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

Power user grouping method based on text mining

A power user and text mining technology, applied in the field of power systems, can solve problems such as the inability to meet the needs of power companies to provide personalized services to power customers, the difficulty of large-scale development, and the difficulty of accurately grouping power customers. Effects of accuracy, noise reduction, and accuracy improvement

Inactive Publication Date: 2017-05-24
YUNNAN POWER GRID CO LTD KUNMING POWER SUPPLY BUREAU
View PDF0 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the traditional customer grouping method, the label system is mainly mapped by business personnel manually, which is difficult to carry out on a large scale due to the limitation of labor costs and personnel experience; at the same time, the data source of traditional customer grouping is mainly the structure of the power company's own system Without processing and analyzing dynamic data such as behavior data, preference data, and emotional information of electricity consumers, it is difficult to accurately group electricity consumers
Therefore, the traditional method of grouping power customers is far from meeting the needs of power companies to provide personalized services to power customers.

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
  • Power user grouping method based on text mining
  • Power user grouping method based on text mining
  • Power user grouping method based on text mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. The specific implementation steps of a method for grouping power users based on text mining are as follows:

[0033] Step 100 Raw Data Acquisition and Preprocessing

[0034] Collect customer profile data and historical operation data of power companies through data mining and ETL tools;

[0035] Collect customer electricity consumption behavior, preferences, operation logs and other data from systems such as online business halls through web crawlers;

[0036] Convert voice information of voice systems such as 95598 into structured text data through voice conversion tools;

[0037] Step 200 establishes a tag system library based on the text automatic classification model of machine learning

[0038] Step 201 Prepare training set data and test set data

[0039] Manually classify a batch of preprocessed documents accurately as the training...

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 provides a power user grouping method based on text mining. The method is characterized by mainly through an automatic text classification model based on machine learning, establishing a label system database; according to a label and a label attribute weight, using a K-means cluster algorithm pair to carry out user portrait; and according to several label attributes under a user portrait, clustering users according to a certain rule, and using a Jaccard similarity calculating method to realize client group division based on the user portrait.

Description

[0001] Technical field: The present invention belongs to the field of power systems, and in particular relates to a method for grouping power users based on text mining. Background technique: [0002] With the new round of power system reform and the transformation of power companies to focus on improving customer service capabilities, power companies are paying more attention than ever to providing differentiated and personalized services to power customers and further improving customer satisfaction. However, the premise of providing differentiated and personalized services to electricity customers is that it is necessary to divide different sets of electricity customers according to their various attributes and characteristics, that is, customer groups. The traditional power customer grouping is mainly based on historical stock data, according to the known empirical rules of business personnel, and adopts the method of combining data analysis and expert evaluation to group c...

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): G06Q30/02G06Q50/06G06F17/30
CPCG06Q30/0201G06F16/2465G06F16/254G06F16/35G06Q50/06
Inventor 李永辉殷俊张苏杨泓段明明杨捷
Owner YUNNAN POWER GRID CO LTD KUNMING POWER SUPPLY BUREAU
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