# US 12,190,872 B2 · Electronic apparatus and controlling method thereof

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

- Number: US 12,190,872 B2
- Document ID: US12190872B2
- Status: Granted
- Kind: B2
- Application number: 17/713,546
- Filed: 2022-04-05
- Published: 2023-02-16
- Granted: 2025-01-07
- Earliest claimed: 2021-08-10
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Ali Ahmad Adel Al Massaeed; Abdelrahman Mustafa Mahmoud Yaseen; Shrouq Walid Jamil Sabah
- Web page: https://patentgrep.com/patent/US12190872B2

## CPC

- G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning}
- G06F 3/048: Interaction techniques based on graphical user interfaces [GUI]
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L 15/05: Word boundary detection
- G10L 15/1822: {Parsing for meaning understanding}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 17/08: Use of distortion metrics or a particular distance between probe pattern and reference templates
- G10L 17/24: the user being prompted to utter a password or a predefined phrase
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- 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)

## Abstract

An electronic apparatus includes: a memory storing one or more commands; and a processor connected to the memory and configured to control the electronic apparatus, wherein the processor is configured, by executing the one or more instructions, to: identify a first intention word and a first target word from first speech, acquire second speech received after the first speech based on at least one of the identified first intention word or the identified first target word not matching a word stored in the memory, acquire a similarity between the first speech and the second speech, and acquire response information based on the first speech and the second speech based on the similarity being a threshold value or more.

## Claims

### Claim 1

An electronic apparatus comprising:
a memory storing one or more commands; and
a processor connected to the memory and configured to control the electronic apparatus,
wherein the processor comprises processing circuitry and is configured, by executing the one or more instructions, to:
identify a first intention word and a first target word from first speech,
acquire second speech received after the first speech based on at least one of the identified first intention word or the identified first target word not matching a word stored in the memory,
acquire a similarity between the first speech and the second speech, and
acquire response information based on the first speech and the second speech based on the similarity being a threshold value or more,
based on the first intention word not matching an intention word stored in the memory and the first target word matching a target word stored in the memory,
acquire a second intention word included in the second speech,
acquire a first similarity between the first intention word and the second intention word based on the second intention word matching the intention word stored in the memory, and
acquire response information based on the second intention word and the first target word based on the first similarity being a threshold value or more, and/or
based on the first intention word matching an intention word stored in the memory and the first target word not matching a target word stored in the memory,
acquire a second target word included in the second speech
acquire second similarity between the first target word and the second target word based on the second target word matching the target word stored in the memory, and
acquire response information based on the first intention word and the second target word based on the second similarity being a threshold value or more.

### Claim 2 (depends on 1)

The electronic apparatus as claimed in claim 1, wherein the processor is configured to acquire a user interface (UI) configured to provide a guide to utter the second speech based on at least one of the identified first intention word or the identified first target word not matching the word stored in the memory.

### Claim 3 (depends on 1)

The electronic apparatus as claimed in claim 1, wherein the processor is configured to acquire speech received within a preset time as the second speech based on at least one of the identified first intention word or the identified first target word not matching the word stored in the memory.

### Claim 4 (depends on 1)

The electronic apparatus as claimed in claim 1, wherein the processor is configured to acquire a UI including information notifying that the response information is not acquired based on the second intention word not matching the intention word stored in the memory, and
the UI includes the second intention word.

### Claim 5 (depends on 1)

The electronic apparatus as claimed in claim 1, wherein the processor is configured to acquire a UI including information notifying that the response information is not acquired based on the second target word not matching the target word stored in the memory, and
the UI includes the second target word.

### Claim 6 (depends on 1)

The electronic apparatus as claimed in claim 1, wherein the processor is configured to:
acquire a second intention word and a second target word included in the second speech based on the first intention word not matching an intention word stored in the memory and the first target word not matching a target word stored in the memory,
acquire a first similarity between the first intention word and the second intention word based on the second intention word matching the intention word stored in the memory,
acquire a second similarity between the first target word and the second target word based on the second target word matching the target word stored in the memory, and
acquire response information based on the second intention word and the second target word based on the first similarity being a threshold value or more and the second similarity being the threshold value or more.

