In 2016, 25% of web searches on Android were made by voice and this percentage is predicted to double by 2018.
From Amazon Alexa to Google Home, smart watches and in-car systems, touch is no longer the primary user interface.
This talk will demonstrate how graphs and machine learning are used to create an extracted and enriched graph representation of knowledge from text corpus and other data sources.
This representation is then used to map user intents made by voice to an entry point in this Neo4j-backed knowledge graph.
Every user interaction is then taken into account in any further steps and we will highlight why graphs are an ideal data structure for keeping an accurate representation of user context in order to avoid what is called “machine or bot amnesia.”
The session will conclude by explaining about how recommendations algorithms are used to predict next steps of the user’s journey.
Christophe Willemsen is a Principal Consultant at GraphAware, the world's number one Neo4j consultancy.
He is an expert on the Neo4j graph database and the Cypher query language, and a skilled software engineer who has been involved in many Neo4j projects optimizing complex Cypher queries, building enterprise-grade, graph-based recommendation engines, and developing search tools combining Neo4j and the Elastic Stack.
Christophe is also the author of the Neo4j driver for PHP and many Java extensions for Neo4j, available on the GraphAware Github.
He has a deep passion for everything Computer Science and has recently focused on the application of natural language processing in voice-driven interfaces and chatbots. Christopher speaks English, French and Dutch and lives with his family in Italy, where he learns Italian.
You can find him on Twitter with handle @ikwattro or at conferences and meetups all around the world.