US 12,282,327 B2
Data processing system with machine learning engine for providing driving data analysis and vehicle control functions
Neal Edgar Coleman, II, Evanston, IL (US); and Matthew Davis Best, Chicago, IL (US)
Assigned to Allstate Insurance Company, Northbrook, IL (US)
Filed by Allstate Insurance Company, Northbrook, IL (US)
Filed on Oct. 2, 2017, as Appl. No. 15/722,134.
Prior Publication US 2019/0101914 A1, Apr. 4, 2019
Int. Cl. G05D 1/00 (2024.01); B60W 30/00 (2006.01); G06N 20/00 (2019.01); G08G 1/01 (2006.01); G08G 1/0967 (2006.01)
CPC G05D 1/0055 (2013.01) [B60W 30/00 (2013.01); G08G 1/0104 (2013.01); G08G 1/0112 (2013.01); G08G 1/012 (2013.01); G08G 1/0129 (2013.01); G08G 1/0145 (2013.01); G08G 1/096725 (2013.01); G08G 1/096741 (2013.01); G08G 1/096775 (2013.01); G06N 20/00 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A computing platform comprising:
at least one processor;
a communication interface in communication with the at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
receive, from a mobile device of a driver in a first vehicle, driving data associated with the first vehicle, the driving data including trip data gathered by one or more sensors associated with the mobile device during a trip associated with the trip data and the first vehicle;
receive external data from one or more data sources, the external data including policy data associated with the first vehicle;
segment the trip data gathered by the mobile device into a plurality of segments based on the first vehicle stopping for a threshold time period;
identify a driving behavior within the driving data separately for each of the plurality of segments;
determine, based on a plurality of machine learning datasets, a ride performance characteristic associated with each of the plurality of segments of the driving data, the ride performance characteristic including at least a quantified level of smoothness associated with each of the plurality of segments of the driving data, wherein the plurality of machine learning datasets is generated using the external data;
generate, based on the ride performance characteristic, an output of safe or unsafe associated with each of the plurality of segments of the driving data,
wherein for each of the plurality of segments, when the output of safe is generated, generate, based on the associated ride performance characteristic, a first instruction for a second vehicle, wherein the first instruction includes a modification to an operational instruction of the second vehicle, and
wherein for each of the plurality of segments, when the output of unsafe is generated,
generate, based on the associated ride performance characteristic, a second instruction, different from the first instruction, for the second vehicle, wherein the second instruction includes a modification to an operational instruction of the second vehicle, and
transmit a notification to the mobile device of the driver;
transmit at least one of the first instruction or the second instruction to the second vehicle, wherein the second vehicle is an autonomous or semi-autonomous vehicle;
cause at least one operational instruction associated with the second vehicle to be modified based on the at least one of the first instruction or the second instruction; and
update the plurality of machine learning datasets using the at least one of the first instruction or the second instruction.