JP2022054294A - Interactive guiding device - Google Patents

Abstract

To smoothly provide guidance for a user.SOLUTION: An interactive guiding device includes: a display that displays an image of a character; a detection unit that detects a person in a prescribed space; a voice input/output unit that outputs an utterance made by the character as a voice, and accepts an utterance made by the detected person as a voice input; and a responding unit that controls the voice input/output unit and the display to cause the character to talk with the detected person, thereby responding to the person. The responding unit, in a response, outputs guidance information for the person as an utterance by the character from the voice input/output unit, and displays character information that supplements the guidance information on the display.SELECTED DRAWING: Figure 6

Description

The present invention relates to an interactive guide device.

Conventionally, security guards have been assigned at the entrance of facilities for security of facilities such as office buildings, commercial facilities, hospitals, etc. and for guidance to users. Further, as described in Patent Document 1, by having a display function for displaying an image of a security guard and a call function with a monitoring room, the security of the facility and the user can be provided without a security guard. A security device that realizes guidance has been proposed.

Japanese Patent No. 6259890

In the security device described in Patent Document 1, guidance is provided by voice dialogue with the user. Here, in a voice dialogue, if a large amount of information is to be conveyed to the user, it becomes redundant, and on the other hand, if the information is carefully selected, the information required by the user may not be provided. Further, although it is possible to provide a lot of information to the user at the same time by displaying a drawing or a photograph instead of the voice, it becomes impossible to naturally convey the information in the communication by dialogue. Therefore, in such a device, it has been required to facilitate the guidance to the user while basically guiding by voice dialogue.

The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to provide an interactive guidance device capable of facilitating guidance to a user.

The interactive guidance device according to the present invention has a display unit that displays an image of a character, a detection unit that detects a person in a predetermined space, and outputs utterances by the character as voice, and also outputs utterances by the detected person as voice. It has a voice input / output unit that accepts input, and a response unit that controls the voice input / output unit and the display unit to interact with the person detected by the character to respond to the person. In the response, the guidance information for the person is output as an utterance by the character, and the character information that supplements the guidance information is displayed.

Further, the interactive guidance device according to the present invention further includes a storage unit for storing a plurality of response scenarios and a selection unit for selecting a response scenario for a person from a plurality of response scenarios based on utterances by the person. It is preferable that the response unit outputs guidance information by voice and displays text information based on the selected response scenario in the response.

Further, in the interactive guidance device according to the present invention, it is preferable that the response unit displays, as text information, related information related to the guidance information and related to the guidance target different from the guidance target of the guidance information.

Further, in the interactive guidance device according to the present invention, it is preferable that the response unit displays detailed information in detail of the guidance information as text information.

The interactive guidance device according to the present invention has a display unit that displays an image of a character, a detection unit that detects a person in a predetermined space, and outputs utterances by the character as voice, and also outputs utterances by the detected person as voice. It has a voice input / output unit that accepts input, and a response unit that controls the voice input / output unit and the display unit to interact with the person detected by the character to respond to the person. In the response, if the utterance by the person is not continued, the guidance information for the person is output from the voice input / output unit as the utterance by the character, and if the utterance by the person is continuing, the character corresponding to the guidance information for the person is output. It is characterized by displaying information in text.

The interactive guidance device according to the present invention makes it possible to facilitate guidance to the user.

It is a front view of the guide device 1. It is a figure which shows an example of the schematic structure of the guide device 1. It is a figure which shows an example of the data structure of the response scenario table 151. It is a flow chart which shows an example of the flow of a guidance process. It is a flow chart which shows an example of the flow of a response process. It is a figure for demonstrating the character information. It is a figure which shows an example of the data structure of the response scenario table 151a. It is a flow chart which shows an example of the flow of the 2nd response processing.

Hereinafter, various embodiments of the present invention will be described with reference to the drawings. It should be noted that the technical scope of the present invention is not limited to these embodiments but extends to the inventions described in the claims and their equivalents.

FIG. 1 is a front view of the guide device 1, and FIG. 2 is a diagram showing an example of a schematic configuration of the guide device 1. The guidance device 1 is arranged near the entrance of a facility such as an office building, a commercial facility, or a hospital. The guidance device 1 guards the facility by displaying an image of a character imitating a security guard and causing the character to perform a monitoring operation such as a wink. In addition, the guidance device 1 guides the user by having the character interact with the user who has visited the facility according to a preset response scenario. Therefore, the guidance device 1 includes a display unit 11, a distance measuring unit 12, an imaging unit 13, an audio input / output unit 14, a storage unit 15, and a processing unit 16.

