Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Implicit feedback recommendation method based on node2vec and deep neural network

A deep neural network, implicit feedback technology, applied in the field of implicit feedback recommendation, to achieve good recommendation effect, high practicability, and ease sparsity effect

Active Publication Date: 2019-01-11
NANJING UNIV OF TECH
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The sparsity level of the data directly leads to the limitations of traditional collaborative filtering methods, namely matrix factorization and its various extension methods

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
  • Implicit feedback recommendation method based on node2vec and deep neural network
  • Implicit feedback recommendation method based on node2vec and deep neural network
  • Implicit feedback recommendation method based on node2vec and deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] One embodiment of the present invention is an implicit feedback recommendation method that integrates node2vec and deep neural network, and its implementation process is as follows figure 1 shown.

[0035] Step 1: Obtain user latent vectors and item latent vectors.

[0036] N users u in one-hot form i As an input vector, the sparse representation of the input layer is mapped to a dense vector through a fully connected embedding layer, and the obtained user embedding is regarded as a user latent vector used to describe the user.

[0037] Put M items of one-hot form v j As an input vector, the sparse representation of the input layer is mapped to a dense vector through a fully-connected embedding layer, and the obtained item embedding is regarded as an item latent vector used to describe the item.

[0038] For example using means user u i The user latent vector of , means item v j The item latent vector of . in Represents the user's latent feature matrix, N, D ...

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 an implicit feedback recommendation method based on node2vec and a depth neural network, belonging to the technical field of data processing. The invention comprises the stepsof obtaining a user potential vector and an item potential vector; obtaining a user context prediction and a project context prediction; generating a user preference prediction for the project and training the user preference prediction; performing joint training. The method can well take into account the rich metadata information of users and items, and has high recommendation accuracy and modeltraining efficiency.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to an implicit feedback recommendation method integrating node2vec and deep neural network. Background technique [0002] In the era of information explosion, recommender systems have played a huge role in alleviating information overload. Personalized recommendation systems are widely used in online service networks such as e-commerce and social media. Traditional recommendation models users' item preferences based on past interactions. Current solutions for recommendation using neural networks focus on explicit feedback and only model rating data. At the same time, when it comes to the interaction between users and item features, matrix decomposition is still used. The recent recommendation trend has shifted from explicit evaluation to implicit feedback, such as purchase, click, watch, etc. It cannot directly reflect user preferences, but the collection cos...

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): G06F16/9535G06N3/04G06N3/08
CPCG06N3/084G06N3/045
Inventor 何瑾琳刘学军张欣李斌徐新艳
Owner NANJING UNIV OF TECH
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
Eureka Blog
Learn More
PatSnap group products