User data classification method and device and storage medium

Abstract

The embodiment of the invention provides a user data classification method and device and a storage medium, and belongs to the field of science and technology finance, and the method comprises the steps: 1, obtaining a sample data set; 2, multi-dimensional vectors in the sample data set are divided into a plurality of target clusters of a data classification model; step 3, determining target optimization parameters corresponding to the plurality of target clusters; step 4, according to the target optimization parameters, removing invalid clusters in the plurality of target clusters and similar features among the plurality of target clusters; 5, circularly executing the step 3 and the step 4 to train the data classification model until the difference value between the target optimization parameter determined by the current cycle and the target optimization parameter determined by the last cycle is smaller than the variable quantity threshold value; and 6, determining the type of the user data to be queried by using the trained data classification model. Through the mode, the number of types of the user data can be automatically optimized, so that the classification efficiency of the user data is improved.

Description

technical field [0001] The present disclosure relates to the field of science and technology finance, and in particular to a user data classification method, device and storage medium. Background technique [0002] With the development of computer technology, more and more technologies are applied in the financial field. The traditional financial industry is gradually transforming into financial technology (Finteh). The classification technology of user data is no exception. However, due to the security and real-time nature of the financial industry requirements, but also put forward higher requirements for technology. [0003] In related technologies, a K-means clustering (k-means) algorithm can be used to analyze the value of user data. The k-means algorithm model can divide user data into K clusters, and the centroid of each cluster is calculated from the average value of user data in the cluster. The choice of K is set by the user based on experience, so as to ensure t...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present disclosure provide a user data classification method, device, and storage medium to solve the problem of low efficiency of user data classification in the prior art

Images