The display unit 11 is configured to display an image, and includes, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, or the like. The display unit 11 displays an image based on the image data supplied from the processing unit 16.

The display unit 11 is provided on the front surface of the guide device 1 and displays an image of the character C. The character C is, for example, a character imitating a security guard, but is not limited to such an example and may be any character such as a mascot character of a facility.

The distance measuring unit 12 is configured to measure the distance to an object around the guide device 1, and includes, for example, a TOF (Time of Flight) type laser distance measuring sensor. The ranging unit 12 irradiates the pulse-modulated laser light in each direction within the measurement range, and calculates the distance to the reflection point in each direction based on the time until the reflected light is detected. The distance measuring unit 12 generates distance image data in which distance information is associated with each pixel based on the direction in which the laser beam is irradiated and the calculated distance, and supplies the data to the processing unit 16.

The image pickup unit 13 is configured to capture an image, and includes, for example, a camera. The image pickup unit 13 generates an image signal of an image captured image corresponding to the imaged subject image by focusing the light rays from the subject within the image pickup range using an optical lens or the like, and converts the image signal into image data in a predetermined format. And supplies it to the processing unit 16.

The distance measuring unit 12 and the imaging unit 13 are provided on the upper front surface of the guide device 1. The measurement range of the distance measuring unit 12 and the imaging range of the imaging unit 13 are both set to include the front of the guide device 1. Further, the correspondence between each pixel of the distance image data generated by the ranging unit 12 and each pixel of the image data generated by the imaging unit 13 is stored in advance as data in the storage unit 15 described later.

The voice input / output unit 14 is configured to receive voice input and output voice, and includes, for example, a microphone and a speaker. The voice input / output unit 14 converts the received voice input into a voice signal which is digital data and supplies it to the processing unit 16, and outputs the voice signal supplied from the processing unit 16 as voice.

The audio input / output unit 14 is preferably provided at the height of the face of the character C on the front surface of the guide device 1, but is not limited to such an example, and may be provided at an arbitrary position of the guide device 1.

The storage unit 15 is configured to store programs and data, and includes, for example, a semiconductor memory. The storage unit 15 stores an operating system program, a driver program, an application program, data, and the like used for processing by the processing unit 16. The program is installed in the storage unit 15 from a computer-readable and non-temporary portable storage medium such as a CD (Compact Disc) -ROM (Read Only Memory) using a setup program or the like. The storage unit 15 stores the response scenario table 151 as data.

The processing unit 16 has a configuration that comprehensively controls the operation of the guidance device 1, and includes one or a plurality of processors and peripheral circuits thereof. The processing unit 16 includes, for example, a CPU (Central Processing Unit), an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), or the like. The processing unit 16 may include a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), and the like. The processing unit 16 controls the operation of each configuration of the guidance device 1 so that the processing of the guidance device 1 is appropriately executed based on the program stored in the storage unit 15, and executes the processing.

The processing unit 16 includes a monitoring unit 161, a detection unit 162, a response unit 163, and a selection unit 164 as its functional blocks. Each of these parts is a functional module realized by a program executed by the processing unit 16. Each of these parts may be implemented in the processing unit 16 as firmware.

FIG. 3 is a diagram showing an example of a data structure of the response scenario table 151 that manages information regarding the response scenario. The response scenario table 151 stores scenario IDs, explanations, keywords, guidance information, and character information in association with each other.

The scenario ID is information that identifies each response scenario. The description is information that outlines each response scenario. Keywords are words associated with each response scenario and are referenced to select a response scenario for the user. The guidance information is information that is output as the utterance of the character C in the response to the user. The character information is information displayed on the display unit 11 in response to the user. The guidance information and the text information are both information presented for guidance to the user.

The text information is information that supplements the guidance information, and is, for example, related information related to the guidance target that is related to the guidance information and different from the guidance target of the guidance information, or detailed information that details the guidance information. In the example shown in FIG. 3, the response scenario of the scenario ID "001" is a scenario related to "guidance for washing". In this response scenario, "The washroom is on your left after exiting the door" is stored as guidance information, and the guidance target is "(normal) washroom". In addition, as textual information, the related information "The multi-functional toilet is on the next floor" is memorized, and the detailed information "Otari is 20 meters to the left after leaving the door." . "Is remembered. The target of related information is "multifunctional toilets", which is different from "(normal) toilets". In this way, when a plurality of guidance targets are assumed as answers in the guidance, the answers regarding the guidance targets different from the guidance targets of the guidance information are stored as related information. For example, a representative answer is stored as guidance information, and other answers are stored as related information.

