US 12,267,283 B2
Utilizing machine learning models to generate interactive digital text threads with personalized digital text reply options
Jigar Mehta, Milpitas, CA (US); Abbey Chaver, Berkley, CA (US); Abhi Sharma, San Francisco, CA (US); and Sashidhar Guntury, Los Angeles, CA (US)
Assigned to Chime Financial, Inc., San Francisco, CA (US)
Filed by Chime Financial, Inc., San Francisco, CA (US)
Filed on Jun. 10, 2024, as Appl. No. 18/738,954.
Application 18/738,954 is a continuation of application No. 17/809,765, filed on Jun. 29, 2022, granted, now 12,010,075.
Prior Publication US 2024/0414110 A1, Dec. 12, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 51/02 (2022.01); G06F 16/355 (2025.01); H04L 51/046 (2022.01)
CPC H04L 51/02 (2013.01) [G06F 16/355 (2019.01); H04L 51/046 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
extracting client features corresponding to a client device participating in an interactive digital text thread;
identifying a hierarchical intent architecture comprising a plurality of intent classifications organized in a plurality of hierarchical layers;
generating, using the hierarchical intent architecture and based on the client features, a plurality of predicted client intent classifications associated with a plurality of intent classification probabilities;
applying a first weight to a first intent classification probability of the plurality of intent classification probabilities associated with a first predicted client intent classification from a first hierarchical layer of the plurality of hierarchical layers, the first weight corresponding to the first hierarchical layer;
applying a second weight to a second intent classification probability of the plurality of intent classification probabilities associated with a second predicted client intent classification from a second hierarchical layer of the plurality of hierarchical layers, the second weight corresponding to the second hierarchical layer;
selecting the first predicted client intent classification from the plurality of predicted client intent classifications based on comparing the first intent classification probability, with the first weight applied, to the plurality of intent classification probabilities; and
providing, for display via the client device, at least two personalized digital text reply options corresponding to the first predicted client intent classification and at least one additional predicted client intent classification via the interactive digital text thread.