JP2021081684A - Dialogue system, dialogue method and dialogue program - Google Patents

Abstract

To provide a dialogue system, a dialogue method, and a dialogue program capable of interacting with a user by a character having improved reality without making the user feel more annoyed.SOLUTION: In a dialogue system, a dialogue device 30 comprises: a background portion 34 with a background decoration; and a virtual image display device 40 that includes an image display portion 42 having a display surface 42a and an optical member 44 which is provided so as to be inclined by a predetermined angle with respect to the display surface 42a, and reflects light output from the display surface 42a and transmits light from the rear to the front as well, and that is provided in the front at a predetermined distance from the background portion 34, and displays a virtual image of a character with which a user U interacts at a predetermined position D in a rear portion 40a or between the rear portion 40a and the background portion 34.SELECTED DRAWING: Figure 4

Description

The present invention relates to dialogue systems, dialogue methods and dialogue programs.

Conventionally, there is an augmented reality technology in which a character is superimposed on a captured image in the real world by a portable information terminal or a head-mounted display to show the user an image as if the real world is virtually expanded.

Further, as another conventional example, there is a dialogue system in which a dialogue with a character can be enjoyed. For example, Japanese Patent Application Laid-Open No. 2012-210039 discloses a game system in which a character's dialogue is displayed on the screen and a dialogue is performed by selecting a player's dialogue to respond to the character's dialogue on the screen. To.

JP2012-210039A

However, when the conventional augmented reality technology is applied to the dialogue system, the trouble of holding the camera of the mobile information terminal over the subject and the wearing of the head-mounted display may make the user feel annoyed, and the character's dialogue The screen display and the selection of the response dialogue on the player's screen may make it difficult for the user to feel the reality of the character.

Therefore, an object of the present invention is to provide a dialogue system, a dialogue method, and a dialogue program capable of interacting with a user by a character having improved reality without making the user feel more annoyed.

The dialogue system of one aspect of the present invention is provided with a background portion with a background decoration, an image display unit having a display surface, and an image display unit having a display surface so as to be inclined by a predetermined angle, and is output from the display surface. It has an optical member that reflects the light from the front and transmits the light from the rear to the front, and is provided in the front at a predetermined distance from the background portion, and is provided at the rear or between the rear portion and the background portion. It has a virtual image display device that displays a virtual image of a character with which the user interacts at a position.

The dialogue method of one aspect of the present invention is provided with a background portion with a background decoration, an image display portion having a display surface, and an image display unit having a display surface so as to be inclined by a predetermined angle, and is output from the display surface. It has an optical member that reflects the light from the front and transmits the light from the rear to the front, and is provided in the front at a predetermined distance from the background portion, and is provided at the rear or between the rear portion and the background portion. A virtual image display device that displays a virtual image of the character with which the user interacts at a position, and a storage unit that stores model information of the character and a favorable impression are prepared, and the control unit responds to the progress of the dialogue. By outputting an image based on the model information to the display surface, the character displayed on the virtual image display device is operated, and the character dialogue is output from the speaker according to the progress of the dialogue, and a predetermined voice recognition process is performed. Acquires speech information from the user's speech, changes the favorability according to the speech information, outputs the first ending when the favorability is equal to or greater than the threshold value, and outputs the first ending when the favorability is less than the threshold value. At one point, the character outputs a second ending that performs an operation representing the favorability lower than that of the first ending.

The dialogue program according to one aspect of the present invention includes a code for operating a character displayed on a virtual image display device by outputting an image based on model information on a display surface according to the progress of the dialogue, and the above-mentioned dialogue program according to the progress of the dialogue. A code that outputs a character's dialogue from a speaker, a code that acquires utterance information from a user's utterance by a predetermined voice recognition process, a code that changes the liking according to the utterance information, and a code that changes the liking according to the utterance information. At one time, a code for outputting the first ending, and a code for outputting the second ending in which the character performs an operation representing the favorability lower than the first ending when the favorability is less than the threshold value. Let the computer execute.

According to the present invention, it is possible to provide a dialogue system, a dialogue method, and a dialogue program capable of interacting with a user by a character having improved reality without causing the user to feel more annoyed.

It is a block diagram which shows an example of the structure of the dialogue system which concerns on embodiment. It is a figure which shows an example of the structure of the user information stored in the server of the dialogue system which concerns on embodiment. It is a figure which shows an example of the structure of the phrase information stored in the server of the dialogue system which concerns on embodiment. It is a figure for demonstrating an example of the appearance structure of the dialogue apparatus of the dialogue system which concerns on embodiment. It is a block diagram which shows an example of the internal structure of the dialogue device of the dialogue system which concerns on embodiment. It is a flowchart which shows an example of the flow of the dialogue processing of the dialogue system which concerns on embodiment. It is a figure for demonstrating the state which displayed the virtual image of a character on the virtual image display device of the dialogue device of the dialogue system which concerns on embodiment. It is a flowchart which shows an example of the flow of order processing of the dialogue system which concerns on embodiment. It is a figure for demonstrating the state in which the standby virtual image is displayed on the virtual image display device of the dialogue device of the dialogue system which concerns on embodiment. It is a flowchart which shows an example of the flow of the 1st game processing of the dialogue system which concerns on embodiment. It is a flowchart which shows an example of the flow of the 2nd game processing of the dialogue system which concerns on embodiment. It is a figure for demonstrating the state which displayed the virtual image of a character in the 2nd game processing of the dialogue system which concerns on embodiment. It is a top view of the support stand of the dialogue system which concerns on the modification of embodiment.

