JPH07325868A - Visitor guiding system - Google Patents

Abstract

PURPOSE:To facilitate operations by a visitor similarly to an attended reception job. CONSTITUTION:When video images photographed by a CCD camera 3 and stored in an image memory 8 are analyzed by a knowledge processing part 9 and the arrival of the visitor is recognized, the data of the expression of a smile are taken out from a face image data base 13 and displayed on a display 1. At the time, the visitor pushes the selection key of a display device 2 with keys and specifies a visiting party corresponding to the voice guidance of a speaker 4 by a voice data base 14. Then, the data of a speech for reporting the arrival of the visitor are taken out from the voice data base 14 and transmitted to a telephone set 7 by a telephone control part 12. Then, corresponding to selection by the push buttons of the telephone set 7 or the like, when the visiting party is present, the message of that effect is outputted along with the face image of the expression of the smile. On the other hand, when the visiting party is not present, the message of that effect is outputted along with the face image of the expression of slight sadness.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a visitor guidance system that enables unmanned reception work in office buildings and the like.

[0002]

2. Description of the Related Art Conventionally, there is a system that enables unmanned reception work regardless of the receptionist. This type of system temporarily stores the image input from the CCD camera in the image memory, and analyzes the image by the knowledge processing unit to detect the arrival of the visitor. When the visitor is detected, the knowledge processing unit conveys various guidance information to the visitor by synthesizing a voice signal in the voice synthesizing unit or displaying characters on the keyed display device. Then, the visitor interactively obtains the guidance information while inputting the data through the keyed display device. On this occasion,
When a visitor enters the data of the other party with whom he / she is going to meet, the system connects the other party to the call and establishes a call with the visitor. When the call ends, the visitor inputs the subsequent processing in response to the question from the system, and the system transmits the guidance information to the visitor by the input (see, for example, JP-A-5-216888).

[0003]

However, the above-mentioned conventional techniques have the following problems. That is, in the device having the above configuration, when a visitor is unfamiliar with the machine, there is still a feeling of discomfort or anxiety about the operation of the machine only by exchanging information by characters or voices, and it is not a substitute for reception guidance by humans. Therefore, it was difficult for the unmanned person to smoothly proceed with the reception work. In addition, when it is known that a visitor will come in advance and you are ready to respond immediately, in the case of a manned person, you can accept the reception by a simple telephone exchange between the receptionist and the person in the office. I was able to do it, but when I left it unattended, the visitor had to call himself to talk to someone in the office. Further, in an office or the like where many people come and go, it takes a lot of time to recognize each other when the visitor and the respondent do not know each other.

[0004]

The visitor guidance system of the present invention is characterized by the following points in order to solve the above-mentioned problems. (1) A face image database storing face image data is provided. A face image synthesizing unit for synthesizing a face image with the data extracted from the face image database is provided. A display for displaying the face image output from the face image synthesis unit to the visitor is provided. A voice database storing voice data corresponding to a face image is provided. A voice synthesizing unit for synthesizing a voice with the data extracted from the voice database is provided.

A speaker for outputting the voice output from the voice synthesizer is provided. The voice of the speech according to the processing result for the instruction input from the input operation unit is taken out from the voice database, the voice is synthesized by the voice synthesis unit and output from the speaker, and the face image of the facial expression corresponding to the voice is stored in the face image database. And a knowledge processing unit for performing processing of synthesizing the face images by the face image synthesizing unit and displaying on the display. A telephone that sends the voice data extracted from the voice database to the destination telephone specified by the input from the input operation unit via the voice synthesizer and sends the response input from the destination telephone to the knowledge processing unit. A control unit is provided.

(2) The face image database stores the data of the face image of the responder who responds to the visitor, the voice database stores the data of the voice of the respondent, and the knowledge processing unit stores the data of the visitor. When a visitor is absent, a display and a speaker are used to introduce the visitor to the visitor, instead of the visitor's visitor, through the image synthesizer and the voice synthesizer. The message database and the character synthesizing unit may be provided so that the character output may be performed by the display instead of the voice output by the speaker.

