Virtual assistant device, virtual assistant system, and program for virtual assistant device

Abstract

To enhance feeling of satisfaction through conversation of a user who uses a virtual assistant device, while reducing a required data amount.SOLUTION: A virtual assistant device 10 comprises a control unit 11. The control unit 11 performs first question control which causes a voice output unit 16 to output therefrom a first question in a manner that makes a character 70 look as if talking, and causes a display unit 15 to display thereon options associated with the first question. After one of the options is inputted to a voice input unit 18, the control unit 11 performs second question control which causes the voice output unit 16 to output therefrom a second question corresponding to the options, in the manner that makes the character 70 look as if talking. After performing the second question control, the control unit 11 performs reply control which causes the voice output unit 16 to output therefrom in the manner that makes the character 70 look as if talking, a reply associated with the second answer inputted to the voice input unit 18.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a virtual assistant device, a virtual assistant system, and a program for a virtual assistant device. [Background technology]

[0002] Patent Document 1 discloses an audio output system. The audio output system of Patent Document 1 includes an audio information acquisition means, an output control means, and a conversation information acquisition means. The audio information acquisition means acquires audio information related to the voice uttered by a speaker. The output control means causes a sentence corresponding to the display content displayed on the display medium to be output to an audio output device used by a user of the display medium in a voice that imitates the manner of the speaker's voice based on the audio information. The conversation information acquisition means acquires conversation information related to a conversation between the user and the speaker. When the speaker utters a sentence by voice, an image imitating the manner of the speaker is displayed on the display medium. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-76885 A Summary of the Invention [Problem to be solved by the invention]

[0004] In a device that displays a character on a display unit and that has a conversation with a user, it is conceivable to carry out a continuous conversation by repeatedly asking the user questions and replying to the user's answers. As a replying method, it is conceivable to prepare answers corresponding to anticipated answers in advance, and if a reply corresponding to an answer from the user is stored, to reply to that answer. In such a configuration, by presenting answer options to the user when asking a question, it is possible to narrow down the user's answers, making it easy to prepare a reply. However, merely repeating answers by selection is not sufficient to increase the user's satisfaction.

[0005] The present disclosure aims to provide a technology that can easily increase satisfaction from conversations between users of virtual assistant devices while reducing the amount of data required. [Means for solving the problem]

[0006] The virtual assistant device of the present disclosure is A virtual assistant device comprising a display unit that displays an image of a character, a voice output unit that utters words, a control unit that controls the display unit and the voice output unit, and a voice input unit to which voice is input, Using a registration unit provided inside or outside the virtual assistant device, the registration unit registers a first question associated with a plurality of options corresponding to a first answer, a second question associated with a plurality of second answers that are questions corresponding to the options and are expected to be answered, and a reply associated with the second answer; The control unit is performing a first question control to output the first question from the voice output unit as if the character were speaking the first question, and to display the options associated with the first question on the display unit; performing second question control to output the second question corresponding to the option from the voice output unit in a manner that the character speaks the second question after any of the options is input to the voice input unit; After performing the second question control, a response control is performed to output the reply associated with the second answer input to the voice input unit from the voice output unit as if the character were speaking.

[0007] The program for the virtual assistant device of the present disclosure is A program used in a virtual assistant device having a display unit that displays an image of a character, a voice output unit that utters words, a control unit that controls the display unit and the voice output unit, and a voice input unit to which voice is input, Using a registration unit provided inside or outside the virtual assistant device, the registration unit registers a first question associated with a plurality of options corresponding to a first answer, a second question associated with a plurality of second answers that are questions corresponding to the options and are expected to be answered, and a reply associated with the second answer; causing the control unit to perform a first question control in which the first question is output from the voice output unit as if spoken by the character, and the option corresponding to the first question is displayed on the display unit; causing the control unit to perform a second question control in which, after any one of the options is input to the voice input unit, the control unit outputs the second question corresponding to the option from the voice output unit in a manner such that the character speaks the second question; After the second question control is performed, the control unit performs response control to output the response corresponding to the second answer input to the voice input unit from the voice output unit as if the character were speaking. Effect of the Invention

[0008] According to the present disclosure, it is easy to increase the satisfaction of users of virtual assistant devices through conversations while reducing the amount of data required. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram showing a simplified electrical configuration of a virtual assistant system including a virtual assistant device of the first embodiment. [Diagram 2] FIG. 2 is an explanatory diagram showing an example of a normal display in the virtual assistant device of the first embodiment. [Diagram 3] FIG. 3 is the first half of a flowchart illustrating the control flow in the virtual assistant device of the first embodiment. [Figure 4] FIG. 4 is the second half of the flowchart illustrating the control flow in the virtual assistant device of the first embodiment. [Diagram 5]FIG. 5 is an explanatory diagram showing an example of a display when the mode is switched to the conversation mode. [Figure 6] FIG. 6 is an explanatory diagram showing an example of a display when the first question control is performed. [Figure 7] FIG. 7 is an explanatory diagram showing a first example of a display when the first reply control and the second question control are performed. [Figure 8] FIG. 8 is an explanatory diagram showing a second example of a display when the first reply control and the second question control are performed. [Figure 9] FIG. 9 is an explanatory diagram showing an example of a display when the second response control is performed. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] [Description of the embodiments of the present disclosure] In the following, embodiments of the present disclosure are listed and illustrated.

