US 12,125,002 B2
Systems and methods of determining vehicle reparability
Jody Ann Thoele, Bloomington, IL (US); Jaime Skaggs, Chenoa, IL (US); Scott Thomas Christensen, Salem, OR (US); Ashish Sawhney, Bloomington, IL (US); Neill Broadstone, Bloomington, IL (US); Angela Glusick, Bloomington, IL (US); and Gustufus Phillip Theofanis, Indianapolis, IN (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 Feb. 16, 2022, as Appl. No. 17/673,171.
Claims priority of provisional application 63/279,045, filed on Nov. 12, 2021.
Prior Publication US 2023/0153766 A1, May 18, 2023
Int. Cl. G06Q 10/20 (2023.01); G06N 20/00 (2019.01); G06Q 30/0283 (2023.01); G06Q 40/08 (2012.01)
CPC G06Q 10/20 (2013.01) [G06N 20/00 (2019.01); G06Q 30/0283 (2013.01); G06Q 40/08 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method for use in determining reparability of a vehicle, the method comprising:
obtaining, by one or more processors, vehicle data from a vehicle data repository, the vehicle data comprising vehicle parts data including parts repair cost information, and the vehicle data being stored in an original equipment manufacturer (OEM)—agnostic terminology;
generating, by the one or more processors, a list of variables from the vehicle data;
training, by the one or more processors, a machine learning algorithm to generate a reparability metric by:
inputting variables of the list of variables into the machine learning algorithm;
for each inputted variable, generating a correlation metric between the inputted variable and a cost to repair the vehicle;
for each generated correlation metric, determining if the generated correlation metric is below a correlation metric threshold;
in response to determining that a generated correlation metric is below the correlation metric threshold, removing the variable corresponding to the generated correlation metric from consideration by the machine learning algorithm;
training the machine learning algorithm based upon variables not removed from consideration by the machine learning algorithm; and
further training the machine learning algorithm by re-running the machine learning algorithm; and
inputting, by the one or more processors, information of a particular part into the trained machine learning algorithm to generate a reparability metric for the particular part.