JP2017084177A - Electronic apparatus and control method thereof - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide home electronic apparatus capable of properly performing interaction with a user.SOLUTION: A home electronic apparatus (10) includes: an interaction control unit (11a) that controls an interaction with a user; an event detection section (11b) that detects an occurrence of a predetermined event which may trigger the home electronic apparatus (10) to start an interaction; and a start determination section (11c) that, when the event detection section (11b) detects an occurrence of an event, determines whether predetermined conditions are satisfied. The interaction control unit (11a) controls to start an interaction according to the determination result by the start determination section (11c).SELECTED DRAWING: Figure 2

Description

  The present invention relates to an electronic device that interacts with a user and a control method thereof.

  Electronic devices such as home appliances tend to be multi-functional year by year, and for example, an electronic device having a function of inputting sound such as a microphone and a function of outputting sound such as a speaker is increasing.

  For example, Patent Document 1 includes a voice recognition unit that recognizes a voice from the outside, and transmits information recognized by the voice recognition unit to an external device, so that a recipe search can be performed using only the voice. A refrigerator is disclosed. The voice recognition unit is activated when the door of the refrigerator is opened or a human sensor detects that a person is in front of the refrigerator. According to this, it is not necessary to manually drive the voice recognition unit.

  Furthermore, in the market today, there are appliances such as refrigerators that start a dialog with a user via voice when a specific button is pressed.

JP 2014-196847 A (released on October 16, 2014)

  By the way, dialogue is essentially what we talk to each other. Therefore, as described above, it is preferable that the user not only starts the dialog by pressing the specific button, that is, the user's will but also starts the dialog by the home appliance. In order to realize this, not only when the specific button is pressed in the home appliance, but also when the door of the home appliance is opened or the presence of a person in front of the home appliance is detected. It is possible to start.

  On the other hand, people may not want to talk. That is, it is bothersome and undesired for the user to talk each time the user approaches the home appliance or to talk every time the door of the home appliance is opened. In such a case, it is useless for the home appliance to start the dialogue, and as a result, the power consumed by the home appliance to operate the dialogue function is wasted.

  The present invention has been made in view of the above problems, and an object of the present invention is to provide an electronic device or the like in which an electronic device such as a home appliance can appropriately interact with the user.

  In order to solve the above-described problem, an electronic device according to an aspect of the present invention is an electronic device including a dialog unit that performs a dialog with a user, and the electronic device is a predetermined event that can serve as a trigger for starting the dialog. A detection unit that detects the occurrence of the event, and a determination unit that determines whether a predetermined condition is satisfied when the detection unit detects the occurrence of the event. According to the result, the dialogue is started.

  In order to solve the above problems, an electronic device control method according to another aspect of the present invention is an electronic device control method for interacting with a user, wherein the electronic device starts the conversation. A detection step that detects the occurrence of a predetermined event that can be, a determination step that determines whether a predetermined condition is satisfied when the occurrence of the event is detected in the detection step, and a determination result of the determination step And a dialogue step for starting the dialogue.

  According to one embodiment of the present invention, there is an effect that an electronic device can appropriately perform a dialogue with a user.

It is a figure which shows the structure of the speech dialogue system which concerns on one Embodiment of this invention. It is a block diagram which shows schematic structure of the household appliance in the said voice interaction system. It is a block diagram which shows schematic structure of the server in the said voice interactive system. It is a flowchart which shows the flow of the process of the voice dialog in the said household appliance. It is a flowchart which shows the flow of the process of the voice dialog in the said household appliance. It is a flowchart which shows the flow of the process of the voice dialog in the said household appliance. It is the external appearance perspective view of the refrigerator which is an example of the said household appliance, and the enlarged view of the operation panel provided in this refrigerator. It is a block diagram which shows schematic structure of the household appliance in the voice interactive system which concerns on another embodiment of this invention. It is a block diagram which shows schematic structure of the household appliance in the voice dialogue system which concerns on another embodiment of this invention. It is a block diagram which shows schematic structure of the server in the said voice interactive system. It is a flowchart which shows the flow of the process of the voice dialogue in the household appliance of the voice dialogue system which concerns on other embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described in detail. For convenience of explanation, members having the same functions as those shown in the embodiments are denoted by the same reference numerals, and description thereof is omitted as appropriate.

Embodiment 1
First, an embodiment of the present invention will be described with reference to FIGS.

(Configuration of spoken dialogue system)
FIG. 1 is a diagram showing a configuration of a voice interaction system 1 according to the present embodiment. As shown in FIG. 1, in the voice interaction system 1, the home appliance 10 (10-1 to 10-4), the server 20, and the communication terminal device 30 (30-1 to 30-3) installed in the user home 70. Are connected via the communication network 60. FIG. 1 shows a part related to a user home 70 in the voice interaction system 1.

  The home appliance 10 (electronic device) is a network home appliance having a wireless communication function for connecting to the communication network 60 and communicating with the server 20. The wireless communication function may be incorporated in the home appliance 10 main body, or may be provided in a communication adapter (not shown) externally attached to the home appliance 10 main body.

  Moreover, the household appliance 10 is provided with the dialog control part 11a (refer FIG. 2) mentioned later, and has the function to interact with a user as an additional function other than the main functions as the household appliance 10. FIG. When the home appliance 10 detects the occurrence of a predetermined event serving as a trigger for starting a dialogue, such as when the door of the home appliance 10 is opened or a predetermined button of the home appliance 10 is operated, the dialogue control unit 11a operates. Thus, it has a voice dialogue function for starting a voice dialogue by speaking to the user.

  In the present embodiment, the home appliance 10 transmits voice data of voice acquired from the user to the server 20, the server 20 performs voice recognition to specify the content of the utterance, and the voice data of the answer based on the specified content is used as the home appliance. 10 illustrates an example of a configuration for transmission.