Further, the response scenario of the scenario ID "002" is a scenario related to "meeting agency". In this response scenario, "Please proceed to the XX meeting room on the XX floor" is stored as guidance information, and as text information, "Please proceed to the XX floor from the elevator on the left", which is detailed information. The meeting room is in front of you after getting off the elevator. " In this way, at least one of the related information and the detailed information is stored as the character information.

In addition, the guidance information in the response scenario may also store a question (preliminary guidance information) for obtaining the information necessary for completing the guidance information. For example, in a scenario related to "meeting agency", it is necessary to determine the content to be guided by the user's name, visited information, and the like. Therefore, the information required for executing the guidance based on each scenario ID is also stored in advance, and in the guidance processing described later, the guidance device 1 outputs the preliminary guidance information when the information is not obtained. Then, when the information is acquired, guidance based on each scenario ID is executed. As described above, there are cases where the response scenario and the guidance information are fixed as in the scenario ID "001", and there are cases where the guidance information changes depending on the situation such as the scenario ID "002". In the former, the guidance information is determined when the scenario is selected, and in the latter, the guidance information is determined by selecting the scenario and acquiring the information necessary for completing the guidance information.

The data in the response scenario table 151 is preset by the administrator of the guidance device 1. Of the data in the response scenario table 151, the guidance information or the character information may be generated by machine learning or the like.

FIG. 4 is an example of the flow of guidance processing executed by the guidance device 1. The guidance process is executed in a state where the character C is displayed on the display unit 11. The guidance processing is realized by the processing unit 16 cooperating with each configuration of the guidance device 1 based on the program stored in the storage unit 15.

First, the monitoring unit 161 executes the monitoring process (S101). The monitoring process is a process of causing the character C displayed on the display unit 11 to perform a monitoring operation. The monitoring operation is an operation in which the character C directs his / her line of sight toward the user.

The monitoring unit 161 causes the character C to perform a monitoring operation based on the captured image. For example, the monitoring unit 161 acquires an captured image from the imaging unit 13 and identifies a person region in the captured image. The person region may be specified based on the feature amount extracted from the pixel value of the captured image, or may be specified by using a trained model in which the relationship between the image and the person region is learned in advance. The feature amount is, for example, a HOG (Histograms of Oriented Gradients) feature amount. The trained model is, for example, YOLO (You Only Look Once) or SSD (Single Shot Detector). The monitoring unit 161 causes the character C to perform a monitoring operation by controlling the display unit 11 so as to cause the character C to perform an operation of directing the line of sight in a direction corresponding to the specified person area.

The monitoring unit 161 may cause the character C to perform a monitoring operation based on the distance image. For example, the monitoring unit 161 acquires a distance image from the distance measuring unit 12 and identifies a person area in the distance image. The person area may be specified based on the feature amount extracted from the three-dimensional shape of the object shown by the distance image, and the relationship between the distance image and the person area may be specified by using a trained model in which the distance image and the person area are learned in advance. May be good. The monitoring unit 161 causes the character C to perform a monitoring operation by controlling the display unit 11 so as to cause the character C to perform an operation of directing the line of sight in a direction corresponding to the specified person area.

The monitoring unit 161 may cause the character C to perform a monitoring operation based on both the captured image and the distance image. For example, the monitoring unit 161 identifies a person area in the captured image, and acquires the distance information associated with the pixel corresponding to the specified person area in the distance image to obtain the distance between the guidance device 1 and the user. Identify. When the specified distance is equal to or less than a predetermined distance, the monitoring unit 161 causes the character C to direct the line of sight in the direction corresponding to the specified person area.

When a plurality of person areas are specified in the captured image or the distance image, the monitoring unit 161 may cause the character C to sequentially direct the line of sight in the direction corresponding to those person areas, and the distance from the guide device 1 may be reduced. The line of sight may be directed in the direction of a small user.

The monitoring unit 161 may cause the character C to perform a monitoring operation based on a plurality of captured images and distance images sequentially acquired. For example, the monitoring unit 161 identifies a person area in each of a plurality of captured images. The monitoring unit 161 associates a plurality of captured images with a person area having a high probability of corresponding to the same user based on the position and size of the specified person area, the pixel value of the pixel in the person area, and the like. And track the user. The monitoring unit 161 determines whether or not the tracking user is approaching the guidance device 1 based on a plurality of distance images, and when it is determined that the tracking user is approaching the guidance device 1, the character. Let C move the line of sight toward the user.