Hereinafter, embodiments will be described with reference to the drawings.

(Structure of Embodiment)
FIG. 1 is a block diagram showing an example of the configuration of the dialogue system 1.

The dialogue system 1 includes a terminal device 10, a server 20, and one or more dialogue devices 30. Hereinafter, the dialogue device 30 refers to all or a part of one or a plurality of dialogue devices 30. The terminal device 10 and the dialogue device 30 are connected to the server 20 by wire or wirelessly via a network such as the Internet or LAN.

The terminal device 10 includes an input unit 11, a monitor 12, a control unit 13, and a storage unit 14. The terminal device 10 is operated by the operator of the dialogue system 1.

The input unit 11 has a keyboard, a mouse, and the like, and outputs an instruction input of the operator to the control unit 13.

The monitor 12 displays various information output from the control unit 13.

The control unit 13 is connected to the server 20. The control unit 13 has a CPU and can execute various processes. The function of the control unit 13 is realized by the CPU reading and executing various programs stored in the storage unit 14. The control unit 13 outputs the information input from the server 20 to the monitor 12, and outputs the information input from the input unit 11 to the server 20.

The storage unit 14 has storage elements such as RAM, ROM, HDD, and SSD, and stores various information and various programs. The storage unit 14 is read and written by the control unit 13.

The server 20 has a main server 21 and a voice recognition server 22.

The main server 21 has a control unit 21a and a storage unit 21b.

The control unit 21a is connected to the control unit 13 and the voice recognition server 22. The control unit 21a has a CPU and can execute various processes. The function of the control unit 21a is realized by the CPU reading and executing various programs stored in the storage unit 21b. The control unit 21a can output various instructions to the dialogue device 30 via the voice recognition server 22.

The storage unit 21b has storage elements such as RAM, ROM, HDD, and SSD. The storage unit 21b is read and written by the control unit 21a. In the storage unit 21b, in addition to the correspondence information between the dialogue device 30 and the user ID of the user U (FIG. 4) and the order contents of the user U, the user information Tu, the phrase information Td, and the program of the dialogue processing unit Pd are also stored. Be remembered.

FIG. 2 is a diagram showing an example of the configuration of the user information Tu.

As shown in FIG. 2, the user information Tu stores the user ID, name, number of visits, and favorability.

FIG. 3 is a diagram showing an example of the configuration of the phrase information Td.

As shown in FIG. 3, the phrase information Td stores the phrase associated with the user ID. The phrase is not particularly limited, but relates to, for example, the hobbies and tastes of the user U.

The dialogue processing unit Pd performs dialogue processing based on a predetermined scenario. In the dialogue processing, the scenario is advanced according to the utterance information acquired from the utterance of the user U, the operation instruction including the operation ID and the dialogue is output according to the progress of the scenario, and the character C (FIGS. 7 and 12) is output. Make it work. The dialogue process also includes an order process for causing the user U to order a product such as food and drink, and a game process for causing the user U to play a game.

The dialogue process also includes a chat process in which the character C and the user U are chatted while the scenario is in progress. The chat process may be provided before and after the order process or the game process. In the chat process, the character C throws a topic, a question, or the like to the user U according to a predetermined operation instruction, acquires a phrase from the response of the user U, and stores the phrase in the phrase information Td.

For example, when the character C asks "what is your favorite drink?" And the user U answers "orange juice", the control unit 21a associates the user ID with the phrase "orange juice" and stores it in the phrase information Td. Let me. The control unit 21a can output an operation instruction for recommending the favorite beverage of the user U based on the phrase information Td.

The voice recognition server 22 is connected to the dialogue device 30. The voice recognition server 22 converts the utterance of the user U input from the dialogue device 30 by a predetermined voice recognition process into utterance information composed of a character string, and outputs the utterance to the main server 21.

FIG. 4 is a diagram for explaining an example of the appearance configuration of the dialogue device 30. FIG. 5 is a block diagram showing an example of the internal configuration of the dialogue system 1.

As shown in FIG. 4, the dialogue device 30 includes a support base 31, a table 32, a chair 33, a background portion 34, a microphone 35, a speaker 36, a virtual image display device 40, and a device main body 50.

