US 11,081,109 B2 · Speech processing method using artificial intelligence device

Abstract

Provided is a speech processing method using an AI device. The speech processing method using an AI device according to an embodiment of the present invention includes receiving a speech command of a speaker, determining a recipient of the speech command by performing a speech recognition operation on the speech command, checking whether the recipient receives feedback corresponding to the speech command, selecting a second AI device which is closest to the recipient based on pre-stored positional information of a plurality of AI devices in a specific space and positional information of the recipient by obtaining the positional information of the recipient if there is no feedback, and transmitting a notification message notifying the speech command to the second AI device. As a result, the speech command of the speaker can be successfully transmitted to a recipient when the recipient does not receive the speech command of the speaker. According to the present invention, at least one of an autonomous vehicle, a user terminal, and a server may be linked with an artificial intelligence module, a drone (unmanned aerial vehicle (UAV)), a robot, an augmented reality (AR) device, a virtual reality (VR) device, devices related to 5G services and the like.

Claims20

Dependent claims

A speech processing method using an artificial intelligence (AI) device using a first AI device in a space in which a speaker, at least one recipient who receives a speech command uttered by the speaker, and a plurality of AI devices which perform a speech interaction with the speaker and the at least one recipient are positioned, the speech processing method comprising:

receiving the speech command uttered by the speaker;
determining at least one specific recipient of the speech command by performing a speech recognition operation on the received speech command;
checking whether at least one feedback response corresponding to the speech command is received from the at least one specific recipient;
obtaining positional information of a recipient who does not transmit the at least one feedback response among the at least one specific recipient when there is feedback which is not received among the at least one feedback response;
selecting at least one second AI device closest to a position of the recipient who does not transmit the at least one feedback response based on pre-stored positional information of the plurality of AI devices in the space and the positional information of the recipient who does not transmit the at least one feedback response;
and
transmitting a notification message notifying that there is the speech command to the at least one second AI device.

4 more elements

An intelligent computing device for supporting a speech processing method using an artificial intelligence (AI) device in a space in which a speaker, at least one recipient who receives a speech command uttered by the speaker, and a plurality of AI devices which perform a speech interaction with the speaker and the at least one recipient are positioned, the intelligent computing device comprising:

a sensing unit including at least one sensor;
a communication unit;
a processor;
and
a memory including one or more instructions executable by the processor;
wherein the one or more instructions configure the processor:
to receive a speech command uttered by the speaker, and perform a speech recognition operation on the received speech command to determine at least one specific recipient of the speech command;
to check whether at least one feedback response corresponding to the speech command is received from the at least one specific recipient;
to obtain positional information of a recipient who does not transmit the at least one feedback response among the at least one specific recipient when there is feedback which is not received among the at least one feedback response;
to select at least one second AI device closest to a position of the recipient who does not transmit the at least one feedback response based on pre-stored positional information of the plurality of AI devices in the space and the positional information of the recipient who does not transmit the at least one feedback response;
and
to transmit a notification message notifying that there is the speech command to the at least one second AI device.

9 more elements

Dependencies are inferred from the claim text.

Speech processing method using artificial intelligence device

Life of this patent

Speech processing method using artificial intelligence device

Life of this patent

Abstract

Claims20