JP2023087483A - Virtual assistant device and program for virtual assistant device - Google Patents

Abstract

To provide a virtual assistant device and a program for the virtual assistant device, which easily increase the interest of a user who uses the virtual assistant device.SOLUTION: In a virtual assistant system 1 comprising a virtual assistant device 10 and a management device 90, the virtual assistant device includes a control section 11 that performs first utterance control so as to cause an interface 13 to output a plurality of choices corresponding to any subject of conversation and cause the interface 13 to output a conversation of a character related to the plurality of output choices, and performs second utterance control so as to cause the interface to output the conversation related to the choice selected by selection input as an utterance from the character after an interval of a predetermined period upon completion of the first utterance control if the selection input for selecting any of choices through the interface 13 after the first utterance control is performed.SELECTED DRAWING: Figure 1

Description

The present invention relates to a virtual assistant device and a program for the virtual assistant device.

Patent Literature 1 discloses an example of an agent device. The agent apparatus disclosed in Patent Document 1 asks questions for user character determination without any sense of incongruity according to the situation by an agent that is displayed by images and sounds using a display device and a speaker. Furthermore, this agent device discriminates the character of the user from the result of the user's answer inputted by the microphone, and changes the character of the agent according to the character of the user.

JP-A-2007-133728 Japanese Patent Application Laid-Open No. 2001-204774

The apparatus disclosed in Patent Document 1 enhances entertainment by changing the character of the agent in accordance with the character of the user determined from the answer result of the user. It is difficult to have a conversation that reflects, and there is room for improvement in terms of increasing user interest.

On the other hand, Patent Literature 2 discloses a communication support system for nursing care facilities. This system includes a knowledge base in which rules for answering simple inquiries from care recipients are registered and a processing unit, and the processing unit answers simple inquiries from care recipients based on the rules. You can operate the agent as follows. However, although this system may be able to provide answers that are suitable for inquiries from care recipients, there is a high possibility that the topic will end with each inquiry. It is difficult to get the impression that you are communicating with In this regard, there is a concern that the caregiver's (user's) interest may be lost.

An object of the present invention is to provide a technology that can easily increase the interest of users who use virtual assistant devices.

A virtual assistant device, which is one of the present invention,
A virtual assistant device comprising an interface for accepting and outputting input from a user, and a control unit for displaying an embodied character on a display unit constituting the interface,
The interface has at least one of a motion detection unit that detects an input motion from the user by contact or non-contact, or a voice input unit that acquires a voice signal indicating the voice of the user,
The control unit uses information in a storage unit that stores correspondence information in which a plurality of options are associated with topics, causes the interface to output the plurality of options corresponding to any topic, and outputs the plurality of options to be output. When a first utterance control is performed to cause the interface to output the character's conversation related to the option of, and a selection input is made to select one of the options through the interface after the plurality of options are output, After a predetermined period of time after the end of the first utterance control, second utterance control is performed to output a story related to the option selected by the selection input to the interface as an utterance from the character.

The above-mentioned virtual assistant device can cause the interface to output a plurality of options corresponding to any topic, and can cause the interface to output a conversation of characters related to the plurality of options that are output. While providing enjoyment, it is possible to accurately confirm the user's intention in a form associated with the conversation. After a period of time has passed from such conversation, the conversation related to the option selected by the selection input can be provided as the character's conversation, giving the impression that the character remembers the contents of the past conversation. It is possible to provide a story to the user in a form that makes it easy to give In particular, this virtual assistant device can reliably prevent the ``speech provided by the second speech control'' from greatly deviating from the ``choices selected by the user,'' making it easier for the user to be more interested. .

In the virtual assistant device, the first utterance control causes the display unit to display a conversation of the character including a question on any topic and the plurality of options that are candidates for answers to the question. Control.

In the first utterance control, the virtual assistant device can display the content of the question and candidate answers to the question on the display unit, so that the user can select the question and answer candidates while visually confirming them. be able to. Therefore, the accuracy of the selection is improved, and in the second speech control, it is possible to more reliably prevent the "speech provided by the second speech control" from greatly deviating from the "choices selected by the user".

In the virtual assistant device described above, the second utterance control is control for causing the interface to output a conversation including the word of the option selected by the selection input as a conversation of the character.

In this virtual assistant device, the conversation provided based on the second utterance control includes "choice words selected according to the first utterance control". When hearing or seeing a story provided by a character, the "word of choice" that the user has selected in the past tends to leave an impression. As a result, the user tends to have the impression that the character has been interested in and remembers his/her own story, and easily develops an interest in and attachment to the character's story.

A program for a virtual assistant device, which is one of the present invention,
A program used in a virtual assistant device comprising an interface for accepting and outputting input from a user, and a control unit for displaying a character embodied in a display unit constituting the interface,
The interface has at least one of a motion detection unit that detects an input motion from the user by contact or non-contact, or a voice input unit that acquires a voice signal indicating the voice of the user,
Using information in a storage unit that stores correspondence information that associates a plurality of options with topics, causes the interface to output the plurality of options corresponding to any topic, and selects one of the plurality of options to be output a step of causing the control unit to perform a first utterance control that causes the interface to output a conversation of the character that prompts the user to select either;
When a selection input for selecting one of the options is made through the interface after the first utterance control, after a predetermined period of time after the end of the first utterance control, the option selected by the selection input is selected. causing the control unit to perform a second utterance control for outputting related conversation to the interface as conversation of the character;
including.

The above program for the virtual assistant device can control the interface to output a plurality of options corresponding to any topic and to output the character's conversation related to the plurality of options to be output to the interface. Therefore, while providing the enjoyment of conversation to the user, it is possible to accurately confirm the intention of the user in a form associated with the conversation. After a period of time has passed from such conversation, the conversation related to the option selected by the selection input can be provided as the character's conversation, giving the impression that the character remembers the contents of the past conversation. It is possible to provide a story to the user in a form that makes it easy to give In particular, this program can reliably prevent the ``speech provided by the second speech control'' from greatly deviating from the ``choices selected by the user'', thereby making it easier for the user to be more interested.

ADVANTAGE OF THE INVENTION According to this invention, it is easy to raise the interest of the user using a virtual assistant apparatus.

