Intelligent terminal depth perception method and system thereof

Abstract

The invention discloses an intelligent terminal depth perception method. The method comprises the following steps: S1, acquiring user mobile Internet flow, and filtering business data traffic from the user mobile Internet traffic; S2, performing identification, feature matching and statistical analysis on the business data traffic according to a preset identification rule to gain the type and content of business data and the identification and statistics results of a special subject; and S3, controlling the business data according to a preset control rule. The invention also discloses an intelligent terminal depth perception system. An intelligent machine application is analyzed, and the operation behaviors of a user on an intelligent system are analyzed, so that an intelligent terminal has a corresponding perception capability and control capability, and identified user operation data is controlled and managed in real time.

Description

technical field [0001] The invention relates to the field of mobile Internet, in particular to a method and system for depth perception of an intelligent terminal. Background technique [0002] With the development of mobile Internet and smart terminals, more and more users conduct corresponding business processing and corresponding shopping, reading, chatting, living, audio-visual, etc. through smart terminals. Smart terminals have become an indispensable part of people's lives. By analyzing the behavior and habits of users downloading application software, we can understand which applications users are interested in, and conduct statistical analysis on the corresponding behavior of smart terminals to obtain data and provide data support for product marketing. [0003] The prior art mainly includes the following two analysis methods: [0004] (1) Collect the data of the application software downloaded by the user in the smart terminal. This method requires the user to in...

AI Technical Summary

Problems solved by technology

Its defect is that although it is possible to accurately analyze the behavior and habits of users downloading mobile phone applications by combining multiple analysis methods, it only uses deep packet inspection (DPI) to predict HTTP traffic and AAA authentication traffic data. After processing, the download URL, user mobile phone number, and download time are obtained and then sent to the mobile Internet application download analysis unit. It does not detect data flow behavior and data flow characteristics, and does not identify services from the network transport layer to the application layer. Therefore, it can also be regarded as a coarse-grained combination analysis method.

Images