Safety evaluator dispatching system and method based on neural network

Abstract

The invention discloses a safety evaluator dispatching system and method based on a neural network. The system comprises a user information data module, a user feature extraction module, an evaluationdispatching graph neural network module, a preliminary evaluation dispatching strategy total module, a re-evaluation dispatching strategy module and a dispatching implementation and tracking module.According to the system and the method provided by the invention, complex influence factors of an evaluation task required by a safety evaluation standard are all included, internal relations among different users are fully embodied in embedded expression while dimensions are reduced, and an optimal evaluator for a first round of evaluation and a second round of evaluation based on historical datais assigned to each user; in the system, a depth auto-encoder and a graph neural network technology are respectively utilized to obtain an optimal allocation scheme.

Description

technical field [0001] The invention relates to the field of secure communication, in particular to a neural network-based dispatching system and method for safety assessors. Background technique [0002] With the development of the national network security strategy, the demand for network security evaluation is growing rapidly. In order to face the rapidly increasing number of users and the complexity of evaluation content, the cloud-based network security evaluation platform has become a key technology for network security evaluation solutions. [0003] The network security evaluation platform faces a large number of users, and at the same time, the current status of the user's network and information system is very different. How to provide the best service for users with different status under the condition of limited resources has become an urgent problem to be solved; on the other hand, network security The resources of assessors are also facing a serious shortage. Th...

AI Technical Summary

Problems solved by technology

[0006] 1) The effect of assigning testers to users is highly dependent on the personal experience of the dispatching administrator, and the effect is unstable

[0007] 2) With the development of network security assessment standards and changes in the network security situation, the content of network security assessment has become more and more complex, and the factors that affect the assessment results of assessors have grown rapidly

Due to the high difficulty of assignment, in many cases, manual assignment assigns the same evaluators for the two rounds of evaluations, which cannot be used to optimally match the evaluators according to the different characteristics of the two rounds of evaluations.

Images