FIG. 1 is a block diagram schematically showing an electrical configuration of a virtual assistant system including a virtual assistant device according to the first embodiment. FIG. 2 is an explanatory diagram showing Example 1 of normal display in the virtual assistant device of the first embodiment. FIG. 3 is an explanatory diagram conceptually showing a data structure example of user data stored in the management device. FIG. 4 is an explanatory diagram conceptually showing an example data structure of content-related data stored in the management device. FIG. 5 is a flowchart illustrating the flow of control in the virtual assistant device of the first embodiment; FIG. 6 is an explanatory diagram showing Example 2 of normal display in the virtual assistant device of the first embodiment. FIG. 7 is an explanatory diagram showing Example 3 of normal display in the virtual assistant device of the first embodiment. FIG. 8 is an explanatory diagram showing Example 4 of normal display in the virtual assistant device of the first embodiment. FIG. 9 is an explanatory diagram illustrating an example of "predetermined notification" in the virtual assistant device of the first embodiment. FIG. 10 is an explanatory diagram showing Example 5 of the normal display in the virtual assistant device of the first embodiment, and is a diagram showing an example in which notification information is displayed. FIG. 11 is an explanatory diagram showing example 1 of content provision by the virtual assistant device of the first embodiment. FIG. 12 is an explanatory diagram showing Content Provision Example 2 in the virtual assistant device of the first embodiment, and is an example of display following the display of FIG. 11 . FIG. 13 is an explanatory diagram showing Example 3 of content provision by the virtual assistant device of the first embodiment, and is an example of display following the display of FIG. 12 . FIG. 14 is an explanatory diagram showing Content Provision Example 4 in the virtual assistant device of the first embodiment, and is an example of display following the display of FIG. 13 . FIG. 15 is an explanatory diagram for explaining the first utterance control for the first specific example 1 of the question action and the related conversation action. FIG. 16 is an explanatory diagram for explaining the second first utterance control for the specific example 1 of the question action and the related conversation action. 17A and 17B are explanatory diagrams for explaining the second utterance control in the specific example 1. FIG. FIG. 18 is an explanatory diagram for explaining the second speech control in the specific example 1, and is a diagram following FIG. 17 . FIG. 19 is an explanatory diagram for explaining the first utterance control for specific example 2 of the question action and the related conversation action. 20A and 20B are explanatory diagrams for explaining the second speech control in the second specific example. FIG. 21 is an explanatory diagram for explaining the second speech control in the specific example 2, and is a diagram following FIG. 20 . FIG. 22 is an explanatory diagram for explaining the first utterance control for specific example 3 of the question action and the related conversation action. 23A and 23B are explanatory diagrams for explaining the second utterance control in the specific example 3. FIG. FIG. 24 is an explanatory diagram for explaining the second speech control in the specific example 3, and is a diagram following FIG. 23 . FIG. 25 is an explanatory diagram for explaining the first utterance control for specific example 4 of questioning action and related conversation action. FIG. 26 is an explanatory diagram for explaining the second speech control in specific example 4. FIG. FIG. 27 is an explanatory diagram for explaining the first utterance control for specific example 5 of questioning action and related conversation action. 28A and 28B are explanatory diagrams for explaining the second utterance control according to the specific example 5. FIG. FIG. 29 is an explanatory diagram 1 for explaining contents of specific example 6. FIG. FIG. 30 is an explanatory diagram 2 for explaining contents of specific example 6. FIG. FIG. 31 is an explanatory diagram 3 for explaining contents of specific example 6. FIG.

<First embodiment>
1. Overview of Virtual Assistant System A virtual assistant system 1 shown in FIG. 1 includes a virtual assistant device 10 and a management device 90 . In the following description, the virtual assistant system 1 is also simply referred to as system 1 . A typical example described below is that 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., for example. be.

2. Hardware Configuration of Virtual Assistant Device As shown in FIG. 1, a virtual assistant device 10 installs an application program in a general-purpose information terminal such as a tablet terminal, a smartphone, a personal computer, and a television configured to communicate with an external device. , an information communication terminal capable of storing and using the data, or a dedicated device capable of realizing each function described later. 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.

As shown in FIG. 1, the virtual assistant device 10 includes a control section 11, a communication section 12, an interface 13, and a storage section . 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.

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 arithmetic device such as a CPU and other peripheral circuits, and can perform various controls and arithmetic operations. The control unit 11 has a function of displaying an embodied character on the display unit 15 constituting the interface 13 .

The communication unit 12 shown in FIG. 1 is a device capable of accessing a wide area network directly or indirectly 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 (for example, the Internet) via the base station (not shown). The communication unit 12 may be configured to perform wireless communication with an access point (not shown) and indirectly access the wide area network via the access point. The communication unit 12 may be configured to perform wired communication with a relay device (router, etc.) and access a wide area communication network via the relay device.

The interface 13 shown in FIG. 1 is a device that accepts and outputs input from a user. The interface 13 includes a display section 15 , an audio output section 16 , an operation section 17 and an audio input section 18 .

The display unit 15 and the audio output unit 16 function as output units that output information. The display unit 15 is configured as a known image display device such as a liquid crystal display or an organic electroluminescence display. In the representative example described below, the display unit 15 forms part of a touch panel type display device. The voice output unit 16 is composed of, for example, a sounding device such as a known speaker. The voice output unit 16 has a function of outputting various voices in cooperation with the control unit 11 .

The operation unit 17 and the voice input unit 18 function as input units for inputting information. The operation unit 17 corresponds to an example of a motion detection unit, and is an input device capable of input operation by a contact method. A suitable example of the operation unit 17 is, for example, a touch panel. The voice input unit 18 is configured by, for example, a voice input device such as a known microphone. The voice input unit 18 has a function of converting an input sound into an electric signal and giving the electric signal to the control unit 11 . The voice input unit 18 is used when the user utters a voice or other sound toward the voice input unit 18 (specifically, when the user utters a voice that can be detected by the voice input unit 18). function to obtain an audio signal indicative of a person's voice.

In the representative example described below, the display unit 15 and the operation unit 17 constitute a touch panel display device 20, as shown in FIG. The touch panel display device 20 is also simply referred to as the touch panel 20 . In the example of FIG. 2 and the like, the operation unit 17 is configured to be able to transmit light from the display unit 15, and a transparent panel covers the display unit 15 so that an image from the display unit 15 can be viewed from the outside. there is

The storage unit 14 has a function of storing various information. The storage unit 14 employs a known storage device such as a semiconductor memory, HDD, SSD, or the like. 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 an application program to be described later are stored in the storage unit 14 . The storage unit 14 also stores identification information (for example, URL (Uniform Resource Locator), etc.) for accessing sites, information, programs, etc. managed by the management device 90 via a wide area network. there is

3. Management Device The management device 90 shown in FIG. 1 has various information processing functions and various arithmetic 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 as long as it has a communication function and an information processing function. The management device 90 is configured as a computer including, 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 section 92 , a display section 93 , an input section 94 and a storage section 95 .

The control device 91 is configured, for example, as a known information processing device. The control unit 11 includes a known arithmetic device such as a CPU and other peripheral circuits, and can perform various controls and arithmetic operations.

The communication unit 92 is a device capable of accessing a wide area network directly or indirectly 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 a wide area 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 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.

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, mouse, touch panel, voice input unit, etc., and enables input of information by touch operation or voice. The storage unit 95 is a storage device that stores various information. A database may be configured in the storage unit 95 .

4. Distribution of Content from Management Apparatus In the management apparatus 90, information regarding users to whom information is to be distributed is registered. FIG. 3 shows an example data structure of user data stored in the storage unit 95 of the management device 90 shown in FIG. As shown in FIG. 3, user data stored in the management device 90 constitutes a database, in which an ID, registration type, and user information are stored in association with each user. The ID is information that can identify each user, and is identification information that can identify each user. The registration type is information for registering the type of information desired by the user and the type of information meaningful to the user. User information is various information about users, and may include personal information such as name, date of birth, email address, hobbies, health information, place of residence, past episodes, etc. It may contain information about the specified delivery destination. For example, in the user data of FIG. 3, if ID1 is specified as the user ID, the type of information desired by the user specified by "ID1" is specified by the information of "registration type 1". The personal information of the user is specified by the information of "user information 1".

In the system 1 according to the present embodiment, various types can be registered as "types of information desired by users" and "meaningful information for users". Specifically, multiple types of hobbies or purpose in life are prepared in advance as ``types of information desired by users'' and ``meaningful information for users'', and any of these types can be selected. One or more types may be included in the registration information. Various types of hobby or purpose of life can be prepared, such as gardening, sports, recreation, gymnastics, music, art, cooking, nostalgic scenery and toys, travel, animals, vehicles, and shopping information. . Alternatively, a plurality of types of disease-related information may be prepared in advance as types of information desired by the user, and one or more types selected from the plurality of types may be included in the registered information. Specifically, a plurality of types related to geriatric syndrome prevention, rehabilitation, and relaxation may be prepared in advance, and one or more types selected from the plurality of types may be included in the registration information.

For example, in the user data of FIG. 3, ID1 is information of "00001", registration type 1 is information specifying "gardening, gymnastics", and user information 1 is "Taro Yamada" as a user name. and specifies "address information 1" as the delivery destination address. In this case, if the control device 91 refers to the user data, the name of the user identified by the ID of "00001" is "Taro Yamada" and the destination address is "address information 1". It is possible to specify that the type desired by the user is "gardening, gymnastics".