  The home appliance 10 has a voice recognition function, and the home appliance 10 performs voice recognition to specify the content of the utterance, transmits the specified content to the server 20, and receives the voice data of the answer from the server 20. It is good. Or it is good also as a structure which the household appliance 10 implements until voice data to reply is prepared while performing voice recognition in the household appliance 10 without going through the server 20.

  In the example of FIG. 1, the refrigerator 10-1, the heating cooker 10-2, the air conditioner 10-3, and the washing machine 10-4 are illustrated as the home appliance 10, but the home appliance 10 having such a voice interaction function is illustrated. May be other household appliances such as an air purifier or a lighting device.

  In the present embodiment, as described above, the server 20 recognizes voice data transmitted from the home appliance 10, prepares voice data of an answer based on the content of the specified utterance, and transmits it to the home appliance 10. have.

  The user home 70 is provided with a wireless local area network (LAN) that forms part of the communication network 60. The wireless LAN relay station 40 is connected to a communication network 60 including the Internet. The relay station 40 is a communication device such as a WiFi (registered trademark) router or a WiFi (registered trademark) access point, for example. In the present embodiment, the configuration including the Internet is exemplified as the communication network 60, but a telephone line network, a mobile communication network, a CATV (CAble TeleVision) communication network, a satellite communication network, or the like can also be used.

  The server 20 and the home appliance 10 can communicate with each other via the communication network 60 and the wireless LAN relay station 40. The server 20 and the communication terminal device 30 can communicate with each other via the communication network 60. The communication terminal device 30 and the Internet in the communication network 60 are connected using 3G (3rd Generation), LTE (Long Term Evolution), a home or public WiFi (registered trademark) access point, and the like.

(Configuration of home appliance 10)
FIG. 2 is a block diagram illustrating a schematic configuration of the home appliance 10. As shown in FIG. 2, the home appliance 10 includes a control unit 11, a storage unit 12 (storage device), a communication unit 13, an audio output unit 14, an audio acquisition unit 15, an operation panel 16, and various sensors 17.

  The control part 11 consists of computer apparatuses comprised by arithmetic processing parts, such as CPU (Central Processing Unit) and a dedicated processor, for example, and controls operation | movement of each part of the household appliance 10. FIG. Details of the control unit 11 will be described later.

  The storage unit 12 stores various types of information used in the home appliance 10 and also stores voice data to be uttered downloaded from the server 20, voice data of answers in a voice conversation, and the like. Details of the storage unit 12 will be described later.

  The communication unit 13 performs mutual communication with the server 20 through the wireless LAN relay station 40 and the communication network 60 under the control of the control unit 11.

  The audio output unit 14 includes a speaker or the like, and outputs audio based on audio data under the control of the control unit 11. The sound acquisition unit 15 includes a microphone and the like, acquires sound under the control of the control unit 11, and converts the acquired sound into sound data.

  The operation panel 16 is for the user to input an instruction to the home appliance 10 under the control of the control unit 11 or to notify the state of the home appliance 10 (interactive state, internal temperature, set temperature, etc.). User interface. The operation panel 16 is provided with an utterance button 16a and a notification lamp 16b. The notification lamp 16b is made of, for example, a three-color LED. Further, the operation panel 16 may be provided with a display button (not shown) or the like for changing a setting related to the dialog state or the dialog of the home appliance 10.

  The utterance button 16a may be a dialogue start button for starting a voice dialogue from the user when not in a voice dialogue state. Furthermore, the utterance button 16a may receive an instruction to start the voice acquisition unit 15 or an instruction to stop the dialogue from the user. The notification lamp 16b notifies the dialog state. Moreover, the notification lamp 16b notifies the presence, when the household appliance 10 has the audio | voice data which should be uttered.

  The various sensors 17 detect various operations and situations in the home appliance 10 under the control of the control unit 11. Examples of the various sensors 17 include an operation panel 16 for operating the home appliance 10, an infrared receiver for remotely operating the home appliance 10, a switch for detecting opening and closing of the door of the home appliance 10, and the situation around the home appliance 10. And a camera for detecting the.

(Configuration of control unit 11 and storage unit 12)
The control unit 11 includes a dialogue control unit 11a (conversation unit), an event detection unit 11b (detection unit), and a start determination unit 11c (determination unit). The storage unit 12 stores condition data 12a. The condition data 12a indicates a start condition for starting a dialog with the user. An example of the start condition will be described later.

  The dialogue control unit 11a controls each unit in the home appliance 10 in order to conduct a dialogue with the user. Details of the dialogue control unit 11a will be described later.

  The event detection unit 11b detects a predetermined event that can be a trigger for the home appliance 10 to start the conversation. Examples of the predetermined event include that a door provided in the home appliance 10 (the refrigerator 10-1, the heating cooker 10-2, the washing machine 10-4, etc.) is opened, and a home appliance using a remote controller (remote controller). 10 (air conditioner 10-3) remote operation is started.

  When the event detection unit 11b detects the predetermined event, the start determination unit 11c determines whether or not to start the dialogue based on the condition data 12a stored in the storage unit 12. The start determination unit 11c instructs the dialogue control unit 11a based on the determination result.

  As described above, it is bothersome and undesired for the user that the home appliance 10 starts a conversation whenever the user approaches the home appliance 10 or that the home appliance 10 starts a conversation every time the door of the home appliance 10 is opened. There is. This problem is caused by the frequency at which the user performs a predetermined action on the home appliance 10 rather than the frequency at which the user desires to interact with the home appliance 10.

  On the other hand, in this embodiment, whether or not the home appliance 10 starts a dialog with the user is determined based on a predetermined start condition indicated by the condition data 12a. That is, even if the user performs a predetermined action on the home appliance 10, if the predetermined start condition is not met, the dialog is not started. Thereby, compared with the case where the said dialog is started whenever a user performs predetermined | prescribed action with respect to the household appliance 10, the conversation with the household appliance 10 and the said user can be performed with appropriate frequency. Moreover, the frequency which operates the dialog control part 11a can be reduced, As a result, power consumption can be suppressed.

(Details of dialog control unit 11a)
When the activation is instructed from the start determination unit 11c or the utterance button 16a is pressed, the dialogue control unit 11a starts a dialogue with the user. At the start, voice data notifying the start is sent to the voice output unit 14 to speak. As an example of the utterance based on the voice data for informing the activation, there is a phrase such as “Yes / what?”. It is desirable that the voice data notifying the start is stored in advance in the storage unit 12.

  When there is voice data to be uttered at the start, the dialogue control unit 11a sends the voice data to the voice output unit 14 to speak instead of the voice data notifying the activation. Examples of voice data to be uttered include data downloaded from the server 20 and data stored in the storage unit 12 since the manufacture of the home appliance 10. The contents include, for example, a message input from the communication terminal device 30, “I have no ice in the ice machine”, “I have an egg in the refrigerator. Would you like to make a dish using eggs?” There are various messages.

  When the utterance at the time of activation is completed, the dialogue control unit 11 a activates the voice acquisition unit 15, creates voice data of the voice acquired by the voice acquisition unit 15, and transmits the voice data to the server 20 via the communication unit 13. Further, when receiving the answer voice data from the server 20 via the communication unit 13, the dialogue control unit 11 a sends the received answer voice data to the voice output unit 14 to speak. At this time, the dialogue control unit 11a temporarily stops the voice acquisition unit 15 during the utterance, and starts again when the utterance is completed. And by repeating the said operation | movement, the speech from a user and the speech from the household appliance 10 corresponding to this speech are repeated, and a dialog with a user is realizable.

  Further, when the voice control unit 11a continues to be unable to acquire voice for a predetermined period (for example, 30 seconds) or when the voice button 16a is pressed while the voice acquisition unit 15 is in operation, End the conversation. At this time, the dialogue control unit 11a sends voice data notifying the end to the voice output unit 14 to utter. Examples of utterances using voice data to notify the end include “See you again!” And “It seems that the communication status is not good!”. The audio data is preferably stored in the storage unit 12 in advance. When the utterance at the end time is completed, the dialogue control unit 11a stops the voice output unit 14 and the voice acquisition unit 15.

  When the speech button 16a is pressed while the voice output unit 14 is speaking, the dialogue control unit 11a may stop the voice output unit 14 to stop speaking. At this time, the dialogue control unit 11a desirably activates the voice acquisition unit 15 once stopped. Thereby, the audio | voice acquisition part 15 can acquire the audio | voice from a user at the timing which a user desires.

  Further, the dialogue control unit 11a controls the lighting of the notification lamp 16b to notify the user of the presence / absence of voice data to be uttered and the operating state of the voice acquisition unit 15.

  Specifically, when there is voice data to be uttered in a state where the dialogue is not started, the dialogue control unit 11a uses a notification lamp with a predetermined first color (for example, pink) to notify that fact. 16b flashes and lights, otherwise, the notification lamp 16b is turned off.

  Further, when the conversation is started and the voice acquisition unit 15 is operating (operating state), the notification lamp 16b is controlled by the second color (for example, green). At this time, if the voice acquisition unit 15 has acquired voice, the notification lamp 16b is turned on and off, and if the voice acquisition unit 15 has not acquired voice, the notification lamp 16b is turned on and on.

  Further, the dialogue control unit 11a turns off the notification lamp 16b while the voice output unit 14 is speaking (while the voice acquisition unit 15 is stopped). The non-flashing color is, for example, the first color if the voice data to be spoken is being spoken, or the speech when starting or stopping, or generated as an answer to the voice input of the user in the dialogue If the response utterance is made, the color is the third color (for example, blue).

  The state in which the voice acquisition unit 15 is stopped and the voice output unit 14 is stopped (not speaking) is a state in which the user is waiting for a response from the home appliance. . In this state, the notification lamp 16b is lit in a non-flashing manner with the third color, thereby notifying the user that the conversation is being processed.

(Configuration of server 20)
FIG. 3 is a block diagram illustrating a schematic configuration of the server 20. The server 20 manages each household appliance 10, and is provided with the control part 21, the memory | storage part 22, the communication part 23, and the speech recognition apparatus 24 as shown in FIG. In addition, a voice providing function unit 21 a is constructed in the control unit 21.

  The control unit 21 may be, for example, a computer device that includes an arithmetic processing unit such as a CPU (Central Processing Unit) or a dedicated processor, and controls the operation of each unit of the server 20.

  The storage unit 22 stores various types of information used in the server 20, and also stores text examples and the like that are referred to when the voice providing function unit 21 a described later creates voice data to be provided to the home appliance 10. The communication unit 23 performs mutual communication with the home appliance 10 and the communication terminal device 30 via the communication network 60 under the control of the control unit 21.

  The voice recognition device 24 recognizes voice data transmitted from the home appliance 10 and received by the communication unit 23 and converts it into a character string. The voice recognition device 24 is provided with a function of converting not only a character string but also a meaningful sentence.

  The voice providing function unit 21a provides the home appliance 10 with voice data that the home appliance 10 utters to the user and voice data of an answer to the utterance acquired by the home appliance 10 at the start of the dialogue with the user. is there. The voice providing function unit 21 a creates the voice data to be provided with reference to the storage unit 22 or obtains it via the communication network 60. The voice providing function unit 21a transmits the created voice data to the home appliance 10 via the communication unit 23 and downloads it.

(Processing flow in voice dialogue)
4-6 is a flowchart which shows the flow of the process of the voice dialog in the household appliance 10 of this embodiment.

  First, as shown in FIG. 4, the event detection unit 11b waits until the utterance button 16a is pressed or it is detected that a predetermined event serving as a trigger for starting the conversation occurs (S1. S2, detection step). At this time, the notification lamp 16b flashes and lights in the first color notifying the presence when there is voice data to be uttered, and is turned off when there is no speech data.

