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

Communication network equipment data association method and system

A device data and communication network technology, applied in biological neural network models, instruments, character and pattern recognition, etc., can solve mechanical, repetitive and cumbersome problems, reduce the number of calls, overcome low correlation accuracy, and improve The effect of expressiveness

Active Publication Date: 2021-10-22
CHINA SOUTHERN POWER GRID COMPANY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is that there are mechanical, repetitive and cumbersome problems when manually correlating communication network data, and the purpose is to provide a communication network device The method and system of data association realizes the replacement of manual work by machines and greatly improves work efficiency

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
  • Communication network equipment data association method and system
  • Communication network equipment data association method and system
  • Communication network equipment data association method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0092] like figure 1 As shown, a method for data association of communication network equipment in the present invention comprises the following steps:

[0093] Step S1. Obtain the communication network data of the equipment, and divide the communication network data of the equipment into three types of data: communication resource data, equipment asset data and daily operation data according to different storage systems;

[0094]Step S2, extracting several specific data respectively from the three types of communication network data, and selecting several specific data under the corresponding categories to combine into one piece of test data, so as to obtain multiple pieces of test data under the corresponding categories of the three types of communication network data, for Each piece of test data is preprocessed to obtain several pieces of training data, and any two pieces of training data under different categories are selected from the several pieces of training data to fo...

Embodiment 2

[0229] like Figure 8 As shown, the difference between this embodiment and Embodiment 1 is that the present invention provides a communication network device data association system, which includes an offline training module and an online prediction module. The offline training module includes a training data preparation module, a training data pre-prediction module Processing module, training data set building module, model training module;

[0230] The training data preparation module is used to extract a number of specific data from the three types of communication network data: communication resource data, equipment asset data and daily operation data, and select a number of specific data under the corresponding category to combine into a piece of test data, Obtain multiple pieces of test data under the corresponding categories of the three types of communication network data;

[0231] The training data preprocessing module is used to preprocess each piece of test data to...

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 communication network equipment data association method and system, and the method comprises the steps: constructing positive and negative category data pairs through manual annotation and an algorithm, enriching training corpora through a data enhancement technology, and avoiding an underfitting phenomenon of a model; sampling a bagging algorithm in a balanced mode to generate data for model training and verification; integrating an ensemble learning thought, comprehensively utilizing a sentence Euclidean structure space vector and a non-Euclidean structure space vector, and extracting sentence features; using the model pre-loading function to reduce task prediction time of the model; performing reverse exclusion on the input to-be-associated data to reduce the calling times of the model service; in the online prediction process, a multi-process and multi-thread parallel operation mode is used, and the prediction time is shortened.

Description

technical field [0001] The invention relates to the application of NLP in the computer field, in particular to a method and system for data association of communication network equipment. Background technique [0002] Communication network data includes three major blocks: communication resource data, equipment asset data, and daily operation data. These three pieces of data jointly describe an equipment entity. The three pieces of data belong to the resource field, financial asset management field, and real-time operation field respectively. They belong to different fields, but they all belong to the same equipment entity. However, the data of various types of communication networks are stored independently in each system, lack of correlation, and are separated from each other, making it difficult to make effective use of them. Therefore, associating different data is a common requirement for digitizing the entire life cycle of assets. The current communication network da...

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): G06K9/62G06N3/04G06F40/58
CPCG06F40/58G06N3/045G06F18/24G06F18/214
Inventor 黄强杨志敏洪丹轲贺云吴桂龙陈一童谢俊毅冯晓芳
Owner CHINA SOUTHERN POWER GRID COMPANY
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