The support base 31 is made of, for example, wood or the like. The support base 31 has a top plate 31a, legs 31b that support the top plate 31a, and a curtain plate 31c that is detachably provided below the top plate 31a. The curtain plate 31c is removed by an operator so that it can enter behind the virtual image display device 40 when performing maintenance on the dialogue device 30.

The table 32 is made of, for example, wood or the like. The table 32 is provided adjacent to the front of the support base 31. The table 32 has a top plate 32a whose upper surfaces are flush with each other, and legs 32b that support the top plate 32a.

The support base 31 and the table 32 are not particularly limited, but may be decorated to imitate a bar counter, for example.

The chair 33 is made of, for example, resin or metal. The chair 33 is provided with a seating portion 33a on which the user U is seated, a support leg 33b for supporting the seating portion 33a, and a display surface 42a provided on the support leg 33b so as to be hidden behind the blind 43 so as not to be seen. The height adjusting mechanism 33c for adjusting the height of the seating portion 33a is provided. The height adjusting mechanism 33c is not limited to a specific mechanism as long as it is fixed in a state adjusted to a desired height. For example, the height adjusting mechanism 33c may be one in which the user U rotates the seating portion 33a screwed into the spiral portion provided on the support leg 33b to adjust the height.

The background portion 34 is composed of, for example, a wall, a board, a sheet, or the like. The background portion 34 is not particularly limited, but is provided with, for example, a background decoration that imitates the structure of a bar. The background decoration may be applied flatly or may be provided three-dimensionally with irregularities.

The microphone 35 is provided at a portion suitable for collecting the sound of the user U's utterance, such as the front upper part of the virtual image display device 40. The microphone 35 inputs the utterance of the user U to the device main body 50 (FIG. 5). The microphone 35 may have directivity so that ambient noise can be suppressed and the user U's voice can be effectively picked up.

The speaker 36 is provided in a portion where the user U can easily hear the sound, such as both front side portions of the virtual image display device 40. The speaker 36 converts the voice information input from the device main body 50 into voice and outputs it to the outside (FIG. 5).

The virtual image display device 40 is provided on the support base 31. The virtual image display device 40 displays a virtual image as if the character C is standing behind the bar counter. More specifically, the virtual image display device 40 is provided in front of the background portion 34 at a predetermined distance, and the user U interacts with the rear portion 40a or the predetermined position D between the rear portion 40a and the background portion 34. Display a virtual image. More preferably, the predetermined position D is between the rear portion 40a and the background portion 34. The virtual image display device 40 includes a frame body 41, an image display unit 42, a blind 43, an optical member 44, a glass 45, a hanging pot 46, and an illumination unit 47.

The frame 41 is made of, for example, metal or the like. The frame body 41 has a support column 41a erected at the four corners of the top plate 31a, and an upper frame 41b supported by the support column 41a. The frame 41 may be hidden from the user U by a decorative board or the like so that the appearance can be improved.

The image display unit 42 is composed of, for example, a display. The image display unit 42 has a display surface 42a for displaying an image, and is held above the frame 41 so that the display surface 42a faces the optical member 44. The image display unit 42 is connected to the device main body 50, which will be described later (FIG. 5), and displays an image input from the device main body 50 on the display surface 42a.

The blind 43 is made of, for example, Hymilon, cloth, resin, or the like. The blind 43 is provided on the front upper part of the virtual image display device 40 so that the display surface 42a can be hidden from the user U's field of view.

The optical member 44 is held by the frame body 41. The optical member has, for example, deflecting glass, but may also have a half mirror. The optical member 44 is provided so as to be inclined at a predetermined angle with respect to the display surface 42a, reflects the light output from the display surface 42a forward, and transmits the light from the rear to the front. The predetermined angle is not particularly limited, but is, for example, 45 °.

The glass 45 is made of a transparent member such as glass or resin. The glass 45 is a decorative tool placed on the support base 31.

The hanging pot 46 is made of, for example, metal or resin. The hanging pot 46 is a decorative tool that is hung from the upper frame 41b behind the optical member 44.

The lighting unit 47 is composed of, for example, a lighting device such as an LED. The illumination unit 47 is provided behind the virtual image display device 40, and is arranged so as to irradiate the ornament with illumination light. Based on the instruction input from the device main body 50, the lighting unit 47 outputs the illumination light so that the user U can easily see it, and illuminates the ornament.

As shown in FIG. 5, the device main body 50 has a control unit 51 and a storage unit 52.

The control unit 51 has a CPU and can execute various processes. The function of the control unit 51 is realized by the CPU executing various programs stored in the storage unit 52. The control unit 51 outputs the utterance of the user U input from the microphone 35 to the voice recognition server 22.

The storage unit 52 has storage elements such as RAM, ROM, HDD, and SSD. The storage unit 52 can be read and written by the control unit 51. In addition to various information, the storage unit 52 also stores programs of model information Ci, image generation unit Pi, and voice conversion unit Ps.

