Interest point recommendation method and device based on space-time sequence and social embedding ranking

A technology of interest points and sequences, applied in the field of deep learning, can solve problems such as poor recommendation performance, and achieve the final result of accurate recommendation

Active Publication Date: 2020-05-29
WUHAN UNIV
View PDF25 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In view of this, the present invention provides a point-of-interest recommendation method and device based on spatio-temporal sequence and social

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
  • Interest point recommendation method and device based on space-time sequence and social embedding ranking
  • Interest point recommendation method and device based on space-time sequence and social embedding ranking
  • Interest point recommendation method and device based on space-time sequence and social embedding ranking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] This embodiment provides a point-of-interest recommendation method based on spatio-temporal sequence and social embedding ranking, the method includes:

[0056] Step S1: Use the hybrid deep model based on horizontal convolution filter, vertical convolution filter and multi-layer perceptron model to model the user check-in timing information, learn the objective function of the timing features of the points of interest, and obtain the user check-in timing model.

[0057] Specifically, based on the hybrid deep model of horizontal convolution filter, vertical convolution filter and multi-layer perceptron model, the spatio-temporal sequence and check-in information of the user's check-in position are first embedded into the latent dimension space, and the embedded information The matrix is ​​regarded as a series of "images", and the time-space sequence mode and user check-in information are regarded as the local features of the "image", and then the joint convolution filter ...

Embodiment 2

[0171] Based on the same inventive concept as in Embodiment 1, this embodiment also provides a device for recommending points of interest based on time-space sequence and social embedding ranking, please refer to Figure 4 , the device consists of:

[0172] The user check-in timing model building module 201 is used to model the user check-in timing information using a hybrid depth model based on horizontal convolution filters, vertical convolution filters and multi-layer perceptron models, and learn the objective function of the timing features of points of interest , get the user sign-in timing model;

[0173] The user social information model construction model 202 is used to construct a weight function based on the metric learning theory for predicting the degree of social relationship between users and users, model the user social information, and obtain the user social information model;

[0174] The information fusion module 203 is used to fuse the user check-in timing ...

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 interest point recommendation method based on a space-time sequence and social embedding ranking, and the method comprises the steps: firstly proposing a mixed depth model based on a horizontal convolution filter, a vertical convolution filter and a multilayer perceptron model, and capturing the user preference and the impact of a space-time sequence mode; secondly, modeling the social relationship of the user by adopting a metric learning method; then, adopting a unified framework based on matrix decomposition to integrate personal interests of the users, sign-in sequence modes and social information of the users; and finally, optimizing a target loss function by adopting a BPR standard, fitting a partial order relationship of the user on the interest point pair, and finally generating an interest point recommendation list. According to the invention, the interest point recommendation method integrating the hybrid depth model and metric learning is constructed, so that the final recommendation is more accurate.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a point-of-interest recommendation method and device based on spatio-temporal sequence and social embedding ranking. Background technique [0002] With the rapid development of Web2.0, wireless communication and location acquisition technology have promoted many location-based social network applications. In these location-based social network service applications, users can establish social connections with other users and explore the surrounding environment. Share their life experiences and experiences by checking in points of interest (such as restaurants, shopping malls and attractions, etc.). In addition to providing an interactive platform for users, LBSN contains rich data (check-in data, social relations, comment information, etc.) that can be used to mine users' interests and preferences, and recommend unvisited geographic locations that users may be intere...

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
CPCG06F16/9535G06N3/08G06N3/048G06N3/045
Inventor 李雪飞徐洋洋高榕张玉洁饶建勋
Owner WUHAN UNIV
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap