Machine Learning Model for Automated Parking Restriction Data Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for populating geographic databases with parking restriction data are manual and resource-intensive, resulting in incomplete coverage, as only a fraction of road links are labeled, making it costly and time-consuming to maintain accurate data.
Innovation Solution
A machine learning model is trained using classification features such as functional class and historical parking availability to automatically label road links with parking restriction data, reducing the need for manual input and increasing data coverage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual methods are used to populate geographic database with parking restriction data, then data accuracy can be maintained, but the process is resource-intensive and time-consuming, resulting in incomplete coverage of road links
Solution Approach 1:
The patent replaces manual mechanical labeling processes with an automated machine learning system. The ML model processes road link features (functional class, historical parking availability) to automatically generate parking restriction labels, eliminating the need for manual data entry while maintaining accuracy through trained classification algorithms
Solution Approach 2:
The system enables the geographic database to self-populate parking restriction data through automated ML processing. The model uses existing road link features and historical data to generate labels independently, reducing reliance on external manual input while improving coverage efficiency
2Quantity of substance
If manual labeling of road links is performed, then parking restriction data can be obtained, but the process requires significant human resources and time
Solution Approach 1:
The patent substitutes manual labeling operations with automated machine learning processing. The ML model rapidly processes multiple road links simultaneously using classification features, generating parking restriction labels without human intervention and dramatically reducing the time required to populate the geographic database
Solution Approach 2:
The system performs preliminary automated labeling using the ML model before any manual verification. By pre-generating labels for all road links based on available features and historical data, the system eliminates the need for sequential manual processing, significantly accelerating data availability
3Use of energy by moving object
If only a fraction of road links are manually labeled, then resource consumption is reduced, but the geographic database has incomplete parking restriction coverage
Solution Approach 1:
The patent creates a universal ML-based labeling system that can process all road links regardless of their specific characteristics. The model uses functional class and historical parking availability features that apply across diverse road types, enabling consistent automated labeling throughout the entire geographic database without requiring separate manual processes for different road categories
Solution Approach 2:
The system replaces selective manual labeling with comprehensive automated ML processing. The machine learning model efficiently processes all road links using available features, generating parking restriction labels at scale without the resource constraints of manual methods, thereby completing the previously missing data coverage
Data Source
AI summary
An approach is provided for generating parking restriction data using a machine learning model. The approach involves determining a plurality of classification features associated with a set of labeled road links. Each of the labeled road links is labeled with a parking restriction label that indicates a parking restriction status of said each of the labeled road links. The approach also involves training the machine learning model to classify an unlabeled road link of the geographic database using the plurality of classification features. The approach further involves determining the plurality of classification features for the unlabeled road link. The approach further involves processing the plurality of classification features for the unlabeled road link using the trained machine learning model to associate an assigned parking restriction label to the unlabeled road link. The approach further involves storing the assigned parking restriction label as the parking restriction data.