Knowledge graphs are prevalent, especially in medicine and healthcare – but so far, only experts can operate them. A natural language chatbot can change that. We have developed a cloud-native medical chatbot called Doctor.ai, backed by a Neo4j graph. We can employ either AWS Lex, GPT-3, or Alan AI as the natural language understanding engine.
This chatbot works in English and can understand German, Chinese, and Japanese. Users can dictate or type their questions. Doctor.ai then converts the questions into Cypher. It queries the Neo4j graph database, gets the answers, and formulates them back in the target languages. With Neovis, we can display Neo4j results in graphs too.
Because it is completely in the cloud, Doctor.ai can scale automatically. It's also easy to use. Because Doctor.ai is also a framework, we can use different products to fulfill the same function. The recent explosion of natural language AI products will help us further improve Doctor.ai. Additionally, you can switch out the backend data and use this technique for logistics, forestry, and other industries.
Speakers: Sixing Huang
Format: Full Session 30-45 min
Level: Advanced
Topics: #KnowledgeGraph, #Featured, #Healthcare, #Advanced
Region: APAC
Slides: https://dist.neo4j.com/nodes-20202-slides/042%20Doctor.ai%20A%20Graph-Based%20Medical%20Chatbot%20-%20NODES2022%20APAC%20Advanced%202%20-%20Sixing%20Huang.pdf
Visit https://development.neo4j.dev/nodes-2022 learn more at https://development.neo4j.dev/developer/get-started and engage at https://community.neo4j.com