A power grid engineering execution state early warning method and device

By screening key indicators and constructing a physical quantity optimization prediction model, combined with feature extraction from construction data and unstructured data, accurate early warning of the execution status of power grid projects was achieved. This solved the problems of indicator redundancy and insufficient environmental response in existing technologies, and improved the accuracy and real-time performance of anomaly identification and progress prediction.

CN122134137APending Publication Date: 2026-06-02STATE GRID JIANGSU ELECTRIC POWER CO LTD TAIZHOU POWER SUPPLY BRANCH +1
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
STATE GRID JIANGSU ELECTRIC POWER CO LTD TAIZHOU POWER SUPPLY BRANCH
Filing Date
2026-04-07
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Existing methods for power grid project progress management and abnormal risk early warning have problems such as redundant and overlapping indicators, inability to reflect regional and project type differences, inability to respond to environmental changes in real time, and insufficient semantic mining of unstructured text anomalies, resulting in systematic deviations between investment completion, cost accounting, and construction progress.

Method used

By screening key indicator data, a physical quantity optimization prediction model is constructed, which is then dynamically optimized in conjunction with construction data to determine the project progress prediction optimization curve. Furthermore, features are extracted from topological and unstructured data, and abnormal feature data is integrated to achieve accurate early warning of the power grid project execution status.

Benefits of technology

It significantly improves the accuracy, timeliness, and interpretability of anomaly identification, provides reliable support for lean engineering management, and enhances the accuracy of schedule forecasting and real-time response capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122134137A_ABST
    Figure CN122134137A_ABST
Patent Text Reader

Abstract

This invention discloses a method and apparatus for early warning of the execution status of power grid projects. The method includes: acquiring construction data, indicator data, and unstructured data of the power grid project; filtering the indicator data based on pre-determined key early warning indicators to provide key indicator data; dynamically optimizing the project progress prediction curve based on a pre-constructed physical quantity optimization prediction model and the construction data; comparing the deviation between the project progress prediction optimization curve and the construction data to provide progress deviation; extracting and mapping features from the topology and unstructured data of the power grid project to identify abnormal feature data; and transforming and fusing the key indicator data, progress deviation, and abnormal feature data to provide abnormal results for the power grid project, thereby achieving early warning of the execution status of the power grid project. This invention can dynamically perceive and accurately warn of the entire process of the power grid project's execution status, improving the accuracy of anomaly identification.
Need to check novelty before this filing date? Find Prior Art