Intersection Location Selection for Transportation Requests
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional on-demand transportation network systems inflexibly determine locations for transportation requests, leading to inaccuracies and inefficiencies, particularly at intersections, resulting in increased cancelations and redundant requests due to their inability to account for navigation logistics and contextual information.
Innovation Solution
An intersection-location system that identifies and selects optimal pickup, drop-off, or waypoint locations at street intersections by comparing intersection-location attributes, such as predicted arrival times and navigation routes, to improve arrival times and reduce cancelations, utilizing machine learning models and objective functions to enhance request fulfillment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional GPS techniques are used to determine transportation locations, then the system can effectively determine GPS locations, but the accuracy of locations for pickups, drop offs, and other transportation events is limited because GPS data provides no context for determining where such transportation events are likely to occur at an intersection
Solution Approach 1:
The patent introduces map data as an intermediary between GPS location data and transportation event determination. The map data provides contextual information about intersections, sidewalks, and navigable areas, enabling the system to accurately determine where transportation events are likely to occur by combining GPS coordinates with geographic context.
Solution Approach 2:
The system changes the parameters used for location determination from raw GPS coordinates alone to a combination of GPS coordinates and map-derived contextual parameters. This includes determining whether a location is at an intersection, on a sidewalk, or in another navigable area, thereby improving location accuracy for transportation events.
2Adaptability or versatility
If conventional systems rigidly utilize a static computational model to select locations for transportation requests, then the system can uniformly identify pickup or drop-off locations, but the system cannot account for whether the location is at an intersection, on a particular side of a street, or has difficult-to-navigate geography
Solution Approach 1:
The patent replaces the static computational model with a dynamic system that adapts location selection based on real-time contextual factors. The system dynamically determines whether a location is at an intersection, on a specific side of the street, or has navigation challenges, and adjusts pickup/drop-off location recommendations accordingly.
Solution Approach 2:
The system applies different location selection criteria based on local geographic characteristics. Instead of using a uniform approach, it tailors the computational model to account for local conditions such as intersection geometry, sidewalk availability, and navigation difficulty at each specific location.
3Productivity
If conventional systems determine pickup or drop-off locations without consideration for navigation logistics, then the system can process requests efficiently, but the requested locations negatively impact the likelihood of request cancelations
Solution Approach 1:
The system performs preliminary analysis of navigation logistics before finalizing pickup and drop-off locations. By evaluating factors such as intersection accessibility, sidewalk proximity, and route complexity in advance, the system selects locations that minimize navigation difficulties and reduce the likelihood of request cancelations.
Solution Approach 2:
The system incorporates feedback from navigation logistics analysis into the location selection process. By continuously evaluating how requested locations impact navigation and cancellation likelihood, the system adjusts location recommendations to improve request fulfillment reliability while maintaining processing efficiency.
Data Source
AI summary
This disclosure describes an intersection-location system that can identify a street intersection indicated by a transportation request and select an event location at the street intersection based on intersection-location attributes. For example, the disclosed systems can receive a transportation request identifying a requested location at a street intersection and compare various candidate designated locations at the intersection as potential pickup, drop-off, or waypoint locations. The disclosed systems can compare intersection-location attributes for the different candidate designated locations by comparing predicted arrival times or predicted routes of different transportation providers at (or from) the candidate designated locations. The disclosed systems can further select a designated pickup, drop-off, or waypoint location from among the candidate designated locations for a transportation route based on the transportation request. Upon selecting the designated location, the disclosed systems can provide the designated location for display on one or more client devices.