Human Mobility Modeling with Limited Information via Large Language Models

2024-09-26

arXiv.org

AI Summary

To address the limitation of conventional human mobility modeling caused by the scarcity of high-quality trajectory data, this paper pioneers the integration of large language models (LLMs) into transportation modeling, thereby reducing reliance on fine-grained GPS traces. Methodologically, we jointly model individual sociodemographic attributes and semantic activity chains, explicitly encoding logical dependencies among activities and household-level coordination patterns (e.g., joint shopping, shared meals). The model is trained and validated using multi-source microsimulation datasets—namely, the National Household Travel Survey (NHTS) and the Southern California Association of Governments Activity-Based Model (SCAG-ABM). Compared to traditional activity-based models (ABMs) and purely sequential baselines, our approach achieves significant improvements in activity sequence accuracy and spatial distribution fidelity. Moreover, it demonstrates strong cross-regional generalizability and enables rapid regional adaptation under low-data conditions.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Understanding human mobility patterns has traditionally been a complex challenge in transportation modeling. Due to the difficulties in obtaining high-quality training datasets across diverse locations, conventional activity-based models and learning-based human mobility modeling algorithms are particularly limited by the availability and quality of datasets. Furthermore, current research mainly focuses on the spatial-temporal travel pattern but lacks an understanding of the semantic information between activities, which is crucial for modeling the interdependence between activities. In this paper, we propose an innovative Large Language Model (LLM) empowered human mobility modeling framework. Our proposed approach significantly reduces the reliance on detailed human mobility statistical data, utilizing basic socio-demographic information of individuals to generate their daily mobility patterns. We have validated our results using the NHTS and SCAG-ABM datasets, demonstrating the effective modeling of mobility patterns and the strong adaptability of our framework across various geographic locations.

Problem

• Modeling human mobility with household coordination activities
• Overcoming data limitations in mobility pattern analysis
• Incorporating semantic relationships in mobility modeling

Innovation

• Retrieval-augmented LLMs for mobility modeling
• Generates activity chains with household coordination
• Uses public statistical and socio-demographic data