US 12,242,802 B2
Parser to identify, interpret, and suggest professional language
Mukundan Sundararajan, Bangalore (IN); and Siddharth K. Saraya, Raniganj (IN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Jul. 20, 2022, as Appl. No. 17/813,611.
Prior Publication US 2024/0028824 A1, Jan. 25, 2024
Int. Cl. G06F 40/205 (2020.01); G06F 40/30 (2020.01); G06F 40/47 (2020.01)
CPC G06F 40/205 (2020.01) [G06F 40/30 (2020.01); G06F 40/47 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A processor-implemented method for coordinating professional language, the method comprising:
running, by a processor, at least one professional parsing algorithm and at least one non-professional parsing algorithm on an ingested writing;
assigning, by at least one of the professional parsing algorithms and at least one of the non-professional parsing algorithms, at least two initial scores to the ingested writing, wherein the at least two initial scores are based on a ratio of professional language to non-professional language in the ingested writing, a ratio of each lexical feature in the ingested writing to a total amount of text in the ingested writing, and repetition of the professional language and each of the lexical features;
determining, by a machine learning model, one or more differences between stored professional data and the ingested writing by comparing the at least two initial scores of the ingested writing to the stored professional data;
determining a variation percentage score of the ingested writing based on the differences; and
transmitting at least one suggested modification of the ingested writing based on the variation percentage score to a transmitting device.