The model information Ci is information for generating a three-dimensional image of the character C associated with the operation ID.

The image generation unit Pi reads the model information Ci according to the operation ID input from the server 20 by the image generation process, generates an image of the character C, and outputs the image to the image display unit 42.

The voice conversion unit Ps synthesizes voice information based on the dialogue input from the server 20 by the voice synthesis process, and outputs the voice information to the speaker 36.

(motion)
Subsequently, the operation of the dialogue processing unit Pd will be described.

FIG. 6 is a flowchart showing an example of the flow of dialogue processing. FIG. 7 is a diagram for explaining a state in which a virtual image of the character C is displayed.

The user U conveys information for identifying the user U, such as a name, to the operator. The operator determines the dialogue device 30 to be used by the user U from the availability and the like, and inputs the user ID of the user U and the correspondence instruction of the dialogue device 30 by the input unit 11. The control unit 13 outputs the association instruction input from the input unit 11 to the control unit 21a. The control unit 21a associates the user ID with the dialogue device 30 in response to the association instruction. The control unit 21a reads the number of plays according to the user ID from the user information Tu, determines the scenario according to the number of plays, and starts the processing of the dialogue processing unit Pd. The following dialogue processing is based on an example of a scenario according to the number of plays, and the scenario is not limited to this.

The operator hands the user U an envelope with a problem for use in the first game.

The user U enters the private room provided with the dialogue device 30, adjusts the height of the seating portion 33a by the height adjusting mechanism 33c so that the line of sight is located at a predetermined height, and sits on the chair 33.

Character C is selected (S1 in FIG. 6). The control unit 21a outputs an operation instruction for causing the user U to select one of the plurality of characters C.

More specifically, the control unit 21a outputs an operation ID and dialogue for selecting the character C to the control unit 51 via the voice recognition server 22. The control unit 51 performs image generation processing based on the operation ID input from the control unit 21a and the model information Ci read from the storage unit 52, and outputs an image to the image display unit 42. When the image display unit 42 outputs an image from the display surface 42a, the optical member 44 reflects the image forward so that the user U can visually recognize the virtual images of the plurality of characters C. The control unit 51 synthesizes voice information by the dialogue input from the main server 21, causes the speaker 36 to introduce the character C by voice, outputs the name, and the like, and prompts the user U to select the character C.

When the user U speaks the name of the desired character C, the control unit 51 outputs the utterance picked up by the microphone 35 to the voice recognition server 22. The voice recognition server 22 performs a predetermined voice recognition process, acquires utterance information from the utterance, and outputs the utterance information to the control unit 21a. The control unit 21a stores the selected character C in the storage unit 21b.

FIG. 7 is an example in which the character C is displayed on the virtual image display device 40. As shown in FIG. 7, the virtual image display device 40 displays virtual images of the character C and the candle stand Cs at a predetermined position D. The control unit 51 outputs a light-off instruction to turn off the lighting unit 47, making the glass 45 difficult to see from the user U (broken line in FIG. 7).

When the name of the user U is not stored in the user information Tu, the control unit 21a may output an operation instruction asking the character C for the name of the user U. When the user U utters his / her own name according to the operation and dialogue of the character C, the control unit 21a acquires the name of the user U and informs the user information Tu via the microphone 35, the control unit 51, and the voice recognition server 22. Remember. The name of the user U is read from the user information Tu by the control unit 21a so that the character C can output voice when talking to the user U.

Process the order (S2). FIG. 8 shows an example of the flow of order processing of the dialogue system 1. The control unit 21a performs order processing according to the flowchart shown in FIG.

Accepts an order (S21 in FIG. 8). The control unit 21a outputs an operation instruction for asking the user U about the order of the beverage. When the user U orders a beverage by utterance according to the operation and dialogue of the character C, the control unit 21a acquires the utterance information indicating the order contents via the microphone 35, the control unit 51, and the voice recognition server 22, and stores the storage unit. The order details are stored in 21b, and the order details are output to the control unit 13. The control unit 13 causes the monitor 12 to display the order details.

Character C is sent off (S22). When the control unit 21a outputs an operation instruction, the character C leaves the virtual image display device 40 together with a voice output of a line such as "get a drink".

It is determined whether or not there is a provision completion input from the terminal device 10 (S23). The operator carries the beverage according to the order contents displayed on the monitor 12 and provides the beverage to the user U. When the provision is completed, the operator inputs the provision completion to the input unit 11. The provision completion input is output to the control unit 21a via the control unit 13. When the control unit 21a determines that the provision completion input has been received (S23: YES), the process proceeds to S25. On the other hand, when there is no provision completion input (S23: NO), the process proceeds to S24.

