System and method for providing voice assistance service

Patent metadata

Field	Value
Publication number	US-11961512-B2
Application number	US-202117385370-A
Country	US
Kind code	B2
Filing date	Jul 26, 2021
Priority date	Jan 25, 2019
Publication date	Apr 16, 2024
Grant date	Apr 16, 2024

Abstract

An artificial intelligence (AI) system using a machine learning algorithm such as deep learning, and an application thereof are provided. A method of providing, by a device, a voice assistance service includes obtaining a voice input of a user, receiving certain context information from at least one peripheral device, generating first query information from the received context information and the voice input, generating second query information including noise information by inputting the first query information into a noise learning model, transmitting the generated second query information to a server, receiving, from the server, response information obtained based on the transmitted second query information, generating a response message by removing response information corresponding to the noise information from the received response information, and outputting the response message.

First claim

What is claimed is:

1. A method of a device providing a voice assistance service, the method comprising:
obtaining a voice input of a user;
in response to obtaining the voice input, receiving context information from at least one peripheral device;
generating first query information from the context information and the voice input;
generating second query information including noise information by inputting the first query information into a noise learning model;
transmitting the second query information to a server;
receiving, from the server, response information obtained based on the second query information;
generating a response message by removing a portion of the response information corresponding to the noise information from the response information; and
outputting the response message,
wherein the context information comprises at least one of an image, a measurement value, or sensing data that are obtained from the at least one peripheral device, and
wherein the portion of the response information corresponding to the noise information is identified based on the first query information.

2. The method of claim 1 , wherein the noise learning model comprises an artificial intelligence algorithm that is a learning model having been trained by using at least one of machine learning, a neural network, a genetic algorithm, deep learning, or a classification algorithm.

3. The method of claim 1 , wherein the receiving of the context information comprises:
based on the voice input, determining a type of context information to be received; and
requesting a peripheral device corresponding to the determined type for the context information of the determined type.

4. The method of claim 3 , wherein the determining of the type of the context information to be received comprises determining a type of context information required to generate response information with respect to the voice input, by interpreting the voice input by using a voice interpretation model.

5. The method of claim 1 ,
wherein the context information comprises an image obtained by the at least one peripheral device, and
wherein the method further comprises recognizing an object related to the voice input among objects in the image by using an object recognition model.

6. The method of claim 1 ,
wherein the context information comprises numerical data representing a body state of the user, and
wherein the generating of the second query information including the noise information comprises changing a value of the numerical data representing the body state of the user according to a preset reference.

7. The method of claim 1 , wherein the response message is obtained by removing the portion of the response information corresponding to the noise information by inputting the first query information into a response learning model.

8. A computer program product comprising a non-transitory computer-readable recording medium having recorded thereon a program for executing the method of claim 1 .

9. A device for providing a voice assistance service, the device comprising:
a communication interface;
a processor; and
a memory storing one or more instructions which, when executed by the processor, cause the processor to:
obtain a voice input of a user,
in response to obtaining the voice input, receive context information from at least one peripheral device,
generate first query information from the context information and the voice input,
generate second query information including noise information by inputting the first query information into a noise learning model,
transmit the second query information to a server,
receive, from the server, response information obtained based on the second query information,
generate a response message by removing a portion of the response information corresponding to the noise information from the response information, and
output the response message,

wherein the context information comprises at least one of an image, a measurement value, or sensing data that are obtained from the at least one peripheral device, and
wherein the portion of the response information corresponding to the noise information is identified based on the first query information.

10. The device of claim 9 , wherein the noise learning model comprises an artificial intelligence algorithm that is a learning model having been trained by using at least one of machine learning, an artificial neural network, a genetic algorithm, deep learning, or a classification algorithm.

11. The device of claim 9 , wherein the processor is further configured to:
determine a type of context information to be received, based on the voice input, and
request a peripheral device corresponding to the determined type for the context information of the determined type.

12. The device of claim 11 , wherein the processor is further configured to determine a type of context information required to generate response information with respect to the voice input, by interpreting the voice input by using a voice interpretation model.

13. The device of claim 10 , wherein the response message is obtained by removing the portion of the response information corresponding to the noise information by inputting the first query information into a response learning model.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Choi Wonjong
• Kim Soofeel
• Park Yewon
• Ham Jina

Classifications

• G06N3/092

  Reinforcement learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G10L2015/226

  using non-speech characteristics · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title