[0011] [1] A virtual assistant device comprising a display unit that displays an image of a character, a voice output unit that utters words, a control unit that controls the display unit and the voice output unit, and a voice input unit to which voice is input, Using a registration unit provided inside or outside the virtual assistant device, the registration unit registers a first question associated with a plurality of options corresponding to a first answer, a second question associated with a plurality of second answers that are questions corresponding to the options and are expected to be answered, and a reply associated with the second answer; The control unit is performing a first question control to output the first question from the voice output unit as if the character were speaking the first question, and to display the options associated with the first question on the display unit; performing second question control to output the second question corresponding to the option from the voice output unit in a manner that the character speaks the second question after any of the options is input to the voice input unit; After performing the second question control, a response control is performed in which the response corresponding to the second answer inputted to the voice input unit is outputted from the voice output unit as if the character were speaking. Virtual assistant device.

[0012] The virtual assistant device can present answer options to the user in the first question control and allow the user to select. Therefore, the virtual assistant device only needs to prepare in the registration unit those that correspond to the options as the second question, which makes it easy to reduce the amount of data in the registration unit. Furthermore, the virtual assistant device can have a conversation with increased freedom of response from the user by performing the second question control after the options are input by voice, which makes it easy to increase the user's satisfaction with the conversation. Therefore, the virtual assistant device can reduce the amount of required data while easily increasing the satisfaction of the user who uses the virtual assistant device with the conversation.

[0013] [2] the registration unit registers a first response corresponding to the option and a second response corresponding to the response; the control unit performs a first response control to output, when any of the options is input to the voice input unit, the first response associated with the option from the voice output unit as if the character were speaking it; performing the second question control after performing the first response control; After the second question control is performed, a second response control corresponding to the response control is performed. The virtual assistant device described in [1].

[0014] The virtual assistant device can output the first response to the option selected by the user from the voice output unit as if the character were speaking. Therefore, the virtual assistant device can more easily increase the user's satisfaction with the conversation. Moreover, since the user's first answer to the first question is selected from the options, it is easy to prepare the first response to the option in advance. Therefore, the virtual assistant device can easily reduce the amount of data required to store the first response.

[0015] [3] The control unit performs the second question control after repeating the first question control and the first response control a plurality of times. The virtual assistant device described in [2].

[0016] The virtual assistant device repeats the first question control multiple times, thereby reducing the amount of data required and allowing the user to continue the conversation. This makes it easier for the virtual assistant device to increase the user's satisfaction with the conversation.

[0017] [4] The registration unit includes a common second question corresponding to a plurality of the options; The control unit controls the voice output unit to output the common second question as if spoken by the character, regardless of which of the plurality of options is input to the voice input unit. A virtual assistant device according to any one of [1] to [3].

[0018] The virtual assistant device can reduce the amount of data required to store the second question and the response by outputting a common second question by voice regardless of the input option.

[0019] [5] The registration unit includes a plurality of the second questions each corresponding to a plurality of the options; The control unit, in the second question control, causes the voice output unit to output the second questions individually associated with the options input to the voice input unit in a manner as if the character is speaking. A virtual assistant device according to any one of [1] to [4].

[0020] By preparing a second question for each option individually, the virtual assistant device can easily output a second question that is more suitable for each option.

[0021] [6] After performing the response control, the control unit switches the image displayed on the display unit to an image indicating the end of the conversation. A virtual assistant device according to any one of [1] to [5].

[0022] The above-mentioned virtual assistant device can make the user recognize that the conversation has ended after performing response control that is likely to increase the user's satisfaction, making it easier to end the conversation in a state of high user satisfaction.

[0023] [7] The second question is made up of a sentence including a general noun and asks about a proper noun included in the general noun. A virtual assistant device according to any one of [1] to [6].

[0024] By asking a proper noun through the second question, the virtual assistant device can make it easier to predict the content of the answer while ensuring a certain degree of freedom in the user's answer. This makes it easier for the virtual assistant device to prepare the second reply, making it easier to reduce the amount of data in the registration unit.

[0025] [8] The registration unit is provided A virtual assistant device according to any one of [1] to [7].

[0026] The virtual assistant device does not need to read the first question, the first response, the second question, and the second response from outside itself.

[0027] [9] A virtual assistant device according to any one of [1] to [7], The registration unit. Virtual assistant system.

