US 11,727,082 B2
Machine-learning based personalization
Aleksandr A. Orlov, Copenhagen (DK); and Tetiana Kostenko, Frederiksberg C (DK)
Assigned to SITECORE CORPORATION A/S, Copenhagen (DK)
Filed by Sitecore Corporation A/S, Copenhagen (DK)
Filed on Apr. 25, 2022, as Appl. No. 17/728,687.
Application 17/728,687 is a continuation of application No. 16/281,803, filed on Feb. 21, 2019, granted, now 11,314,825.
Prior Publication US 2022/0253496 A1, Aug. 11, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/00 (2020.01); G06F 16/958 (2019.01); G06F 16/9535 (2019.01); G06N 20/00 (2019.01); G06F 18/243 (2023.01)
CPC G06F 16/958 (2019.01) [G06F 16/9535 (2019.01); G06F 18/24323 (2023.01); G06N 20/00 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for generating personalized digital content, comprising:
performing multiple content tests by presenting different variants of content to a set of different consumers of one or more consumers, wherein results of the multiple content tests are based on behavioral profiles of the different consumers;
generating and training a machine learning (ML) model based on an analysis of the results of the multiple content tests;
outputting, based on the ML model, personalization rules, wherein each personalization rule specifies a certain variance for a defined set of facts, wherein the defined set of facts are based on the behavioral profiles;
exposing the personalization rules and the different variants of content to an administrative user, wherein the administrative user selects one or more of the personalization rules to personalize consumer experiences, wherein the exposing comprises determining, via input from the administrative user, a winning variant, of the different variants of content, to use as a default;
receiving a request for content from a requesting consumer of the one or more consumers; and
based on similarities between the defined set of facts and the requesting consumer, automatically determining an applicable personalization rule of the selected one or more personalization rules.