US 11,948,220 B2
Systems and methods for dynamically selecting transportation options based on transportation network conditions
Abhinav Amrut Vora, San Francisco, CA (US); Hao Yu Liu, Union City, CA (US); Benjamin Han, San Francisco, CA (US); Julia Yu, San Francisco, CA (US); Le Guan, San Francisco, CA (US); Xiaoyuan Xu, San Mateo, CA (US); Mayank Gulati, San Francisco, CA (US); Charles Parker Spielman, San Francisco, CA (US); Chirag Chhagan Chheda, San Francisco, CA (US); and David Chouinard, San Francisco, CA (US)
Assigned to Lyft, Inc., San Francisco, CA (US)
Filed by Lyft, Inc., San Francisco, CA (US)
Filed on Dec. 21, 2021, as Appl. No. 17/557,994.
Application 17/557,994 is a continuation of application No. 16/207,004, filed on Nov. 30, 2018, granted, now 11,238,555.
Prior Publication US 2022/0164914 A1, May 26, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/06 (2023.01); G06Q 10/0631 (2023.01); G06Q 50/30 (2012.01)
CPC G06Q 50/30 (2013.01) [G06Q 10/063114 (2013.01); G06Q 10/06315 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
determining that a transportation requester device has initiated a session with a dynamic transportation network;
prior to receiving a request for transportation via the dynamic transportation network, determining a current state of a plurality of different transportation provider options within a specific distance of the transportation requester device;
identifying, based at least in part on the determined current state of the different transportation provider options, which transportation provider options are available for the transportation requester device;
training a neural network in a first stage using a first set of training data representing different types of transportation provider options that are available through the dynamic transportation network;
training the neural network in a second stage using a second set of training data representing the ranking factors for the different transportation provider options, such that the neural network is trained to dynamically rank the available transportation provider options according to the ranking factors;
ranking, by the trained neural network, the available transportation provider options according to one or more ranking factors, wherein the ranking factors are specific to each type of transportation provider option; and
sending, to the transportation requester device for display on the transportation requester device, the ranked list of available transportation provider options.