A standby virtual image is displayed (S24). When the control unit 21a outputs a display instruction, the control unit 51 causes the virtual image display device 40 to display, for example, the standby virtual image shown in FIG. In FIG. 9, the control unit 21a acquires utterance information according to the utterance of the user U via the microphone 35, the control unit 51, and the voice recognition server 22, and stands up from the candle stand Cs to draw characters of the utterance information. The virtual image of the drifting smoke Sm is displayed on the virtual image display device 40. By repeating S23 and S24, the standby imaginary image is displayed until the terminal device 10 receives the provision completion input.

In S25, when the control unit 21a outputs an operation instruction, the character C appears in the virtual image display device 40. When the control unit 21a outputs an effect instruction, the control unit 51 causes the lighting unit 47 to illuminate the glass 45 and displays a virtual image of the liquid in the glass 45 so as to overlap with the glass 45 in the line-of-sight direction of the user U, as if it were. Character C also produces a production that looks as if he has fetched a drink. After the execution of S25, the order processing ends.

Subsequently, the first game process is performed (S3 in FIG. 6). FIG. 10 shows the flow of the first game processing of the dialogue system 1. The control unit 21a performs the first game processing according to the flowchart shown in FIG.

Ask questions and encourage answers (S31 in FIG. 10). When the control unit 21a outputs an operation instruction, the character C causes the user U to open the envelope handed to the operator, asks the question described on the sheet in the envelope, and prompts the answer.

It is determined whether or not it is within the time limit (S32). If the control unit 21a determines that the time limit is within the time limit, the process proceeds to S33 (S32: YES). On the other hand, when the time limit is exceeded (S32: NO), the process proceeds to S37.

It is determined whether or not the answer is correct (S33). When the control unit 21a determines that the utterance information acquired by the predetermined voice recognition process indicates a correct answer (S33: YES), the process proceeds to S37. On the other hand, when the answer is not correct (S33: NO), the process proceeds to S34.

It is determined whether or not the person has surrendered (S34). When the control unit 21a determines that the utterance information in S33 indicates surrender (S34: YES), the process proceeds to S37. On the other hand, when it is not a surrender (S34: NO), the process proceeds to S35.

It is determined whether or not there is a request for a hint (S35). When the control unit 21a determines that the utterance information in S33 indicates a hint request (S35: YES), the process proceeds to S36. On the other hand, when the request for a hint is not made (S35: NO), the process returns to S32.

The hint is output by voice (S36). The control unit 21a counts the number of times the hint is output. When the control unit 21a outputs an operation instruction, the character C outputs a hint by voice. The process returns to S32.

In S37, the favorable impression is memorized. The control unit 21a determines the favorability according to the presence / absence of time out, the presence / absence of surrender, and the number of times the hint is output, and adds the favorability of the user information Tu. Further, when the user U does not answer correctly, the control unit 21a causes the character C to output the correct answer by voice. After the execution of S37, the first game process ends.

Subsequently, the control unit 21a performs the second game processing.

FIG. 11 shows the flow of the second game processing of the dialogue system 1. FIG. 12 is a diagram for explaining a state in which a virtual image of the character C is displayed on the virtual image display device 40.

Shuffle (S41 in FIG. 11). As shown in FIG. 12, one correct object Jc is hidden in the three objects J. When the control unit 21a outputs an operation instruction, the three objects J switch their positions by shuffling, and the character C asks the user U about the position of the correct object Jc.

It is determined whether or not it is within the time limit (S42). If the control unit 21a determines that the time limit is within the time limit, the process proceeds to S43 (S42: YES). On the other hand, when the time limit is exceeded (S42: NO), the process proceeds to S44.

It is determined whether or not the answer is either correct or incorrect (S43). When the control unit 21a determines that the utterance of the user U answers either a correct answer or an incorrect answer (S43: YES), the process proceeds to S44. On the other hand, when it is neither a correct answer nor an incorrect answer (S43: NO), the process returns to S42.

In S44, the favorable impression is memorized. The control unit 21a determines the favorability according to any of the correct answer, the incorrect answer, and the time out, and adds the favorability of the user information Tu. The control unit 21a outputs an operation instruction to operate the character C according to any of the correct answer, the incorrect answer, and the time out. After the execution of S44, the second game process ends.

Returning to FIG. 6, in S4, it is determined whether or not the favorability stored in the user information Tu is equal to or greater than the threshold value. When the control unit 21a determines that the favorability is equal to or higher than the threshold value, the process proceeds to S5. When the favorability is less than the threshold, the process proceeds to S6.

In S5, the control unit 21a outputs an operation instruction for displaying the first ending. After S5, the process proceeds to S7.

In S6, the control unit 21a outputs an operation instruction for displaying the second ending. The second ending is predetermined so that the character C performs an operation showing a lower favorability than the first ending.

It is determined whether or not to output the additional ending (S7). When the control unit 21a determines that the favorability stored in the user information Tu is equal to or higher than a predetermined value, the process proceeds to S8. Further, when the favorability is less than a predetermined value, the control unit 21a prompts the user U to charge. When there is a charge, the process proceeds to S8. On the other hand, when the favorability is less than the predetermined value and there is no charge, the process ends.

