JP6495014B2 - Spoken dialogue control device, control method of spoken dialogue control device, and spoken dialogue device - Google Patents

Description

  The present invention relates to a voice dialogue control device for controlling a voice dialogue device that responds to a user's utterance.

  2. Description of the Related Art Conventionally, a speech dialogue apparatus (robot) that interacts with a user by responding to the user's utterance with voice or motion has been widely studied. Here, in the dialogue between the user and the voice interactive device, a certain amount of time is required from when the user speaks until the voice interactive device responds according to the content of the speech. If the voice interaction device does not operate at this time, the user may feel stress in communication with the voice interaction device. As a solution to this problem, for example, in Patent Document 1 below, a waiting time from when a user input is received until the communication state with the server is restored is calculated, and predetermined information corresponding to the waiting time is calculated. A technique for presenting the above is disclosed.

JP 2014-174485 A (published on September 22, 2014) JP 2014-191030 A (released on October 06, 2014) JP 2003-330923 A (published November 21, 2003)

  However, in the techniques described in Patent Documents 1 to 3, the contents of the joining operation are uniform, and it is not possible to take a flexible response according to the length of the standby time. For example, in the technique of Patent Document 1, if the calculated waiting time is equal to or longer than a predetermined time, no matter how long the waiting time is, the connecting operation that is executed will output a message that apologizes for interruption of the dialogue. .

  The present invention has been made in view of the above problems, and an object thereof is to improve the flexibility of communication between the user and the voice interactive apparatus by executing a joint operation according to the length of the standby time. It is to provide a voice dialogue control device and the like.

  In order to solve the above-described problem, the voice conversation control device according to one aspect of the present invention can output a response to the voice from a predetermined time point after the voice dialogue device acquires the voice uttered by the user. A standby time prediction unit that predicts a standby time until the operation time, the standby time predicted by the standby time prediction unit, and an operation time required to execute each of a plurality of operation candidates indicating operations that can be executed by the voice interactive device Based on the above, a field joining operation determining unit that selects one or more of the plurality of motion candidates as a field joining operation, and a field joining that causes the voice interactive apparatus to execute the field joining operation selected by the field joining operation determining unit. An operation execution unit.

  In order to solve the above problems, a control method for a voice interaction control device according to an aspect of the present invention is a method for controlling a voice interaction control device to be executed by a voice interaction device, wherein the voice interaction device is a user. A standby time predicting step for predicting a standby time until a response to the sound can be output from a predetermined time after acquiring the voice emitted by the voice, and the standby time predicted in the standby time predicting step, Based on the operation time required for execution of each of the plurality of operation candidates indicating the operations that can be performed by the voice interaction device, the step of selecting a joint operation to select one or more from the plurality of operation candidates as a joint operation; A field joining operation execution step for causing the voice interactive apparatus to execute the field joining operation determined in the field joining operation determining step.

  According to one aspect of the present invention, there is an effect that the flexibility of communication between the user and the voice interaction apparatus is improved.

It is a block diagram which shows the structure of the voice interactive apparatus which concerns on Embodiment 1 of this invention. It is a figure which shows the data structure and example of a data which are stored in the memory | storage part of the voice interactive apparatus shown in FIG. It is a figure which shows the data structure and example of a data of a connection connection order table memorize | stored in the memory | storage part of the voice interactive apparatus shown in FIG. It is a flowchart which shows an example of the flow of the response execution process which the voice dialogue control apparatus shown in FIG. 1 performs. It is a flowchart which shows an example of the flow of the joining operation | movement determination process in the flowchart shown in FIG. It is a block diagram which shows the structure of the voice interactive apparatus which concerns on Embodiment 2 of this invention. FIG. 7 is a diagram illustrating a data structure and a data example of a joining operation table stored in a storage unit of the voice interactive apparatus shown in FIG. 6. It is a flowchart which shows an example of the flow of the place connection operation | movement determination process which the voice interactive control apparatus shown in FIG. 6 performs. It is a block diagram which shows the structure of the voice interactive apparatus which concerns on Embodiment 3 of this invention. It is a flowchart which shows an example of the flow of the response execution process which the voice interactive control apparatus shown in FIG. 9 performs.

Embodiment 1
An embodiment (Embodiment 1) of the present invention will be described below with reference to FIGS.

  First, the voice interactive apparatus 10 according to the present embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing a configuration of a voice interaction apparatus 10 according to the present embodiment.

  The voice interaction device 10 is a device that interacts with a user by responding to the user's utterance with a voice or action. In addition, although a humanoid robot is mentioned as a specific example of the voice interactive apparatus 10, it is not limited to this. For example, other specific examples of the voice interaction device 10 include a mobile terminal with a voice interaction function such as a smartphone, a car navigation system with a voice interaction function, and the like. As shown in FIG. 1, the voice interaction device 10 includes a voice interaction control device as the control unit 1. Note that the voice interaction device 10 and the voice interaction control device may be separate. The voice interaction device 10 includes a voice input unit 2, a communication unit 3, a voice output unit 4, a drive unit 5, and a storage unit 6 in addition to the control unit 1 (voice conversation control device).

  The voice input unit 2 is a so-called microphone that acquires voice uttered by the user. The voice input unit 2 converts the acquired voice into voice data and outputs the voice data to the voice recognition unit 13 described later. The voice input unit 2 outputs at least one of the size (data amount) and time (speech time) of the voice data (hereinafter referred to as voice attached information) to the standby time prediction unit 11. The communication unit 3 performs communication between the voice interaction device 10 and an external device. Specifically, the communication unit 3 is controlled by a response generation unit 14 described later, and receives data necessary for generating a response from an external device. For example, the communication unit 3 acquires data on tomorrow's weather from a weather forecast server (not shown) that manages data on weather forecasts, and outputs the data to the response generation unit 14. The audio output unit 4 is a so-called speaker that outputs audio. Specifically, the voice output unit 4 outputs a response to a voice uttered by the user and a voice as a jointing operation described later. The drive unit 5 drives a movable part such as a head or a leg in the voice interaction device 10 (humanoid robot), and is a servo motor, for example. An actuator other than the servo motor may be used. Specifically, the drive unit 5 causes the voice interaction device 10 to perform a response to a voice uttered by the user or an operation as a jointing operation by driving the movable part. In addition, when the voice interaction apparatus 10 is an apparatus that does not have a movable part such as a smartphone, the driving unit 5 may be omitted. The storage unit 6 stores various data used in the voice interaction device 10. The storage unit 6 stores at least a field connection operation table 61 and a field connection order table 62. Details of these tables will be described later.

  The control unit 1 performs overall control of each unit included in the voice interaction device 10. The control unit 1 includes a standby time prediction unit 11, a joining operation control unit 12, a voice recognition unit 13, a response generation unit 14, and a response execution unit 15.

