Classification error correction method based on sequence connection model and binary tree model

An error correction method and binary tree technology, applied in the field of communication network business records, can solve problems such as large deviations in compression and recovery, failure to learn, etc., to achieve the effect of reducing audit workload and improving data quality

Active Publication Date: 2020-02-04
WUHAN UNIV
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

By learning the characteristic relationship of the data, for the abnormal data with a small proportion, their characteristics

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
  • Classification error correction method based on sequence connection model and binary tree model
  • Classification error correction method based on sequence connection model and binary tree model
  • Classification error correction method based on sequence connection model and binary tree model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] During specific implementation, the technical solution provided by the present invention can be implemented by those skilled in the art using computer software technology to automatically run the process. The technical solution of the present invention will be described in detail below with reference to the drawings and embodiments.

[0056] Step 1: Data preprocessing

[0057] First, read the communication network business records in the database based on python, use regular expressions to perform Chinese word segmentation for the text information, and store the results in different text files by field, with one word per line, and remove the duplicate; pass The obtained word file encodes the corresponding field, and then performs the normalization operation; performs the normalization operation on the numeric field.

[0058] Step 2: Build a Replicator Neural Network neural network model

[0059] (1) Construct the input layer and output layer. The number of nodes in the input ...

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 relates to a classification error correction method based on a sequence connection model and a binary tree model. The method belongs to the research category of data quality. The invention relates to the field of communicationfeed-forward neural network, in particularRNN, to a feed-feed new networkCART. The method mainly aims at communication network service records and service channel records, a Repulator Replicator Neural Network + CART classification model is constructed, a BP optimization method is adopted to carry out model training, and a trained model is utilized to carryout classification tasks. The method has the advantages that the training data is automatically selected, manual data identification is not needed, abnormal data is automatically found for truth valuerecommendation, the manual auditing workload is reduced, and the data quality is improved.

Description

Technical field [0001] The invention belongs to the technical field of unsupervised classification, and particularly relates to communication network business records and channel type information generated in a power communication management system. Background technique [0002] Electric power communication management system: It is an electric power dedicated communication network system that is an important support for smart grids. It is a "two-level deployment" for headquarters and provincial companies, and a "four-level application" communication management system for headquarters, branches, provincial companies, and city and county companies. SG-TMS". Through standardized and standardized project construction and the vigorous advancement of the practicality of the system, "SG-TMS" has been deeply integrated into the daily work of tens of thousands of power communication professionals, and has comprehensively collected the construction, operation and management of tens of thou...

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): G06F16/35G06F40/289G06N3/08
CPCG06F16/35G06N3/084
Inventor 李石君李学礼杨济海龚红霞余伟余放甘琳李宇轩
Owner WUHAN UNIV
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