As a monitoring operation, the monitoring unit 161 may cause the character C to turn not only the line of sight but also the entire body. Further, the monitoring unit 161 may further control the audio input / output unit 14 to cause the character C to greet the user as a monitoring operation. As a monitoring operation, the monitoring unit 161 may make another arbitrary operation and utterance to make the character C appear to be guarding the facility.

Subsequently, the detection unit 162 detects a user in the predetermined space (S102). The predetermined space is a space where there is a user to be treated, for example, a space in front of the guide device 1 and a distance from the guide device 1 of a predetermined distance (for example, 2 meters) or less. The predetermined space may be a space separated from the guide device 1 (for example, a space in which the distance from the guide device 1 is 1 meter or more and 3 meters or less).

As described above, the detection unit 162 specifies a person region in the captured image. When the person area is not specified, the detection unit 162 determines that the user in the predetermined space has not been detected.

When the person area is specified, the detection unit 162 specifies the distance between the guidance device 1 and the user corresponding to the specified person area based on the distance image, as described above. The detection unit 162 specifies the position of the user based on the direction of the specified person area and the distance to the user. The detection unit 162 determines that the user in the predetermined space is detected when the position of the user is in the predetermined space, and detects the user in the predetermined space when the position of the user is outside the predetermined space. It is determined that it was not done.

When the user is detected (S102-Yes), the response unit 163 controls the audio input / output unit 14 and the display unit 11 to cause the character C to interact with the user to respond to the user. The process is executed (S103). The details of the response process will be described later. When the user is not detected (S102-No) or when the response process is completed, the monitoring unit 161 restarts the monitoring process (S101).

FIG. 5 is a flow chart showing an example of the flow of the response process.

First, the selection unit 164 selects a response scenario for the detected user based on the utterance by the user (S201). For example, the selection unit 164 acquires the utterance to the audio input / output unit 14 by the detected user as an audio signal. The selection unit 164 converts a voice signal acquired by using a known voice recognition technique into character information, and acquires a word included in the user's utterance by performing morphological analysis or the like. The selection unit 164 refers to the response scenario table 151 and selects a response scenario to which the acquired word is associated as a keyword.

The method of selecting a response scenario is not limited to the above example. The response scenario may be selected using a trained model such as a neural network in which the relationship between the character information corresponding to the user's utterance and the response scenario is learned in advance.

Here, when the information necessary for completing the guidance information is not obtained, the selection unit 164 outputs a question (preliminary guidance information) regarding the information from the audio input / output unit 14 as an utterance by the character C. For example, when the response scenario with the scenario ID "002" is selected and the "user's name" or "visit destination information" is not obtained, the selection unit 164 "customer's name and visit". Please let me know the destination. " Then, the selection unit 164 determines the guidance information based on the information obtained from the user. For example, the guidance device 1 stores a list of meeting information (user, meeting place, etc.) in advance in the storage unit 15, and the selection unit 164 collates the information obtained from the user with the list. , Decide the meeting place to guide. As a result, even if the guidance information is different for each user, it is possible to provide guidance according to the user.

Subsequently, the response unit 163 outputs the guidance information as an utterance by the character C from the voice input / output unit 14, and displays the character information supplementing the guidance information on the display unit 11 (S202). For example, the response unit 163 acquires guidance information and related information associated with the selected response scenario. The response unit 163 converts the acquired guidance information into an audio signal, outputs it as an utterance of the character C from the audio input / output unit 14, and displays the acquired related information on the display unit 11. The response unit 163 may display detailed information instead of the related information.

FIG. 6 is a diagram for explaining the character information displayed on the display unit 11. In the example shown in FIG. 6, the character information 111 is displayed at the upper part of the display unit 11. The display mode of the character information 111 is not limited to such an example. For example, the character information 111 may be displayed at an arbitrary position on the display unit 11, or may be displayed in a manner as if the character C is speaking by using a blowout or the like.

As described above, the guidance device 1 outputs the guidance information to the user as an utterance by the character C and displays the character information supplementing the guidance information in the response to the user in the predetermined space. As a result, the guidance device 1 makes it possible to facilitate guidance to the user. That is, when the related information or the detailed information supplementing the guidance information is output as the utterance of the character C, the user must wait until all the information is heard. On the other hand, the guidance device 1 displays related information and detailed information as text information, thereby shortening the waiting time of the user while realizing communication by dialogue, and realizing smooth guidance.

