APPLICATION IDENTIFICATION METHOD, AND DATA MINING METHOD, DEVICE AND SYSTEM

摘要

Disclosed are a data mining method, device and system. The UBA data mining method comprises: acquiring data to be processed, the data to be processed comprising a plurality of records, wherein each record comprises: application information and far-end triad information in a corresponding relationship; performing clustering processing on a record with the same far-end triad information and application information in the data to be processed, and calculating a service load corresponding to the far-end triad information and application information according to the record with the same far-end triad information and application information in the data to be processed, so as to obtain a clustering result comprising the far-end triad information, the application information and the service load in a corresponding relationship; selecting far-end triad and application information with a high degree of reliability and in a corresponding relationship from the clustering result according to the size or proportion of the service load; and sending to a DPI subsystem the far-end triad and application information with a high degree of reliability and in a corresponding relationship, thereby improving DPI identification performance and application identification rate.