[0007]

[Action]

(1) When a still image is displayed on the image captured by the image capturing unit, the knowledge processing unit recognizes that the visitor has appeared. At this time, for example, smiley face expression data is retrieved from the face image database and displayed on the display. Further, guidance input dialogue data of the visitor is retrieved from the voice database, and voice is output from the speaker. As a result, the visitor is visually guided by audio and is also visually guided. After this, the visitor specifies the visitor by pressing the selection key. When the visitor completes the designated input, the data of the confirmation line of the visitor is retrieved from the voice database and the voice is output from the speaker.
When the visitor confirms the visitor, the speech data requesting that the visitor wait for the call processing of the visitor is retrieved from the voice database, and the voice is output from the speaker.
Thereafter, the expressionless data is retrieved from the face image database and displayed on the display.

When calling the person to be visited, the data of the line telling that the visitor has come is retrieved from the voice database, the telephone is ringed by the telephone controller, and the voice is output when the answerer picks up the receiver. To be done. At this time, the presence or absence of the person to be visited is selected by the push button or the like of the telephone. The selection result is transmitted to the knowledge processing unit via the telephone control unit. When the person you are visiting is present, the facial expression data is retrieved from the face image database and displayed on the display, and the line data that tells you that the person is responding is retrieved from the voice database and the voice is output from the speaker. To be done.
If there is no person to visit, the data of the expression of a slight sadness is retrieved from the face image database, displayed on the display, and the data of the line telling that the person is absent is retrieved from the voice database,
Sound is output from the speaker. As a result, it is possible to visually inform the visitor of the location of the visitor together with the voice.

(2) In (1), when there is no person to visit, the knowledge processing section retrieves the face image data of the substitute respondent from the face image database and displays it on the display. In addition, the data of the voice of the other respondent is taken out from the voice database and output from the speaker. As a result, the visitor is previously introduced to the substitute responder before the visitor visits the substitute respondent. By displaying characters on the display instead of the sound from the speaker, it is possible to provide reception guidance even when the visitor is a hearing impaired person, etc. This can reduce the discomfort of visitors to the machine.

[0010]

The present invention will be described in detail below with reference to the embodiments shown in the drawings. In the following description, a person who visits an office or the like and uses the system is called a visitor, and a person whom the visitor is going to meet is called a visitor. In addition, a person who handles a visitor, including a visitor, is called a responder. FIG. 1 is a block diagram showing an embodiment of a visitor guidance system of the present invention. The illustrated system includes a display 1, a display device with keys 2, a CCD camera 3, a speaker 4, a telephone 5, a knowledge processing unit 9, a voice synthesis unit 10, an image synthesis unit 11, a telephone control unit 12, a face image database 13, Voice database 1
It has 4 etc.

The display 1 is composed of a CRT, a liquid crystal display device or the like, and displays the face image combined by the image combining unit 11. The display device 2 with a key is configured by providing a touch panel or the like on a CRT or a liquid crystal display device, and the touch panel or the like serves as a key. Under the control of the knowledge processing unit 9, the character information is displayed and the key input is accepted.
The CCD camera 3 is installed above or around the display 1 so that a person in front of the display 1 can be photographed. The video output from the CCD camera 3 is digitized, and the image memory 8 is used for image processing.
Is temporarily stored in. The speaker 4 is the voice synthesizer 10
The audio electrical signal output from is converted into audio and output.

The telephone 5 is connected to the telephone controller 12 and is also connected to the telephone 7 in the office via the telephone line 6 so that it is possible to talk with a person in the office. The knowledge processing unit 9 is composed of a processor and the like, and performs various kinds of knowledge processing. For example, by comparing an image stored in the image memory 8 with a background image, an intruding object is detected by detecting a change from the background image. Further, by detecting that the change of the intruding object disappears, it is detected that the intruding object stands still in front of the display 1. Then, the output of the character information to the keyed display device 2 is controlled, and the key input from the keyed display device 2 is received. It also controls the image synthesis unit 11, the voice synthesis unit 10, and the telephone control unit 12. Furthermore, it monitors and controls the program of all of these.

