Training method and device for active risk real-time identification model

A technology for identifying models and risks, applied in the field of data processing, can solve problems such as difficult to meet the timeliness requirements of active risks and high costs, and achieve the effect of reducing manual labor and improving generation efficiency

Active Publication Date: 2018-12-18
ADVANCED NEW TECH CO LTD
View PDF10 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since there are basically no reports, complaints, and other feedback on active risk behaviors, when using machine learning models for active r

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Training method and device for active risk real-time identification model
  • Training method and device for active risk real-time identification model
  • Training method and device for active risk real-time identification model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The embodiment of this specification proposes a new training method for active risk real-time identification model, which uses the offline anomaly detection model to filter out the marked historical business behavior set from the historical business behavior, and applies the marked historical business behavior set to the The semi-supervised learning method is used to generate the training sample set, and the generated training sample set is used to train the active risk real-time identification model, so that the training sample set can be automatically generated, which greatly reduces the workload of manual marking and improves the training sample. The generation efficiency provides good support for preventing rapidly changing active risks.

[0020] The embodiments of this specification can run on any device with computing and storage capabilities, such as mobile phones, tablet computers, PCs (Personal Computers, personal computers), notebooks, servers and other devices...

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

PUM

No PUM Login to view more

Abstract

The invention provides a training method for an active risk real-time identification model, comprising the steps of: marking a history business behavior according to an output of at least one offlineanomaly detection model, and generating a history business behavior set with the marking, wherein the input of the offline anomaly detection model includes the offline characteristics of the historical business behavior, and the output is the possibility that the historical business behavior belongs to the anomaly. Based on the tagged set of historical business behaviors, the tagged set of training samples is generated by semi-supervised learning. The real-time identification model of active risk is trained by training sample set with marker. The input of the active risk identification real-time model includes the real-time characteristics of the real-time business behavior, and the output has the possibility of active risk for the real-time business behavior.

Description

technical field [0001] This specification relates to the technical field of data processing, and in particular to a training method and device for a real-time active risk identification model. Background technique [0002] The vigorous development of the Internet has brought great convenience to people's lives, but at the same time, the anonymous, open, and fast characteristics of the Internet also provide favorable conditions for the implementation of various illegal acts. Among them, different from passive victims such as misappropriation and fraud, active risk behaviors are initiated by users who are account owners, usually using concealed methods to cover up illegal purposes, such as obtaining illegal benefits from marketing funds through false transactions , or organize participation in online gambling through App (application program), etc. [0003] With the rapid development of Internet finance, the harm caused by active risks is also increasing, and the real-time id...

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

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06Q40/04
CPCG06Q40/04G06F18/2155
Inventor 程羽刘腾飞夏威陆毅成郝嘉然刘晓韵陆逊陈弢
Owner ADVANCED NEW TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap