# US 12,182,311 B1 · Apparatus and a method for generating a dictionary data filter for data deidentification

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

- Number: US 12,182,311 B1
- Document ID: US12182311B1
- Status: Granted
- Kind: B1
- Application number: 18/744,653
- Filed: 2024-06-16
- Granted: 2024-12-31
- Earliest claimed: 2024-06-16
- Assignees: nference, Inc.
- Applicants: nference, Inc.
- Inventors: Sankar Ardhanari; Karthik Murugadoss
- Web page: https://patentgrep.com/patent/US12182311B1

## CPC

- G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An apparatus for generating a dictionary data filter for data deidentification is disclosed. The apparatus includes at least processor and a memory communicatively connected to the processor. The memory instructs the processor to receive a plurality of user data. The memory instructs the processor to generate contextual data as a function of the plurality of user data. The memory instructs the processor to identify a plurality of patient identifiers and a plurality of localized terms within the plurality of user data. The memory instructs the processor to generate a dictionary data filter as a function of the plurality of localized terms. The memory instructs the processor to identify one or more misidentified patient identifiers within the plurality of patient identifiers using the dictionary data filter. The memory instructs the processor to modify the plurality of patient identifiers as a function of the one or more misidentified patient identifiers.

## Claims

### Claim 1

An apparatus for generating a dictionary data filter for data deidentification, wherein the apparatus comprises:
at least a processor; and
a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to:
receive a plurality of user data;
generate contextual data as a function of the plurality of user data;
identify a plurality of patient identifiers within the plurality of user data;
identify a plurality of localized terms within the plurality of user data as a function of the contextual data;
generate a dictionary data filter as a function of the plurality of localized terms;
identify one or more misidentified patient identifiers within the plurality of patient identifiers using the dictionary data filter; and
modify the plurality of patient identifiers as a function of the one or more misidentified patient identifiers.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein identifying the plurality of localized terms further comprises:
generating a plurality of tokens associated with the plurality of user data;
classifying each token of the plurality of tokens into at least one semantic category using a dictionary classifier; and
identifying the plurality of localized terms as a function of the classification.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein generating the contextual data further comprises identifying a plurality of related terms as a function of the plurality of user data.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein identifying the plurality of localized terms further comprises identifying the plurality of localized terms as a function their proximity to at least one related term of the plurality of related terms.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the memory further instructs the processor to:
structure the plurality of user data as a function of the modified patient identifiers using an indexing system; and
store the structured user data in an index structure, wherein the indexing system is configured to iteratively modify the index structure in response to receiving additional user data.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein receiving the plurality of user data comprises receiving the plurality of user data from an electronic health record (EHR).

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein memory further instructs the processor to generate anonymized data as a function of the plurality of patient identifiers.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the dictionary data filter comprises a lookup table.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein identifying the plurality of localized terms comprises:
training a dictionary classifier using dictionary training data, wherein dictionary training data comprises examples of contextual data correlated to examples of localized terms; and
identifying the plurality of localized terms within the plurality of user data as a function of the contextual data using the trained dictionary classifier.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the dictionary classifier comprises a large language model.

### Claim 11

A method for generating a dictionary data filter for data deidentification, wherein the method comprises:
receiving, using at least a processor, a plurality of user data;
generating, using the at least a processor, contextual data as a function of the plurality of user data;
identifying, using the at least a processor, a plurality of patient identifiers within the plurality of user data;
identifying, using the at least a processor, a plurality of localized terms within the plurality of user data as a function of the contextual data;
generating, using the at least a processor, a dictionary data filter as a function of the plurality of localized terms;
identifying, using the at least a processor, one or more misidentified patient identifiers within the plurality of patient identifiers using the dictionary data filter; and
modifying, using the at least a processor, the plurality of patient identifiers as a function of the one or more misidentified patient identifiers.

### Claim 12 (depends on 11)

The method of claim 11, wherein identifying the plurality of localized terms further comprises:
generating a plurality of tokens associated with the plurality of user data;
classifying each token of the plurality of tokens into at least one semantic category using a dictionary classifier; and
identifying the plurality of localized terms as a function of the classification.

### Claim 13 (depends on 11)

The method of claim 11, wherein generating the contextual data further comprises identifying a plurality of related terms as a function of the plurality of user data.

### Claim 14 (depends on 13)

The method of claim 13, wherein identifying the plurality of localized terms further comprises identifying the plurality of localized terms as a function their proximity to at least one related term of the plurality of related terms.

### Claim 15 (depends on 11)

The method of claim 11, wherein the method further comprises:
structuring, using the at least a processor, the plurality of user data as a function of the modified patient identifiers using an indexing system; and
storing, using the at least a processor, the structured user data in an index structure, wherein the indexing system is configured to iteratively modify the index structure in response to receiving additional user data.

### Claim 16 (depends on 11)

The method of claim 11, wherein receiving the plurality of user data comprises receiving the plurality of user data from an electronic health record (EHR).

### Claim 17 (depends on 11)

The method of claim 11, wherein the method further comprises generating, using the at least a processor, anonymized data as a function of the plurality of patient identifiers.

### Claim 18 (depends on 11)

The method of claim 11, wherein the dictionary data filter comprises a lookup table.

### Claim 19 (depends on 11)

The method of claim 11, wherein identifying the plurality of localized terms comprises:
training a dictionary classifier using dictionary training data, wherein dictionary training data comprises examples of contextual data correlated to examples of localized terms; and
identifying the plurality of localized terms within the plurality of user data as a function of the contextual data using the trained dictionary classifier.

### Claim 20 (depends on 19)

The method of claim 19, wherein the dictionary classifier comprises a large language model.