The GraphRAG Manifesto: Unlock Better GenAI Results With Knowledge Graphs | Read Now

Neo4j logo

Nodes2024

Dev Conference by Neo4j

Register for NODES 24

You only need to register once to attend all sessions.

Building Knowledge Graphs with LLMs from USPTO Patent Data

Session Track: Graphs

Session Time:

Session description

We transformed 50 years of complex USPTO patent data into a knowledge graph. Key points we'll cover: - Vector Embeddings in Neo4j - Simplifying Legal Jargon with GPT - Visualizing Patent Landscapes - Finding Similar Patents with RAG - Interactive Results with Streamlit - Analyzing Patent Influence with PageRank Explore how combining Neo4j and AI can benefit a wide range of industries facing complex data.

Speaker

photo of Tim Eastridge

Tim Eastridge

Founder, Eastridge Analytics

Timothy (Tim) Eastridge is an A.I. consultant passionate about innovation and the integration of knowledge graphs with Generative AI and Large Language Models (LLMs). Tim's expertise in extracting actionable insights from complex datasets positions him as a leader in transforming data into understandable formats. Tim's innovative solutions led to billions of dollars of suspicious activity reports (SARs) for a major bank related to the Paycheck Protection Program (PPP), and Tim continues this work as a consultant to the Pandemic Response Accountability Committee (PRAC) continuing to help the team identify, prioritize, and indict fraudsters using a combination of unsupervised machine learning and recommendation systems. Tim's implementations of graph neural networks (GNNs) in the private equity space uncovered alpha and new investment strategies for clients. His mission is to illuminate the hidden connections within data, transforming complex webs of interactions into easily comprehensible formats to deliver previously hidden, actionable insights.