Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

MR coverage influence factor determining method based on random forest

A technology of influencing factors and random forest, applied in the field of big data processing and machine learning, can solve problems such as insufficient accuracy, doubtful effectiveness, and inability to judge the accuracy rate, and achieve the effect of strong stability and high precision

Inactive Publication Date: 2018-12-25
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are many methods for calculating the correlation between MR coverage and various dimensions, but many of them calculate the linear correlation between the two, and the accuracy is not enough; some methods can calculate the nonlinear correlation, but their accuracy cannot Judgment, therefore, in the process of application, its validity remains in doubt

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
  • MR coverage influence factor determining method based on random forest
  • MR coverage influence factor determining method based on random forest
  • MR coverage influence factor determining method based on random forest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Below in conjunction with accompanying drawing of description, the present invention will be further described.

[0044] The present invention provides a random forest-based MR coverage factor determination method, such as figure 1 and figure 2 shown, including the following steps:

[0045] 1) Select several relevant dimensions that affect MR coverage, as shown in Table 1.

[0046] Several relevant dimensions that affect MR coverage include working frequency band, number of carrier frequencies, coverage type, longitude, latitude, maximum transmit power, number of weak coverage sampling points, total number of sampling points, proportion of weak coverage sampling points, and channel number of the center carrier frequency , Whether it is an uplink interference cell, whether it is an uplink weak coverage cell, whether it is an over-coverage cell, station height, cell individual offset, frequency band indication, electronic downtilt, mechanical downtilt, azimuth, antenna...

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 method for judging MR coverage influencing factors based on random forest, which comprises the following steps: selecting a plurality of correlation dimensions influencing MRcoverage; cleaning the dimension data to obtain the related dimension after cleaning; extracting dimension data as training sample and remaining dimension data as test sample; a random forest model being trained according to the training sample, which is characterized by the correlation dimension after washing; inputting the test sample into the stochastic forest model to obtain the output accuracy; adjusting the parameters of the stochastic forest model until the output accuracy is greater than the set threshold, and then using the stochastic forest model as the MR coverage influencing factors decision model; calculating the degree of influence of each correlation dimension affecting MR coverage; according to the degree of influence, several correlative dimensions which influence MR coverage being sorted. MR coverage factors were used to determine the factors affecting MR coverage, and the root causes of MR coverage deterioration were clearly identified. The method has high accuracyand stability.

Description

technical field [0001] The invention relates to a method for judging influencing factors, in particular to a random forest-based method for judging influencing factors of MR coverage, and belongs to the technical fields of big data processing and machine learning. Background technique [0002] MR coverage is some key KPIs (Key Performance Indicators) that need to be paid attention to in the operation and management of mobile communication networks. In addition to routine maintenance, operators hope to know the factors that affect MR coverage, and obtain the relationship between MR coverage and the network. The association of network optimization tasks is convenient for later allocation and guarantee; therefore, it is necessary to dig out the factors that affect MR coverage from the network operation process, that is, the relevant dimensions. [0003] At present, there are many methods for calculating the correlation between MR coverage and various dimensions, but many of the...

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): G06Q10/06G06Q50/30G06N99/00
CPCG06Q10/06393G06Q50/40
Inventor 范山岗田梦倩陆怡琪朱颖熊健杨洁桂冠
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
Eureka Blog
Learn More
PatSnap group products