A customer label modeling and recommendation method and device

A recommendation method and technology of a recommendation device, which are applied in the field of customer tags, can solve the problems of family attribute business without considering the common friends of customers, affecting recognition accuracy, etc., and achieve reasonable customer trust, high recommendation quality, and accurate tag recognition rate. Effect

Active Publication Date: 2020-12-01
CHINA MOBILE GRP GUANGDONG CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, only the direct communication between customers is used to calculate the density factor, without considering the mutual friends between customers and the customers' use of family network, family network and other services with family attributes; in addition, when calculating customer tag features, The weight of each customer is the same, and there is no identification of customers with high influence factors in the social circle. In practice, some customers have the characteristics of opinion leaders and have high influence factors on the people around them, so they should be given more weights. Affect the recognition accuracy

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 customer label modeling and recommendation method and device
  • A customer label modeling and recommendation method and device
  • A customer label modeling and recommendation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to understand the characteristics and technical contents of the embodiments of the present invention in more detail, the implementation of the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the embodiments of the present invention.

[0054] In the technical solution of the embodiment of the present invention, the pagerank algorithm is improved according to the customer communication circle and family attribute business characteristics, and the pagerank algorithm based on customer trust is established, and a new customer label modeling and recommendation method is proposed on this basis. Through the classic data model, the shortcomings of one-sidedness and contingency brought about by previous empiricism are discarded, and the scientificity and accuracy of the model are improved.

[0055] Based on this,...

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 tag modeling and recommendation method and apparatus. The method comprises the steps of constructing a customer trust degree matrix; based on the customer trust degree matrix, calculating customer influence factors; obtaining a customer tag feature matrix; in combination with the customer influence factors, the customer trust degree matrix and the customer tag feature matrix, calculating feature information of each customer; and selecting out a target tag from the feature information of each customer and pushing the target tag to a customer recommendation system.

Description

technical field [0001] The invention relates to customer labeling technology in the field of business support, in particular to a customer label modeling and recommendation method and device. Background technique [0002] Customer label modeling is a very important research topic in the carrier industry. Customer tags refer to the identification of customers' interests and hobbies, which are customer business and behavior preferences in operators, such as IPHONE, 4G, games, travel, etc. Customer label modeling is mainly to mine the relationship between customers and various business or behavioral characteristics, make a comprehensive portrait of customers, and identify the relationship between customers and various labels, so as to provide personalized recommendation services for customers. Improve the success of referrals. For example, customer 4G label recognition, accurately identify potential 4G target customers, make accurate recommendations for customers with obvious...

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 Patents(China)
IPC IPC(8): G06F16/9535G06F16/9532G06F16/955G06Q30/02
CPCG06Q30/0201G06F16/951G06F16/9562
Inventor 刘伟平刘忱杨应宝严关武王建宏刘钰柏黄志豪李少奇
Owner CHINA MOBILE GRP GUANGDONG CO LTD
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