A multi-dimensional data-based supply chain anomaly intelligent identification method and system

By acquiring timestamps of order and logistics information, analyzing delay duration and abnormal inventory allocation characteristics, and combining cross-system interface fault logs, the root causes of supply chain anomalies can be identified. This solves the problem of low accuracy in existing technologies and enables more efficient anomaly localization and system optimization.

CN122414993APending Publication Date: 2026-07-17STATE GRID ZHEJIANG ELECTRIC POWER CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610857039.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-06-15
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies cannot accurately identify the root causes of supply chain anomalies when processing multi-source heterogeneous data, resulting in low accuracy in anomaly localization.

Method used

By obtaining timestamps from the order management system and logistics information, we can analyze the delay duration, identify abnormal inventory allocation characteristics, combine cross-system interface fault logs, determine the conflict points of status fields, analyze the degree of diffusion of adjustment operation information, and finally identify the cause of the anomaly.

Benefits of technology

It improves the accuracy of supply chain anomaly identification by deeply analyzing cross-system data to accurately pinpoint the root cause of anomalies, thereby enhancing the accuracy of order processing and the efficiency of system optimization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122414993A_ABST
    Figure CN122414993A_ABST
Patent Text Reader

Abstract

本发明公开了一种基于多维度数据的供应链异常智能识别方法及系统,应用于供应链异常识别技术领域,通过获取订单管理系统中各个订单的订单信息和物流信息;基于各个订单的订单信息和物流信息各自对应的时间戳,得到延迟时长,根据延迟时长,得到频次分布和高频偏差幅度;根据频次分布和高频偏差幅度进行分析,得到状态字段冲突点集合;根据状态字段冲突点集合获取存在冲突的订单的调整操作信息,对调整操作信息进行分析,得到扩散程度,根据扩散程度,得到订单处理冲突的根因分布;根据根因分布对各个订单的融合参数进行调整和分析,得到延迟影响路径图,基于延迟影响路径图,得到异常原因识别结果,提高了供应链异常识别的准确性。
Need to check novelty before this filing date? Find Prior Art