Transaction volume real-time monitoring method and system

A technology for real-time monitoring and transaction volume, applied in the field of big data processing

Pending Publication Date: 2021-04-13
AGRICULTURAL BANK OF CHINA
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These online products or businesses that have been attacked or exploited will experience obviously abnormal transaction volume fluctuations i

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
  • Transaction volume real-time monitoring method and system
  • Transaction volume real-time monitoring method and system
  • Transaction volume real-time monitoring method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] For reference and clarity, the technical terms used below are summarized as follows:

[0040] Stream Computing: A computing framework for stream data that can perform stateful or stateless calculations on unbounded and bounded data streams in real time. Common stream computing engines include Flink, Storm, Spark Streaming, etc.;

[0041] LSTM: A time series prediction method based on RNN, which can predict future data based on past arrays, and is suitable for time series with obvious cycles in autocorrelation.

[0042] With the advent of the era of big data and the rise of artificial intelligence, the application scenarios of flow computing and machine learning have become more and more extensive and diverse. Among them, flow computing technology, taking Flink as an example, is widely used because it supports high throughput, low latency, and high performance, and can process and display real-time data at memory speed and at any scale; and the rich algorithms of machin...

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 transaction volume real-time monitoring method and system. Statistics can be performed on the transaction volume in real time, the future transaction volume is predicted to obtain the transaction volume prediction value, then deviation degree calculation is performed on the real transaction volume and the transaction volume prediction value at the same moment, and when deviation exceeds the preset value, real-time early warning is performed; operators can conveniently find abnormities in time and carry out emergency disposal, and huge economic losses are avoided. Moreover, training of the machine learning model and the prediction of the transaction volume are operated on production at the same time; on one hand, a training platform periodically acquires data in a database to train and update a machine learning model, and publishes the trained machine learning model and model parameters to a stream computing platform; and on the other hand, the flow calculation platform periodically loads the latest machine learning model and model parameters to predict the real-time transaction volume. The method is advantaged in that the the machine learning model can be quickly iterated, and adaptation to actual changes of services and transactions is quicker.

Description

technical field [0001] The invention relates to the technical field of big data processing, in particular to a method and system for real-time monitoring of transaction volume. Background technique [0002] With the continuous development of online products and businesses, some malicious transactions (such as attacks, "sweeping wool") followed, and there is a trend of intensification. These online products or businesses that have been attacked or exploited will experience obviously abnormal transaction volume fluctuations in a short period of time when they are subjected to abnormal applications; Behavior buys more time and can also recover huge economic losses. Contents of the invention [0003] In view of this, the embodiments of the present invention provide a method and system for real-time monitoring of trading volume, so as to quickly detect abnormal trading volume fluctuations. [0004] In order to achieve the above purpose, embodiments of the present invention pr...

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): G06Q30/02G06Q40/04G06N20/00
CPCG06Q30/0202G06Q40/04G06N20/00
Inventor 刘晓龙赵焕芳侯鑫磊刘云飞牛佩云马晓维
Owner AGRICULTURAL BANK OF CHINA
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