Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916345760710656 |
|---|---|
| author | Li, Xuchuan Huang, Fei Lv, Jianrong Xiao, Zhixiong Li, Guolong Yue, Yang |
| author_facet | Li, Xuchuan Huang, Fei Lv, Jianrong Xiao, Zhixiong Li, Guolong Yue, Yang |
| contents | Human mobility is inextricably linked to social issues such as traffic congestion, energy consumption, and public health; however, privacy concerns restrict access to mobility data. Recently, research have utilized Large Language Models (LLMs) for human mobility generation, in which the challenge is how LLMs can understand individuals' mobility behavioral differences to generate realistic trajectories conforming to real world contexts. This study handles this problem by presenting an LLM agent-based framework (MobAgent) composing two phases: understanding-based mobility pattern extraction and reasoning-based trajectory generation, which enables generate more real travel diaries at urban scale, considering different individual profiles. MobAgent extracts reasons behind specific mobility trendiness and attribute influences to provide reliable patterns; infers the relationships between contextual factors and underlying motivations of mobility; and based on the patterns and the recursive reasoning process, MobAgent finally generates more authentic and personalized mobilities that reflect both individual differences and real-world constraints. We validate our framework with 0.2 million travel survey data, demonstrating its effectiveness in producing personalized and accurate travel diaries. This study highlights the capacity of LLMs to provide detailed and sophisticated understanding of human mobility through the real-world mobility data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_18932 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles Li, Xuchuan Huang, Fei Lv, Jianrong Xiao, Zhixiong Li, Guolong Yue, Yang Computers and Society Artificial Intelligence Human mobility is inextricably linked to social issues such as traffic congestion, energy consumption, and public health; however, privacy concerns restrict access to mobility data. Recently, research have utilized Large Language Models (LLMs) for human mobility generation, in which the challenge is how LLMs can understand individuals' mobility behavioral differences to generate realistic trajectories conforming to real world contexts. This study handles this problem by presenting an LLM agent-based framework (MobAgent) composing two phases: understanding-based mobility pattern extraction and reasoning-based trajectory generation, which enables generate more real travel diaries at urban scale, considering different individual profiles. MobAgent extracts reasons behind specific mobility trendiness and attribute influences to provide reliable patterns; infers the relationships between contextual factors and underlying motivations of mobility; and based on the patterns and the recursive reasoning process, MobAgent finally generates more authentic and personalized mobilities that reflect both individual differences and real-world constraints. We validate our framework with 0.2 million travel survey data, demonstrating its effectiveness in producing personalized and accurate travel diaries. This study highlights the capacity of LLMs to provide detailed and sophisticated understanding of human mobility through the real-world mobility data. |
| title | Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2407.18932 |