# US 2026/0093761 A1 · Apparatus for personalizing document search and creating new document within institution using artificial intelligence and method thereof

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

- Number: US 2026/0093761 A1
- Document ID: US20260093761A1
- Status: Published application
- Kind: A1
- Application number: 18/923,871
- Filed: 2024-10-23
- Published: 2026-04-02
- Earliest claimed: 2024-10-02
- Assignees: Archivsoft Co., Ltd.
- Applicants: ARCHIVSOFT Co., Ltd.
- Inventors: Ji Sung KIM
- Web page: https://patentgrep.com/patent/US20260093761A1

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/93: Document management systems
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The present disclosure relates to an apparatus for personalizing document search and creating a new document using artificial intelligence and a method thereof, and according to the present disclosure, and includes obtaining first data including a search history of a user, a document viewing history, department information, and an electronic document through an input module; preprocessing the first data; learning the preprocessed first data; generating a document search personalization and new document creation model using the learning result; obtaining a request message through the input module; generating at least one of a document search result and a new document corresponding to the request message using the document search personalization and new document creation model; and controlling the display to display the generated result.

## Claims

### Claim 1

An apparatus for personalizing document search and creating a new document within an institution using artificial intelligence, comprising:
an input module configured to acquire data;
a communication module configured to transmit and receive the data with an external device;
a memory configured to store at least one process for performing an operation and storing user input and data;
a display configured to display a graphic image; and
a processor configured to perform a control method according to the process,
wherein the processor is configured to:
obtain first data including a search history of a user, a document viewing history, department information, and an electronic document through the input module,
preprocess the first data,
learn the preprocessed first data,
generate a document search personalization and new document creation model using the learning result,
obtain a request message through the input module,
generate at least one of a document search result or a new document corresponding to the request message using the document search personalization and new document creation model, and
control the display to display the generated result,
wherein the processor is further configured to:
learn a user feedback, which include a click rate and a document opening time, by applying a machine learning model, to generate the learning result,
wherein the processor is further configured to:
based on the new document creation model, search for a similar document of which content and similarity to the new document is within a predetermined range or higher;
analyze a structure of the searched similar document; and
control the display to sequentially display a plurality of templates, which reflect the analysis result, and
wherein the processor is further configured to:
search for real-time news and select a document of which similarity to a subject of the document currently being written is greater than a threshold, and control the display to display the selected document.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to:
generate a personal profile based on at least one of the search history of the user, the document viewing history, or the department information, and
control the display to display the generated personal profile.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to:
generate a recommended document search result by analyzing search patterns of users performing similar tasks, and
control the display to display the generated recommended document search result.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to:
analyze a keyword and a topic of the document viewed by the user within a predetermined period, and
control the display to display the document with a similarity exceeding a threshold based on the analysis result.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to:
control the display to display the document with a relevance exceeding a threshold by reflecting recent search history and information on current proceeding project.

### Claim 6

(canceled)

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to:
search for a related document of which similarity level with the new document is a predetermined range or higher,
automatically summarize and cite a core content of the related document, and
control the display to display the summary and citation result.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to:
search for a related document of which similarity level with the new document is a predetermined range or higher,
extract a main keyword of the related document, and
control the display to display the extracted main keyword.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to:
analyze a context of the document being written, and
control the display to display a text message containing a phrase corresponding to the analyzed context.

### Claim 10

A method for personalizing document search and creating a new document using artificial intelligence performed by a processor of an apparatus, comprising:
obtaining first data including a search history of a user, a document viewing history, department information, and an electronic document through an input module;
preprocessing the first data;
learning the preprocessed first data;
generating a document search personalization and new document creation model using the learning result;
obtaining a request message through the input module;
generating at least one of a document search result and a new document corresponding to the request message using the document search personalization and new document creation model; and
controlling a display to display the generated result,
wherein the learning comprises:
learning a user feedback, which include a click rate and a document opening time, by applying a machine learning model, to generate the learning result,
wherein the controlling comprises:
based on the new document creation model, searching for a similar document of which content and similarity to the new document is within a predetermined range or higher;
analyzing a structure of the searched similar document; and
controlling the display to sequentially display a plurality of templates, which reflect the analysis result, and
wherein the controlling further comprises:
searching for real-time news and select a document of which similarity to a subject of the document currently being written is greater than a threshold, and controlling the display to display the selected document.

### Claim 11 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to search for legal information with a similarity greater than a threshold value in relation to the subject of the document currently being written, and control the display to display the searched legal information.

### Claim 12 (depends on 10)

The method of claim 10, wherein the controlling further comprises:
searching for legal information with a similarity greater than a threshold value in relation to the subject of the document currently being written, and controlling the display to display the searched legal information.
