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

Method and device for risk identification

A risk identification and risk technology, applied in the construction of characteristic fields in risk identification, can solve the problems of inefficiency of risk events, low risk identification accuracy, and consumption of system computing resources.

Pending Publication Date: 2022-05-27
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current method of using models to identify risk events is relatively inefficient, resulting in low accuracy of risk identification and greatly consuming system computing resources

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
  • Method and device for risk identification
  • Method and device for risk identification
  • Method and device for risk identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0112] In order to make the above objects, features and advantages of the present invention more clearly understood, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0113] Numerous specific details are set forth in the following description to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways than those described herein, and thus the present invention is not limited by the specific embodiments disclosed below.

[0114] In risk identification, each sample (training sample or to-be-predicted sample) needs to be converted into a feature vector to input into the model for training and prediction. For example, a sample may correspond to a transaction, and the sample may include multiple features, such as IP addresses used by both parties to the transaction, the user's province, city, and historical transaction times.

[0115] Eac...

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 method and a device for risk identification. A method for risk identification includes: acquiring a sample set, each sample in the sample set including a plurality of features; for each category feature in the plurality of features, determining the category number of the category feature in the sample set; comparing the category number of the category feature with a category number threshold value; if the category number of the category features is smaller than or equal to the category number threshold value, encoding the category features in a random encoding mode to generate a feature mapping set for the category features; and if the category number of the category features is greater than the category number threshold, encoding the category features by using a statistical encoding mode to generate a feature mapping set for the category features.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular, to a method and apparatus for constructing features in risk identification. Background technique [0002] With the development of Internet business, various risk events (for example, payment account theft, etc.) have appeared. In order to maintain the stability of the business platform, it is necessary to monitor the business (for example, transactions) and identify the illegal business in time. [0003] With the rapid development of machine learning technology, the identification of risk events can be achieved using models for risk identification. However, the current method of identifying risk events by using a model is relatively inefficient, which leads to low accuracy of risk identification and greatly consumes computing resources of the system. [0004] Therefore, there is an urgent need for a solution that can improve the recognition effect of machine l...

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 Applications(China)
IPC IPC(8): G06Q10/06G06Q30/02G06K9/62G06N20/00
CPCG06Q10/0635G06Q30/0201G06N20/00G06F18/214
Inventor 张长浩傅欣艺王维强
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD