# US 2019/0378515 A1 · Dialogue system, vehicle and method for controlling the vehicle

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

- Number: US 2019/0378515 A1
- Document ID: US20190378515A1
- Status: Published application
- Kind: A1
- Application number: 16/191,738
- Filed: 2018-11-15
- Published: 2019-12-12
- Earliest claimed: 2018-06-12
- Assignees: Hyundai Motor Company; Kia Motors Corporation
- Applicants: Hyundai Motor Company; Kia Motors Corporation
- Inventors: Kye Yoon KIM; Donghee SEOK; Dongsoo SHIN; Jeong-Eom LEE; Ga Hee KIM; Seona KIM; Jung Mi PARK; HeeJin RO
- Web page: https://patentgrep.com/patent/US20190378515A1

## CPC

- G06F 40/35: Discourse or dialogue representation
- G10L 17/00: Speaker identification or verification techniques
- G10L 17/22: Interactive procedures; Man-machine interfaces
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A dialogue system, a vehicle and a method for controlling the vehicle is disclosed. The method for controlling the vehicle includes: acquiring an utterance and a speech pattern by recognizing a speech when a speech of a plurality of speakers is input through a speech input device; classifying dialogue contents for each speaker based on the acquired utterance and speech pattern; acquiring a relationship between the speakers based on the acquired utterance; understanding an intention and a context for each speaker based on the acquired relationship between the speakers and the acquired dialogue content for each speaker determining an action corresponding to the acquired relationship and the acquired intention and context for each speaker, and outputting an utterance corresponding to the determined action; generating a control command corresponding to the determined action; and controlling a load based on the generated control command.

## Claims

### Claim 1

A dialogue system comprising:
a speech input processor configured to:
when a speech of a plurality of speakers is input, acquire an utterance and a speech pattern by recognizing the input speech, and
classify dialogue contents for each speaker of the plurality of speakers based on the acquired utterance and speech pattern;
a context information processor configured to:
acquire a relationship between speakers of the plurality of speakers based on the acquired utterance, and
determine an intention and a context for each speaker of the plurality of speakers based on the acquired relationship between the speakers of the plurality of speakers and the classified dialogue contents for each speaker of the plurality of speakers;
a storage configured to store the relationship between the speakers of the plurality of speakers and the speech pattern for each speaker of the plurality of speakers;
a dialogue manager configured to determine an action corresponding to the acquired relationship and the intention and context for each speaker of the plurality of speakers; and
a result processor configured to output an utterance corresponding to the determined action.

### Claim 2 (depends on 1)

The dialogue system of claim 1, wherein
when receiving contact information from a mobile device, the context information processor is configured to: acquire at least one of a name, a title, or a phone number of a speaker who has a dialogue with a user, based on the received contact information, and acquire the relationship between the speakers of the plurality of speakers based on the acquired at least one of the name, the title, or the phone number of the speaker having the dialogue with the user.

### Claim 3 (depends on 1)

The dialogue system of claim 1, wherein:
the context information processor is configured to determine a priority between the speakers of the plurality of speakers based on the acquired relationship of the speakers of the plurality of speakers,
the storage is configured to store function control information for each speaker of the plurality of speakers,
the dialogue manager is configured to determine an action corresponding to the determined priority and the stored function control information, and
the result processor is configured to generate a control command controlling a function based on the determined priority and the stored function control information for each speaker of the plurality of speakers, and to output the generated control command to a device.

### Claim 4 (depends on 1)

The dialogue system of claim 1, further comprising:
a pre-utterance determiner configured to determine a pre-utterance context,
wherein the context information processor is configured to determine a priority between the speakers of the plurality of speakers based on the acquired relationship between the speakers of the plurality of speakers and recognize a speaker of the plurality of speakers having a highest priority based on the determined priority; and
the dialogue manager is configured to determine an action corresponding to the speaker having the highest priority and the pre-utterance context.

### Claim 5

A vehicle comprising:
a plurality of loads;
a speech input device configured to receive a speech;
a dialogue system configured to:
acquire an utterance and a speech pattern by recognizing a speech input through the speech input device,
classify dialogue contents for each speaker of a plurality of speakers based on the acquired utterance and the speech pattern,
acquire a relationship between speakers of the plurality of speakers based on the acquired utterance,
determine an intention and a context for each speaker of the plurality of speakers based on the acquired relationship between the speakers of the plurality of speakers and the classified dialogue contents for each speaker of the plurality of speakers,
determine an action corresponding to the acquired relationship between the speakers of the plurality of speakers, and the acquired intention and the context of each speaker of the plurality of speakers,
output an utterance corresponding to the determined action, and
generate a control command corresponding to the determined action; and
a vehicle controller configured to control at least one load among the plurality of loads, based on the received control command, when the control command is received.

### Claim 6 (depends on 5)

The vehicle of claim 5, further comprising:
a communication device configured to communicate with a mobile device,
wherein the dialogue system is configured to:
acquire at least one of a name, a title, or a phone number of a speaker who has a dialogue with a user, based on contact information when receiving the contact information from the mobile device,
acquire a relationship between speakers of the plurality of speakers based on the acquired at least one of the name, the title, or the phone number of the speaker having the dialogue with the user, and
store at least one information of a name, a title, or a phone number for each speaker of the plurality of speakers, the relationship between the speakers of the plurality of speakers, and a speech pattern for each speaker of the plurality of speakers.

### Claim 7 (depends on 6)

The vehicle of claim 6, wherein, the dialogue system is configured to:
receive function control information for controlling functions of the vehicle from a mobile device of the plurality of speakers,
store the received function control information for each speaker of the plurality of speakers in a storage,
determine a priority between speakers of the plurality of speakers based on the relationship between the speakers of the plurality of speakers,
determine an action corresponding to the determined priority and the stored function control information,
generate a control command controlling at least one function based on the determined priority and the stored function control information, and
output the generated control command to at least one load among the plurality of loads.

