US 12,443,906 B1
Systems and methods for enhanced risk identification based on textual analysis
Robert Milden, Washington, DC (US); and Terri Kennell, Washington, DC (US)
Assigned to Fannie Mae
Filed by Fannie Mae, Washington, DC (US)
Filed on May 8, 2023, as Appl. No. 18/144,488.
Application 18/144,488 is a continuation of application No. 17/184,092, filed on Feb. 24, 2021, granted, now 11,681,966.
Int. Cl. G06Q 10/0635 (2023.01); G06F 40/247 (2020.01); G06F 40/40 (2020.01)
CPC G06Q 10/0635 (2013.01) [G06F 40/247 (2020.01); G06F 40/40 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computing system comprising:
a processing circuit comprising a processor and memory, the memory structured to store instructions that are executable by the processor and cause the processing circuit to:
tokenize input text, using at least one of first machine learning or first artificial intelligence, from an input text file into a token comprising a word or a phrase;
based on a location of the token in the input text file, determine, using at least one of second machine learning or second artificial intelligence, that the token is indicative of a potential risk event;
generate an early risk alert, the early risk alert indicative of the potential risk event;
assign a responsibility score to each of a plurality of responsible parties;
determine whether a responsible party of the plurality of responsible parties is involved in the potential risk event; and
in response to matching the potential risk event to the responsibility score of the responsible party and determining that the responsible party is not involved in the potential risk event, transmit the early risk alert to the responsible party, the early risk alert comprising a secure link to a webpage configured to receive data files uploaded by the responsible party, wherein the data files are associated with the potential risk event.