A user behavior analysis method based on user power consumption data

A technology of electricity consumption data and consumption data, which is applied in data processing applications, instruments, calculations, etc., can solve the problems of ignoring and not extracting the main characteristics of user power data, and achieve the effect of high identification and detection efficiency

Inactive Publication Date: 2019-01-11
NANJING UNIV OF SCI & TECH
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing technologies all analyze the abnormalities of user power data from the perspective of power companies, and only pay attention to the authenticity of data to facilitate power companies to make correct marketing decisions, but they do not do a good job of digging out the abnormalities behind power data from the perspective of users.

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
  • A user behavior analysis method based on user power consumption data
  • A user behavior analysis method based on user power consumption data
  • A user behavior analysis method based on user power consumption data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] Taking the user electricity consumption data to be processed as an example, the user electricity consumption data has three attributes, which are as follows: user ID, electricity consumption time, and electricity consumption. Some users obtained family type tags through investigation, and there are 4 types: vacant house residents, elderly family residents, office worker households, and elderly office worker households living together.

[0073] The specific implementation is mainly divided into four stages: single-day user power data feature extraction; mark samples through user family information, use constrained seed k-means algorithm for semi-supervised learning, and train four types of user power consumption models; outlier points and clusters Change detection finds abnormal user behavior.

[0074] 1. Single-day user power data feature extraction

[0075] In the present invention, the steps of extracting the feature of single-day user power data are as follows:

[...

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 user behavior analysis method based on user power consumption data. The method comprises the following steps: taking a batch user data training set of electricity consumptionper hour per day as input; pre-processing the input electricity data, including extracting the electricity characteristics, normalizing the data, and reducing the dimension by principal component analysis; taking the family characteristic information of some users as input; using the constrained seed k-means algorithm and some household information data, carrying out the semi-supervised clustering analysis on the training set of user power consumption data, and constructing the power consumption data models of different types of users; taking as input the data set of power consumption per hour per day of the user to be detected; using the model to detect the abnormal behavior of users. The method can efficiently identify and detect the user behavior according to the real-time power consumption data of the user.

Description

technical field [0001] The invention relates to the technical field of user behavior analysis methods, in particular to a user behavior analysis method based on user power consumption data. Background technique [0002] With the construction and development of smart cities in my country, through the accelerated deployment of smart meters, the power industry has accumulated large-scale user power consumption data, and these power consumption data are closely related to the daily life behavior of residents. The continuous improvement of information technology in the power system provides a solid foundation for the storage, analysis and mining of user power consumption data. Using data mining technology to analyze and research these massive data, we can discover the behavior rules of different users, and can judge the abnormal behavior of users and abnormal users. [0003] Existing technologies all analyze the abnormalities of user power data from the perspective of power comp...

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): G06Q10/06G06Q50/06G06K9/62
CPCG06Q10/06393G06Q50/06G06F18/23213
Inventor 陈盛之李千目侯君蔡志成张静
Owner NANJING UNIV OF SCI & TECH
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