Ride Sharing Recommendation System Using Automated Trip Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current ride-sharing services face inefficiencies due to reliance on user-provided trip information, leading to inaccurate data and excessive computing resource usage, resulting in wasted time and resources, as users must actively search for matches and negotiate trip details, often resulting in unsuccessful matches.

Innovation Solution

A suggestion system that utilizes machine learning models to analyze driving data from vehicle devices to identify recurrent trips, calculate shared and unshared costs, and recommend ride-sharing opportunities based on accurate trip information, thereby reducing the need for user input and optimizing matching algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If user-provided trip information is used for ride matching, then the system can operate with minimal data collection, but the accuracy of trip information deteriorates and computing resources are wasted

Engineering Contradiction:

Improvetrip information accuracyVSAvoiddata collection system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The vehicle device automatically collects and provides trip information without requiring user input or manual data entry. The system uses the vehicle's own sensors and communication capabilities to gather accurate trip data, eliminating the need for users to manually provide information while reducing the burden on the matching system.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual user input mechanisms with automated vehicle device data collection. Instead of relying on users to manually enter trip information, the system uses automated sensors, GPS, and vehicle communication systems to automatically capture and transmit accurate trip data to the matching algorithm.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If users actively search for matches and negotiate trip details, then the system can handle complex matching requirements, but the time required for matching increases significantly

Engineering Contradiction:

Improvematch success rateVSAvoidmatching time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by automatically collecting and validating trip information from vehicle devices before the matching process begins. Accurate trip data is prepared in advance, allowing the matching algorithm to operate more efficiently without requiring users to manually search and negotiate during the matching process.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback mechanisms where the matching algorithm receives accurate trip information from vehicle devices and automatically adjusts matching decisions. The system continuously monitors trip status and provides real-time feedback to optimize matching, reducing the need for manual user intervention and negotiation.

Inventive Principle:

Principle #23Feedback

3Productivity

If more vehicles are used to ensure successful matches, then the availability of ride sharing increases, but fuel consumption and environmental impact increase

Engineering Contradiction:

Improveride sharing availabilityVSAvoidfuel consumption

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system changes the parameters used for matching by focusing on accurate trip information, trip compatibility, and cost calculations rather than simply increasing the number of available vehicles. By optimizing matching based on precise data about trip routes, times, and costs, the system maximizes ride sharing availability while minimizing the number of vehicles needed.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11803790B2Systems and methods for utilizing machine learning models to determine suggested ride sharing of vehicles

Publication Date: 2023.10.31 VERIZON CONNECT DEVELOPMENT LTD

AI summary

A device may generate a shortest path tree based on a passenger starting point identified in driving data. The device may generate a graph with a first layer and a second layer that correspond to the shortest path tree and may add paths from nodes in the first layer to corresponding nodes in the second layer. The device may identify a first shortest path that starts from a driver starting node in the first layer and ends at a passenger end node in the second layer and a second shortest path that starts from the passenger end node and ends at a driver end node in the second layer. The device may calculate a shared cost associated with the driver and the passenger sharing a ride based on the first shortest path and the second shortest path. The device may generate a recommendation based on the shared cost.