Project: Making the Invisible Visible: Identifying and Linking Internal Knowledge Sources in an Industrial KG
Description
Background
Marel, a global leader in the food processing industry, specializes in designing and manufacturing advanced machinery for processing poultry, meat, and fish. Effective knowledge sharing among engineers at Marel is important for sustaining business operations.
Description
This project will explore how internally referenced knowledge sources—such as documents, spreadsheets, machine data, and social networks—mentioned during expert interviews at Marel can be systematically identified and integrated into the Marel Knowledge Graph. These interviews, available as transcripts and recordings, contain insights into how employees create, interact with, and use knowledge within the organization. Currently, employees might only need a very specific piece of information or might not even know that a specific piece (or a system as a whole) of information exists.
In the current version of MarelKG such references remain disconnected from Marel’s formal knowledge infrastructure, limiting the graph’s completeness and practical utility. The project aims to research how these information sources are available systematically (if at all), how they should and can be linked. By developing a schema proposal for specifying these internal sources, a method should be designed to link them to relevant entities (according to Marel employees) in the knowledge graph. The outcome will be an improved version of MarelKG, and researching the evaluation of its usability.
Student requirements
• Pragmatic but research oriented, with the intention to publish the results
• Work in Boxmeer 3-4 days a week
• Having passed (or intending to take) Knowledge Engineering (2AMD20) is a plus
Perks
• An internship allowance and travel allowance
Details
- Supervisor
-
George Fletcher
- Secondary supervisor
-
Sepehr Sadoughi
- External location
- Marel
- Interested?
- Get in contact