Invention Grant
- Patent Title: Graph structure model training and junk account identification
-
Application No.: US16882084Application Date: 2020-05-22
-
Publication No.: US10917425B2Publication Date: 2021-02-09
- Inventor: Ziqi Liu , Chaochao Chen , Jun Zhou , Xiaolong Li
- Applicant: Advanced New Technologies Co., Ltd.
- Applicant Address: KY Grand Cayman
- Assignee: Advanced New Technologies Co., Ltd.
- Current Assignee: Advanced New Technologies Co., Ltd.
- Current Assignee Address: KY Grand Cayman
- Agency: Seed IP Law Group LLP
- Priority: CN201810209270 20180314
- Main IPC: H04L29/06
- IPC: H04L29/06 ; G06N20/00 ; G06F16/901 ; G06F21/55 ; G06N5/04

Abstract:
Implementations of the present specification disclose graph structure model training and junk account identification methods, apparatuses, and devices. The solution includes: obtaining an account medium network graph, a node in the account medium network graph representing an account and a medium, and at least some edges indicating that a login behavior relationship exists between nodes connected by the edges; obtaining feature data and risk labeling data of the node, the feature data reflecting a login behavior of the corresponding node in a time sequence; and training, based on the account medium network graph, the feature data, and the risk labeling data, a predefined graph structure model for identifying a junk account.
Public/Granted literature
- US20200287926A1 GRAPH STRUCTURE MODEL TRAINING AND JUNK ACCOUNT IDENTIFICATION Public/Granted day:2020-09-10
Information query