US 11,836,904 B2
Utilizing a neural network model to generate a reference image based on a combination of images
Christian Souche, Cannes (FR); Edouard Mathon, Antibes (FR); and Ji Tang, Valbonne (FR)
Assigned to Accenture Global Solutions Limited, Dublin (IE)
Filed by Accenture Global Solutions Limited, Dublin (IE)
Filed on Mar. 23, 2021, as Appl. No. 17/210,176.
Prior Publication US 2022/0309631 A1, Sep. 29, 2022
Int. Cl. G06T 5/50 (2006.01); G06N 3/08 (2023.01); G06F 18/214 (2023.01)
CPC G06T 5/50 (2013.01) [G06F 18/214 (2023.01); G06N 3/08 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a device, complex data from a user device;
providing, by the device, a plurality of images to the user device based on receiving the complex data;
receiving, by the device and from the user device, a selection of two or more images from the plurality of images;
determining, by the device, whether a combination of the two or more images is stored in a data structure;
determining, by the device, a mapping of the two or more images with the complex data, based on the combination of the two or more images not being stored in the data structure;
storing, by the device, information identifying the two or more images, the complex data, and the mapping in the data structure;
processing, by the device, the two or more images to generate a reference image that satisfies a memorability score threshold;
providing, by the device, the reference image to another user device;
receiving, by the device and from the other user device, a selection of the two or more images;
retrieving, by the device, the complex data from the data structure based on the mapping and based on the selection of the two or more images; and
performing, by the device, one or more actions based on the complex data.