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

A point-of-interest recommendation method for fusing social network and image content

A technology of image content and social network, applied in the field of information recommendation, can solve problems such as ignorance, no text data and image data integrated at the same time, achieve the effect of improving accuracy, solving cold start and accuracy problems, and improving experience

Active Publication Date: 2019-01-18
GUANGDONG UNIV OF TECH
View PDF4 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods are based on text-type data information, ignoring multimedia information rich in implicit information such as image content.
Not incorporating both text data and image data into the matrix factorization model

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 point-of-interest recommendation method for fusing social network and image content
  • A point-of-interest recommendation method for fusing social network and image content
  • A point-of-interest recommendation method for fusing social network and image content

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as Figure 1-2 As shown, a POI recommendation method that integrates social network and image content includes the following steps:

[0056] Step 1. Construct user-POI scoring matrix R ij , by fusing the distance and label factors, a new user-point of interest scoring matrix is ​​constructed; in the present invention, users who have checked in less than 10 times are filtered out, and each point of interest should be visited by the user at least 10 times, and the user should be at least Visit 5 different points of interest. For picture data, the present invention filters out pictures containing portraits and the like.

[0057] Step 2, realize the VGG16 convolutional neural network, modify the last soft layer, process the picture into a 1000-dimensional vector, and construct the image content matrix according to the points of interest; when using the VGG16 model to process the image into a 1000-dimensional vector, due to each Interest points correspond to multiple...

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 point of interest recommendation method for fusing social network and image conten.Based on the existing social recommendation model, a new matrix decomposition model which integrates social network and image content is proposed, which can make full use of the picture information in user evaluation information, alleviate the sparsity of data, and improve the accuracy of interest point recommendation. In addition, the invention utilizes the text information, the geographic information and the tag classification information of the interest point evaluation to better solve the cold start and accuracy problems of the interest point recommendation, recommends the most desired interest point to the user, and improves the user's experience degree.

Description

technical field [0001] The present invention relates to the field of information recommendation, and more specifically, to a point-of-interest recommendation method that integrates social network and image content. Background technique [0002] With the rapid development of Web 2.0, wireless communication and location collection technologies have led to many location-based social networks (LBSNs), for example. Yelp, Foursquare, Facebook Places, etc. Users can post their geotags and physical locations in the form of "check-ins", and share their experience and experience with friends about visited points of interest (eg, shopping malls, restaurants, museums, entertainment venues, hotels, etc.). In daily life, people usually like to explore the cities they live in and nearby places, and choose points of interest related to their preferences according to their personal interests. Since the data of points of interest and user preferences contains a lot of valuable information, ...

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): G06F16/9537G06Q50/00
CPCG06Q50/01
Inventor 邵长城陈平华
Owner GUANGDONG 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com