# US 2025/0165993 A1 · Systems and methods for human-in-the-loop training of a machine learning model for extracting targets from records

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0165993 A1
- Document ID: US20250165993A1
- Status: Published application
- Kind: A1
- Application number: 18/516,093
- Filed: 2023-11-21
- Published: 2025-05-22
- Earliest claimed: 2023-11-21
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Leeyat Bracha TESSLER; John MARTIN; Dexter FERGUSON; Jerry WU
- Web page: https://patentgrep.com/patent/US20250165993A1

## CPC

- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods for training a machine learning model by extracting targets from records are disclosed. A method includes receiving data packets including data associated with previous interactions of a user, determining at least one party to the previous interactions with whom the user interacted at a level above a threshold, and comparing the at least one party to a plurality of parties identified in a target database to identify at least one potential target, for each potential target, determining a respective target metric by inputting the data packets into a machine learning model, providing an identification of the at least one potential target, with reference to the respective target metrics, to a user device associated with the user, receiving, via the user device, feedback regarding the identification, and training the machine learning model based on the feedback.

## Claims

### Claim 1

A computer-implemented method for training a machine learning model by extracting one or more targets from records, the method comprising:
receiving, by at least one processor, data packets including data associated with previous interactions of a first user;
determining, by the at least one processor, at least one party to the previous interactions with whom the first user interacted at a level above a threshold;
comparing the at least one party to a plurality of parties identified in a target database to identify at least one potential target;
for each of the at least one potential targets, determining, by the at least one processor, a respective target metric by inputting the data packets into a machine learning model;
providing, by the at least one processor, an identification of the at least one potential target, with reference to the respective target metrics, to a user device associated with the first user;
receiving, via the user device, feedback regarding the identification; and
training the machine learning model based on the feedback.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein determining the respective target metric further comprises:
obtaining information related to each target from one or more websites associated with each target in the target database; and
inputting the information related to each target to the machine learning model along with the data packets to determine the respective target metric.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the information related to each target comprises information related to providing gifts.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein determining the at least one party to the previous interactions with whom the first user interacted at the level above the threshold comprises:
determining whether a classification code associated with each of the previous interactions is of a predetermined type, the classification code indicating a classification of a party with whom each of the previous interactions occurred.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the feedback regarding the identification comprises an indication that the first user rejects the at least one potential target.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the respective target metric indicates an ease with which a second user may acquire an item intended for the first user from the at least one party.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, further comprising:
providing, by the at least one processor, the at least one potential target to a second user device associated with a second user.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, further comprising:
receiving an indication from the second user device that the second user has visited a website associated with the at least one potential target; and
further training the machine learning model based on the indication.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining that the at least one party does not match any of the plurality of parties identified in the target database; and
adding the at least one party to the target database.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, further comprising:
authenticating, by at least one processor, the user device associated with the first user.

### Claim 11

A system for training a machine learning model by extracting one or more targets from records, the system comprising:
a memory storing instructions; and
a processor operatively connected to the memory and configured to execute the instructions to perform operations including:
receiving data packets including data associated with previous interactions of a first user;
determining at least one party to the previous interactions with whom the first user interacted at a level above a threshold;
comparing the at least one party to a plurality of parties identified in a target database to identify at least one potential target;
for each of the at least one potential targets, determining a respective target metric by inputting the data packets into a machine learning model;
providing an identification of the at least one potential target, with reference to the respective target metrics, to a user device associated with the first user;
receiving, via the user device, feedback regarding the identification; and
training the machine learning model based on the feedback.

### Claim 12 (depends on 11)

The system of claim 11, wherein determining the respective target metric further comprises:
obtaining information related to each target from one or more websites associated with each target in the target database; and
inputting the information related to each target to the machine learning model along with the data packets to determine the respective target metric.

### Claim 13 (depends on 12)

The system of claim 12, wherein the information related to each target comprises information related to providing gifts.

### Claim 14 (depends on 11)

The system of claim 11, wherein determining the at least one party to the previous interactions with whom the first user interacted at the level above the threshold comprises:
determining whether a classification code associated with each of the previous interactions is of a predetermined type, the classification code indicating a classification of a party with whom each of the previous interactions occurred.

### Claim 15 (depends on 11)

The system of claim 11, wherein the feedback regarding the identification comprises an indication that the first user rejects the at least one potential target.

### Claim 16 (depends on 11)

The system of claim 11, wherein the respective target metric indicates an ease with which a second user may acquire an item intended for the first user from the at least one party.

### Claim 17 (depends on 11)

The system of claim 11, wherein the processor is configured to execute the instructions to perform additional operations including:
providing the at least one potential target to a second user device associated with a second user.

### Claim 18 (depends on 17)

The system of claim 17, wherein the processor is configured to execute the instructions to perform additional operations including:
receiving an indication from the second user device that the second user has visited a website associated with the at least one potential target; and
further training the machine learning model based on the indication.

### Claim 19 (depends on 11)

The system of claim 11, wherein the processor is configured to execute the instructions to perform additional operations including:
determining that the at least one party does not match any of the plurality of parties identified in the target database; and
adding the at least one party to the target database.

### Claim 20

A non-transitory computer readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations for training a machine learning model by extracting one or more targets from records, the operations comprising:
receiving data packets including data associated with previous interactions of a first user;
determining at least one party to the previous interactions with whom the first user interacted at a level above a threshold;
comparing the at least one party to a plurality of parties identified in a target database to identify at least one potential target;
for each of the at least one potential targets, determining a respective target metric by inputting the data packets into a machine learning model;
providing an identification of the at least one potential target, with reference to the respective target metrics, to a user device associated with the first user;
receiving, via the user device, feedback regarding the identification;
training the machine learning model based on the feedback;
providing the at least one potential target to a second user device associated with a second user;
receiving an indication from the second user device that the second user has visited a website associated with the at least one potential target; and
further training the machine learning model based on the indication.
