The usage of language models for human assistance in production failure root cause analysis
- Downtimes (outages) are unfavorable and costly events in production. Although approaches exist, they have to be implemented mainly manually and with a huge effort. Language models could be useful to support the production root cause failure analysis and help to get production up and running again more quickly. However, sparse research focused on this point so far. Therefore, it is still unclear how the usage of language models for human assistance in production failure root case analysis should be implemented. A qualitative expert study was conducted to reveal the potentials of such an approach and to find suitable use cases for language models. Based on the insights triggering factors, use cases as well as benefits and risks were identified and summarized within a model.
| Author of HS Reutlingen | Möhring, Michael; Bierhals, Daniel |
|---|---|
| Editor of HS Reutlingen | Zimmermann, Alfred |
| DOI: | https://doi.org/10.1007/978-981-97-8598-8_5 |
| ISBN: | 978-981-97-8597-1 |
| ISBN: | 978-981-97-8598-8 |
| Published in: | Human centred intelligent systems : proceedings of KES-HCIS 2024 conference |
| Publisher: | Springer |
| Place of publication: | Singapore |
| Editor: | Alfred ZimmermannORCiD, Rainer SchmidtORCiD, Lakhmi C. Jain, Robert J. Howlett |
| Document Type: | Conference proceeding |
| Language: | English |
| Publication year: | 2025 |
| Page Number: | 11 |
| First Page: | 39 |
| Last Page: | 49 |
| PPN: | Im Katalog der Hochschule Reutlingen ansehen |
| DDC classes: | 004 Informatik |
| Open access?: | Nein |
| Licence (German): |  In Copyright - Urheberrechtlich geschützt |
