US 12,086,122 B2
Task dependency extraction sharing and notification
Meenakshi Madugula, Newark, CA (US); Bailey Duncan, San Jose, CA (US); Nishtha Atrey, San Jose, CA (US); Archana Yadawa, San Jose, CA (US); and Mu Qiao, Belmont, CA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Oct. 14, 2022, as Appl. No. 18/046,523.
Prior Publication US 2024/0126737 A1, Apr. 18, 2024
Int. Cl. G06F 16/20 (2019.01); G06F 16/22 (2019.01); G06F 40/284 (2020.01)
CPC G06F 16/2264 (2019.01) [G06F 40/284 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a processor, message data from a natural language conversation among participants in a project;
identifying, by the processor, at least two tasks mentioned in the message data;
determining, by the processor, a dependency between the at least two tasks based on the output of a sequential language model, wherein the messages associated with the at least two tasks are inputs to the sequential language model;
generating, by the processor, a directed graph depicting the at least two tasks and the determined dependency of the at least two tasks;
sharing, by the processor, a directed graph across participants; and
notifying, by the processor, participants who are blocked subsequent to completion of dependent tasks.