17454909. INDENTIFYING RELEVANT GRAPH PATTERNS IN A KNOWLEDGE GRAPH BACKGROUND simplified abstract (International Business Machines Corporation)

From WikiPatents
Jump to navigation Jump to search

INDENTIFYING RELEVANT GRAPH PATTERNS IN A KNOWLEDGE GRAPH BACKGROUND

Organization Name

International Business Machines Corporation

Inventor(s)

Joern Ploennigs of Dublin (IE)

Konstantinos Semertzidis of Thessaloniki (GR)

Fabio Lorenzi of Tyrrelstown (IE)

INDENTIFYING RELEVANT GRAPH PATTERNS IN A KNOWLEDGE GRAPH BACKGROUND - A simplified explanation of the abstract

This abstract first appeared for US patent application 17454909 titled 'INDENTIFYING RELEVANT GRAPH PATTERNS IN A KNOWLEDGE GRAPH BACKGROUND

Simplified Explanation

The patent application describes a method for identifying relevant graph patterns in a knowledge graph using a processor in a computing environment.

  • Data elements from a knowledge graph and associated datasets are identified, which are related to nodes in the knowledge graph and external to it.
  • Subgraphs are selected and created based on missing data elements and inferred knowledge data.
  • The knowledge graph is modified by incorporating the selected subgraphs.

Potential Applications

This technology has potential applications in various fields, including:

  • Data analysis and mining: The method can be used to identify patterns and relationships in large knowledge graphs, enabling better data analysis and mining.
  • Recommendation systems: By identifying relevant graph patterns, the method can enhance recommendation systems by suggesting more accurate and personalized recommendations.
  • Semantic search: The technology can improve semantic search engines by identifying relevant patterns and relationships in knowledge graphs, leading to more precise search results.

Problems Solved

The technology addresses several problems in knowledge graph analysis and modification, such as:

  • Incomplete data: By selecting and creating subgraphs based on missing data elements, the method helps fill in gaps in knowledge graphs, improving their completeness and accuracy.
  • Inferred knowledge: The method leverages inferred knowledge data to create subgraphs, enabling the incorporation of additional information into the knowledge graph.
  • Scalability: The technology can handle large knowledge graphs and associated datasets, allowing for efficient analysis and modification.

Benefits

The use of this technology offers several benefits, including:

  • Improved data analysis: By identifying relevant graph patterns, the method enables more comprehensive and insightful data analysis, leading to better decision-making.
  • Enhanced recommendation systems: The technology can enhance recommendation systems by providing more accurate and personalized recommendations based on identified graph patterns.
  • More precise semantic search: By incorporating relevant graph patterns into knowledge graphs, the method improves the precision of semantic search engines, delivering more relevant search results.


Original Abstract Submitted

Various embodiments are provided for identifying relevant graph patterns in a knowledge graph in a computing environment by a processor. Data elements may be identified from a knowledge graph and associated datasets that is related to one or more nodes of the knowledge graph and external to the knowledge graph. One or more subgraphs may be selected and created based on missing data elements and inferred knowledge data. The knowledge graph may be modified with one or more subgraphs.

Retrieved from "http://wikipatents.org/index.php?title=17454909._INDENTIFYING_RELEVANT_GRAPH_PATTERNS_IN_A_KNOWLEDGE_GRAPH_BACKGROUND_simplified_abstract_(International_Business_Machines_Corporation)&oldid=23541"