US 12,475,317 B2
System and method for query authorization and response generation using machine learning
Guilherme Gomes, Porto Alegre (BR); Bruno Apel, Porto Alegre (BR); Jarismar Silva, Porto Alegre (BR); Vincent Kellers, Bloomfield, NJ (US); Roberto Rodrigues Dias, Porto Alegre (BR); Roberto Masiero, Basking Ridge, NJ (US); and Roberto Silveira, Hoboken, NJ (US)
Assigned to ADP, Inc., Roseland, NJ (US)
Filed by ADP, Inc., Roseland, NJ (US)
Filed on Aug. 9, 2023, as Appl. No. 18/447,273.
Application 18/447,273 is a continuation of application No. 18/068,736, filed on Dec. 20, 2022, granted, now 11,748,569.
Application 18/068,736 is a continuation of application No. 16/864,931, filed on May 1, 2020, granted, now 11,562,749.
Prior Publication US 2023/0385552 A1, Nov. 30, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/295 (2020.01); G06F 18/24 (2023.01); G06F 40/205 (2020.01); G06N 20/00 (2019.01); G10L 17/24 (2013.01)
CPC G06F 40/295 (2020.01) [G06F 18/24 (2023.01); G06F 40/205 (2020.01); G06N 20/00 (2019.01); G10L 17/24 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
establishing, by one or more processors, an interface for a chatbot;
receiving, by the one or more processors via the interface for the chatbot, a query from a computing device;
parsing, via the one or more processors executing a trained machine-learning classifier, the query to determine a subject of the query;
selecting, by the one or more processors, based on the subject of the query, a response template from a plurality of response templates stored in a data repository, wherein the response template is selected to provide a response to the query;
filling, via the one or more processors accessing a restricted database, the response template by matching an identifier included in the response template with a key to the restricted database to retrieve at least a portion of restricted data from the restricted database associated with the subject, resulting in a filled response template, wherein the identifier is associated with the at least the portion of the restricted data;
removing, via the one or more processors, one or more portions of the filled response template that are not associated with the subject, resulting in a partially filled response template;
determining, via the one or more processors, based on execution of a comprehension model on the partially filled response template, that a probability associated with the partially filled response template satisfies a threshold; and
providing, via the one or more processors, responsive to the probability associated with the partially filled response template satisfying the threshold, the partially filled response template via the interface of the chatbot.