Method and device of identifying target terminal

Abstract

The invention discloses a method of identifying a target terminal. The method includes the following steps: extracting data from a data source, pre-processing the data according to preset strategies to remove abnormal first data, and keeping normal second data used for obtaining an analysis data set; performing data verification and/or data conversion on the second data and then obtaining an analysis data set; obtaining the analysis data set, and extracting characteristic vectors of users from the analysis data set on the basis of communication characteristics of the users, wherein the characteristic vectors of the users is used for representing the communication characteristics of the users; dividing all the users into first users and second users on the basis of the characteristic vectors of the users, obtaining cluster results corresponding to all the first users on the basis of data of the first users, and taking the cluster results as first cluster results; performing clustering on the basis of the characteristic vectors of the second users and the first cluster results, obtaining cluster results corresponding to all the users, and taking the cluster results as second clusterresults; and identifying a target terminal on the basis of the second cluster results. The invention also discloses a device of identifying a target terminal.

Description

technical field [0001] The present invention relates to business support technology, in particular to a method and device for identifying a target terminal. Background technique [0002] In the mobile Internet era, the second curve is the key to driving revenue, and the terminal is an important carrier of the second curve. At this stage, the mobile company's overall terminal sales mainly rely on social channels for sales. How to effectively monitor and manage social channel sales terminals and improve the efficiency of mobile company remuneration for user development quality is one of the main problems currently facing mobile companies. The method is to conduct cluster analysis on the communication behavior between users and sales terminals, dig out suspected illegal sales terminals, and prevent and control the market order of mobile company terminal sales and the risk of loss of remuneration. [0003] In the prior art, the K-means similarity clustering algorithm is used fo...

AI Technical Summary

Problems solved by technology

[0006] 1. The addition of new network users and new index dimensions affect the accuracy of clustering

Since new network users show little communication characteristic information, the newly added statistical dimension will also affect user characteristic information, which will cause cold start phenomenon

The K-means similarity clustering algorithm does not have enough diversity, so that the clustering results will quickly converge to a small-scale set, thus losing the judgment on the association of more user communication feature information and content, and unable to effectively analyze new data. Add users to make comprehensive and accurate clustering, and the newly added statistical dimension will also have an impact on the accuracy of user clustering

[0007] 2. Data sparse problem

When the user's communication behavior, consumption characteristics, business handling and location information are converted into user feature vectors and user correspondence, very few users can cover feature vectors of most dimensions, and a large part of users only show interest in certain dimensions. The eigenvector of the user, a large number of new users make the data sparse problem of the user feature matrix more obvious, and at the same time, the difference in the selection of users also causes great data sparseness

For the problem of data sparsity, using the K-means similarity clustering algorithm based on the binary relationship method cannot achieve a comprehensive and accurate identification of suspected illegal terminals

Images