阅读说明：本技术 电子设备及其控制方法 (Electronic device and control method thereof ) 是由 赵恩希 裵在铉 于 2018-11-01 设计创作，主要内容包括：提供一种电子装置及其控制方法和用于其的计算机程序产品。该电子装置包括：通信器,所述通信器被配置为与多个外部装置通信；存储装置,该存储装置被配置为存储情况信息；处理器,该处理器被配置为：基于用户的第一发声,进行控制以执行在与多个外部装置有关的多个操作中的与该第一发声相对应的第一操作；在存储装置中,存储与基于第一发声执行第一操作的多种情况中的每一种情况相对应的情况信息；基于用户的第二发声,基于所存储的情况信息从多个操作中识别与第二发声相对应的第二操作；以及进行控制以执行所识别的第二操作。这样,电子装置可以执行用户期望的操作。(An electronic device, a control method thereof, and a computer program product therefor are provided. The electronic device includes: a communicator configured to communicate with a plurality of external devices; a storage device configured to store situation information; a processor configured to: controlling to perform a first operation corresponding to a first utterance among a plurality of operations related to a plurality of external devices, based on the first utterance of the user; storing, in a storage device, situation information corresponding to each of a plurality of situations in which a first operation is performed based on a first utterance; identifying, based on a second utterance of the user, a second operation corresponding to the second utterance from the plurality of operations based on the stored situation information; and controlling to perform the identified second operation. In this way, the electronic apparatus can perform an operation desired by the user.)

1. An electronic device, comprising:

a communicator configured to communicate with a plurality of external devices;

a storage configured to store situation information;

a processor configured to:

controlling to perform a first operation corresponding to a first utterance among a plurality of operations related to the plurality of external devices, based on the first utterance of the user;

storing, in the storage device, situation information corresponding to each of a plurality of situations in which the first operation is performed based on the first utterance;

based on a second utterance of the user, identifying a second operation from the plurality of operations that corresponds to the second utterance based on the stored situational information; and

control is performed to perform the identified second operation.

2. The apparatus of claim 1, wherein the situation information comprises a plurality of factors including at least one of device, spatial, temporal, or spatial status.

3. The apparatus of claim 1, wherein the processing is configured to: identifying the second operation by further considering a similarity of at least one factor of the plurality of factors and a similarity of utterance contents.

4. The apparatus of claim 1, wherein the processor is configured to store or edit the situational information in accordance with the user's input.

5. The apparatus of claim 1, further comprising:

a display configured to output a screen,

wherein the processor is configured to store or edit the situation information by using a user interface UI output on the screen.

6. The apparatus of claim 1, wherein the processor is configured to preferentially identify an operation for applying similarity identification thereto based on a number of times the operation is performed.

7. The apparatus of claim 1, wherein the processor is configured to classify and store the situation information according to a classification of a plurality of factors.

8. The apparatus of claim 1, wherein the processor is configured to classify and store the situation information according to a multi-factor user.

9. A method of controlling an electronic device, comprising:

controlling, based on a first utterance of a user, to perform a first operation corresponding to the first utterance among a plurality of operations related to a plurality of external devices that are capable of communicating with the electronic device through a communicator of the electronic device;

storing, in a storage device, situation information corresponding to each of a plurality of situations in which the first operation is performed based on the first utterance;

based on a second utterance of the user, identifying a second operation from the plurality of operations that corresponds to the second utterance based on the stored situational information; and

control is performed to perform the identified second operation.

10. The method of claim 9, wherein the situation information comprises a plurality of factors including at least one of device, spatial, temporal, or spatial status.

11. The method of claim 9, wherein the identifying comprises: the second operation is identified by further considering a similarity of at least one factor of the plurality of factors and a similarity of the utterance content.

12. The method of claim 9, further comprising:

storing or editing the situation information according to the input of the user.

13. The method of claim 9, further comprising:

storing or editing the situation information by using a user interface UI output on a screen via a display configured as an output screen.

14. The method of claim 9, wherein the identifying comprises: operations for applying similarity identification thereto are preferentially identified based on the number of times the operations are performed.

15. A computer program product, comprising:

a memory configured to store instructions; and

a processor for processing the received data, wherein the processor is used for processing the received data,

wherein the instructions, when executed by the processor, are configured to control an electronic device for:

performing a first operation corresponding to a first utterance of a user among a plurality of operations related to a plurality of external devices that are capable of communicating with the electronic device through a communicator of the electronic device;

storing, in a storage device, situation information corresponding to each of a plurality of situations in which the first operation is performed based on the first utterance;

based on a second utterance of the user, identifying a second operation from the plurality of operations that corresponds to the second utterance based on the stored situational information; and

the identified second operation is performed.

Technical Field

Apparatuses and methods consistent with embodiments relate to an electronic apparatus and a control method thereof, and more particularly, to an electronic apparatus that can recognize a user's voice, a control method thereof, and a computer program product therefor.

Background

In recent years, electronic devices can execute commands according to the voice of a user. The electronic device may recognize a voice of a user to perform an operation corresponding thereto. If the electronic device is a device that does not operate, it may transmit a command corresponding to the user's voice to other electronic devices.

In the voice recognition, if a user speaks a sentence including all information required for the electronic device to perform an operation, the electronic device may recognize the user's voice to perform a command corresponding thereto. However, in general daily life, a user speaks a free-style sentence, from which some required information is omitted.

According to the related art, if a user speaks an imperfect sentence to an electronic device like talking with a person, there are the following problems: the electronic device may not perform a command corresponding to a voice recognized from a spoken sentence or perform an operation different from the user's intention.

