US 12,493,918 B2
Systems and methods for dispute resolution
Rahul Bajaj, New Delhi (IN); Kailash Sati, Bangalore (IN); Luis Felipe Gonzalez Fuentes, San Francisco, CA (US); Uzma Khan, Toronto (CA); Punith Kumar, Bangalore (IN); and Karuna Rawat, Lucknow (IN)
Assigned to Walmart Apollo, LLC, Bentonville, AR (US)
Filed by Walmart Apollo, LLC, Bentonville, AR (US)
Filed on Jan. 21, 2022, as Appl. No. 17/581,539.
Prior Publication US 2023/0237602 A1, Jul. 27, 2023
Int. Cl. G06N 20/00 (2019.01); G06F 40/20 (2020.01); G06Q 30/016 (2023.01); G06Q 30/0601 (2023.01); G06Q 50/18 (2012.01)
CPC G06Q 50/182 (2013.01) [G06F 40/20 (2020.01); G06N 20/00 (2019.01); G06Q 30/016 (2013.01); G06Q 30/0609 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors;
a dispute resolution system, wherein the dispute resolution system includes a machine learning engine that comprises a plurality of machine learning modules, and wherein the plurality of machine learning modules corresponds to a plurality of respective tiers; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the dispute resolution system to perform:
receiving dispute resolution information from a user corresponding to a dispute, wherein the dispute resolution information comprises a first data input and a second data input;
analyzing, with a first machine learning module in a first tier of the machine learning engine, the dispute resolution information from the user to identify a dispute reason, wherein the first tier corresponds to a first level of dispute reasons and the first machine learning module is trained to analyze the first level of dispute reasons to identify the dispute reason within the first level of dispute reasons;
analyzing, with at least one of second and third machine learning modules in a second tier of the machine learning engine, the dispute resolution information based on the dispute reason, as identified, wherein the second tier corresponds to a second level of dispute reasons each related to a respective dispute reason in the first level of dispute reasons and the at least one of the second and third machine learning modules is trained to analyze the second level of dispute reasons to identify the dispute reason within the second level of dispute reasons;
determining a dispute resolution based on an output of the second tier of the machine learning engine to resolve the dispute;
training the machine learning engine on the dispute resolution information, wherein the training of the machine learning engine comprises individually training each of the first machine learning module, the second machine learning module, and the third machine learning module based on corresponding dispute reason codes using partial computing resources of the machine learning engine; and
based on the determined dispute resolution, executing one or more dispute resolution actions, wherein the one or more dispute resolution actions include at least one of outputting a dispute reason code, replacing a dispute reason code submitted by the user, and processing the dispute resolution to remove the dispute from further processing.