# US 2025/0156466 A1 · Document reading support method

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

- Number: US 2025/0156466 A1
- Document ID: US20250156466A1
- Status: Published application
- Kind: A1
- Application number: 18/931,462
- Filed: 2024-10-30
- Published: 2025-05-15
- Earliest claimed: 2023-11-09
- Assignees: Semiconductor Energy Laboratory Co., Ltd.
- Applicants: Semiconductor Energy Laboratory Co., Ltd.
- Inventors: Yoshitaka DOZEN; Kunitaka YAMAMOTO
- Web page: https://patentgrep.com/patent/US20250156466A1

## CPC

- G06F 16/345: {Summarisation for human users}
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F 40/56: Natural language generation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A document reading support method using a language model is provided. The document reading support method includes the steps of: displaying a segmented document; receiving selection of a part of the document; inputting the part and an instruction sentence for summarizing the part to a language model; determining whether the number of tokens of the part is less than or equal to a predetermined value; and obtaining a summary of the part determined to have the tokens of less than or equal to the predetermined value.

## Claims

### Claim 1

A document reading support method comprising the steps of:
displaying a segmented first document;
receiving selection of a part of the first document as a second document;
inputting the second document and an instruction sentence for summarizing the second document to a language model;
determining whether the number of tokens of the second document is less than or equal to a predetermined value; and
obtaining a summary of the second document determined to have the tokens of less than or equal to the predetermined value.

### Claim 2

A document reading support method comprising the steps of:
displaying a document segmented into a plurality of sections comprising at least a first section;
receiving selection of the first section;
inputting the first section and an instruction sentence for summarizing the first section to a language model;
determining whether the number of tokens of the first section is less than or equal to a predetermined value; and
obtaining a summary of the first section determined to have the tokens of less than or equal to the predetermined value.

### Claim 3

A document reading support method comprising the steps of:
displaying a drawing and a segmented document;
receiving selection of the drawing;
collecting a sentence related to the selected drawing from the document;
inputting the collected sentence and an instruction sentence for summarizing the collected sentence to a language model;
determining whether the number of tokens of the collected sentence is less than or equal to a predetermined value; and
obtaining a summary of the collected sentence determined to have the tokens of less than or equal to the predetermined value.

### Claim 4 (depends on 3)

The document reading support method according to claim 3,
wherein the document is in a first language,
wherein the instruction sentence is in a second language, and
wherein the summary generated by the language model is in the first language.

### Claim 5 (depends on 4)

The document reading support method according to claim 4, wherein the summary is translated into the first language from the second language.

### Claim 6 (depends on 3)

The document reading support method according to claim 3, further comprising the step of:
displaying the summary generated by the language model,
wherein a first word not used in the document is highlighted in the displayed summary.

### Claim 7 (depends on 3)

The document reading support method according to claim 3, further comprising the step of:
displaying the summary generated by the language model,
wherein a sentence comprising a second word in the document is displayed when the second word is selected in the displayed summary.

### Claim 8 (depends on 3)

The document reading support method according to claim 3,
wherein an alert is displayed when the number of tokens is greater than the predetermined value in the step of determining whether the number of tokens is less than or equal to the predetermined value.
