How to use large language models and knowledge graphs to manage enterprise data

Join senior executives in San Francisco on July 11-12 to learn how leaders are integrating and optimizing AI investments for success. Find out more

In recent years, knowledge graphs have become an important tool for organizing and accessing large volumes of enterprise data across a variety of industries, from healthcare and manufacturing to banking and insurance , retail, etc.

A knowledge graph is a graph-based database that represents knowledge in a structured and semantically rich format. This could be generated by extracting entities and relationships from structured or unstructured data, such as text from documents. A key requirement for maintaining data quality in a knowledge graph is to base it on a standard ontology. Having a standardized ontology often involves the cost of integrating that ontology into the software development cycle.

Organizations can take a systematic approach to generating a knowledge graph by first ingesting a standard ontology (like insurance risk) and using a large language model (LLM) like GPT-3 to create a script to generate and populate a graph database.

The second step is to use an LLM as a middle layer to take natural language text inputs and create queries against the graph to return knowledge. Build and search queries can be customized based on the platform the chart is stored on, such as Neo4j, AWS Neptune, or Azure Cosmos DB.

Event

Transform 2023

Join us in San Francisco on July 11-12, where senior executives will discuss how they've integrated and optimized AI investments for success and avoided common pitfalls.

Register now Combining ontology and natural language techniques

The approach described here combines ontology and natural language-driven techniques to create a knowledge graph that can be easily queried and updated without extensive engineering efforts to create bespoke software. Below we give an example of an insurance company, but the approach is universal.

The insurance industry faces many challenges, including the need to manage large amounts of data both effectively and efficiently. Knowledge graphs make it possible to organize and access this data in a structured and semantically rich format. This can include nodes, edges, and properties where nodes represent entities, edges represent relationships between entities, and properties represent attributes of entities and relationships.

The use of a knowledge graph in the insurance industry has several advantages. First, it provides a way to organize and access data that is easy to query and update. Second, it provides a way to represent knowledge in a structured and semantically rich format, which facilitates its analysis and interpretation. Finally, it provides a way to integrate data from different sources, including structured and unstructured data.

Below is a 4-step approach. Let's go through each step in detail.

Approach Step 1: Study the ontology and identify entities and relationships

The first step in generating a knowledge graph is to study the relevant ontology and identify the entities and relationships relevant to the domain. An ontology is a formal representation of knowledge...