Multi-point combination monitoring analysis method and system based on streaming data

An analysis method and streaming data technology, which are applied in the field of multi-point combined monitoring and analysis methods and systems based on streaming data, can solve the problems of monitoring system data processing capability and lack of means for dimensional analysis, and inability to identify independently, so as to improve background data operation capabilities. , Improve the ability of data processing and analysis, the effect of good scalability

Active Publication Date: 2021-06-18
国家电网有限公司客户服务中心 +2
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the promotion of online APP and the surge in the number of users, the monitoring system lacks means in terms of data processing capabilities and dimensional analysis, and cannot independently identify and process abnormal monitoring point data by itself.

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
  • Multi-point combination monitoring analysis method and system based on streaming data
  • Multi-point combination monitoring analysis method and system based on streaming data
  • Multi-point combination monitoring analysis method and system based on streaming data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The technical solutions of the present invention will be further described below in conjunction with the examples.

[0038] Such as Figure 3-Figure 4 As shown, the business operation data real-time monitoring system is designed and developed using the J2EE framework, the monitoring and early warning algorithm is implemented in Python language, and the system uses the Jython package to call the Python .py file. The acquisition of monitoring information is realized by Java programs. The abnormal probability of monitoring indicators and personnel is calculated by Python, and the calculation results are returned to the Java program. The Java program compares the probability with the threshold, and then gives the early warning information.

[0039] The multi-point combined monitoring and analysis method based on stream data of the present invention comprises the following steps:

[0040] (1) Single-point monitoring and early warning results obtained by using the naive Baye...

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 multi-point combined monitoring analysis method and system based on streaming data. The method comprises the following steps: obtaining a single-point monitoring early warning result by using a naive Bayesian model; taking a single-point monitoring and early warning result as a known current state, carrying out the iteration on a Metropolis-Hasting algorithm, and obtaining the service system pause probability calculated through multi-level combined monitoring and early warning; determining whether early warning is carried out or not by comparing the core service abnormal probability calculated through multi-level combined monitoring and early warning obtained through calculation with a threshold value set in a service monitoring system, and providing a multi-point combined monitoring and analyzing system based on streaming data. According to the method and the system, a data acquisition link is reduced, the calculation performance of the monitoring data is improved, the calculation time is shortened, the pressure on an oracle database is reduced, the real-time requirement of data statistical analysis is met, and powerful support is provided for a data operation specialist to formulate personalized analysis scenes of various scenes.

Description

technical field [0001] The invention relates to a multi-point combined monitoring and analysis method and system, in particular to a flow data-based multi-point combined monitoring and analysis method and system. Background technique [0002] At present, the real-time monitoring of online business operation mainly conducts comprehensive monitoring and analysis from the two modules of APP business operation and online customer service on-site management and control. The monitoring scenarios of each business module are designed according to different monitoring and analysis requirements. With the continuous promotion and deepening of the business, the monitoring scenarios cover The number of monitoring points continues to increase, and the existing monitoring operation system cannot fully support the expansion of the newly added monitoring points, and the degree of completion of automatic identification and early warning and visual display is not mature enough, and the effect o...

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): G06F11/07G06N7/00G06F16/2455G06F16/25G06F16/28G06F9/54
CPCG06F11/0754G06F16/24568G06F16/24552G06F16/25G06F16/284G06F9/546G06F2201/80G06F2209/548G06N7/01Y02P90/02
Inventor 张才俊江帆樊涛余锦河张波戴振龙程飞飞朱红林郭源焦子荣
Owner 国家电网有限公司客户服务中心
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