Electronic device and control method therefor
The present disclosure provides an electronic device and a control method therefor. The electronic device of the present disclosure comprises: a voice reception unit; and a processor for, when a first user voice and a second user voice are received through the voice reception unit, determining whether the second user voice corresponds to a candidate of utterance subsequent to the first user voice on the basis of a result obtained by dividing a plurality of attributes of the second user voice according to a predefined attribute, and controlling the electronic device to perform an operation corresponding to the second user voice on the basis of the intent of the second user voice obtained through a result of the determination.
1. An electronic device comprising:
a voice reception part; and
a processor configured to:
based on a first user voice and a second user voice being received through the voice reception part, determine whether the second user voice corresponds to a subsequent utterance candidate of the first user voice based on a result obtained by classifying a plurality of attributes of the second user voice according to a predefined attribute, and control the electronic device to perform an operation corresponding to the second user voice based on intent of the second user voice obtained through a result of the determination,
wherein the processor is further configured to:
determine whether the second user voice corresponds to a subsequent utterance candidate of the first user voice based on a plurality of adjusted attribute values in which different weights are applied to attribute values of a plurality of classified attributes according to relevance to the predefined attribute.
2. The electronic device of claim 1 ,
wherein the processor is configured to:
classify the plurality of attributes according to relevance to the predefined attribute; and
adjust attribute values of the plurality of classified attributes by applying different weights to the attribute values of the plurality of classified attributes according to the relevance to the predefined attribute.
3. The electronic device of claim 2 ,
wherein the plurality of attributes is classified into a first attribute having the relevance to the predefined attribute and a second attribute having no relevance to the predefined attribute, and
the processor is configured to:
adjust a first attribute value for the first attribute obtained from the second user voice based on a first weight corresponding to the first attribute; and
adjust a second attribute value for the second attribute obtained from the second user voice based on a second weight corresponding to the second attribute, and
the first weight is bigger larger than the second weight.
4. The electronic device of claim 3 ,
wherein the predefined attribute includes a time attribute indicating a time interval at which the first user voice and the second user voice were received,
the first attribute includes at least one of an utterance frequency or a device state attribute indicating a state of the electronic device, and
the second attribute includes at least one of a speaker attribute indicating whether a user who uttered the first user voice and a user who uttered the second user voice are a same user or a command attribute indicating similarity between commands included in the first user voice and the second user voice.
5. The electronic device of claim 1 ,
wherein the processor is configured to:
determine respectively a user who uttered the first user voice and a user who uttered the second user voice; and
based on the determination that the user who uttered the first user voice and the user who uttered the second user voice being the same, obtain the plurality of attribute values of the second user voice.
6. The electronic device of claim 1 ,
wherein the processor is configured to:
based on the second user voice being received within a predetermined time after the first user voice was received, classify the plurality of attributes of the second user voice according to the predefined attribute.
7. The electronic device of claim 1 ,
wherein the processor is configured to:
based on the second user voice being received after the first user voice corresponding to the subsequent utterance candidate, determine the intent of the second user voice based on intent and a domain of the first user voice.
8. An electronic device comprising:
a voice reception part; and
a processor configured to:
based on a first user voice and a second user voice being received through the voice reception part, determine whether the second user voice corresponds to a subsequent utterance candidate of the first user voice based on a result obtained by classifying a plurality of attributes of the second user voice according to a predefined attribute, and control the electronic device to perform an operation corresponding to the second user voice based on intent of the second user voice obtained through a result of the determination,
wherein the processor is configured to:
classify the plurality of attributes according to relevance to the predefined attribute;
adjust attribute values obtained from the plurality of classified attributes;
sum up the plurality of adjusted attribute values; and
based on a summed-up attribute value being larger than a predetermined threshold, determine that the second user voice corresponds to the subsequent utterance candidate, and based on the summed-up attribute value being smaller than or equal to the predetermined threshold, determine that the second user voice does not correspond to the subsequent utterance candidate.
9. A control method for an electronic device, the method comprising:
receiving a first user voice and a second user voice;
determining whether the second user voice corresponds to a subsequent utterance candidate of the first user voice based on a result obtained by classifying a plurality of attributes of the second user voice according to a predefined attribute; and
controlling the electronic device to perform an operation corresponding to the second user voice based on intent of the second user voice obtained through a result of the determination,
wherein the determining comprises:
determining whether the second user voice corresponds to a subsequent utterance candidate of the first user voice based on a plurality of adjusted attribute values in which different weights are applied to attribute values of a plurality of classified attributes according to relevance to the predefined attribute.
10. The control method of claim 9 ,
wherein the determining comprises:
classifying the plurality of attributes according to relevance to the predefined attribute; and
adjusting attribute values of the plurality of classified attributes by applying different weights to the attribute values of the plurality of classified attributes according to the relevance to the predefined attribute.
11. The control method of claim 9 ,
wherein the plurality of attributes is classified into a first attribute having the relevance to the predefined attribute and a second attribute having no relevance to the predefined attribute; and
the adjusting a plurality of attribute values comprises:
adjusting a first attribute value for the first attribute obtained from the second user voice based on a first weight corresponding to the first attribute; and
adjusting a second attribute value for the second attribute obtained from the second user voice based on a second weight corresponding to the second attribute, and
the first weight is larger than the second weight.
12. The control method of claim 11 ,
wherein the predefined attribute includes a time attribute indicating a time interval at which the first user voice and the second user voice were received,
the first attribute includes at least one of an utterance frequency or a device state attribute indicating a state of the electronic device, and
the second attribute includes at least one of a speaker attribute indicating whether a user who uttered the first user voice and a user who uttered the second user voice are a same user or a command attribute indicating similarity between commands included in the first user voice and the second user voice.
13. The control method of claim 9 ,
wherein the control method comprises:
determining respectively a user who uttered the first user voice and a user who uttered the second user voice; and
based on the determination that the user who uttered the first user voice and the user who uttered the second user voice being same, obtaining the plurality of attribute values of the second user voice.
14. A non-transitory computer-readable recording medium including a program for executing a control method for an electronic device, the method comprising:
receiving a first user voice and a second user voice;
determining whether the second user voice corresponds to a subsequent utterance candidate of the first user voice based on a result obtained by classifying a plurality of attributes of the second user voice according to a predefined attribute; and
controlling the electronic device to perform an operation corresponding to the second user voice based on intent of the second user voice obtained through a result of the determination,
wherein the determining comprises:
determining whether the second user voice corresponds to a subsequent utterance candidate of the first user voice based on a plurality of adjusted attribute values in which different weights are applied to attribute values of a plurality of classified attributes according to relevance to the predefined attribute.