Dynamically verifying a signature for a transaction

Patent metadata

Field	Value
Publication number	US-11715102-B2
Application number	US-202016774977-A
Country	US
Kind code	B2
Filing date	Jan 28, 2020
Priority date	Jan 28, 2020
Publication date	Aug 1, 2023
Grant date	Aug 1, 2023

Abstract

A first device may receive, from a second device, a request to approve a transaction wherein the request includes transaction data related to the transaction and an image of a signature of an individual that submitted the request. The first device may determine, after receiving the request, a priority level associated with the transaction based on the transaction data. The first device may process the image of the signature using a computer vision technique and/or a vector-based technique. The first device may select, from a memory storing a plurality of comparator signatures, a comparator signature for the signature based on the priority level. The first device may use the comparator signature to verify the signature to approve or deny the transaction. The first device may perform a comparison of the comparator signature and the signature in the image after processing the image and selecting the comparator signature.

First claim

What is claimed is:

1. A method, comprising:
receiving, by a first device and from at least one of a user device, a transaction device, or a financial institution device, a request to approve a transaction,
wherein the request includes:
transaction data related to the transaction, and
an image of an electronic signature that is manually provided by an individual, that submitted the request, via a user interface of the at least one of the user device, the transaction device, or the financial institution device, and wherein the first device includes a memory storing:
images of a plurality of comparator electronic signatures, that are manually provided by the individual via the user interface of the at least one of the user device, the transaction device, or the financial institution device, including:
an image of a first comparator electronic signature, and
an image of a second comparator electronic signature different from the first comparator electronic signature, and

information that identifies a plurality of priority levels, selected by the individual via the user interface of the at least one of the user device, the transaction device, or the financial institution device to correspond to the plurality of comparator electronic signatures, including:
a first priority level corresponding to the first comparator electronic signature, and
a second priority level corresponding to the second comparator electronic signature and different from the first priority level;

determining, by the first device and after receiving the request, that the transaction is associated with the first priority level based on the transaction data;
processing, by the first device, the image of the electronic signature, using at least one of a computer vision technique or a vector-based technique, to identify one or more attributes of the electronic signature in the image of the electronic signature provided in the request to approve the transaction;
selecting, by the first device and from the memory, the image of the first comparator electronic signature based on the transaction being associated with the first priority level and the information that identifies the plurality of priority levels;
performing, by the first device, a comparison of one or more attributes of the first comparator electronic signature, in the image of the first comparator electronic signature, to the one or more attributes of the electronic signature in the image of the electronic signature; and
determining, by the first device and based on a result of performing the comparison, whether the comparison satisfies a matching threshold.

2. The method of claim 1 , further comprising:
receiving, from the at least one of the user device, the transaction device, or the financial institution device and prior to receiving the request, the images of the plurality of comparator electronic signatures and the information that identifies the plurality of priority levels; and
storing, in the memory, the images of the plurality of comparator electronic signatures and the information that identifies the plurality of priority levels after receiving the images of the plurality of comparator electronic signatures and the information that identifies the plurality of priority levels.

3. The method of claim 1 , wherein determining that the transaction is associated with the first priority level is based on at least one of:
an amount of the transaction,
a type of the transaction,
a location of the transaction, or
one or more entities associated with the transaction.

4. The method of claim 1 , wherein processing the image of the electronic signature using the computer vision technique comprises:
detecting, using the at least one of the computer vision technique or vector-based technique, a set of markings in the image of the electronic signature based on a contrast between the set of markings and a background of the image of the electronic signature; and
identifying, based on detecting the set of markings, attributes of at least one of:
a set of characters included in the electronic signature,
a set of symbols included in the electronic signature, or
a set of characteristics of the electronic signature.

5. The method of claim 1 , wherein processing the image of the electronic signature using the vector-based technique comprises at least one of:
determining a horizontal vector projection for the electronic signature based on a height of the electronic signature in the image of the electronic signature in pixels,
determining a vertical vector projection for the electronic signature based on a width of the electronic signature in the image of the electronic signature in pixels, or
determining vectors that represent directional orientations of the electronic signature at points in the image of the electronic signature.

6. The method of claim 1 , wherein performing the comparison is based on at least one of:
corresponding sets of characters included in the first comparator electronic signature and the electronic signature,
corresponding sets of symbols included in the first comparator electronic signature and the electronic signature,
corresponding characteristics of the first comparator electronic signature and the electronic signature,
corresponding horizontal projections of the first comparator electronic signature and the electronic signature, or
corresponding vertical projections of the first comparator electronic signature and the electronic signature.

7. The method of claim 1 , further comprising:
training a machine learning model to determine a risk score for the transaction based on the transaction data related to transaction, historical transaction data related to historical transactions, and determinations regarding whether the transaction and historical transactions are associated with fraudulent activity.

8. The method of claim 7 , further comprising:
assigning a first weight to one or more user-selected characteristics related to the transaction; and
assigning a second weight to one or more historical characteristics that are different than the one or more user-selected characteristics and related to the historical transactions,
wherein the second weight is greater than the first weight, and
wherein training the machine learning model is based on assigning the first weight to the one or more user-selected characteristics and assigning the second weight to the one or more historical characteristics.

9. A device, comprising:
one or more memories storing:
images of a plurality of comparator electronic signatures, that are manually provided by an individual via a user interface of at least one of a user device, a transaction device, or a financial institution device, including:
an image of a first comparator electronic signature, and
an image of a second comparator electronic signature different from the first comparator electronic signature, and

information that identifies a plurality of priority levels, selected by the individual via the user interface of the at least one of the user device, the transaction device, or the financial institution device to correspond to the plurality of comparator electronic signatures, including:
a first priority level corresponding to the first comparator electronic signature, and
a second priority level corresponding to the second comparator electronic signature and different than the first priority level; and

one or more processors, coupled to the one or more memories, to:
receive, from the at least one of the user device, the transaction device, or the financial institution device, a request to approve a transaction,
wherein the request includes:
transaction data related to the transaction, and

Assignees

• Capital One Service Llc
• Capital One Services Llc

Inventors

• Edwards Joshua
• Mossoba Michael
• Benkreira Abdelkader M'Hamed

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06Q20/4014 Primary

  Identity check for transactions · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q20/322

  Aspects of commerce using mobile devices [M-devices] · CPC title