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

Method for representing crowd movement patterns through context-dependent graph embedding

A technology of moving patterns and embedded representations, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve problems such as lack of labeled training data

Inactive Publication Date: 2020-02-21
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

(3) Lack of labeled training data

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
  • Method for representing crowd movement patterns through context-dependent graph embedding
  • Method for representing crowd movement patterns through context-dependent graph embedding
  • Method for representing crowd movement patterns through context-dependent graph embedding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] The method provided by this implementation to represent crowd movement patterns through context-sensitive graph embeddings can be used for such datasets containing user check-in records. The real-world LBSN dataset as shown in Table 1, with Gowalla ( http: / / snap.stanford.edu / data / loc-gowalla.html acquisition) as an example to experiment.

[0054] Table 1: Relevant information of experimental data of the present invention

[0055]

[0056] |u| indicates the number of users;

[0057] |D L | / |D U |respectively represent the number of sub-trajectories used for training and testing;

[0058] |L| represents the number of different check-in points in the dataset;

[0059] Represents the average length of the trajectory before it is divided;

[0060] T r Represents the range of trajectory lengths in the dataset;

[0061] New York represents the data that the area in the dataset Foursquare is New York;

[0062] Tokyo represents the data whose region is Tokyo in...

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 new method for representing crowd movement through a context-related graph embedding model. The method comprises the following steps: firstly, generating a fully-connected context correlation graph according to a historical track of a user; applying a word embedding technology to a graph model for the first time, learning sign-in point vector representation fused with context semantic information, then obtaining vector representation of each track through a recurrent neural network, and then introducing a reinforcement learning method to find out a current track generator. In the training process of the whole model, the track with the label and the track without the label are used for training synchronously, meanwhile, a strategy gradient method in adversarial learning is used for updating model parameters, and the model performance is further enhanced.

Description

technical field [0001] The invention belongs to the field of neural networks in machine learning, and is a method based on deep learning. The method applies word embedding technology to a graph model for the first time, and learns the vector representation of check-in points that integrates contextual semantic information, and then passes through a cyclic neural network. (Recurrent Neural Network, RNN) obtains the vector representation of each trajectory, and then uses reinforcement learning to extract the user's implicit movement patterns from the labeled and unlabeled trajectory data to find the user who generated the current trajectory. Background technique [0002] In Location-Based Social Network (LBSN) applications based on geographic location information, such as personalized location recommendation, travel planning, and crowd flow prediction, it is an important and complex task to learn crowd mobility rules. This task has a very wide range of application scenarios, f...

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): G06N3/04G06N3/08G06K9/62G06F40/30G06F16/29G06F16/9537G06Q50/00
CPCG06N3/084G06F16/29G06F16/9537G06Q50/01G06N3/045G06F18/241
Inventor 刘芳钟婷周帆
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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