发表机构
University of Arizona（亚利桑那大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出开源Python平台BuildOcc，基于ATUS数据集构建大语言模型居住者智能体，为建筑能源工具提供三层接口，经验证可复现活动分布并实现角色一致推理，为建筑能源领域提供可复用的居住者行为层实现。
AI 中文摘要
居住者是建筑能源消耗与管理不确定性的主要来源，但现有的居住者行为模型无法捕捉结合居住者个人历史、当前情境及所传递能源信号类型的适应性与推理响应。本研究提出BuildOcc，这是一个开源Python平台，将大语言模型智能体基于美国时间使用调查（ATUS）构建，该调查是涵盖16684名受访者的全国代表性日记数据集。通过BuildOcc，每个模拟居住者智能体可实例化为源自ATUS人口统计数据的人口统计角色、积累并反思时间步级观测结果的记忆流，以及从ATUS活动时间分布中经验采样的活动调度器。该平台提供三层接口——Python库、REST API和模型上下文协议服务器，使任何建筑能源工具（EnergyPlus、Home Assistant）都能集成行为智能，无需定制耦合代码。插件注册表允许社区添加新的居住者分层、定制调度器及替代记忆后端作为独立可安装包。两个验证层级显示，基于ATUS的采样可复现经验校准的活动分布，且人口统计先验会跨时间步传播为符合角色的智能体推理，建立分层间的内部一致性。BuildOcc为建筑能源社区提供了可复用、公开可用的居住者行为层实现，BuildOcc根据Apache许可证2.0公开发布，可通过pip install buildocc安装。
英文摘要
Occupants are a primary source of uncertainty in building energy consumption and management, yet existing occupant behavior models cannot capture adaptive and reasoning responses considering the occupant's personal history, current context, and the type of energy signal being delivered. This study presents BuildOcc, an open-source Python platform that grounds large language model agents in the American Time Use Survey (ATUS), a nationally representative diary dataset covering 16,684 respondents. Through BuildOcc, each simulated occupant agent can be instantiated with a demographic persona drawn from ATUS population statistics, a memory stream that accumulates and reflects on timestep-level observations, and an activity scheduler that samples empirically from ATUS time-at-activity distributions. The platform exposes a three-layer interface - Python library, REST API, and Model Context Protocol server - so that any building energy tool (EnergyPlus, Home Assistant) can integrate behavioral intelligence without bespoke coupling code. A plugin registry lets the community add new occupant strata, custom schedulers, and alternative memory backends as separate installable packages. Two validation tiers show that ATUS-grounded sampling reproduces empirically calibrated activity distributions and that demographic priors propagate into persona-consistent agent reasoning across timesteps, establishing internal consistency across strata. BuildOcc provides the building energy community with a reusable, openly available implementation of the occupant behavioral layer. BuildOcc is openly released at https://doi.org/10.5281/zenodo.21192895 under the Apache License 2.0 and installable via pip install buildocc.
CommentsAccepted manuscript. Published in SoftwareX. 29 pages, 4 figures, 11 tables, 3 appendices. Software: https://github.com/humanbuildingsynergy/BuildOcc
Journal refSoftwareX 103068 (2026)
DOI：10.1016/j.softx.2026.103068
