Automated Knowledge Graph Construction from Text
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating knowledge graphs from text are manual and labor-intensive, requiring significant effort and resources.
Innovation Solution
The system automatically generates knowledge graph entities from text using natural language processing techniques such as named entity recognition, part-of-speech tagging, and business object recognition, creating nodes and edges to represent entities and relationships.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual methods are used to generate knowledge graphs from text, then the quality and accuracy of knowledge graph construction can be maintained through human expertise, but the labor intensity and time consumption increase significantly
Solution Approach 1:
The patent introduces natural language processing techniques as an intermediary between manual knowledge graph construction and automated processing. The system uses NLP to automatically extract entities, relationships, and attributes from text, serving as a mediator that reduces manual labor while maintaining construction quality through algorithmic precision
Solution Approach 2:
The patent replaces the mechanical manual process of knowledge graph construction with automated computational methods. Instead of manually identifying entities and relationships, the system uses NLP algorithms, part-of-speech tagging, and named entity recognition to automatically generate knowledge graphs from text
2Ease of operation
If manual methods are used to generate knowledge graphs from text, then detailed control over the construction process can be maintained, but the resource consumption and cost increase
Solution Approach 1:
The patent enables the system to automatically perform knowledge graph construction without requiring extensive human resources. The NLP-based system self-services by automatically extracting information, identifying entities, and constructing knowledge graphs from input text, thereby reducing both labor and computational resource consumption
3Productivity
If automated NLP methods are used to generate knowledge graphs from text, then productivity and efficiency improve, but the complexity of the system increases
Solution Approach 1:
The patent segments the knowledge graph generation process into distinct modular components: named entity recognition, part-of-speech tagging, relationship extraction, and graph construction. Each module handles a specific aspect of the process, making the overall complex system manageable through functional decomposition and enabling parallel processing to improve productivity
Data Source
AI summary
Example methods and systems are directed to generating knowledge graph entities from text. Natural language text is received as input and processed using named entity recognition (NER), part of speech (POS) recognition, and business object recognition (BOR). The outputs of the NER, POS, and BOR processes are combined to generate knowledge entity triples comprising two entities and a relationship between them. Keywords are extracted from the text using NER to generate a set of entities. A node in a knowledge graph is created for at least some of the entities. A POS tagger identifies verbs in the text, generating a set of verbs. Relational verbs (e.g., “talk to” or “communicated with”) are detected and used to create edges in the knowledge graph. The knowledge graph may be converted back to natural language text using a trained machine learning model.