Augmented data for security during record updates

Patent metadata

Field	Value
Publication number	US-12373589-B2
Application number	US-202318336861-A
Country	US
Kind code	B2
Filing date	Jun 16, 2023
Priority date	Jun 16, 2023
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

A method and related system may analyze metadata associated with a first set of transactions to determine whether to perform a second set of transactions. The method and related system may include determining a data category based on first device-provided data of a first database transaction indicating a first record associated with a second record, and may further include obtaining, based on whether the data category satisfies a first set of criteria, an identifier and an amount based on image data using a prediction model. The method may further include querying a database based on the identifier to obtain an indication that the identifier is mapped to an object category, validating the amount based on a result indicating whether the object category satisfies a second set of criteria, and causing a second transaction that changes fields of the first and second records.

First claim

What is claimed is:

1. A system for increasing security by verifying object identity with obtained images, the system comprising one or more processors and a set of non-transitory, computer-readable storage media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
determining a data richness category for device-provided data associated with a first set of database transactions that updates a dependent record of a dependent user, wherein the dependent record is linked to a source record of a controlling user;
generating an indicator that identifies the first set of database transactions in response to a result indicating whether the data richness category matches a target category;
obtaining, in response to the indicator, an object identifier and an amount by providing an obtained image to a machine learning model to obtain the object identifier and the amount;
querying a database with a query comprising the object identifier to retrieve a record value of an object database record, wherein the record value indicates an object category;
validating the amount based on a result indicating that the object category is a category of a set of permitted object categories; and
causing a second set of database transactions that reduces a field of the source record by the amount and increases a field of the dependent record by the amount in response to the validating of the amount.

2. A method comprising:
determining a data richness category based on first device-provided data of a first set of database transactions indicating a first record, wherein the first record is associated with a second record;
obtaining, based on a result indicating whether the data richness category satisfies a first set of criteria, an object identifier and an amount based on image data using a prediction model;
querying a database based on the object identifier to obtain an indication that the object identifier is mapped to an object category;
validating the amount based on a result indicating whether the object category satisfies a second set of criteria; and
causing a second set of database transactions that reduces a field of the second record by the amount and increases a field of the first record by the amount in response to the validating of the amount.

3. The method of claim 2 , wherein the image data is first image data, and wherein the first image data is provided by a first computing device, further comprising:
receiving later device-provided data of a later set of database transactions indicating a third record;
receiving later image data provided by a second computing device;
obtaining a second object identifier by using the prediction model based on second image data;
in response to a first set of results indicating that the later device-provided data shares a merchant category code with the first device-provided data, updating a configuration value associated with the first record;
receiving third device-provided data of a third set of database transactions identifying the first record; and
causing a fourth set of database transactions that reduces the field of the second record by a second amount and increases the field of the first record by the second amount in response to the updating of the configuration value and a result indicating that the third device-provided data comprises the merchant category code.

4. The method of claim 3 , wherein a second set of results indicates that a time difference between a timestamp of the later set of database transactions and a timestamp of the fourth set of database transactions satisfies a duration threshold.

5. The method of claim 2 , further comprising:
receiving third device-provided data of a third set of database transactions identifying the first record; and
causing a fourth set of database transactions that reduces the field of the second record by a second amount and increases the field of the first record by the second amount in response to a result indicating whether the second amount satisfies a transaction amount threshold.

6. The method of claim 2 , further comprising sending, in response to the result indicating whether the data richness category satisfies the first set of criteria, a notification message to a computing device based on the first device-provided data that causes the computing device to display a request for an image, wherein the image data is obtained from the computing device.

7. The method of claim 2 , wherein the first device-provided data comprises a merchant category code, wherein causing the second set of database transactions comprises causing the second set of database transactions based on a result indicating whether the merchant category code is identified in a set of permitted merchant category codes.

8. The method of claim 2 , wherein the first device-provided data comprises a geographical location, wherein causing the second set of database transactions comprises causing the second set of database transactions based on a result indicating whether the geographical location satisfies a geographic boundary.

9. The method of claim 2 , wherein:
the object identifier is a first object identifier;
receiving the image data comprises receiving multiple images comprising a first image and a second image from a computing device;
providing the image data to the prediction model comprises:
obtaining the first object identifier and a first confidence value associated with the first object identifier by providing the prediction model with the first image;
obtaining a second object identifier and a second confidence value associated with the second object identifier by providing the prediction model with the second image, wherein the second object identifier is associated with a second object category;
selecting the first object identifier based on a result indicating that the first confidence value is greater than the second confidence value; and

the method further comprises:
sending, to the computing device, a notification based on at least one of the second object category or the second object identifier;
receiving, from the computing device, an indicator that the second object category is incorrect; and
retraining the prediction model based on the second image in response to receiving the indicator.

10. The method of claim 2 , wherein the database is a first database, wherein obtaining the object identifier comprises detecting an alphanumeric sequence presented in the image data, the method further comprising:
obtaining an augmented dataset by augmenting the first device-provided data with the alphanumeric sequence; and
storing, in a second database that comprises transaction data, the augmented dataset.

11. A set of non-transitory, computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
determining a data richness category based on first device-provided data of a first set of database transactions indicating a first record, wherein the first record is associated with a second record;
in response to a result indicating whether the data richness category satisfies a first set of criteria, obtaining an object identifier based on image data and model parameters of a prediction model;
determining an object category based on an indication that the object identifier is mapped to the object category;
validating an amount based on a result indicating whether the object category satisfies a second set of criteria; and
causing a second set of database transactions that reduces a field of the second record by the amount and

Assignees

• Capital One Services Llc

Inventors

• Douglas Lawrence
• Rule Jeffrey
• Macomber Jackson

Classifications

• G06F21/6218 Primary

  to a system of files or objects, e.g. local or distributed file system or database · CPC title