[0028] The virtual assistant device of the above virtual assistant system does not need to prepare the first question, the first response, the second question, and the response by itself.

[0029]

[10] A program for use in a virtual assistant device having a display unit that displays an image of a character, a voice output unit that utters words, a control unit that controls the display unit and the voice output unit, and a voice input unit to which voice is input, Using a registration unit provided inside or outside the virtual assistant device, the registration unit registers a first question associated with a plurality of options corresponding to a first answer, a second question associated with a plurality of second answers that are questions corresponding to the options and are expected to be answered, and a reply associated with the second answer; causing the control unit to perform a first question control in which the first question is output from the voice output unit as if spoken by the character, and the option corresponding to the first question is displayed on the display unit; causing the control unit to perform a second question control in which, after any one of the options is input to the voice input unit, the control unit outputs the second question corresponding to the option from the voice output unit in a manner that the character speaks the second question; After the second question control is performed, the control unit is caused to perform a response control for outputting the response associated with the second answer inputted to the voice input unit from the voice output unit as if the character were speaking. A program for virtual assistant devices.

[0030] The program for the virtual assistant device uses the virtual assistant device to present answer options to the user in the first question control and allow the user to select one. Therefore, the program only requires that the second question corresponding to the option is prepared in the registration unit, which makes it easy to reduce the amount of data in the registration unit. Furthermore, the program allows the control unit to perform the first reply control and then the second question control, thereby making it possible to have a conversation with increased freedom in the user's answers, which makes it easy to increase the user's satisfaction with the conversation. Therefore, the program makes it easy to increase the satisfaction of the user who uses the virtual assistant device with the conversation while reducing the amount of data required.

[0031] [Details of the embodiment of the present disclosure] 1. First embodiment 1. Overview of Virtual Assistant System The virtual assistant system 1 shown in FIG. 1 includes a virtual assistant device 10 and a management device 90. In the representative example described below, the virtual assistant device 10 functions as a virtual assistant device for elderly people, and can be used by users in nursing homes, homes, hospitals, etc.

[0032] 2.Hardware configuration of virtual assistant device 1, the virtual assistant device 10 may be an information communication terminal in which an application program is installed and stored and made available on a general-purpose information terminal such as a tablet terminal, a smartphone, a personal computer, or a television configured to be able to communicate with an external device, or may be a dedicated device capable of realizing each function described below. The virtual assistant device 10 may be a portable information device having a communication function, or may be a stationary information device having a communication function.

[0033] 1, the virtual assistant device 10 includes a control unit 11, a communication unit 12, an interface 13, and a storage unit 14. A representative example of the virtual assistant device 10 described below is an example in which the virtual assistant device 10 is realized by a tablet terminal as shown in FIG.

[0034] The control unit 11 shown in Fig. 1 is configured as, for example, a known information processing device. The control unit 11 includes a known calculation device such as a CPU and other peripheral circuits, and can perform various controls and calculations. The control unit 11 has a function of controlling the display unit 15 and the audio output unit 16 that configure the interface 13, and has a function of, for example, causing the display unit 15 to display an embodied character.

[0035] The communication unit 12 shown in Fig. 1 is a device capable of directly accessing a wide area communication network or indirectly accessing a wide area communication network via another device by a known wired communication method or a known wireless communication method. The communication unit 12 may be configured to perform wireless communication with a base station and directly access a wide area communication network (e.g., the Internet) via a base station not shown. The communication unit 12 may be configured to perform wireless communication with an access point not shown and indirectly access a wide area communication network via the access point. The communication unit 12 may be configured to perform wired communication with a relay device (such as a router) and access a wide area communication network via the relay device.

[0036] 1 is a device for receiving and outputting input from a user. The interface 13 includes a display unit 15, a voice output unit 16, an operation unit 17, and a voice input unit 18.

[0037] The display unit 15 and the audio output unit 16 correspond to an example of an output unit, and have a function of outputting information. The display unit 15 is configured as a known image display device such as a liquid crystal display or an organic electroluminescence display, and has a function of displaying various images. In the representative example described below, the display unit 15 forms a part of a touch panel type display device. The audio output unit 16 is configured by a sound output device such as a known speaker. The audio output unit 16 has a function of outputting various sounds in cooperation with the control unit 11.

[0038] The operation unit 17 and the voice input unit 18 function as an input unit for inputting information. The operation unit 17 corresponds to an example of a motion detection unit, and is an input device capable of inputting operations in a contact manner. A suitable example of the operation unit 17 is a touch panel, and may include a button for inputting information. The voice input unit 18 is configured by a voice input device such as a known microphone. The voice input unit 18 has a function of converting input sound into an electric signal and providing it to the control unit 11. The voice input unit 18 functions to obtain a voice signal indicating the voice of the user when the user utters a voice or other sound toward the voice input unit 18. Specifically, when the user utters a sound that can be detected by the voice input unit 18, the voice input unit 18 can obtain a voice signal indicating the content of the sound and convert it into an electric signal.

