Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Negative sample adversarial generation method with noise learning

A negative sample and noise technology, applied in the field of electronic transaction negative sample generation, can solve the problem of adding semantic information to input noise, achieve good experimental results, improve capture ability, and improve the quality of data generation

Active Publication Date: 2020-07-17
DONGHUA UNIV
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The problem to be solved by the present invention is: in the generator confrontation network, the input of the generator is a noise vector subject to Gaussian distribution, and no semantic information is added to the input noise, which brings certain disadvantages to the training of the generator

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
  • Negative sample adversarial generation method with noise learning
  • Negative sample adversarial generation method with noise learning
  • Negative sample adversarial generation method with noise learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] Below in conjunction with specific embodiment, further illustrate the present invention. It should be understood that these examples are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the teachings of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the appended claims of the present application.

[0057] A method for generating an adversarial example based on noise learning that the present invention involves mainly has the following three parts:

[0058] (1) Basic framework of the model

[0059] The basic framework of the system is an autoencoder combined with a structure that generates an adversarial network. The specific network structure is as follows: figure 2 shown. The structure is composed of a generative con...

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 relates to a data generation method based on an automatic encoder network and a generative adversarial network. The data generation method provided by the invention can effectively solvethe problem that an anti-fraud model is difficult to construct due to sample imbalance in electronic transaction. The sample characterization capability of an automatic encoder is used; an input sample code is combined with random noise to serve as generator input; guidance information is added to prior noise, the coded noise can fairly allocate the probability of generation of each sample, the capture capability of the generation model for edge distribution data is effectively improved, and the model provides a new technical support scheme for solving the problem of fraudulent sample deficiency and has certain practical value.

Description

technical field [0001] The invention relates to a method for generating negative samples of electronic transactions, which belongs to the field of information technology. Background technique [0002] With the rapid development of modern science and technology, Internet finance has become the hottest topic at present. Internet finance is closely related to people's daily life, and has become the mainstream direction of industry development. Statistics show that in 2016, 3687.24 trillion yuan of non-cash transactions were completed; in 2017, a total of 3759.94 trillion yuan of non-cash transactions were completed, of which the scale of mobile payment transactions was nearly 150 trillion yuan, ranking first in the world. As of June 2019, the number of online payment users in my country reached 633 million, an increase of 32.65 million from the end of 2018, accounting for 74.1% of the total Internet users. With the rapid development of finance, transaction fraud cases in vari...

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): G06N3/04G06N3/08G06K9/62
CPCG06N3/084G06N3/045G06F18/214G06F18/241Y02T10/40
Inventor 章昭辉蒋昌俊王鹏伟杨丽俊
Owner DONGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com