Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework

从自然语言策略到可执行决策：一种可解释的大语言模型框架

Abstract: 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.

摘要： 在大规模旅游行业中，定价自动化面临着巨大挑战，因为旅游订单高度非结构化，而定价策略复杂、演变迅速且本质上具有开放性。传统的规则引擎脆弱且维护成本高昂，而无约束的大语言模型（LLM）智能体则缺乏财务决策所需的可靠性和可审计性。

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.

我们提出了一种生产级的大语言模型定价系统，该系统具有严格的决策边界：大语言模型负责结构化提取和有界策略/路径选择，而所有数值定价（包括总价计算）均以确定性方式执行。策略被编译为可解释的条件树，从而在无需更改代码的情况下，为新条款和演变规则提供开放式支持，同时为“人在回路”（human-in-the-loop）控制提供可审计的产物。

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.

通过对记录的轨迹进行定期微调，进一步提升了树归纳和路径匹配的效果。该系统在一家市属国有旅游企业部署，覆盖 7 个景区和 12 个业务类别，涉及 1,500 多名操作员和 1,000 多项活跃策略。在六个月内，该系统处理了 3,960 笔订单，将订单管理团队从 15-20 人缩减至 3 人，并将单笔订单的处理时间从 10 分钟缩短至 2 分钟以内。