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

Intelligent operation and maintenance anomaly detection model training method and system

A technology of anomaly detection and training method, applied in the field of machine learning, can solve the problem of ineffective detection of anomalies, and achieve the effect of detecting anomalies

Pending Publication Date: 2022-04-29
北京中软国际信息技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Therefore, the training method and system of an intelligent operation and maintenance anomaly detection model provided by the present invention overcomes the defect that the anomaly cannot be effectively detected 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
  • Intelligent operation and maintenance anomaly detection model training method and system
  • Intelligent operation and maintenance anomaly detection model training method and system
  • Intelligent operation and maintenance anomaly detection model training method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A training method for an intelligent operation and maintenance anomaly detection model provided by an embodiment of the present invention is a single-valued anomaly detection method, such as figure 1 shown, including the following steps:

[0039] Step S1: Collect KPI data and convert the raw data into a time series with preset intervals.

[0040] In the embodiment of the present invention, KPI data is collected, and the raw data is processed into a time series with preset intervals. The preset intervals are not limited here, and responses are selected according to actual conditions.

[0041] Step S2: Based on the Hawkes process, use the time series of KPI data to establish a forecasting model.

[0042] In the embodiment of the present invention, the Hawkes process is a point process, which is a special linear self-excited model. Using the Hawkes process, past events will affect the probability of future events. The incentives of past events are positive, Additive and ...

Embodiment 2

[0055] An embodiment of the present invention provides a training system for an intelligent operation and maintenance abnormality detection model, such as figure 2 shown, including:

[0056] The data preprocessing module 1 is used to collect KPI data and convert the raw data into a time series with preset intervals; this module executes the method described in step S1 in Embodiment 1, which will not be repeated here.

[0057] The forecasting model building module 2 is used to build a forecasting model based on the Hawkes process by using the time series of KPI data; this module executes the method described in step S2 in Embodiment 1, which will not be repeated here.

[0058] The parameter initialization module 3 is used to initialize the parameters of the conditional strength function of the prediction model, and solve the parameters of the model through a preset algorithm; this module executes the method described in step S3 in Embodiment 1, which will not be repeated here....

Embodiment 3

[0062] An embodiment of the present invention provides a terminal, such as image 3 As shown, it includes: at least one processor 401 , such as a CPU (Central Processing Unit, central processing unit), at least one communication interface 403 , memory 404 , and at least one communication bus 402 . Wherein, the communication bus 402 is used to realize connection and communication between these components. Wherein, the communication interface 403 may include a display screen (Display) and a keyboard (Keyboard), and the optional communication interface 403 may also include a standard wired interface and a wireless interface. The memory 404 may be a high-speed RAM memory (Random Access Memory, volatile random access memory), or a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory 404 may also be at least one storage device located away from the aforementioned processor 401 . The processor 401 may execute the training method of the...

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 training method and system for an intelligent operation and maintenance anomaly detection model, and the method comprises the steps: collecting KPI data, and converting the original data into a time sequence at a preset interval; establishing a prediction model by using the time sequence of the KPI data based on the hox process; initializing various parameters of a condition intensity function of the prediction model, and solving various parameters of the model through a preset algorithm; and calculating a loss function based on a preset data set and various parameters of the solved model, and finishing the training of the intelligent operation and maintenance anomaly detection model when the loss function is smaller than a preset numerical value, and according to the intelligent operation and maintenance anomaly detection method and system, each KPI is modeled by using the Horkes model, and the anomaly of intelligent operation and maintenance is effectively detected.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a training method and system for an intelligent operation and maintenance anomaly detection model. Background technique [0002] In the intelligent operation and maintenance system, anomaly detection aims to discover abnormal fluctuations in key performance indicators (Key Performance Indicator, KPI) time series data through algorithms, which is the basis for subsequent alarms, root cause analysis, and automatic processing. In actual scenarios, there are various types of anomalies and KPIs, which bring great challenges to anomaly detection. According to the deviation status of the abnormal point, it is slightly abnormal, trend abnormal, and cycle abnormal. A single point value jump, much larger than the value at the previous moment, is called point anomaly. A series of point value changes that deviate from the historical trend (period) and become trend anomalies (perio...

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): G06K9/62G06Q10/06
CPCG06Q10/0639G06F18/214
Inventor 董旭策
Owner 北京中软国际信息技术有限公司
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