US 12,067,056 B2
Feedback control for automated messaging adjustments
Phoebe Atkins, Rockville, VA (US); Max Miracolo, Brooklyn, NY (US); Joshua Edwards, Philadelphia, PA (US); Brian McClanahan, Silver Spring, MD (US); Alexander Lin, Arlington, VA (US); Lin Ni Lisa Cheng, New York, NY (US); and Cruz Vargas, Denver, CO (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jul. 27, 2023, as Appl. No. 18/226,905.
Application 18/226,905 is a continuation of application No. 17/838,349, filed on Jun. 13, 2022, granted, now 11,755,656.
Application 17/838,349 is a continuation of application No. 17/396,919, filed on Aug. 9, 2021, granted, now 11,386,160, issued on Jul. 12, 2022.
Prior Publication US 2023/0367816 A1, Nov. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/9032 (2019.01); G06F 16/901 (2019.01); G06F 16/9035 (2019.01); G06F 16/9038 (2019.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01)
CPC G06F 16/90332 (2019.01) [G06F 16/9017 (2019.01); G06F 16/9035 (2019.01); G06F 16/9038 (2019.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a processor, text data;
generating, by the processor, a quantified representation of the text data by processing the text data using at least one natural language processing (NLP) algorithm, the quantified representation of the text data indicating a sentiment of content of the text data; and
automatically revising, by the processor, the content of the text data, the revising comprising:
determining a difference between quantified data indicative of a reaction and the quantified representation of the text data;
identifying, based on the difference, a portion of the content having an unintended sentiment;
replacing the portion of the content with different content, the replacing comprising inserting the different content within a user interface to thereby adjust a sentiment associated with the user interface;
replacing a third portion of the content with untested replacement content; and
publishing the text data including the untested replacement content and obtaining feedback on the untested replacement content from at least one public source.