A method and device for detecting outliers
A machine detection and outlier technology, applied in instruments, unstructured text data retrieval, data processing applications, etc., can solve problems such as a large number of resources, alarm storms, changes, etc., and achieve the effect of convenient expansion and optimization of algorithm effects
Active Publication Date: 2022-08-02
北京必示科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At this time, if all the indicators (business indicators, performance indicators, etc.) of each machine are monitored independently, it will not only require a lot of resources, but also easily cause problems such as alarm storms.
And due to the characteristics of timing anomaly detection itself (need to refer to history or manual labeling), it cannot deal with problems such as changes, continuous abnormality of access data, abnormality in baseband, etc.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0062] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
[0063] There are two common approaches to existing outlier machine analysis. One is to analyze common methods for outliers: n-sigma, box plot, Isolation-Forest, XGBoost, etc.; the other is to judge based on similarity of indicators and use clustering to judge outliers. However, due to the variety of indicators, the sha...
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
Login to View More Abstract
The present invention provides an outlier machine detection method and device. The technical solution of the present invention includes detection modules and algorithms such as deletion detection, mutation detection, timing similarity judgment, distribution similarity judgment, feature similarity judgment, and shape similarity judgment. Each detection module analyzes a large amount of financial data and makes targeted optimizations. At the same time, it also supports the free adjustment of module parameters, execution order and module functions for different indicators, which can effectively detect outlier scenarios such as missing outliers, waterline outliers, periodic outliers, fluctuation outliers, and shape outliers.
Description
technical field [0001] The present application relates to the technical field of financial operation and maintenance monitoring, and in particular, to a method and device for detecting outliers. Background technique [0002] In the field of financial operation and maintenance monitoring, various indicators are collected through various monitoring and collection tools such as Tivoli, Zabbix, APM, network packet capture, and application buried point monitoring to monitor the health of machines. These indicators are usually stored as time series data (including collection time and indicator values). Traditional monitoring solutions generally monitor through fixed thresholds and alarm rules. For example, "CPU usage is higher than 90% for 3 minutes" and an alarm is generated, indicating that At this time, the monitoring object may be abnormal, and the administrator needs to check. However, due to the increasing complexity of the current financial Internet business, different tra...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/33G06F16/36G06F16/35G06Q10/06
CPCG06F16/3331G06F16/367G06F16/35G06Q10/06393
Inventor 程博曹立隋楷心刘大鹏
Owner 北京必示科技有限公司