  The standby time prediction unit 11 predicts a standby time from when the voice interaction apparatus 10 acquires a voice uttered by the user until a response to the voice can be output. Specifically, when the standby time prediction unit 11 receives the audio attachment information from the audio input unit 2, the standby time prediction unit 11 predicts the standby time using the size (data amount) of the audio data. More specifically, the standby time prediction unit 11 uses the calculation formula “standby time = α × data amount (α is a standby time required per unit data amount, which is a predetermined value)” to calculate the standby time. Is calculated. The standby time predicting unit 11 outputs the predicted (calculated) standby time to the place transition operation determining unit 21 described later. Note that the standby time prediction unit 11 may predict the standby time using the time of the voice data (user's speech time). Specifically, the standby time prediction unit 11 uses the calculation formula “standby time = β × speech time (β is a standby time required per unit utterance time, which is a predetermined value)”. May be calculated. Further, the standby time may be predicted (calculated) using both the data amount of the voice data and the speech time. When the waiting time calculated from the data amount and the waiting time calculated from the utterance time are different, the longer (or shorter) waiting time may be adopted, or the average value of the two waiting times is calculated and calculated. The average waiting time may be output to the operation determining unit 21 by connecting.

  The field connection operation control unit 12 determines and executes the field connection operation. The field connection operation control unit 12 includes a field connection operation determination unit 21 and a field connection operation execution unit 22.

  Based on the standby time predicted by the standby time predicting unit 11, the cross-linking operation determining unit 21 determines the connecting operation performed by the voice interaction device 10. Here, the place-joining operation is an operation that is executed by the voice interaction apparatus 10 during the standby time, that is, the time from when the voice uttered by the user is acquired until the response to the voice can be output. Specifically, the field connection operation determination unit 21 uses the field connection operation table 61 stored in the storage unit 6 to predict the standby time predicted by the standby time prediction unit 11 and the voice interaction apparatus 10 during the standby time. The field joining operation is determined in accordance with the field joining operation time required for the field joining operation to be executed by the computer.

  Here, with reference to FIG. 2, the details of the joining operation table 61 will be described. FIG. 2 is a diagram illustrating a data structure and a data example of the connection operation table 61 stored in the storage unit 6. 2 is an example, and the data structure and the data example are not limited to the example in FIG. The field connection operation table 61 is a table in which information indicating a field connection operation is associated with a field connection operation time that is a time required for the field connection operation. Stored in the “place-joining action” column is information on a plurality of action candidates (hereinafter referred to as place-joining action information) indicating actions that can be executed by the voice interaction apparatus 10. In the “type” column, whether the connection operation at each place outputs a voice (indicated by “voice” in FIG. 2), or moves the movable part of the voice interactive apparatus 10 ( Information indicating whether or not to perform both (indicated by “gesture” in FIG. 2) (indicated by “voice + gesture” in FIG. 2) is stored. The above-mentioned “joining operation time” is stored in the “joining operation time” column.

More specifically, the field connection operation determination unit 21 subtracts each field connection operation time in the field connection operation table 61 from the received standby time, and subtracts the value T _N (first subtraction value) in each field connection operation information. ) Is calculated. Note that N is a number stored in “No.” in the connection operation table 61. Subsequently, for each of the calculated subtraction values T _N , the field connection operation determination unit 21 is greater than or equal to 0, and from the time when the voice interaction apparatus 10 executes the field connection operation until the generation of the response is completed, the voice interaction apparatus 10. It is determined whether or not the time is equal to or shorter than a first allowable time X indicating a time that is allowable as a time during which no operation is performed (whether there is connection operation information that satisfies 0 ≦ T _N ≦ X). The first allowable time X is a preset value. For example, if X = 2, the allowable time from the completion of the splicing operation until the generation of the response is 2 seconds. That is.

When there is field connection operation information satisfying 0 ≦ T _N ≦ X, the field connection operation determination unit 21 determines the field connection operation indicated by the field connection operation information as a field connection operation that causes the voice interaction apparatus 10 to execute, and The field connection operation information is output to the field connection operation execution unit 22. For example, when the standby time is 2 seconds and the first allowable time X = 1, No. 1 shown in FIG. 2 and no. The field connection operation information of 3 satisfies 0 ≦ T _N ≦ X. Therefore, the spot-linking operation determining unit 21 determines the No. 2 or No. 3 is read out and output to the connecting operation execution unit 22.

In addition, when there are a plurality of field connection operation information satisfying 0 ≦ T _N ≦ X, the field connection operation information with a smaller value of the subtraction value T _N is used in order to shorten the time during which the voice interactive device 10 does not execute the operation. Is preferably selected. That is, in the case of the above example, No. 1 in which the subtraction value _TN is 0. It is preferable to select the operation information for connecting the three. Further, when there are a plurality of field joining operation information having the same value of the subtraction value _TN , one of the field joining operation information may be selected at random.

On the other hand, when there is no field joining operation information that satisfies 0 ≦ T _N ≦ X, the field joining operation determining unit 21 changes the sign change value −T _N (second subtraction) that is a value obtained by changing the sign of the subtraction value T _N. (Value) For each of them, it is 0 or more and whether or not it is equal to or less than a second allowable time Y indicating an allowable time from when the generation of the response is completed to when the connection operation of the voice interactive device 10 is completed (0 ≦ −T _N ≦ Y or not is determined). The second allowable time Y is a preset value. For example, if Y = 2, the allowable time from the completion of response generation to the completion of the splicing operation is 2 seconds. That is. Incidentally, the field joint operation determining unit 21 may calculate the code conversion value -T _N by subtracting the waiting time received from the play connecting operation time.

When there is field connection operation information satisfying 0 ≦ −T _N ≦ Y, the field connection operation determination unit 21 determines the field connection operation indicated by the field connection operation information as a field connection operation that causes the voice interaction apparatus 10 to execute. The field connection operation information is output to the field connection operation execution unit 22. For example, when the standby time is 1 second and the second allowable time Y = 1, No. 1 shown in FIG. 2 and no. The field connection operation information of 3 satisfies 0 ≦ −T _N ≦ Y. For this reason, the place-connecting operation determination unit 21 determines whether the No. 2 or No. 3 is read out and output to the connecting operation execution unit 22.

Incidentally, 0 ≦ -T If field joint operation information satisfying _N ≦ Y have multiple, in order to shorten the time for the voice dialogue system 10 does not perform the operation, the value of the code conversion value -T _N is smaller than field It is preferable to select bridging operation information. In other words, in the case of the above example, the code conversion value −T _N becomes 0. It is preferable to select the operation information for connecting the two points. Also, if the value of the code conversion value -T _N there are multiple same field joint operation information, a field joint operation information may be selected in a single random from those.

