Unlock instant, AI-driven research and patent intelligence for your innovation.

Risk control model training method, risk identification method and hardware for personal information protection

An information protection and risk control technology, applied in character and pattern recognition, digital data protection, computer parts, etc., can solve problems such as inability to give accurate understanding, and achieve the effect of protecting privacy

Active Publication Date: 2021-05-07
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is impossible to give an accurate understanding of some deeper information, such as the predictions brought about by changes in user portraits.

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
  • Risk control model training method, risk identification method and hardware for personal information protection
  • Risk control model training method, risk identification method and hardware for personal information protection
  • Risk control model training method, risk identification method and hardware for personal information protection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to make those skilled in the art better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described The embodiments are only some of the embodiments of the present specification, but not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

[0046] As mentioned above, at this stage, the training of the risk control model mainly relies on the user portrait features in the historical data. The risk analysis dimension of this method is relatively simple, and generally only some relatively simple risk-related user characteristics are excavated. However, with the evolution o...

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 embodiments of this specification provide a risk control model training method, risk identification method, and hardware for personal information protection. The training method includes: obtaining the combination of user portrait vectors of the sample users in the sample user set at the first time node and the second time period, the combination of the user portrait vectors of the sample users at the first time node and the user portrait vector at the second time node. Combinations have the same user persona dimension. A difference feature between the user portrait vector combination at the first time node and the user portrait vector combination at the second time node of the sample user is determined. The difference characteristics corresponding to the base sample users and the risk classification labels corresponding to the second time node are used to train the risk control model. The first time node is earlier than the second time node, and there is at least one sample user in the sample user set at the second time node. The risk level indicated by the risk classification label corresponding to the node is higher than the risk level indicated by the risk classification label corresponding to the node at the first time.

Description

technical field [0001] This document relates to the field of artificial intelligence technology, especially to a risk control model training method, risk identification method and hardware for personal information protection. Background technique [0002] Deep learning models have been used more and more widely in the field of risk control due to their ability to mechanize information processing. At this stage, the training of risk control models mainly relies on user portraits in historical data. The risk analysis dimension of this method is relatively simple, and generally only some relatively simple risk-related user portraits are excavated. However, for some deeper information, such as the foreshadowing of changes in user portraits, it is impossible to give an accurate understanding. [0003] In view of this, on the basis of protecting the privacy of user portraits, how to explain risks through the evolution of user portraits over time is a technical problem that needs...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F21/62G06Q10/06G06K9/62
CPCG06F21/6245G06Q10/0635G06F18/24G06F18/214
Inventor 宋博文朱勇椿
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD