Systems and methods for improving driver safety using uplift modeling

Patent metadata

Field	Value
Publication number	US-12567339-B2
Application number	US-202218084899-A
Country	US
Kind code	B2
Filing date	Dec 20, 2022
Priority date	Nov 27, 2017
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

Methods and systems for improving vehicular safety by utilizing uplift modeling techniques to improve a driving tip treatment generation model are provided. According to embodiments, a tip server can analyze telematics data associated with operation of one or more vehicles to determine that a driving tip should be provided to a driver of a vehicle. The tip server then utilize a treatment generation model to determine a treatment for how to provide the driving tip in a manner optimized for the particular driver. The tip server can analyze additional telematics data to determine an effectiveness of the driving tip and to update the treatment generation model in accordance with uplift modeling techniques.

First claim

We claim:

1 . A computer implemented method comprising:
receiving, by one or more processors, a first set of telematics data collected by one or more sensors associated with a vehicle driven by a driver; analyzing, by the one or more processors, the first set of telematics data to determine a driving tip to be provided to the driver; generating, by the one or more processors, a treatment for providing the driving tip to the driver, the treatment being generated using a treatment generation model and including a plurality of treatment facets;
wherein the treatment generation model includes a plurality of options for each treatment facet of the plurality of treatment facets;
wherein the treatment generation model determines a set of drivers having similar characteristics as the driver; and
wherein the treatment generation model selects an option of the plurality of options for each treatment facet of the plurality of treatment facets by applying uplift modeling techniques and by combining (i) a respective weight associated with the option based upon an effectiveness of the option for drivers within the set of drivers, and (ii) a respective confidence score associated with the option based upon a sample size of treatments containing the option provided to the drivers within the set of drivers;
providing, by the one or more processors, the driving tip to the driver in accordance with the treatment; receiving, by the one or more processors, a second set of telematics data collected by the one or more sensors after providing the driving tip; determining, by the one or more processors, whether the driver complied with the driving tip based on the second set of telematics data; and updating, by the one or more processors, the treatment generation model by adjusting the respective weight and the respective confidence score associated with the option, as selected, for each treatment facet of the plurality of treatment facets utilized in the treatment to personalize future treatments for the driver.

2 . The computer implemented method of claim 1 , wherein:
the treatment generation model includes a plurality of possible channels of delivery, timings of delivery, and tip contents; and the treatment generation model associates each of the plurality of possible channels of delivery, timings of delivery, and tip contents with an initial score.

3 . The computer implemented method of claim 2 , further comprising:
determining, by the one or more processors, the initial score for each of the plurality of possible channels of delivery, timings of delivery, and tip contents based upon demographic data of the driver and an effectiveness of each of the plurality of possible channels of delivery, timings of delivery, and tip contents for other drivers having similar demographic data.

4 . The computer implemented method of claim 3 , wherein the other drivers having similar demographic data are located within a geographic range of the driver.

5 . The computer implemented method of claim 2 , wherein:
the treatment generation model associates each of the plurality of possible channels of delivery, timings of delivery, and tip contents with a corresponding confidence level based upon a corresponding sample size associated with a number of treatments having at least one of the plurality of possible channels of delivery, timings of delivery, or tip contents provided to other drivers having similar demographic data as the driver.

6 . The computer implemented method of claim 5 , wherein generating the treatment comprises:
assigning, by the one or more processors, weights to the plurality of possible channels of delivery, timings of delivery, and tip contents based upon respective initial scores and confidence levels; and selecting, by the one or more processors, a channel of delivery, a timing of delivery, and a tip content based upon the weights and the confidence levels, as assigned.

7 . The computer implemented method of claim 1 , wherein updating the treatment generation model comprises, when the driver complied with the driving tip:
increasing, by the one or more processors, the respective weight and the respective confidence score associated with the option, as selected, for each treatment facet of the plurality of treatment facets utilized in the treatment.

8 . The computer implemented method of claim 1 , wherein updating the treatment generation model comprises, when the driver did not comply with the driving tip:
decreasing, by the one or more processors, the respective weight and the respective confidence score associated with the option, as selected, for each treatment facet of the plurality of treatment facets utilized in the treatment.

9 . A computer system comprising:
one or more sensors associated with a vehicle; one or more processors; one or more transceivers adapted to communicate with the vehicle driven by a driver; a non-transitory program memory coupled to the one or more processors and storing executable instructions that, when executed by the one or more processors, cause the computer system to:
receive, via the one or more sensors, a first set of telematics data associated with the vehicle;
analyze the first set of telematics data to determine a driving tip to be provided to the driver;
generate, using a treatment generation model, a treatment for providing the driving tip to the driver, the treatment including a plurality of treatment facets;
wherein the treatment generation model includes a plurality of options for each treatment facet of the plurality of treatment facets;
wherein the treatment generation model determines a set of drivers having similar characteristics as the driver; and
wherein the treatment generation model selects an option of the plurality of options for each treatment facet of the plurality of treatment facets by applying uplift modeling techniques and by combining (i) a respective weight associated with the option based upon an effectiveness of the option for drivers within the set of drivers, and (ii) a respective confidence score associated with the option based upon a sample size of treatments containing the option provided to the drivers within the set of drivers;

provide, by the one or more processors, the driving tip to the driver in accordance with the treatment;
receive, by the one or more processors, a second set of telematics data collected by the one or more sensors after providing the driving tip;
determine, by the one or more processors, whether the driver complied with the driving tip based on the second set of telematics data; and
update, by the one or more processors, the treatment generation model by adjusting the respective weight and the respective confidence score associated with the option, as selected, for each treatment facet of the plurality of treatment facets utilized in the treatment to personalize future treatments for the driver.

10 . The computer system of claim 9 , wherein:
the treatment generation model includes a plurality of possible channels of delivery, timings of delivery, and tip contents; and the treatment generation model associates each of the plurality of possible channels of delivery, timings of delivery, and tip contents with an initial score.

11 . The computer system of claim 10 , wherein the instructions, when executed by the one or more processors, further cause the computer system to:
determine the initial score for each of the plurality of possible channels of delivery, timings of delivery, and tip contents based upon demographic data of the driver and an effectiveness of each of the plurality of possible channels of delivery, timings of delivery, and tip contents f

Assignees

• Quanata Llc

Inventors

• Sanchez Kenneth J
• Konrardy Blake
• Dahl Eric
• Shimer Aaron
• Russo Micah Wind
• Leung Theobolt N

Classifications

• B60G9/00

  Resilient suspensions of a rigid axle or axle housing for two or more wheels {(the axle being a part of a set of tandem axles B60G5/00-B60G5/065; with leaf springs B60G11/02-B60G11/08)} · CPC title

• B60K35/22

  Display screens · CPC title

• B60K35/10

  Input arrangements, i.e. from user to vehicle, associated with vehicle functions or specially adapted therefor · CPC title

• G06Q40/08

  Insurance · CPC title

• G09B9/04

  for teaching control of land vehicles · CPC title