The management device 90 is capable of registering and distributing content. FIG. 4 shows an example data structure of content-related data stored in the storage unit 95 of the management device 90 shown in FIG. As shown in FIG. 4, the content-related data stored in the management device 90 constitute a database, and for each content, content identification information, content data, distribution date and time, and type of content are stored in association with each other. ing. In this specification, content data corresponds to an example of content information and is also simply called content.

The content identification information may be information that can identify and specify each content, and may be an identification number or a specific name. Content data is specific data of content, and may include moving image data, still image data, audio data, etc., and may include other data (for example, program data, etc.). The distribution date and time is information specifying the date and time when the associated content (content data) is distributed. The type information is information specifying the type of associated content (content data). The type of content specified by the type information may be one type or a plurality of types.

The management device 90 sends each content (content data) specified by each identification information to the virtual assistant device 10 of the user to whom each content should be distributed (the user who has registered the type of each content). Deliver on each delivery date and time associated with the content. Although FIG. 1 illustrates only one virtual assistant device 10 possessed by one user, in the system 1, many users can possess the virtual assistant device 10, and in FIG. , the illustration of the virtual assistant device 10 possessed by another user is omitted. When distributing content, if there are a plurality of users to whom the content is to be distributed, the management device 90 can distribute the content to any user's virtual assistant device 10 . In this embodiment, the management device 90 specifies a user to whom each content should be distributed (a user who has registered the type of each content), and sends each content ( content data), but the content distribution is not limited to this. For example, the virtual assistant device 10 of the user requests the management device 90 to distribute the content based on the information stored in its own storage unit, so that the virtual assistant device 10 of the user: Each content (content data) may be distributed.

For example, in the content-related data of FIG. 4, "identification information 1" is information of "0000A", "data 1" is "predetermined video data related to gardening", and "date and time information 1" is "January 2021 10:00 on the first day of the month", and the "type information 1" is information specifying "gardening". In this case, the control device 91, referring to the content-related data in FIG. As data, it is possible to specify that it should be delivered at “10:00 on January 1, 2021”. In this case, the management device 90 allows the content data specified by the identification information 1 (0000A) (“Predetermined video data regarding gardening” in data 1) to be registered by the user who registers the data of the type “gardening” (see FIG. 3). (user whose user data includes "gardening" as a registration type) to the virtual assistant device 10 at "10:00 on January 1, 2021".

5. Reception control of virtual assistant device 5-1. Basic Control 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, read out by the control unit 11, and executed.

As described above, the management device 90 distributes content (content data) to the virtual assistant device 10 . Content distributed from the management device 90 to the virtual assistant device 10 may be content belonging to a type registered in advance by the user who owns the virtual assistant device 10, and selected by the management device 90 regardless of registration by the user. It may be content that has been created. The virtual assistant device 10 receives the content delivered to itself from the management device 90 by the communication unit 12 . When the communication unit 12 receives content (content data) distributed from the outside (the management device 90), the control unit 11 stores the content data in the storage unit 14, and issues a “predetermined notification” through the interface 13. ” to perform the control. Note that the “predetermined notification” may be performed before the content data is stored in the storage unit 14 .

Specifically, the application program is a program that causes the control unit 11 to perform control according to the flow shown in FIG. When a predetermined start condition is satisfied (for example, when a predetermined start operation (for example, operation of the touch panel 20 for starting the application program) is performed on the operation unit 17), the control unit 11 The application program is executed, and the character 70 embodied by an image is displayed on the display unit 15 in step S1.

FIG. 2 shows a specific example of display performed in step S1. In FIG. 2, the character 70 is a virtual assistant (personification) imitating a general person. The character 70 displayed in FIG. 2 is merely an example, and may be, for example, a virtual assistant imitating a person of a specific occupation such as a care worker, a nurse, or a doctor. Also, the virtual assistant may be a virtual assistant imitating an animal, a robot, or the like, 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 can automatically have a conversation. The content of the automatic conversation can be changed or selected according to the user's pre-registered attributes (gender, family structure, housing environment, birthday, hobbies, content difficulty, etc.). The image of the character 70 shown in FIG. 2 can be realized by a still image, a moving image, or the like. 7. As shown in FIG. 8, the facial expression, posture, motion, action, etc. of the character 70 may be changed in various ways.

In steps S1, S3, S4, S8, etc., the control unit 11 causes the character 70 to be displayed as shown in FIGS. etc., or illustrations, photographs, computer graphics, other images, etc. that image the time zones of morning, noon, evening, and night may be displayed. For example, FIG. 6 shows an image of a predetermined daytime period. In this image, the color of the background outside the character 70 is changed to a bright color (specifically is shown in a predetermined light color). On the other hand, FIG. 8 shows an image during a predetermined nighttime period. In this image, the color of the background outside the character 70 is changed to a dark color (predetermined color) to indicate the nighttime period. shown in darker shades).

After step S1, the control unit 11 determines in step S2 whether or not the conversation start condition is satisfied. The conversation start condition is a condition predetermined as a condition for starting a conversation from 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, a predetermined wake word is input). In the representative example described below, the name of the character 70 is the wake word, and voice input of the wake word is one of the conversation start conditions. Note that this example is merely an example, and a predetermined greeting (for example, "Hello") may be used as a wake word, and voice input of this wake word may be set as one of the conditions for starting a conversation. The conversation start condition is not limited to these examples, and may be, for example, that a predetermined operation has been performed on the operation unit 17 (for example, an operation of tapping near the display unit 15 has been performed). Alternatively, the conversation start condition may be the arrival of a preset reservation time.

When the control unit 11 determines in step S2 that the conversation start condition is established, the process proceeds to step S3 to start providing the conversation or content. Conversation and content provision in step S3 can be performed in the same manner as in step S8, which will be described later. On the other hand, if it is determined in step S2 that the conversation start condition is not met, the process proceeds to step S4 to continue normal display. While the No determination in step S2 and the No determination in step S5 are repeated, the character display as shown in FIGS. 2 and 6 to 8 is continued. To change actions, actions, etc.

After step S3 or step S4, the control unit 11 determines whether or not there is a new delivery in step S5. When the control unit 11 determines in step S5 that the communication unit 12 has not received the content (content data) distributed from the management device 90, it determines No in step S5 and returns the processing to step S2. The subsequent processing is performed again. If the control unit 11 determines that there is a new delivery in step S5, it determines YES in step S5, and performs the processing after step S6.

5-2. When there is a new delivery In step S5, the control unit 11 determines whether or not the communication unit 12 has received the content (content data) delivered from the management device 90. If it is determined that the content (content data) has been received, in step S6 , causes the interface 13 to perform "predetermined notification". The "predetermined notification" is the display or voice output of "communication information for notifying that the virtual assistant device 10 has received new content delivered from the outside". The display and voice output of the transmission information may be the display or voice output of a message, or may be an image display such as a symbol or pattern that conveys that new content has been delivered. It may be an output of a notification sound (generation of an alarm sound, a buzzer sound, etc.) to notify that the delivery of the information has been received. As the notification sound, for example, a ringing sound of a telephone or a charm sound, which is familiar in daily life, is preferable. For example, FIG. 9 shows an example of "predetermined notification". In the example of FIG. 9, as the "predetermined notification", the display unit 15 displays an image 72 of a message to the effect that the delivery identified by the delivery name has arrived. In combination with the display, it is also possible to perform message notification by voice, image display such as a pattern, output of notification sound, and the like. For example, the notification may be made by a character's conversation.

In this way, when the communication unit 12 receives the content data (content information) distributed from the outside (the management device 90), the above application program, in step S6, "predetermines notification via the interface 13. control” is executed by the control unit 11.

After causing the interface 13 to perform a "predetermined notification" in step S6, the control unit 11 determines whether or not there is a provision instruction in step S7. Specifically, in step S7, the control unit 11 determines "whether or not an input instructing provision of content has been received via the interface 13".

