# US 2026/0073157 A1 · System and Method For Automatically Marking Classification Of Textual Data

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

- Number: US 2026/0073157 A1
- Document ID: US20260073157A1
- Status: Published application
- Kind: A1
- Application number: 19/323,374
- Filed: 2025-09-09
- Published: 2026-03-12
- Earliest claimed: 2024-09-09
- Assignees: Booz Allen Hamilton Inc.
- Applicants: Booz Allen Hamilton Inc.
- Inventors: Steven TOMITA; Terry Michael SCHOOF; Sergey BLOK
- Web page: https://patentgrep.com/patent/US20260073157A1

## CPC

- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 40/30: Semantic analysis
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Embodiments can relate to systems and methods for autonomously marking classification of textual data. Textual data and a classification guide can be submitted to an interfacing module configured to interface a processor with a database and a large language model. A semantic search of textual data against classification rules that fall within the classification guide can be done to identify a first subset of classification rules. A curating operation of the textual data against the first subset of classification rules can be done to generate a second subset of classification rules to be used to classify the textual data. A prompt can be generated including the second subset of classification rules and instructions for a response. The prompt and textual data can be sent to the LLM to generate the response as an output document autonomously modified to include a classification marking.

## Claims

### Claim 1

A system for autonomously marking classification of textual data, comprising:
a processor including an interfacing module configured to interface the processor with a database and a large language model (LLM);
a memory having instructions stored thereon that when executed by the processor will cause the processor, via a context management module, to:
perform a semantic search of textual data against classification rules stored in a vector database to identify a first subset of classification rules to be used to classify the textual data;
perform a curating operation of the textual data against the first subset of classification rules to generate a second subset of classification rules to be used to classify the textual data;
generate a prompt including the second subset of classification rules and instructions for use by the LLM to produce a response; and
send the prompt and the textual data to the LLM to generate the response as an output document automatically modified to include (i) one or more classification markings for one or more portions of the textual data, or (ii) no classification marking if the classification rules do not identify a corresponding classification marking for any of the textual data.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the database is a vector database that contains classification rules stored as mathematical representations.

### Claim 3 (depends on 1)

The system of claim 1, wherein instructions will cause the processor to:
perform the semantic search via a Retrieval-Augmented Generation (RAG) dataflow and vectorization process.

### Claim 4 (depends on 3)

The system of claim 3, wherein instructions will cause the processor to:
use vectors of user-identified classification guides when performing the semantic search.

### Claim 5 (depends on 4)

The system of claim 4, wherein instructions will cause the processor to:
identify ten classification rules from one or more user-identified classification guides as the first subset of classification rules.

### Claim 6 (depends on 1)

The system of claim 1, wherein instructions will cause the processor to:
perform the curating operation via a similarity process involving cross-encoders.

### Claim 7 (depends on 6)

The system of claim 6, wherein instructions will cause the processor to:
perform the similarity process via a Euclidian distance process.

### Claim 8 (depends on 6)

The system of claim 6, wherein instructions will cause the processor to:
identify five classification rules from the first subset of classification rules as the second subset of classification rules.

### Claim 9

A system for autonomously marking classification of textual data, comprising:
an Application Program Interface (API) module;
a processor;
a memory;
an interfacing module configured to interface a database and a large language model (LLM);
a plug-in data classifier application configured to support features of a software application;
wherein, when executed by a processor, the plug-in data classifier application will cause the processor, via a context management module, to:
perform a semantic search of textual data against classification rules stored in a vector database to identify a first subset of classification rules to be used to classify the textual data;
perform a curating operation of the textual data against the first subset of classification rules to generate a second subset of classification rules to be used to classify the textual data;
generate a prompt including the second subset of classification rules and instructions for use by the LLM to produce a response;
send the prompt and the textual data to the LLM to generate the response; and
send the response via the API module to the plug-in data classifier application to cause the software application to generate an output, the output including a document automatically modified to include (i) one or more classification markings for one or more portions of the textual data, or (ii) no classification marking if the classification rules do not identify a corresponding classification marking for any of the textual data.

### Claim 10

A database management system for efficient curating of classification rule selection,
comprising:
a database containing classification rules;
a processor including an interfacing module configured to interface the processor with the database and a large language model (LLM);
a memory having instructions stored thereon that when executed by the processor will cause the processor, via a context management module, to:
perform a semantic search of textual data against the classification rules stored in a vector database to identify a first subset of classification rules to be used to classify the textual data;
perform a curating operation of the textual data against the first subset of classification rules to generate a second subset of classification rules to be used to classify the textual data;
generate a prompt including the second subset of classification rules, the prompt configured to be executed in the LLM to generate a response.

### Claim 11

A method for autonomously marking classification of textual data, the method
comprising:
submitting textual data and a classification guide to an interfacing module configured to interface a processor with a database and a large language model (LLM);
performing a semantic search of textual data against classification rules stored in a vector database that fall within the classification guide to identify a first subset of classification rules to be used to classify the textual data;
performing a curating operation of the textual data against the first subset of classification rules to generate a second subset of classification rules to be used to classify the textual data;
generating a prompt including the second subset of classification rules and instructions for a response; and
sending the prompt and textual data to the LLM to generate the response as an output document automatically modified to include (i) one or more classification markings for one or more portions of the textual data, or (ii) no classification marking if the classification rules do not identify a corresponding classification marking for any of the textual data.

### Claim 12 (depends on 11)

The method of claim 11, wherein:
the database is a vector database that contains possible classification rules stored as mathematical representations.

### Claim 13 (depends on 11)

The method of claim 11, wherein:
performing the semantic search involves a Retrieval-Augmented Generation (RAG) dataflow and vectorization process.

### Claim 14 (depends on 13)

The method of claim 13, wherein:
using vectors of user-identified classification guides when performing the semantic search.

### Claim 15 (depends on 14)

The method of claim 14, comprising:
identifying ten classification rules from the classification guides as the first subset of classification rules.

### Claim 16 (depends on 11)

The method of claim 11, comprising:
performing the curating operation via a similarity process involving cross-encoders.

### Claim 17 (depends on 16)

The method of claim 16, comprising:
performing the similarity process via a Euclidian distance process.

### Claim 18 (depends on 17)

The method of claim 17, comprising:
identifying five classification rules from the first subset of classification rules as the second subset of classification rules.