The voice synthesizing unit 10 is composed of a processor or the like, synthesizes a voice signal under the control of the knowledge processing unit 9, and transmits the synthesized voice signal to the speaker 4 and the telephone control unit 12. The image synthesizing unit 11 is composed of a processor or the like, and synthesizes images of face images under the control of the knowledge processing unit 9 and displays them on the display 1. The telephone control unit 12 is composed of a processor or the like, connects a telephone from the telephone 5 to the visitor under the control of the knowledge processing unit 9, and receives a signal output by a touch-tone telephone or the like from the telephone 7 of the visitor through the telephone line 6. The face image database 13 is composed of a magnetic disk device or the like, and has personal data of human faces in the office.
This personal data can be searched by the ID number, and the searched data is combined with the face image by the image combining unit 11.

The voice database 14 is composed of a magnetic disk device or the like, and stores personal data of voice of a person in the office. This personal data is also I
You can search by D number. FIG. 2 shows the appearance of the visitor reception device in the system of FIG. The face image synthesized by the image synthesizing unit 11 is displayed on the display 1 on the front side, which plays the role that the receptionist bears when this is manned. In front of the display 1,
A display device with a key is provided. A CCD camera 3 that detects the presence of a visitor is provided above the display 1. A speaker 4 is provided on the side of the keyed display device 2, and a telephone 5 is provided on the side of the display 1.

Next, the operation of the system shown in FIG. 1 will be described. FIG. 3 is a flowchart showing the processing of the entire system, and the processing of the system is roughly divided into three stages. These are a part that recognizes that a visitor has visited the office (step S301), and a part that explains the procedure to the visitor when the visitor is going to meet (step S302). This is a part where the system informs the visitor that the visitor has arrived and informs the visitor of the intention of the visitor (step S303).

FIG. 4 is a flow chart of the processing of the visitor recognition portion, FIG. 5 is a flow chart of the processing of the designated portion of the visitor, and FIGS. 6 to 9 are flow charts of the processing of the calling portion of the visitor. . First, the operation of the recognition part of the visitor will be described with reference to FIG. First, as an initial setting, a faceless front face image is combined (step S401). Next, an intruding object is detected in front of the display 1 by taking a difference between the background image having no intruding object and the current image (step S402).
When an intruding object is detected, it is determined whether the object is stationary in front of the display 1 (step S40).
3) If it is stationary, a face image with a smiling expression is combined (step S404). Then, the dialogue that asks whether or not the visitor is output is output (step S
405). An example of the line is "Please push the button if you need it." If it is a visitor, the process proceeds to the next stage, it is determined whether or not a key is pressed by the keyed display device 2 (step S406), and if there is no reaction for a certain time (step S407), the stationary object is not a visitor. And the process of detecting a stationary object is repeated (step S401).

Next, the operation of the designated part of the visited partner will be described with reference to FIG. First, a face image in which the line of sight is directed to the keyed display device 2 is synthesized (step S501), and guidance is provided by a dialog prompting the designation of a visited place (step S502).
An example of the line is "Welcome. Please specify the place to visit." The search for a visitor is performed interactively by repeating voice instructions and display and input on the keyed display device 2 (step S503). When the search is completed (step S504), guidance is given by a dialog prompting confirmation of whether or not the designated visitor can be called (step S505). As an example of dialogue, "*
I will go to *. is this good. , Etc.
When the visitor confirms the visitor (step S50)
6) The face image with the line of sight directed to the visitor is synthesized, and the system guides the user with a dialogue to the effect that the visitor should wait a little for contacting the visitor (step S50).
5). An example of the line is "Please wait a moment." Then, in order to communicate with the person to be visited at the next stage, an expressionless face image with a lowered line of sight is synthesized (step S508).

