US 12,131,277 B2
System and method of predicting a repair project
Garen W. Armstrong, Overland Park, KS (US); Paul M. Payne, Denver, CO (US); and Shae M. Adams, Lake Worth, FL (US)
Assigned to Smart Media LLC, Denison, TX (US)
Filed by Smart Media LLC, Denison, TX (US)
Filed on May 10, 2023, as Appl. No. 18/195,584.
Claims priority of provisional application 63/340,136, filed on May 10, 2022.
Prior Publication US 2023/0368095 A1, Nov. 16, 2023
Int. Cl. G06Q 10/0631 (2023.01); G06Q 10/0875 (2023.01); G06Q 10/10 (2023.01); G06Q 30/0202 (2023.01); G06Q 30/0204 (2023.01); G06Q 40/08 (2012.01)
CPC G06Q 10/06313 (2013.01) [G06Q 10/063118 (2013.01); G06Q 10/0875 (2013.01); G06Q 10/103 (2013.01); G06Q 30/0202 (2013.01); G06Q 30/0205 (2013.01); G06Q 40/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for predicting repair projects, comprising:
training a first machine learning model to determine likelihoods of roofs requiring repairs for predicting an associated materials need for future roof repairs in a geographic region using a first training data set that comprises historical repair data and historical weather forecasting data; receiving, by the first machine learning model, current weather forecasting data indicative of a future weather event in the geographic region and aerial imagery of a plurality of homes in the geographic region; determining, by the first machine learning model and based on the current weather forecasting data and the aerial imagery, a likelihood of a roof requiring a repair for each of the plurality of homes in the geographic region to obtain a plurality of likelihoods: thresholding the plurality of likelihoods to identify a subset of the plurality of homes; and for each home of the subset of the plurality of homes having a lead likelihood above a threshold, preemptively determining needed materials for the repairs, wherein preemptively determining the needed materials comprises: obtaining, from a building dimensions database, dimensional data for each home; obtaining, from at least one materials database, materials data for each home, the materials data including at least a material type; and determining a needed materials type and a needed materials quantity based on analyzing the materials data and the dimensional data.