OMiLAB
Wilfrid Utz
Type: software-download
TRL: 5-6
Scene2Model is an environment for supporting physical design thinking workshops based on paper figures, by offering an environment for automatically creating digital models out of the physical models. These digital models are usable during and after the workshop, where the represent the created idea for humans, based on their semantically rich representation. But the models are also processable, meaning functionality is offered based on this processing, which supports the users.
The core is an ADOxx-based modelling tool, which manages the creation and processing of the digital conceptual models. It enables an easy adaptation of the available objects to represent the idea during the usage of the tool, allowing a continuous tailoring of the tool to the domain needs and thereby increasing the expressiveness of the created models.
The modelling tool can be combined with additional components, which facilitate the automatic creation of digital models, out of the physical ones and therefore reduce manual and cumbersome tasks of the users. The components, can be easily installed at workshop sites, allowing the complete utilisation of Scene2Model.
All the components needed to use Scene2Model, are available over its webpage (see links provide below) and open source. Therefore, with Scene2Model not only the available figures can be easily adapted, which is provided as an important feature of the tool. But also, the tool as a whole can be adapted to new circumstances if needed.
Contact Person
Information
More information is provided in:
- our D2.1, to be precise
- chapter 2.1: Design Methodology for Decision Process Design
- chapter 3.2: The Model-Based Alignment
- chapter 3.7.3 of our D3.3: Using Conceptual Models to Support Explanations within Decision Support Systems
In FAIRWork we integrated the Scene2Model tool in the Design Methodology introduced in our Deliverable 2.1 and the two paper listed below. We applied physical workshops between project partners and stakeholders from the production lines of the use case partners. The goal was to understand the decision scenarios that should be tackled by FAIRWork’s Democratic AI-based Decision Support System (DAI-DSS). The results of these workshops are than enriched and shared with all the involved parties in providing the DAI-DSS, to have a shared understanding. This high level models were afterwards also translated into more detailed models, like BPMN or DMN, to provide more detailed understanding of the decision scenarios.
To improve the usage of within FAIRWork, the Scene2Model environment was not just used but also enhanced an improved.
Papers regarding Scene2Model in the context of FAIRWork
- Woitsch, R., Muck, C., Utz, W., & Zeiner, H. (2023, September). Towards a democratic AI-based decision support system to improve decision making in complex ecosystems. Joint Proceedings of the BIR 2023 Workshops and Doctoral Consortium Co-Located with 22nd International Conference on Perspectives in Business Informatics Research (BIR 2023). https://ceur-ws.org/Vol-3514/paper94.pdf
- Woitsch, R., Muck, C., Utz, W., & Zeiner, H. (2024). Enable Flexibilisation in FAIRWork’s Democratic AI-based Decision Support System by Applying Conceptual Models Using ADOxx. Complex Systems Informatics and Modeling Quarterly, 38, 27–53. https://doi.org/https://doi.org/10.7250/csimq.2024-38.02
- Muck, C., & Utz, W. (2023). A Recognition Service for Haptic Modelling in Scene2Model. In AAAI Spring Symposium: MAKE. https://ceur-ws.org/Vol-3433/short4.pdf
In addition to the improvement to the Scene2model environment, an experiment and corresponding extension to the Scene2Model modelling tool were created during the project, analysing how data from the DAI-DSS can be fed back into high-level decision scenario models created with Scene2Model. The goal is to enrich these models with information created by the DAI-DSS to visualize made decisions. The enhanced models can than be used to support the explanation of how a decision is made on a high abstraction level. The high abstraction level facilitates a broader understanding by stakeholders with various backgrounds.
This idea is also published in the following paper:
- Muck, C., Tschuden, J., Zeiner, H., & Utz, W. (2024). Explainability of Industrial Decision Support System using Digital Design Thinking with Scene2Model. Cognitive Computing and Internet of Things, 124(124). https://doi.org/http://doi.org/10.54941/ahfe1004710
The code an information on the extension and how to use it can be found on the GitLab project of the extension:
Use
More information on how to use the Scene2Model tool and how to download it can be found on the Scene2Model page:
More information on how to set up and use the extension can be found at its GitLab project:
Extend
For tailoring the Scene2Model environment to specific needs, different options are available. It posses build in functionality to adapt the available domain concepts to represent the scenarios. A description on how to apply such changes can be found in the documentation:
The Scene2Model modelling tool was implemented with ADOxx Metamodelling Platform, and therefore this platform can be used to extend the modelling tools functionality. The source of the tool can be found at: