Method for identifying sensitive information and device

Abstract

The embodiment of the invention discloses a method for identifying sensitive information, wherein the method includes steps of receiving target information, and extracting text information in the target information; calculating Hash value of the text information, and segmenting the text information and acquiring the word segmentation set when the Hash value of the text information is different from that of the preset feature sensitive information; calculating the Hash value of the segmented word in the word segmentation set; according to the Hash value of the segmented word in the word segmentation set, generating the similarity between the target information and the preset feature sensitive information; according to the similarity and / or the sematic analysis on the text information, judging that the target information is sensitive information. The invention further correspondingly discloses a device for identifying the sensitive information. The method and device for identifying sensitive information have high identifying accuracy in judging if the content published by a user is sensitive information.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for identifying sensitive information. Background technique [0002] In the existing web2.0 Internet social applications, the content of the application is no longer published and pushed by the server, but more published and interacted by the users themselves. For example, users can take pictures on their mobile phones and share them on the Internet and send them to other users, and they can edit forum topics, blogs, forum posts, Weibo and other text content to share with other users. However, the content shared by users may be illegal or unethical, such as foul language, violence, obscenity, fraud, etc. Therefore, it is necessary to identify and block sensitive information posted by users. [0003] In the existing methods for online interception of sensitive information, a relatively simple text similarity algorithm strategy such as full-text md5 similarit...

AI Technical Summary

Problems solved by technology

However, the content shared by users may be illegal or unethical, such as foul language, violence, obscenity, fraud, etc. Therefore, it is necessary to identify and block sensitive information from the content posted by users

[0003] In the existing methods for online interception of sensitive information, a relatively simple text similarity algorithm strategy such as full-text md5 similarity is usually used to find and intercept sensitive information. Although the accuracy of this method is very high, the recall rate of sensitive information depends heavily on the existing The size of the sensitive information feature library, and sensitive information is very prone to variants, it is difficult for this similarity algorithm to effectively find similar text messages, the recall rate of sensitive information is low, and the method of manually adding sensitive information features has A certain time lag makes it difficult to solve the problem of message variants

[0004] Therefore, the method of online interception of sensitive information in the traditional technology has a certain time lag due to the artificial addition of sensitive information features, which makes the accuracy of identifying sensitive information not high, and cannot accurately identify variants and approximate sensitive information.

Images