  Note that, in at least one of the first allowable time X and the second allowable time Y, the same value may be set for all the joining motion information, or different values may be set for each joining motion information. Good. Further, at least one of the first allowable time X and the second allowable time Y may be set according to at least one of the amount of audio data and the speech time. That is to say, the field connection operation determination unit 21 determines at least one of the first allowable time X and the second allowable time Y based on the data amount or speech time of the audio data received from the standby time prediction unit 11.

On the other hand, when there is no field connection operation information that satisfies 0 ≦ −T _N ≦ Y, the field connection operation determination unit 21 selects a plurality of field connection operation information. Specifically, the field connection operation determination unit 21 selects one field connection operation information having the longest field connection operation time among the field connection operation information satisfying the field connection operation time ≦ the standby time. Then, a value (remaining time) obtained by subtracting the field connection operation time associated with the selected field connection operation information from the standby time is calculated, and the field connection operation information satisfying the field connection operation time ≦ the remaining time is further selected. . Then, the field connection operation determination unit 21 calculates a total value obtained by summing the field connection operation times associated with the selected plurality of field connection operation information, and 0 ≦ standby time−total value ≦ X or 0 ≦ − ( It is determined whether or not standby time−total value) ≦ Y is satisfied. When either one is satisfied, a plurality of field connection operation information is output to the field connection operation execution unit 22 in association with the numbers in the “No.” column.

  On the other hand, if none of them is satisfied, a value obtained by subtracting the total value from the waiting time is calculated, and the joining operation information satisfying the joining operation time ≦ the calculated value is further selected. Then, the field connection operation determination unit 21 calculates a total value obtained by summing the field connection operation times associated with the selected plurality of field connection operation information, and 0 ≦ standby time−total value ≦ X or 0 ≦ − ( It is determined whether or not standby time−total value) ≦ Y is satisfied. The field connection operation determination unit 21 repeats these processes until either 0 ≦ standby time−total value ≦ X or 0 ≦ − (standby time−total value) ≦ Y is satisfied.

  The field connection operation execution unit 22 causes the voice interaction apparatus 10 to execute the field connection operation indicated by the field connection operation information determined by the field connection operation determination unit 21. Specifically, when the field connection operation execution unit 22 receives the field connection operation information from the field connection operation determination unit 21, the field connection operation execution unit 22 causes the voice interaction apparatus 10 to execute the field connection operation indicated by the field connection operation information. For example, the voice output unit 4 is controlled to output a voice, or the drive unit 5 is controlled to operate a movable part of the voice interaction device 10. When the execution of the joining operation is completed, the jumping operation execution unit 22 notifies the response execution unit 15 to that effect. In addition, when the field connection operation execution unit 22 receives a plurality of field connection operation information from the field connection operation determination unit 21, a plurality of field connection operation information is stored using the field connection order table 62 stored in the storage unit 6. The execution order of the connection operation indicated by is determined.

  Here, the details of the joining order table 62 will be described with reference to FIG. FIG. 3 is a diagram illustrating a data structure and data example of the connecting sequence table 62 stored in the storage unit 6. 3 is merely an example, and the data structure and the data example are not limited to the example in FIG. The field connection order table 62 is a table in which combinations of field connection operations are associated with the order of field connection operations in the combinations. In other words, the field joining operation execution unit 22 can determine the order in which the field joining operation indicated by the plurality of field joining operation information received from the field joining operation determination unit 21 is executed by referring to the field joining order table 62. it can. A plurality of numbers in the “No.” column of the field connection operation table 61 are stored in the “field connection operation No.” column. In the column, the order of a plurality of numbers has no particular meaning. On the other hand, a plurality of numbers in the “No.” column of the joining operation table 61 are also stored in the “operation order” column. However, the order of the numbers in the column indicates the order in which the joining operation is performed. For example, as shown in FIG. 1 is “3, 2”, the No. 1 shown in FIG. No. 3 shown in FIG. 2 shows that the field connection operation indicated by the field connection operation information is executed. In the column of “joining operation”, the contents of the joining operation corresponding to the order stored in the “operation order” column are stored. This column is shown for easy understanding of the operation order, and may be omitted from the joining order table 62. Further, the joining order table 62 may be editable by the user.

  The field joining operation execution unit 22 identifies a combination of numbers “No.” associated with a plurality of field joining operation information received from the field joining order table 62 from the “field joining operation No” column. The operation sequence of the spot connection operation is specified. Then, the voice interactive device 10 is caused to execute the connecting operation in the specified operation order. Note that the determination of the operation order of a plurality of spot joining operations is not limited to the example using the spot joining order table 62 described above. For example, the jumping operation execution unit 22 may randomly determine the operation order of a plurality of jumping operations, or sets the movement order in ascending order of the numbers “No.” associated with the jumping operation. Also good. In this case, the storage unit 6 does not have to store the joining order table 62.

  The voice recognition unit 13 performs voice recognition processing on the voice data received from the voice input unit 2. Note that existing technology can be used for the speech recognition processing. The voice recognition unit 13 outputs the voice recognition result of the received voice data to the response generation unit 14.

  The response generation unit 14 generates response information indicating a response to the voice uttered by the user. There are three types of responses: voice output, movement of the moving part of the voice interaction device 10, and voice output and movement of the movable part. An existing technique can be used to generate response information by the response generation unit 14. For example, a table (not shown) in which the content of the voice data recognized and the response content are associated with each other may be stored in the storage unit 6, and the response information may be generated by referring to the table. In addition, when it is necessary to use external data such as tomorrow's weather information to generate response information, the response generation unit 14 generates response information using the external data acquired by controlling the communication unit 3. . The response generation unit 14 outputs the generated response information (voice data for voice output, action data for operating the movable part, etc.) to the response execution unit 15.

  The response execution unit 15 executes a response indicated by the response information generated by the response generation unit 14. Specifically, when the response execution unit 15 receives the response information from the response generation unit 14 and is notified that the joining operation has been completed from the joining operation executing unit 22, the response information indicates the operation indicated by the response information. Let the device 10 execute it. For example, the voice output unit 4 is controlled to output a voice, or the drive unit 5 is controlled to operate a movable part of the voice interaction device 10.

  Next, based on FIG. 4, the flow of response execution processing executed by the control unit 1 will be described. FIG. 4 is a flowchart illustrating an example of a response execution process executed by the control unit 1.

  First, the voice input unit 2 waits for voice input (S1). When the voice input unit 2 acquires the voice uttered by the user (YES in S1), the voice input unit 2 converts the acquired voice into voice data, outputs the voice data to the voice recognition unit 13, and the voice attached information of the voice data. Is output to the standby time prediction unit 11.

