Password word segmentation system and method based on semantic structure

Abstract

The invention discloses a password word segmentation system and method based on a semantic structure. The system comprises a preprocessing module, an NLP semantic extraction module and a non-NLP semantic annotation module, wherein the preprocessing module is used for receiving a password to be subjected to word segmentation, extracting a special semantic factor which cannot be identified in the subsequent steps in the password, carrying out word pre-segmentation on the rest part according to a character type, outputting a letter part to the NLP semantic extraction module, and outputting a non-letter part to the non-NLP semantic annotation module; the NLP semantic extraction module performs word segmentation on the letter part of the password by using an NLP tool to obtain multiple semanticfactors; and the non-NLP semantic annotation module performs semantic annotation on the part, which cannot be subjected to word segmentation by the NLP tool, in the password. According to the method,word segmentation is carried out on the password according to the semantic information contained in the password based on the corpus, the semantic structure of the password is recognized, and accurate word segmentation can be carried out on the passwords set by both the Chinese user and the English user.

Description

technical field [0001] The invention relates to a technology in the field of computer security, in particular to a semantic structure-based password word segmentation system and method. Background technique [0002] Because text passwords have good security and usability, text passwords are still widely used in user authentication of computer systems and online services. Since the passwords used by most users are defined by the users themselves, in order to facilitate memory, users often choose several strings with specific semantics or rules as passwords, so the research on the semantic structure of passwords is of great significance for improving the security of user passwords. [0003] Different from natural language, passwords do not have a fixed grammatical structure. Users can arbitrarily combine various semantic factors according to the rules of the website when setting passwords. Therefore, word segmentation methods for natural language are not suitable for password ...

AI Technical Summary

Problems solved by technology

[0004] In the past, most of the research on the semantic structure of passwords focused on English user passwords. Due to the differences between the passwords set by English users and Chinese users, word segmentation methods proposed for English user passwords often performed poorly on Chinese leak databases.

In recent years, several researchers have begun to study Chinese user passwords. The research shows that adding additional semantic information to the word segmentation system is effective, but what information to add and how to add information are still subjective judgments, and there is no systematic method.

Images