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

Multidimensional individualized recommendation method in heterogeneous network

A recommendation method and heterogeneous network technology, applied in the fields of data mining and machine learning, can solve the problems of users and items that do not consider item content and user attributes, do not consider the rich semantic information of users and items, and have limited recommendation accuracy.

Inactive Publication Date: 2017-01-25
SHANDONG UNIV
View PDF4 Cites 48 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional collaborative filtering algorithms are divided into memory-based collaborative filtering algorithms and model-based collaborative filtering algorithms. Both of them only use the information of a single user-item matrix, and the recommendation accuracy is limited.
Facing the shortcomings of the traditional recommendation system, which has a single relationship between users and items, does not consider the content of items and user attributes, and does not consider the rich semantic information between users and items, how to combine traditional recommendation methods with user feedback information and heterogeneous information networks? It is a problem to be solved to combine the comprehensive information integration ability of the system with the rich semantic information contained in it to make personalized recommendations.

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
  • Multidimensional individualized recommendation method in heterogeneous network
  • Multidimensional individualized recommendation method in heterogeneous network
  • Multidimensional individualized recommendation method in heterogeneous network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] This embodiment refers to the movie recommendation network, such as figure 1 As shown, the movie recommendation network is a heterogeneous information network with right and direction, and there are 5 different entity types in this network: users (including user 1, user 2), movies (including movie 1, movie 2, movie 3. Movie 4), director (including director 1 and director 2), starring role (including actor 1 and actor 2) and movie category (including movie style 1 and movie style 2). For each movie entity, there will be its starring, director and movie category entities connected to it. Users give ratings from 1 to 5 for the movies they have watched. According to the user's attribute information, users are divided into different user groups according to their viewing interests. The divisions can overlap, and the same user group likes movies of the same style or likes the same star director. In this embodiment, movies, interest groups, directors, actors, etc. that the u...

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 relates to a multidimensional individualized recommendation method in a heterogeneous network which includes: 1, obtaining information; 2, establishing a similarity matrix between the user and item; 3, establishing a semi-structured heterogeneous information network; calculating the degree of correlation between users and items and between users and users under different meta paths based on the semi-structured heterogeneous information network; distributing different weights to the degree of correlation of each meta path to form a similarity matrix between users and other types of entities in the semi-structured heterogeneous information network; 4, distributing different weights and integrating the degree of correlation between users and items and between users and users with user's preference to items to form the final similarity matrix; 5, recommending a plurality of items with big similarity in the final similarity matrix to users. The multidimensional individualized recommendation method is added with user subordinate information and item subordinate information, considers the rich semantic information between users and items, and improves the recommendation accuracy and percentage of coverage.

Description

technical field [0001] The invention relates to a meta-path-based correlation search method in a heterogeneous information network and a multi-dimensional personalized recommendation method combined with user feedback information and subordinate information, and belongs to the technical field of data mining and machine learning. Background technique [0002] In recent years, heterogeneous information networks have been widely studied because they are good at representing various relationships between different types of entities and can accurately distinguish different contexts in information networks to mine more meaningful knowledge. Among them, the meta-path representing the relationship between two entities is a unique concept in the heterogeneous information network. Different meta-paths represent different physical meanings. The rich semantic features contained in the meta-path are a part of the heterogeneous information network. A very important feature. Many meta-pat...

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 Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/9535
Inventor 张海霞吕振李苏雪
Owner SHANDONG UNIV
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