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

Website recommendation method and equipment based on variational self-encoding data fusion

A technology of data fusion and recommendation method, applied in the direction of website content management, network data retrieval, neural learning method, etc., can solve the problems of inability to get recommendation results, information loss, etc., and achieve the effect of improving website recommendation effect and increasing available information

Pending Publication Date: 2021-01-15
NANJING UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, according to the work of the current named inventor, the existing recommendation method based on variational self-encoding processes the input information, and the information it uses only includes the interaction information mentioned below, which has caused a large degree of The loss of information on the network, so it is not possible to get excellent recommendation results

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
  • Website recommendation method and equipment based on variational self-encoding data fusion
  • Website recommendation method and equipment based on variational self-encoding data fusion
  • Website recommendation method and equipment based on variational self-encoding data fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings. It should be understood that the embodiments provided below are only intended to disclose the present invention in detail and completely, and fully convey the technical concept of the present invention to those skilled in the art. The present invention can also be implemented in many different forms, and does not Limited to the embodiments described herein. The terms used in the exemplary embodiments shown in the drawings do not limit the present invention.

[0018] In the embodiment of the present invention, a website recommendation method based on variational self-encoding data fusion is used for website recommendation. Based on collaborative filtering method, neural network, variational autoencoder, and side information extraction method, accurate website recommendation is realized. refer to figure 1 , the present invention comprises the f...

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 website recommendation method and device based on variational self-encoding data fusion, and the method achieves the website recommendation based on a collaborative filteringmethod, a neural network, a variational self-encoder and a side information extraction method. In model construction, side information extraction and a variational auto-encoder are combined to complete a website recommendation task with ranking information, and due to the fact that the side information in implicit feedback data is extracted, the information input by the model is more comprehensive. The invention has a good website recommendation effect.

Description

technical field [0001] The invention relates to a neural network, a variational autoencoder, website recommendation, and side information extraction, in particular to a website recommendation method based on a variational autoencoder. Background technique [0002] The amount of information on the Internet continues to increase, and the workload required to filter information on the network also increases. Search engines can help users find useful information when users have clear goals, and recommendation systems recommend users based on past behaviors. Discover information that users may be interested in. Collaborative filtering technology is widely used in recommendation systems, and for many years collaborative filtering has always been a research direction that has attracted the attention of researchers. Traditional collaborative filtering methods can be divided into two categories, neighbor-based methods and latent factor model methods. The neighbor-based method finds...

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): G06F16/9535G06F16/958G06N3/04G06N3/08
CPCG06F16/9535G06F16/958G06N3/08G06N3/045Y02D10/00
Inventor 李文中王品皓余泽鹏张淋洺陆桑璐
Owner NANJING UNIV