  When event detection unit 11b detects that the predetermined event has occurred (YES in S2), start determination unit 11c determines whether to start the dialogue based on the condition data stored in storage unit 12 or not. (S3, S4, determination step). If it is determined not to start the dialogue (NO in S4), the process returns to step S1 and the above operation is repeated.

  On the other hand, when event detection unit 11b detects that utterance button 16a has been pressed (YES in S1), or when start determination unit 11c determines that the conversation starts (YES in S4), dialog control The unit 11a executes the following dialog control process (S5, dialog step).

  That is, as shown in FIG. 5, when there is voice data to be uttered, the dialogue control unit 11a utters the voice data (S10). At this time, the notification lamp 16b switches from blinking lighting of the first color to non-flashing lighting of the first color. On the other hand, when there is no voice data to be uttered, the dialogue control unit 11a causes the utterance (for example, “Yes / what?”) To notify the activation of the voice acquisition unit 15 (S10). ). At this time, the notification lamp 16b is lit non-flashing in the third color.

  When the utterance is completed, the dialogue control unit 11a activates the voice acquisition unit 15 (S10). At this time, the notification lamp 16b flashes and lights in the second color notifying the operating state of the voice acquisition unit 15. Even after the transition to the blinking lighting of the second color, during the speech of the voice output unit 14, the non-flashing lighting of the third color is performed, and when the speech of the voice output unit 14 is completed, the flashing lighting of the second color is resumed.

  Next, the dialogue control unit 11a waits until a predetermined time (for example, 30 seconds) elapses, or the voice acquisition unit 15 acquires a voice such as a user's utterance (S11 and S12). When the voice is acquired (YES in S11), voice data of the acquired voice is created and transmitted to the server 20 (S13). Thereafter, the voice data of the answer is received from the server 20, or it waits until a predetermined time (for example, 10 seconds) elapses (S14 and S15). When the voice data is received (YES in S14), this is uttered (S16). Then, it returns to step S11 and repeats the said operation | movement.

  On the other hand, when the predetermined time has elapsed without receiving the voice data (YES in S15), the dialog control unit 11a stops the voice acquisition unit 15 and stops waiting for reception of the voice data from the server 20. (S17). Also, an utterance notifying the stop (for example, “communication state seems to be bad!”) Is performed (S17). Thereafter, the dialog control process (S5) is terminated, the process returns to step S1 shown in FIG. 4, and the above operation is repeated.

  On the other hand, when the predetermined time has elapsed without acquiring the voice (YES in S11), the dialogue control unit 11a stops the voice acquisition unit 15 and also utters the notification of the stop (for example, “See you again”). ! ") Is performed (S18). Thereafter, the dialog control process (S5) is terminated, the process returns to step S1 shown in FIG. 4, and the above operation is repeated.

  When the utterance button 16a is pressed during the execution of the dialog process shown in FIG. 5, the dialog control unit 11a executes the following interrupt process. That is, as shown in FIG. 6, it is determined whether or not the voice output unit 14 is speaking (S20). If the utterance is being made (YES in S20), the utterance from voice output unit 14 is stopped (S21), and then the process returns to step S11 to repeat the above operation. Thereby, the voice from a user can be acquired immediately.

  When the utterance button 16a is pressed during the execution of the dialog process shown in FIG. 5, the dialog control unit 11a executes the following interrupt process. That is, as shown in FIG. 6, it is determined whether or not the voice output unit 14 is speaking (S20). If the speech is being made (YES in S20), the speech from the voice output unit 14 is stopped and the voice acquisition unit 15 is activated (S21), and then the process returns to step S11 to repeat the above operation. Thereby, the voice from a user can be acquired immediately. If speech data to be uttered is being uttered, the speech acquisition unit 15 may be activated after the utterance is completed without returning the utterance, and the process may return to step S11.

  On the other hand, when not speaking (NO in S20), the dialogue control unit 11a proceeds to step S18, assuming that the user has instructed the end of the voice dialogue, and then returns to step S1 shown in FIG. repeat.

  From step S11 to step S16, the notification lamp 16b is non-flashing in the third color when the voice output unit 14 is speaking, and flashing in the second color in other cases. When the process proceeds to step S17 or step S18, the notification lamp 16b switches the flashing color to the first color when the voice data to be uttered cannot be uttered at step S21, and turns off in the other cases. .

(Configuration of refrigerator 10-1)
Here, the refrigerator 10-1 as an example of the household appliance 10 is demonstrated in detail using FIG. FIG. 7 is an external perspective view of the refrigerator 10-1 and an enlarged view of the operation panel 16. As shown in FIG. 7, the refrigerator 10-1 is provided with a vegetable room 41, a freezing room 42, an adjustment freezing room 43, an ice making room 44, and the like at the lower part, and a refrigeration room 45 at the upper part. The door 46 of the refrigerator compartment 45 is a double door opening type, and the vertically long operation panel 16 is provided on the open end side of the larger first door 46a of the two doors 46a and 46b.

  In addition to the speech button 16a and the notification lamp 16b described above, the operation panel 16 includes a connect lamp 16c that indicates a connection state with the server 20. The utterance button 16a and the connect lamp 16c are arranged at the upper part of the operation panel 16 so as to be at the height of the face of the user (general height user) standing in front of the refrigerator 10-1, and the utterance button 16a is It is desirable to be disposed below that.

  Although not shown in FIG. 7, the microphone of the sound acquisition unit 15 and the speaker of the sound output unit 14 are provided at appropriate positions of the refrigerator 10-1 (for example, the hinge cover portions 51 a and 51 b of the main body 47). ing.

  Therefore, when the voice acquisition unit 15 is activated with the user's action on the home appliance 10 as a trigger, by confirming the lighting state of the notification lamp 16b together with the utterance notifying the activation, the user acquires the voice acquisition unit 15 Can be checked to see if it is in operation.

