IoT Pedestrian Flow Prediction Using Graph Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Public places in smart cities often experience uneven pedestrian flow, leading to overcrowding in some areas and empty spaces in others, which can result in long waiting times for users.
Innovation Solution
An IoT system and method that utilize a cloud platform to collect and analyze pedestrian distribution data, employing a graph neural network model to predict area locations with high population flow loads and provide prompt information to users to avoid congested areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If cloud platforms are introduced to improve information processing capabilities, then computing efficiency and scalability are improved, but system complexity increases
Solution Approach 1:
The patent introduces a cloud platform as an intermediary between IoT devices and end users. The cloud platform receives data from various IoT devices, performs centralized processing and analysis, then delivers results to users. This mediator approach enables complex processing capabilities while keeping individual IoT devices simple and manageable.
2Productivity
If real-time pedestrian flow monitoring is implemented across multiple public places, then population flow balance is improved, but data collection and processing complexity increases
Solution Approach 1:
The patent merges data collection from multiple public places into a unified cloud-based system. Instead of managing separate monitoring systems for each location, the cloud platform consolidates pedestrian flow data from various IoT devices across different public places, enabling centralized analysis and coordinated management of population flow across the entire network.
Solution Approach 2:
The cloud platform is designed as a universal system that can handle data from multiple types of public places (parks, plazas, streets, etc.) and multiple types of IoT devices simultaneously. This multi-functional platform provides a single solution for diverse monitoring needs, reducing overall system complexity while maintaining comprehensive coverage.
3Reliability
If predictive analysis is performed to identify high-load area locations, then crowd avoidance capability is improved, but computational requirements and processing time increase
Solution Approach 1:
The system performs preliminary actions by continuously collecting and pre-processing pedestrian flow data in real-time. The cloud platform maintains an ongoing analysis of traffic patterns, performing preliminary computations that prepare prediction models for rapid execution. This allows the system to have prediction capabilities ready in advance, reducing the time needed when actual predictions are required.
Data Source
AI summary
The disclosure provides an Internet of Things system and a method for managing a people flow of a public place in a smart city. The method may comprise obtaining pedestrian distribution information in a preset area during a current time period via network from a storage device; determining, by processing the pedestrian distribution information through an area location prediction model, at least one area location in the preset area for a future time period, a population flow load of the area location being greater than a first threshold, wherein the area location prediction model includes a graph neural network model, a graph input into the graph neural network model includes at least two nodes and at least one edge; generating, based on the area location, prompt information; and feedbacking the prompt information to a user terminal of a user platform through a service platform via the network.