[0039] In a representative example described below, as shown in Fig. 2 etc., display unit 15 and operation unit 17 constitute touch panel type display device 20. In the example in Fig. 2 etc., a touch panel constituting a part or all of operation unit 17 is configured to be able to transmit light from display unit 15, and covers display unit 15 as a transparent panel configured to allow an image from display unit 15 to be visible from the outside.

[0040] The storage unit 14 has a function of storing various information. A known storage device such as a semiconductor memory, HDD, or SSD is adopted as the storage unit 14. The control unit 11 has a function of writing various information to the storage unit 14 and a function of reading various information stored in the storage unit 14. Various programs such as application programs described below are stored in the storage unit 14. The storage unit 14 also stores identification information (e.g., URL (Uniform Resource Locator) and the like) and other data for accessing sites, information, programs, etc. managed by the management device 90 via a wide area communication network.

[0041] 3.Management device The management device 90 shown in FIG. 1 has various information processing functions and various calculation functions. The management device 90 is an external device provided outside the virtual assistant device 10. The management device 90 has a function of registering various information, a function of distributing various information, and the like. The management device 90 may be any device having a communication function and an information processing function. The management device 90 is configured as a computer equipped with, for example, a CPU, a storage medium, a communication device, and the like. In the example of FIG. 1, the management device 90 includes a control device 91, a communication unit 92, a display unit 93, an input unit 94, and a storage unit 95.

[0042] The control device 91 is configured as, for example, a known information processing device. The control device 91 includes a known arithmetic unit such as a CPU and other peripheral circuits, and can perform various controls and calculations.

[0043] The communication unit 92 is a device capable of directly accessing a wide area communication network or indirectly accessing the wide area communication network via another device by a known wired communication method or a known wireless communication method. The communication unit 92 may be configured to perform wireless communication with a base station and directly access the wide area communication network via a base station (not shown). The communication unit 92 may be configured to perform wireless communication with an access point (not shown) and indirectly access the wide area communication network via the access point. The communication unit 92 may be configured to perform wired communication with a relay device (router, etc.) and access the wide area communication network via the relay device.

[0044] The display unit 93 is configured as a known image display device. The input unit 94 is configured as a known input device such as a keyboard, a mouse, a touch panel, or a voice input unit, and allows information to be input by touch operation or voice input. The storage unit 95 is a storage device that stores various information. A database may be configured in the storage unit 95.

[0045] 4. Example of virtual assistant device operation 4-1.Basic operation An application program is stored in the virtual assistant device 10. This application program is installed in the virtual assistant device 10. This application program is stored in the storage unit 14 and is read and executed by the control unit 11. This application program corresponds to an example of a program for the virtual assistant device.

[0046] The application program is a program that causes the control unit 11 to perform control in the flow shown in Figures 3 and 4. When a predetermined start condition is met (for example, when a predetermined start operation (for example, an operation of the touch panel display device 20 for starting the application program) is performed on the operation unit 17), the control unit 11 executes the application program and goes into standby mode in step S1. The control unit 11 switches between a conversation mode in which a conversation with a user is conducted and a standby mode in which no conversation is conducted.

[0047] Regardless of which mode is selected, the display unit 15 displays a character 70 embodied by an image. The character 70 shown in FIG. 2 is a virtual assistant (anthropomorphic) that imitates an ordinary person. The character 70 shown in FIG. 2 is merely an example, and may be a virtual assistant that imitates a person in a specific profession such as a care worker, a nurse, or a doctor. The virtual assistant may also be an animal or a robot, not limited to a person. The application program may include a program that realizes the function of a chatbot so that the character 70 displayed in FIG. 2 automatically converses. The image of the character 70 shown in FIG. 2 may be realized by a still image, a video, or the like.

[0048] In the standby mode, the image of the character 70 shown in Fig. 2 may be changed in various ways over time, such as the facial expression, posture, movement, action, and speech such as tweets and calls. In the standby mode, the control unit 11 may display the season, calendar, date, time, user information, etc., as characters or icons on the display unit 15 as shown in Fig. 2, and may display illustrations, photographs, computer graphics, and other images that evoke the time periods of morning, noon, evening, and night.

[0049] After step S1, in step S2, the control unit 11 determines whether or not a conversation start condition is satisfied. The conversation start condition is a condition that is predetermined as a condition for performing communication in the virtual assistant device 10. The conversation start condition may be that a predetermined voice is input to the voice input unit 18 (for example, that a predetermined wake word is input). In a representative example described below, the name of the character 70 is set as the wake word, and the voice input of this wake word is set as one of the conversation start conditions. Note that this example is merely an example, and a predetermined greeting (for example, the word "hello") may be set as the wake word, and the voice input of this wake word may be set as one of the conversation start conditions. The conversation start condition is not limited to these examples, and may be, for example, that a predetermined operation is performed on the operation unit 17. An example of "that a predetermined operation is performed on the operation unit 17" may be, for example, that an operation is performed to tap the vicinity of the character or the character on the display unit 15, or that an operation is performed to select some button to instruct the start of a conversation. Alternatively, the conversation start condition may be the arrival of a preset reserved time.