  Therefore, the user can interact with the home appliance 10 without feeling uneasy about whether the spoken voice is definitely acquired. In addition, it is possible to confirm that the voice acquisition unit 15 is not operating even when voice acquisition is not desired.

  Thereby, in addition to the main function as the home appliance 10, a convenient additional function of performing a voice conversation triggered by the user's action on the home appliance 10 can be used without causing the user to feel bothered.

  Moreover, since the operating state of the voice acquisition unit 15 is notified by both the utterance by the voice output unit 14 and the lighting state of the notification lamp 16b, it can be known from both visual and auditory senses. In addition, the notification of the operating state of the voice acquisition unit 15 may be configured to be notified by either the lighting of the notification lamp 16b or the utterance, or may be configured to display a message on the display panel. Also good.

[Example 1]
In the present embodiment, various examples of start conditions indicated by the condition data 12a stored in the storage unit 12 will be described. In the following embodiment, the predetermined event serving as a trigger for starting the dialogue with the user is “the door 46 of the refrigerator 10-1 is opened”, but is not limited thereto.

(Example 1-1)
In this embodiment, the start condition is “to start a dialog with a predetermined probability”. More specifically, the start condition is “a dialog is started with a probability of 20% when the door 46 of the refrigerator 10-1 is opened”.

  In this case, a numerical value (20) representing the predetermined probability as a percentage may be stored in the storage unit 12 in advance as the condition data 12a. And the start determination part 11c should just select a number at random from the numbers 1-100, and should determine whether the selected number is below the said numerical value (20).

(Example 1-2)
In the present embodiment, the start condition is “determining whether or not to start a conversation according to a time zone”. More specifically, the start condition is “when the door 46 of the refrigerator 10-1 is opened, the conversation starts if the current time is in the time zone (6:00 to 21:59). On the other hand, if the current time is sleeping (22:00 to 5:59), the conversation is not started. "

  In this case, the above-described time zone may be stored in the storage unit 12 in advance as the condition data 12a. Then, the start determination unit 11c may acquire the current time and determine whether or not the acquired current time is included in the time zone in which the start occurs.

(Example 1-3)
In this embodiment, the start condition is “to start a conversation with a probability set for each time slot”. More specifically, the start condition is “when the door 46 of the refrigerator 10-1 is opened, if the current time is busy in the morning (6: 00-8: 59), the probability is 10%. If the current time is within the daytime (9: 00-15: 59), the conversation starts with a 50% probability, and the current time is the time to prepare dinner (16: If it is 00-19: 59), the conversation starts with a probability of 10%, and if the current time is a time zone with a margin of night (20: 00-21: 59), the conversation starts with a probability of 30%. In addition, if the current time is a sleeping time zone (22:00 to 5:59) in the middle of the night, the dialogue is started with a probability of 0% (that is, the dialogue is not started).

  In this case, as the condition data 12a, a numerical value representing the predetermined probability in percentage may be stored in advance in the storage unit 12 in association with the time zone information. The start determination unit 11c acquires the current time, selects a number from 1 to 100 at random, and the selected number is associated with the time zone included in the acquired current time. What is necessary is just to determine whether it is below a numerical value.

[Embodiment 2]
Next, another embodiment of the present invention will be described with reference to FIG.

  FIG. 8 is a block diagram illustrating a schematic configuration of the home appliance 10A according to the present embodiment. Compared with the home appliance 10 shown in FIG. 2, the home appliance 10 </ b> A of the present embodiment has a history of detecting the predetermined event (detection history) and a history of starting the conversation (start history) in the storage unit 12. The history data 12b (history information) is stored, and in the control unit 11, instead of the dialogue control unit 11a, the event detection unit 11b, and the start determination unit 11c, the dialogue control unit 11d, the event detection unit 11e, And the point from which the start determination part 11f is provided differs, and other structures are the same.

  Compared with the event detection unit 11b shown in FIG. 2, the event detection unit 11e is newly provided with a configuration for adding the time (detection time) at which the predetermined event is detected to the history data 12b of the storage unit 12. However, other configurations are the same. The dialog control unit 11d is different from the dialog control unit 11a shown in FIG. 2 in that a configuration for newly adding the time (start time) of the dialog to the history data 12b of the storage unit 12 is provided. Other configurations are the same.

  Further, the start determination unit 11f determines whether or not to start the dialogue based on the condition data 12a and the history data 12b stored in the storage unit 12 as compared to the start determination unit 11c illustrated in FIG. However, other configurations are the same.

  According to the above configuration, the occurrence frequency of the predetermined event and the start frequency of the dialogue can be grasped from the history data 12b. Therefore, it is determined whether or not the home appliance 10A starts the dialogue with the user in consideration of the occurrence frequency and the start frequency, and thus the dialogue between the home appliance 10A and the user can be performed at a more appropriate frequency. . Moreover, the frequency which operates the dialog control part 11d and the audio | voice acquisition part 15 can further be reduced, As a result, power consumption can further be suppressed.

[Example 2]
In the present embodiment, various examples of start conditions indicated by the condition data 12a stored in the storage unit 12 will be described.

(Example 2-1)
In the present embodiment, the start condition is “calculated by using the history data 12b to calculate the number (frequency) of occurrence of the predetermined event within a predetermined period (recently going back to the past). The probability is set based on the number of times, and the dialogue is started with the set probability ”. More specifically, the above start condition is: “When the door 46 of the refrigerator 10-1 is opened, if the number of times the door 46 is opened and closed in the last 10 minutes is 3 times or more, the dialogue has a probability of 5%. On the other hand, if it is less than 3 times, the dialogue is started with a probability of 20%. "

  In this case, as the condition data 12a, the frequency threshold (3), a numerical value (20) that represents the probability when the frequency is less than the threshold, and a numerical value (5) that represents the probability when the frequency is the threshold or higher (5). ) May be stored in the storage unit 12 in advance. The start determination unit 11f calculates the recent frequency at which the predetermined event has occurred from the history data 12b, selects a number from 1 to 100 at random, and the selected number is the calculated frequency. What is necessary is just to determine whether it is below the numerical value corresponding to.

