Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Content-based cross-domain recommendation method

A recommendation method and cross-domain technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as data sparseness and cold start

Inactive Publication Date: 2019-09-13
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings and deficiencies in the prior art, and provide a content-based cross-domain recommendation method, which can solve the problems of data sparseness and cold start faced by existing recommendation methods, and can not only achieve cross-domain recommendation, and improve the recommendation performance in the target domain

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
  • Content-based cross-domain recommendation method
  • Content-based cross-domain recommendation method
  • Content-based cross-domain recommendation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] Such as figure 1 and figure 2 As shown, the content-based cross-domain recommendation method of the present invention includes the following steps:

[0033] Step S1: collect the text corpus of the source domain and the text corpus of the target domain respectively, and perform word segmentation statistics to obtain the user interest vocabulary.

[0034] Step S2: Use the text information of items in the user behavior sequence in the source domain as the source domain training data, and use the text information of each item in the target domain as the target domain training data.

[0035] Step S21: Take the text information of the 50 items that the user has recently interacted with in the source domain and splicing them into the user behavior sequence text according to the interaction occurrence time, and randomly select one of the 50 item sequences as the prediction target, and delete it in the sequence ; The text information of the rest of the items is used as the so...

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 provides a content-based cross-domain recommendation method. The content-based cross-domain recommendation method comprises the following steps: S1, obtaining a user interest word list;S2, taking the text information of projects in a user behavior sequence of a source domain as source domain training data, and taking the text information of each project in the target domain as target domain training data; S3, constructing a content semantic coding network model; S4, using the content semantic coding network model trained in the step S3 to carry out content semantic coding on theuser behavior of the source domain and the project of the target domain to obtain a user behavior interest vector and a project semantic vector; and S5, for each user, calculating the similarity by using the interest vector and the project semantic vector of the user, and obtaining k most similar projects as recommended projects. Due to the content-based cross-domain recommendation method, the user interest vectors can be coded based on the text information of the projects in the source domain user behavior sequence and are matched with the projects in the target domain, so that cross-domainrecommendation is realized.

Description

technical field [0001] The present invention relates to the technical field of recommendation, and more specifically, to a content-based cross-domain recommendation method. Background technique [0002] With the continuous development of mobile Internet technology, the amount of information in the network is rapidly expanding and increasing exponentially, and the problems of information overload and information wandering on the network are becoming more and more serious. In order to provide users with satisfactory information and services, recommender systems emerged as the times require, and have become a research field that many researchers pay attention to. The recommendation system performs information filtering by predicting the user's preference for information resources. [0003] At present, the commonly used recommendation method is the recommendation algorithm based on collaborative filtering. This type of method is mainly used for single-domain recommendation, req...

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): G06F16/9535G06Q30/06G06K9/62G06N3/04G06N3/08
CPCG06F16/9535G06Q30/0631G06N3/084G06N3/044G06N3/045G06F18/241
Inventor 佘焕波田翔
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products