Risk detection method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a risk detection method, device and equipment and a storage medium. The method comprises the steps of obtaining a sub-graph structure of a target node, the sub-graph structure comprising node neighbor snapshots of the target node at a plurality of time points within a preset time period, and the node neighbor snapshots comprising an association relationshipbetween the target node and at least one associated node of the target node; obtaining a time sequence vector list of the target node according to the sub-graph structure; and inputting the time sequence vector list into the risk detection model to obtain a risk detection result of the target node. According to the method provided by the embodiment of the invention, multi-source heterogeneous threat information data can be fused, so that a time sequence association network formed by node characteristics and node association relationships under long-time performance is constructed, and scene risk prediction of the nodes is realized through association learning and time sequence prediction.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This patented technology helps create an associational structure that explains how multiple sources (such as different types) are used together more efficiently than just one source alone. It also allows nodes within this structure to interact with each other over longer periods without being affected or losing their effectiveness due to factors like environmental conditions such as temperature changes or interference from external signals. Overall, it provides technical benefits to improving security systems' ability to detect attacks on complex networks.

Problems solved by technology

The technical problem addressed in this patented technology relates to detecting potential threats related to intelligent networks (IN). Current methods for extracting structural properties from graphs require significant computing resources and result in low accuracy due to limitations like repetitive computations.

Images