Visual user classification method, service method, system and device and storage medium

A classification method and user technology, applied in visual data mining, relational database, structured data retrieval, etc., can solve the problem of difficulty in selecting the most relevant dimensions of fraudulent behavior, and achieve the effect of rapid and accurate analysis or evaluation
CN113553369APending Publication Date: 2021-10-26TSINGHUA UNIV
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
TSINGHUA UNIV
Publication Date
2021-10-26

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a visual user classification method, a service method, a system, a device and a storage medium. The method comprises the following steps: obtaining visual data obtained according to input information and user group data of a user group, wherein the input information is used for setting a fraud detection algorithm, algorithm parameters and at least one user behavior feature set for processing user group data. The visual data is used for displaying a distribution view which is formed by reflecting the behavior similarity of the user group based on one or more user behavior characteristics in at least one user behavior characteristic set; the magnitude of the behavior similarity between the users is negatively correlated to the magnitude of the mapping spacing of the users in the distribution view, so as to carry out visual output. According to the scheme provided by the invention, the synchronization of the user on different behaviors can be intuitively and accurately displayed according to the behavior similarity of different user behaviors, and the fraud behavior can be quickly and accurately analyzed or the fraud detection quality can be evaluated.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present application relates to the technical field of graphic display, in particular to a visual user classification method, service method, system, device and storage medium. Background technique

[0002] Many online services today are rife with fraud, such as fake accounts on forums and video sites, and bots on social networks. Fraud conducts malicious activities that damage the commercial value of an online service.

[0003] Correspondingly, online fraud detection technology is needed to detect fraud problems in online services. Over the years, researchers have proposed many fraud detection algorithms based on fraudulent behaviors, especially unsupervised learning methods, and the detection of fraudulent behaviors is based on the log records of users' online behaviors. However, designing and evaluating these algorithms is challenging: 1) log records contain many dimensions describing user behavior, and it is difficult to select the most releva...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More