Multi-customer offer

Patent metadata

Field	Value
Publication number	US-11238486-B2
Application number	US-202016776004-A
Country	US
Kind code	B2
Filing date	Jan 29, 2020
Priority date	Jan 29, 2020
Publication date	Feb 1, 2022
Grant date	Feb 1, 2022

Abstract

A device may determine a multi-customer offer, wherein the multi-customer offer identifies a threshold quantity of customers of the multi-customer offer to allow access to the multi-customer offer. The device may receive one or more requests to accept the multi-customer offer, wherein a request, of the one or more requests, is associated with a customer device of the one or more customer devices. The device may determine, based on a quantity of requests of the one or more requests, that the threshold quantity of customers is not satisfied. The device may identify, based on the threshold quantity of customers not being satisfied, one or more candidate customer devices having a likelihood of requesting to accept the multi-customer offer, wherein the one or more candidate customer devices are associated with respective users that are the potential customers, and wherein the likelihood satisfies a threshold.

First claim

What is claimed is:

1. A method, comprising:
determining, by a device associated with a merchant, a multi-customer offer,
wherein the multi-customer offer identifies a threshold quantity of customers of the multi-customer offer to allow access to the multi-customer offer;

receiving, by the device and from one or more customer devices, one or more requests to accept the multi-customer offer,
wherein a request, of the one or more requests, is associated with a customer device of the one or more customer devices;

determining, by the device and based on a quantity of requests of the one or more requests, that the threshold quantity of customers is not satisfied;
using, by the device, natural language processing to determine characteristics of the multi-customer offer;
identifying, by the device and based on the characteristics of the multi-customer offer and the threshold quantity of customers not being satisfied, one or more candidate customer devices using a candidate identification model trained to identify potential customers having a likelihood of requesting to accept the multi-customer offer,
wherein the one or more candidate customer devices are associated with respective users that are the potential customers,
wherein the potential customers are different from customers associated with the one or more customer devices,
wherein the likelihood satisfies a threshold, and
wherein using the candidate identification model uses natural language processing to determine characteristics of historical multi-customer offers,
wherein the characteristics of historical multi-customer offers include:
characteristics of a plurality of historical customer devices, and
characteristics of a plurality of historical associated users, and

wherein using the candidate identification model includes classifying, by the device, relationships among the characteristics of the plurality of historical customer devices and the characteristics of the plurality of historical associated users;

training, by the device, the candidate identification model with information identifying the one or more candidate customer devices and the characteristics of the multi-customer offer,
wherein training the candidate identification model comprises:
performing dimensionality reduction to reduce the information identifying the one or more candidate customer devices and the characteristics of the multi-customer offer to a minimum feature set, and
training the candidate identification model based on the minimum feature set; and

providing, by the device, a notification of another multi-customer offer to the one or more candidate customer devices identified by the trained candidate identification model.

2. The method of claim 1 , further comprising:
receiving, from the one or more candidate customer devices, one or more additional requests to accept the multi-customer offer;
determining, based on receiving the one or more additional requests, that the threshold quantity of customers is satisfied; and
providing access to the multi-customer offer based on the threshold quantity of customers being satisfied.

3. The method of claim 2 , further comprising:
providing, to one or more additional customer devices, a notification indicating that access to the multi-customer offer is allowed.

4. The method of claim 2 , further comprising:
receiving payment information associated with the one or more requests to accept the multi-customer offer;
receiving additional payment information associated with the one or more additional requests to accept the multi-customer offer;
determining a payment defect in the payment information or the additional payment information; and
performing one or more actions based on determining the payment defect in the payment information.

5. The method of claim 4 , wherein performing the one or more actions based on determining the payment defect comprises:
providing a notification of the payment defect to a customer device, of the one or more customer devices or the one or more candidate customer devices, associated with the payment defect;
receiving, from the customer device associated with the payment defect, new payment information; and
processing payments from one or more transactions accounts associated with the payment information or the new payment information.

6. The method of claim 1 , wherein the notification of the multi-customer offer comprises an indication of a difference between a quantity of the one or more requests to accept the multi-customer offer and the threshold quantity of customers of the multi-customer offer.

7. The method of claim 1 , wherein identifying the one or more candidate customer devices comprises one or more of:
identifying the one or more candidate customer devices based on the one or more candidate customer devices being in proximity to a physical location associated with the merchant;
identifying the one or more candidate customer devices based on the one or more candidate customer devices being associated with the customer device of the one or more customer devices; or
identifying the one or more candidate customer devices based on the one or more candidate customer devices being associated with an application that is associated with the merchant.

8. The method of claim 1 , further comprising receiving, from the one or more candidate customer devices prior to identifying the one or more candidate customer devices, an authorization to receive push notifications from the device,
wherein identifying the one or more candidate customer devices comprises identifying the one or more candidate customer devices based on the authorization to receive push notifications from the device.

9. A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
determine a multi-customer offer,
wherein the multi-customer offer identifies a threshold quantity of customers of the multi-customer offer to allow access to the multi-customer offer;

identify characteristics of the multi-customer offer using natural language processing;
receive, from a customer device, a request to accept the multi-customer offer;
identify, based on the characteristics of the multi-customer offer, one or more candidate customer devices using a machine learning model trained to identify potential customers having a likelihood of requesting to accept the multi-customer offer,
wherein the one or more candidate customer devices are associated with respective users that are the potential customers,
wherein the one or more candidate customer devices are different from the customer device,
wherein the likelihood satisfies a threshold, and
wherein using the candidate identification model uses natural language processing to determine characteristics of historical multi-customer offers,
wherein the characteristics of historical multi-customer offers include:
 characteristics of a plurality of historical customer devices, and
 characteristics of a plurality of historical associated users, and

wherein using the candidate identification model includes classifying relationships among the characteristics of the plurality of historical customer devices and the characteristics of the plurality of historical associated users;

train the candidate identification model with information identifying the one or more candidate customer devices and the characteristics of the multi-customer offer,
wherein the one or more processors, when training the candidate identification model, are configured to:
perform an artificial neural network processing technique to perform pattern recognition with regard to patterns of whether the characteristics of

Assignees

• Capital One Services Llc

Inventors

• Mossoba Michael
• Maiman Tyler
• Chatman Ljubica
• Edwards Joshua
• Benkreira Abdelkader M'Hamed

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N3/09

  Supervised learning · CPC title

• H04L67/55

  Push-based network services · CPC title

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• G06F9/54

  Interprogram communication · CPC title