# US 2021/0240682 A1 · Automatic entity resolution with rules detection and generation system

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

- Number: US 2021/0240682 A1
- Document ID: US20210240682A1
- Status: Published application
- Kind: A1
- Application number: 17/229,995
- Filed: 2021-04-14
- Published: 2021-08-05
- Earliest claimed: 2015-06-18
- Assignees: Aware, Inc.
- Applicants: Aware, Inc.
- Inventors: Olukayode Isaac OSESINA; Taras P. RIOPKA
- Web page: https://patentgrep.com/patent/US20210240682A1

## CPC

- G06F 16/215: Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
- G06N 5/048: Fuzzy inferencing
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Entity resolution (i.e., record linkage) involves the analysis/discovering of datasets that refer to the same real world entity. Analysis typically involves transformation and comparison of different fields of the dataset followed by the application of often domain/data specific logic for determining datasets that refer to the same real world entity (e.g., person). Consider, a bulk mailing of product catalogs to potential customers. Some individuals may have numerous public records that identify the individual differently. Illustratively, several records associated with Jane Doe at her current home address may exist: one record with her name listed as J. Doe, a second record as Jane H. Doe, a third record as Doe, Jane, and a fourth record as Jan Doe (a misspelling). Conceivably, the bulk mailing could unwittingly send multiple catalogs to Jane Doe at her current address, one for each name variation. The entity resolution process described herein can overcome such problems.

## Claims

### Claim at position 1

1-24. (canceled)

### Claim 25

A challenging training sample selection method comprising:
consideration of record fields as indepenedent;
selection of challenging training samples based on a number of multiple labels/classess that record field values, and/or link feature values are associated also termed ambiguity;
proportional selection of challenging training samples based on a level of that record field values, and/or link feature values ambiguity;
contribution of each linkage feature to the training sample is determined by its relative level of ambiguity;
contribution of a linkage feature value within a linkage feature is determined by its relative level of ambiguty;
contribution of value pairs associated with the same linkage feature is determined by its relative level of ambiguity; and
use of that record field values from positive labels to optimize the determination of record field values, and/or link feature values ambiguty.

### Claim 26 (depends on 25)

The method of claim 25, wherein the level of ambiguity of the linkage feature, linkage feature value and, value pair in any order of combination are used to determine the contibution of samples to the training set.

### Claim 27 (depends on 25)

The method of claim 25, where in any method is used to determine the level of amibguity (relative number of instances with multiple classess/labels) of linkage feature, linkage feature value and, value pair in any combination.

### Claim 28

A non-transitory computer readable information storage media having stored thereon instructions, that when executed by a processor perform a challenging training sample selection method comprising:
consideration of record fields as indepenedent;
selection of challenging training samples based on a number of multiple labels/classess that record field values, and/or link feature values are associated also termed ambiguity;
proportional selection of challenging training samples based on a level of that record field values, and/or link feature values ambiguity;
contribution of each linkage feature to the training sample is determined by its relative level of ambiguity;
contribution of a linkage feature value within a linkage feature is determined by its relative level of ambiguty;
contribution of value pairs associated with the same linkage feature is determined by its relative level of ambiguity; and
use of that record field values from positive labels to optimize the determination of record field values, and/or link feature values ambiguty.

### Claim 29 (depends on 28)

The media of claim 28, wherein the level of ambiguity of the linkage feature, linkage feature value and, value pair in any order of combination are used to determine the contibution of samples to the training set.

### Claim 30 (depends on 28)

The media of claim 28, where in any technique is used to determine the level of amibguity (relative number of instances with multiple classess/labels) of linkage feature, linkage feature value and, value pair in any combination.

### Claim 31

A challenging training sample selection system comprising:
a processor;
an I/O interface; and
storage, the storage having stored thereon instructions, that when executed by the processor, cause to be performed:
consideration of record fields as indepenedent;
selection of challenging training samples based on a number of multiple labels/classess that record field values, and/or link feature values are associated also termed ambiguity;
proportional selection of challenging training samples based on a level of that record field values, and/or link feature values ambiguity;
contribution of each linkage feature to the training sample is determined by its relative level of ambiguity;
contribution of a linkage feature value within a linkage feature is determined by its relative level of ambiguty;
contribution of value pairs associated with the same linkage feature is determined by its relative level of ambiguity; and
use of that record field values from positive labels to optimize the determination of record field values, and/or link feature values ambiguty.

### Claim 32 (depends on 31)

The system of claim 31, wherein the level of ambiguity of the linkage feature, linkage feature value and, value pair in any order of combination are used to determine the contibution of samples to the training set.

### Claim 33 (depends on 31)

The system of claim 31, where in any technique is used to determine the level of amibguity (relative number of instances with multiple classess/labels) of linkage feature, linkage feature value and, value pair in any combination.
