Room 8513, 154-42, Gwangkyosan-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do, 16227, Republic of Korea.

Tel: 82-31-249-9679
email: kwang@kgu.ac.kr

Research on BPM-Supported Enterprise Social Network Intelligence Frameworks (2017.03.01 – 2020.02.29)

Main conents of this project is to research & develop BPM-supported enterprise social network intelligence framework with discovery/rediscovery, analyze, visualize algorithms and techniques for mining human oriented network intelligence – social network intelligence, affiliation network intelligence, information diffusion network intelligence from the BPM-supported enterprise big data.

The Yearly Research Purposes

The 1st Year: BPM-supported enterprise social network intelligence frameworks
The 2nd Year: BPM-supported enterprise affiliation network intelligence frameworks
The 3rd Year: BPM-supported enterprise information diffusion network intelligence frameworks
Research Details

Define three BPM-supported enterprise social network models from BPM-supported enterprise business process model based on ICN and research conceptual intelligence framework which is discovering/rediscovering, analyzing, and visualizing these enterprise social network models from BPM-supported enterprise big data.
Develop a technique that discovers/rediscovers three enterprise social network models from BPM-supported enterprise big data which contains the execution history of XPDL-based process model, process package, and organization package.
Develop a log format or state model for defining execution history of the process model.
Develop an intelligence system for analyzing, predicting, monitoring, and controlling the performer oriented social network/affiliation network/information diffusion network intelligence from BPM-supported enterprise social network intelligence models.
Extend the basic social network analyzing techniques such as density analyze and centrality analyze to adapt to BPM-supported enterprise social network models.
Develop large-scale visualizing technique to graphically represent analyze results of the BPM-supported enterprise social network models.