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

Cell scene division method based on machine learning

A machine learning and community technology, applied in machine learning, instruments, computer components, etc., can solve problems such as inability to visualize community data, division of community scenes relying on manual work, and inability to divide community scenes

Active Publication Date: 2019-11-22
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art, and propose a method for dividing community scenes based on machine learning, which solves the problem that the traditional community scene division relies on manual work, cannot accurately divide community scenes, and cannot visualize community data. question

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
  • Cell scene division method based on machine learning
  • Cell scene division method based on machine learning
  • Cell scene division method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0038] A kind of cell scene division method based on machine learning of the present invention, see figure 1 shown, including the following steps:

[0039] Step 1: Collect wireless perception KQI data of each cell 8 busy hours as a data set.

[0040] 8 Busy hour is a term commonly used by communication operators. Communication operators generally choose the wireless perception indicators of the busiest 8 hours of the 24 hours a day to represent the perception situation of the day. These 8 hours usually refer to 8 and 9 in the morning. ,10pm and 6,7,8,9,10pm.

[0041] KQI (Key Quality Indicator) represents the key quality indicator, and this data contains 14 columns of KQI indicators. A cell ...

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 cell scene division method based on machine learning, and belongs to the field of mobile communication. The mehtod comprises the following steps of: acquiring wireless sensing KQI (Key Quality Indicator) index data of each cell during 8 busy hours; expanding the data of each cell into a vector; performing dimension reduction on the vector data of each cell; clustering thedata subjected to dimension reduction; carrying out visualization on the clustered data; and comparing the clustered data of each type of cells to realize scene division of the cells. Dimension reduction and clustering algorithms are used for dividing cell scenes, the problems that a traditional manual division method is not fine enough and visualization cannot be conducted due to the fact that the cell data dimension is too high are solved, and an important basis is provided for making an accurate network optimization strategy in the next step.

Description

technical field [0001] The present invention relates to the technical field of scene division, in particular to a machine learning-based community scene division method. Background technique [0002] In recent years, with the rapid development of mobile communication networks and increasingly fierce market competition, the network service quality of communities has gradually become a key factor in the core competitiveness of communication operators. Among them, for the construction and optimization of community network services, effectively dividing scenarios is an important basis for more accurate formulation of planning and construction plans, more accurate determination of network optimization strategies, and realization of refined management and effective use of resources. Traditional scene division is mainly based on coverage and experience. This method of scene division is a coarse-grained qualitative division, which cannot be used as an accurate basis for precise adju...

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
IPC IPC(8): H04W24/02H04W24/08G06N20/00G06K9/62
CPCH04W24/02H04W24/08G06N20/00G06F18/23213Y02D30/70
Inventor 桂冠曾骏张凯旋樊广辉
Owner NANJING UNIV OF POSTS & TELECOMM
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