  Subsequently, the standby time prediction unit 11 predicts the standby time (S2, standby time prediction step). The standby time prediction unit 11 outputs the predicted standby time to the operation determination unit 21 by connecting. Subsequently, the field joining operation determination unit 21 performs a field joining operation determination process (S3). Note that the details of the joining operation determination process will be described later. The field connection operation determination unit 21 outputs the field connection operation information indicating the field connection operation determined to be executed by the voice interaction apparatus 10 to the field connection operation execution unit 22. Then, the field connection operation execution unit 22 causes the voice interaction device 10 to execute the field connection operation according to the received field connection operation information (S4, field connection operation execution step). When the execution of the joining operation is completed, the jumping operation execution unit 22 notifies the response execution unit 15 to that effect.

  On the other hand, the voice recognition unit 13 performs voice recognition processing (S5). Specifically, when receiving the voice data, the voice recognition unit 13 performs voice recognition processing on the voice data and outputs the voice recognition result to the response generation unit 14. Subsequently, the response generation unit 14 generates response information (S6). Specifically, the response generation unit 14 generates response information corresponding to the received voice recognition result and outputs the response information to the response execution unit 15.

  As shown in FIG. 4, the processes in steps S2, S3, and S4 and the processes in steps S5 and S6 are performed in parallel. That is, when only one of the response information and the notification that the execution of the joining operation is completed is received, the response execution unit 15 waits until the other is received. When the response execution unit 15 receives the notification and the response information, the response execution unit 15 causes the voice interaction device 10 to execute a response (S7). Specifically, the response execution unit 15 controls the voice output unit 4 to output voice or controls the drive unit 5 to operate the movable part of the voice interaction device 10 according to the received response information. To do. Thus, the response execution process ends.

  Next, the flow of the field connection operation determination process executed by the field connection operation determination unit 21 will be described with reference to FIG. FIG. 5 is a flowchart showing an example of the flow of the jointing operation determination process in the flowchart of FIG. In the flowchart of FIG. 5, it is assumed that the field connection operation information included in the field connection operation table 61 is associated with a field connection operation time that is generally equal to a standby time.

First, when a standby time is received from the standby time predicting unit 11, the field transition operation determination unit 21 reads the field transition operation table 61 and calculates a subtraction value _TN obtained by subtracting each field connection operation time from the predicted standby time. (S11). Subsequently, the field connection operation determination unit 21 refers to the field connection operation table 61 using the calculated subtraction value _TN and the first allowable time X, and determines whether there is field connection operation information satisfying 0 ≦ T _N ≦ X. It is determined whether or not (S12).

When there is field connection operation information satisfying 0 ≦ T _N ≦ X (YES in S12), the field connection operation determination unit 21 performs the field connection operation indicated by one of the field connection operation information by the voice interactive device 10. It is determined to be a place joining operation to be executed (S13, place joining operation determining step). Specifically, the field connection operation information having a smaller value of T _N is selected from the field connection operation information satisfying 0 ≦ T _N ≦ X. Then, the field connection operation determination unit 21 outputs the selected field connection operation information to the field connection operation execution unit 22.

On the other hand, 0 ≦ _{T N} When situ joint operation information satisfying ≦ X is not (NO at S12), the field joint operation determiner 21 calculates a sign change value -T _N from the subtraction value _{T N,} sign change value - It is determined whether or not there is connection operation information satisfying 0 ≦ −T _N ≦ Y by referring to the connection operation table 61 using _TN and the second allowable time Y (S14).

When there is field connection operation information satisfying 0 ≦ −T _N ≦ Y (YES in S14), the field connection operation determination unit 21 displays the field connection operation indicated by one of the field connection operation information as the voice interactive device 10. Is determined to be a field joining operation to be executed (S15, field joining operation determining step). Specifically, of the field joint operation information satisfying 0 ≦ -T _N ≦ Y, the value of -T _N selects a smaller field joint operation information.

On the other hand, when there is no field connection operation information satisfying 0 ≦ −T _N ≦ Y (NO in S14), the field connection operation information indicating the field connection operation executed by the voice interactive device 10 by combining a plurality of field connection operations and (S16, step of determining the jointing operation). In this case, in step S4, the field connection operation execution unit 22 refers to the field connection order table 62 using the received plurality of field connection operation information and the number “No.”, and performs a plurality of field connection operations. The execution order (operation order) is specified, and the jumping operation is executed in the specified operation order. This is the end of the joining operation determination process.

  In the present embodiment, when the generation of the response information is completed earlier than the standby time predicted by the standby time prediction unit 11, the joining operation determining unit 21 selects a plurality of joining operations. In this case, the joining operation executing unit 22 may cancel the execution of the joining operation performed after that time. Specifically, when the response transfer unit 15 is notified that the response can be output from the response execution unit 15, the connection transfer operation unit 22 cancels the execution of the link transfer operation performed after that time, The response execution unit 15 is notified that the execution of the operation has been completed. Further, the field connection operation determination unit 21 may change the field connection operation time of a plurality of field connection operations to be combined.

[Embodiment 2]
Another embodiment (second embodiment) of the present invention will be described below with reference to FIGS. For convenience of explanation, members having the same functions as those described in the embodiment are given the same reference numerals, and descriptions thereof are omitted.

In the first embodiment described above, when there is no field connection operation information that satisfies 0 ≦ −T _N ≦ Y, a plurality of field connection operation information is combined to obtain field connection operation information that satisfies 0 ≦ −T _N ≦ Y. . On the other hand, in this embodiment, when there is no field connection operation information that satisfies 0 ≦ −T _N ≦ Y, by changing the field connection operation time associated with the field connection operation information, 0 ≦ −T _N ≦ Y. An example of the connection operation information that satisfies the following conditions will be described.

  First, the voice interactive apparatus 10a according to the present embodiment will be described with reference to FIG. FIG. 6 is a block diagram showing the configuration of the voice interaction apparatus 10a according to this embodiment. As shown in FIG. 6, the voice interaction device 10 a includes a control unit 1 a instead of the control unit 1 and a storage unit 6 a instead of the storage unit 6 as compared with the voice interaction device 10 according to the first embodiment. ing. In the present embodiment, the control unit 1a includes a field joining operation control unit 12a instead of the field joining operation control unit 12 as compared with the control unit 1 according to the first embodiment. In addition, the storage unit 6 a stores a joining operation table 61 a instead of the joining operation table 61 as compared with the storage unit 6 according to the first embodiment. Further, unlike the storage unit 6, the storage unit 6 a does not store the connection order table 62.

  The field connection operation control unit 12a determines and executes the field connection operation. The field connection operation control unit 12a includes a field connection operation determination unit 21a and a field connection operation execution unit 22a.

The field connection operation determination unit 21a determines a field connection operation performed by the voice interaction device 10a based on the standby time predicted by the standby time prediction unit 11. Unlike the field connection operation determination unit 21 according to the first embodiment, the field connection operation determination unit 21a refers to the field connection operation table 61a when there is no field connection operation information that satisfies 0 ≦ −T _N ≦ Y. By changing the field connection operation time associated with the connection operation information, the field connection operation information satisfying 0 ≦ −T _N ≦ Y is obtained.