(Example 2-2)
In the present embodiment, the start condition is “a dialog is started every time the predetermined event occurs a predetermined number of times”. More specifically, the start condition is as follows: “When the door 46 of the refrigerator 10-1 is opened, if the number of opening / closing of the door 46 is five times or more since the start of the previous dialogue, the dialogue is started. To do.

  In this case, the predetermined number of times (5) may be stored in the storage unit 12 in advance as the condition data 12a. Then, the start determination unit 11f refers to the history data 12b, acquires the number of times that the predetermined event has occurred since the start of the previous conversation, and determines whether the acquired number is equal to or greater than the predetermined number of times. do it.

  Instead of using the history data 12b, a counter that counts the opening / closing of the door 46 may be newly provided. In this case, when detecting that the door 46 has been opened, the event detection unit 11e increments the count number of the counter by 1, and the start determination unit 11f determines whether the count number of the counter is equal to or greater than the predetermined number of times. The dialogue control unit 11d may return the count value of the counter to 0 when the dialogue is started.

(Example 2-3)
In this embodiment, the start condition is “to start a dialog when a predetermined period has elapsed since the start of the previous dialog”. More specifically, the start condition is “when the door 46 of the refrigerator 10-1 is opened, if 30 minutes have passed since the start of the previous conversation, the conversation is started”. .

  In this case, the predetermined period (30 minutes) may be stored in the storage unit 12 in advance as the condition data 12a. Then, the start determination unit 11f refers to the history data 12b and may determine whether or not the predetermined period has elapsed since the previous conversation was started. Thereby, since the refrigerator 10-1 does not start the dialogue even if the door 46 of the refrigerator 10-1 is opened for 30 minutes after the dialogue is started, the user is frequently bothered by the refrigerator 10-1. Can prevent you from feeling.

(Example 2-4)
In the present embodiment, the start condition is that “a time zone is set for each unit time, and a dialogue is started a predetermined number of times in each time zone”. More specifically, the start condition is as follows: “When the door 46 of the refrigerator 10-1 is opened, the number of times the conversation has started in the current time zone is less than 1 in a time zone of 30 minutes. If it is (0), the dialogue is started.

  In this case, the unit time (30 minutes) and the predetermined number of times (1) may be stored in the storage unit 12 in advance as the condition data 12a. In addition, what is necessary is just to set the said time slot | zone for every said unit time from arbitrary time, such as 0:00, the starting time of the refrigerator 10-1, for example. Then, the start determination unit 11f refers to the history data 12b and may determine whether or not the number of times the conversation has started in the current time zone is less than the predetermined number.

(Example 2-5)
In the present embodiment, the start condition is “the predetermined probability is changed according to the number of times the conversation is started by pressing the utterance button 16a within the recent predetermined period, and the conversation is started with the changed probability”. It is. More specifically, the start condition is “when the door 46 of the refrigerator 10-1 is opened, the number of times the conversation is started by pressing the utterance button 16a in the last hour is 3 times or more. If there is, the dialogue is started with a probability of 40%, which is twice the predetermined probability of 20%.

  In this case, as the condition data 12a, the predetermined period (1 hour), the threshold value for the number of times (three times), and the numerical value (20) representing the predetermined probability as a percentage may be stored in the storage unit 12 in advance. Moreover, what is necessary is just to memorize | store in the log | history data 12b the time which started the dialogue by pressing the utterance button 16a. Then, the start determination unit 11f refers to the history data 12b, acquires the number of times the conversation has started by pressing the utterance button 16a within the recent predetermined period, and changes the above numerical value according to the acquired number of times. On the other hand, a number may be selected at random from 1 to 100, and it may be determined whether or not the selected number is equal to or less than the changed number.

(Modification 1)
The above embodiments can be combined as appropriate. In this case, it is desirable to give priority to each embodiment. For example, from the user's point of view, the consumer electronics 10 is not desired in the midnight time zone. Therefore, the embodiment 1-2 having the corresponding start condition is prioritized over the other embodiments.

  In addition, by combining the examples 1-1, 1-2, and 2-1, the start condition is changed to “the number of times the door 46 was opened in the last 10 minutes in the time period from 6:00 to 21:59”. If the number is less than 3 times, the conversation starts with a probability of 20%. If the number is 3 times or more, the conversation starts with a probability of 5%. On the other hand, the conversation is not started between 22:00 and 5:59. ".

  Also, in Examples 1-2 and 2-2 to 2-4 that do not have a probability of starting a dialogue, the probability of starting the dialogue is 100%, and the case of not starting the dialogue is the probability of 0%. By doing so, it can be combined with other embodiments. For example, by combining the embodiments 1-1 and 2-2, the above start condition is changed to “If the number of doors 46 is 4 or less since the start of the previous conversation, the conversation is performed with a probability of 0%. “If it is 5 times or more, the dialogue is started with a probability of 80%”. In addition, by combining the examples 1-1 and 2-3, the above start condition is changed to “When the door 46 of the refrigerator 10-1 is opened, 30 minutes have passed since the start of the previous dialogue. Then, the dialogue can be started with a probability of 80%.

[Embodiment 3]
Next, still another embodiment of the present invention will be described with reference to FIG. 9 and FIG. In the present embodiment, the frequency at which the home appliance 10B starts a conversation is changed based on the utterance content from the user. Specifically, when the server 20B recognizes a keyword that changes the frequency with which the home appliance 10B starts the conversation (for example, “be quiet” or “speak more”), the home appliance 10B is based on the recognized phrase. Changes the condition data 12 a stored in the storage unit 12. According to said structure, the interaction with household appliance 10B and a user can be performed with the frequency which a user desires.

