# US 2026/0245560 A1 · Electronic device and method for processing user utterance

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

- Number: US 2026/0245560 A1
- Document ID: US20260245560A1
- Status: Published application
- Kind: A1
- Application number: 19/646,136
- Filed: 2026-04-13
- Published: 2026-08-20
- Earliest claimed: 2023-10-13
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Sangmin PARK; Gajin Song; Kyungtae Kim
- Web page: https://patentgrep.com/patent/US20260245560A1

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G06F 40/279: Recognition of textual entities
- G06N 3/092: Reinforcement learning
- G10L 15/04: Segmentation; Word boundary detection
- G10L 15/10: using distance or distortion measures between unknown speech and reference templates
- G10L 15/1822: {Parsing for meaning understanding}
- G10L 25/51: for comparison or discrimination
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An operation method of an electronic device includes: receiving a first input from a user; based on receiving the first input, creating a first session; providing a first output corresponding to the first input, based on a generative model; receiving a second input from the user; based on a condition between the first input and the second input and a condition between the first output and the second input being satisfied, creating a second session that is different from the first session; and providing a second output corresponding to the second input, based on the generative model.

## Claims

### Claim 1

An operating method of an electronic device, the operating method comprising:
receiving a first input from a user;
based on receiving the first input, creating a first session;
providing a first output corresponding to the first input, based on a generative model;
receiving a second input from the user;
based on a condition between the first input and the second input and a condition between the first output and the second input being satisfied, creating a second session that is different from the first session; and
providing a second output corresponding to the second input, based on the generative model.

### Claim 2 (depends on 1)

The operating method of claim 1, wherein the providing the first output comprises:
configuring first prompt text;
generating first text data by inputting the first prompt text to the generative model;
performing a first task corresponding to the first input, based on the first text data; and
providing the first output corresponding to the first task.

### Claim 3 (depends on 2)

The operating method of claim 2, wherein the providing the second output comprises:
configuring second prompt text;
generating second text data by inputting the second prompt text to the generative model;
performing a second task corresponding to the second input, based on the second text data; and
providing the second output corresponding to the second task.

### Claim 4 (depends on 3)

The operating method of claim 3, wherein information used in the first session to configure the first prompt text is different from information used in the second session to configure the second prompt text.

### Claim 5 (depends on 1)

The operating method of claim 1, wherein each of the first session and the second session comprises an input of the user and an output of the electronic device, and
wherein the second session is created based on both a correlation between the first input and the second input and a correlation between the first output and the second input being less than a threshold value.

### Claim 6 (depends on 5)

The operating method of claim 5, wherein each of the correlation between the first input and the second input and the correlation between the first output and the second input is determined based on a similarity between utterances or reinforcement learning with human feedback.

### Claim 7 (depends on 1)

The operating method of claim 1, wherein the providing the second output comprises providing the second output after reviewing appropriateness of the second output.

### Claim 8

An electronic device comprising:
at least one processor; and
memory storing instructions,
wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to:
receive a first input from a user;
based on receiving the first input, create a first session;
provide a first output corresponding to the first input, based on a generative model;
receive a second input from the user;
based on a condition between the first input and the second input and a condition between the first output and the second input being satisfied, create a second session that is different from the first session; and
provide a second output corresponding to the second input, based on the generative model.

### Claim 9 (depends on 8)

The electronic device of claim 8, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to:
configure first prompt text;
generate first text data by inputting the first prompt text to the generative model;
perform a first task corresponding to the first input, based on the first text data; and
provide the first output corresponding to the first task.

### Claim 10 (depends on 9)

The electronic device of claim 9, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to:
configure second prompt text;
generate second text data by inputting the second prompt text to the generative model;
perform a second task corresponding to the second input, based on the second text data; and
provide the second output corresponding to the second task.

### Claim 11 (depends on 10)

The electronic device of claim 10, wherein information used in the first session to configure the first prompt text is different from information used in the second session to configure the second prompt text.

### Claim 12 (depends on 8)

The electronic device of claim 8, wherein each of the first session and the second session comprises an input of the user and an output of the electronic device, and
wherein the second session is created based on both a correlation between the first input and the second input and a correlation between the first output and the second input being less than a threshold value.

### Claim 13 (depends on 12)

The electronic device of claim 12, wherein each of the correlation between the first input and the second input and the correlation between the first output and the second input is determined based on a similarity between utterances or reinforcement learning with human feedback.

### Claim 14 (depends on 8)

The electronic device of claim 8, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to provide the second output after reviewing appropriateness of the second output.

### Claim 15

An operating method of an electronic device, the operating method comprising:
receiving a first input from a user;
based on receiving the first input, creating a first session;
providing a first output corresponding to the first input, based on a generative model;
receiving a second input from the user;
adaptively configuring prompt text based on at least one of a correlation between the first input and the second input or a correlation between the first output and the second input; and
providing a second output corresponding to the second input by inputting the prompt text to the generative model.

### Claim 16 (depends on 15)

The operating method of claim 15, wherein when the correlation between the first input and the second input and the correlation between the first output and the second input are less than a threshold value, the second input may be managed through a different session from the first input, and
wherein when at least one of the correlation between the first input and the second input or the correlation between the first output and the second input is greater than or equal to the threshold value, the second input may be managed through the same session as the first input.

### Claim 17 (depends on 16)

The operating method of claim 16, wherein when the second input is managed through the same session as the first input, the prompt text may be configured based on at least one of the first input or the first output.

### Claim 18 (depends on 15)

The operating method of claim 15, wherein the providing the second output comprises:
generating text data by inputting the prompt text to the generative model;
performing a task corresponding to the second input based on the text data; and
providing the second output corresponding to the task.

### Claim 19 (depends on 15)

The operating method of claim 15, wherein the at least one is determined based on a similarity between utterances or RLHF.

### Claim 20 (depends on 15)

The operating method of claim 15, wherein the providing the second output comprises provide the second output after reviewing the appropriateness of the second output.
