Graph Machine Learning Recommender POC for Public Safety Agency

The Challenge A government agency responsible for regulating and enforcing occupational safety sought to build a content recommender proof-of-concept (POC) that leverages semantic technologies to model the relevant workplace safety domains. The agency aimed to optimize project planning and construction site design by centralizing information from siloed and unstructured sources and extracting a comprehensive view of potential safety risks and related regulations. Automatically connecting and surfacing this information in a single location via the recommender would serve to minimize time currently spent searching for content and limit burdensome manual efforts, ultimately improving risk awareness and facilitating data-driven decision-making for risk mitigation and regulatory adherence.  The Solution The agency partnered with EK to develop a knowledge graph-powered semantic recommendation engine with a custom front-end. Based on the use case we refined for construction site project planners, we redesigned the agency’s applicable taxonomies and developed an ontology that defined relationships to model the recommendation journey from the user’s inputs of construction site elements to the expected outputs of risks and regulations.