POI Congestion Estimation Using Route Demand and Arrival Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems fail to provide accurate real-time congestion information for points of interest (POIs), which is crucial for users planning their routes, leading to potential confusion and inefficiency in selecting destinations.
Innovation Solution
A method and device that estimate congestion based on route demand by utilizing an estimation model to analyze demand data from vehicles expected to travel to a POI, incorporating deep learning techniques to predict congestion levels and provide real-time updates to users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If existing navigation functions provide routes to POIs, then users can reach destinations, but accurate real-time congestion information at POIs is not provided
Solution Approach 1:
The system performs preliminary actions by collecting route demand data from multiple vehicles before the user arrives at the POI. It aggregates travel pattern data, destination information, and route selection data in advance to predict congestion levels, providing congestion information proactively rather than reactively.
Solution Approach 2:
The patent introduces an intermediary estimation model that processes raw route demand data and transforms it into meaningful congestion predictions. This model acts as a mediator between the complex data collection system and the user interface, simplifying the information flow while maintaining accuracy.
2Measurement precision
If congestion status is provided irrespective of user's expected arrival time and distance, then congestion data is available, but the information becomes meaningless or confusing to the user
Solution Approach 1:
The system applies local quality by customizing congestion information according to each user's specific context. It considers the user's expected arrival time, current location, and distance to the POI to provide tailored congestion predictions. The congestion status is not generic but specifically relevant to the user's situation, making it both precise and easy to understand.
Solution Approach 2:
The patent changes key parameters including expected arrival time, distance to POI, and route demand timing to generate context-aware congestion predictions. By dynamically adjusting these parameters based on real-time user data, the system transforms static congestion data into dynamic, user-specific information that is both accurate and comprehensible.
3Reliability
If route demand data from multiple vehicles is collected, then congestion prediction accuracy improves, but data processing complexity increases
Solution Approach 1:
The system merges route demand data from multiple vehicles into a unified dataset for congestion prediction. It combines travel patterns, destination information, and route selection data from various sources, then processes this consolidated data through the estimation model to generate reliable congestion predictions while managing processing complexity through integration.
Data Source
AI summary
A method and device for estimating congestion based on route demand utilize an electronic apparatus having a processor and a memory in order to determine an optimal route of a user of a vehicle. The method includes: acquiring demand data based on vehicles that are expected to be traveling to a point of interest (POI) related to a user request; estimating, by an estimation model, congestion of the POI based on the demand data; and providing the congestion of the POI to an electronic device of the user, so that the user can optimally reach the POI as a destination in the vehicle. For example, the vehicles may be expected to be traveling in real time along at least portion of routes to the POI.