A data generalization method for network security events
By generating synthetic datasets through data sampling, cleaning, aggregation, binning, dimensionality reduction, and feature selection, the problem of information loss and distortion in the generalization of cybersecurity incident data is solved, and the data privacy protection and usability are improved, adapting to multi-task requirements.
CN117150256BActive Publication Date: 2026-07-14CHINA TOBACCO ZHEJIANG IND CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA TOBACCO ZHEJIANG IND CO LTD
- Filing Date
- 2023-08-25
- Publication Date
- 2026-07-14
Smart Images
Figure CN117150256B_ABST
Abstract
The application discloses a data generalization method for network security events, comprising: sampling a network security event data set, obtaining sampled data and performing data cleaning, judging whether the cleaned data matches an aggregation rule based on the cleaned data set, and performing data aggregation calculation on the data matching the aggregation rule to obtain a data set aggregated according to object, time agreement, and preset limit value of aggregation times; performing data binning processing on the data set to obtain a data set with multiple discrete data intervals and performing dimension reduction processing to obtain a dimension-reduced data set; performing feature selection on the dimension-reduced data set to obtain a feature subset in the dimension-reduced data set; and the feature subset in the dimension-reduced data set is the finally generated generalization data of the network security event; the application realizes generalization through the steps of data sampling, cleaning, aggregation, binning, dimension reduction and feature selection of the network security event, reduces the scale and dimension of the data, and simultaneously retains key information and insight.
Need to check novelty before this filing date? Find Prior Art