KPI and multi-dimension network data cleaning method based on scene

A technology of network data and dimensional data, applied in the field of data cleaning, can solve the problems of high data complexity and inability to dig deep into data, and achieve the effect of solving high complexity, facilitating correlation analysis and effective cleaning

Active Publication Date: 2018-09-21
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to optimize network data, propose a scene-based KPI and multi-dimensional network data cleaning method, realize effective cleaning of data, and solve the technical problem that the data cannot be deeply excavated due to the high complexity of the data

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
  • KPI and multi-dimension network data cleaning method based on scene
  • KPI and multi-dimension network data cleaning method based on scene
  • KPI and multi-dimension network data cleaning method based on scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The technical solutions of the present invention will be further elaborated below according to the drawings and in conjunction with the embodiments.

[0029] The present invention adopts the following technical solution, a scene-based KPI and multi-dimensional network data cleaning method, the experimental data comes from some data of some regions of a certain operator, and the data are all given in the form of Excel. The present invention uses Python to realize, figure 1 It is a flow chart of the scene-based KPI and multi-dimensional network data cleaning method. The specific steps are as follows:

[0030] 1) Divide the collected raw data into the basic dimension data of the community and the list of problematic communities. Among them, the basic dimension data of the community is the directly collected community data, that is, the data that has not been judged by the KPI index threshold; the problematic community list is a certain item The cell data where the KPI is o...

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 KPI and multi-dimension network data cleaning method based on a scene, which comprises the following steps of: firstly, importing collected data into a data structure; standardizing the imported data format, dividing the resource data according to the scene, merging the resource data of the same scene to obtain resource sub data, and detecting and processing the conflictgenerated by a data value; correlating the data of a plurality of data sources or files and judging and processing data redundancy and mode mismatch; processing the data which cannot be mined directly; checking the missing rate of each attribute, determining a processing mode according to the missing rate, including discarding and using a K-NN regression method; backing up the original data in thedata storage module and storing the cleaned data; according to the method, effective cleaning of data is realized, and the technical problem that data cannot be deeply excavated due to the high degree of complexity of the data is solved.

Description

technical field [0001] The invention belongs to the field of data cleaning, and in particular relates to a scenario-based KPI and multi-dimensional network data cleaning method. Background technique [0002] Some Key Performance Indicators (KPIs) need to be paid attention to in mobile communication network operation management, such as call drop rate, call loss, etc. In addition to routine maintenance, operators hope to grasp the factors that affect KPIs and obtain the relationship between KPIs and the network. The correlation between them facilitates the distribution and guarantee of network optimization tasks in the later stage. [0003] Before in-depth analysis and mining of the degree of association between KPIs and the network, it is necessary to effectively clean the data and reduce the complexity of the data. Contents of the invention [0004] The purpose of the present invention is to optimize network data, propose a scene-based KPI and multi-dimensional network d...

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): G06F17/30
Inventor 程崇虎陆怡琪朱颖田梦倩范山岗杨洁熊健桂冠
Owner NANJING UNIV OF POSTS & TELECOMM
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