User identity authentication method based on gait information

Abstract

The invention provides a user identity authentication method based on gait information. The method includes: cutting an acceleration data sequence generated by walking of a user; after the data is cut, inputting the data into a neural network model for data training to extract walking characteristics of the user so as to identify the identity of the user; inputting the verification data set into the updated neural network model to determine a variance and a threshold value of a correct authorized user, and calculating the distance between the characteristic space of the unauthorized user and the characteristic space of the authorized user by adopting an extreme value statistics method, so that the identity of the unauthorized user is rejected, and the potential safety hazard of illegal login of the user can be controlled. By preprocessing, learning and analyzing acceleration data of the sensor, walking characteristics of a user are learned, the user can be identified, an illegal user can be automatically locked, and passive authentication is achieved.

Description

technical field [0001] The invention belongs to the technical field of biological authentication and artificial intelligence, and in particular relates to a user identity authentication method based on gait information. Background technique [0002] Biometrics provide improved reliability and usability for user authentication because, unlike traditional methods, it does not need to be remembered. With the integration of dedicated hardware and biometric information in smartphones, new biometric authentication methods have emerged that use motion sensors to acquire behavioral biometric information and allow users to authenticate smartphones or services based on the actions they will perform, This biometric authentication method respectively utilizes motion sensors to acquire biological movement information and allows users to verify their identity according to the operations they will perform. Users can be authenticated by motion sensor behavior, and the data of the motion se...

AI Technical Summary

Problems solved by technology

[0003] Human motion behavior is a repetitive task. By using mobile phone motion sensors, user motion status can be measured unobtrusively and continuously. It is a more user-friendly authentication mechanism to distinguish motion status from other biometric patterns, but in user Once logged in, there is no further authentication process with traditional authentication methods until the phone is locked or turned off, allowing a thief to gain access to the phone without anyone noticing

Images