### Claim 8 (depends on 7)

The vehicle of claim 7, wherein,
the dialogue system is configured to recognize a speech when the speech is input through the speech input device, and recognize a speaker by comparing the recognized speech pattern of the speech with a speech pattern stored in the storage.

### Claim 9 (depends on 7)

The vehicle of claim 7, wherein,
the function control information comprises seat angle information for each seat of a plurality of seats, information of a horizontal position of each seat in front side and a rear side, a wind volume and a wind direction of air conditioner information, seat heating wire on/off information, seat heating wire temperature information, seat ventilation on/off information, and lumber support information.

### Claim 10 (depends on 9)

The vehicle of claim 9, further comprising:
an information except for the speech input device,
wherein the dialogue system is configured to store a seat location for a speaker input through the information except for the speech input device.

### Claim 11 (depends on 9)

The vehicle of claim 9, wherein
the dialogue system is configured to recognize an utterance position based on a time at which a signal of a speech reaches the speech input device, identify a seat location corresponding to the recognized utterance position, recognize a speech pattern of a speech reaching at the speech input device, match the recognized speech pattern of the speech with the identified seat location, and store information of the matching the recognized speech pattern of the speech with the identified seat location.

### Claim 12 (depends on 11)

The vehicle of claim 11, further comprising:
a detector provided in the plurality of seats and configured to detect the seat angle information of the plurality of seats and the horizontal position of each seat in the front and rear sides,
wherein the dialogue system is configured to match the seat angle information and the horizontal position with the identified seat location, and store information of the matching the seat angle information and the horizontal position with the identified seat location.

### Claim 13 (depends on 5)

The vehicle of claim 5, wherein
the dialogue system is configured to determine a pre-utterance context and output an utterance corresponding to the pre-utterance context based on the relationship between the speakers of the plurality of speakers.

### Claim 14 (depends on 13)

The vehicle of claim 13, wherein
the dialogue system is configured to determine a priority between speakers of the plurality of speakers based on the relationship between the speakers of the plurality of speakers, recognize a speaker having a highest priority based on the determined priority, and determine an action corresponding to the speaker having the highest priority and the pre-utterance context.

### Claim 15 (depends on 5)

The vehicle of claim 5, wherein
when an intention of a currently input utterance is determined as a response to a previously input speech, the dialogue system is configured to acquire a relationship with the speaker of the currently input utterance based on an utterance corresponding to the previously input speech.

### Claim 16 (depends on 15)

The vehicle of claim 15, wherein
the dialogue system is configured to match the acquired relationship of the speaker of the currently input speech, with a speech pattern of the currently input speech, and store matched information thereof.

### Claim 17

A method for controlling a vehicle, the method comprising:
when a speech of a plurality of speakers is input through a speech input device, acquiring an utterance and a speech pattern by recognizing the speech;
classifying dialogue contents for each speaker of the plurality of speakers based on the acquired utterance and the speech pattern;
acquiring a relationship between speakers of the plurality of speakers based on the acquired utterance;
determining an intention and a context for each speaker of the plurality of speakers based on the acquired relationship;
determining an action corresponding to the acquired relationship and the acquired intention and context for each speaker of the plurality of speakers, and outputting an utterance corresponding to the determined action;
generating a control command corresponding to the determined action; and
controlling at least one load among a plurality of loads based on the generated control command.

### Claim 18 (depends on 17)

The control method of claim 17, further comprising:
acquiring at least one of a name, a title, or a phone number of a speaker of the plurality of speakers based on contact information received from a mobile device;
acquiring the relationship between the speakers of the plurality of speakers based on the at least one of the name, the title, or the phone number of the speaker of the plurality of speakers; and
storing at least one of a name, a title, and a phone number for each speaker, and the relationship between the speakers of the plurality of speakers, in a storage.

### Claim 19 (depends on 18)

The control method of claim 18, further comprising:
receiving function control information for controlling functions of the vehicle, from mobile devices of the plurality of speakers;
determining a priority between the speakers of the plurality of speakers based on the relationship between the speakers of the plurality of speakers;
determining an action corresponding to the determined priority and the received function control information for each speaker;
generating a control command controlling at least one function based on the determined priority and the received function control information for each speaker; and
outputting the generated control command to at least one load among the plurality of loads.

### Claim 20 (depends on 17)

The control method of claim 17, further comprising:
receiving a seat location for a speaker; and
storing the seat location for the speaker.

### Claim 21 (depends on 17)

The control method of claim 17, further comprising:
recognizing an utterance position based on a time at which a signal of a speech reaches at the speech input device;
identifying a seat location corresponding to the recognized utterance position;
recognizing a speech pattern of a speech reaching at the speech input device; and
matching the recognized speech pattern of the speech with the identified seat location, and storing matched information thereof.

### Claim 22 (depends on 21)

The control method of claim 21, further comprising:
determining a priority between the speakers of the plurality of speakers based on the relationship between the speakers of the plurality of speakers;
recognizing a speaker having a highest priority based on the determined priority and determining a pre-utterance context; and
outputting an utterance corresponding to the speaker having the highest priority and the pre-utterance context when the pre-utterance context is determined.

### Claim 23 (depends on 17)

The control method of claim 17, wherein
acquiring the relationship between the speakers of the plurality of speakers based on the acquired utterance comprises:
when an intention of a currently input utterance is determined as a response to a previously input speech, acquiring a relationship with a speaker of the currently input utterance based on an utterance corresponding to the previously input speech; and
matching the acquired relationship of the speaker of the currently input utterance with a speech pattern of the currently input speech, and storing matched information thereof.
