Campus Digital Twin Knowledge Graph for Constraint-Aware Spatial Reasoning

A GraphRAG framework integrates large language models with a spatiotemporal knowledge graph to enhance spatial reasoning. The graph explicitly models campus facilities, events, accessible entrances, and real-time parking availability. The approach, authored by Wenyu Zhang and shared under CC-BY-4.0, is implemented as a decision-support chatbot with a visual analytics interface.

Use Cases

• Route planning based on campus facilities and accessible entrances.
• Parking recommendations based on real-time parking availability and operational conditions.
• Multi-criteria spatial query resolution based on geospatial topology and constraints.
• Visual inspection of reasoning processes based on the integrated analytics interface.

Strengths

• Framework leverages graph-structured retrieval to enforce physical, temporal, and operational constraints.
• Experimental results demonstrate significant outperformance over baseline methods in accuracy and interpretability.
• Released under the permissive CC-BY-4.0 license for open use.

Limitations

• The dataset is a 99.1 KB DOCX file, suggesting limited scope and likely containing a paper description rather than a large-scale dataset.
• Column-level documentation and sample data are unavailable, requiring manual inspection after download.
• Row count is unknown, which may limit suitability assessment for training machine learning models.

Provenance

Source

Wenyu Zhang via figshare.

Collection Method

Likely created as part of a research framework implementation.

Freshness

Last updated 2026-06-01 04:40:11.

Geography

Campus environment.