Search

Social norms constrain behavior of individuals either through obligating or prohibiting certain types of behavior. Norm-based mechanisms have only recently found applications in enhancing decisions of knowledge workers in an automated business process management context. While previous work on such social BPM has focused on the use of prohibition norms based approach for norm inference, this paper extends the work by combining both prohibition and obligation norm based approaches to provide a holistic approach of norm inference. The norms inferred in the context of business process executions are then recommended to users so as to enable them to make informed decisions. The previous work on prohibition norm inference focused on identifying failure cases, which is now complemented by first inferring norms from the successful process execution cases (i.e. obligations) and then inferring prohibition norms. This approach based on considering social feedback (i.e. inferring what is obliged and prohibited from history logs of process execution) shows encouraging results under uncertain business environments. Using simulation results the paper demonstrates that using the norm based mechanism results in reduced failure rates in the decision making of a knowledge worker while still providing maximum flexibility for the user to choose from a range of actions to execute.

Decision making in complex and volatile business environments is still the realm of human decision makers since their knowledge and experience are paramount in making good decisions. The standard run-of-the-mill automation approaches for making decisions do not work well in these contexts. This paper investigates the use of a socially-inspired norm inference mechanism proposed in the area of multi-agent systems to assist human users to make decisions. Using simulation results the paper demonstrates that using the norm-based mechanism results in reduced failure rates in the decision making of a knowledge worker while still providing maximum flexibility for the user to choose from a range of actions to execute.

Social norms constrain behavior of individuals either through obligating or prohibiting certain types of behavior. Norm-based mechanisms have only recently found applications in enhancing decisions of knowledge workers in an automated business process management context. The norms inferred in the context of business process executions are then recommended to users so as to enable them to make informed decisions. The previous work on prohibition norm inference focused on identifying failure cases, which is now complemented by first inferring norms from the successful process execution cases and then inferring prohibition norms. This approach based on considering social feedback (i.e. inferring what is obliged and prohibited from history logs of process execution) shows encouraging results under uncertain business environments. Using simulation results the paper demonstrates that using the norm based mechanism results in reduced failure rates in the decision making of a knowledge worker while still providing maximum flexibility for the user to choose from a range of actions to execute.