US 12,267,460 B2
Utilizing machine learning models to generate interactive digital text threads with personalized agent escalation digital text reply options
Jigar Mehta, Milpitas, CA (US); Abbey Chaver, Berkeley, CA (US); Paul Zeng, New York, NY (US); and Abhi Sharma, San Francisco, CA (US)
Assigned to Chime Financial, Inc., San Francisco, CA (US)
Filed by Chime Financial, Inc., San Francisco, CA (US)
Filed on Mar. 18, 2024, as Appl. No. 18/608,356.
Application 18/608,356 is a continuation of application No. 18/057,886, filed on Nov. 22, 2022, granted, now 11,936,814.
Prior Publication US 2024/0364814 A1, Oct. 31, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04M 3/51 (2006.01); H04L 51/02 (2022.01); H04L 51/046 (2022.01)
CPC H04M 3/5191 (2013.01) [H04L 51/02 (2013.01); 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 automated interactive digital text thread;
generating, utilizing an agent escalation machine learning model, a plurality of predicted client-agent escalation classes and a plurality of escalation class probabilities from the client features;
selecting a predicted client-agent escalation class from the plurality of predicted client-agent escalation classes utilizing the plurality of escalation class probabilities;
providing, for display via the client device, a personalized escalation digital text reply option corresponding to the predicted client-agent escalation class via the automated interactive digital text thread, wherein the personalized escalation digital text reply option is associated with a client self-service workflow corresponding to the predicted client-agent escalation class; and
executing the client self-service workflow based on receiving an indication of a user interaction with the personalized escalation digital text reply option.