发表机构
Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工大学宁波数字孪生研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对旅游业定价自动化的挑战，提出一种可解释的LLM驱动定价系统，通过结构化提取、确定性数值计算等实现可靠可审计的定价，部署后大幅缩减团队规模并缩短订单处理时间。
AI 中文摘要
大规模旅游业中的定价自动化颇具挑战，因为旅游订单高度非结构化，而定价政策复杂、快速演变且本质上是开放式的。传统规则引擎脆弱且维护成本高昂，而无约束的大语言模型（LLM）智能体缺乏财务决策所需的可靠性和可审计性。我们提出一种生产级的LLM驱动定价系统，具有严格的决策边界：LLM执行结构化提取和受限政策/路径选择，而所有数字定价（包括总价计算）均确定性执行。政策被编译为可解释的条件树，无需代码变更即可为新条款和演变规则提供开放式支持，同时暴露可审计的人工介入控制工件。对记录的轨迹进行定期微调进一步改进了树归纳和路径匹配。该系统部署在一家市政国有旅游企业，覆盖7个景区、12个业务类别，服务1500余名运营者和1000+项活跃政策，六个月内处理了3960份订单，将订单管理团队从15-20人缩减至3人，每份订单处理时间从10分钟缩短至不到2分钟。
英文摘要
Pricing automation in large-scale tourism is challenging because travel orders are highly unstructured, while pricing policies are complex, rapidly evolving, and inherently open-ended. Traditional rule engines are brittle and costly to maintain, whereas unconstrained LLM agents lack the reliability and auditability required for financial decisions. We present a production-grade LLM-powered pricing system with a strict decision boundary: LLMs perform structured extraction and bounded policy/path selection, while all numeric pricing, including total-price computation, is executed deterministically. Policies are compiled into interpretable condition trees, enabling open-ended support for new clauses and evolving rules without code changes, while exposing auditable artifacts for human-in-the-loop control. Periodic fine-tuning on logged traces further improves tree induction and path matching. Deployed at a municipal state-owned tourism enterprise across 7 scenic sites and 12 business categories with 1,500+ operators and 1,000+ active policies, the system processed 3,960 orders in six months, reduced the order management team from 15-20 to 3, and cut per-order handling time from 10 minutes to <2 minutes.
