US 12,300,109 B1
Frontline collaboration system for automatically posting a notice to a conversation thread
Krunalkumar G. Patel, Flower Mound, TX (US); Sunil K. John, Carrollton, TX (US); Shalini Neelankavil, Lewisville, TX (US); Chaitanya Kommidi, Plano, TX (US); and Christopher Clair, Dallas, TX (US)
Assigned to American Airlines, Inc., Fort Worth, TX (US)
Filed by AMERICAN AIRLINES, INC., Fort Worth, TX (US)
Filed on Feb. 1, 2022, as Appl. No. 17/590,378.
Int. Cl. G08G 5/00 (2006.01); G06N 20/00 (2019.01); G08G 5/22 (2025.01); H04L 51/216 (2022.01); H04L 51/224 (2022.01)
CPC G08G 5/22 (2025.01) [G06N 20/00 (2019.01); H04L 51/216 (2022.05); H04L 51/224 (2022.05)] 22 Claims
OG exemplary drawing
 
1. A method, comprising:
generating, using a communication application, a conversation thread so that the conversation thread is displayed on a user interface to members of the conversation thread;
wherein the conversation thread is associated with an event;
wherein the event has an expected event timeline;
wherein the event comprises a subevent;
wherein the expected event timeline is dependent upon completion of the subevent; and
wherein the members of the conversation thread are associated with the event;
posting, using the communication application, a member post from one of the members to the conversation thread;
wherein the member post comprises a first timestamp and a first message body; and
wherein the first message body comprises an indication of time associated with the completion of the subevent;
posting, using the communication application, an automated post to the conversation thread, wherein the automated post contains a message autonomously generated by a software application;
performing, using a machine learning model that performs sentiment analysis of member posts, sentiment analysis of the member post;
wherein performing, using the machine learning model that performs sentiment analysis of member posts, sentiment analysis of the member post comprises the machine learning model identifying, based on the indication of time, a completion time of the subevent;
identifying, using the machine learning model, a predicted delay to the expected event timeline, wherein the identification of the predicted delay is based on the sentiment analysis and the message autonomously generated by the software application;
sending, to the communication application and from the machine learning model, a notice regarding the predicted delay;
receiving, by the communication application, the notice regarding the predicted delay; and
automatically posting, using the communication application and in response to the receipt of the notice by the communication application, the notice regarding the predicted delay to the conversation thread.