发表机构
Chengdu Jincheng College（成都锦城学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SmartWeatherAgent，融合规则方法与LLM及LightGBM，通过12轮自优化提示词提升高原天气预警质量，实现F1-Macro 0.605和预警分数提升112%。
AI 中文摘要
为解决旅游气象服务中情境化不足、泛化能力弱和场景适应性差的问题，我们提出了SmartWeatherAgent——一个统一的三阶段架构，集成了意图识别、灾害预测和推理增强生成。该系统将基于规则的方法与大型语言模型相融合，以多粒度解析查询，并采用富含高原特定特征（如风速突变率）的LightGBM模型，在高风、降水和低温事件上实现了0.605的F1-Macro分数和1.60毫秒的延迟。一个12轮微步提示词自优化循环将综合预警质量分数S_final从4.2（B01）提升至8.9（B12，提升112%）。关键改进包括：B08中数据源引用的显著提升（6.5升至8.5），B10通过物理机制解释保持的高性能，以及B12中通过明确不确定性陈述达到的9.2的科学严谨性峰值分数。该系统自主生成结构化预警，整合因果机制、时空演变、定量证据、法规引用和置信度陈述，增强了专业深度、逻辑严谨性和科学可靠性，推动气象服务向主动感知、可解释决策和智能代理方向发展。
英文摘要
To address insufficient contextualization, weak generalization, and poor scenario adaptation in tourism meteorological services, we propose SmartWeatherAgent--a unified three-stage architecture integrating intent recognition, hazard prediction, and reasoning-enhanced generation. The system fuses rule-based methods with large language models to parse queries at multiple granularities and employs a LightGBM model enriched with highland-specific features (e.g., wind speed abruptness rate), achieving an F1-Macro score of 0.605 with 1.60 ms latency on high-wind, precipitation, and low-temperature events. A 12-round micro-step prompt self-optimization loop boosts the composite warning quality score S_final from 4.2 (B01) to 8.9 (B12, +112%). Key improvements include a sharp rise in B08 from data source citation (6.5 -> 8.5), sustained high performance in B10 via physical mechanism explanation, and a peak scientific rigor score of 9.2 in B12 through explicit uncertainty statements. The system autonomously generates structured warnings that integrate causal mechanisms, spatiotemporal evolution, quantitative evidence, regulatory references, and confidence statements--enhancing professional depth, logical rigor, and scientific soundness, and advancing meteorological services toward proactive perception, explainable decision-making, and intelligent agency.
CommentsAccepted by ISPDS 2025
