Natural language interface for urban network analytics

Název česky Rozhraní přirozeného jazyka pro městskou analýzu
Autoři

BOGOMOLOV Jura BRETSKO Daniel PAING Swam Pyae SOBOLEVSKIJ Stanislav

Rok publikování 2025
Druh Článek v odborném periodiku
Časopis / Zdroj COMPUTATIONAL URBAN SCIENCE
Citace
www https://link.springer.com/article/10.1007/s43762-025-00230-9
Doi https://doi.org/10.1007/s43762-025-00230-9
Klíčová slova Urban analytics; Large language models; Prompt engineering; Network analysis; Geospatial data
Popis We introduce the first natural language interface for complex urban analytics, leveraging Large Language Models (LLMs) and Spatio-Temporal Transactional Networks (STTNs). By combining intuitive natural language querying with structured data analytics, our framework simplifies complex urban analyses, such as identifying commuter patterns, detecting anomalies, and exploring mobility networks. We propose a comprehensive evaluation dataset that demonstrates that minor architectural improvements can significantly improve analytical accuracy. Our approach bridges the gap between non-expert users and sophisticated urban insights, paving the way for accessible, reliable, and scalable urban data analytics.

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.

Další info