In S8, an additional ending is output. The control unit 21a outputs an operation instruction for the character C to sing a song and dance. After S8, the process ends.

As a result, the dialogue system 1 expands the real world without using the camera or head-mounted display of the mobile information terminal, and displays a virtual image of the upper body of character C as if standing behind a bar counter. , Can interact with the user U by voice.

In addition, the dialogue system 1 performs an effect in which the ordering and provision of products in the real world and the exit and appearance of the character C are linked to further improve the reality of the character C.

According to the embodiment, the dialogue system 1 can interact with the user U by the character C with improved reality without making the user U feel more annoyed.

(Modified example of the embodiment)
In the embodiment, the rear end of the top plate 31a of the support base 31 has a linear shape, but it may have a concave shape.

FIG. 13 is a top view of the support base 131 of the dialogue system 1 according to the modified example.

The rear end of the top plate 131a of the support base 131 has a concave portion 131b having a concave shape toward the front.

As a result, the dialogue system 1 more reliably displays the character C behind the support base 131, and improves the reality of the character C by producing an effect as if standing behind the bar counter.

In the embodiment and the modified example, the example in which the dialogue device 30, the server 20, and the terminal device 10 are separate bodies has been described, but all or a part of them may be integrated. For example, the control unit 51, the control unit 21a, the control unit 13, the storage unit 52, and the storage unit 21b may be provided in the dialogue device 30.

In the embodiment and the modified example, the model information Ci, the image generation unit Pi, and the voice conversion unit Ps are stored in the storage unit 52, and the user information Tu, the phrase information Td, the scenario, and the dialogue processing unit Pd are stored in the storage unit 21b. However, all or part of these may be stored in any of the storage units 14, 21b, 52, or may be stored in all of them.

That is, the dialogue system 1 has storage units 14, 21b, 52 and control units 13, 21a, 51. The storage units 14, 21b, and 52 store the model information Ci of the character C and the favorability. The control units 13, 21a, and 51 operate the character C displayed on the imaginary image display device 40 by outputting an image based on the model information Ci to the display surface 42a according to the progress of the dialogue, and the characters C are operated according to the progress of the dialogue. The dialogue of C is output from the speaker 36, the utterance information is acquired from the utterance of the user U by a predetermined voice recognition process, the liking is changed according to the utterance information, and when the liking is equal to or higher than the threshold value, the first ending Is output, and when the favorability is less than the threshold value, the second ending in which the character C performs an operation indicating a favorability lower than that of the first ending is output. Further, the control units 13, 21a, and 51 cause the character C to leave the virtual image display device 40 in response to the utterance of the user U, and cause the character C to appear in the virtual image display device 40 in response to an instruction input from the operator. The lighting unit 47 is provided so that the decorative tool can be illuminated. The control units 13, 21a, and 51 output a lighting instruction for illuminating the decorative tool, and cause the virtual image display device 40 to display a virtual image so as to overlap the decorative tool in the line-of-sight direction of the user U.

Further, the dialogue method is provided so as to incline a predetermined angle with respect to the background portion 34 with the background decoration, the image display portion 42 having the display surface 42a, and the display surface 42a, and the dialogue method is output from the display surface 42a. It has an optical member 44 that reflects light forward and transmits light from the rear to the front, and is provided in the front at a predetermined distance from the background portion 34, and is provided between the rear portion 40a or the rear portion 40a and the background portion 34. A virtual image display device 40 that displays a virtual image of the character C with which the user U interacts at a predetermined position D, and storage units 14, 21b, and 52 that store the model information Ci of the character C and the favorable impression are prepared. , Control units 13, 21a, 51 operate the character C displayed on the virtual image display device 40 by outputting an image based on the model information Ci to the display surface 42a according to the progress of the dialogue, and respond to the progress of the dialogue. The dialogue of the character C is output from the speaker 36, the speech information is acquired from the speech of the user U by a predetermined voice recognition process, the favorability is changed according to the speech information, and when the favorability is equal to or higher than the threshold value, the first The ending is output, and when the favorability is less than the threshold value, the character C outputs the second ending that performs an operation showing a favorability lower than that of the first ending.

Further, the dialogue program includes a code for operating the character C displayed on the virtual image display device 40 by outputting an image based on the model information Ci to the display surface 42a according to the progress of the dialogue, and the character C according to the progress of the dialogue. The code for outputting the dialogue from the speaker 36, the code for acquiring the utterance information from the utterance of the user U by a predetermined voice recognition process, the code for changing the liking according to the utterance information, and the liking being equal to or higher than the threshold value. When, the code that outputs the first ending and the code that outputs the second ending in which the character C performs an operation indicating a lower favorability than the first ending when the favorability is less than the threshold are executed in the computer. Let me.

In the embodiment, the table 32 and the support base 31 are configured separately, but may be configured integrally.

