Ontology-Guided Multimodal Large Language Model for Semantic Recognition of Ship Navigation Behaviors

Automatic Identification System (AIS) data provide sequential motion observations for ship-behavior analysis, yet high-level navigational behavioral semantics cannot be reliably interpreted from low-level motion features alone, especially considering ship-environment spatial interactions and their temporal dependencies. To mitigate this limitation, this study proposes an ontology-guided multimodal large language model for semantic recognition of ship navigation behaviors. Built on a three-layer hierarchical behavioral model, the approach unifies motion states, spatial interactions, and temporal associations via a ship-behavior ontology and temporal behavior knowledge graph. It fuses extracted local temporal knowledge, global structured navigation context, and trajectory-motion composite imagery under ontology semantic constraints to reason about high-level behavioral semantics. Validated on real-world Honolulu-Harbor AIS datasets, the method yields a Macro-F1 of 0.7619 (6.1 pp above the strongest baseline in Macro-F1), an Accuracy of 0.9654, and a Normalized Edit Similarity of 0.7980. Ablation studies show that structured knowledge provides the main discriminative contribution, ontology constraints improve class-balanced recognition, and the visual view provides complementary information on trajectory continuity and behavioral transitions. This method realizes structured semantic representation from AIS trajectories and spatial environment data, supporting harbor ship-behavior supervision, semantic-trajectory mining and maritime-traffic-situation assessment.