US 11,868,316 B2
Event management device and method
Thibault Serot, Waverton (AU); Maxime Godeau, Bourg des comptes (FR); Jeremy Teyssedre, Vallauris (FR); Mathieu Philippe Alexis Beynel, Pegomas (FR); and Amar Muharemovic, Antibes (FR)
Assigned to AMADEUS S.A.S., Biot (FR)
Filed by AMADEUS S.A.S., Biot (FR)
Filed on Apr. 1, 2020, as Appl. No. 16/837,473.
Claims priority of application No. 1903521 (FR), filed on Apr. 2, 2019.
Prior Publication US 2020/0320038 A1, Oct. 8, 2020
Int. Cl. G06F 16/17 (2019.01); G06F 16/182 (2019.01); G06N 20/00 (2019.01)
CPC G06F 16/1734 (2019.01) [G06F 16/182 (2019.01); G06N 20/00 (2019.01)] 11 Claims
OG exemplary drawing
 
1. An event management device for managing events, the event management device comprising:
an event detector configured to:
(i) detect the occurrence of an event related to data delivered by a data delivery system, and
(ii) extract user data related to the detected event from a user data storage, the extracted user data comprising user data stored in at least one entry of the user data storage; and
a rule manager configured to:
(i) select one or more rules based on at least one of the detected event or the extracted user data, and
(ii) determine one or more actions to be executed by applying the selected one or more rules using said extracted user data, wherein the one or more actions to be executed are determined in the form of a logical combination of actions using at least one Boolean operator;
wherein the event detector is further configured to trigger execution of the one or more determined action based on respective action relevance scores associated with the actions of the logical combination in an action relevance database; and
wherein the rule manager is further configured, in response to execution of the one or more actions, to:
receive, from each of a plurality of users, a respective feedback value corresponding to the one or more actions,
determine whether the number of feedback values received exceeds a threshold,
when the number of feedback values exceeds the threshold, execute a machine learning engine to determine an updated action relevance score for each executed action,
dynamically update the selected one or more rules based on the action relevance score, and
store, in the action relevance database, the updated action relevance scores for each executed action.