US 11,783,125 B2
System and method for electronic text analysis and contextual feedback
Lee Adcock, Midlothian, VA (US); Nahid Ghalaty, Fairfax, VA (US); Ana Cruz, Arlington, VA (US); Geeta Shyamala, Herndon, VA (US); and Patrick Sofo, Arlington, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Oct. 11, 2022, as Appl. No. 17/963,779.
Application 17/963,779 is a continuation of application No. 16/884,399, filed on May 27, 2020, granted, now 11,487,936, issued on Nov. 1, 2022.
Prior Publication US 2023/0030957 A1, Feb. 2, 2023
Int. Cl. G06F 40/205 (2020.01); G06N 20/00 (2019.01); G06F 40/35 (2020.01); G06F 40/289 (2020.01)
CPC G06F 40/205 (2020.01) [G06F 40/289 (2020.01); G06F 40/35 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
one or more processors and a memory having instructions that, when executed, cause the one or more processors to:
extract a word from content of an electronic communication;
assign the word a score;
generate a communication sentiment score based on the score of the word;
request a party sentiment score for a party to the electronic communication from a database;
compare the party sentiment score to the communication sentiment score;
determine a party deviation between the party sentiment score and the communication sentiment score;
request a job-title sentiment score for a job title of the party from the database;
compare the job-title sentiment score to the communication sentiment score;
determine a job-title deviation between the job-title sentiment score and the communication sentiment score; and
provide a warning to the electronic communication when the party deviation is greater than a first threshold and when the job-title deviation is greater than a second threshold.