The “input for instructing provision of content” may be, for example, a predetermined operation on the operation unit 17 or a predetermined voice input. For example, in the example in which the "predetermined notification" as shown in FIG. 9 is performed by the process of step S6, two selection buttons (button images of "not see" and "see") are displayed together with the message of "predetermined notification". be. In this case, an operation of selecting "view" among the selection buttons (for example, an operation of clicking the image 72 of "view") corresponds to an example of "input instructing provision of content". Therefore, when an operation to select "view" is performed after the display as shown in FIG. 9 is performed in step S6, it is determined in step S7 that an input instructing provision of content has been received, and the process proceeds to step S8. to run.

If the control unit 11 determines in step S7 that it has not received the "input for instructing provision of content", it stores the newly distributed content data in the storage unit 14 in step S9. For example, after the "predetermined notification" is performed in step S6, if the "input for instructing provision of content" is not performed until a predetermined time elapses, the control unit 11 outputs the content data (content information) is displayed on the display unit 15. For example, when two pieces of content data are newly distributed from the management device 90 and "predetermined notification" is performed in step S6 as shown in FIG. If the "view" button has not been pressed, the process advances to step S9 to accumulate newly distributed content data and display an image such as that shown in FIG. In the image of FIG. 10, an image 74 displays, as notification information, the number of unprovided contents among newly distributed contents. Note that when the "predetermined notification" is performed in step S6 as shown in FIG. 9, the "not watch" button is selected (that is, when an input instructing suspension of provision of the content is made). Also, the process proceeds to step S9 and similar processing is performed.

If the control unit 11 determines in step S7 that it has received an "input for instructing provision of content", in step S8 it causes the display unit 15 to display a conversation or content. When determining Yes in step S7 and performing the process of step S8, the control unit 11 outputs content based on content data (content information) newly distributed from the management device 90 (for example, newly distributed content The display unit 15 and the audio output unit 16 are caused to reproduce moving images, display still images, output audio, etc. included in the data.

The control performed in step S8 when the process proceeds to Yes in step S7 is control for outputting the “conversation regarding the content received by the communication unit 12” via the interface 13. FIG. FIGS. 11 to 14 show an example of control performed by the control section 11 in step S8 when the process proceeds to Yes in step S7. FIGS. 11 to 14 show an example of providing the content in step S8 in the case where the content “lively delivery” related to “gardening” is newly delivered from the management device 90. In this example, the delivered content data contains videos and conversation data about "gardening". In this case, the control unit 11 performs control so as to reproduce the motion in step S8 and emit a voice for conversation. For example, in the example of FIG. 13, at the timing when the sunflower field is displayed, the conversation "Summer flowers, sunflowers have a lively image, don't they?" By displaying the character 70 when making this conversation, it is possible to give the impression that the character 70 is speaking. It should be noted that the control unit 11 may speak with the pre-registered nickname of the user when speaking.

The control unit 11 provides the content in step S8, and when the user speaks to the user as shown in FIG. Attempt to "recognise user responses" based on at least one of the sounds. For example, a predetermined response operation to the operation unit 17 (for example, an operation of tapping the character 70 or other design) or a predetermined voice input to the voice input unit 18 (for example, input of words) is referred to as a “response from the user”. It is defined. When the interface 13 receives a "response from the user", the control unit 11 performs control so that a further conversation in response to this response is output via the interface 13. FIG. The "further conversation in response" may be a topic of the type of content being served, or a different topic than that type. It is desirable to use both character display and voice output for the "further conversation in response", but either one may be used. It should be noted that, when the control unit 11 performs control to issue a "further conversation in response to the response", it is desirable to attempt "recognition of the response from the user" again. Then, when there is a "response from the user", it is desirable to output a further conversation in response to this response via the interface 13. FIG. In this way, the conversation can be continued by repeating "further conversation in response to the response" and "recognition of the response from the user".

In this way, when the control unit 11 recognizes a “response from the user” via the interface 13 after outputting “conversation about the content” via the interface 13, the control unit 11 via the interface 13 outputs “a response to the response”. Control to output "conversation". Step S8 is a step of causing the control unit 11 to perform such control.

In addition, when the conversation is performed in step S8, the control unit 11 uses the voice input/output together with the speech content (user's speech content) input by voice via the voice input unit 18 and the virtual assistant device 10 (for example, the speech content of the character 70) may be displayed in characters on the display unit 15. FIG.

11 to 14 show an example of providing content of the type registered in association with the virtual assistant device 10 (the type desired by the user). It is not limited to this example.

5-3. Details of Normal Operation During No New Delivery Period The following description relates to details of the normal operation performed during the period during which there is no new delivery (the period during which No is determined in step S5). During this period, the control unit 11 mainly switches between the standby mode and the conversation mode. In this embodiment, a mode in which the process of step S4 is continued during a period in which there is no new distribution (a period in which No is determined in step S5) is an example of the standby mode. Further, the mode in which the process of step S3 is continued during the period described above is an example of the conversation mode.

The conversation mode is a mode from when it is judged as Yes in step S2 until the termination condition of the conversation mode is satisfied. The termination condition of the conversation mode may be that the content executed in the conversation mode has ended, or that a predetermined input (for example, voice input, touch panel operation, etc.) has not been made to the interface for a certain period of time or longer. Alternatively, the user may input an instruction to end the interface (such as a voice input or a touch operation to instruct the end). Specifically, the conversation mode is a mode in which the control unit 11 detects words other than wake words. When voice is input to the interface during conversation mode, the control unit 11 analyzes the voice input to the interface and recognizes the words that the voice means by a known method.

The standby mode is a mode during which No is determined in step S2, and is a mode when the conversation mode is canceled. The standby mode is a mode in which the controller 11 monitors whether or not a wake word has been input to the interface. When voice is input to the interface during the standby mode, the control unit 11 determines by a known method whether or not the voice is the wake word. However, the control unit 11 does not recognize any voice other than the wake word from the voice input to the interface during the standby mode. That is, in the standby mode, the control unit 11 does not need to recognize voices other than the wake word, and only determines whether or not it is the wake word. can be

As shown in the flowchart of FIG. 5, the control unit 11 is set to the standby mode during the period in which the determination of No is repeated in steps S2 and S5, and continuously tries to detect the wake word during the standby mode. When the control unit 11 detects that the wake word has been voice-inputted to the interface 13 during the standby mode, it determines Yes in step S2, switches to the conversation mode, and advances the process to step S3. Then, the conversation mode is continued until the end condition of the conversation mode is satisfied. When the end condition of the conversation mode is satisfied, the control unit 11 switches to the standby mode and continues the standby mode. The control unit 11 can also cause the display unit 15 to display an image in which the character performs a standby action during the standby mode.

The content provided by the virtual assistant device in steps S3 and S8 may be content for simply displaying a still image or simply playing a moving image, or may be content that allows a virtual experience. Contents that allow a virtual experience include content that allows a pseudo driving experience as shown in FIG. 21, content that allows a pseudo work experience as shown in FIG. Examples include content that allows you to experience raising animals. In addition, it is desirable that the user can select which content is performed in step S3. The content selection method by the user may be, for example, a method in which a plurality of types of content names are displayed on the touch panel 20 and the user selects the desired content. Would you like to watch a travel video?", and when the user performs a desired instruction (tap operation, voice input of a term to be instructed, etc.) in response to the suggestion, that content is selected. You may do so. Content may be selected by other methods without being limited to these methods.

5-4. Concrete Example 1 of Question Action and Related Conversation Action
The following description relates to specific examples of conversations that take place in steps S3 and S8.
The control unit 11 can employ various types of conversations as the conversations employed in the process of step S3 in the control of FIG. As one of them, as shown in FIGS. 15 and 16, it is possible to provide conversations in which questions are asked to the user. When providing a conversation to ask questions to the user (question conversation), the question conversation may be provided independently of the provision of the content, and after or during the provision of the content as shown in FIGS. , may provide a question conversation of content related to the content.

The control unit 11 operates the interface 13 so as to provide a question conversation selected by a predetermined method when a provision condition for providing a question conversation is satisfied. Specifically, as shown in FIGS. 15 and 16, the control unit 11 causes the interface 13 to output a plurality of options corresponding to any of the topics, and allows the interface to display the character's conversation related to the plurality of options that are output. The first utterance control is performed so that 13 is output. In the examples of FIGS. 15 and 16, the first utterance control is performed so that the display unit 15 displays the character's conversation including a question on one of the topics and a plurality of options that are candidates for the answer to the question. ing. In the program for executing the control in FIG. 5, a part of the program for executing step S3 or step S8 corresponds to an example of "the step of causing the control unit 11 to perform the first utterance control".

In addition, in order to realize such first utterance control, a plurality of types of correspondence information are prepared in which a "topic", a "question", and a "plurality of options" are associated with each other. It is desirable that the information is stored in the storage unit 14 . For example, when the topic of "travel" is prepared, the type of the topic "travel", the question (see FIG. 15) related to the topic of "travel", and the multiple options (see FIG. 15) that are candidates for the answer to the question. ) in association with each other is stored in the storage unit 14 . Further, when the topic of "vehicles" is prepared, the type of the topic "vehicles", the question (see FIG. 19) related to the topic of "vehicles", and the multiple options (see FIG. 19) which are the answer candidates for the question. ) in association with each other is stored in the storage unit 14 . In addition, when the topic of "work" is prepared, the type of the topic of "work", the question about the topic of "work" (see FIG. 22), and the multiple options (see FIG. 22) that are candidates for the answer to the question. ) in association with each other is stored in the storage unit 14 . With this configuration, when any topic is selected, the control unit 11 selects corresponding information (selected topic corresponding information (including the "question" corresponding to the "question" and "multiple choices" that are candidates for the answer to the "question"), and based on the read correspondence information, it is associated with the selected topic. can grasp the questions and options presented.

Note that the "topic" of the correspondence information may be an independent topic, or may be a topic of "options associated with the topic in the correspondence information of any topic". For example, when the corresponding information for the topic of "travel" includes options of "Hokkaido", "Okinawa", and "Tohoku" as options corresponding to "travel", "Hokkaido" is treated as a separate topic, and this topic ( As correspondence information corresponding to the topic of Hokkaido), a question about Hokkaido (for example, a question asking what souvenirs you want to buy in Hokkaido as shown in FIG. 16) and multiple options as answer candidates for this question (for example, as shown in FIG. 16). , potato, cheese, corn, etc.) may be stored separately.

If stored in this way, for example, when a question about any topic is asked in the first utterance control for the first time, one of the options is selected in response to the question (for example, FIG. 15 If Hokkaido is selected in the question), and the corresponding information associated with the topic of the selected option is stored in the storage unit 14 (for example, if it is associated with the above "Hokkaido", (If the correspondence information associated with the topic of "Hokkaido souvenir" is stored in the storage unit 14), the control unit 11, based on the correspondence information associated with the topic of the option, Questions and multiple options can be provided. That is, if there is correspondence information whose topic is the option selected during the first utterance control, the control unit 11 asks a question about the option selected during the first utterance control based on the correspondence information. The first utterance control can be performed for the second time so as to provide a plurality of options, which are candidates for the answer to the question, through the character's conversation as shown in FIG. In either case, the correspondence information may be continuously stored in the storage unit 14, or may be distributed from the management device 90 to the virtual assistant device 10 and stored in the storage unit 14 as necessary. .

The topic of the question provided in the first utterance control may be a topic related to the type of information previously associated with the user (the user to be provided in the control of FIG. 5) in the registered information. The topic may be related to the content provided in S8. For example, when "travel" is associated with the user in the registration information and registered, information such as that shown in FIG. 15 may be provided as a question conversation regarding this "travel". Alternatively, when displaying content (movie, etc.) related to "travel" in steps S3 and S8, information such as that shown in FIG. may be provided. In order to enable the "question conversation about 'travel'" as shown in FIG. All you have to do is

In the example of FIG. 15, a question about "the prefecture you want to visit" is adopted as a question about the topic of travel, and a plurality of choices indicating a plurality of types of specific prefecture names are adopted as candidates for the answer to the question. ing. When performing the first utterance control as shown in FIGS. 15 and 16, the control unit 11 controls the voice output unit 16 so that the character 70 reads out the conversation (such as questions and options) displayed on the display unit 15. It is desirable to output audio to

When controlling the interface 13 to output a plurality of options as shown in FIG. 15 in the first speech control, the control unit 11 selects one of the options via the interface 13 after the plurality of options are output. It is confirmed whether the selection input to do is made. In the example of FIG. 15, the “selection input to select one of the options” is any surface of each area where each option (specifically, each of Hokkaido, Okinawa, and Tohoku) is displayed on the touch panel 20 This is an operation that touches the For example, in the state of FIG. 15 , when an “operation (user operation) of touching the surface of the area where the option of “Hokkaido” is displayed” is performed on the touch panel 20, the control unit 11 selects “user”. Information that associates "options selected by operation" and "question content" is stored in the storage unit 14 (specifically, result information that specifies that the prefecture that the user wants to visit is Hokkaido is stored in the storage unit 14). stored in the storage unit 14).

The question conversation may be completed in one session, or a plurality of question conversations as shown in FIGS. 15 and 16 may be conducted. In the examples of FIGS. 15 and 16, after the question conversation (first question conversation) as shown in FIG. 15, a further question conversation (second question conversation) regarding the options selected in the first question conversation is provided. This is an example of

In the example of FIG. 16, a question about "souvenirs I would like to buy when I go to Hokkaido" is adopted as a question about the option selected in the first question conversation, and a plurality of types of concrete answer candidates are used as candidates for the answer to the question. In addition, multiple options indicating the name of the souvenir are adopted. In this example as well, when the control unit 11 controls the interface 13 to output a plurality of options as shown in FIG. Confirm whether or not an input is made. In the example of FIG. 16, the "selection input for selecting one of the options" is any surface of each area where each option (specifically, each of potato, cheese, and corn) is displayed on the touch panel 20. This is an operation that touches the For example, in the state of FIG. 16 , when an “operation (user operation) of touching the surface of the area where the option of “cheese” is displayed” is performed on the touch panel 20, the control unit 11 Information that associates "options selected by operation" and "contents of questions" is stored in the storage unit 14 (specifically, if the user goes to Hokkaido, the souvenir he or she wants to buy is cheese). is stored in the storage unit 14).

When the first utterance control is performed in step S3 or S8, the control unit 11 confirms the above-mentioned selection input performed in response to the first utterance control, and when the selection input is confirmed, the above-mentioned result information is transmitted. After storing in the storage unit 14, the first utterance control ends. When the first utterance control is performed in step S3, the control unit 11 performs the processing after step S3 after the first utterance control is finished. When the first utterance control is performed in step S8, the control unit 11 performs the processes after step S8 after the first utterance control is finished.

The control unit 11 performs the second utterance control after a predetermined period of time after the first utterance control ends. The 'predetermined period' may be a standard indicating that a certain amount of time has passed, for example, it may be a 'predetermined period of time' such as one week or one month. It may be a period until the content is distributed" or the like, or a period until a predetermined number of contents are distributed".

Specifically, the control unit 11 satisfies a first condition that "a predetermined period of time has elapsed since the end of the first speech control", and satisfies a second condition that "a predetermined speech start condition is satisfied". When the conditions are satisfied, the second speech control is performed. That is, the condition for starting the second speech control is to satisfy the first condition and the second condition. The speech start condition, which is the second condition, may be, for example, ``that the content related to the option selected in the first speech control has been delivered from the management device'', ``that it is a predetermined day of the week'', or `` It may be "a predetermined date" or "a conversation start condition of step S2 is satisfied".