### Claim 7 (depends on 6)

The electronic apparatus as claimed in claim 6, wherein the processor is configured to acquire a UI including information notifying that the response information is not acquired based on the intention word not matching the intention word stored in the memory or the second target word not matching the target word stored in the memory, and
the UI includes the second target word.

### Claim 8 (depends on 1)

The electronic apparatus as claimed in claim 1, wherein the processor is configured to:
acquire a second intention word and a second target word from the second speech,
acquire a first similarity between the first intention word and the second intention word,
acquire a second similarity between the first target word and the second target word, and
acquire third speech received after the second speech based on the first similarity being less than a threshold value or the second similarity being less than a second threshold value.

### Claim 9

A method of controlling an electronic apparatus, the method comprising:
identifying a first intention word and a first target word from first speech;
acquiring second speech received after the first speech based on at least one of the identified first intention word or the identified first target word not matching a word stored in the memory of the electronic apparatus;
acquiring a similarity between the first speech and the second speech; and
acquiring response information based on the first speech and the second speech based on the similarity being a threshold value or more,
based on the first intention word not matching an intention word stored in the memory and the first target word matching a target word stored in the memory,
acquiring a second intention word included in the second speech,
acquiring a first similarity between the first intention word and the second intention word based on the second intention word matching the intention word stored in the memory, and
acquiring response information based on the second intention word and the first target word based on the first similarity being a threshold value or more, and/or based on the first intention word matching an intention word stored in the memory and the first target word not matching a target word stored in the memory,
acquiring a second target word included in the second speech,
acquiring second similarity between the first target word and the second target word based on the second target word matching the target word stored in the memory, and
acquiring response information based on the first intention word and the second target word based on the second similarity being a threshold value or more.

### Claim 10 (depends on 9)

The method as claimed in claim 9, further comprising acquiring a user interface (UI) configured to provide a guide to utter the second speech based on at least one of the identified first intention word or the identified first target word not matching the word stored in the memory.

### Claim 11 (depends on 9)

The method as claimed in claim 9, further comprising acquiring speech received within a preset time as the second speech based on at least one of the identified first intention word or the identified first target word not matching the word stored in the memory.

### Claim 12 (depends on 9)

The method as claimed in claim 9, further comprising acquiring a UI including information notifying that the response information is not acquired based pm the second intention word not matching the intention word stored in the memory,
wherein the UI includes the second intention word.

### Claim 13 (depends on 9)

The method as claimed in claim 9, further comprising acquiring a UI including information notifying that the response information is not acquired based on the second target word not matching the target word stored in the memory,
wherein the UI includes the second target word.

### Claim 14 (depends on 9)

The method as claimed in claim 9, further comprising acquiring a second intention word and a second target word included in the second speech based on the first intention word not matching an intention word stored in the memory and the first target word not matching a target word stored in the memory,
wherein in the acquiring of the similarity, a first similarity between the first intention word and the second intention word is acquired based on the second intention word matching the intention word stored in the memory, and a second similarity between the first target word and the second target word is acquired based on the second target word matching the target word stored in the memory, and
in the acquiring of the response information, the response information is acquired based on the second intention word and the second target word based on the first similarity being a threshold value or more and the second similarity being the threshold value or more.

### Claim 15 (depends on 14)

The method as claimed in claim 14, further comprising acquiring a UI including information notifying that the response information is not acquired based on the intention word not matching the intention word stored in the memory or the second target word not matching the target word stored in the memory,
wherein the UI includes the second target word.

### Claim 16 (depends on 9)

The method as claimed in claim 9, further comprising acquiring a second intention word and a second target word from the second user's speech,
wherein in the acquiring of the similarity, a first similarity between the first intention word and the second intention word is acquired, and a second similarity between the first target word and the second target word is acquired, and
the method further includes acquiring third speech received after the second speech based on the first similarity being less than a threshold value or the second similarity being less than a second threshold value.