Self-adaptive distributed intelligent decision making method

Abstract

The invention belongs to the field of data safety and particularly relates to a self-adaptive distributed intelligent decision making method. Possible abnormalities are detected through exploiting aiming at real-time monitoring logs and operation request logs, advantages of a neutral network in mode recognition and knowledge based reasoning theories are combined, a self-adaptive mechanism is introduced on the basis of integrating of multiple adjacent node data to realize intrusion detection in a distributed manner, and a decision making process is arranged in distributed nodes instead of a central control board, so that network transmission is reduced, and distributed decision making speed is increased. By integrating of information feedback of adjacent nodes, self-adaptive regulation is performed without dependency on global information, and accordingly data transmission is reduced, and intrusion data difficult for a single node to detect can be detected out effectively.

Description

technical field [0001] The invention belongs to the field of data security, and in particular relates to an adaptive distributed intelligent decision-making method. Background technique [0002] The techniques commonly used in intrusion detection include expert systems, pattern matching (such as neural networks, etc.) and techniques based on statistical methods. But in recent years, the research hotspots are more and more concentrated on neural network, because it can better deal with the random characteristics of the original data, and it does not need to make any statistical assumptions on these data. At the same time, it also has better anti-interference ability. [0003] However, only using neural networks as the main technology for intrusion detection also has many limitations; at the same time, the current research on intrusion detection is generally limited to a single detection point, and the current network attack methods are developing in a distributed direction, a...

AI Technical Summary

Problems solved by technology

[0003] However, only using neural networks as the main technology for intrusion detection also has many limitations; at the same time, the current research on intrusion detection is generally limited to a single detection point, and the current network attack methods are developing in a distributed direction, and it is difficult for a single node to detect The intrusion data is becoming more and more destructive and concealed. These studies generally use the information of multiple detection nodes to be processed and analyzed by a central console.

However, considering the delay caused by network transmission and the large detection load brought by large-scale networks, the intrusion detection of this architecture will face many difficulties.

Images