AI-powered Digital Assistant (AIDA)

The AI-powered Digital Assistant (AIDA) was developed under ESA TDE activity 1000033025 to explore use cases and technologies able to assist systems engineers. AIDA is able to analyse systems engineering models and:

  • UC1: propose requirement flow-down, traceability between existing requirements and evaluation of their verification method
  • UC2: propose new elements (functions/components) for existing system architectures
  • UC3: check the coherency between requirements and architectures

For this, different machine learning techniques are used including Natural Language Processing (NLP), classification, clustering and Large Language Models (LLMs).

The estimated Technology Readiness Level (TRL) is 4.

Final Data Pack

The released data pack contains:

  • A series of documents describing the use cases, technologies used, validation, etc. as well as the software user manual
  • The source and application code: trained models, training code and dummy datasets for training

AIDA Documentation and Software are available to download. 

Please, register/ log in to see the download links.

Download Instructions for AIDA SW

This procedure was tested using 7zip. Make sure to have the application installed for guaranteed results. 

  1. Download the files AIDA_SW.zip.001 til AIDA_SW.zip.005
  2. In the AIDA_SW files download location,
    1. Rename AIDA_SW.zip.001.zip to AIDA_SW.zip.001
    2. Rename AIDA_SW.zip.002.bin to AIDA_SW.zip.002
    3. Rename AIDA_SW.zip.003.bin to AIDA_SW.zip.003
    4. Rename AIDA_SW.zip.004.bin to AIDA_SW.zip.004
    5. Rename AIDA_SW.zip.005.bin to AIDA_SW.zip.005
  3. Right click on AIDA_SW.zip.001 and select "Extract files"
  4. The reconstitution of the AIDA_SW.zip archive parts should result in SW.zip
  5. Extract the SW.zip archive by right clicking on it and select "Extract files"
  6. The resulting extracted files should be a app folder accompanied by 5 files (yml scripts, dockerfile, a readme file and a license file) 

Comments & Support

You can direct your comments or questions to alberto.gonzalez.fernandez@ext.esa.int.