	US 11,869,050 B2
	Facilitating responding to multiple product or service reviews associated with multiple sources
Jerry Wagner, Chesterfield, VA (US); and Mario Munoz, Richmond, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 27, 2022, as Appl. No. 17/809,067.
Application 17/809,067 is a continuation of application No. 16/405,823, filed on May 7, 2019, granted, now 11,373,220.
Prior Publication US 2022/0327588 A1, Oct. 13, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/0282 (2023.01); G06F 9/54 (2006.01); G06N 20/00 (2019.01)

CPC G06Q 30/0282 (2013.01) [G06F 9/54 (2013.01); G06N 20/00 (2019.01)]

20 Claims

1. A method, comprising:

obtaining, by a device, information from a plurality of sources;

identifying, by the device, one or more sources of the plurality of sources,

wherein the one or more sources include one or more reviews, and

wherein the identifying comprises determining the one or more sources based on following links associated with a root page;

obtaining, by the device, review information associated with a product or a service from the one or more sources;

processing, by the device, the review information to determine additional review information associated with the review information,

the additional review information including:

an authenticity indicator,

a review history associated with a profile related to the review information, and

a measure of influence associated with the profile;

training, by the device, based on pre-processing historical information to generate a minimum feature set that corresponds to the additional review information, and based on applying a classification technique to the minimum feature set, a machine learning model,

wherein the historical information is associated with a plurality of reviews;

identifying, by the device, using the machine learning model, and based on the review information and the additional review information, a particular review related to the review information,

wherein identifying the particular review comprises:

providing, as input to the machine learning model, the additional review information,

receiving, as output from the machine learning model, a relevance score indicating a respective measure of importance that is based on the additional review information, and

identifying the particular review based on the relevance score; and

sending, by the device and based on the particular review, an electronic calendar invite to one or more personnel associated with the product or the service.