  FIG. 9 is a block diagram illustrating a schematic configuration of the home appliance 10B according to the present embodiment. The home appliance 10B of the present embodiment is different from the home appliance 10A shown in FIG. 8 in that a condition changing unit 11g is newly provided in the control unit 11, and the other configurations are the same.

  FIG. 10 is a block diagram showing a schematic configuration of the server 20B according to the present embodiment. Compared with the server 20 shown in FIG. 3, the server 20 </ b> B of the present embodiment is provided with a voice recognition device 24 </ b> B instead of the voice recognition device 24, and a frequency change instruction unit 21 b is newly provided. And other configurations are the same.

  The voice recognition device 24B of the server 20B has the following configuration added to the voice recognition device 24 shown in FIG. 3, and the other configurations are the same. That is, in the voice recognition device 24B, keywords that change the frequency with which the home appliance 10B starts the conversation are set in advance. In addition, the voice recognition device 24B determines whether or not the keyword is included in the character string converted by voice recognition of the voice data from the home appliance 10B. The frequency change instruction unit 21b is notified.

  The frequency change instruction unit 21b of the server 20B transmits an instruction (frequency change instruction) for changing the frequency at which the home appliance 10B starts a dialogue to the home appliance 10B via the communication unit 23 based on the keyword from the voice recognition device 24B. Is. For example, if the keyword is “be quiet”, a frequency change instruction to decrease the frequency is transmitted to the home appliance 10B. Also, if the keyword is “more talk”, a frequency change instruction to increase the frequency is transmitted to the home appliance 10B.

  When the condition change unit 11g of the home appliance 10B receives the frequency change instruction from the server 20B via the communication unit 13, the condition change unit 11g changes the condition data 12a in the storage unit 12 based on the received frequency change instruction.

  For example, if the condition changing unit 11g receives a frequency change instruction for decreasing the frequency, the condition changing unit 11g halves the probability of starting the conversation in the embodiments 1-1, 1-3, and 2-1. -2 times, the predetermined period of Example 2-3, and the unit time of Example 2-4 are multiplied by 1.5. When the date changes, the changed numerical value may be restored.

  In addition, if the condition change unit 11g receives the frequency change instruction to increase the frequency, the condition change unit 11g increases the probability of starting the conversation in the above embodiments 1-1, 1-3, and 2-1 by 1.5 times, The predetermined number of times in Example 2-2, the predetermined period in Example 2-3, and the unit time in Example 2-4 are halved. When the date changes, the changed numerical value may be restored.

  The condition changing unit 11g receives the frequency change instruction for increasing the frequency after receiving the frequency change instruction for decreasing the frequency, or decreases the frequency after receiving the frequency change instruction for increasing the frequency. If the frequency change instruction is received, the changed numerical values in the above embodiments 1-1, 1-3, 2-1 to 2-4 may be restored.

[Embodiment 4]
Next, another embodiment of the present invention will be described with reference to FIG. In this embodiment, when the household appliance 10 has the message which should be uttered, the point which always starts a dialog differs, and the other structure is the same. According to said structure, it can prevent that the utterance of the said message delays.

  The message to be uttered may be a message that the home appliance 10 or the voice dialogue system 1 particularly wants to inform the user, particularly a theme that the user wants to talk about. For example, “From 12:00 to ** Super time sale! ”,“ ** The expiry date of ** is about to expire. Should I use it now? ”.

  FIG. 11 is a flowchart showing the flow of voice conversation processing in the home appliance 10 according to the present embodiment. The flowchart shown in FIG. 11 is different from the flowchart shown in FIG. 4 in that step S30 is added between steps S2 and S3, and other processes are the same.

  As shown in FIG. 11, in step S30, when event detecting unit 11b detects that the predetermined event has occurred (YES in S2), whether or not a message to be uttered is stored in storage unit 12 or not. Judging. If stored, the process proceeds to the dialog control process (S5) in the dialog control unit 11a. If not stored, the process proceeds to the start determination process (S3 / S4) in the start determination unit 11c.

[Additional Notes]
In the above embodiment, the present invention is applied to the home appliance 10 such as the refrigerator 10-1. However, the present invention is not limited to this, and can be applied to any electronic device.

  Further, some home appliances 10 may not have a communication function with the server 20. In this case, a communication adapter having the communication function may be attached to the home appliance 10 and electrically connected. At this time, in the configuration illustrated in FIG. 2, the communication adapter includes the control unit 11, the storage unit 12, the communication unit 13, and the voice acquisition unit 15, while the home appliance 10 includes the voice output unit 14, the operation panel 16, In addition, various sensors 17 may be included. Thereby, the interactive function of this invention is realizable only by attaching the said communication adapter to the household appliance 10. FIG.

  Moreover, in the said embodiment, although the event detection part 11b has detected only one event (opening / closing of the door 46), you may detect a some event. In this case, the start condition may be set for each event.

  Moreover, in the said embodiment, although the start condition which starts the dialog with a user is set, you may set the conditions which do not start a dialog. In this case, the dialogue may be started when the condition is not satisfied.

[Example of software implementation]
The control blocks (particularly the control unit 11 and the control unit 21) of the home appliance 10 and the server 20 may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or a CPU (Central Processing Unit) ) May be implemented by software.

  In the latter case, the home appliance 10 and the server 20 include a CPU that executes instructions of a program that is software that realizes each function, and a ROM (Read Only Memory) in which the program and various data are recorded so as to be readable by a computer (or CPU). ) Or a storage device (these are referred to as “recording media”), a RAM (Random Access Memory) for expanding the program, and the like. And the objective of this invention is achieved when a computer (or CPU) reads the said program from the said recording medium and runs it. As the recording medium, a “non-temporary tangible medium” such as a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. The program may be supplied to the computer via an arbitrary transmission medium (such as a communication network or a broadcast wave) that can transmit the program. The present invention can also be realized in the form of a data signal embedded in a carrier wave in which the program is embodied by electronic transmission.