[0050] If the control unit 11 determines in step S2 that the conversation start condition is not satisfied, it repeats the process of step S2. During this time, the control unit 11 changes the facial expression, posture, movement, behavior, and the like of the character 70 in various ways.

[0051] When the control unit 11 determines in step S2 that the conversation start condition is met, the process proceeds to step S3 to switch to the conversation mode. In the conversation mode, voice input is possible. FIG. 5 shows a specific example of the display of the display unit 15 in the conversation mode. The character 70 is also displayed in the conversation mode. In the conversation mode, information indicating that voice input is possible (more specifically, an image 31 resembling a microphone) is displayed on the display unit 15. In the conversation mode, a button used to provide a topic (more specifically, a "topic" button 32) is displayed on the display unit 15.

[0052] After switching to the conversation mode in step S3, the control unit 11 proceeds to step S4 to determine whether or not a topic or keyword has been input to the voice input unit 18. The keyword is a keyword related to the topic. If the control unit 11 determines that neither a topic nor a keyword has been input to the voice input unit 18, it repeats the process of step S4. If a topic or keyword has been input to the voice input unit 18, the control unit 11 proceeds to step S11 in FIG. 4 to start a conversation with the user. Note that the virtual assistant device 10 may be configured to input a topic or keyword by an operation of selecting a topic or keyword.

[0053] In step S11, the control unit 11 performs a first question control. The first question control is a control to output the first question from the voice output unit 16 so that the character 70 speaks it, and to display options associated with the first question on the display unit 15. The options correspond to the first answer that is an answer to the first question. The options are, for example, made of text information. The above-mentioned storage unit 14 stores a plurality of first questions in advance. The storage unit 14 stores a plurality of topics, and a plurality of first questions are stored for each topic. The first question is, for example, made of text information. The storage unit 14 stores options associated with the first question. A plurality of options are stored corresponding to each of the plurality of first questions. The control unit 11 reads the first question corresponding to the topic input in step S4 from the storage unit 14, and outputs the first question from the voice output unit 16 so that the character 70 speaks it. The control unit 11 also displays the options associated with the read first question on the display unit 15.

[0054] After displaying the options on the display unit 15 in step S11, the control unit 11 proceeds to step S12 to determine whether any of the options has been input to the voice input unit 18. If the user does not speak for a predetermined time, or if the control unit 11 cannot recognize the user's words, the control unit 11 determines that none of the options have been input. If the control unit 11 determines that none of the options have been input, it switches to standby mode and returns to step S2. At this time, the control unit 11 may output words such as "I'm sorry, I couldn't hear you" from the voice output unit 16 so that the character 70 speaks, or may switch to standby mode without outputting any voice. When the user utters an option, the option is input to the voice input unit 18. If the control unit 11 determines that any of the options has been input to the voice input unit 18, it proceeds to step S13.

[0055] The control unit 11 performs first reply control in step S13. The first reply control is a control for outputting a first reply associated with an option input to the voice input unit 18 from the voice output unit 16 as if the character 70 were speaking the option. A plurality of first replies are stored in the memory unit 14. The first replies are associated with the options. The first replies are composed of text information, for example. The control unit 11 causes the voice output unit 16 to output the first reply corresponding to the option input in step S13 as if the character 70 were speaking the option.

[0056] After performing the first reply control in step S13, the control unit 11 proceeds to step S14 to perform the second question control. The second question control is a control for causing the voice output unit 16 to output a second question as if spoken by the character 70 after performing the first reply control. A plurality of second questions are stored in the memory unit 14. The second questions correspond to the options. The second questions consist of, for example, text information. After performing the first reply control, the control unit 11 causes the voice output unit 16 to output a second question corresponding to the option input in step S13 as if spoken by the character 70.

[0057] After outputting the second question from the voice output unit 16, the control unit 11 proceeds to step S15 to determine whether or not a second answer corresponding to the second question has been input to the voice input unit 18. A plurality of expected second answers are stored in the storage unit 14 in association with the second question. The second answer is, for example, composed of text information. If the user does not say anything for a predetermined time, or if the control unit 11 cannot recognize the user's words, the control unit 11 determines that the second answer stored in the storage unit 14 has not been input to the voice input unit 18. If the control unit 11 determines that the second answer stored in the storage unit 14 has not been input to the voice input unit 18, the control unit 11 switches to a standby mode and returns to step S2. At this time, the control unit 11 may output words such as "I'm sorry, I couldn't hear you" from the voice output unit 16 so that the character 70 speaks them, or may switch to a standby mode without outputting any voice. When the user utters the second answer, the second answer is input to the voice input unit 18. If the control unit 11 determines that the second answer stored in the storage unit 14 has been input to the voice input unit 18, the process proceeds to step S16.

