In the evolving framework of the Intelligence of Social Things (IoST), which amalgamates social networks and IoT ecosystems, knowledge graphs are essential for facilitating networked systems to efficiently process and leverage intricate relational data. Knowledge graphs offer essential technical assistance for various artificial intelligence applications, such as e-commerce, intelligent navigation, healthcare, and social media. Nonetheless, current knowledge graphs frequently lack completeness, harboring a considerable quantity of implicit knowledge that remains to be revealed. Consequently, tackling the difficulty of finalising knowledge graphs has emerged as a pressing research priority. Most contemporary methods separately analyse entity neighbourhood information or connection routes, neglecting the significance of entity neighbourhood information in the investigation of relationship paths. A novel approach, RPEN-KGC (Relationship Path and Entity Neighbourhood Knowledge Graph Completion), is suggested to enable the fusion of relationship paths and entity neighbourhood information for knowledge graph completion. RPEN-KGC comprises a sampler and an inferencer. The sampler conducts random walks between entity pairs to furnish dependable inference methods for the inferencer. The sampler utilises a contrastive method grounded in entity neighbourhood similarity to steer random walks, hence enhancing sampling efficiency and augmenting inference strategies. The inferencer derives semantic characteristics of relationship paths and deduces a greater variety of relationship paths within the semantic domain. Experiments performed on the public NELL-995 and FB15K-237 datasets for the link prediction task indicate that RPEN-KGC significantly enhances most metrics relative to baseline approaches. These findings demonstrate that RPEN-KGC proficiently forecasts absent information in knowledge graphs.