[Summary]
The electronic device (home appliance 10) according to the first aspect of the present invention is an electronic device including a dialog unit (a dialog control unit 11a) that performs a dialog with a user, and the electronic device can serve as a trigger for starting the dialog. A detection unit (event detection unit 11b) that detects the occurrence of an event; and a determination unit (start determination unit 11c) that determines whether a predetermined condition is satisfied when the detection unit detects the occurrence of the event. The dialogue unit is configured to start the dialogue according to a determination result of the determination unit.

  According to said structure, it is judged based on a predetermined condition whether an electronic device starts the dialogue with a user. That is, even if the user performs a predetermined action on the electronic device, if the predetermined condition is not met, the dialog is not started. Thereby, compared with the case where the said dialog is started whenever a user performs predetermined | prescribed action with respect to an electronic device, the dialog with the said electronic device and the said user can be performed with appropriate frequency. In addition, the frequency of operating the dialogue unit can be reduced, and as a result, power consumption can be suppressed.

  The electronic device according to aspect 2 of the present invention is the electronic device according to aspect 1, in which the history information (history data 12b) of at least one of the detection history of the occurrence of the event by the detection unit and the start history of the conversation by the interaction unit is described. ) Is further stored, and the determination unit preferably determines whether the predetermined condition is satisfied using the history information.

  In this case, it is determined whether or not the electronic device starts a dialogue with the user in consideration of the occurrence frequency of the event and / or the start frequency of the dialogue. Interaction with the user can be performed at a more appropriate frequency. In addition, the frequency of operating the dialog unit can be further reduced, and as a result, power consumption can be further suppressed.

  The electronic device according to aspect 3 of the present invention further includes a condition changing unit 11g that changes the predetermined condition based on an instruction from the user in the above-described aspect 1 or 2, and the determination unit is configured to change the condition. It may be determined whether the condition changed by the part is satisfied.

  In this case, the interaction between the electronic device and the user can be performed at a frequency desired by the user. The instruction from the user may be acquired via the operation panel 16 provided in the electronic device, or may be acquired by recognizing the voice from the user (voice recognition). Furthermore, the voice recognition may be performed by an external device (server 20).

  The electronic device according to aspect 4 of the present invention further includes a storage device that stores a message to be uttered to the user in the above aspects 1 to 2, and the dialog unit is configured such that the detection unit causes the occurrence of the event. Preferably, the dialogue is started when the message is detected and the message is stored in the storage device. In this case, it is possible to prevent the utterance of the message from being delayed.

  An electronic device control method according to an aspect 5 of the present invention is a control method for an electronic device that performs a dialog with a user, and the detection step of detecting occurrence of a predetermined event that can be a trigger for the electronic device to start the dialog. And a determination step for determining whether a predetermined condition is satisfied when the occurrence of the event is detected in the detection step, and a dialog step for starting the dialog according to a determination result of the determination step. Is the method.

  According to said method, there can exist an effect similar to the said aspect 1. FIG.

  The electronic apparatus according to each aspect of the present invention may be realized by a computer. In this case, the electronic apparatus is realized by a computer by operating the computer as each unit (software element) included in the electronic apparatus. A control program for an electronic device and a computer-readable recording medium that records the control program also fall within the scope of the present invention.

  The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope shown in the claims, and embodiments obtained by appropriately combining technical means disclosed in different embodiments. Is also included in the technical scope of the present invention. Furthermore, a new technical feature can be formed by combining the technical means disclosed in each embodiment.

1 Spoken Dialogue System 10, 10A, 10B Home Appliances (Electronic Equipment)
11 Control unit 11a, 11d Dialog control unit (dialogue unit)
11b, 11e Event detector (detector)
11c, 11f Start determination unit (determination unit)
11g Condition change unit 12 Storage unit (storage device)
12a Condition data 12b History data (history information)
DESCRIPTION OF SYMBOLS 13 Communication part 14 Audio | voice output part 15 Voice acquisition part 16 Operation panel 16a Speech button 16b Notification lamp 17 Various sensors 20, 20B Server 21 Control part 21a Voice provision function part 21b Frequency change instruction part 22 Storage part 23 Communication part 24, 24B Voice Recognition device 30 Communication terminal device 40 Relay station 46, 46a, 46b Door 47 Main body 51a / 51b Hinge cover unit 60 Communication network 70 User's house

Claims (5)

An electronic device having a dialogue unit for dialogue with a user,
A detection unit that detects the occurrence of a predetermined event that can trigger the electronic device to start the dialogue;
A determination unit that determines whether or not a predetermined condition is satisfied when the detection unit detects the occurrence of the event,
The electronic device is characterized in that the dialogue unit starts the dialogue according to a determination result of the determination unit. A storage device for storing history information of at least one of the detection history of the occurrence of the event by the detection unit and the start history of the dialog by the dialog unit;
The electronic device according to claim 1, wherein the determination unit determines whether the predetermined condition is satisfied using the history information. Further comprising a condition changing unit for changing the predetermined condition based on an instruction from the user;
The electronic device according to claim 1, wherein the determination unit determines whether the condition changed by the condition change unit is satisfied. A storage device for storing a message to be uttered to the user;
4. The dialogue unit according to claim 1, wherein the dialogue unit starts the dialogue when the detection unit detects the occurrence of the event and the message is stored in the storage device. 5. The electronic device according to any one of the above. A method of controlling an electronic device that interacts with a user,
A detection step of detecting the occurrence of a predetermined event that can trigger the electronic device to start the dialogue;
A determination step of determining whether a predetermined condition is satisfied when the occurrence of the event is detected in the detection step;
And a dialog step of starting the dialog according to a determination result of the determination step.

Images