US 11,809,969 B2
Dynamically integrating interactive machine learning multi-models
Richard Pong Nam Sinn, Milpitas, CA (US); Chun Hao Wang, San Jose, CA (US); and Thomas Todd Donahue, Carlsbad, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Jun. 30, 2020, as Appl. No. 16/916,807.
Prior Publication US 2021/0406325 A1, Dec. 30, 2021
Int. Cl. G06N 20/00 (2019.01); G06F 16/9535 (2019.01); G06F 18/24 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 16/9535 (2019.01); G06F 18/24 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
identifying a user segment for a user;
based on the user segment, deploying a set of models related to the user segment to generate recommendations for the user;
applying the recommendations with regard to an order of interactive content for display;
receiving interactions between the user and first interactive content, wherein the first interactive content is related to a recommendation based on a first model of the set of models;
based on a threshold of runtime attributes related to the interactions being reached, updating a second model, of the set of models, associated with the runtime attributes, wherein the second model is different from the first model and is updated based on the interactions between the user and the first interactive content related to the recommendation based on the first model; and
generating at least one updated recommendation for the user based on deploying the updated second model of the set of models.