Further, the guidance device 1 selects a response scenario for the user from a plurality of response scenarios based on the utterance by the user, outputs guidance information based on the selected response scenario, and displays character information. As a result, the guidance device 1 can facilitate guidance on matters requested by the user.

Further, the guidance device 1 outputs information in which character information is simplified as guidance information. Since detailed information is easier to understand when it is displayed as text information than when it is output by utterance, this makes it easier for the user to understand the guidance and realizes smooth guidance.

In the above description, the guidance device 1 selects the response scenario in S201, but the present invention is not limited to such an example, and the guidance device 1 does not have to select the response scenario. For example, the guidance device 1 outputs general guidance information such as "The reception is on the right hand side" to the user detected in the predetermined space in the response processing, and supplements the guidance information. Related information or detailed information may be displayed as text information.

Further, the guidance device 1 may have a configuration for measuring the body temperature of a user such as a thermal image camera. In this case, if the guidance device 1 determines in the response process that the user detected in the predetermined space has a body temperature above the predetermined temperature (for example, 37.5 degrees or higher), "there is a suspicion of fever. Even if the guidance information such as "Please proceed to the inspection area" is output as an utterance and the detailed information that supplements this guidance information in detail, that is, "The partition on the left is the inspection area" is displayed as text information. good.

In the above description, one character information is displayed, but the present invention is not limited to such an example, and the response unit 163 is a plurality of related information or detailed information associated with the selected response scenario in S202. The character information of may be displayed on the display unit 11.

Further, the response unit 163 may select any character information from the plurality of character information and display it on the display unit 11 based on the attribute of the user. In this case, in the response scenario table 151, the attributes of the user targeted by the character information are associated with the plurality of character information in advance. For example, when the attributes of the user are male, female, children, etc., the attribute of "male" is associated with the text information that guides the men's toilet, and the text information that guides the multi-function toilet is ". The "with children" attribute is associated.

In S202, the response unit 163 identifies the attributes of the user based on the image captured from the image pickup unit 13. The attribute may be specified, for example, based on the feature amount extracted from the pixel value of the captured image, or the relationship between the image and the attribute may be specified using a trained model trained in advance. Further, the attribute may be specified based on the distance image acquired from the distance measuring unit 12 or the audio signal acquired from the audio input / output unit 14.

The response unit 163 refers to the response scenario table 151 and selects the character information associated with the specified attribute. The response unit 163 outputs the guidance information associated with the selected response scenario as an utterance, and displays the selected character information. By doing so, the guidance device 1 makes it possible to facilitate guidance suitable for the attributes of the user.

In the above description, the guidance device 1 returns to S101 to execute the monitoring process after the response process is completed, but may return to S102 to detect the user in the predetermined space. As a result, the guidance device 1 makes it possible to facilitate guidance when there are a plurality of users in a predetermined space or when a specific user continuously desires guidance.

In the above description, the response unit 163 outputs the guidance information as an utterance by the character C in the response processing of S103, and displays the character information supplementing the guidance information, but the present invention is not limited to such an example. .. In the response unit 163, when the content to be spoken by the character C is specified based on the user's utterance (for example, when the response scenario is selected or the guidance information is determined), the user's utterance continues. If not, the guidance information is output as the utterance by the character C, and if the utterance by the user continues, the text corresponding to the guidance information is displayed as the text information without the utterance by the character C. May be good.

In this case, the storage unit 15 stores the response scenario table 151a. Further, the response unit 163 executes the second response process described later in S103.

FIG. 7 is a diagram showing an example of the data structure of the response scenario table 151a. The response scenario table 151a stores the scenario ID, the description, the keyword, and the guidance information in association with each other. That is, the response scenario table 151a is different from the response scenario table 151 of FIG. 3 in that it is not necessary to store the character information.

FIG. 8 is a flow chart showing an example of the flow of the second response process.

First, the selection unit 164 selects a response scenario for the detected user in the same manner as in S201 (S301).

Subsequently, the response unit 163 determines whether or not the utterance by the user continues (S302). For example, in the response unit 163, when the voice input to the voice input / output unit 14 is continued or the interruption of the voice input is less than a predetermined time (for example, 3 seconds), the utterance by the user is continued. It is determined that the utterance is not continued when the interruption is for a predetermined time or longer. The continuous voice input means that the volume of the voice input indicated by the voice signal supplied by the voice input / output unit 14 is continuously equal to or higher than a predetermined value, and the voice input is interrupted. , It means that the volume of the voice input is less than the predetermined value.