In the embodiments and modifications, the glass 45 and the hanging pot 46, which are ornaments, are provided, but the ornaments are not limited thereto. Anything may be used as long as it decorates the virtual image display device 40.

In the embodiment and the modified example, the lighting unit 47 is arranged so as to illuminate the glass 45, but the present invention is not limited to this. For example, the lighting unit 47 may be arranged to illuminate the hanging pot 46 or the background unit 34, or may be arranged to illuminate other ornaments.

In the embodiment and the modified example, a virtual image representing a beverage is superimposed on the glass 45, but the glass 45 is not limited to this. For example, a virtual image representing the rising flame F may be superimposed on the glass 45 (broken line in FIG. 12).

In the embodiment and the modified example, the game processing is composed of the first game processing and the second game processing, but the present invention is not limited thereto. The game processing may be either one of the first game processing or the second game processing, there may be three or more game processing, the execution order of each of the game processing may be different, and the first game processing may be different. The game process and / or the second game process may be repeated a plurality of times.

In the first game process and the modified example, the question is given by having the user U open the envelope given in advance by the operator, but the question is not limited to this, and the question may be given by the character C by voice output. Good.

In the embodiment and the modified example, the three objects J in the second game processing include one correct answer object Jc, but this correct answer object Jc is composed of a mascot character that is hidden until the correct answer is given. It may be configured to say a line such as "turning eyes".

In the embodiment and the modified example, a dimming device may be provided in a private room provided with the dialogue device 30 so that the user U can adjust the room to a desired brightness by the dimming device.

In the embodiment and the modified example, the image display unit 42 is held above the frame body 41, but the height is between the image display unit 42 and the frame body 41 so that the predetermined position D can be adjusted in the front-rear direction. Adjusters may be provided.

Each step of each procedure in the present embodiment may be executed at the same time by changing the execution order, or may be executed in a different order for each execution, as long as it does not violate the nature of the steps. Further, all or a part of each step of each procedure in the present embodiment may be realized by hardware.

The present invention is not limited to the above-described embodiment, and various modifications, modifications, and the like can be made without changing the gist of the present invention.

1 Dialogue system 10 Terminal device 11 Input unit 12 Monitor 13 Control unit 14 Storage unit 20 Server 21 Main server 21a Control unit 21b Storage unit 22 Voice recognition server 30 Dialogue device 31 Support base 31a Top plate 31b Leg 31c Curtain plate 32 Table 32a Top plate 32b Leg 33 Chair 33a Seating 33b Support leg 33c Height adjustment mechanism 34 Background 35 Microphone 36 Speaker 40 Virtual image display device 40a Rear 41 Frame 41a Strut 41b Upper frame 42 Image display 42a Display surface 43 Blind 44 Optics Member 45 Glass 46 Hanging pot 47 Lighting unit 50 Device body 51 Control unit 52 Storage unit 131 Support base 131a Top plate 131b Concave part C Character Ci Model information Cs Candle stand D Predetermined position F Flame J Object Jc Correct object Pd Dialogue processing unit Pi Image generation unit Ps Speech conversion unit Td Word information Tu User information Sm Smoke U User

The dialogue system of one aspect of the present invention is provided with a background portion with a background decoration, an image display portion having a display surface, and an image display unit having a display surface so as to be inclined by a predetermined angle, and is output from the display surface. It has an optical member that reflects the light from the front and transmits the light from the rear to the front, and is provided in the front at a predetermined distance from the background portion, and is provided at the rear or between the rear portion and the background portion. The control unit includes a virtual image display device that displays a virtual image of a character with which the user interacts at a position, a storage unit that stores model information of the character and a favorable impression, and a control unit. The character displayed on the virtual image display device is operated by outputting an image based on the model information to the display surface according to the progress of the dialogue, and the dialogue of the character is output from the speaker according to the progress of the dialogue. , The utterance information is acquired from the utterance of the user by a predetermined voice recognition process, the character is removed from the virtual image display device according to the utterance information, and the character is displayed on the virtual image display device according to an instruction input by the operator. Is made to appear, the favorability is changed according to the speech information, the first ending is output when the favorability is equal to or more than the threshold value, and when the favorability is less than the threshold value, the character is said to be the first. The second ending that performs the operation expressing the favorable sensitivity lower than the one ending is output .

