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

Data exception detection method and device

A technology of data anomaly and detection method, which is applied in the field of computer network and can solve the problems of difficult setting of judgment threshold and inaccurate prediction value.

Active Publication Date: 2019-09-06
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a data anomaly detection method and detection device in order to overcome the problems of inaccurate predicted values ​​and difficult setting of data anomaly judgment thresholds in the prior art

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 exception detection method and device
  • Data exception detection method and device
  • Data exception detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0037] figure 1 is a flow chart of the data anomaly detection method provided by the embodiment of the present invention, such as figure 1 As shown, the following steps may be included:

[0038] S100. Mining user behavior patterns.

[0039] Preferably, by acquiring the historical data for the user, and according to the preset cycle, several user behavior patterns with the preset cycle as the unit are mined from the historical data.

[0040] Specifically, due to the influence of weekends, statutory holidays, holidays, etc., the detected user data is based on the data of the previous day, the same day last week, the same day last month, or the same day last yea...

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 exception detection method and device. The data exception detection method comprises the steps: obtaining the historical data for a user, and mining a plurality of userbehavior modes with a preset period as a unit from the historical data according to a preset period; determining a user behavior mode corresponding to the current period according to the detected datain the set time period in the current period, and predicting the to-be-detected data of the current period based on the user behavior mode to obtain predicted data; and according to the prediction data, using a pre-constructed detection model to carry out abnormal detection on the detected data. According to the technical scheme, the data is predicted based on the user behavior mode mined according to the historical data of the user, so that a reasonable predicted value can be obtained; and abnormity judgment is carried out through the detection model, so that the setting process of the judgment threshold value is avoided, and then the problem that the detection result is inaccurate due to inaccurate setting of the judgment threshold value is avoided.

Description

technical field [0001] The invention relates to the technical field of computer networks, in particular to a data anomaly detection method and detection device. Background technique [0002] In recent years, time-series data prediction and anomaly detection have received more and more attention. Internet companies at home and abroad have begun to use anomaly detection technology to monitor their operation and maintenance and related time-series data in order to detect abnormal events in the first time, thereby Reduce losses caused by abnormal events. For the curves of some core data, such as the revenue data curve of core products, the abnormal situation of slow decline in the data also needs to be discovered in time and paid close attention to. [0003] However, in the prior art, the year-on-year algorithm is usually used to directly use the data of yesterday or the same day of last week as the predicted value, and compare the detected value with the predicted value to cal...

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): G06F11/34
CPCG06F11/3438G06F11/3452
Inventor 陈云陈宇王博苗贝贝
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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