Digitization

ExANT

Consortium from Germany uses AI to convert technical text into a form that computers can understand.

Today, requirements for technical systems are still predominantly written in natural language text, which is incomprehensible to computers. It is true that text can be manually converted into a form that a computer can understand. However, this is prone to errors and costs a lot of time and money, especially for complex systems such as those used in aerospace. This hurdle is to be overcome through the use of artificial intelligence (AI).

The "ExANT: Extraction of requirements from natural language text" project aims to demonstrate whether and how this translation can be reliably automated using natural language processing (NLP) methods - a sub-area of AI. The consortium consists of the Institute of Space Systems at the University of Stuttgart, the space systems company OHB System AG, the technology company OHB Digital Services and the software technology specialist BSSE, which is also coordinating the consortium. Various NLP tools - including some open source systems - are to be applied to natural language requirements from real space projects.

The participants want answers to the following questions, among others: What are the potential time and cost savings? How can AI errors be recognized or avoided during translation? Can the content of the requirements be - significantly - improved using NLP tools? This concerns, for example, unclear or incompletely described requirements, which can lead to delays and additional costs.

The project is funded by the Federal Ministry for Economic Affairs and Energy as part of the National Program for Space and Innovation and is technically and administratively managed by the German Space Agency at DLR. The work should be completed by the end of November 2023.