US 12,229,793 B2
Machine learning technologies for identifying category purchases and generating digital product offers
Anthony David Smaniotto, Portage, IN (US); and Ankit Patel, Union City, NJ (US)
Assigned to Fetch Rewards, LLC, Chicago, IL (US)
Filed by FETCH REWARDS, LLC, Chicago, IL (US)
Filed on Mar. 19, 2024, as Appl. No. 18/610,202.
Application 18/610,202 is a continuation of application No. 18/132,735, filed on Apr. 10, 2023, granted, now 11,941,655.
Prior Publication US 2024/0338726 A1, Oct. 10, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/02 (2023.01); G06Q 30/0202 (2023.01); G06Q 30/0207 (2023.01); G06Q 30/0241 (2023.01)
CPC G06Q 30/0224 (2013.01) [G06Q 30/0202 (2013.01); G06Q 30/0222 (2013.01); G06Q 30/0277 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method of training multiple machine learning models, the computer-implemented method comprising:
training, by at least one processor, a first machine learning model using a first set of training data indicating how a purchased set of products or services is categorized within a set of data structures;
receiving, by the at least one processor from a plurality of electronic devices associated with a plurality of users, a plurality of digital images captured by the plurality of electronic devices;
analyzing, by the at least one processor using an image recognition technique, the plurality of digital images to identify, as included in the plurality of digital images, a plurality of identifiers corresponding to a plurality of products or services purchased by the plurality of users;
analyzing, by the at least one processor using the first machine learning model, (i) data indicating the plurality of products or services purchased by the plurality of users, and (ii) a data structure associated with an entity to determine a plurality of user affinity profiles respectively associated with the plurality of users;
training, by the at least one processor, a second machine learning model using a second set of training data identifying (i) a training set of products or services purchased by a set of individuals, and (ii) a set of offers provided to the set of individuals in association with the purchase of the training set of products or services by the set of individuals;
identifying, by the at least one processor from the data indicating the plurality of products or services purchased by the plurality of users, at least one product or service associated with the entity and purchased by a user of the plurality of users;
analyzing, by the at least one processor using the second machine learning model, data identifying the at least one product or service and a user affinity profile of the plurality of user affinity profiles associated with the user of the plurality of users to determine a digital offer for an additional product or service associated with the entity or an additional entity;
availing, by the at least one processor, the digital offer for review by the user via an electronic device, of the plurality of electronic devices, associated with the user;
accessing, by at least one processor from a digital image captured by the electronic device associated with the user, an additional set of data indicating whether the additional product or service was purchased by the user; and
updating, by the at least one processor, the second machine learning model using the additional set of data to enable more accurate digital offer determinations in subsequent analyses.