GPS-Enhanced Tourist Mobility Modeling with Seasonal Spatial Priors and LLM-Based Activity Chain Generation

2026-05-28

AI Summary

Existing approaches struggle to model individual tourists’ non-commute, purpose-driven travel behavior, particularly due to insufficient representation of idiosyncratic constraints such as trip duration, seasonal attraction preferences, and group composition. This work proposes a four-stage simulation framework that integrates aggregated GPS and survey data to construct monthly spatial priors, predicts trip ranges based on demographic attributes, heuristically assigns feasible sequences of visited neighborhoods, and—novelty introduced here—employs a large language model to generate geographically anchored, demographically consistent activity chains under household and spatial constraints. Experiments in Tokyo demonstrate that the synthesized trips closely replicate real-world patterns: the distribution of neighborhood visits aligns well with both survey data and monthly visitation modes derived from stay-point trajectories, effectively capturing the spatial visitation characteristics of tourist populations.

Abstract

Tourist mobility poses a distinct challenge for urban transportation planning. Unlike resident commuting, tourist travel is largely non-routine, attraction driven, and highly sensitive to trip purpose, travel season, and trip member composition. Existing approaches either measure aggregate tourist spatial patterns without generating individual schedules, or synthesize mobility without tourist specific structure such as trip duration conditioning, month varying attraction demand, and household co-travel rules. To address these challenges, we propose a four stage simulation framework combining month conditioned spatial priors derived from GPS and survey data, trip extent prediction from tourist demographics, distance feasible ward sequence assignment, and LLM-based activity chain generation under household and spatial constraints. GPS data are used only in privacy preserving aggregated form as month conditioned spatial priors, with no individual traces retained or exposed. Experiments on tourism in Tokyo demonstrate that the GPS based tourist cohort extraction recovers spatial visitation signatures consistent with survey references, and our framework produces demographically aligned synthetic schedules whose ward-level visitation shares align closely with both survey distributions and staypoint derived monthly visitation patterns. The results demonstrate the framework's effectiveness as a geographically grounded, demographically aware approach to tourist mobility modeling.

Problem

• tourist mobility
• spatial priors
• activity chain
• seasonal variation
• household co-travel

Innovation

• tourist mobility modeling
• seasonal spatial priors
• LLM-based activity chain
• privacy-preserving GPS
• demographically aware simulation