.png){kind=icon}
.png){kind=icon}
Return
Shedding light on blind spots-Developing a reference architecture to leverage video data for process mining
.png){kind=icon}
OA
AI
DOI：10.1016/j.dss.2022.113794.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Process mining is one of the most active research streams in business process management. In recent years, numerous methods have been proposed for analyzing structured process data. In many cases, however, only the digitized parts of processes are directly captured by process-aware information systems, whereas manual activities often leave blind spots in the process analysis. While video data can contain valuable process-related information that is not captured in information systems, a standardized approach to extracting event logs from unstructured video data remains lacking. To solve this problem and facilitate the systematic usage of video data in process mining, we have designed the ViProMiRA, a reference architecture that bridges the gap between computer vision and process mining. The various evaluation activities in our design science research process ensure that the proposed ViProMiRA allows flexible, use case-driven, and context-specific instantiations. Our results also show that a prototypical implementation of the ViProMiRA is capable of automatically extracting more than 70% of the process-relevant events from a real-world video dataset in a supervised learning scenario.
Keywords:
computer vision
process mining
reference architecture
unstructured data
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.8
Papers:
3.8K
Citations:
1.5W