Power system software security risk early warning method, device and equipment and storage medium

CN122153904APending Publication Date: 2026-06-05ELECTRIC POWER RES INST CHINA SOUTHERN POWER GRID CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ELECTRIC POWER RES INST CHINA SOUTHERN POWER GRID CO LTD
Filing Date
2026-02-11
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing technologies are insufficient for efficiently and accurately identifying the correlations between software vulnerabilities in power systems, resulting in low efficiency in vulnerability correlation analysis and reduced power system security.

Method used

By acquiring the dependencies and information of software nodes and vulnerability nodes in the power system, extracting features, and inputting them into a trained vulnerability association probability prediction model, the model predicts the association probability between each vulnerability node, generates a vulnerability association network, and issues early warnings based on this network.

Benefits of technology

It improves the accuracy of vulnerability correlation, reduces the difficulty of knowledge graph construction and maintenance, can efficiently process massive amounts of software vulnerability data, dynamically adapt to the addition and updating of vulnerability nodes, promptly discover potential hidden dangers, and improve the security of power systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122153904A_ABST
    Figure CN122153904A_ABST
Patent Text Reader

Abstract

The application relates to a power system software security risk early warning method, device and equipment and a storage medium. The method comprises the following steps: acquiring first dependency relationships and software information of software nodes in a power system, and second dependency relationships and vulnerability information of vulnerability nodes; performing feature extraction on the first dependency relationships and the software information to obtain multi-dimensional software node features, and performing feature extraction on the second dependency relationships and the vulnerability information to obtain multi-dimensional vulnerability node features; inputting the multi-dimensional software node features and the multi-dimensional vulnerability node features into a trained vulnerability correlation probability prediction model to predict correlation probabilities between the vulnerability nodes; screening, from the vulnerability nodes, a vulnerability node combination with a correlation probability greater than a preset correlation probability threshold, adding edges between the vulnerability nodes in the vulnerability node combination, and generating a vulnerability correlation network; and early warning the power system according to the vulnerability correlation network. The method is beneficial to improving the safety of the power system.
Need to check novelty before this filing date? Find Prior Art