Knowledge Maps:

What happens when you combine graph technology, interactive visualization, and generative AI?

Kineviz builds a visual platform used for collecting and exploring complex connections in data, uncovering hidden patterns, and ultimately helping people make better-informed decisions. Their customer use cases span across anti-fraud, cybersecurity, law enforcement, life sciences, and much more.

Many people are familiar with the basics of graph visualization, such as using pre-set layouts, though Kineviz goes much further. Consider other ways in which visualizations could be augmented… How about visually comparing results from different graph algorithms side by side? How about leveraging generative AI tools to augment what you’re seeing in a graph? Instead of working to extract “facts” from unstructured content, Kineviz promotes a practice called knowledge maps for developing evidence-linked structure and context within a graph. One might think of this as a kind of “late-binding” to build context and meaning gradually — letting a team work together to interpret the data and figure out its structure over time, rather than locking everything into rigid definitions upfront. The graph itself serves as an evidentiary chain from structure back to language. This is important for using entity resolution with graphs, where some resolutions must be scoped based on available data, while other resolutions require judgement by users after they’ve been working with the graph visualization.

In this episode we’re delighted to host Weidong Yang from Kineviz as our guest to explore how advanced graph visualizations and AI tools work together. We’ll also talk about related communities and projects — including Kinetech Arts, the project from which Kineviz grew.

We’d love to see you at our next event! Keep an eye out for our upcoming webinars by subscribing to our mailing list and following Senzing on LinkedIn.

Related Videos