The dialogue method of one aspect of the present invention is provided with a background portion with a background decoration, an image display portion having a display surface, and an image display unit having a display surface so as to be inclined by a predetermined angle, and is output from the display surface. It has an optical member that reflects the light from the front and transmits the light from the rear to the front, and is provided in the front at a predetermined distance from the background portion, and is provided at the rear or between the rear portion and the background portion. A virtual image display device that displays a virtual image of the character with which the user interacts at a position, and a storage unit that stores model information of the character and a favorable impression are prepared, and the control unit responds to the progress of the dialogue. By outputting an image based on the model information to the display surface, the character displayed on the virtual image display device is operated, and the character dialogue is output from the speaker according to the progress of the dialogue, and a predetermined voice recognition process is performed. Acquires utterance information from the utterance of the user, causes the character to leave the virtual image display device in response to the utterance information, causes the character to appear in the virtual image display device in response to an instruction input by the operator, and causes the utterance. The favorability is changed according to the information, and when the favorability is equal to or more than the threshold value, the first ending is output, and when the favorability is less than the threshold value, the character is lower than the first ending. Outputs the second ending that performs the operation that expresses the favorable impression.

The dialogue program according to one aspect of the present invention includes a code for operating a character displayed on a virtual image display device by outputting an image based on model information on a display surface according to the progress of the dialogue, and the dialogue program according to the progress of the dialogue. A code for outputting a character's dialogue from a speaker, a code for acquiring speech information from a user's speech by a predetermined voice recognition process, a code for leaving the character from the virtual image display device according to the speech information, and an operator. A code that causes the character to appear on the virtual image display device in response to the instruction input, a code that changes the favorability according to the speech information, and a code that outputs the first ending when the favorability is equal to or greater than a threshold value. And, when the favorability is less than the threshold value, the computer is made to execute a code for outputting a second ending in which the character performs an operation representing the favorability lower than the first ending.

Claims (8)

The background part with background decoration and
An image display unit having a display surface, and an optical member provided so as to be inclined at a predetermined angle with respect to the display surface to reflect the light output from the display surface forward and transmit the light from the rear to the front. A virtual image display device, which is provided in front of the background portion at a predetermined distance and displays a virtual image of a character with which the user interacts at a rear portion or a predetermined position between the rear portion and the background portion.
Has a dialogue system. It has a storage unit and a control unit.
The storage unit stores the model information of the character and the favorable impression.
The control unit
In response to the progress of the dialogue, the character displayed on the virtual image display device is operated by outputting an image based on the model information to the display surface.
As the dialogue progresses, the dialogue of the character is output from the speaker.
The utterance information is acquired from the utterance of the user by a predetermined voice recognition process, and the utterance information is acquired.
The favorability is changed according to the utterance information.
When the favorability is equal to or higher than the threshold value, the first ending is output.
When the favorability is less than the threshold value, the character outputs a second ending that performs an operation representing the favorability lower than the first ending.
The dialogue system according to claim 1. The control unit
The character is removed from the virtual image display device in response to the user's utterance.
The character appears on the virtual image display device in response to an instruction input from the operator.
The dialogue system according to claim 2. It has decorations and lighting,
The lighting unit is provided so that the decorative tool can be illuminated.
The control unit outputs a lighting instruction for illuminating the ornament, and causes the virtual image display device to display a virtual image so as to overlap with the ornament in the line-of-sight direction of the user.
The dialogue system according to claim 2. Has chairs and blinds,
The blind is provided in the upper front part of the virtual image display device.
The chair is provided in front of the virtual image display device, and has a height adjusting mechanism for adjusting the height of the seated portion so that the display surface is hidden behind the blind and cannot be seen by the seated user. ,
The dialogue system according to claim 1. Has a support
The virtual image display device is provided on the support base and is provided on the support base.
The rear end of the top plate of the support base has a concave portion having a concave shape toward the front.
The dialogue system according to claim 1. The background part with background decoration and
An image display unit having a display surface, and an optical member provided so as to be inclined at a predetermined angle with respect to the display surface to reflect the light output from the display surface forward and transmit the light from the rear to the front. A virtual image display device, which is provided in front of the background portion at a predetermined distance and displays a virtual image of a character with which the user interacts at a rear portion or a predetermined position between the rear portion and the background portion.
A storage unit that stores the model information of the character and the favorable impression,
Prepare,
By the control unit
In response to the progress of the dialogue, the character displayed on the virtual image display device is operated by outputting an image based on the model information to the display surface.
As the dialogue progresses, the dialogue of the character is output from the speaker.
The utterance information is acquired from the utterance of the user by a predetermined voice recognition process, and the utterance information is acquired.
The favorability is changed according to the utterance information.
When the favorability is equal to or higher than the threshold value, the first ending is output.
When the favorability is less than the threshold value, the character outputs a second ending that performs an operation representing the favorability lower than the first ending.
Dialogue method. A code that operates the character displayed on the virtual image display device by outputting an image based on model information to the display surface according to the progress of the dialogue.
A code that outputs the dialogue of the character from the speaker according to the progress of the dialogue, and
A code that acquires utterance information from the user's utterance by a predetermined voice recognition process,
A code that changes the favorability according to the utterance information,
When the favorability is equal to or higher than the threshold value, the code for outputting the first ending and
A code that outputs a second ending in which the character performs an operation representing the favorability lower than the first ending when the favorability is less than the threshold value.
A dialogue program that causes a computer to execute.

Images