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

POI recommendation method based on hierarchical attention mechanism

An attention and mechanism technology, applied in neural learning methods, special data processing applications, instruments, etc.

Active Publication Date: 2020-06-05
SHAANXI NORMAL UNIV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is still room for improvement in recommendation accuracy

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 method based on hierarchical attention mechanism
  • POI recommendation method based on hierarchical attention mechanism
  • POI recommendation method based on hierarchical attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In one embodiment, such as figure 1 As shown, it discloses a POI recommendation method based on a hierarchical attention mechanism, and the method includes the following steps:

[0020] S100: designing an LSTM-based decoder-encoder explicit feature extraction model for extracting explicit features from structured data;

[0021] S200: Design an implicit feature extraction model based on an NLP attention mechanism for extracting implicit features from unstructured data;

[0022] S300: Calculate user-POI matching degree by using text similarity;

[0023] S400: Use a softmax function to predict a preliminary POI recommendation list from the explicit features and the implicit features, and then use the user-POI matching degree to fine-tune the preliminary POI recommendation list to obtain a final POI recommendation list as a prediction result.

[0024] As far as this example is concerned, a hierarchical attention based POI recommendation method (TPOIRec) is proposed. Firs...

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 POI recommendation method based on a hierarchical attention mechanism, and the method comprises the following steps: S100, designing an explicit feature extraction model of adecoder-encoder based on LSTM, and extracting explicit features from structured data; s200, designing an implicit feature extraction model of an attention mechanism based on NLP, wherein the implicitfeature extraction model is used for extracting implicit features from the unstructured data; s300, calculating a user-POI matching degree by using the text similarity; and S400, predicting a preliminary POI recommendation list from the explicit features and the implicit features by using a softmax function, and then finely adjusting the preliminary POI recommendation list by using the user-POI matching degree to obtain a final POI recommendation list as a prediction result. Compared with an existing method, the method improves the data utilization rate and recommendation precision.

Description

technical field [0001] The disclosure belongs to the field of information processing technology and network communication technology in the field of Internet technology, and in particular relates to a POI recommendation method based on a hierarchical attention mechanism. Background technique [0002] With the rapid development of mobile devices and location acquisition technology, it is becoming more and more convenient for people to obtain real-time location information, and related platforms of Location-Based Social Networks (LBSNs) including Yelp, Foursquare, Dianping, and Mafengwo have also received corresponding attention. improve dramatically. Users of these platforms share their locations and share their related experiences in places they have visited (such as tourist attractions, restaurants, and shops, etc.), generating a large amount of user check-in data (Checkin). The places that these users have visited and are interested in are Point-of-Interest (POI). A larg...

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): G06F16/9537G06F16/9536G06N3/04G06N3/08
CPCG06F16/9537G06F16/9536G06N3/08G06N3/044G06N3/045
Inventor 王小明庞光垚郝飞王亮谢杰航王新燕
Owner SHAANXI NORMAL UNIV
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