  Here, with reference to FIG. 7, the detail of the joining operation | movement table 61a is demonstrated. FIG. 6 is a diagram illustrating a data structure and a data example of the joining operation table 61a stored in the storage unit 6a. In the field connection operation table 61a, the field connection operation information and the field connection operation time are further associated with information indicating the change range of the field connection operation time. In the column of “placement operation time change width”, a numerical value (change permission information, hereinafter referred to as change width) indicating a changeable range of each place connection operation time is stored. For example, no. In the field joining operation of No. 2, the field joining operation time is 1 second, but the change width is 0.8 to 1.5 seconds. This means that no. This shows that the linking operation of 2 can be made faster or slower in the time range of 0.8 to 1.5 seconds, that is, the utterance of “um”. In the example of FIG. 7, time range information is stored as the change width, but the change width is not limited to this example. For example, as a change width, information of a percentage (for example, information such as “80 to 150%”) using the connection operation time as the reference time (100%) may be stored. Also, the change width may be the same for all the connection operation information.

More specifically, when there is no field connection operation information satisfying 0 ≦ −T _N ≦ Y, the field connection operation determination unit 21a refers to the field connection operation table 61a and 0 ≦ T _N ≦ X or 0 ≦. The field connection operation information including a numerical value satisfying −T _N ≦ Y in the change width is specified, and the numerical value is set as a new field connection operation time. Then, the identified field connection operation information and the changed field connection operation time are associated with each other and output to the field connection operation execution unit 22a. When the change width is a percentage, the field joining operation determination unit 21a obtains a new field joining operation time by multiplying the field joining operation time (reference time) and the percentage.

  The field connection operation execution unit 22a causes the voice interaction device 10a to execute the field connection operation indicated by the field connection operation information determined by the field connection operation determination unit 21a. Unlike the field connection operation execution unit 22 according to the first embodiment, the field connection operation execution unit 22a receives the field connection operation information and the field connection operation time from the field connection operation determination unit 21a. The voice interactive device 10a is caused to execute the jointing operation so that the jointing operation indicated by the jointing operation information is completed. For example, when receiving the field connection operation information indicating the utterance of “Et.” And the field connection operation time of 1.5 seconds, the field connection operation execution unit 22a normally utters the speech (voice output). “Et.” (Output from the unit 4) is extended to 1.5 seconds and output from the audio output unit 4.

  Next, based on FIG. 8, the flow of the field joining operation determination process executed by the field joining operation determination unit 21a will be described. FIG. 8 is a flowchart showing an example of the flow of the field connection operation determination process in the present embodiment. The response execution process in the present embodiment is the same as the response execution process described in the first embodiment (the response execution process shown in FIG. 4) except for the contents of the joining operation determination process. Description is omitted. Also, in the flowchart shown in FIG. 8, steps S21 to S25 are the same as steps S11 to S15 shown in FIG.

When there is no field connection operation information that satisfies 0 ≦ −T _N ≦ Y (NO in S24), the field connection operation determination unit 21a changes the field connection operation time to 0 ≦ T _N ≦ X or 0 ≦ −T. _The joining operation is performed when _N ≦ Y is satisfied (S26). Then, the identified field connection operation information and the changed field connection operation time are associated with each other and output to the field connection operation execution unit 22a. In this case, in step S4, when the field connection operation execution unit 22a receives the field connection operation information and the field connection operation time from the field connection operation determination unit 21a, the field connection operation information is displayed in the field connection operation time. The voice interactive device 10a is caused to execute the joining operation so that the joining operation shown is completed. Finally, when the joining operation is completed, the joining operation executing unit 22a notifies the response executing unit 15 to that effect. This is the end of the joining operation determination process.

[Embodiment 3]
The following will describe still another embodiment (Embodiment 3) of the present invention with reference to FIGS. 9 and 10. FIG. For convenience of explanation, members having the same functions as those described in the embodiment are given the same reference numerals, and descriptions thereof are omitted.

  In the first and second embodiments described above, the standby time is predicted using at least one of the amount of speech data and the speech time. On the other hand, in the present embodiment, an example in which a voice recognition result is further used will be described.

  First, the voice interactive apparatus 10b according to the present embodiment will be described with reference to FIG. FIG. 9 is a block diagram showing the configuration of the voice interactive apparatus 10b according to the present embodiment. As shown in FIG. 9, the voice interaction device 10 b includes a control unit 1 b instead of the control unit 1 as compared with the voice interaction device 10 according to the first embodiment. In this embodiment, compared with the control unit 1 according to the first embodiment, the control unit 1b includes a standby time prediction unit 11b instead of the standby time prediction unit 11, and replaces the field connection operation control unit 12 with a field connection. An operation control unit 12b is included, and a voice recognition unit 13b is included instead of the voice recognition unit 13.

  Unlike the standby time prediction unit 11 according to the first embodiment, the standby time prediction unit 11b first determines the voice recognition standby time from when the voice uttered by the user is acquired until the voice recognition unit 13b completes the voice recognition. Predict. Specifically, when the standby time predicting unit 11b receives the voice attached information from the voice input unit 2, the standby time predicting unit 11b predicts the voice recognition standby time using the size (data amount) of the voice data. Note that the example using the data amount has already been described in the first embodiment, and thus the description thereof is omitted here. Further, when the standby time predicting unit 11b operates to receive the voice recognition result from the voice recognition unit 13b, the standby time prediction unit 11b predicts a response generation standby time from when the voice recognition process is completed until a response can be output. Specifically, the standby time prediction unit 11b predicts the response generation standby time using the size (data amount) of the audio data. Note that the example using the data amount has already been described in the first embodiment, and thus the description thereof is omitted here. Further, the standby time prediction unit 11b may predict the voice recognition standby time and the response generation standby time using the time of the voice data (user's utterance time). Further, the voice recognition standby time and the response generation standby time may be predicted (calculated) using both the data amount of the voice data and the speech time. Since an example using the utterance time and an example using both the data amount and the utterance time have already been described in the first embodiment, description thereof is omitted here.

  Further, the standby time prediction unit 11b corrects the predicted (calculated) response generation standby time according to the received voice recognition result. Specifically, when the speech recognition result indicates that the response generation unit 14 needs to perform some kind of search via the communication unit 3, it is expected that the time required for generating the response information will be long. In this case, the standby time prediction unit 11b increases the response generation standby time according to the number of necessary searches. For example, if the voice recognition result indicates that the voice data contains words that require information to be acquired from an external server that manages the weather forecast, such as “Tomorrow's weather” and “Precipitation probability” Increase the response generation waiting time. In addition, when the voice recognition result indicates that the voice interaction device 10b needs to recognize the user (for example, call the user name as a response, face the user), the user can be identified, It is expected that the time required for generating the response information will be longer because it is necessary to specify the location where there is. Also in this case, the standby time prediction unit 11b increases the response generation standby time. Note that the process of identifying the user and specifying the location where the user is located can be performed by acquiring a moving image or a still image from a camera (not shown) provided in the voice interactive apparatus 10b. Then, the standby time prediction unit 11b outputs the response generation standby time to the operation determination unit 21b. Note that the standby time prediction unit 11b may predict the response generation standby time from only the speech recognition result by a method such as predicting the standby time from the data size of the speech recognition result.

