TU Darmstadt / ULB / TUbiblio

Extracting problem related entities from production chats to enhance the data base for assistance functions on the shop floor

Müller, Marvin ; Lee, Ji-Ung ; Frick, Nicholas ; Stangier, Lorenz ; Gurevych, Iryna ; Metternich, Joachim (2021)
Extracting problem related entities from production chats to enhance the data base for assistance functions on the shop floor.
In: Procedia CIRP, 103
doi: 10.1016/j.procir.2021.10.037
Article

Abstract

This paper presents an approach to recognize problem related entities in production chats to structure the informal communication and include arising problems into digital shop floor management and its assistance functions. Requirements are derived from employee surveys, company surveys and from union experts. Based on annotated data that has been collected during a simulation in the process learning factory ``Center for Industrial Productivity'' (CiP) at the Technical University of Darmstadt, approaches for identifying and structuring problem recognition and solution in production chat logs are evaluated. Finally, a system design is suggested to utilize such an entity recognition in an industrial chat application to improve digital shop floor management systems.

Item Type: Article
Erschienen: 2021
Creators: Müller, Marvin ; Lee, Ji-Ung ; Frick, Nicholas ; Stangier, Lorenz ; Gurevych, Iryna ; Metternich, Joachim
Type of entry: Bibliographie
Title: Extracting problem related entities from production chats to enhance the data base for assistance functions on the shop floor
Language: English
Date: 20 October 2021
Publisher: Elsevier B.V.
Journal or Publication Title: Procedia CIRP
Volume of the journal: 103
DOI: 10.1016/j.procir.2021.10.037
URL / URN: https://www.sciencedirect.com/science/article/pii/S221282712...
Abstract:

This paper presents an approach to recognize problem related entities in production chats to structure the informal communication and include arising problems into digital shop floor management and its assistance functions. Requirements are derived from employee surveys, company surveys and from union experts. Based on annotated data that has been collected during a simulation in the process learning factory ``Center for Industrial Productivity'' (CiP) at the Technical University of Darmstadt, approaches for identifying and structuring problem recognition and solution in production chat logs are evaluated. Finally, a system design is suggested to utilize such an entity recognition in an industrial chat application to improve digital shop floor management systems.

Uncontrolled Keywords: Digital shop floor management, entity recognition, natural language processing, UKP_a_DLinNLP; UKP_a_TexMinAn, UKP_p_texprax
Divisions: 16 Department of Mechanical Engineering
16 Department of Mechanical Engineering > Institute of Production Technology and Machine Tools (PTW)
Date Deposited: 05 Nov 2021 07:04
Last Modified: 05 Nov 2021 07:04
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details