A work order data processing method and device, electronic equipment and storage medium

By performing semantic recognition and temporal correlation processing on historical work order data, and combining it with regression residual analysis on real-time work order data, the problem of insufficient accuracy in work order prediction was solved, enabling timely detection of anomalies and reduction of fault occurrence, thus improving the reliability of work order processing.

CN122113043APending Publication Date: 2026-05-29CHINA TELECOM DIGITAL TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA TELECOM DIGITAL TECHNOLOGY CO LTD
Filing Date
2026-01-28
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

In existing technologies, the prediction of the number or type of work orders relies on simple historical statistical data, which cannot accurately grasp trend changes. Especially when facing sudden events or seasonal changes, the prediction accuracy is insufficient, the processing efficiency is low, and it is difficult to detect anomalies, which can easily lead to failures.

Method used

By acquiring historical work order data for semantic recognition, determining the time-series feature sequence, and performing time-series correlation processing, combined with real-time work order data for regression residual processing, anomalies are identified and fault warnings are provided.

Benefits of technology

It improves the accuracy of work order data detection, enables timely detection of anomalies, reduces the occurrence of failures, and improves operational reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122113043A_ABST
    Figure CN122113043A_ABST
Patent Text Reader

Abstract

Embodiments of the present application provide a work order data processing method and device, electronic equipment and storage medium, comprising: in response to the start time of the current time step, obtaining historical work order data; performing semantic recognition on the historical work order data to determine a time sequence feature sequence; performing time sequence correlation processing on the time sequence feature sequence to determine predicted work order data; in response to the end time of the current time step, obtaining real-time work order data; performing regression residual processing based on the historical work order data, the predicted work order data and the real-time work order data to determine residual data; and in the case that the residual data meets a preset residual threshold, determining fault warning information based on the real-time work order data. Through the embodiments of the present application, the accuracy of work order prediction can be improved, and the abnormal situation of work order can be effectively detected and warned in advance.
Need to check novelty before this filing date? Find Prior Art