  Compared to the field connection operation control unit 12 according to the first embodiment, the field connection operation control unit 12b includes a field connection operation determination unit 21b instead of the field connection operation determination unit 21, and replaces the field connection operation execution unit 22. A tethering operation execution unit 22b is included.

  Unlike the field connection operation determination unit 21, the field connection operation determination unit 21b determines the field connection operation to be executed by the voice interaction device 10b when receiving the voice recognition standby time or the response generation standby time from the standby time prediction unit 11b. Note that the details of the determination are the same as those of the joining operation determination unit 21 according to the first embodiment, and thus the description thereof is omitted here.

  Unlike the field connection operation execution unit 22, the field connection operation execution unit 22b completes the execution of the field connection operation during the voice recognition standby time, and from the field connection operation determination unit 21b during the response generation standby time. When the field connection operation information of the field connection operation to be executed is received, the voice interaction device 10b is caused to execute the field connection operation during the response generation waiting time.

  Unlike the speech recognition unit 13 according to the first embodiment, the speech recognition unit 13b outputs a speech recognition result to the response generation unit 14 and the standby time prediction unit 11b.

  Next, the flow of response execution processing executed by the control unit 1b will be described with reference to FIG. FIG. 10 is a flowchart illustrating an example of the flow of response execution processing executed by the control unit 1b.

  First, the voice input unit 2 waits for voice input (S31). When the voice input unit 2 acquires the voice uttered by the user (YES in S31), the voice input unit 2 converts the acquired voice into voice data, outputs the voice data to the voice recognition unit 13b, and the voice attached information of the voice data. Is output to the standby time prediction unit 11b.

  Subsequently, the standby time prediction unit 11b predicts a speech recognition standby time (S32). The standby time prediction unit 11b outputs the predicted voice recognition standby time to the operation determination unit 21b. Subsequently, the field connection operation determination unit 21b performs a field connection operation determination process (S33). Note that the details of the jointing operation determination process are the same as those in the first embodiment, and thus the description thereof is omitted here. The field connection operation determination unit 21b outputs, to the field connection operation execution unit 22b, field connection operation information indicating the field connection operation determined to be executed by the voice interaction apparatus 10b. Then, the place joining operation execution unit 22b causes the voice interaction device 10b to execute the place joining operation according to the received place joining operation information (S34).

  On the other hand, the voice recognition unit 13b performs voice recognition processing (S35). The voice recognition unit 13b outputs the voice recognition result to the standby time prediction unit 11b and the response generation unit 14.

  When receiving the voice recognition result, the standby time predicting unit 11b predicts a response generation standby time based on the voice attached information and the voice recognition result (S36). The standby time prediction unit 11b outputs the predicted response generation standby time to the operation determination unit 21b. Subsequently, the field joining operation determination unit 21b performs a field joining operation determination process (S37). The field connection operation determination unit 21b outputs, to the field connection operation execution unit 22b, field connection operation information indicating the field connection operation determined to be executed by the voice interaction apparatus 10b.

  On the other hand, the response generation unit 14 generates response information (S39). Specifically, the response generation unit 14 generates response information corresponding to the received voice recognition result and outputs the response information to the response execution unit 15.

  As shown in FIG. 10, when the execution of the field connection operation in step S34 is completed and the field connection operation determination process in step S37 is completed, the field connection operation execution unit 22b performs the field connection operation determination unit 21b. The voice dialogue device 10b is caused to execute the joining operation in accordance with the joining operation information received from (S38). Here, when one of the process of step S34 and the process of step S37 has not ended, the joining operation executing unit 22b waits until the process ends.

  Also, as shown in FIG. 10, the process of step S38 and the process of step S39 are performed in parallel. That is, when only one of the response information and the notification that the execution of the joining operation is completed is received, the response execution unit 15 waits until the other is received. When the response execution unit 15 receives the notification and the response information, the response execution unit 15 causes the voice interaction device 10b to execute a response (S40). Thus, the response execution process ends.

  In the present embodiment, the joining operation is executed in the voice interaction device 10b during the speech recognition process, but the joining process may not be executed during the speech recognition process. In this case, when the voice input unit 2 acquires the voice, the voice input unit 2 outputs the voice data of the voice to only the voice recognition unit 13b. In this case, steps S32 to S34 in FIG. 10 are omitted. That is, the standby time predicted by the standby time prediction unit 11b is only the response generation standby time.

[Modification]
In Embodiment 1 described above, the voice recognition of the voice uttered by the user and the generation of response information for the voice are both performed by the voice dialogue control device (control unit 1). An external device (external server, not shown) that can communicate with the device 10 may perform the processing. That is, when the voice interaction apparatus 10 acquires voice, it converts it into voice data, and transmits the voice data to an external device via the communication unit 3. The external device performs voice recognition and response information generation, and transmits the response information to the voice interaction device 10. Alternatively, the determination using only one of the first allowable time X and the second allowable time Y may be performed. In addition, in the case where there are a plurality of pieces of place joining operation information that satisfy the condition, the place joining operation determining unit 21 selects the one having a smaller subtraction value T _N (or sign change value −T _N ). It is not limited to. For example, if there is a column for storing history information indicating the date and time when each place-joining operation was last executed in the place-joining operation table 61, and there are a plurality of place-joining action information that satisfy the conditions, the date and time when the history information is older. You may choose what is shown. Further, when the generation of response information is completed earlier than the standby time predicted by the standby time prediction unit 11, the joining operation execution unit 22 increases the speed of the joining operation that is being executed, and the execution of the operation is performed. It may be completed early. Specifically, when the response execution unit 15 is notified that the response can be output, the connection operation execution unit 22 increases the speed of the connection operation performed. These modifications can also be applied to the second and third embodiments.

  In the above-described first embodiment, when the response information generation takes longer than the standby time predicted by the standby time prediction unit 11, the standby time prediction unit 11 displays the voice recognition result performed by the voice recognition unit 13. It may be used to predict the waiting time again. When the new standby time becomes longer than the previous standby time, the joining operation determining unit 21 may determine the joining operation again. This modification can also be applied to the second embodiment.

