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

POI recommendation system and method based on spatio-temporal semantic interval perception under self-attention

A space-time semantics and recommendation system technology, applied in the field of recommendation, can solve problems such as the impact of recommendation effects

Active Publication Date: 2021-09-21
NORTHEASTERN UNIV LIAONING
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even if POIs have the same check-in order, POIs with shorter time intervals will have a greater impact on recommendation performance

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
  • POI recommendation system and method based on spatio-temporal semantic interval perception under self-attention
  • POI recommendation system and method based on spatio-temporal semantic interval perception under self-attention
  • POI recommendation system and method based on spatio-temporal semantic interval perception under self-attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0073] On the one hand, a POI recommender system with spatio-temporal semantic interval awareness under self-attention, such as figure 1 As shown, it includes a data collection and cleaning module, a personalized time interval module, a personalized spatial interval module, a semantic correlation calculation module, a spatiotemporal semantic interval-aware self-attention module, and a POI recommendation module;

[0074] The data collection and cleaning module is used to collect and clean location-based social network data, that is, the user check-in data set of a social networking site, including user information and POI check-in information, which are stored after data cl...

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 POI recommendation system and method based on self-attention-based space-time semantic interval perception, and relates to the technical field of recommendation. The system of the present invention includes a system, including a data collection and cleaning module, a personalized time interval module, a personalized space interval module, a semantic correlation calculation module, a space-time semantic interval perception self-attention module, and a POI recommendation module; by modeling the user interaction sequence as The sequence with different time intervals not only considers the absolute position of the user check-in data, but also incorporates these different time intervals into the recommendation system; based on the user's historical check-in data, by considering the time interval, spatial interval and semantic correlation between the check-in data , effectively capture the user's dynamic preferences, reasonably recommend to the user where they will go next, and improve the accuracy of recommendation.

Description

technical field [0001] The present invention relates to the technical field of recommendation, in particular to a POI recommendation system and method based on self-attention-based space-time semantic interval perception. Background technique [0002] With the rapid development of positioning technology and the popularity of smart phones, social network services have been greatly enhanced. More and more people use online social networks through smart phones. Users can share their current location, pictures, audio, Videos and trajectories have produced many location-based social networks (Location Based SocialNetworks, LBSNs), such as Foursquare, Gowalla, and Yelp. In LBSNs, users record their location and spatial information in the form of check-in through mobile devices, and share their comments and experiences on related POIs (Point Of Interest) such as tourist attractions, museums, libraries, restaurants, etc. The so-called check-in means that the system of the mobile de...

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): G06F16/9536G06F16/9537G06F16/9535G06N3/04G06N3/08
CPCG06F16/9536G06F16/9537G06F16/9535G06N3/08G06N3/044
Inventor 于亚新吴晓露包健王亚龙
Owner NORTHEASTERN UNIV LIAONING