US 12,265,448 B2
Apparatus and method for data fault detection and repair
Christopher Turner, Dover, DE (US)
Assigned to EmergIP, LLC, Dover, DE (US)
Filed by EmergIP, LLC, Dover, DE (US)
Filed on Apr. 21, 2023, as Appl. No. 18/137,682.
Prior Publication US 2024/0354185 A1, Oct. 24, 2024
Int. Cl. G06F 11/07 (2006.01); G06F 16/23 (2019.01); G16H 10/60 (2018.01)
CPC G06F 11/0793 (2013.01) [G06F 11/0721 (2013.01); G06F 11/0775 (2013.01); G06F 16/2365 (2019.01); G16H 10/60 (2018.01)] 18 Claims
OG exemplary drawing
 
1. An apparatus for data fault detection and repair, wherein the apparatus comprises:
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 a user profile relating to a user, wherein the user profile comprises provider data of the user;
generate practitioner data as a function of the user profile, wherein the practitioner data comprises procedure data and a cost of medical transportation;
identify remittance data as a function of the practitioner data, wherein identifying the remittance data comprises:
generating a financial responsibility identification, wherein generating the financial responsibility identification includes comparing the provider data of the user to the practitioner data; and
identifying at least a data category code assigned to the user;
identify at least one data fault in the remittance data, wherein identifying the data fault comprises comparing the procedure data to the at least a data category code;
generate a data fault rank for the at least one data fault as a function of the cost of medical transportation, wherein generating the data fault rank further comprises:
iteratively training a machine learning model wherein the machine learning model is trained using rank training data wherein the rank training data comprises at least one data fault input and at least a data fault rank output;
updating the rank training data as a function of a correlation between the at least one data fault input and the at least a data fault rank output; and
retraining the machine learning model as a function of an updated rank training data; and
initiate a data correction action comprising automatically disputing wrongful charges to the user based on the identified data fault and the data fault rank; and
display the data fault and the data correction action to the user using a graphical user interface.