Construction method and construction system of app application feature code library

Abstract

The invention discloses a construction method of an App application feature code library. The protocol analysis is performed on each data packet of an apk file, the preset key protocol fields are extracted, and the extracted key protocol fields are generated with the App application by using a predefined second rule. Each corresponding feature code rule, and then identify the feature code rule that satisfies the preset conditions as the feature code of the corresponding App application, and add it to the existing feature code library. The present invention can process a large number of App applications at the same time, has a unified feature code identification standard, and has high accuracy, which greatly improves the work efficiency. According to the preset time, the machine learning training is performed on the feature code library according to the predefined third rule, which can delete the wrong rules or invalid rules, ensure the automatic and accurate update of the feature code library, greatly reduce the workload of manual intervention, and can be very good. It is applied in the field of application traffic identification with high accuracy. The invention also discloses a construction system of an App application feature code library.

Description

technical field [0001] The invention belongs to the technical field of data traffic analysis, and in particular relates to a construction method and a construction system of an App application feature code library. Background technique [0002] With the development of the mobile Internet, it is very important to identify applications (commonly known as Apps) at the entrance and exit of network traffic, whether it is network security products, service quality analysis products, user behavior analysis products, traffic control products or professional traffic Analysis engine, accurate identification of application traffic can not only gain insight into the operation of the entire network, accurately identify the usage behavior of each user, but also accurately control user behavior according to specific needs. [0003] The accuracy of application traffic identification is very dependent on the signature library. The so-called feature code refers to a single or combined condit...

AI Technical Summary

Problems solved by technology

This method basically depends on manual experience. For the same App application, different analysts may sum up different feature codes, which is not accurate and inefficient.

Especially now that the content of the Internet is vast, new App applications emerge in endlessly, version updates and content iterations come one after another, making the update of the signature database very labor-intensive, and it is difficult to achieve timely and accurate

Images