Equipment owner identity real-time identification method and device based on acceleration period change rule

Abstract

The invention relates to an equipment owner identity real-time identification method and device based on an acceleration period change rule. An acceleration sensor is arranged in equipment, and an equipment processor receives data of the acceleration sensor and carries out identity identification. The method specifically comprises the following steps that by means of acceleration projections of the acceleration sensor in the X axis, Y axis and X axis, an acceleration amplitude value of the acceleration sensor is obtained in real time; according to the acceleration amplitude value in the period, the period change rule is calculated through the clustering algorithm, and a focusing area of owner period data points in a multi-dimensional space is determined; three-axis data of the acceleration sensor of the equipment is collected in real time at a preset time interval, a corresponding acceleration amplitude value is calculated, and the identity of the owner is judged according to the focusing area of the owner period data points in the multi-dimensional space. By means of the method and device, continuous real-time identity monitoring can be achieved under the condition that use habits of a user are not interfered too much, and the possibility of counterfeit is reduced, so that the safety is improved, and the method and device have an important guiding significance for information safety.

Description

technical field [0001] The invention belongs to the technical field of information security, and in particular relates to a method and a device for real-time identification of the identity of an equipment owner based on the periodic change rule of acceleration. Background technique [0002] In today's society with highly developed information technology, how to accurately identify a person's identity and protect information security is a key social problem that must be solved in today's information age, which requires an identification system. Identification systems have been applied to various industries and are increasingly used. There are many schemes for identifying identity by using motion features through mobile phones at present, which include two types of schemes that are relatively close to the present invention: one scheme is to use short-term motion (gesture) features to realize identification of mobile phone users. When learning the identity characteristics of t...

AI Technical Summary

Problems solved by technology

Another solution is to analyze the gait characteristics based on the acceleration sensor data, and identify the human body activity or the identity of the owner. The whole process is similar to the present invention, but there are the following differences: (1) In the second solution, there are also studies based on smart phones. User identity recognition, but it needs to use unsupervised feature learning technology, such as principal component analysis PCA method, to extract features by compressing and reducing the dimensionality of sensor data, and then treat identity recognition as a classification problem, using C4.5 algorithm, simple Bayesian method and support vector machine SVM algorithm to identify the identity of the owner

The existing methods of identity authentication based on mobile phone sensors have the following disadvantages: (1) Active cooperation of users is required, and too many verification operations will reduce user satisfaction

(2) It belongs to one-time authentication and cannot realize continuous identity monitoring

(3) Low security

Images