In this study, a modular, data-free pipeline for multi-label intention recognition is proposed for agentic AI applications in transportation. Unlike traditional intent recognition systems that depend on large, annotated corpora and often struggle with fine-grained, multi-label discrimination, our approach eliminates the need for costly data collection while enhancing the accuracy of multi-label intention understanding. Specifically, the overall pipeline, named DMTC, consists of three steps: 1) using prompt engineering to guide large language models (LLMs) to generate diverse synthetic queries in different transport scenarios; 2) encoding each textual query with a Sentence-T5 model to obtain compact semantic embeddings; 3) training a lightweight classifier using a novel online focal-contrastive (OFC) loss that emphasizes hard samples and maximizes inter-class separability. The applicability of the proposed pipeline is demonstrated in an agentic AI application in the maritime transportation context. Extensive experiments show that DMTC achieves a Hamming loss of 5.35% and an AUC of 95.92%, outperforming state-of-the-art multi-label classifiers and recent end-to-end SOTA LLM-based baselines. Further analysis reveals that Sentence-T5 embeddings improve subset accuracy by at least 3.29% over alternative encoders, and integrating the OFC loss yields an additional 0.98% gain compared to standard contrastive objectives. In conclusion, our system seamlessly routes user queries to task-specific modules (e.g., ETA information, traffic risk evaluation, and other typical scenarios in the transportation domain), laying the groundwork for fully autonomous, intention-aware agents without costly manual labelling.

翻译：本研究提出了一种模块化、无数据驱动的多标签意图识别管道，专为交通领域的智能体AI应用设计。与依赖大规模标注语料库且常难以实现细粒度多标签区分的传统意图识别系统不同，我们的方法在无需昂贵数据收集的同时，提升了多标签意图理解的准确性。具体而言，该整体管道（命名为DMTC）包含三个步骤：1）利用提示工程引导大语言模型（LLMs）在不同交通场景中生成多样化的合成查询；2）使用Sentence-T5模型对每个文本查询进行编码，以获取紧凑的语义嵌入；3）采用一种新颖的在线焦点对比（OFC）损失训练轻量级分类器，该损失强调困难样本并最大化类间可分离性。所提出管道的适用性在海事交通背景下的智能体AI应用中得到了验证。大量实验表明，DMTC实现了5.35%的汉明损失和95.92%的AUC，优于当前最先进的多标签分类器及近期基于端到端SOTA LLM的基线方法。进一步分析显示，Sentence-T5嵌入相较于其他编码器将子集准确率提升了至少3.29%，而集成OFC损失相比标准对比目标带来了额外0.98%的增益。总之，我们的系统能够无缝地将用户查询路由至特定任务模块（例如ETA信息、交通风险评估及其他交通领域的典型场景），为无需昂贵人工标注、完全自主且意图感知的智能体奠定了基础。