Commodity recommendation list generating method and system for e-commerce

A product recommendation and e-commerce technology, applied in marketing and other directions, can solve the problems of difficulty in comprehensively describing all relationships of complex business, unsatisfactory prediction accuracy and robustness, etc., achieving high accuracy, improving model accuracy and robustness. Good results

Inactive Publication Date: 2017-01-04
SUNING COM CO LTD
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the current commodity purchase forecast, the use of a single model is still relatively common, but at the same time it also exposes tha

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 list generating method and system for e-commerce
  • Commodity recommendation list generating method and system for e-commerce
  • Commodity recommendation list generating method and system for e-commerce

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The technical solutions of the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0040] Such as figure 1 As described above, this embodiment provides a method for generating a product recommendation list in e-commerce, including the following steps:

[0041] S11 collects the user's feature data, and fuses the data of each terminal to obtain a real-time predicted feature vector after fusion;

[0042] S12 calculates the purchase probability of the behavioral commodity;

[0043] S13 corrects the purchase probability of the behavioral commodity obtained in S12 to obtain the purchase probability of the fused behavioral commodity;

[0044] S14 Measures the purchase probability of similar related products, sorts them according to the purchase rate, and generates a product recommendation list.

[0045] In the above-mentioned embodiments, the collected user feature data comes from in-station data of the PC ...

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 list generating method for e-commerce. The method comprises the following steps that S11) characteristic data of a user is collected and integrated with data of different terminals to obtain a real-time prediction characteristic vector after integration; S12) the purchasing probability of a behavior commodity is calculated; S13) the purchasing probability, obtained in S12), of the behavior commodity is corrected to obtained the purchasing probability of the behavior commodity after integration; and S14) according to the corrected purchasing probability of the behavior commodity, the purchasing probabilities of related commodities are measured, and a commodity recommendation list is generated from high to low purchasing probabilities. The invention discloses a commodity recommendation list generating system for e-commerce. The generating method and system can improve the prediction precision of the commodity recommendation list.

Description

technical field [0001] The present invention relates to the field of e-commerce, in particular to a method and system for generating a product recommendation list in e-commerce. Background technique [0002] At present, the standard of Internet e-commerce purchase prediction algorithm is based on multi-dimensional feature data source, using logistic regression model, and the model learning and training method is basically the maximum likelihood algorithm or the gradient descent algorithm. Most of the prediction models use a unified data source, a unified model, and a single-terminal algorithmic prediction model. [0003] In the current commodity purchase forecasting, the use of a single model is still relatively common, but at the same time it also reveals that it is difficult to fully describe all the relationships of complex businesses, and the prediction accuracy and robustness are not satisfactory. Similarly, a single terminal and a unified data source are not conducive...

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 陈雪峰孙奉海张侦刘勇
Owner SUNING COM 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