Abstract: Behavior-based context-aware intelligent recommendation systems (BCAIRS) have become a research hotspot in the field of recommendation systems. We provided a brief overview and definition of existing BCAIRS, summarizing the basic recommendation procedures of such systems. Building on this, we proposed a comprehensive classification framework and conducted an in-depth analysis of different types of BCAIRS from perspectives such as model structure and application fields. We summarized and analyzed how to select recommendation methods for specific recommendation tasks and outlined the directions for future research.