Decoding Urban Industrial Complexity: Enhancing Knowledge-Driven Insights via IndustryScopeGPT
Abstract: Industrial parks are critical to urban economic growth, blending technology and urban life to foster innovation. Yet, their development often faces challenges due to imbalances between industrial needs and urban services, necessitating strategic planning and operation. This paper presents IndustryScopeKG, a pioneering multi-modal, multi-level large-scale industrial park knowledge graph, and the IndustryScopeGPT framework. By leveraging vast datasets, including corporate, socio-economic, and geospatial information, IndustryScopeKG captures the intricate relationships and semantics of industrial parks, facilitating comprehensive analysis and planning. The IndustryScopeGPT framework, integrating LLMs with Monte Carlo Tree Search, enhances decision-making capabilities, enabling dynamic and adaptable responses to the diverse needs of industrial park planning and operation (IPPO) tasks. Our contributions include the release of the first open-source industrial park knowledge graph, IndustryScopeKG, and the demonstration of the IndustryScopeGPT framework's efficacy in site selection and planning tasks through the IndustryScopeQA benchmark. Our findings highlight the potential of combining LLMs with extensive datasets and innovative frameworks, setting a new standard for research and practice in the field.
Primary Subject Area: [Content] Multimodal Fusion
Secondary Subject Area: [Experience] Interactions and Quality of Experience, [Engagement] Summarization, Analytics, and Storytelling, [Engagement] Multimedia Search and Recommendation
Relevance To Conference: Our research introduces IndustryScopeKG, the first open-source, multi-modal, multi-level knowledge graph dataset specifically designed for the intelligent planning and operation of industrial parks. This dataset stands out as a pioneering contribution to the multimedia and multimodal processing field, featuring an unprecedented integration of diverse data types and sources, including corporate information, socio-economic indicators, and rich geospatial data. The multi-layered structure of IndustryScopeKG captures the intricate relationships and semantics of industrial park ecosystems, offering a granular view of urban economic dynamics previously unattainable with traditional datasets. The development of IndustryScopeKG addresses a critical gap in multimedia research by providing a rich, heterogeneous dataset that supports the application of large language models (LLMs) for urban planning. By facilitating the exploration of complex industrial park ecosystems through multimodal data fusion, IndustryScopeKG enables a broad spectrum of research tasks, from interpretable multi-spatial scale, multi-category site selection, and the functional planning of industrial parks.
Submission Number: 5739
Loading