  In the above-described first embodiment, when the type of the field connection operation determined by the field connection operation determination unit 21 is “voice”, the field connection operation time is shorter than the determined field connection operation and the type is “gesture”. May be selected, and the two pieces of field connection operation information may be combined and output to the field connection operation execution unit 22. Similarly, when the determined type of the field transition operation is “gesture”, the field transition operation time is shorter than the determined field transition operation and the type is “speech”, and The joining operation information may be combined and output to the joining operation execution unit 22. For example, in FIG. In the case where the place-joining operation (type: gesture, performing “getting up” action) indicated by the place-joining action information in FIG. No. 2 4 is further determined as a place-joining operation executed by the voice interaction device 10, and the place-joining action information indicated by the place-joining action information indicated by the place-joining action information in FIG. The data is output to the connecting operation execution unit 22. Upon receiving this information, the place-linking operation execution unit 22 causes the voice interaction apparatus 10 to execute “an operation to“ wake up ”while speaking“ Please wait a moment ””. As a result, variations in the joining operation can be increased and the user can be prevented from getting bored. This modification can also be applied to the second and third embodiments.

[Example of software implementation]
The voice interaction control device, that is, the control unit 1, the control unit 1a, and the control unit 1b may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or may be a CPU (Central Processing Unit). ) May be implemented by software.

  In the latter case, the voice interaction device 10 includes 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). Alternatively, a storage device (these are referred to as “recording media”), a RAM (Random Access Memory) that expands the program, and the like are provided. 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 voice conversation control device (control unit 1) according to the first aspect of the present invention can output a response to the voice from a predetermined time after the voice dialogue device (10) acquires the voice uttered by the user. The waiting time prediction unit (11) that predicts the waiting time until the waiting time, the waiting time predicted by the waiting time prediction unit, and the operations required to execute each of a plurality of motion candidates indicating the operations that can be performed by the voice interactive device And, based on the time, select one or more of the plurality of motion candidates as a field connection operation, a field connection operation determination unit (21), and the field connection operation selected by the field connection operation determination unit as the field connection operation. And a connection operation execution unit (22) to be executed.

  According to the above configuration, since the joining operation is determined from the plurality of motion candidates based on the standby time and the operation time required for each of the plurality of motion candidates, the length of the standby time is determined in the voice interaction device. It is possible to execute the connecting operation according to the situation. For example, when the waiting time is short, a joining operation is executed in a short time such as uttering “um”. When the waiting time is long, a joining operation such as a “repeating periodically the operation of raising and lowering the neck with arms folded” is executed when it takes a long time to complete. Therefore, the flexibility of communication between the user and the voice interaction device can be improved.

  The “predetermined time point after acquiring the voice uttered by the user” is a word indicating the start point of the standby time. The start point of the waiting time indicated by the wording may be the time when the voice uttered by the user is acquired, may be the time after a predetermined time after acquiring the voice, or the voice recognition process is completed. It may be the time when the generation of the response is started. In other words, the start point of the waiting time can be arbitrarily set after the voice uttered by the user is acquired until the response to the voice can be output.

  In the voice interaction control device according to aspect 2 of the present invention, in the aspect 1 described above, the joining motion determination unit includes a first subtraction value obtained by subtracting the operation time from the standby time among the plurality of operation candidates. The motion candidates that are equal to or greater than 0 and less than or equal to a first permissible time indicating a time that is acceptable as a time during which the voice interactive device does not operate until the response can be output after the execution of the splicing operation is completed. It may be determined as the above-described place-joining operation.

  According to the above configuration, since the standby time is longer than the operation time, and the operation in which the difference between the standby time and the operation time is equal to or less than the first allowable time is determined as the joining operation, the response is made after the joining operation is finished. The time during which the voice interactive apparatus does not operate can be minimized until the process is executed. Thereby, it can prevent that a user feels stress in communication with a voice interactive apparatus.

  In the voice interaction control device according to aspect 3 of the present invention, in the aspect 2, the first allowable time is at least one of the motion candidates or the time of the sound and the size of the sound data generated from the sound. It may be set according to one.

  Regarding the time during which the voice interactive device does not operate after the end of the connecting operation until the response is executed, the time that the user can accept is considered to be different for each operation. Therefore, according to the above configuration, the first allowable time is set for each motion candidate, so that the allowable time according to the motion can be set. For example, the allowable time according to the operation can be set by shortening the first allowable time for an operation with a short operation time or increasing the first allowable time for an operation with a long operation time.

  Further, when the time of the sound and the size of the sound data generated from the sound are large, the actual standby time is likely to be affected by the outside, so that the deviation from the predicted standby time is considered to be large. Therefore, according to the above configuration, since the first allowable time is set according to at least one of the time of the sound and the size of the sound data generated from the sound, the difference between the actual waiting time and the predicted waiting time is taken into consideration. In this case, it is possible to select a connection operation. For example, when the size of the voice data is large, if the first allowable time is increased, the time during which the voice interactive apparatus does not operate can be shortened even if the actual standby time exceeds the predicted standby time.

  In the voice interaction control device according to aspect 4 of the present invention, in any one of the aspects 1 to 3, the stage connection operation determining unit is configured to subtract the waiting time from the operation time among the plurality of operation candidates. 2 If the subtraction value is 0 or more and the motion candidate is less than a second allowable time indicating a time that is acceptable as the time from when the response can be output to when the execution of the connection operation is completed, The connection operation may be determined.

  According to the above configuration, since the operation time is longer than the standby time and the operation in which the difference between the standby time and the operation time is equal to or less than the second allowable time is determined as the bridging operation, the operation is performed after the generation of the response is completed. The time required for completing the joining operation can be minimized. Thereby, the time from the completion of the generation of the response to the execution of the response can be minimized.

  In the voice interaction control device according to aspect 5 of the present invention, in the above aspect 4, the second allowable time is at least one of the motion candidates or the time of the sound and the size of the sound data generated from the sound. It may be set according to one.

  Regarding the time at which the jointing operation is executed, the time that the user can accept is considered to be different for each operation. Therefore, according to the above configuration, the second allowable time is set for each motion candidate, so that the allowable time according to the motion can be set. For example, by shortening the second permissible time of an operation having a long operation time, the voice interactive apparatus immediately returns a response after a long-time connection operation. Thereby, it can prevent that a user feels stress in communication with a voice interactive apparatus.

  Further, when the time of the sound and the size of the sound data generated from the sound are large, the actual standby time is likely to be affected by the outside, so that the deviation from the predicted standby time is considered to be large. Therefore, according to the above configuration, since the second allowable time is set according to at least one of the time of the sound and the size of the sound data generated from the sound, the difference between the actual waiting time and the predicted waiting time is considered. In this case, it is possible to select a connection operation. For example, if the second allowable time is increased when the size of the voice data is large, even if the actual standby time exceeds the predicted standby time, the voice interactive device immediately responds after the generation of the response is completed. Can be returned.

