IP Library Granted Patent US 12,146,750
Granted Patent B2
US 12,146,750 · App. 17/851,577 · Granted Nov 19, 2024

Peer-to-peer ride-sourcing system

Inventor: Neda Masoud (Dexter, MI)
Assignee: The Regents of The University of Michigan
G01C21/3438G06Q10/047G06Q50/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,146,750
App. No.
17/851,577
Granted
Nov 19, 2024
Kind
B2
Abstract

A ride-sourcing method including receiving a plurality of ride-sourcing requests; grouping a first set of the plurality of ride-sourcing requests into a first cluster and a second set of the plurality of ride-sourcing requests into a second cluster; computing a tour formation for each of the first cluster and the second cluster to define a series of stations and a cost function; applying trips to the first cluster and the second cluster under uniformity constraints; repeating the computing and applying steps until the cost function between consecutive iterations is below a threshold to define a first cluster of trips and a second cluster of trips; and assigning the first cluster of trips to a first driver and the second cluster of trips to a second driver.

Claims (9)

1. A ride-sourcing method comprising:

a. at least one service provider receiving a plurality of ride-sourcing requests from at least one service recipient, each of the plurality of ride-sourcing requests comprising an origin, a destination, and a time window within which to start and end to define a trip;

b. grouping a first set of the plurality of ride-sourcing requests into a first cluster of trips and a second set of the plurality of ride-sourcing requests into a second cluster of trips;

c. computing a tour formation for each of the first cluster and the second cluster to define a series of stations and a cost function;

d. applying each of the trips to the first cluster and the second cluster under uniformity constraints to obtain approximately uniform clusters;

e. repeating steps c and d until the cost function between consecutive iterations is below a threshold to define a first cluster of trips and a second cluster of trips and performing dynamic re-optimization of steps c and d; and

f. assigning the first cluster of trips to a first driver and the second cluster of trips to a second driver.

2. The ride-sourcing method according to claim 1 wherein the step of grouping the first set of the plurality of ride-sourcing requests into the first cluster of trips and the second set of the plurality of ride-sourcing requests into the second cluster of trips comprises randomly grouping the first set of the plurality of ride-sourcing requests into the first cluster of trips and the second set of the plurality of ride-sourcing requests into the second cluster of trips.

3. The ride-sourcing method according to claim 1 wherein the step of assigning the first cluster of trips to the first driver and the second cluster of trips to the second driver comprises determining the average cost of driver-tour assignment.

Assignments (2)
CONFIRMATORY LICENSE Recorded Apr 7, 2025
From: UNIVERSITY OF MICHIGAN
To: NATIONAL SCIENCE FOUNDATION
Reel/Frame 070755/0505 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 13, 2022
From: MASOUD, NEDA
To: THE REGENTS OF THE UNIVERSITY OF MICHIGAN
Reel/Frame 060498/0156 →
Continuity (2)
Provisional Application 63216184 · Jun 29, 2021
Related Publication 20230019021A1 · Jan 19, 2023