Next-point-of-interest (POI) recommendation is a crucial part of location-based social applications. Existing works have attempted to learn behavior representation through a sequence model combined with spatial-temporal-interval context. However, these approaches ignore the impact of implicit behavior patterns contained in the visit trajectory on user decision making. In this paper, we propose a novel graph self-supervised behavior pattern learning model (GSBPL) for the next-POI recommendation. GSBPL applies two graph data augmentation operations to generate augmented trajectory graphs to model implicit behavior patterns. At the same time, a graph preference representation encoder (GPRE) based on geographical and social context is proposed to learn the high-order representations of trajectory graphs, and then capture implicit behavior patterns through contrastive learning. In addition, we propose a self-attention based on multi-feature embedding to learn users’ short-term dynamic preferences, and finally combine trajectory graph representation to predict the next location. The experimental results on three real-world datasets demonstrate that GSBPL outperforms the supervised learning baseline in terms of performance under the same conditions.