Disclosure of Invention

Technical problem

Drawings

FIG. 1 illustrates an electronic device according to an embodiment;

FIG. 2 shows a block diagram of an electronic device according to an embodiment;

FIG. 3 shows a flow chart of the operation of an electronic device according to an embodiment;

fig. 4 illustrates situation information of an electronic device according to an embodiment;

FIG. 5 illustrates a method of an electronic device analyzing an utterance, according to an embodiment;

fig. 6 shows an operation execution process of the electronic apparatus according to the embodiment;

fig. 7 shows an arrangement example of an electronic apparatus according to the embodiment;

fig. 8 shows an operation example of an electronic apparatus according to the embodiment;

fig. 9 shows another operation example of the electronic apparatus according to the embodiment;

fig. 10 shows still another operation example of the electronic apparatus according to the embodiment;

fig. 11 shows an example of a User Interface (UI) according to an embodiment; and

fig. 12 illustrates an example of another UI according to an embodiment.

Embodiments provide an electronic device, a control method thereof, and a computer program product therefor, which can predict a user's intention and select a correct command corresponding thereto if an imperfect sentence uttered by the user is received at the time of voice recognition.

Technical scheme

According to an embodiment, an electronic device includes: a communicator configured to communicate with a plurality of external devices; a storage device configured to store situation information; a processor configured to: controlling to perform a first operation corresponding to a first utterance among a plurality of operations related to a plurality of external devices, based on the first utterance of the user; storing, in a storage device, situation information corresponding to each of a plurality of situations in which a first operation is performed based on a first utterance; identifying, based on a second utterance of the user, a second operation corresponding to the second utterance from the plurality of operations based on the stored situation information; and controlling to perform the identified second operation. In this way, the electronic device can predict the user's intention in free sounding, thereby reducing its mistakes.

The context information may include a plurality of factors including at least one of device, spatial, temporal, or spatial status. Accordingly, the electronic device can more accurately predict the user's intention.

The processor may be configured to: the second operation is identified by further considering the similarity of at least one factor of the plurality of factors and the similarity of the utterance content. Therefore, the electronic apparatus can predict the user's intention with higher accuracy.

The processor may be configured to store or edit the situation information according to the user's input. Accordingly, the electronic device may store situation information optimized for the user to more accurately predict the user's intention.

The apparatus may further include a display configured to output a screen, and the processor may be configured to store or edit the situation information by using a User Interface (UI) output on the screen. Therefore, the user can edit the situation information conveniently.

The processor may be configured to preferentially identify an operation to which similarity identification is to be applied based on a number of times the operation is performed. Therefore, the electronic apparatus can perform an operation frequently used by the user, thereby reducing malfunction thereof.

The processor may be configured to classify and store the situation information according to a classification of the plurality of factors. Therefore, the electronic apparatus can more efficiently perform the similarity recognition processing.

The processor may be configured to sort and store the situation information according to users of a plurality of factors (users of a plurality of factors). Accordingly, the electronic device can efficiently perform voice recognition according to the user.

According to an embodiment, a method of controlling an electronic device includes: controlling to perform a first operation corresponding to a first utterance among a plurality of operations related to a plurality of external devices that are capable of communicating with the electronic device through a communicator of the electronic device, based on the first utterance of the user; storing, in a storage device, situation information corresponding to each of a plurality of situations in which the first operation is performed based on the first utterance; identifying, based on a second utterance of the user, a second operation corresponding to the second utterance from the plurality of operations based on the stored situation information; and controlling to perform the identified second operation. In this way, the electronic device can predict the user's intention in free sounding, thereby reducing its mistakes.

The context information may include a plurality of factors including at least one of device, spatial, temporal, or spatial status. Accordingly, the electronic device can more accurately predict the user's intention.

The identifying may include: the second operation is identified by further considering the similarity of at least one factor of the plurality of factors and the similarity of the utterance content. Therefore, the electronic apparatus can predict the user's intention with higher accuracy.

The method may include: the situation information is stored or edited according to the input of the user. Accordingly, the electronic device may store situation information optimized for the user to more accurately predict the user's intention.

The method may include: the situation information is stored or edited by using a User Interface (UI) output on a screen via a display configured as the output screen. Therefore, the user can edit the situation information conveniently.

The identifying may include: operations to which similarity identification is to be applied are preferentially identified based on the number of times the operations are performed. Therefore, the electronic apparatus can perform an operation frequently used by the user, thereby reducing malfunction thereof.

The storing may include: the situation information is classified and stored according to the categories of the plurality of factors. Therefore, the electronic apparatus can more efficiently perform the similarity recognition processing.

The storing may include: the situation information is classified and stored according to users of a plurality of factors. Accordingly, the electronic device can efficiently perform voice recognition according to the user.

According to one embodiment, a computer program product comprises: a memory configured to store instructions; and a processor, the instructions, when executed by the processor, configured to control the electronic device to: performing a first operation corresponding to a first sound emission among a plurality of operations related to a plurality of external devices capable of communicating with the electronic device through a communicator of the electronic device, based on the first sound emission of the user; storing, in a storage device, situation information corresponding to each of a plurality of situations in which the first operation is performed based on the first utterance; identifying, based on a second utterance of the user, a second operation corresponding to the second utterance from the plurality of operations based on the stored situation information; and performing the identified second operation. In this way, the electronic device can predict the user's intention in free sounding, thereby reducing its mistakes.

Advantageous effects

As described above, according to the embodiments, the electronic apparatus, the control method thereof, and the computer program product therefor can find out the user's intention from an imperfect sentence at the time of voice recognition to perform an operation corresponding thereto.