US 12,071,146 B2
Systems and methods of determining effectiveness of vehicle safety features
Alexander Cardona, Gilbert, AZ (US); David Dohrmann, Mesa, AZ (US); Tim G. Sanidas, Bloomington, IL (US); Jaime Skaggs, Chenoa, IL (US); Pamela Rearden, Bloomington, IL (US); Timothy J. Nickel, Bloomington, IL (US); Thomas Hilton Jannusch, McLean, IL (US); James P. Rodriguez, Avondale, AZ (US); Scott T. Christensen, Salem, OR (US); and Karthikeyan Srinivasan, Phoenix, AZ (US)
Assigned to STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed by STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed on Apr. 20, 2023, as Appl. No. 18/137,297.
Application 18/137,297 is a continuation of application No. 16/928,793, filed on Jul. 14, 2020, granted, now 11,661,072.
Claims priority of provisional application 62/935,890, filed on Nov. 15, 2019.
Claims priority of provisional application 62/905,742, filed on Sep. 25, 2019.
Claims priority of provisional application 62/879,130, filed on Jul. 26, 2019.
Claims priority of provisional application 62/874,749, filed on Jul. 16, 2019.
Prior Publication US 2023/0249697 A1, Aug. 10, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. B60W 50/00 (2006.01); G06N 20/00 (2019.01); G06Q 40/08 (2012.01); G07C 5/02 (2006.01)
CPC B60W 50/0098 (2013.01) [G06N 20/00 (2019.01); G06Q 40/08 (2013.01); G07C 5/02 (2013.01); B60W 2050/0083 (2013.01); B60W 2556/55 (2020.02)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining an effectiveness of vehicle safety features, the method comprising:
analyzing, by a processor, vehicle build information for a plurality of vehicles manufactured by a plurality of original equipment manufacturers (OEMs), the vehicle build information containing OEM-specific terminology associated with one or more safety features associated with each vehicle, to train a machine learning model mapping each safety feature to any OEM-specific terminology associated with the safety feature for each OEM;
applying, by the processor, the trained machine learning model to the vehicle build information to generate translated vehicle build information for each of the plurality of vehicles, such that the OEM-specific terminology associated with each safety feature is replaced with OEM-agnostic terminology for the safety feature; and
calculating, by the processor, using the OEM-agnostic terminology for each safety feature associated with each of the plurality of vehicles and vehicle accident record information for each of the plurality of vehicles, an effectiveness score associated with each safety feature.