The Internet of Things (IoT) is exploding, and this new technology affects all the layers in any enterprise architecture, from infrastructure to business. To survive this new evolution and make the most out of this paradigm shift, a communication channel must be created between Business Process Management (BPM) domain and IoT domain in order to bridge the gap between the business layer and the IoT physical layer. The allocation of business process resources to IoT events is an important step towards an end-to-end IoT-BPM integration approach to assist organizations in their scheduling and incident management journey. In this paper, we propose a combination approach which is based on i)unsupervised machine learning algorithms to generate clusters of priorities, used to estimate incoming events priority, and to ensure a learning feedback loop that feeds forward insight to continuously adjust decisions made at each layer, and ii) genetic algorithm (GA) to guarantee the assignment of the most critical IoT generated event to the qualified human resource while respecting several constraints such as resource availability and reliability, and taking into consideration the priority of each event that launch process instances. A case study is presented and the obtained results from our experimentations demonstrate the benefit of our approach and allowed us to confirm the efficiency of our assumptions.