[0058] The control unit 11 performs a second reply control in step S16. The second reply control is a control for outputting, after performing the second question control, a second reply associated with the second reply input to the voice input unit 18 from the voice output unit 16 as if the character 70 were speaking. The second reply is stored in the memory unit 14. The second reply is associated with the second reply. The second reply is composed of, for example, text information. The control unit 11 performs a second reply associated with the second reply input to the voice input unit 18 in step S15 from the voice output unit 16 as if the character 70 were speaking.

[0059] After performing the second reply control in step S16, the control unit 11 proceeds to step S17 to perform the termination control. The termination control is a control to terminate the conversation mode and return to the standby mode. In the termination control, the control unit 11 switches the image displayed on the display unit 15 to an image indicating the end of the conversation. The image indicating the end of the conversation may be, for example, an image in which information indicating that voice input is possible is removed from the display unit 15, or an image in which the "topic" button is removed. After performing the termination control, the control unit 11 proceeds to step S2.

[0060] 4-2. Specific examples of conversation 5 to 9 show display examples in the case where "old stories" are input as a topic. When control unit 11 switches to the conversation mode in step S3, the image shown in Fig. 5 is displayed. In the conversation mode, as shown in Figs. 5 to 9, information indicating that voice input is possible (specifically, image 31 resembling a microphone) is displayed on display unit 15.

[0061] In the image shown in FIG. 5, the "topic" button 32 is displayed. When the "topic" button 32 is operated, the virtual assistant device 10 provides a topic. For example, as shown in FIG. 5, the virtual assistant device 10 provides the topic "old stories" by displaying text information "old stories" on the display unit 15. The topic displayed on the display unit 15 may be switched each time the "topic" button is operated. A plurality of topics may be displayed on the display unit 15. When the user utters a topic or keyword, the topic or keyword is input to the voice input unit 18. The topic may be input by the operation unit 17. In FIG. 5, only the text information "old stories" is displayed on the display unit 15, but the text information "old stories" may be displayed superimposed on an image such as a photo displayed on the display unit 15. In addition, a plurality of options may be displayed on the display unit 15, and the text information "old stories" may be included as one of the options. Furthermore, the virtual assistant device 10 may guide the user to say "an old story" only by the voice output of the character 70, without displaying the text information "an old story" on the display unit 15.

[0062] When "old stories" is input as the topic to the voice input unit 18 in step S4, the first question control is performed in step S11, and the first question is output from the voice output unit 16. Furthermore, as in the image shown in FIG. 6, the first question and options corresponding to the first question are displayed on the display unit 15. In the example shown in FIG. 6, the first question is "Please tell me which did you do during the New Year holidays, shuttlecock or kite flying." In the example shown in FIG. 6, the options are "I did shuttlecock" and "I did kite flying."

[0063] When "I played shuttlecock" is input to the voice input unit 18, a first reply control is performed in step S13. In the first reply control, a first reply corresponding to the option "I played shuttlecock" is output from the voice output unit 16. Also, as in the image shown in FIG. 7, the first reply is displayed on the display unit 15. In the example shown in FIG. 7, the first reply is "It's a traditional Japanese game."

[0064] When "I flew a kite" is input to the voice input unit 18, first reply control is performed in step S13, and a first reply corresponding to the option "I flew a kite" is output from the voice output unit 16. Also, as in the image shown in Fig. 7, the first reply is displayed on the display unit 15. In the example shown in Fig. 8, the first reply is "It's fun when the wind is strong."

[0065] After the first reply control is performed, the second question control is performed in step S14. In the second question control, the second question is output from the voice output unit 16, and is displayed on the display unit 15 as shown in Figs. 7 and 8. In this embodiment, the second question is output from the voice output unit 16 following the first reply. The second question is also displayed on the display unit 15 together with the first reply. In the example shown in Figs. 7 and 8, the second question is "Speaking of New Year's, what is your favorite osechi dish?"

[0066] When a second answer corresponding to the second question is input to the voice input unit 18, a second reply control is performed in step S16. In the second reply control, a second reply corresponding to the input second answer is output from the voice output unit 16, and the second reply is displayed on the display unit 15 as shown in Fig. 9. For example, when the second answer is "black beans," the second reply is, "I love them too. Plump black beans are delicious," as shown in Fig. 9.

[0067] As described above, the virtual assistant device 10 can converse with the user. The first question, the options, the first reply, the second question, the second reply, and the second reply vary depending on the topic.

[0068] For example, if the topic is "health," the first question might be, "Do you like to take long baths? Or is that a crow's way of thinking?" The options might be, "I like to take long baths" or "I like to take long baths."

