Data anomaly detection method and device and electronic equipment

A detection method and anomaly detection technology, applied in the field of data processing, can solve the problems of low detection accuracy of anomaly detection system, achieve the effect of solving low detection accuracy, real-time discovery, and improving detection rate

Pending Publication Date: 2022-02-08
INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a data anomaly detection method, its device, and electronic equipment,

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
  • Data anomaly detection method and device and electronic equipment
  • Data anomaly detection method and device and electronic equipment
  • Data anomaly detection method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0036] Example one

[0037] According to an embodiment of the present invention, a data abnormality detecting method embodiment is provided, and it is to be noted that the steps shown in the flowcharts shown in the drawings can be performed in a computer system such as a set of computer executable instructions, and though The logical order is shown in the flowchart, but in some cases, the steps shown or described may be performed in a description thereof.

[0038] figure 1 It is a flow chart of an optional data abnormality detection method according to an embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:

[0039] Step S102, receive the product running data.

[0040] Step S104, sends the product to the target park, where the target park has an abnormal detection system, and there is a data detection model in the abnormal detection system. The data detection model is greater than the probability of the loss during model trainin...

Example Embodiment

[0076] Example 2

[0077] figure 2 AI is a schematic diagram warning system to improve the accuracy of the method of an alternative embodiment of the present invention, comprising the steps of:

[0078] Step 1: Check well trained model, historical data sample for the base stock production model training obtain an initial model, and the model is built into production anomaly detection system (wherein, the system can be divided into different abnormality detection zone (e.g., a, B Zone), different park can perform different functions, the system can be disposed bis-active zone, to reduce the system pressure single zone).

[0079] Step 2: production of real-time data corresponding to the access zone, through the anomaly detection system, an initial model of the data is detected, based on a result of the training model output initially determine whether the data abnormality, and the sample data into database.

[0080] Step 3: alarm detection, anomaly alarm system in real time whether...

Example Embodiment

[0096] Third Embodiment

[0097] A data embodiment of the present embodiment provides the abnormality detection device comprises a plurality of unit embodiments, each embodiment corresponding to the embodiment means a step in the various embodiments.

[0098] Figure 4 Is a schematic view of an alternative embodiment of the present invention is a data abnormality detecting means, such as Figure 4 Shown, the detection means may comprise: a receiving unit 40, a first transmission unit 42, the analysis unit 44, second sending unit 46, wherein,

[0099] A receiving unit 40 for receiving the product is run transactions;

[0100] A first transmission unit 42, the product is run for data sent to the target zone, wherein the target park access system abnormality detection, the abnormality detection system running model data detection, data detection resulting in a loss of value of the model in the model training process rate is greater than a threshold probability of sample data mining, a...

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 discloses a data anomaly detection method, a data anomaly detection device and electronic equipment. The detection method comprises the steps that product operation data is received and sent to a target park, an anomaly detection system is connected to the target park, and a data detection model runs in the anomaly detection system; the data detection model mines sample data causing a loss value rate to be greater than a preset probability threshold value in a model training process and retrains the sample data, the loss value rate is used for indicating a ratio of a sample data volume of a model classification error to a total data volume, an anomaly detection system is adopted to analyze product operation data; a detection result is acquired and abnormal data is sent in the detection result to an alarm system. According to the invention, the technical problem of low detection accuracy of an anomaly detection system in the prior art is solved.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular, to a data anomaly detection method and device thereof, and electronic equipment. Background technique [0002] In the financial technology industry, most companies / companies have begun to build alarm systems based on artificial intelligence algorithms to identify abnormal data so that relevant personnel can quickly process these data. In related technologies, by introducing a mature artificial intelligence algorithm, a model trained based on historical data is designed to detect abnormal data in production and then issue an alarm. However, the existing model is obtained through training and iteration of the offline data of the previous cycle. With the rapid development of the financial business field, there are many difficult positive and negative samples in various training samples, which leads to the current model The actual detection rate is reduced, which reduc...

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): G06F16/2458
CPCG06F16/2465G06F16/2462
Inventor 张为欢王培君管虹翔梁广会
Owner INDUSTRIAL AND COMMERCIAL 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