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

A Heterogeneous Information Network Enhanced Academic Paper Recommendation Method

A heterogeneous information network and recommendation method technology, which is applied in neural learning methods, biological neural network models, digital data information retrieval, etc., can solve problems such as sparse interactive data, and achieve the effect of improving accuracy

Active Publication Date: 2022-07-19
NINGBO UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention uses heterogeneous information network to solve the problem of sparse interactive data, which can improve the accuracy of recommendation

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 Heterogeneous Information Network Enhanced Academic Paper Recommendation Method
  • A Heterogeneous Information Network Enhanced Academic Paper Recommendation Method
  • A Heterogeneous Information Network Enhanced Academic Paper Recommendation Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] Example: A method for recommending academic papers enhanced by heterogeneous information network, the process is as follows figure 1 shown.

[0061] Step 1. Build a heterogeneous information network.

[0062] like figure 2 is a heterogeneous information network based on the citeulike dataset, figure 2 In (a) part represents node type, (b) part represents heterogeneous information network, (c) part represents meta-path, (d) part represents meta-path neighbors, the network contains 3 types of nodes: user U, paper P and label T, 3 kinds of relationships: user-paper interaction relationship, inter-paper citation relationship and paper label inclusion relationship. The citeulike dataset is a public dataset suitable for the field of paper recommendation. Three files, users.dat, citations.dat and item-tag.dat are selected as the original data, where users.dat is the user's historical click paper record, citations. dat is the citation record of the paper, and item-tag.dat...

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 method for recommending academic papers enhanced by a heterogeneous information network, comprising the following steps: Step 1, constructing a heterogeneous information network, the heterogeneous information network includes three types of nodes: users, papers, tags, and user and The interaction between papers, the citation relationship between papers and papers, and the affiliation between papers and tags are three kinds of relationships; step 2, use matrix factorization algorithm to learn the interaction features between users and papers; step 3, combine the interaction features Input the heterogeneous graph attention network to learn the high-level features of the paper in the heterogeneous information network; step 4, use the outer product calculation to fuse the features learned in steps 2 and 3; step 5, input the features fused in step 4 into the depth The recommendation model predicts the score. The present invention solves the problem of sparse interaction data by utilizing a heterogeneous information network, and can improve the accuracy of recommendation.

Description

technical field [0001] The invention relates to a method for recommending academic papers, in particular to a method for recommending academic papers enhanced by heterogeneous information networks. Background technique [0002] With the explosive growth in the number of academic publications and the rapid iteration of knowledge, it is difficult for researchers to easily find academic papers that meet their needs, and they are facing more and more serious information overload problems. APR) to accurately recommend papers to researchers is becoming an indispensable tool for researchers. Collaborative Filtering (CF) is widely used in recommender systems to predict users' personalized preferences by exploring users' historical interactions. However, CF cannot produce robust performance when the interaction matrix is ​​very sparse; in recent years, Many methods propose to utilize various auxiliary information to improve recommendation performance. In paper recommendation, two k...

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): G06F16/335G06N3/04G06N3/08
CPCG06F16/335G06N3/08G06N3/045
Inventor 刘柏嵩吴俊超沈小烽张雪垣王冰源
Owner NINGBO UNIV