A Scalable Knowledge Graph Embedding Model for Next Point-of-Interest Recommendation in Tallinn City

Ounoughi, Chahinez; Mouakher, Amira; Sherzad, Muhammad Ibraheem; Yahia, Sadok Ben

doi:10.1007/978-3-030-75018-3_29

Cited by 4 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors then configured the KG using the relationships between users and POIs. Alternatively, Ounoughi et al (2021) elaborated on the relationship between POIs, users, time, and descriptive words based on user check‐in activity. Tang et al (2021) suggested a dual‐level semantic spatial graph, while acknowledging the geographic influence in POI recommendations.…”

Section: Related Workmentioning

confidence: 99%

SSIKG: A framework for spatial‐semantic integrated indoor knowledge graph construction

Park

Lee

2022

Transactions in GIS

View full text Add to dashboard Cite

The demand for place retrieval and route guidance services of indoor environments has increased owing to the extensive development of large complexes. In comparison to increasingly customizable and diversified general place retrieval services, indoor place‐related services currently offer few features. Existing knowledge graphs mostly deal with limited spatial context based on geographic location, and hence do not cover indoor environments. In this study, we propose a framework for a Spatial‐Semantic integrated Indoor Knowledge Graph (SSIKG) as a multi‐layered model of the indoor environment. The spatial layer involves knowledge of navigable paths by preserving network‐based topological relationships between places. Concurrently, the semantic layer expresses features from an end‐user perspective. To assess framework utility, place retrieval tests with resulting graphs were performed for six practical use cases, returning lists of the places and their corresponding optimal paths. Finally, the results were reviewed in terms of spatial inference and expansion of our graphs.

show abstract

Section: Related Workmentioning

confidence: 99%