In the representative examples shown in FIGS. 17 and 18, the above-mentioned speech start condition is met when "the content relating to the option selected in the first speech control is delivered from the management device 90". For example, after the predetermined period of time has elapsed since the end of the first utterance control, the "content related to the option (Hokkaido) selected in the first utterance control" is displayed while the normal display in step S4 is being continued. When delivered from the management device 90 to the virtual assistant device 10 (that is, when the content is delivered and the condition for starting the second utterance control is satisfied), the control unit 11 determines Yes in step S5, and step In S6, after causing the interface 13 to perform "predetermined notification" as shown in FIG. 17, in step S7, it is determined whether or not there is a provision instruction. In step S7, the control unit 11 determines whether either "view" or "not view" is selected in the display state as shown in FIG. If the "view" button has not been pressed or the "not view" button has been selected, the process proceeds to step S9 to store newly distributed content data. On the other hand, when the "view" button is selected in the display state as shown in FIG. 17, the control unit 11 performs the second speech control so as to display the image as shown in FIG. In the example of FIG. 18, the control unit 11 selects the option (Hokkaido, cheese) selected by the selection input (input for selecting "Hokkaido" and "cheese") in the first utterance control as shown in FIGS. The second speech control is performed so that the interface 13 outputs the related story as speech from the character 70 . In this example, in the program for executing the control in FIG. 5, the program for executing steps S5, S6, S7, and S8 corresponds to an example of "the step of causing the control unit 11 to perform the second utterance control." do.

Specifically, the control unit 11 performs the second utterance control so as to cause the interface 13 to output the conversation including the words of the option (Hokkaido) selected by the selection input as the conversation of the character 70 . Furthermore, the control unit 11 performs second utterance control so that the interface 13 outputs the conversation including the word of the option (cheese) selected by the selection input as the conversation of the character 70 together with the image of the option (cheese). Is going. When performing the second utterance control as shown in FIG. 18, the control unit 11 desirably outputs voice so that the character 70 reads out the conversation (words) displayed on the display unit.

5-5. Concrete Example 2 of Question Action and Related Conversation Action
Instead of the first speech control as shown in FIGS. 15 and 16, the first speech control as shown in FIG. 19 may be performed. In the example of FIG. 19, a question about "a vehicle you want to ride" is adopted as a question on the topic "vehicle", and multiple options indicating a plurality of types of specific vehicle names are adopted as candidates for the answer to the question. ing. In the first utterance control, when the interface 13 is controlled to output a plurality of options as shown in FIG. It is confirmed whether or not an operation has been made to touch the surface of each area where is displayed. For example, in the state of FIG. 19, when "an operation of touching the surface of the display area of 'passenger car'" is performed on the touch panel 20, the control unit 11 selects the 'user', 'options selected by the operation', and ' (Specifically, result information specifying that the vehicle that the user wants to ride is a passenger car is stored in the storage unit 14).

In the example of FIG. 19 as well, after the first utterance control ends, the second utterance control is started when the conditions for starting the second utterance control are met. For example, when the normal display (step S4 in FIG. 5) is continued after the predetermined period of time has passed since the first utterance control as shown in FIG. When the "content related to (vehicle)" is delivered from the management device 90 to the virtual assistant device 10, the control unit 11 determines Yes in step S5 of FIG. After the "predetermined notification" is performed, in step S7, it is determined whether or not there is a provision instruction. The control unit 11 controls the display unit 15 to display an image as shown in FIG. 21 when the "view" button is selected in the display state as shown in FIG.

In this example, making the interface 13 perform conversation and display as shown in FIG. 20 is also one of the second speech control. In the example of FIG. 20, the control unit 11 generates a speech (more specifically, The second utterance control is performed so as to cause the interface 13 to output the message "the content of the simulated driving experience has arrived") as an utterance from the character 70 . Furthermore, it is one of the second utterance controls to have the character provide a story (for example, voice story) about a passenger car while displaying a moving image as shown in FIG. The story provided in the example shown in FIG. Various stories can be adopted, such as a description of the location.

5-6. Concrete Example 3 of Question Action and Related Conversation Action
Instead of the first speech control as shown in FIGS. 15 and 16, the first speech control as shown in FIG. 22 may be performed. In the example of FIG. 22, a question about "the job you dreamed of when you were a child" is adopted as a question on the topic of "work", and a plurality of specific job names are displayed as candidates for the answer to the question. options are adopted. In the first utterance control, when the interface 13 is controlled to output a plurality of options as shown in FIG. ) is displayed, confirms whether or not an operation has been made to touch the surface of any of the displayed areas. For example, in the state of FIG. 22, when an operation is performed to touch the surface of the display area for "hairdresser", the control unit 11 displays "user", "options selected by operation", and "question content". is stored in the storage unit 14 (specifically, result information specifying that the job dreamed of by the user as a child was a beautician is stored in the storage unit 14).

In the example of FIG. 22 as well, after the end of the first speech control, the second speech control is started when the conditions for starting the second speech control are met. For example, when the normal display (step S4 in FIG. 5) is continued after the predetermined period of time has elapsed since the first utterance control as shown in FIG. (Hairdresser)" is delivered from the management device 90 to the virtual assistant device 10, the control unit 11 causes the interface 13 to perform a "predetermined notification" as shown in Fig. 23 in step S6. In S7, it is determined whether or not there is a provision instruction. The control unit 11 controls the display unit 15 to display an image as shown in FIG. 24 when the "view" button is selected in the display state as shown in FIG.

In this example, making a conversation or display as shown in FIG. 23 is one of the second speech controls. In the example of FIG. 23, the control unit 11 generates a speech (more specifically Specifically, the second utterance control is performed so as to cause the interface 13 to output the notification "The content of the simulated hairdresser's experience has arrived") as an utterance from the character 70 . Furthermore, it is one of the second utterance controls to have the character provide a story about the hairdresser's work and simulated experience while displaying a moving image as shown in FIG.

5-7. Concrete Example 4 of Question Action and Related Conversation Action
Instead of the first speech control as shown in FIGS. 15 and 16, the first speech control as shown in FIG. 25 may be performed. In the example of FIG. 25, a question about "what you are interested in and want to study" is adopted as a question about the topic of "study", and a plurality of candidates indicating a plurality of types of specific study subjects are used as answer candidates for the question. Choices (specifically cooking, flower arrangement, handicrafts) are employed. For example, in the state of FIG. 25, when an operation is performed to touch the surface of the display area for "handicraft" on the touch panel 20, the control unit 11 outputs result information specifying that handicraft is what the user wants to study. Stored in the storage unit 14 . In this example as well, the control unit 11 starts the second speech control based on the result information when the conditions for starting the second speech control are satisfied after the first speech control as shown in FIG. 25 is finished. For example, when the conversation start condition of step S2 (FIG. 5) is satisfied after the above-described predetermined period has elapsed after the first speech control is finished, the control unit 11 causes the conversation shown in FIG. output to The conversation in FIG. 26 is a conversation (more specifically, "3 or You wanted to study handicrafts a month ago.Let's go learn embroidery together next week.” In this example, in the program for executing the control in FIG. 5, the program for executing steps S2 and S3 corresponds to an example of "the step of causing the control unit 11 to perform the second speech control."

