Cloud environment network equipment entity identification method

Abstract

The invention discloses a cloud environment network equipment entity identification method. The method comprises the following steps: firstly, collecting original data of a text corpus corresponding to cloud environment network equipment information; according to the characteristics of cloud environment network equipment information, a small number of features are artificially formulated to form a feature template, and an input statement is converted into a corresponding word vector sequence; extracting character-level features of each word according to the converted word vector sequence; combining the character-level feature vector and the local context feature as input information, and extracting a semantic feature of the input information; and finally, for the obtained semantic features of the input information, performing cloud environment network equipment entity labeling on each character by using a conditional random field to complete identification of the cloud environment network equipment entity. The method can be used for identifying and classifying network equipment entities in the cloud environment, and internal system architecture of the closed cloud environment can be quickly reconstructed outside the closed cloud environment.

Description

technical field [0001] The invention relates to the technical field of cloud environment network device entity recognition, specifically a method for cloud environment network device entity recognition based on a convolutional neural network, a bidirectional long-short-term memory neural network, and a conditional random field. Background technique [0002] Cloud environment: Cloud environment is a distributed computing system based on virtualization technology. Its system architecture can be mainly divided into three levels: infrastructure layer, platform layer and software service layer. The corresponding names are infrastructure as a service. (IaaS, Infrastructure as a Service), which mainly includes computer servers, communication, storage devices, etc., and these computing resources are uniformly virtualized into computing resources, storage resources and network resources through virtualization technology; Platform as a Service (PaaS, Platform as a Service), which main...

AI Technical Summary

Problems solved by technology

Although the deep neural network has achieved good results in the field of naming recognition in the general field, in the cloud environment, due to the difficulty in distinguishing physical nodes from virtual devices after layer-by-layer virtualization, it is difficult to locate dynamically changing cloud resources. With various security protection measures, traditional port scanning, IP scanning, and infiltration methods are not only difficult to describe the overall picture of the network device entity in the cloud environment, but will even be quickly discovered and disposed of by cloud security protection measures

Images