Smartwatch unlocking and authentication method based on motion sensing behavioral features

Abstract

The invention discloses a motion sensing behavior feature-based intelligent watch unlocking and authentication method. The method comprises the steps of analyzing sensor data generated when a user performs motion behaviors on an intelligent watch according to prompts; dividing the motion behaviors into multiple motion behavior modes; extracting a behavior feature in each motion behavior mode; building a user identity model in each behavior mode based on the behavior feature; and performing authentication on an identity of the intelligent watch user by adopting a window averaging method. According to the method, the motion behaviors do not need to be memorized and carried, behavior data collection is convenient and natural, and non-invasive unlocking and authentication can be realized; and in addition, by adopting a method for performing modeling and window authentication on different types of motion behaviors, the stability of an authentication model can be ensured, the motion behavior features of the user can be better reflected, and the robustness and fault tolerance of unlocking and authentication can be remarkably improved.

Description

technical field [0001] The invention belongs to the technical field of smart watch safety protection, and in particular relates to a method for safely unlocking and authenticating smart watch users. Background technique [0002] With the advancement of social informatization and intelligence, smart watches (such as Apple Watch and Huawei Watch) have penetrated into all aspects of people's lives, and more and more personal information (such as text messages, emails, pictures, etc.) and sensitive Information (such as bank account number, office data, etc.) is stored in the smart watch. In addition, the increasing popularity of business applications on smart watches and the frequent occurrence of privacy information leakage incidents have gradually brought the security protection of smart watches into the public's field of vision. [0003] The existing unlocking and authentication methods of smart watches are mainly passwords, Jiugongge pattern locks, and fingerprints. Howeve...

AI Technical Summary

Problems solved by technology

However, the first two methods are vulnerable to observation attacks and guessing attacks, and the unlocking method is stolen by the attacker; the fingerprint authentication method requires special hardware support; and these methods require the user to operate on the watch screen with a limited size. Higher rate, detrimental to user experience

Images