arXiv cs.AI· Changxu Duan·· 13 小时前AI 评分31
用级联查找恢复业务规则：LLM 智能体助力企业字段预测
Recovering Business Rules as Cascade Lookups for Enterprise Field Prediction
AI 导读
研究提出一种知识图谱引导的工作流，由 LLM 智能体提出候选业务键（如客户与单据类型的列组合），经 SQL profiling 验证后编译为确定性级联查找，LLM 仅在离线规则发现阶段使用，推理时无需模型服务。在企业销售订单预测和公开关系基准上的实验显示，字段遵循稳定业务规则时级联查找最有效，而预测依赖时间或邻域模式时学习型图模型更优。漂移分析可将残余误差转化为配置维护诊断。
正文 · 原文
Abstract:Enterprise sales-order systems rely on manually maintained configuration rules to determine fields such as payment terms, shipping points, and sales ownership. When these rules are incomplete or stale, operators must enter values by hand, and downstream errors spread into billing, logistics, and reporting. This paper studies whether missing or outdated rules can be recovered from historical transactions instead of being relearned as opaque statistical patterns. We introduce a knowledge-graph-guided workflow in which an LLM agent proposes candidate business keys, meaning column combinations such as customer and document type, validates them through SQL profiling, and compiles the resulting evidence into deterministic cascade lookups. The LLM is used only during offline rule discovery. At inference time, prediction is a transparent key lookup with no model-serving requirement. Experiments on enterprise sales-order prediction and public relational benchmarks show that cascades are most effective when fields follow stable business rules, while learned graph models remain preferable when prediction depends on temporal or neighborhood patterns. Drift analysis further turns residual errors into diagnostics for configuration maintenance. Code and data: this https URL.
| Comments: | Accepted at ECML PKDD 2026 Applied Data Science Track |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Databases (cs.DB); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.34258 [cs.LG] |
| (or arXiv:2610.34258v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34258 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.1007/978-3-032-37682-4_6
DOI(s) linking to related resources |
Submission history
From: Changxu Duan [view email]
[v1]
Sun, 25 Oct 2026 12:33:59 UTC (509 KB)
来源：arXiv cs.AI · arxiv.org