Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Decoding Urban Industrial Complexity: Enhancing Knowledge-Driven Insights via IndustryScopeGPT

Siqi Wang, Chao Liang, Yunfan Gao, Yang Liu, Jing Li, Haofen Wang

TL;DR

The IndustryScopeGPT framework is presented, which leverages Large Language Models (LLMs) with Monte Carlo Tree Search to enhance tool-augmented reasoning and decision-making in Industrial Park Planning and Operation (IPPO).

Abstract

Industrial parks are critical to urban economic growth. Yet, their development often encounters challenges stemming from imbalances between industrial requirements and urban services, underscoring the need for strategic planning and operations. This paper introduces IndustryScopeKG, a pioneering large-scale multi-modal, multi-level industrial park knowledge graph, which integrates diverse urban data including street views, corporate, socio-economic, and geospatial information, capturing the complex relationships and semantics within industrial parks. Alongside this, we present the IndustryScopeGPT framework, which leverages Large Language Models (LLMs) with Monte Carlo Tree Search to enhance tool-augmented reasoning and decision-making in Industrial Park Planning and Operation (IPPO). Our work significantly improves site recommendation and functional planning, demonstrating the potential of combining LLMs with structured datasets to advance industrial park management. This approach sets a new benchmark for intelligent IPPO research and lays a robust foundation for advancing urban industrial development. The dataset and related code are available at https://github.com/Tongji-KGLLM/IndustryScope.

Decoding Urban Industrial Complexity: Enhancing Knowledge-Driven Insights via IndustryScopeGPT

TL;DR

The IndustryScopeGPT framework is presented, which leverages Large Language Models (LLMs) with Monte Carlo Tree Search to enhance tool-augmented reasoning and decision-making in Industrial Park Planning and Operation (IPPO).

Abstract

Industrial parks are critical to urban economic growth. Yet, their development often encounters challenges stemming from imbalances between industrial requirements and urban services, underscoring the need for strategic planning and operations. This paper introduces IndustryScopeKG, a pioneering large-scale multi-modal, multi-level industrial park knowledge graph, which integrates diverse urban data including street views, corporate, socio-economic, and geospatial information, capturing the complex relationships and semantics within industrial parks. Alongside this, we present the IndustryScopeGPT framework, which leverages Large Language Models (LLMs) with Monte Carlo Tree Search to enhance tool-augmented reasoning and decision-making in Industrial Park Planning and Operation (IPPO). Our work significantly improves site recommendation and functional planning, demonstrating the potential of combining LLMs with structured datasets to advance industrial park management. This approach sets a new benchmark for intelligent IPPO research and lays a robust foundation for advancing urban industrial development. The dataset and related code are available at https://github.com/Tongji-KGLLM/IndustryScope.

Paper Structure

This paper contains 20 sections, 5 equations, 6 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Urban Intelligence and Dataset
  4. LLMs Reasoning
  5. IndustryScopeKG
  6. Data Collection and Pre-processing
  7. Data Acquisition
  8. Data Pre-processing
  9. Knowledge Graph Construction
  10. IndustryScopeKG
  11. Relational Triples Extraction
  12. Attributional Triples Extraction
  13. IndustryScopeKG Management
  14. IndustryScopeGPT
  15. Monte Carlo Tree Search Planner
  16. ...and 5 more sections

Figures (6)

  • Figure 1: The challenges in integrating LLMs for IPPO solutions.
  • Figure 2: Park vectorization and grid processing.
  • Figure 3: IndustryScopeKG construction pipeline. It follows the process from data collection and preprocessing to triple extraction and management, forming a graph with hierarchy, spatial correlation, and semantic association.
  • Figure 4: Overview of IndustryScopeGPT - illustrating conditional financial facility siting based on user queries.
  • Figure 5: Designed tools and their typical reasoning chains.
  • ...and 1 more figures