US 11,941,546 B2
Method and system for generating an expert template
Scott Donnell, Phoenix, AZ (US); Travis Adams, Phoenix, AZ (US); and Chad Willardson, Phoenix, AZ (US)
Assigned to Gravystack, Inc., Phoenix, AZ (US)
Filed by Gravystack, Inc., Phoenix, AZ (US)
Filed on Jul. 25, 2022, as Appl. No. 17/872,982.
Prior Publication US 2024/0037428 A1, Feb. 1, 2024
Int. Cl. G06N 5/048 (2023.01); G06N 5/022 (2023.01); G06N 20/00 (2019.01); G06Q 50/10 (2012.01)
CPC G06N 5/048 (2013.01) [G06N 5/022 (2013.01); G06N 20/00 (2019.01); G06Q 50/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus for generating an expert template, the apparatus comprising:
at least a processor; and
a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor to:
receive user goal data relating to a user;
obtain expert data relating to an expert, wherein obtaining expert data comprises retrieving a plurality of expert data from at least a resource as a function of the user goal data, wherein retrieving the expert data comprises:
utilizing a web crawler to search a list of seed websites from an expert knowledge database;
spidering through each website of the list of seed websites through hyperlinks to find at least a new website to add to the expert knowledge database; and
adding the at least a new website to the expert knowledge database;
classify the user goal data to the expert, wherein classification of the user goal data to the expert further comprises:
iteratively training an expert classifier using training data which correlates expert knowledge data and the expert, including data generated by previous inputs and outputs by the expert classifier; and
classifying the user goal data set to the expert using the expert classifier;
produce an expert template; and
input the expert template to a matching classifier to obtain a match between the user and the expert, wherein obtaining a match further comprises:
iteratively training the matching classifier using training data with user goal and expert template as inputs to output a match between the user and the expert.