[0069] For example, a first response corresponding to the option "I like long baths" is "It improves blood circulation." Also, a second question corresponding to the option "I like long baths" is, for example, "Can you tell me which hot spring is the best one you have ever been to?" If the second response "Noboribetsu Onsen" is entered in response to this second question, the second response would be, for example, "It's one of the famous hot springs in Hokkaido. Noboribetsu Jigokudani is also a tourist spot and apparently has a hot spring source."

[0070] An example of the first response corresponding to the option "crow's gyozui" is "Maybe he's sensitive to heat." Also, an example of the second question corresponding to the option "crow's gyozui" is "What is your favorite bath salt scent?" If the second response "herbs" is entered in response to this second question, the second response is, for example, "They say that herbs have the effect of improving blood circulation."

[0071] As yet another example, when the topic is "talking about hobbies," the first question is, for example, "Have you ever written a picture letter?" The options are, for example, "I have written a picture letter" and "I don't write picture letters."

[0072] An example of the first response corresponding to the option "I wrote a picture letter" is "That's a nice hobby." Also, an example of the second question corresponding to the option "I wrote a picture letter" is "If you were to draw an animal, what animal would you draw?" If the second response "lion" is entered in response to this second question, an example of the second response is "I'm looking forward to a powerful picture of the king of the beasts."

[0073] An example of the first response corresponding to the option "I don't write picture letters" is "I see." Also, an example of the second question corresponding to the option "I don't write picture letters" is "What color stationery do you like to write letters on?" If the second response "light blue" is entered in response to this second question, the second response would be, for example, "Light blue has a clean image. I think white is a safe choice."

[0074] 5. Example of effects The virtual assistant device 10 presents answer options to the user in the first question control and allows the user to select one. Therefore, the virtual assistant device 10 only needs to prepare the second question corresponding to the option, which makes it easy to reduce the amount of data in the storage unit 14. Furthermore, the virtual assistant device 10 can have a conversation with increased freedom of response by the user by performing the second question control after the option is input by voice, which makes it easy to increase the user's satisfaction with the conversation. Therefore, the virtual assistant device 10 can easily increase the satisfaction of the user who uses the virtual assistant device 10 with the conversation while reducing the amount of required data.

[0075] The virtual assistant device 10 outputs the second question associated with the option selected by the user from the voice output unit 16 as if the character 70 were speaking, so that it is easy to output a second question more suitable for the option. Therefore, the virtual assistant device 10 is more likely to increase the user's satisfaction with the conversation.

[0076] The virtual assistant device 10 can output the first response to the option selected by the user from the voice output unit 16 as if the character 70 were speaking. Therefore, the virtual assistant device 10 can more easily increase the user's satisfaction with the conversation. Moreover, since the user's first answer to the first question is selected from the options, it is easy to prepare the first response to the option in advance. Therefore, the virtual assistant device 10 can easily reduce the amount of data for storing the first response.

[0077] The virtual assistant device 10 can continuously talk with the user while reducing the amount of data required by repeating the first question control multiple times. This makes it easier for the virtual assistant device 10 to increase the user's satisfaction with the conversation.

[0078] The virtual assistant device 10 can reduce the amount of data required to store the second question and the second response by outputting a common second question by voice regardless of the input option, as in the example of the topic "old stories" described above.

[0079] By preparing a second question for each option individually, such as in the above-mentioned examples of the topics "health talk" and "hobbies talk," the virtual assistant device 10 can easily output a second question that is more appropriate for each option.

[0080] The virtual assistant device 10 can make the user recognize that the conversation has ended after performing the second response control, which is likely to increase the user's satisfaction, and therefore makes it easier for the user to end the conversation in a state of high satisfaction.

[0081] By asking a proper noun through the second question, the virtual assistant device 10 can easily predict the content of the answer while ensuring a certain degree of freedom in the user's answer. This makes it easier for the virtual assistant device 10 to prepare the second reply, making it easier to reduce the amount of data in the storage unit 14.

[0082] The virtual assistant device 10 does not need to read the first question, the first response, the second question, and the second response from outside itself.

[0083] The program for the virtual assistant device 10 can use the virtual assistant device 10 to present answer options to the user in the first question control and allow the user to select. For this reason, the above program only needs to prepare answers corresponding to the options as the second question, making it easy to reduce the amount of data in the storage unit 14. Furthermore, the above program allows the control unit 11 to perform the first answer control and then the second question control, making it possible to have a conversation with increased freedom in the user's answers, which makes it easy to increase the user's satisfaction with the conversation. Therefore, the above program makes it easy to increase the satisfaction of the user who uses the virtual assistant device 10 with the conversation while reducing the amount of data required.

[0084] <Other embodiments> The present invention is not limited to the embodiments described above and in the drawings, and the following embodiments are also included in the technical scope of the present invention. In addition, the various features of the above-mentioned embodiments and the embodiments to be described later may be combined in any combination as long as they are not contradictory.

