Skip to content

Ingest, Enrich, Index

Frank Linnenbach
Frank Linnenbach |

Online Conference: The Art Museum in the Digital Age

einlesen-anreichern-indexierenPaul Clough, © Österreichische Galerie Belvedere 

Ingest, Enrich, Index

The "Story at Mount Oswald" project combines multiple collections into a single structure that is accessible around the clock via a search service. From the start, the Durham County Council decided to use digital technologies such as artificial intelligence (AI).

The project was divided into three steps:

  • Ingest
  • Enrich
  • Index

In the first step, Ingest, connections to the source were established and data was retrieved. Afterwards, transformations were applied and the data was mapped onto a global schema.

In the second step, Enrich, associated name entities were identified with the help of AI and lists, additionally ages and cross-connections were added, and spatial information and duplicates were detected.

The last step, Index, involved the creation of a search index in which documents were added, updated, and deleted. The index is constantly monitored and optimized.

Paul Clough learned some important lessons along the way:

  • Multiple stakeholders must be involved to ensure a comprehensive view of the project.
  • Knowledge about the data and the domain is crucial.
  • A simple approach and continuous building are advantageous.
  • The end goal should always be kept in mind to stay on course.
  • Manage the expectations and costs of the project.

According to Clough, the project goes beyond the purely technological level and also emphasizes the social benefits of digitalization for cultural heritage in Durham. The digitalization of the collections thus opens up new opportunities for the public.

Thank you Paul Clough for the lecture "Ingest, Enrich and Index. Building a Cross-Collection Search Service for Durham’s New Cultural Heritage Site" at the online conference "The Art Museum in the Digital Age".

Share this post