Most existing decision making models rely on task-related data for knowledge learning and cannot explain the decision making process. To fill this important gap, this article proposes a knowledge flow empowered cognitive framework, which combines both task-related and task-agnostic data for bottom-up knowledge learning. In addition, a knowledge flow model is developed for top-down knowledge representation. For the case study of traffic anomaly detection, our method demonstrates the Recall value improvements of up to 31% and 42% over models that only use task-related data on the Caltrans performance measurement system and NYC datasets, respectively. In the case study of vehicle following anomaly detection, our method achieves competitive results and has the human-like cognitive process. To sum up, our method not only delivers an excellent performance, but also enables knowledge representation, which significantly enhances the interpretability of decision making processes.

The extreme complexity of many real-world tasks poses considerable challenges to agents' decision making. Most existing models only rely on task-related data for knowledge learning, while ignoring the important influence of potential task-agnostic factors. Effective learning coupled with both task-related and task-agnostic data can strongly enrich the agent's knowledge and improve its decision making performance. Furthermore, many existing learning models simply leverage data to learn knowledge but fail to express the thought process of decision making as humans do, which significantly limits their explanatory capability. To this end, we propose a novel knowledge flow empowered cognitive framework for real-world tasks. To obtain more reliable and trustworthy knowledge, a bottom-up knowledge learning model is developed, which incorporates both task-related data and task-agnostic data for comprehensive knowledge accumulation and value assessment of influencing factors. To demonstrate the...