becomes time-consuming and complex
Solution Approach 1:
The system enables self-service by automatically completing the data flow formulation process. Once users provide their partial topology specification, the system autonomously generates the complete data flow, validates it against the specification, and constructs the knowledge graph without requiring further user intervention or manual data flow writing.
Solution Approach 2:
The patent replaces the mechanical process of manual data flow writing with an automated computational system. The system uses algorithmic processing to translate the user's high-level topology specification into executable data flows, substituting manual procedural work with automated intelligent generation.
3Productivity
If procedural data flows are used to build knowledge graphs, then the construction process is systematic, but it becomes difficult for users to understand and formulate correctly
Solution Approach 1:
The patent segments the knowledge graph construction process into two distinct parts: (1) user-friendly topology specification where users define only the essential graph structure, and (2) automated data flow generation where the system creates the procedural implementation. This segmentation allows users to work at a higher level of abstraction without needing to understand the underlying procedural complexity.
Solution Approach 2:
The system introduces an additional dimension of abstraction by separating the conceptual model (partial topology specification) from the implementation model (complete data flow). Users operate in the conceptual dimension using simple node-edge definitions, while the system handles the implementation dimension by generating the procedural data flows, effectively adding an abstraction layer that hides complexity.
Data Source
AI summary
A computer-implemented method, a computer program product, and a computer system for building a knowledge graph. A computer system converts user inputs as to a partial topology of a knowledge graph that a user wants to build into one or more initial nodes corresponding to respective natural language descriptions. A computer system interprets the respective natural language descriptions using natural language processing to match the one or more initial nodes against reference data. A computer system, based on matched reference data, obtains a valid topology of nodes and edges, wherein the nodes and edges are mapped onto the matched reference data. A computer system, based on the valid topology, generates a data flow linking to the matched reference data via associations of the nodes and edges and the matched reference data. A computer system builds an executable knowledge graph from the data flow.