5-8. Concrete Example 5 of Question Action and Related Conversation Action
Instead of the first speech control as shown in FIGS. 15 and 16, the first speech control as shown in FIG. 27 may be performed. In the example of FIG. 27, a question about "usual tooth care method" is adopted as a question on the topic "brushing survey", and multiple types of specific tooth care methods are shown as candidates for the answer to the question. options (specifically, toothbrushes, interdental brushes, and floss) have been adopted. For example, in the state of FIG. 27 , when an operation is performed to touch the surface of the “interdental brush” display area on the touch panel 20, the control unit 11 specifies that the user's care method is the interdental brush. The result information obtained is stored in the storage unit 14 . In this example as well, the control unit 11 starts the second utterance control based on the result information when the conditions for starting the second utterance control are satisfied after the first utterance control as shown in FIG. 27 is completed. For example, when the conversation start condition of step S2 (FIG. 5) is established after the above-mentioned predetermined period has elapsed after the first speech control is finished, the control unit 11 causes the conversation shown in FIG. output to The conversation in FIG. 28 is a conversation (more specifically, , ``You always used an interdental brush, didn't you?

5-9. Concrete Example 6 of Question Action and Related Conversation Action
The content provided in step S3 may be content for watching pseudo breeding and breeding as shown in FIGS. In this example, the control unit 11 executes monitoring content such as watching the growth of pseudo creatures (pseudo animals, plants, fictitious creatures, etc.) during the period in which the virtual assistant device 10 is continuously used. It is designed to be obtained. Specifically, the program for executing the control in FIG. 5 also has a program for executing the watching content.

In the program for executing the watching content, the situation of the pseudo-watching target is subdivided into many patterns, and an image is prepared for each situation (for each pattern). Then, this program can operate the control unit 11 so as to select an action for the pseudo-watched target according to an instruction from the user when the pseudo-watched target is in each situation. Specifically, the above program is designed to reflect the user's impressions and opinions when viewing the previous content in the next virtual experience, and the user's impressions and opinions are linked to action selection. For example, the above program operates the control unit 11 to display a screen such as that shown in FIG. In this case, based on the current situation of the watching target and the selected action, the control unit 11 is operated so as to shift the growth situation of the watching target to a situation corresponding to the selected action. In the example of FIG. 29, when a pseudo-dog is to be watched over, the user is asked about the user's impressions and opinions (specifically, the desired next action). Either action can be selected according to the question. When the user selects any action while the screen shown in FIG. 29 is displayed, the above program displays the simulated dog's growth situation based on the current situation of the simulated dog and the selected action. to a situation corresponding to the selected action. In this example, the control unit 11 can operate, for example, to display an image as shown in FIG. 29 in step S3 of FIG. 5, and the control for displaying the image as shown in FIG. It corresponds to an example. In the example of FIG. 29, the first utterance control causes the interface 13 to output a plurality of options corresponding to the subject of the pseudo-watching target (a pseudo-dog), and causes the character's conversation related to the plurality of options to be output. is output to the interface 13.

For example, in the above program, the situation of the person being watched over (for example, a pseudo-dog) is subdivided into a number of patterns, and it is determined which pattern to shift to when each action is selected in each pattern. ing. For example, when the situation of the watching target (pseudo dog) when the question as shown in FIG. Similarly, it is determined which pattern to shift to when "playing with a toy" is instructed in the above specific pattern, and "feed food" is instructed in the above specific pattern. It is determined which pattern to shift to when A transition from one situation (pattern) to another situation (another pattern) is made by an instruction from the user, but may be made by other changes in the environment. For example, it may be determined which state to shift to when a certain state (certain pattern) is maintained for the first period of time. It may be determined to which state to shift to in the case. Of course, examples of environmental changes may be other than these.

The program that executes the control in FIG. 5 can operate to ask the user whether or not he/she wishes to display an image related to the watching content at a predetermined timing. The "predetermined timing" is, for example, one of the conditions for starting the conversation in step S2. It may be that a predetermined time (for example, a predetermined time) has arrived, or that a predetermined operation for displaying a watching content image has been performed on the interface 13. good. For example, when the normal display of step S4 in FIG. 5 is repeated (when No in step S2 and No in step S5 are repeated), the "predetermined timing" comes. In this case, the process proceeds to Yes in step S2, and in step S3, displays an image such as that shown in FIG. In step S3, when "view" is selected during display of an image such as that shown in FIG. , an image showing the current situation of the watching target (pseudo dog) is displayed. In the example of FIG. 31, the character 70 is having a conversation explaining the situation of the watching target, and the moving image of the watching target is displayed in parallel with such conversation.

Even in such an example, when a selection input is made to select one of the options via the interface 13 after a plurality of options are output by the first utterance control, the control unit 11, after the end of the first utterance control, After a predetermined period of time, the second speech control can be performed. In this example as well, the control unit 11 causes the interface 13 to output a story related to the option selected by selection input (for example, selection of one of the options in FIG. 29) as an utterance from the character 70. control. For example, when "play with a toy" is selected in the above-described first utterance control for displaying the image of FIG. , ``I played with Coco-chan the other day.

6. Exemplification of Effects As described above, the virtual assistant device 10 can cause the interface 13 to output a plurality of options corresponding to any topic, and can cause the interface 13 to output a conversation of characters related to the plurality of options that are output. Therefore, it is possible to accurately confirm the intention of the user in a manner related to the conversation while providing the enjoyment of the conversation to the user. After a certain period of time has elapsed from such conversation, at a later date, the conversation related to the option selected by the selection input can be provided as the character's conversation. It is possible to provide a story to the user in a form that easily gives a strong impression. In particular, the virtual assistant device 10 can reliably prevent the ``speech provided by the second speech control'' from greatly deviating from the ``options selected by the user'', and the user is more likely to be interested in it. Become.

For example, in the example of FIG. 18, the option (Hokkaido, cheese) that the user intentionally selected in the past conversation as shown in FIGS. Therefore, the user can have a feeling or impression as if the character remembered the specific words he or she uttered in the past conversation, and the user has attachment to the character, a sense of distance, and trust. It is easy to increase the feeling, etc., and it is easy to increase the interest in conversation.

Since the virtual assistant device 10 can display the question content and the candidate answer to the question on the display unit 15 in the first utterance control, the user can select the question and the candidate answer while visually confirming. can do. Therefore, the accuracy of the selection is improved, and in the second speech control, it is possible to more reliably prevent the "speech provided by the second speech control" from greatly deviating from the "choices selected by the user".

Since the virtual assistant device 10 includes "words of options selected according to the first utterance control" in the conversation provided based on the second utterance control, the user can When hearing or seeing a story provided by a character, the "word of choice" that the user has selected in the past tends to leave an impression. As a result, the user tends to have the impression that the character has been interested in and remembers his/her own story, and easily develops an interest in and attachment to the character's story.

<Other embodiments>
The present invention is not limited to the embodiments explained by the above description and drawings, and the following embodiments are also included in the technical scope of the present invention. In addition, various features of the embodiments described above and the embodiments described later may be combined in any way as long as they are consistent combinations.

In the above-described embodiment, the first utterance control is control for displaying on the display unit a character's conversation including a question on any topic and a plurality of options that are candidates for the answer to the question. , and a plurality of options that are candidates for the answer to the question. In this case, the input for selecting one of the plurality of options may be performed by operating the touch panel, or may be performed by voice input.

In the above-described embodiment, the first utterance control includes, as shown in FIG. 15, an image of the character, an image representing the content of the conversation asked by the character in characters, and a plurality of candidate answers to the question from the character. Although the example in which the image representing the options with characters is displayed on the display unit 15 at the same time has been adopted, the present invention is not limited to this example. For example, after simultaneously displaying an "image of a character" and an "image in which text represents the content of a conversation asked by the character", the display then displays "an image of a plurality of options, which are candidates for the answer to the question asked by the character." ” may be displayed in order with a time lag.

In the above-described embodiment, the second utterance control is a control for causing the interface 13 to output a conversation including all the words of the option selected by the selection input as the character's conversation, but it is not limited to this example. The second utterance control may be control for causing the interface 13 to output, as a character's conversation, a conversation including a noun that is part of the word of the option selected by the selection input. Alternatively, the second utterance control may be control for causing the interface 13 to output a still image or a moving image that displays the option selected by the selection input.

