Product analysis platform to perform a facial recognition analysis to provide information associated with a product to a user

Patent metadata

Field	Value
Publication number	US-2023385834-A1
Application number	US-202318447672-A
Country	US
Kind code	A1
Filing date	Aug 10, 2023
Priority date	Nov 28, 2018
Publication date	Nov 30, 2023
Grant date	—

Abstract

A device may determine that a user has a threshold level of interest in a type of product. The device may receive an image of a face of the user, may perform a facial recognition analysis of the image, and may determine identification information of the user based on the facial recognition analysis. The device may identify account information associated with the user based on the identification information and may identify a product in an inventory that is associated with the type of product. The device may perform a preauthorization process associated with a transaction involving the product and the user based on the account information, and may perform an action associated with the transaction based on the preauthorization process.

First claim

What is claimed is:

1 . A method, comprising:
determining, by a kiosk device, identification information of a user based on a biometric from the user; determining, by a product processing model and the kiosk device, that the user has a threshold level of interest in a type of product based on the identification information,
wherein the product processing model is trained using information that includes transaction information identifying a plurality of transactions and product information identifying a plurality of products to determine one or more transactions, of the plurality of transactions, with one or more products, of the plurality of products, that are associated with a probability of being of interest to the user, and
wherein the product processing model determines a probability of the type of product being of interest to the user and outputs a score;
identifying, by the kiosk device and based on determining that the score exceeds the threshold level of interest, a product, of the one or more products, in an inventory that is associated with the type of product; and providing, by the kiosk device, information associated with the product.

2 . The method of claim 1 , further comprising:
identifying account information associated with the user based on the identification information; and wherein determining that the user has the threshold level of interest in the type of product comprises: determining that the user has the threshold level of interest in the type of product based on the account information.

3 . The method of claim 1 , wherein the product processing model is further trained using one or more characteristics of the user,
wherein the one or more characteristics of the user include:
physical traits,
family traits, or
known preferences.

4 . The method of claim 1 , wherein the threshold level of interest in the type of product is higher if the user infrequently engages in a certain transaction involving a certain product and the threshold level of interest is lower if the user frequently engages in a certain transaction involving a certain product.

5 . The method of claim 1 , further comprising:
determining one or more parameters for a transaction for the product based on a preauthorization process; and providing the one or more parameters to the user to permit the user to engage in the transaction by accepting the one or more parameters.

6 . The method of claim 1 , wherein providing information associated with the product comprises:
recommending a product to the user, or providing a targeted offer for the product.

7 . The method of claim 1 , wherein the score indicating that the product is likely of interest to the user is assigned to transactions or products that are determined to be similar as previously performed transactions or identifications of products that were of interest to the user.

8 . A device, comprising:
one or more memories; and one or more processors, coupled to the one or more memories, configured to:
determine identification information of a user;
identify account information associated with the user based on the identification information;
determine, by a product processing model, that the user has a threshold level of interest in a type of product,
wherein the product processing model is trained using information that includes a plurality of transactions and a plurality of products to determine one or more transactions, of the plurality of transactions, with one or more products, of the plurality of products, that are associated with a probability of being of interest to the user, and
wherein the product processing model determines a probability of the type of product being of interest to the user and outputs a score;

identify, based on determining that the score exceeds the threshold level of interest, a product, of the one or more products, in an inventory that is associated with the type of product; and provide information associated with the product.

9 . The device of claim 8 , wherein the one or more processors, to determine the identification information of the user, are to:
determine the identification information of the user based on facial recognition of the user.

10 . The device of claim 8 , wherein the one or more processors, to provide the information associated with the product, are to:
provide the information associated with the product on display on the device,
wherein the device is in a merchant location and the product is associated with the merchant location.

11 . The device of claim 8 , wherein the one or more processors, to provide the information associated with the product, are to:
provide the information associated with the product to the device to permit the user to engage in a transaction involving the product.

12 . The device of claim 8 , wherein the one or more processors, to identify the product in the inventory that is associated with the type of product, are to:
identify, from the identification information, a location associated with the user; and identify the product in the inventory based on the location associated with the user and a location associated with the product,
wherein the location associated with the product is within a threshold distance of the location associated with the user.

13 . The device of claim 8 wherein the one or more processors, to provide the information associated with the product, are to:
provide the information associated with the product and provide information associated with a transaction,
the information associated with the transaction specifying that the user is preauthorized to purchase the product, and enabling the user to authorize purchase of the product.

14 . The device of claim 8 , wherein the one or more processors, to determine that the user has the threshold level of interest in the type of product, are to:
determine that the user has the threshold level of interest in the type of product, based on the identification information and based on at least one of a purchase history or a rental history,
wherein the purchase history identifies one or more purchases associated with the type of product and the rental history identifies one or more rentals associated with the type of product.

15 . A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to: determine identification information of a user based on a biometric from the user; identify profile information associated with the user based on the identification information; determine, by a product processing model, that the user has a threshold level of interest in a type of product based on the profile information,
wherein the product processing model is trained using information that includes transaction information identifying transactions and product information identifying one or more products to determine one or more transactions, of a plurality of transactions, with one or more products, of a plurality of products, that are associated with a probability of being of interest to the user, and
wherein the product processing model determines a probability of the type of product being of interest to the user and outputs a score;
identify, based on determining that the score exceeds the threshold level of interest, a product, of the one or more products, in an inventory that is associated with the type of product; and perform an action associated with the product.

16 . The non-transitory

Assignees

• Capital One Services Llc

Inventors

• Mathews Liju
• Chikkaveerappa Satish
• Subramanian Ponnazhakan
• Deshpande Amit

Classifications

• G06Q20/40145 Primary

  Biometric identity checks · CPC title

• G06F16/9035

  Filtering based on additional data, e.g. user or group profiles · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title

• G06Q20/206

  comprising security or operator identification provisions, e.g. password entry · CPC title

• G06V40/161

  Detection; Localisation; Normalisation · CPC title