Problem rectification suggestion generation method based on deep learning

Abstract

The invention discloses a problem rectification suggestion generation method based on deep learning, and the method comprises the following steps: adding entity labels to safety problem data of a training set and a verification set, and then splicing the safety problem data with various entity definition types; constructing an entity recognition model; constructing a relation extraction model; performing equivalent protection evaluation on the system to be evaluated, performing entity identification by using the entity identification model, outputting entity information, performing entity relationship extraction by using the relationship extraction model, and outputting entity relationship information; according to the determined entity information and entity relation information, knowledge graph reasoning is carried out, and rectification suggestion related information is obtained; and combining the entity information, the entity relationship information and the rectification suggestion related information to generate a protection evaluation safety problem rectification suggestion. The method has the beneficial effects that the generation quality and efficiency of the safety problem rectification suggestions are improved, and the labor cost is reduced.

Description

technical field [0001] The invention relates to the technical field of rectification suggestion generation. More specifically, the present invention relates to a deep learning-based problem rectification suggestion generation method. Background technique [0002] Equal Protection Evaluation (Information Security Level Protection Evaluation) is a qualified evaluation agency certified by the Ministry of Public Security. According to the national information security level protection regulations, entrusted by relevant units, in accordance with relevant management norms and technical standards, information system security level protection Activities to detect and evaluate conditions. [0003] For the security problems found during the evaluation of information system security by the evaluation agency, the evaluator needs to manually write the corresponding security problem rectification suggestions. The manual writing has the following problems: [0004] Low efficiency: It req...

AI Technical Summary

Problems solved by technology

[0004] Low efficiency: manual review of a large amount of data is required, making it difficult to improve efficiency;

[0005] High labor cost: Professionals are required to participate, and the labor cost is high;

[0006] No unified standard: Due to the diversity of questions and personal subjective reasons of the assessors, there is no unified standard for the recommendations and the quality is uneven;