US 12,233,883 B1
Systems and methods for intelligently transforming data to generate improved output data using a probabilistic multi-application network
Michael Naoom, Columbus, OH (US); Michael Rortvedt, Madison, WI (US); and Trent Tinsley, Eureka, MO (US)
Assigned to CRAWFORD GROUP, INC., St. Louis, MO (US)
Filed by CRAWFORD GROUP, INC., St, Louis, MO (US)
Filed on Jun. 17, 2024, as Appl. No. 18/745,961.
Application 18/745,961 is a continuation of application No. 18/382,418, filed on Oct. 20, 2023, granted, now 12,012,110.
This patent is subject to a terminal disclaimer.
Int. Cl. B60W 40/12 (2012.01); G06N 5/02 (2023.01); G06N 7/01 (2023.01); H04W 4/44 (2018.01)
CPC B60W 40/12 (2013.01) [G06N 5/02 (2013.01); G06N 7/01 (2023.01); H04W 4/44 (2018.02); B60W 2556/10 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A method of transforming vehicle data using a probabilistic network and a knowledge base generated using historic vehicle data to generate improved vehicle output data, the method comprising:
receiving, at one or more first servers from a first computing device, first vehicle data, wherein the first vehicle data is associated with a first user and associated with a first vehicle associated with the first user;
generating, at the one or more first servers, in response to receiving, at the one or more first servers from the first computing device, the first vehicle data, a first computing object;
transmitting, from the one or more first servers to the first computing device, the first computing object;
receiving, at the one or more first servers from the first computing device, a first selection, wherein the first selection comprises a selection, by the first user, associated with the first computing object;
receiving, at the one or more first servers from the first computing device, second vehicle data, wherein the second vehicle data is associated with the first vehicle of the first user, and wherein the second vehicle data comprises a first image of the first vehicle from a first angle, wherein the second vehicle data indicates at least one characteristic resulting from an incident associated with the first vehicle, wherein the at least one characteristic resulting from the incident associated with the first vehicle is identifiable in the first image of the first vehicle from the first angle, wherein the second vehicle data is transformed at the one or more first servers, wherein transforming the second vehicle data comprises:
comparing, at the one or more first servers, the second vehicle data or the first vehicle data to the historic vehicle data, wherein the historic vehicle data is associated with one or more first data of the first vehicle data or one or more second data of the second vehicle data, and wherein comparing the second vehicle data or the first vehicle data to the historic vehicle data comprises:
generating or accessing, at the one or more first servers, a probabilistic network of the historic vehicle data, wherein the probabilistic network comprises a relationship between two or more third data of the historic vehicle data, wherein the relationship between the two or more third data of the historic vehicle data comprises one or more probabilities;
processing, using at least one processor at the one or more first servers, the historic vehicle data, using the probabilistic network, into processed historic vehicle data;
generating, using the at least one processor at the one or more first servers, one or more machine learning models for producing a knowledge base;
producing, using the at least one processor at the one or more first servers and the one or more machine learning models, the knowledge base, wherein the knowledge base is trained to recognize one or more patterns of the processed historic vehicle data; and
generating, using the at least one processor at the one or more first servers and the knowledge base, one or more data groups, wherein the one or more data groups are associated with at least one of the one or more patterns of the processed historic vehicle data, and wherein the one or more data groups are used to transform the second vehicle data and the first vehicle data, based on the associated at least one of the one or more patterns of the historic vehicle data, into modified vehicle data; and
transforming, using the at least one processor at the one or more first servers and the one or more data groups, the second vehicle data and the first vehicle data into the modified vehicle data, wherein the modified vehicle data is based on the historic vehicle data or the first vehicle data or the second vehicle data;
generating, at the one or more first servers, first vehicle output data, wherein the first vehicle output data is generated based in part on the modified vehicle data, and wherein the first vehicle output data comprises one or more first locations, and wherein the one or more first locations is based on one or more of a second location associated with the first user or the first computing device and a third location associated with a first user input, wherein the first user input is received, at the one or more first servers, from the first computing device; and
transmitting, from the one or more first servers to the first computing device, the first vehicle output data.