US 12,014,145 B2
Systems and methods of automatic message creation using machine learning on digital assets
Abdessamad Echihabi, Los Angeles, CA (US); Bryant Huang, Santa Clarita, CA (US); Quinn Lam, Los Angeles, CA (US); and Mihai Vlad, London (GB)
Assigned to SDL Inc., Wakefield, MA (US)
Filed by SDL Inc., Wakefield, MA (US)
Filed on Jun. 20, 2023, as Appl. No. 18/212,104.
Application 18/212,104 is a continuation of application No. 17/582,841, filed on Jan. 24, 2022, granted, now 11,734,516.
Application 17/582,841 is a continuation of application No. 16/155,658, filed on Oct. 9, 2018, granted, now 11,256,867, issued on Feb. 22, 2022.
Prior Publication US 2023/0334256 A1, Oct. 19, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/30 (2020.01); G06F 3/0482 (2013.01); G06F 3/0484 (2022.01); G06F 40/106 (2020.01); G06F 40/166 (2020.01); G06N 20/00 (2019.01); H04L 51/02 (2022.01)
CPC G06F 40/30 (2020.01) [G06F 3/0482 (2013.01); G06F 3/0484 (2013.01); G06F 40/106 (2020.01); G06F 40/166 (2020.01); G06N 20/00 (2019.01); H04L 51/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving one or more assets that comprise textual content;
performing machine learning on the one or more assets in order to determine relevant words, phrases, and statistics included in the textual content, and generating a summary of the textual content;
receiving feedback from an editor with respect to the summary;
incorporating the feedback into the machine learning;
automatically generating a message using the machine learning through use of a message creation ruleset;
displaying on a graphical user interface:
the relevant words, the phrases, and the statistics;
segments of the textual content that have been extracted from the one or more assets based on the relevant words, the phrases, and the statistics; and
an interface that is used to create the message using content from the segments of the textual content that have been extracted from the one or more assets, wherein the machine learning applies natural language processing rules to convert a run-on or a fragment, in at least one of the segments of the textual content, into a sentence; and
distributing the message across one or more communication channels.