Systems and methods for matching transportation requests over extended batching windows

Patent metadata

Field	Value
Publication number	US-11625652-B2
Application number	US-201816024349-A
Country	US
Kind code	B2
Filing date	Jun 29, 2018
Priority date	Jun 29, 2018
Publication date	Apr 11, 2023
Grant date	Apr 11, 2023

Abstract

The disclosed computer-implemented method may include matching transportation requests. By collecting and batching match requests over an extended period, a dynamic transportation matching system may identify more efficient matches (e.g., may match transportation requests with greater overlaps). In addition, by dynamically setting and/or extending the upper bound of time that a transportation request may remain batched with other transportation requests, the dynamic transportation matching system may account for contextual information thereby situationally improving matching efficiencies made possible with higher upper bounds while avoiding requestor dissatisfaction, lost conversions, or other inefficiencies that may result from upper bounds that are too high. Furthermore, by providing a notification interface for a transportation requestor device that notifies the requestor when to be ready, a transportation matching application may provide a positive requestor experience while allowing for longer match windows. Various other methods, systems, and computer-readable media are also disclosed.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving, by a dynamic transportation matching system, at least a first transport request and a second transport request;
entering the first transport request and one or more other transport requests including the second transport request into a batch of transport requests;
evaluating, by the dynamic transportation matching system, a fitness of matching the first transport request with the one or more other transport requests including the second transport request to be completed by a transport provider, wherein the matching is subject to one or more matching criteria set at a minimum matching threshold;
determining an elasticity associated with the first transport request, wherein the elasticity indicates a measure of sensitivity to a cost associated with the first transport request;
determining an upper bound for an amount of time based on characteristics of the first transport request including the determined elasticity, a probability that a transport requestor associated with the first transport request will cancel the first transport request as a function of time after the transport requestor has submitted the first transport request, and contextual conditions in which the first transport request was submitted, wherein the upper bound for the amount of time is to monitor the batch of transport requests for potential alternative matchings involving the first transport request that have a greater fitness than the fitness of matching the first transport request with at least one of the other transport requests including the second transport request;
monitoring, by the computer, the batch of transport requests in response to determining the upper bound amount of time; and
matching a provider computing device associated with the transport provider with the first transport request and with the second transport request based at least in part on: the evaluated fitness of matching the first transport request with the second transport request, and on a constraint to match the first transport request within the upper bound.

2. The computer-implemented method of claim 1 , further comprising sending, by the dynamic transportation matching system to a transportation requestor device corresponding to the first transport request, an instruction for the transportation requestor device to provide a notification to a transportation requestor in possession of the transportation requestor device based on a proximity of the transport provider to the transportation requestor.

3. The computer-implemented method of claim 2 , wherein the notification to the transportation requestor comprises an earliest notification to the transportation requestor of the first transport request being matched with the transport provider.

4. The computer-implemented method of claim 2 , wherein providing the notification to the transportation requestor is further based on a distance of the transportation requestor from a meeting location for the transport provider and the transportation requestor.

5. The computer-implemented method of claim 2 , wherein the notification comprises a vibration of the transportation requestor device.

6. The computer-implemented method of claim 2 , wherein the transportation requestor device further displays an initial notification to the transportation requestor, after submitting the first transport request and before receiving information indicating that the first transport request has been matched with a transport provider, the initial notification instructing the transportation requestor to expect a non-visual notification.

7. The computer-implemented method of claim 1 , wherein matching the first transport request with the second transport request based at least in part on the upper bound comprises:
determining a current proximity to the upper bound;
determining, based at least in part on the current proximity to the upper bound, a fitness threshold for accepting a candidate matching involving the first transport request; and
determining that the fitness of matching the first transport request with the second transport request exceeds the fitness threshold.

8. The computer-implemented method of claim 1 , wherein matching the first transport request with the second transport request is further based at least in part on at least one of:
evaluating a fitness of matching the first transport request with an alternative transport request; and
evaluating a fitness of matching the second transport request with an alternative transport request.

9. The computer-implemented method of claim 1 , wherein the characteristics of the first transport request comprises a geographical region to which the first transport request pertains.

10. The computer-implemented method of claim 9 , wherein the characteristics of the first transport request comprises at least one of:
an amount of transportation requested within a dynamic transportation network within the geographical region; and
an availability of transportation providers within the dynamic transportation network to provide transportation within the geographical region.

11. The computer-implemented method of claim 1 , wherein the characteristics of the first transport request comprises an elasticity associated with the first transport request, and wherein the elasticity associated with the first transport request is determined based on historical data indicating the elasticity of past transportation demand or based on requestor-supplied preference data indicating price elasticity preferences of the transport requestor.

12. The computer-implemented method of claim 1 , wherein determining, the upper bound comprises:
identifying the characteristics of the first transport request upon receiving the first transport request;
determining the probability that the transport requestor will cancel the first transport request as a function of time after submitting the first transport request upon receiving the first transport request;
analyzing the contextual conditions in which the first transport request was submitted upon receiving the first transport request; and
setting the upper bound upon receiving the first transport request based on the characteristics, the determined probability, and the contextual conditions.

13. The computer-implemented method of claim 1 , wherein determining, based at least in part on the characteristics of the first transport request, the upper bound comprises dynamically adjusting the upper bound based at least in part on a change to the contextual conditions that impacts an expected fitness of potential future matchings involving the first transport request in light of the characteristics.

14. The computer-implemented method of claim 1 , wherein determining the upper bound further comprises:
simulating a plurality of matching scenarios;
applying a plurality of differing upper bounds for waiting for alternative matchings within to the plurality of matching scenarios;
evaluating outcomes of applying each of the plurality of differing upper bounds to the plurality of matching scenarios; and
selecting the upper bound based at least in part on evaluating the outcomes of applying each of the plurality of differing upper bounds to the plurality of matching scenarios in light of the characteristics, the determined probability related to the transport requestor, and the contextual conditions.

15. The computer-implemented method of claim 1 , wherein the upper bound is at least two minutes.

16. The computer-implemented method of claim 1 , wherein determining the upper bound f

Assignees

• Lyft Inc

Inventors

• Tsur Orit Balicer
• Chang Vincent Chih-Jye
• Levi Dor
• Lorenzo Molly Angelica Ingles
• Puranmalka Keshav
• Selvam Krishna Kumar

Classifications

• G06Q2240/00

  Transportation facility access, e.g. fares, tolls or parking · CPC title

• G06Q10/0631 Primary

  Resource planning, allocation, distributing or scheduling for enterprises or organisations · CPC title