Automatic identifying and classifying method for sensitive data

Abstract

The invention discloses an automatic identifying and classifying method for sensitive data, comprising the steps of: pre-treating a training dataset, removing unmeaning words, and thereby obtaining a word set; treating the word set according to TF-IDF, calculating the vector weighed value of each word, and thereby obtaining a basic data corpus; manually identifying and classifying the basic data corpus, selecting the words on which sensitive data can be marked, and thereby forming a sensitive word corpus; performing word segmentation on target data by the word segmentation technology, and then matching extracted features with the sensitive word corpus; and sorting the classification according to accumulated values of the weighted values of the sensitive words from high to low. According to the automatic identifying and classifying method for sensitive data, through establishing the sensitive word corpus, performing word segmentation on the target data, and calculating the accumulated values of the weighted values of the sensitive words, the classification of the sensitive data is achieved, and thereby efficiency and accuracy of the sensitive data identification and classification are improved, and the defect that the existing sensitive data is identified depending on dictionary classification and manual classification is remedied.

Description

technical field [0001] The invention relates to the technical field of information monitoring in computer networks, in particular to a method for automatic identification and classification of sensitive data. Background technique [0002] Data is the supporting foundation of enterprise business and the core part of enterprise information system. Once there is a problem with the database management system, it will affect the continuity of the entire enterprise business. In the protection scheme for sensitive data, the core part is to select sensitive data from massive data and complete the identification of sensitive data. [0003] At present, the identification of sensitive data mainly relies on dictionary matching methods and manual identification methods. [0004] The dictionary matching method matches the data one by one by manually defining the pattern matching formula of sensitive data. When the data is found to meet the pattern matching formula, the data is defined ...

AI Technical Summary

Problems solved by technology

[0007] The sensitive data dictionary matching method has the following defects: 1. The recognition accuracy is low. The dictionary matching adopts a pattern matching method, so the establishment of the data dictionary determines the accuracy of sensitive data recognition. When the dictionary is incomplete or the dictionary is established incorrectly , there will be a problem of reduced recognition accuracy; 2. Classification result interference. Because dictionary matching is used, the same data information will be matched to multiple data dictionaries. Because traditional data dictionaries cannot perform weighted calculations, it will cause interference to classification results. , resulting in inaccurate classification results

[0008] The artificial identification method of sensitive data has the following defects: 1. The identification speed is slow. Due to the manual processing method, when faced with a large amount of data, the manual combing speed is relatively long compared with the machine identification speed cycle, and the professional quality of the processing personnel is relatively high. High; 2. The judging standards are not uniform. Since the sensitive data identification process mainly depends on the subjective judgment of people, different people may have different judging standards for the same data, and even the results identified by the same person at different times are still different. different, which will lead to discrepancies in sensitive data identification results