Knowledge Graphs(KG) are used to represent the real-world relationships between entities and to make connections between data points. They can use a combination of structured and unstructured data to create a graph structure that can be used by AI applications. Data in a KG is stored as nodes and edges in a graph structure, which can then be used to retrieve information from the knowledge graph.
They can be used to create more accurate and personalized AI systems that can better understand the context of data and make decisions based on the relationships between data points.
Summary
- Knowledge graphs are networks (graphs) of things (entities) and their relationships to other things.
- Knowledge graphs consist of Nodes (Entities / Names etc) and Verticies (relationship between these entities).
- A simple example is a social network where the Nodes are people (“Paco”, “Juanita”, “Sara”) and the verticies are realtaionships between nodes (“Likes”, “Is part of the same group”, “Is friends with” … etc.)
- Interpretation of a knowledge graph can lead to “wisdom”. That is to say, studying several nodes and their relationships can lead to “know-how”.
- Application of AI can include
- Automatically adding knowledge to a knowledge graph
- KG analysis – sporting patterns and predicting links
- Recommending contacts with similar characteristics or interests (Social Networks, Enterprise)
- Recommending similar products (eCommerce, Sales)
- Identifying processes from groupings of nodes and then discovering, recommending, predicting similar processes in other parts of the company
