Granted Patent B2

US 12,400,183 · App. 18/405,629 · Granted Aug 26, 2025

Inventors: Kevin Osborn (Newton Highlands, MA); Francis Ogbennah (Baltimore, MD); Anita Eradla (Ashburn, VA)

Assignee: Capital One Services, LLC

G06Q10/087G06Q40/12

Abstract

Claims (70)

1. A computer implemented method for determining purchased items in a transaction, the method comprising:

receiving, via a network from one or more client computers, one or more website records indicating retrieval of website data from one or more websites;

analyzing the one or more website records to determine a plurality of individual costs respectively of a plurality of items;

receiving, via the network, a transaction record identifying: a vendor, and a total cost of the transaction with the vendor;

correlating the total cost of the transaction with the plurality of individual costs;

identifying, based on the correlating, a subset of the plurality of items included in the transaction;

retrieving, via the network, a classifier model, wherein the classifier model analyzes the transaction record and the one or more website records;

determining, via the classifier model, a likelihood that the plurality of items were purchased; and

updating, based on identifying the subset and based on determining the likelihood, a database that tracks purchases of the plurality of items.

2. The computer implemented method of claim 1 , wherein the updating of the database comprises:

generating a data structure including a first list and a plurality of second lists, wherein the first list identifies a plurality of transactions that include the transaction with the vendor, and each of the plurality of second lists is associated with one of the plurality of transactions identified in the first list, and wherein the one of the plurality of second lists associated with the transaction with the vendor includes the subset of the plurality of items; and

storing the data structure to the database.

3. The computer implemented method of claim 2 , further comprising:

determining that the plurality of transactions is associated with a user account; and

identifying the user account in the data structure.

4. The computer implemented method of claim 3 , wherein the user account is a credit card account or a debit card account.

5. The computer implemented method of claim 3 , further comprising:

receiving, via the network, a query identifying the user account; and

transmitting, via the network, the data structure in response to the query.

6. The computer implemented method of claim 5 , further comprising:

encoding the data structure as a webpage, wherein the transmitting of the data structure includes transmitting the webpage.

7. The computer implemented method of claim 1 , wherein the correlating comprises, for each item of the plurality of items:

calculating a likelihood that the item is included in the transaction;

comparing the likelihood to a threshold; and

including, based on the likelihood exceeding the threshold, the item in the subset.

8. The computer implemented method of claim 1 , further comprising:

associating the transaction record with one of the one or more client computers;

transmitting, based on the associating, a request to the one of the one or more client computers to confirm that one or more items in the subset were included in the transaction identified in the transaction record;

receiving, in response to the request, a confirmation that the one or more items in the subset were included in the transaction identified in the transaction record; and

updating, using a machine learning algorithm, the classifier model based on the confirmation.

9. The computer implemented method of claim 1 , further comprising:

retrieving, from the database, a training dataset that includes: historical costs for each of the plurality of items from a plurality of vendors, purchase data identifying multiple items of the plurality of items purchased together, browsing history data identifying one or more of the plurality of items viewed on the one or more websites, shopping history data identifying one or more of the plurality of items purchased by an individual, a plurality of transaction records for purchases by the individual, or vendor records identifying one or more of the plurality of items purchased from one of the plurality of vendors;

applying a machine learning algorithm to the training dataset to generate the classifier model; and

storing the classifier model in the database.

10. The computer implemented method of claim 1 , wherein the transaction record identifies a credit card used for the transaction.

11. The computer implemented method of claim 1 , wherein the one or more website records indicate that the one or more websites provided: a quantity in stock of one of the items in the subset, availability of one of the items in the subset for immediate purchase, availability of one of the items in the subset for purchase at a future time, or a past purchase of one of the items in the subset via the one or more websites.

12. A server comprising:

at least one computer processor; and

computer memory comprising computer-executable instructions that when executed by the at least one computer processor, cause the server to:

receive, via a network from one or more client computers, one or more website records indicating retrieval of website data from one or more websites;

analyze the one or more website records to determine a plurality of individual costs respectively of a plurality of items;

retrieve, from one or more databases, a plurality of transaction records each identifying: one of a plurality of vendors, and a total cost of a respective transaction of a plurality of transactions; and

for each respective transaction of the plurality of transactions:

correlate the total cost of the respective transaction with the plurality of individual costs;

identify, based on the correlating, a respective subset of the plurality of items included in the respective transaction;

retrieve, via the network, a classifier model, wherein the classifier model analyzes the respective transaction and the respective subset;

determine, via the classifier model, a likelihood that the respective subset is associated with the respective transaction; and

update, based on the likelihood, the one or more databases to associate the respective subset with the respective transaction.

13. The server of claim 12 , wherein the computer-executable instructions, when executed by the at least one computer processor, cause the server to:

determine that the plurality of transactions is associated with a user account; and

update the one or more databases to associate the plurality of transactions with the user account.

14. The server of claim 13 , wherein the computer-executable instructions, when executed by the at least one computer processor, cause the server to:

generate a hierarchical data structure comprising:

a first list identifying the plurality of transactions, and

for each respective transaction of the plurality of transactions, a subordinate list that identifies the respective subset associated with the respective transaction; and

update the one or more databases to store the hierarchical data structure.

15. The server of claim 14 , wherein the computer-executable instructions, when executed by the at least one computer processor, cause the server to:

receive, via the network, a query identifying the user account; and

transmit, in response to the query, the hierarchical data structure to a particular client computer associated with the user account.

16. The server of claim 14 , wherein the hierarchical data structure associates the plurality of transactions with a credit card account or a bank account.

17. A non-transitory machine-readable medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:

receive, via a network from one or more client computers, one or more website records indicating retrieval of website data from one or more websites;

receive, via the network, one or more transaction records associated with a user account, wherein each of the one or more transaction records identifies: one of a plurality of vendors, and a total cost of a respective transaction of one or more transactions;

retrieve, from one or more databases, a classifier model;

determine, using the classifier model with information from the one or more website records and information from the one or more transaction records as inputs, a likelihood that each of a plurality of items was included in each of the one or more transactions;

generate, based on the likelihood, a first list including the one or more transactions, and for each transaction of the one or more transactions, a subordinate list including a respective subset of the plurality of items associated with the respective transaction;

receive, via the network, a query identifying the user account; and

transmit, via the network, a response to the query that includes the first list and the subordinate list for each transaction of the one or more transactions in the first list.

18. The non-transitory machine-readable medium of claim 17 , wherein the response comprises a command to display the first list and the subordinate list for each transaction of the one or more transactions in the first list.

19. The non-transitory machine-readable medium of claim 18 , wherein the response includes hyperlinks to the one or more websites.

Assignments (1)

Continuity (2)

References Cited (24)