Unlock instant, AI-driven research and patent intelligence for your innovation.

A Recommendation Method Based on User Interest Association

A technology of user interest and recommendation method, applied in the field of content-based book recommendation, can solve the problem of unsatisfactory recommendation effect

Active Publication Date: 2018-05-04
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This kind of recommendation does not deeply explore the interest characteristics of A and B, and the final recommendation effect is often unsatisfactory

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 Recommendation Method Based on User Interest Association
  • A Recommendation Method Based on User Interest Association
  • A Recommendation Method Based on User Interest Association

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0030] figure 1 The steps of the recommendation method based on user interest association are shown, mainly including:

[0031] Step S100, establishing a user interest model. The user interest model is expressed as:

[0032] P={(W 0 , IP 0 ), (W 1 , IP 1 ),..., (W n , IP n )}

[0033] Among them, W i Represents the total number of times a user visits a point of interest, IP i It describes the user's point of interest. The point of interest refers to the last level of the product classification directory structure of the e-commerce website. A point of interest includes all product pages under this category. IP i Contains the interest vector for each item in the interest point, whose expression is:

[0034] IP i =[w 0 ,w 1 ,...,w m ]

[0035] Among them, w j On behalf of the user to point of interest IP i The calculation method...

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 recommendation method based on user interest association, which mainly includes the following steps: establishing a user interest model; calculating the correlation between different users to the same point of interest based on the user interest model; calculating each interest point of the user based on the user interest model Correlation between points; calculate the recommended value of related points of interest of other users with the same interest under the current point of interest; rank the above recommended values, and select the top n points of interest for recommendation. The present invention makes full use of the correlation between the interest points, and recommends the local optimal result to the user.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a content-based book recommendation method. Background technique [0002] In recent years, with the advancement of computer and network technology, e-commerce has developed rapidly. Users can purchase various commodities through the network. In order to help customers find suitable products as soon as possible, and also to promote products, e-commerce websites will integrate a recommendation system to automatically generate product recommendations for customers. In the product recommendation system, in order to encourage users to purchase more products, the recommendation system needs to make targeted product recommendations based on the user's interest characteristics, try to explore the potential needs of users, and finally form an order. [0003] At present, most recommendation systems only make simple product recommendations based on the user's purchase history and browsi...

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): G06Q30/02G06F17/30
Inventor 韩军
Owner BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD