# US 2023/0053567 A1 · Entity household generation based on attribute-pair matching

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

- Number: US 2023/0053567 A1
- Document ID: US20230053567A1
- Status: Published application
- Kind: A1
- Application number: 17/409,262
- Filed: 2021-08-23
- Published: 2023-02-23
- Earliest claimed: 2021-08-23
- Assignees: U.S. Bancorp, National Association
- Applicants: U.S. Bancorp, National Association
- Inventors: Christopher Kallas; Xiaoqiao Wei; Ding Ma
- Web page: https://patentgrep.com/patent/US20230053567A1

## CPC

- G06F 16/285: {Clustering or classification}
- G06F 16/288: {Entity relationship models}
- G06F 16/23: Updating
- G06F 16/24564: {Applying rules; Deductive queries}
- G06F 16/24565: {Triggers; Constraints}
- G06F 16/24573: {using data annotations, e.g. user-defined metadata}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method comprises storing a plurality of entity profiles; applying a predetermined first set of rules to a plurality of attribute-value pairs of the plurality of entity profiles; identifying a first set of entity profiles that satisfy the predetermined first set of rules; identifying a second set of entity profiles that satisfy the predetermined second set of rules; and updating a first attribute-value pair of the first and second sets of entity profiles by adding a first label to the first attribute-value pair responsive to determining the first set of entity profiles and the second set of entity profiles share a common entity profile.

## Claims

### Claim 1

A method, comprising:
storing, by one or more processors, a plurality of entity profiles, each of the plurality of entity profiles associated with a different entity and comprising a plurality of attribute-value pairs;
applying, by the one or more processors, a predetermined first set of rules to the plurality of attribute-value pairs of the plurality of entity profiles;
identifying, by the one or more processors, a first set of entity profiles that satisfy the predetermined first set of rules based on the first set of entity profiles having a matching first set of attribute-value pairs;
applying, by the one or more processor, a predetermined second set of rules to the plurality of attribute-value pairs of the plurality of entity profiles;
identifying, by the one or more processors, a second set of entity profiles that satisfy the predetermined second set of rules based on the second set of entity profiles having a matching second set of attribute-value pairs; and
updating, by the one or more processors, a first attribute-value pair of the first and second sets of entity profiles by adding a first label to the first attribute-value pair responsive to determining the first set of entity profiles and the second set of entity profiles share a common entity profile, the first label linking the first and second sets of entity profiles.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
responsive to determining the first set of entity profiles and the second set of entity profiles share a common entity profile, generating, by the one or more processors, the first label as a numeric, alphabetic, or alphanumeric string,
wherein updating the first attribute-value pair of the first and second sets of entity profiles with the first label comprises adding, by the one or more processors, the first label to the first attribute-value pair of the first and second sets of entity profiles.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
comparing, by the one or more processors, the first set of entity profiles to a first threshold; and
comparing, by the one or more processors, the second set of entity profiles to a second threshold,
wherein updating the first attribute-value pair of the first and second sets of entity profiles is performed in response to determining the first set of entity profiles does not exceed the first threshold and the second set of entity profiles does not exceed the second threshold.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
identifying, by the one or more processors, a third set of entity profiles that satisfy the predetermined first set of rules;
generating, by the one or more processors, a list of the third set of entity profiles;
comparing, by the one or more processors, the third set of entity profiles to a first threshold; and
discarding, by the one or more processors, the list of the third set of entity profiles responsive to determining the third set of entity profiles exceed the first threshold.

### Claim 5 (depends on 1)

The method of claim 1, wherein identifying the first set of entity profiles that satisfy the predetermined first set of rules comprises:
identifying, by the one or more processors, a first subset of entity profiles responsive to determining the first subset of entity profiles have a second attribute-value pair and a third attribute-value pair in common;
identifying, by the one or more processors, a second subset of entity profiles responsive to determining the second subset of entity profiles have a fourth attribute-value pair and a fifth attribute-value pair in common; and
combining, by the one or more processors, the first and second subsets of entity profiles into the first set of entity profiles responsive to the first and second subsets having an entity profile in common.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
subsequent to the updating the first attribute-value pair of the first and second sets of entity profiles with the first label, identifying, by the one or more processors, a third subset of entity profiles responsive to determining the third subset of entity profiles have matching attribute-value pairs;
aggregating, by the one or more processors, the third subset of entity profiles with the first set of entity profiles to generate a third set of entity profiles responsive to the third subset of entity profiles and the first set of entity profiles having an entity profile in common; and
removing, by the one or more processors, the first label from the first set of entity profiles responsive to determining the third set of entity profiles exceeds a threshold.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
removing, by the one or more processors, the first label from the second set of entity profiles responsive to determining the third set of entity profiles exceeds a threshold.

### Claim 8 (depends on 1)

The method of claim 1, wherein identifying the second set of entity profiles that satisfy the predetermined first set of rules comprises:
identifying, by the one or more processors, a first subset of entity profiles responsive to determining the first subset of entity profiles have a matching second attribute-value pairs and matching third attribute-value pairs;
identifying, by the one or more processors, a second subset of entity profiles responsive to determining the second subset of entity profiles have matching second attribute-value pairs and matching fourth attribute-value pairs; and
combining, by the one or more processors, the first and second subsets of entity profiles into the second set of entity profiles responsive to the first and second subsets having an entity profile in common.

### Claim 9 (depends on 1)

The method of claim 1, wherein the second attribute-value pair is an account number of the respective entity profile stored in a separate data structure from the entity profile.

### Claim 10 (depends on 1)

The method of claim 1, wherein applying the predetermined first set of rules to the plurality of entity profiles comprises:
determining, by the one or more processors using an edit distance function, whether entity profiles have a second attribute-value pair that is an exact match and a third attribute-value pair that is a non-exact match within a threshold,
wherein identifying the first set of entity profiles comprises identifying entity profiles that have a second attribute-value pair that exactly matches and a third attribute-value pair that is a non-exact match within the threshold.

### Claim 11 (depends on 1)

The method of claim 1, further comprising:
subsequent to updating the first attribute-value pair of the first and second sets of entity profiles with the first label, re-applying, by the one or more processors, the first set of rules and the second set of rules to the plurality of entity profiles;
re-identifying, by the one or more processors, the first set of entity profiles that satisfy the predetermined first set of rules;
re-identifying, by the one or more processors, the second set of entity profiles that satisfy the predetermined second set of rules; and
updating, by the one or more processors, the first attribute-value pair of the first and second sets of entity profiles with the first label responsive to determining the first set of entity profiles and the second set of entity profiles share a common entity profile.

### Claim 12

A system, the system comprising:
one or more hardware processors configured by machine-readable instructions to:
store a plurality of entity profiles, each of the plurality of entity profiles associated with a different entity and comprising a plurality of attribute-value pairs;
apply a predetermined first set of rules to the plurality of attribute-value pairs of the plurality of entity profiles;
identify a first set of entity profiles that satisfy the predetermined first set of rules based on the first set of entity profiles having a matching first set of attribute-value pairs;
apply a predetermined second set of rules to the plurality of attribute-value pairs of the plurality of entity profiles;
identify a second set of entity profiles that satisfy the predetermined second set of rules based on the second set of entity profiles having a matching second set of attribute-value pairs; and
update a first attribute-value pair of the first and second sets of entity profiles by adding a first label to the first attribute-value pair responsive to determining the first set of entity profiles and the second set of entity profiles share a common entity profile, the first label linking the first and second sets of entity profiles.

### Claim 13 (depends on 12)

The system of claim 12, wherein the one or more hardware processors are further configured to:
responsive to determining the first set of entity profiles and the second set of entity profiles share a common entity profile, generate the first label as a numeric, alphabetic, or alphanumeric string,
wherein the one or more hardware processors are configured to update the first attribute-value pair of the first and second sets of entity profiles with the first label by adding the first label to the first attribute-value pair of the first and second sets of entity profiles.

### Claim 14 (depends on 12)

The system of claim 12, wherein the one or more hardware processors are further configured to:
compare the first set of entity profiles to a first threshold; and
compare the second set of entity profiles to a second threshold,
wherein the one or more hardware processors are configured to update the first attribute-value pair of the first and second sets of entity profiles in response to determining the first set of entity profiles does not exceed the first threshold and the second set of entity profiles does not exceed the second threshold.

### Claim 15 (depends on 12)

The system of claim 12, wherein the one or more hardware processors are further configured to:
identify a third set of entity profiles that satisfy the predetermined first set of rules;
generate a list of the third set of entity profiles;
compare the third set of entity profiles to a first threshold; and
discard the list of the third set of entity profiles responsive to determining the third set of entity profiles exceed the first threshold.

### Claim 16 (depends on 12)

The system of claim 12, wherein the one or more hardware processors are configured to
identify the first set of entity profiles that satisfy the predetermined first set of rules by:
identifying a first subset of entity profiles responsive to determining the first subset of entity profiles have a second attribute-value pair and a third attribute-value pair in common;
identifying a second subset of entity profiles responsive to determining the second subset of entity profiles have a fourth attribute-value pair and a fifth attribute-value pair in common; and
combining the first and second subsets of entity profiles into the first set of entity profiles responsive to the first and second subsets having an entity profile in common.

### Claim 17

A non-transitory computer-readable storage medium having instructions embodied thereon, the instructions being executable by one or more processors to perform a method, the method comprising:
storing a plurality of entity profiles, each of the plurality of entity profiles associated with a different entity and comprising a plurality of attribute-value pairs;
applying a predetermined first set of rules to the plurality of attribute-value pairs of the plurality of entity profiles;
identifying a first set of entity profiles that satisfy the predetermined first set of rules based on the first set of entity profiles having a matching first set of attribute-value pairs;
applying a predetermined second set of rules to the plurality of attribute-value pairs of the plurality of entity profiles;
identifying a second set of entity profiles that satisfy the predetermined second set of rules based on the second set of entity profiles having a matching second set of attribute-value pairs; and
updating a first attribute-value pair of the first and second sets of entity profiles by adding a first label to the first attribute-value pair responsive to determining the first set of entity profiles and the second set of entity profiles share a common entity profile, the first label linking the first and second sets of entity profiles.

### Claim 18 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the method further comprises:
responsive to determining the first set of entity profiles and the second set of entity profiles share a common entity profile, generating the first label as a numeric, alphabetic, or alphanumeric string,
wherein updating the first attribute-value pair of the first and second sets of entity profiles with the first label comprises adding the first label to the first attribute-value pair of the first and second sets of entity profiles.

### Claim 19 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the method further comprises:
comparing the first set of entity profiles to a first threshold; and
comparing the second set of entity profiles to a second threshold,
wherein updating the first attribute-value pair of the first and second sets of entity profiles is performed in response to determining the first set of entity profiles does not exceed the first threshold and the second set of entity profiles does not exceed the second threshold.

### Claim 20 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the method further comprises:
identifying a third set of entity profiles that satisfy the predetermined first set of rules;
generating a list of the third set of entity profiles;
comparing the third set of entity profiles to a first threshold; and
discarding the list of the third set of entity profiles responsive to determining the third set of entity profiles exceed the first threshold.
