Systems and methods for generating dynamic transit routes

Patent metadata

Field	Value
Publication number	US-12422264-B2
Application number	US-202418662733-A
Country	US
Kind code	B2
Filing date	May 13, 2024
Priority date	Mar 4, 2020
Publication date	Sep 23, 2025
Grant date	Sep 23, 2025

Abstract

A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations: building, using a machine learning algorithm, a transit model based at least in part upon telematics data associated with a user; generating, based at least in part upon the transit model, a dynamic transit route for the user; calculating, based at least in part upon the telematics data associated with the user, a potential benefit comprising an amount of fuel cost savings for the user, reduced travel time for the user, insurance savings, or environmental pollution reduction for the user; generating a notification comprising the dynamic transit route and the potential benefit; and transmitting the notification to a mobile device of the user. Other embodiments are described.

First claim

What is claimed:

1. A transit analytics (TA) computing device comprising:
at least one processor; and
at least one non-transitory computer-readable media, storing computing instructions that, when executed on the at least one processor, cause the at least one processor to perform operations comprising:
building, using a machine learning algorithm, a transit model based at least in part upon telematics data associated with a user;
generating, based at least in part upon the transit model, a dynamic transit route for the user;
calculating, based at least in part upon the telematics data associated with the user, a potential benefit comprising an amount of fuel cost savings for the user, reduced travel time for the user, insurance savings, or environmental pollution reduction for the user when the user uses the dynamic transit route compared to a different route;
transmitting a notification comprising the dynamic transit route and the potential benefit to a mobile device of the user;
receiving a response message from the mobile device of the user, wherein the response message includes an indicator that the user accepts or declines the dynamic transit route;
when the indicator comprises the user declining the dynamic transit route, modifying the dynamic transit route;
and
when the indicator comprises the user accepting the dynamic transit route, transmitting the dynamic transit route to a transit vehicle computing device associated with an autonomous vehicle, wherein the autonomous vehicle is configured to autonomously implement the dynamic transit route.

2. The TA computing device of claim 1 , wherein building the transit model further comprises:
generating transit predictions based upon calendar data of the mobile device of the user.

3. The TA computing device of claim 1 , wherein the operations further comprise:
after building the transit model, receiving additional telematics data associated with the user; and
updating the transit model based upon the additional telematics data.

4. The TA computing device of claim 1 , wherein the operations further comprise:
characterizing transportation patterns of behavior of the user comprising at least one of: frequent times of travel, frequent origin locations, frequent destination locations, or frequent routes of travel.

5. The TA computing device of claim 1 , wherein generating the dynamic transit route further comprises:
generating multiple transit predictions of one or more daily commutes taken by one or more groups with one or more respective users in a geographic area, wherein the dynamic transit route corresponds to at least one of: an average proximity to a pick-up location, an average proximity to a drop-off location, a maximum passenger capacity for each autonomous vehicle implementing the dynamic transit route, as modified, or traffic congestion.

6. The TA computing device of claim 1 , wherein the operations further comprise:
calculating an amount of risk associated with one or more trips taken by the user based on: a predicted number of trips using one or more dynamic transit routes over a period of time, or a number of confirmed trips using the one or more dynamic transit routes over the period of time.

7. The TA computing device of claim 1 , wherein the operations further comprise:
connecting to the transit vehicle computing device associated with the autonomous vehicle.

8. A computer-implemented method implemented via execution of computing instructions configured to run on one or more processors and stored at one or more non-transitory media, the computer-implemented method comprising:
building, using a machine learning algorithm, a transit model based at least in part upon telematics data associated with a user;
generating, based at least in part upon the transit model, a dynamic transit route for the user;
calculating, based at least in part upon the telematics data associated with the user, a potential benefit comprising an amount of fuel cost savings for the user, reduced travel time for the user, insurance savings, or environmental pollution reduction for the user when the user uses the dynamic transit route compared to a different route;
transmitting a notification comprising the dynamic transit route and the potential benefit to a mobile device of the user;
receiving a response message from the mobile device of the user, wherein the response message includes an indicator that the user accepts or declines the dynamic transit route;
when the indicator comprises the user declining the dynamic transit route, modifying the dynamic transit route;
and
when the indicator comprises the user accepting the dynamic transit route, transmitting the dynamic transit route to a transit vehicle computing device associated with an autonomous vehicle, wherein the autonomous vehicle is configured to autonomously implement the dynamic transit route.

9. The computer-implemented method of claim 8 , wherein building the transit model further comprises:
generating transit predictions based upon calendar data of the mobile device of the user.

10. The computer-implemented method of claim 8 further comprising:
after building the transit model, receiving additional telematics data associated with the user; and
updating the transit model based upon the additional telematics data.

11. The computer-implemented method of claim 8 further comprising:
characterizing transportation patterns of behavior of the user comprising at least one of: frequent times of travel, frequent origin locations, frequent destination locations, or frequent routes of travel.

12. The computer-implemented method of claim 8 , wherein generating the dynamic transit route further comprises:
generating multiple transit predictions of one or more daily commutes taken by one or more groups with one or more respective users in a geographic area, wherein the dynamic transit route corresponds to at least one of: an average proximity to a pick-up location, an average proximity to a drop-off location, a maximum passenger capacity for each autonomous vehicle implementing the dynamic transit route, as modified, or traffic congestion.

13. The computer-implemented method of claim 8 further comprising:
calculating an amount of risk associated with one or more trips taken by the user based on: a predicted number of trips using one or more dynamic transit routes over a period of time, or a number of confirmed trips using the one or more dynamic transit routes over the period of time.

14. The computer-implemented method of claim 8 further comprising:
connecting to the transit vehicle computing device associated with the autonomous vehicle.

15. A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising:
building, using a machine learning algorithm, a transit model based at least in part upon telematics data associated with a user;
generating, based at least in part upon the transit model, a dynamic transit route for the user;
calculating, based at least in part upon the telematics data associated with the user, a potential benefit comprising an amount of fuel cost savings for the user, reduced travel time for the user, insurance savings, or environmental pollution reduction for the user when the user uses the dynamic transit route compared to a different route;
transmitting a notification comprising the dynamic transit route and the potential benefit to a mobile device of the user;
receiving a

Assignees

• Blueowl Llc
• Quanata Llc

Inventors

• Sanchez Kenneth Jason
• Leung Theobolt N
• Piontkowski Mary
• Smith Bennett

Classifications

• G05D1/81

  Handing over between on-board automatic and on-board manual control · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G01C21/3415

  Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title