# US 2025/0328720 A1 · Document processing for reducing data usage

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

- Number: US 2025/0328720 A1
- Document ID: US20250328720A1
- Status: Published application
- Kind: A1
- Application number: 18/643,744
- Filed: 2024-04-23
- Published: 2025-10-23
- Earliest claimed: 2024-04-23
- Assignees: KYOCERA Document Solutions Inc.
- Applicants: KYOCERA Document Solutions Inc.
- Inventors: Regil Yana; Kendrick Esperanza Wong; Kilho Shin
- Web page: https://patentgrep.com/patent/US20250328720A1

## CPC

- G06F 40/103: Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191)
- G06V 30/10: Character recognition
- G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Apparatuses and methods relate generally to reducing data usage by a document processing system. In one such method, a segmented layout of a page from a preprocessed image thereof is detected. Components of the layout are separated into one or more blocks. Each type of the one or more blocks are identified. A block of the one or more blocks identified as a text block is converted to text. Meta information for the block is stored. A formatted page for the page including the text and the meta information is constructed. It is determined whether the formatted page has a smaller storage size than the preprocessed image associated with the formatted page.

## Claims

### Claim 1

A method for reducing data usage by a document processing system, comprising:
detecting a segmented layout of a page from a preprocessed image thereof;
separating components of the layout into one or more blocks;
identifying each type of the one or more blocks;
converting a block of the one or more blocks identified as a text block to text;
storing meta information for the block;
constructing a formatted page for the page including the text and the meta information; and
determining whether the formatted page has a smaller storage size than the preprocessed image associated with the formatted page.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the one or more blocks are two or more blocks, and wherein the block is a first block, the method further comprising:
separating a second block of the two or more blocks from the preprocessed image of the page identified as an image block;
converting the image block into an object; and
wherein the constructing of the formatted page for the page includes the text, the meta information, and the object.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the detecting, the separating of the first block, the separating of the second block, the identifying, the converting of the text block, and the converting of the image block are performed in software.

### Claim 4 (depends on 3)

The method according to claim 3, wherein the software is LayoutLMv3.

### Claim 5 (depends on 1)

The method according to claim 1, further comprising:
separating one or more lines of the layout;
converting the one or more lines of the layout into drawing commands;
wherein the constructing of the formatted page for the page includes the text, the meta information, the object, and the drawing commands.

### Claim 6 (depends on 5)

The method according to claim 5, wherein:
the drawing commands are portable document format drawing commands; and
the formatted page is a portable document format page.

### Claim 7 (depends on 6)

The method according to claim 6, wherein the image block is a picture or a table.

### Claim 8 (depends on 5)

The method according to claim 5, further comprising responsive to the formatted page having a smaller storage size than the preprocessed image of the page, sending the formatted page from the document processing system in place of the preprocessed image.

### Claim 9 (depends on 5)

The method according to claim 5, further comprising:
responsive to the formatted page having a smaller storage size than the preprocessed image of the page, storing the formatted page from the document processing system in place of the preprocessed image; and
distributing the formatted page responsive to a send command.

### Claim 10 (depends on 9)

The method according to claim 9, wherein the formatted page is stored in page form.

### Claim 11 (depends on 10)

The method according to claim 10, wherein the first block is converted to text with optical character recognition of the document processing system.

### Claim 12

An apparatus, comprising:
a document processing system with a system memory, a data storage, one or more processor units, and an interface;
the system memory configured to store program code including document services;
the interface coupled for receiving user requests for the document services;
wherein, in response to executing the program code, the document processing system is configured to initiate operations for implementing a process for reducing data usage, the process including:
detecting a segmented layout of a page from a preprocessed image thereof;
separating components of the layout into one or more blocks;
identifying each type of the one or more blocks;
converting a block of the one or more blocks identified as a text block to text;
storing meta information for the block;
constructing a formatted page for the page including the text and the meta information; and
determining whether the formatted page has a smaller storage size than the preprocessed image associated with the formatted page.

### Claim 13 (depends on 12)

The apparatus according to claim 12, wherein the one or more blocks are two or more blocks, and wherein the block is a first block, the process further comprising:
separating a second block of the two or more blocks from the preprocessed image of the page identified as an image block;
converting the image block into an object; and
wherein the constructing of the formatted page for the page includes the text, the meta information, and the object.

### Claim 14 (depends on 13)

The apparatus according to claim 13, wherein the detecting, the separating of the first block, the separating of the second block, the identifying, the converting of the text block, and the converting of the image block are performed in software.

### Claim 15 (depends on 13)

The apparatus according to claim 13, wherein the process further comprises:
separating one or more lines of the layout;
converting the one or more lines of the layout into drawing commands;
wherein the constructing of the formatted page for the page includes the text, the meta information, the object, and the drawing commands.

### Claim 16 (depends on 15)

The apparatus according to claim 15, wherein:
the drawing commands are portable document format drawing commands;
the formatted page is a portable document format page; and
the image block is a picture or a table.

### Claim 17 (depends on 15)

The apparatus according to claim 15, further comprising responsive to the formatted page having a smaller storage size than the preprocessed image of the page, sending the formatted page from the document processing system in place of the preprocessed image.

### Claim 18 (depends on 15)

The apparatus according to claim 15, further comprising:
responsive to the formatted page having a smaller storage size than the preprocessed image of the page, storing the formatted page from the document processing system in place of the preprocessed image; and
distributing the formatted page responsive to a send command.

### Claim 19 (depends on 18)

The apparatus according to claim 18, wherein the formatted page is stored in page form.

### Claim 20 (depends on 19)

The apparatus according to claim 19, wherein the first block is converted to text with optical character recognition of the document processing system.
