US 12,074,837 B2
Notifications of action items in messages
Dikla Dotan-Cohen, Herzliya (IL); Haim Somech, Ramat Gan (IL); and Ido Priness, Redmond, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed on Jul. 11, 2022, as Appl. No. 17/861,759.
Application 17/861,759 is a continuation of application No. 16/822,996, filed on Mar. 18, 2020, granted, now 11,388,130.
Application 16/822,996 is a continuation of application No. 15/623,300, filed on Jun. 14, 2017, granted, now 10,623,364, issued on Apr. 14, 2020.
Claims priority of provisional application 62/397,680, filed on Sep. 21, 2016.
Prior Publication US 2022/0345432 A1, Oct. 27, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 15/16 (2006.01); G06Q 10/10 (2023.01); G06Q 10/107 (2023.01); H04L 51/04 (2022.01); H04L 51/224 (2022.01); H04L 51/42 (2022.01); H04L 67/50 (2022.01)
CPC H04L 51/224 (2022.05) [G06Q 10/103 (2013.01); G06Q 10/107 (2013.01); H04L 51/04 (2013.01); H04L 51/42 (2022.05); H04L 67/535 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A computerized system comprising:
one or more computer processors; and
computer memory storing computer-useable instructions that, when used by the one or more computer processors, cause the one or more computer processors to perform operations comprising:
receiving a message;
receiving a notification associated with an action item, wherein the notification is generated based on the message, the notification being associated with an extracted completion criteria of the action item and parameters of the extracted completion criteria from a message portion of the message, and the notification being generated based on an inference that at least one of the extracted completion criteria of the action item is unsatisfied based on a user routine model and parameters,
wherein the inference associated with the message is based on user interaction data associated with the user routine model and the parameters, and
wherein the user routine model is a probabilistic machine learning model construct that infers routine-related aspects associated with the user interaction data; and
providing the notification to at least one user associated with the action item.