[0085] The registration unit may be provided outside the virtual assistant device. For example, the registration unit may be configured by the memory unit 95.

[0086] In the above-described embodiment, the virtual assistant device 10 is configured as a virtual assistant device mainly for elderly people, but is not limited to this example. For example, it may be targeted at other categories of subjects such as children.

[0087] In the above-described embodiment, in any example where the character 70 is displayed and a conversation is carried out, one or more of the character's facial expression, character's action, subtitles, sound effects, and icons may be displayed or changed during the conversation. For example, the control unit 11 may change the character 70's facial expression to a smile, or cause the character 70 to perform an action such as jumping or skipping. The facial expression of the character employed is not limited to a smile, and may be changed to a gloomy expression, an angry expression, a sad expression, or the like, or the character 70 may perform a happy action or a crying action.

[0088] It should be noted that the embodiments disclosed herein are illustrative and not restrictive in all respects. The scope of the present invention is not limited to the embodiments disclosed herein, and is intended to include all modifications within the scope indicated by the claims or within the scope equivalent to the claims. [Explanation of symbols]

[0089] 1. Virtual assistant system 10. Virtual assistant device 11...Control section 12…Communications Department 13. Interface 14...Memory unit (registration unit) 15…Display section 16…Audio output section 17...Operation unit 18…Audio input section 20...Touch panel display device 31...Image that resembles a microphone 32…"Topic" button 70…Character 90…Management device 91...Control device 92…Communications Department 93…Display section 94...Input section 95...Storage section

Claims

1. A virtual assistant device comprising a display unit that displays an image of a character, a voice output unit that utters words, a control unit that controls the display unit and the voice output unit, and a voice input unit to which voice is input, Using a registration unit provided inside or outside the virtual assistant device, the registration unit registers a first question associated with a plurality of options corresponding to a first answer, a second question associated with a plurality of second answers that are questions corresponding to the options and are expected to be answered, and a reply associated with the second answer, The control unit is performing a first question control to output the first question from the voice output unit as if the character were speaking the first question, and to display the options associated with the first question on the display unit; performing a second question control for outputting the second question corresponding to the option from the voice output unit as if the character were speaking the second question, without displaying a second option consisting of the second answer on the display unit, after any of the options is input to the voice input unit; After performing the second question control, a response control is performed in which the response corresponding to the second answer inputted to the voice input unit is outputted from the voice output unit as if the character were speaking. Virtual assistant device.

2. a first reply corresponding to the option and a second reply corresponding to the reply are registered in the registration unit, the control unit performs a first response control to output, when any of the options is input to the voice input unit, the first response associated with the option from the voice output unit as if the character were speaking, performing the second question control after performing the first response control; After the second question control is performed, a second response control corresponding to the response control is performed. The virtual assistant device according to claim 1.

3. The control unit performs the second question control after repeating the first question control and the first response control a plurality of times. The virtual assistant device according to claim 2.

4. the registration unit includes a common second question corresponding to a plurality of the options; The control unit controls the voice output unit to output the common second question as if spoken by the character, regardless of which of the plurality of options is input to the voice input unit. The virtual assistant device according to claim 1.

5. the registration unit includes a plurality of the second questions each corresponding to a plurality of the options; The control unit, in the second question control, causes the voice output unit to output the second questions individually associated with the options input to the voice input unit in a manner as if the character is speaking the second questions. The virtual assistant device according to claim 1.

6. The control unit, after performing the response control, switches the image displayed on the display unit to an image indicating an end of the conversation. The virtual assistant device according to claim 1.

7. The second question is composed of a sentence including a general noun and is a question asking about a proper noun included in the general noun. The virtual assistant device according to claim 1.

8. The registration unit A virtual assistant device according to any one of claims 1 to 7.

9. A virtual assistant device according to any one of claims 1 to 7; The registration unit. Virtual assistant system.

10. A program used in a virtual assistant device having a display unit that displays an image of a character, a voice output unit that utters words, a control unit that controls the display unit and the voice output unit, and a voice input unit to which voice is input, Using a registration unit provided inside or outside the virtual assistant device, the registration unit registers a first question associated with a plurality of options corresponding to a first answer, a second question associated with a plurality of second answers that are questions corresponding to the options and are expected to be answered, and a reply associated with the second answer, causing the control unit to perform a first question control in which the first question is output from the voice output unit as if spoken by the character, and the option corresponding to the first question is displayed on the display unit; causing the control unit to perform a second question control in which, after any one of the options is input to the voice input unit, the control unit outputs the second question corresponding to the option from the voice output unit as if the character is speaking it, without causing a second option consisting of the second answer to be displayed on the display unit; After the second question control is performed, the control unit is caused to perform a response control for outputting the response associated with the second answer inputted to the voice input unit from the voice output unit as if the character were speaking. A program for virtual assistant devices.

Images