In the above-described embodiment, the operation unit 17 corresponding to an example of the motion detection unit is configured as a touch panel, but is not limited to this example. The operation unit 17 may be other known input devices (keyboard, mouse, touch pen, etc.). Alternatively, the motion detection unit may include another input device (for example, an input device capable of non-contact input operation) instead of or in addition to the operation unit 17 . Specifically, the motion detection section may have a non-contact sensor such as an imaging section or a motion sensor. In this case, the non-contact sensor and the control unit 11 may cooperate to detect the user's movement, gesture, and the like.

In the above-described embodiment, the display unit 15 is configured as a display device that displays still images and moving images in two dimensions, but is not limited to this example. The display unit 15 may be a three-dimensional display capable of three-dimensional display.

In the system 1 described above, the type of information desired by the user is registered in the registration unit (storage unit 95) provided outside the virtual assistant device 10, and the control unit 11 is registered in the registration unit. It was designed to control the output of the conversation about the type of content via the interface 13 . However, it is not limited to this example. For example, a registration unit may be provided in the virtual assistant device 10, and the type of information desired by the user may be registered. For example, the virtual assistant device 10 may receive from the management device 90 only the type of content registered in the virtual assistant device 10 (the type desired by the user). Alternatively, when receiving content from the management device 90, the virtual assistant device 10 receives content of the type registered in the virtual assistant device 10 (the type desired by the user). It can be determined that there was Then, in step S7, only the type of content registered in the virtual assistant device 10 (the type desired by the user) may be provided.

Although the virtual assistant apparatus 10 showed the example comprised mainly as a virtual assistant apparatus for elderly people in embodiment mentioned above, it is not limited to this example. For example, other categories of subjects such as children may be targeted.

In any example of this specification, when the control unit 11 conducts a conversation via the interface 13, in at least one of the conversation about the content and the conversation about the response, the expression of the character, the action of the character, the telop, the sound effect, the icon display or audio output of any one or more of may be generated or changed. For example, the control unit 11 may make the character 70 smile, or cause the character 70 to perform actions such as jumping and skipping. The facial expression of the adopted character is not limited to a smiling face, and may be changed to a depressed facial expression, an angry facial expression, a sad facial expression, or the like, and the character 70 may be made to perform a happy motion, a crying motion, or the like.

In the embodiment described above, the storage unit 14 is provided in the virtual assistant device 10, and multiple types of correspondence information are stored in the storage unit 14, but the present invention is not limited to this example. For example, correspondence information similar to the correspondence information stored in the storage unit 14 of the first embodiment may be stored in a device provided outside the virtual assistant device 10 . For example, the storage unit 95 of the management device 90 may function as a "storage unit that stores correspondence information in which a plurality of options are associated with topics". When changing the contents of the first embodiment to this example, when any topic is selected in the above-described first speech control, the control unit 11 provides correspondence information corresponding to the selected topic ( A request is made to the management device 90 for correspondence information including a corresponding "question" and "multiple options" that are candidates for answers to the "question" by communication, and the management device 90 responds to any topic. When a request for corresponding information is received, the corresponding information corresponding to the requested topic is read out of the plurality of types of corresponding information stored in the storage unit 95, and the read corresponding information is transmitted to the virtual assistant device 10. It should work like this. In this case, after acquiring the correspondence information from the management device 90, the virtual assistant device 10 may operate in the same manner as in the first embodiment based on the acquired correspondence information. The main difference between this modified example and the first embodiment is that when using correspondence information corresponding to a topic, the correspondence information is read from the storage unit 14 and used, or the correspondence information is managed. All that is required is whether to acquire it from the device 90 and use it, and the operation after acquiring the correspondence information can be performed in the same manner as in the first embodiment even in the above modified example.

Note that the correspondence information may be provided in both the storage unit 14 and the storage unit 95 . In this example, for example, when correspondence information corresponding to any topic is not stored in the storage unit 14 but is stored in the storage unit 95, the correspondence information stored in the storage unit 95 is used. Alternatively, if correspondence information corresponding to any topic is stored in the storage unit 14, the correspondence information stored in the storage unit 14 may be used.

Even if the correspondence information is stored in the storage unit 14 as in the first embodiment, and even if the correspondence information is stored in the storage unit 95 as in the modified example described above, the correspondence information is stored in the storage units 14 and 95. , the information for performing the second speech control may be stored in the storage unit in which the correspondence information is stored. The information for performing the second utterance control may include each "talk information" corresponding to each option included in the corresponding information (for example, information such as conversation and image associated with the option). . For example, in a system in which "information for performing the second utterance control" is stored in the storage unit 95 together with correspondence information, when performing the second utterance control when any option is selected in the first utterance control, The management device 90 is requested by communication to send the "talk information" corresponding to the option selected in the first utterance control. ', the 'story information' corresponding to the requested option is read from among the plurality of types of story information stored in the storage unit 95, and the read 'story information' is sent to the virtual assistant. It is only necessary to operate to transmit to the device 10 . And the virtual assistant device 10 should just provide the conversation and the image corresponding to the option selected by the 1st utterance control based on the acquired "talk information." The above example is an example in which the correspondence information and the information for performing the second speech control are stored in the same storage unit, but the present invention is not limited to this example, and each information is stored separately. may be stored in the unit.

It should be noted that the embodiments disclosed this time should be considered as examples in all respects and not restrictive. The scope of the present invention is not limited to the embodiments disclosed this time, and includes all modifications within the scope indicated by the claims or within the scope equivalent to the claims. is intended.

DESCRIPTION OF SYMBOLS 1... Virtual assistant system 10... Virtual assistant apparatus 11... Control part 13... Interface 14... Storage part 15... Display part 17... Operation part (motion detection part)
18... Audio input unit 90... Management device (external device)

Claims (4)

A virtual assistant device comprising an interface for accepting and outputting input from a user, and a control unit for displaying an embodied character on a display unit constituting the interface,
The interface has at least one of a motion detection unit that detects an input motion from the user by contact or non-contact, or a voice input unit that acquires a voice signal indicating the voice of the user,
The control unit uses information in a storage unit that stores correspondence information in which a plurality of options are associated with topics, causes the interface to output the plurality of options corresponding to any topic, and outputs the plurality of options to be output. When a first utterance control is performed to cause the interface to output the character's conversation related to the option of, and a selection input is made to select one of the options through the interface after the plurality of options are output, After a predetermined period of time after the end of the first utterance control, the virtual assistant device performs second utterance control for outputting a story related to the option selected by the selection input to the interface as an utterance from the character. 2. According to claim 1, the first utterance control is a control for displaying on the display unit a conversation of the character including a question on any topic and the plurality of options that are candidates for answers to the question. Virtual assistant device as described. The virtual assistant device according to claim 1 or 2, wherein the second utterance control is control for outputting a conversation including a word of the option selected by the selection input to the interface as a conversation of the character. A program used in a virtual assistant device comprising an interface for accepting and outputting input from a user, and a control unit for displaying a character embodied in a display unit constituting the interface,
The interface has at least one of a motion detection unit that detects an input motion from the user by contact or non-contact, or a voice input unit that acquires a voice signal indicating the voice of the user,
Using information in a storage unit that stores correspondence information that associates a plurality of options with topics, causes the interface to output the plurality of options corresponding to any topic, and relates to the plurality of options that are output. a step of causing the control unit to perform a first utterance control for outputting a conversation of the character to the interface;
When a selection input for selecting one of the options is made through the interface after the first utterance control, after a predetermined period of time after the end of the first utterance control, the option selected by the selection input is selected. causing the control unit to perform a second utterance control for outputting related conversation to the interface as conversation of the character;
Programs for virtual assistant devices, including .

Images