  In the voice interaction control device according to aspect 6 of the present invention, in any one of the aspects 1 to 5, the standby time prediction unit uses at least one of the time of the sound and the size of the sound data generated from the sound. Thus, the waiting time may be predicted.

  If the voice time is long or the voice data size is large, it is considered that the time required for generating a response becomes long. Therefore, according to the above configuration, the standby time is predicted using at least one of the audio time and the audio data size. As a result, the standby time can be predicted with high accuracy.

  In the voice interaction control device according to aspect 7 of the present invention, in the aspect 6, the standby time prediction unit may further use the speech recognition result for the prediction of the standby time.

  According to the above configuration, since the standby time is predicted using the voice recognition result in addition to the voice time and the size of the voice data, the standby time can be predicted according to the contents of the voice. Precise prediction is possible. For example, if it is necessary to search information managed by an external server as a result of voice recognition, it is expected that it takes time to generate a response. In such a case, it is possible to further reduce the difference between the standby time and the time required for actual response generation by predicting the standby time longer.

  In the voice interaction control device according to aspect 8 of the present invention, in any one of the above aspects 1 to 7, the motion candidate is preliminarily set with a changeable range of the operation time together with the operation time. The bridging motion determination unit may select the motion candidate based on the motion time in which the motion time is changed within the changeable range.

  According to the above configuration, since the time from the start to the end of execution can be changed, it is possible to select a joint operation that cannot be selected when the operation time is fixed. Therefore, the variation of the joining operation can be increased.

  In the voice conversation control device according to aspect 9 of the present invention, in any of the above aspects 1 to 8, the connection motion determination unit may select a combination of two or more motion candidates from the plurality of motion candidates. Good.

  According to the above configuration, since two or more motion candidates are selected in combination, it is possible to execute one place connecting operation or to execute two or more place connecting operations during the standby time. Therefore, the variation of the joining operation can be increased.

  In the voice interaction control device according to aspect 10 of the present invention, in the above aspect 9, the field connection operation execution unit is selected by the field connection operation determination unit when a response to the sound can be output, and If there is the above-described joining operation that has not started execution, the execution of the joining operation may be canceled.

  According to the above configuration, when the response can be output, the execution of the connection operation that has not started execution is canceled, so the time from when the response can be output until the response is executed is minimized. Limit.

  A control method for a voice interaction control device according to an aspect 11 of the present invention is a control method for a voice interaction control device to be executed by a voice interaction device, wherein the voice interaction device obtains a predetermined sound after acquiring a voice uttered by a user. A standby time prediction step (S2) for predicting a standby time from the time point until the response to the voice can be output, the standby time predicted in the standby time prediction step, and the voice interactive device can be executed Based on the operation time required to execute each of a plurality of motion candidates indicating a correct motion, a joint motion determining step (S13, S15, S16) for selecting one or more of the plurality of motion candidates as a joint motion; A step of performing a jointing operation (S4) for causing the voice interaction apparatus to execute the jointing operation selected in the jointing operation determining step. According to this control method, the same function and effect as those of the spoken dialogue control apparatus according to aspect 1 are obtained.

  The voice interaction apparatus according to aspect 12 of the present invention may include the voice interaction control apparatus according to any one of aspects 1 to 10 described above. According to the above configuration, this voice interaction apparatus can improve the flexibility of communication with the user.

  The voice conversation control device according to each aspect of the present invention may be realized by a computer. In this case, the voice conversation control device is operated by causing the computer to operate as each unit (software element) included in the voice dialogue control device. The control program of the voice interaction control device that realizes the above in a computer and a computer-readable recording medium on which the control program is recorded 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.

  INDUSTRIAL APPLICABILITY The present invention can be used for a voice dialogue control device for controlling a voice dialogue device that responds to a user's utterance.

  1, 1a, 1b Control unit (voice dialogue control device) 10, 10a, 10b Voice dialogue device, 11, 11b Standby time prediction unit, 21, 21a, 21b Field connection operation determination unit, 22, 22a, 22b Field connection operation Execution unit, S2 standby time prediction step, S13, S15, S16 field connection operation determination step, S4 field connection operation execution step

Claims (6)

A standby time prediction unit that predicts a standby time from when a voice interaction device acquires a voice uttered by a user until a response to the voice can be output;
Based on the standby time predicted by the standby time prediction unit and the operation time required to execute each of the plurality of operation candidates indicating the operations that can be performed by the voice interactive device, one or more of the plurality of operation candidates is selected. A place-joining operation determining unit to select as a place-joining operation;
A field connection operation execution unit that causes the voice interaction device to execute the field connection operation selected by the field connection operation determination unit ;
The field transition operation determination unit is configured to perform the field transition operation after the second subtraction value obtained by subtracting the waiting time from the operation time is 0 or more and the response can be output among the plurality of motion candidates. execution of the second permissible time less is the operation candidate indicating a time acceptable as the time to complete the voice interaction control apparatus to said Rukoto determined as the field joint operation.   The field connection operation determination unit has a first subtraction value obtained by subtracting the operation time from the standby time among the plurality of operation candidates is 0 or more, and the response after the execution of the field connection operation is completed. 2. The motion candidate that is equal to or shorter than a first allowable time indicating a time that is allowable as a time during which the voice interactive device does not operate until the voice interactive device can be output is determined as the jointing operation. Voice dialogue control device. 3. The voice dialogue according to claim 1, wherein the waiting time prediction unit predicts the waiting time by using at least one of the time of the voice and the size of voice data generated from the voice. Control device. In the operation candidate, a changeable range of the operation time is set in advance together with the operation time,
The field joint operation determination unit, the operation time based on operating time was changed within the change range, according to any one of claims 1 to 3, characterized in that selecting the operation candidate Spoken dialogue control device. A method for controlling a voice dialogue control device to be executed by a voice dialogue device, comprising:
A standby time prediction step of predicting a standby time from when a voice interaction device acquires a voice uttered by a user until a response to the voice can be output;
Based on the standby time predicted in the standby time prediction step and the operation time required to execute each of the plurality of operation candidates indicating the operations that can be executed by the voice interactive device, one or more of the plurality of operation candidates is A step of determining a joining operation for selecting a plurality of joining operations as a joining operation;
And situ connecting operation execution step of executing the field connecting operation selected by the field joint operation determining step in the voice dialogue system, only including,
In the step of linking operation, the second operation of subtracting the waiting time from the operation time is 0 or more among the plurality of operation candidates, and the linking operation is performed after the response can be output. A control method for a spoken dialogue control apparatus, wherein the motion candidate that is equal to or shorter than a second permissible time indicating a time that is permissible as a time until the execution of the voice is completed is determined as the jointing motion . Voice dialogue system, characterized in that it comprises a voice conversation control apparatus according to any one of claims 1 to 4.

Images