Real world, business-focused success stories of how knowledge graphs, ontologies, and AI have been applied to address business needs. The track will focus on return on investment and value to organizations.
Managing connections between types and individuals is a crucial aspect of applied ontology, and effective scaling is one aspect of the challenge. At Indeed, we help people get jobs. In order to do this, we need to understand jobseekers’ qualifications and the requirements of jobs they search for. Millions of jobs and job seekers are connected to our system on any given day, however, and they could not possibly all be included in a single accurate and efficient knowledge graph.
Fortunately, a lot of common-sense general reasoning is about types of things. Our taxonomies and ontology form a graph of types, which are used to apply metadata to documents at scale. We also leverage meta-types and type-type relationships in order to provide the most sophisticated and accurate metadata. In implementing these solutions, we take advantage of a useful ambiguity: in the SKOS (Simple Knowledge Organization System) standard, a “Concept” is syntactically an individual, but most concepts seem to have semantic uses as types. This talk will discuss how using skos:Concept for first-order types and rdfs:Class for meta-types enables automated reasoning patterns and dynamic application behavior without any need for a knowledge graph of individuals.