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
提出基于知识图谱上限与AI智能体实测准确率的建筑AI就绪评估框架，将就绪问题转化为可审计的改造优先级排序。
AI 中文摘要
智能体人工智能（AI）系统正成为建筑交互的界面，负责回答问题并控制运行，但建筑对其就绪程度尚未被系统评估。本研究提出一个量化该就绪程度的框架。首先，建筑的知识图谱设定两个上限：可回答就绪上限是数据能回答的运行问题占比，可执行就绪上限是其暴露的控制动作占比。其次，参考AI智能体在一组固定问题上的准确率显示上限的实现程度。在模拟办公室中，智能体实现了0.64可回答上限中的0.62，因此缺失数据而非AI限制了就绪程度，但在故障原因命名上除外。在37个公开的真实建筑图谱中，中位可回答上限为0.16，且在45个中的15个里，未连接的传感器降低了该上限。该框架将“此建筑是否AI就绪？”转化为一个可审计、可排序的改造问题。
英文摘要
Agentic artificial intelligence (AI) systems are becoming the interface to buildings, answering questions and controlling operations, but a building's readiness for them has not been systematically assessed. This study proposes a framework to quantify it. First, a building's knowledge graph sets two ceilings. The answerable-readiness ceiling is the share of operational questions its data could answer, and the actuation-readiness ceiling is the share of control actions it exposes. Second, a reference AI agent's accuracy on a fixed set of these questions shows how much of the ceilings is realized. On a simulated office, the agent realizes 0.62 of a 0.64 answerable ceiling, so missing data, not the AI, limit readiness, except in naming a fault's cause. Across 37 public real-building graphs, the median answerable ceiling is 0.16, and in 15 of 45, unlinked sensors lower it. The framework turns "is this building AI-ready?" into an auditable, ranked retrofit question.
Comments47 pages, 11 figures, 23 tables. Code, results and data supplement: https://doi.org/10.5281/zenodo.23197610
