Method and system for generating full-traffic vectorized records in network application layer

Abstract

The present invention provides a method and system for generating a full flow vectorized record at a network application layer, including: a known protocol analysis module, an information flow comprehensive analysis module, a time window flow description module, a full flow vectorized model generation module, and a full flow vector module. The invention not only fully covers the full flow information in a time slice, but also compresses the representation space; uses a deep neural network to automatically extract important features in the full flow information of each time slice, and then forms a full volume record. It not only retains the important information of the full flow, but also compresses the record storage space. It can be widely used in long-term recording and storage, presentation, application layer alarm calculation, similarity calculation, security intrusion budget, value mining and other scenarios.

Description

technical field [0001] The invention relates to the fields of data processing, traffic analysis, log processing, network analysis, and application performance monitoring, in particular to a method and system for generating a vectorized record of full traffic at a network application layer. Background technique [0002] A distributed system generally refers to a software system built on a network. This system has a high degree of cohesion and transparency, and has a wide range of applications in the commercial, public, and IT infrastructure fields. Correspondingly, the monitoring and representation of distributed systems also have broad meanings and uses, such as operation and maintenance assurance, security assurance, and data value mining. [0003] In a distributed system, the log-based monitoring scheme has the advantage of being easy to implement, but the disadvantage is that due to the lack of a unified standard, the amount of data is too noisy (for example, including th...

AI Technical Summary

Problems solved by technology

At present, due to the large amount of data on the one hand and the rich diversity on the other hand, the full data of the application layer can only record some indicators of the application layer based on business experience, such as transaction volume, response time, success rate, etc. presented and analyzed, but undocumented metrics may contain important information

Images