Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

ORB: Pioneering Graph Database Technology using Generative AI

Reference number
Coordinator Kungliga Tekniska Högskolan - DIVISION OF SOFTWARE AND COMPUTER SYSTEMS
Funding from Vinnova SEK 836 258
Project duration September 2023 - December 2024
Status Completed
Venture Emerging technology solutions
Call Emerging technology solutions stage 1 2023

Important results from the project

The project has contributed to the creation of the world´s first error-proof prediction system based on graph technology. The technology we developed enables different industries to “tune” the level of AI-generated content to their specific needs. The technology thus creates new opportunities for reliable AI solutions in critical application areas where safety and precision are crucial.

Expected long term effects

The project is expected to democratize the use of AI in all industries in the long term, regardless of their demands for precision or tolerance for “hallucinations.” The technology allows for the margin of error to be adjusted as needed. For example, medical researchers can use generative AI to predict the effects of new drugs with a low margin of error, while creative and commercial industries, such as marketing or design, can accept higher errors to generate new ideas more quickly.

Approach and implementation

The project followed the planned structure, but the development went faster than expected and reached the TRL4 level. Even before the end of the project, we had companies that showed interest in testing the technology. This allowed us to use the project time to adapt Orb to their needs. An unexpected insight was that many companies lack experience in creating and managing graph data. This led us to expand our strategy to also include data management and integration.

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 7 March 2025

Reference number 2023-01406