Autodesk Knowledge Transfer Graph: Just in time for Halloween - The Haunting of Hill House

I was watching a new Netflix series and I couldn't tell one character from the other...

Autodesk is working to help solve some of the world's most complex design problems, from pressing ecological challenges to the development of scalable smart infrastructure. Designers use Autodesk tools to not only create plans for buildings, for example, but also to simulate their impact on the environment and track their performance over time. Autodesk Research is unique in that we are dedicated to innovation and discovery in this realm. Our interests range from methods to help users learn powerful digital prototyping tools, to visualization and simulation techniques which enable designers to achieve new levels of performance. Advancing the state of the art in human-computer interaction, computer graphics, and digital design technology, we collaborate openly with researchers at leading universities around the world.

Principal Research Scientist, Michael Glueck, works in our technology center in Toronto. The Autodesk Technology Centers are where the future of making takes shape. With locations around the world, we collaborate with industry, academic, and entrepreneurial communities to reimagine what it means to design and make, and create a shared vision of the future that will enable us to do more and make better things with less negative impact. Specifically, the Autodesk Technology Center in Toronto supports the research and development of emerging technologies, including machine learning, generative design, and artificial intelligence, to reimagine how we design and make things.

One of the projects that Michael and other Autodesk Researchers are working on is the Knowledge Transfer Graph. Autodesk researchers developed an interactive visual analysis system that supports asynchronous investigative document analysis tasks. Users create nodes and define relationships among them. I used the technology to map the various characters in the Netflix series as I watched each episode:

The Haunting of Hill House is an American supernatural horror television series that is loosely based on the 1959 novel of the same name by Shirley Jackson. In the summer of 1992, the Crain family temporarily move into an old mansion, Hill House. They experience paranormal occurrences and tragic loss, forcing them to move out of the house. In October 2018, 26 years after the hauntings, the Crain siblings and their estranged father reunite after tragedy strikes again, forcing them to confront their inner demons from their shared childhood while mourning their losses. ^[Wikipedia]

The Knowledge Transfer Graph helped me keep all of those characters straight. The series bounces back between the present day and when the characters were children, so time is constantly changing. And since they are a family, sisters look like sisters or their mom, and the son looks like the dad. In my graph, although I could have easily done so for the mothers also, I only listed the children under the fathers to reduce the complexity of the graph. Documenting the paternal relationships and marriages was sufficient for me to know who was who.

Thanks to my colleague, Hilmar Koch, who let me run the Knowledge Transfer Graph from his server.

Power is alive in the lab.