Congestion-Dependent Parking Navigation Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solutions for locating parking spots are overly simplistic and fail to accurately predict driver preferences, leading to a degraded user experience and safety concerns due to drivers being distracted from the road while navigating to parking facilities.
Innovation Solution
A method that determines a vehicle's need to park, identifies nearby parking facilities with specific congestion levels, and selects a parking model based on these levels to recommend optimal parking spots, using historical search paths and machine-learning models to score candidate spots and provide navigation assistance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing simple parking location solutions are used, then device complexity is reduced, but parking spot recommendation accuracy deteriorates
Solution Approach 1:
The patent segments the parking recommendation system into multiple components: historical search path recording, machine learning model training, real-time candidate spot identification, and navigation guidance. This segmentation allows each component to be optimized independently while maintaining overall system accuracy without excessive complexity
Solution Approach 2:
The system performs preliminary actions by pre-training machine learning models using historical search path data before actual parking recommendations are needed. This pre-processing of data and model training enables accurate real-time recommendations without adding complexity to the moment-of-need decision process
2Loss of information
If drivers use displays to locate parking spots, then parking spot information is provided, but driver safety deteriorates due to distraction
Solution Approach 1:
The patent introduces an intermediary navigation system that provides directional guidance to parking spots rather than requiring drivers to study detailed parking facility maps on displays. This intermediary layer translates complex parking location information into simple navigation instructions, maintaining information provision while reducing driver distraction
Solution Approach 2:
The system replaces the mechanical interaction of drivers manually searching and selecting parking spots with automated machine learning-based candidate identification and ranking. This substitution removes the need for drivers to actively search through parking facility information, reducing distraction while maintaining full information availability
3Productivity
If drivers search for parking spots manually, then parking model complexity is reduced, but time consumption deteriorates
Solution Approach 1:
The patent implements self-service by enabling the system to automatically learn from historical search paths and independently generate parking recommendations without requiring manual driver input or complex real-time analysis. The machine learning model serves itself by continuously improving from accumulated data, enhancing productivity while managing complexity through automated learning rather than manual programming
Solution Approach 2:
The system incorporates feedback mechanisms where historical search path data is continuously fed back into the machine learning model to improve future recommendations. This feedback loop allows the system to automatically refine its parking spot identification accuracy over time, increasing productivity while the complexity is managed through iterative learning rather than complex rule-based systems
Data Source
AI summary
The disclosure describes a method for an ego vehicle. The method includes determining that a vehicle needs to park. The method further includes identifying a parking facility within proximity to the vehicle and a corresponding congestion level of the parking facility. The method further includes selecting a first parking model from two or more parking models based on the corresponding congestion level being closer to a first congestion range than a second congestion range. The method further includes identifying a parking spot for the vehicle within the parking facility based on the first parking model.