Contract2Plan: 一种基于合同的验证性检索增强优化方法用于BOM感知采购和多层级库存规划
Contract2Plan: Verified Contract-Grounded Retrieval-Augmented Optimization for BOM-Aware Procurement and Multi-Echelon Inventory Planning
AI总结:
Contract2Plan通过验证性检索增强优化方法,解决合同条款与BOM耦合导致的采购和库存规划问题,确保计划的可行性与合规性。
摘要:
采购和库存规划不仅受需求预测和物料清单(BOM)的影响,还受合同和供应商文件中的运营条款(如最低订单量、交货时间、价格梯度、分配上限、替代批准等)的影响。基于LLM的提取可以加速这些条款的结构化,但仅提取或仅LLM决策流程存在脆弱性:遗漏的条款、单位错误和未解决的冲突可能导致不可行的计划或沉默的合同违规,这在BOM耦合情况下被放大。我们引入Contract2Plan,一种经过验证的GenAI到优化器的管道,在计划发出之前插入一个基于求解器的合规性闸门。该系统通过可追溯的证据检索条款证据,提取带有证据跨度的类型化约束模式,将约束编译成BOM感知的MILP,并利用求解器诊断验证接地性、资格性、一致性和可行性,当自动化不安全时触发针对性修复或回避。我们正式化了哪些条款类别允许保守修复并具有合同安全的可行性保证,哪些需要人工确认。一个自包含的合成微基准(500个实例;T=5)通过精确枚举在具有MOQ提升和紧急采购的执行模型下计算,显示出重尾遗憾和非平凡的MOQ违规发生率,这促使验证成为合同基础规划系统中的首要组件。
英文摘要:
Procurement and inventory planning is governed not only by demand forecasts and bills of materials (BOMs), but also by operational terms in contracts and supplier documents (e.g., MOQs, lead times, price tiers, allocation caps, substitution approvals). LLM-based extraction can speed up structuring these terms, but extraction-only or LLM-only decision pipelines are brittle: missed clauses, unit errors, and unresolved conflicts can yield infeasible plans or silent contract violations, amplified by BOM coupling. We introduce Contract2Plan, a verified GenAI-to-optimizer pipeline that inserts a solver-based compliance gate before plans are emitted. The system retrieves clause evidence with provenance, extracts a typed constraint schema with evidence spans, compiles constraints into a BOM-aware MILP, and verifies grounding, eligibility, consistency, and feasibility using solver diagnostics, triggering targeted repair or abstention when automation is unsafe. We formalize which clause classes admit conservative repair with contract-safe feasibility guarantees and which require human confirmation. A self-contained synthetic micro-benchmark (500 instances; T=5) computed by exact enumeration under an execution model with MOQ uplift and emergency purchases shows heavy-tailed regret and nontrivial MOQ-violation incidence for extraction-only planning, motivating verification as a first-class component of contract-grounded planning systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。