Customer service strategy making method and device based on random forest and logistic regression

A random forest and logistic regression technology, applied in the field of machine learning, can solve the problems that the business system architecture is difficult to meet the requirements of system operation, and achieve the effect of maintaining long-term sustainable development, increasing loyalty, and enhancing competitiveness

Inactive Publication Date: 2018-08-10
STATE GRID SHANDONG ELECTRIC POWER
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] With the explosive growth of data volume and the continuous improvement of business requirements, the traditional business system architecture has become increasingly difficult to meet the requirements of system operation

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
  • Customer service strategy making method and device based on random forest and logistic regression
  • Customer service strategy making method and device based on random forest and logistic regression
  • Customer service strategy making method and device based on random forest and logistic regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] This embodiment discloses a method for formulating customer service strategies based on random forest and logistic regression, such as figure 1 shown, including the following steps:

[0060] (1) Data preparation stage

[0061] 1. Establish a customer value evaluation feature index system:

[0062] By collecting user profile information, economic value information, load value information, development value information, credit value information, and industry value information, comprehensively analyze various factors that affect the comprehensive value of customers, and establish a customer value evaluation characteristic index system. Through concentrated customer discussions and customer surveys, the high-quality discrimination of sample users in various cities is realized, and data basis is provided for model training.

[0063] Based on the various value characteristics brought by high-quality customers to the power grid company, sort out the various electricity consu...

Embodiment 2

[0162] The purpose of this embodiment is to provide a computing device.

[0163] A client service strategy formulation device based on random forest and logistic regression, comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor implements the following steps when executing the program, including :

[0164] Step 1: Obtain the value characteristics of sample customers and conduct high-quality judgment;

[0165] Step 2: Use sample customer data to build a high-quality customer identification model based on random forest and logistic regression algorithms;

[0166] Step 3: Analyze the validity of the judgment results of the high-quality customer identification model based on the expert supervision method, and train the high-quality customer optimization identification model based on the analysis results;

[0167] Step 4: Taking the value characteristics of the customer to be identified as input, and based on th...

Embodiment 3

[0169] The purpose of this embodiment is to provide a computer-readable storage medium.

[0170] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are performed:

[0171] Step 1: Obtain the value characteristics of sample customers and conduct high-quality judgment;

[0172] Step 2: Use sample customer data to build a high-quality customer identification model based on random forest and logistic regression algorithms;

[0173] Step 3: Analyze the validity of the judgment results of the high-quality customer identification model based on the expert supervision method, and train the high-quality customer optimization identification model based on the analysis results;

[0174] Step 4: Taking the value characteristics of the customer to be identified as input, and based on the high-quality customer identification model, judging whether the customer is a high-quality customer.

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 customer service strategy making method and device based on random forest and logistic regression. The method comprises the following steps that: obtaining sample customer value features, and carrying out high-quality discrimination; adopting sample customer data, and constructing a high-quality customer identification model on the basis of the random forest and a logic regression algorithm; taking the value feature of a customer to be identified as input, and judging whether the customer is a high-quality customer or not; obtaining the service requirement of the sample customer, and carrying out standardized classification analysis to establish a service requirement library; matching service requirements in the service requirement library with service contents, matching the service contents with different levels of high-quality customers, and establishing a service strategy library; and on the basis of the service requirement library and the service strategylibrary, according to a high-quality customer identification result, automatically matching with a service strategy. By use of the method, the accurate positioning of the high-quality customer is realized on the basis of big data, and the analysis result of the service requirement analysis is combined to make a personalized and value-added service product and service strategy.

Description

technical field [0001] The invention belongs to the field of machine learning, in particular to a method and device for formulating customer service strategies based on random forest and logistic regression. Background technique [0002] With the deepening of electric power reform and the full liberalization of the electricity sales side market, power supply companies at all levels of the State Grid Corporation of China are facing pressure from market competition. In order to improve the profitability and competitiveness of power grid enterprises, increase the loyalty, satisfaction and customer Stickiness. On the basis of providing general services to the whole society, providing high-quality services to high-quality customers will be the main means and strategy for all electricity sales entities to compete for high-quality customers. It is necessary to formulate targeted competitive service strategies to reduce limited service It is an inevitable choice for power grid enter...

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): G06Q10/04G06Q10/06G06Q30/02G06Q50/06
CPCG06Q10/04G06Q10/0639G06Q30/0201G06Q50/06
Inventor 张洪利李云亭荣以平朱伟义刘霄慧尹明立粱波乔学明王伟刘昳娟王鑫
Owner STATE GRID SHANDONG ELECTRIC POWER
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