Keypress behavior pattern construction and analysis system of touch screen user and identity recognition method thereof

Abstract

The invention provides a keypress behavior pattern construction and analysis system of a touch screen user and an identity recognition method thereof. According to the invention, data analysis is performed by using history keypress information of inputting a password by a soft keyboard on a mobile phone touch screen; a corresponding neural network model is established; and model calculation is performed on new to-be-tested data, to recognize a user identity. The system comprises a user data acquisition module, a data pre-processing module, a model training module, and a user identity identification module. The user data acquisition module is responsible for acquiring time series information of a user clicking the soft keyboard and inputting the password, and pressure and contact area information. The data pre-processing module is responsible for pre-processing the acquired data, removing dirty data, and performing normalization on the data. The model training module is responsible for performing analysis and modeling on a key-in mode of all users. The user identity identification module is responsible for performing model calculation on the new to-be-tested data, to recognize the user identity and improve security of a user account password.

Description

technical field [0001] The invention relates to e-commerce identity authentication, in particular to a system for constructing and analyzing button behavior patterns of touch screen users and an identity identification method thereof. Background technique [0002] The impact of computer network on human life and economy is incomparable to other information carriers. Its rapid development and all-round penetration have accelerated the process of informatization of the entire society. Among them, e-commerce is an important application of Internet technology, and it is becoming a global economic theme with rapid development. In the growing e-commerce market, a considerable number of users have begun to turn to mobile commerce. [0003] However, with the development of various e-commerce websites, more and more potential safety hazards involving electronic transactions have emerged. Illegal users pretending to be legitimate users to steal information and account funds have brou...

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a system for constructing and analyzing user button behavior patterns on a touch screen and its identification method, which is used to solve the problem that the existing authentication methods and means cannot effectively guarantee the security of user accounts. sexual problems

Images