Commodity recommendation optimizing method based on customer behavior

A product recommendation and optimization method technology, applied in marketing and other directions, can solve problems such as inability to update online, failure to consider customer purchase interest, and delay in updating calculation results, etc., to achieve the effect of solving cold start and personalized recommended products

Inactive Publication Date: 2012-10-10
姚明东
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Can only be calculated offline, cannot be updated online, and there is a delay in updating the calculation results
It is not personalized enough and doe

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
  • Commodity recommendation optimizing method based on customer behavior
  • Commodity recommendation optimizing method based on customer behavior
  • Commodity recommendation optimizing method based on customer behavior

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0061] The present invention will be described in detail below in conjunction with specific embodiments.

[0062] reference figure 1 , Is a flow chart of the optimization method for product recommendation based on customer behavior, including steps 1 to 7:

[0063] Step 1: Initialization.

[0064] The customer's purchase interest value for all commodities is initialized. The customer's purchase interest value for all commodity categories is initialized.

[0065] buyInterest(u,s)=clickWeight×clickCount(u,s)+buyWeight×buyCount(u,s)

[0066] buyInterestType(u, Type[s])=typeWeight×buyInterest(u,s)

[0067] In the above formula, buyInterest(u,s) represents the purchase interest of customer u's product s, clickCount(u,s) represents the number of clicks on the recommended product s by customer u, clickWeight represents the weight of the customer’s click on the recommended product, buyCount(u, s), represents the number of customer u's purchases of the recommended product s, buyWeight represent...

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 commodity recommendation optimizing method based on a customer behavior. The method comprises the following steps of: 1, initializing; 2, adjusting a purchase interest configuration file of a registered customer according to best-selling commodities; 3, adjusting the purchase interest configuration file of the registered customer according to the clicking of recommended commodities by the customer; 4, adjusting the purchase interest configuration file of the registered customer according to the purchase of the recommended commodities by the customer; 5, adjusting the purchase interest configuration file of the registered customer according to low-concern recommended commodities of the customer; 6, adjusting the recommended position ranking of commodities according to the concern of the customer on recommended commodities; and 7, adjusting the purchase interest configuration file of the registered customer according to the purchase interest values of the customer on commodities, and arranging commodities with higher purchase interest values in recommended positions.

Description

technical field [0001] The invention is applied to a product recommendation system of B2C e-commerce. It can get feedback information based on customer behavior, discover customers' purchasing interests, adjust recommended products, and improve the performance of the product recommendation system in a targeted manner. Background technique [0002] With the rapid development of B2C e-commerce, the research on product recommendation methods has become more and more in-depth, but on the whole, the relevant research is not mature enough, and there is a lot of room for research. [0003] Currently, there are two mainstream product recommendation methods: (1) content-based recommendation methods; (2) collaborative filtering-based recommendation methods. Both of these recommendation methods have deficiencies and need to be improved. [0004] (1) In the content-based recommendation method, according to the products that customer u has purchased, similar products are recommended to...

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): G06Q30/02
Inventor 姚明东
Owner 姚明东
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