Context Clouds for Automated Knowledge Graph Construction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing knowledge base systems face difficulties in automatically extracting and interpreting meanings and relationships from unstructured data, such as free-form text, which limits their ability to accurately generate and update knowledge graphs without manual input.
Innovation Solution
The system employs context clouds and occurrence lists to analyze unstructured data by identifying target objects, proximate objects, and determining relationships, using co-occurrence frequencies and seed knowledge to dynamically generate and update knowledge graphs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual input is used to extract meanings and relationships from data, then accuracy of knowledge graphs is improved, but productivity and automation are worsened
Solution Approach 1:
The system automatically extracts meanings and relationships from unstructured data using context clouds and occurrence lists without requiring manual input. The knowledge graph system serves itself by autonomously analyzing documents, identifying target objects, and determining relationships through computational methods, thereby maintaining accuracy while dramatically improving productivity
Solution Approach 2:
The patent replaces manual mechanical processes of data extraction and relationship identification with automated computational systems. Context clouds and occurrence lists are generated and analyzed algorithmically, substituting human manual input with automated text analysis and pattern recognition systems that maintain accuracy while enabling scale
2Measurement precision
If manual input is used to extract meanings and relationships from data, then accuracy of knowledge graphs is improved, but extent of automation is worsened
Solution Approach 1:
The knowledge graph system performs self-service by automatically analyzing unstructured data, generating context clouds, creating occurrence lists, and determining relationships without human intervention. The system autonomously updates itself with new information from documents, achieving both high accuracy and complete automation
Solution Approach 2:
Manual processes of data extraction, analysis, and knowledge graph updates are completely replaced with automated computational systems that use context clouds and occurrence lists to identify meanings and relationships algorithmically, achieving full automation while maintaining accuracy
3Extent of automation
If context clouds and occurrence lists are used to analyze unstructured data, then extent of automation is improved, but device complexity is worsened
Solution Approach 1:
The system segments the complex task of analyzing unstructured data into distinct components: context cloud generation, occurrence list creation, target object identification, and relationship determination. Each component handles a specific aspect of the analysis, making the overall automated system more manageable and maintainable despite its complexity
Solution Approach 2:
Context clouds and occurrence lists serve as intermediary structures that bridge unstructured data and the knowledge graph. These intermediaries organize and structure information in a way that facilitates automated relationship identification, reducing the complexity of directly mapping unstructured text to structured knowledge
Data Source
AI summary
Computer-implemented systems and methods are disclosed for building knowledge bases, such as knowledge graphs, using context clouds. According to certain embodiments, a target object is identified in a portion of unstructured or semi-structured data in a target document, which does not conform to a predefined structure or pattern. A knowledge server may build a context cloud for the target document. The knowledge server may analyze one or more other documents stored in a networked database, to identify candidate documents that may include a meaning or relationship associated with the target object. The knowledge server may analyze one or more context clouds for the candidate documents to determine a meaning or relationship of the target object based on objects in the candidate document(s). The knowledge server may associate the determined meanings and/or relationships with the target object in the target document, thereby creating a new portion of a knowledge graph.