PoolParty Demo: A Knowledge Graph Driven Recommender Engine

By on

Download the slides here>>

According to various studies, employees in knowledge-intensive industries spend >20% of their time searching for the right information. The right information might be the relevant document you are looking for, the right person to talk to, the right piece of equipment to use, etc. So relevance is key and ideally, you would want to describe what you are looking for and get back what best meets your expectations.

It is quite clear that no traditional search system can meet these expectations. But a recommender system built on a knowledge graph can do the trick. When you connect your business objects to the knowledge graph, each of those objects is given a semantic footprint. This footprint can be generated automatically, regardless of the type of object. It can be used in many cases to describe a document, a person, a device in more detail. It can be used to recommend similar objects or objects of a different type instead.

In my talk, I will show how such a system is built and works in a real-world example.

Helmut Nagy

Job Title: COO, Director of Professional Services

Since 2013, Helmut has been COO of the Semantic Web Company and is responsible for design and implementation of all customer-oriented processes, together with the involved teams and team leads based on SWC’s business strategy. He is working as the senior consultant on several customer projects (industry and public administration) and participates in European research projects. Helmut is co-author of “The Knowledge Graph Cookbook”.

Leave a Reply