When it is determined that the utterance by the user is continuing (S302-Yes), the response unit 163 displays the text information corresponding to the guidance information associated with the selected response scenario on the display unit 11 as text (S302-Yes). S303), the response process is terminated. When it is determined that the utterance is not continued (S302-No), the response unit 163 outputs the guidance information associated with the selected response scenario from the voice input / output unit 14 as an utterance by the character C (S304). End the response process.

When it is determined that the response process is not completed at the stage where the guidance information is displayed as character information on the display unit 11 and the user's utterance is not continued, the guidance information is used as the character C's utterance in the voice input / output unit. You may output from 14 and end the response process. As a result, it is possible to communicate by voice dialogue while promptly transmitting guidance information.

By doing so, the guidance device 1 can present the guidance information to the user without interrupting the utterance of the user, so that the guidance to the user can be facilitated.

In the above description, the character information displayed in S303 and the guidance information output in S304 are the same information, but the information is not limited to such an example, and both may be different information. For example, the character information displayed in S303 may be related information or detailed information of the guidance information displayed in S304.

In addition, if the information required to complete the guidance information is insufficient, the guidance device 1 is a question for which an answer to the information is requested. Preliminary guidance information (for example, "Notify the customer's name and destination". Please. ") Is preferably displayed as text information. As a result, it is possible to obtain information necessary for guidance without interrupting the user's utterance, so that guidance to the user can be facilitated.

Although the description has been made assuming that the character information is displayed on the display unit 11, the description is not limited to this. For example, a projection device such as a projector may be provided to project and display the selected character information on a wall surface, a floor, or the like.

Further, the guide device 1 may be shown to the user that the user is in a state of accepting the voice input at the timing when the user approaches the guide device 1. For example, when the monitoring process is switched to the response process, the display unit 11 displays an icon indicating the surrounding environmental sound, a voice collecting state, a schematic waveform indicating the sound collecting level, and the like. Alternatively, the icon related to voice recognition may be always displayed, and the display of the icon may be changed so as to indicate that the voice input is being accepted when the response processing is switched. As a result, the user can grasp that he / she has been recognized by the guidance device 1 and can also grasp that the character C is accepting the voice input, so that he / she can speak naturally.

It will be appreciated by those skilled in the art that various changes, substitutions and modifications can be made to this without departing from the spirit and scope of the invention. For example, the processes of the above-mentioned parts may be executed in different orders as appropriate within the scope of the present invention. Further, the above-described embodiments and modifications may be carried out in appropriate combinations within the scope of the present invention.

1 Guidance device 11 Display unit 12 Distance measurement unit 13 Imaging unit 14 Audio input / output unit 15 Storage unit 161 Monitoring unit 162 Detection unit 163 Response unit 164 Selection unit

Claims (5)

A display unit that displays a character image and
A detector that detects a person in a predetermined space,
An audio input / output unit that outputs utterances by the character as voice and receives utterances by the detected person as voice input.
It has a response unit that controls the audio input / output unit and the display unit to cause the character to interact with the detected person to respond to the person.
In the response, the response unit outputs guidance information for the person from the voice input / output unit as an utterance by the character, and displays character information supplementing the guidance information on the display unit.
An interactive guidance device characterized by this. A storage unit that stores multiple response scenarios,
Further, it has a selection unit for selecting a response scenario for the person from the plurality of response scenarios based on the utterance by the person.
In the response, the response unit outputs the guidance information by voice and displays the character information based on the selected response scenario.
The interactive guidance device according to claim 1. The response unit displays, as the character information, related information related to the guidance information and related to a guidance target different from the guidance target of the guidance information.
The interactive guidance device according to claim 1 or 2. The response unit displays detailed information in detail of the guidance information as the character information.
The interactive guidance device according to claim 1 or 2. A display unit that displays a character image and
A detector that detects a person in a predetermined space,
An audio input / output unit that outputs utterances by the character as voice and receives utterances by the detected person as voice input.
It has a response unit that controls the audio input / output unit and the display unit to cause the character to interact with the detected person to respond to the person.
In the response, when the utterance by the person is not continued, the response unit outputs guidance information for the person as the utterance by the character from the voice input / output unit, and the utterance by the person continues. In that case, the character information corresponding to the guidance information for the person is displayed as text on the display unit.
An interactive guidance device characterized by this.

Images