Finally, the calling portion of the visitor is shown in FIG.
This will be described with reference to FIG. In FIG. 1, the speech synthesizer 1
The synthesized voice signal of 0 is reproduced by the speaker of the telephone 7 of the visitor, and the visitor sends a control signal to the knowledge processing unit 9 via the telephone controller 12 by pressing a button of the telephone 7. The detailed processing procedure of the knowledge processing unit 9 at this time is shown in FIGS. The knowledge processing unit 9 first calls the visitor designated by the visitor (step S
601), The words which tell the arrival of the visitor are combined (step S602). An example of this line is "*
* We are looking forward to seeing you. , Etc. As a result, the visitor selects either processing in which the person himself / herself responds, a substitute person responds, or talks with the visitor by telephone, and informs the knowledge processing unit 9 (step S603,
S604). In this case, in order to prevent the visitor from making a selection mistake, the knowledge processing unit 9 synthesizes a dialogue prompting the visitor to confirm the option (steps S605, S606, S60).
7) Confirmation is performed (steps S608, S609, S
610). When it is selected that a person instead of the person to visit visits to answer, the knowledge processing unit 9 accepts the input of the ID number of the answerer (step S701), and confirms who will respond.

When the person visiting the person chooses to respond, he or she synthesizes a face image with a smiling face with a line of sight to the visitor (steps S611 and S612), and outputs a line telling that the person responds. Yes (step S61
3). An example of a line is "I will come soon, so please wait a while." After that, the ID of the visitor
The face image data is retrieved from the face image database 13 by the number (step S614), and the face image is changed to the person's face (step S615). Similarly, the voice is changed to that of the visitor (step S616), and "I am **
is. I'll come right now. ", Etc. are output to make the visitor recognize the image of the face and voice of the visitor.

On the other hand, in step S604, if the substitute person chooses to respond because the visitor is absent or the like, he / she turns his line of sight to the visitor and expresses the expression of slight sorrow, which means an apology. After synthesizing, a facial expression in which the line of sight is directed downward is synthesized while outputting at 15 a message telling that the person to be visited is absent (steps S702 to S702).
704). An example of a line is "Sorry, but ** is absent." Next, a face image with a smiling face with a line of sight directed to the visitor is synthesized, and a line is output to notify that a substitute person will respond (steps S705 to S707). An example of a dialogue is "Please wait, because a substitute will come."
After that, the face image data is retrieved from the face image database 13 by the ID number of the respondent (step S708),
The face image is changed to the face of the respondent (step S70).
9). Similarly, the voice is also changed to that of the respondent (step S710), and "I am **. I will come."
Introduce by the lines such as, and let the visitors recognize the image of the face and voice of the respondent.

[0021] When the other party chooses to talk to the visitor by telephone, a face image with a smiling face with a line of sight toward the visitor is synthesized, and a line for guiding the user to pick up the receiver is output. While synthesizing the face image with the line of sight facing the telephone (steps S801 to S804). Next, an expressionless face image with the eyes directed downward is synthesized (step S80).
5) Wait for the signal from the person you are visiting. When the telephone conversation between the visitor and the visitor is over (step S806), the visitor selects either a response or a return to the knowledge processing unit 9 (step S8).
07-S809). In this case, in order to prevent the visitor from making a selection mistake, a line is output to encourage the visitor to confirm the options.

When the respondent chooses to respond,
Knowledge processing unit 9 accepts the input of the ID number of the respondent (step S904), and recognizes who will respond. In this case, a face image with a smiling expression with a line of sight directed to the visitor is synthesized (steps S902 and S903), and a dialogue such as "please wait a moment" is used to guide the arrival of the respondent (step S904). After that, the respondent I
The face image data is converted into the face image database 13 by the D number.
(Step S905), and the face image is changed to that of the respondent (step S906). Similarly, the voice is also changed to that of the respondent (step S907), and introduction is made by a predetermined line so that the visitor recognizes the image of the face and voice of the respondent.

On the other hand, in the case where the visitor returns as it is in step S809 of FIG. 8, a face image with a smiling face with a line of sight toward the visitor is synthesized, and a farewell greeting line is output while the line of sight is directed downward. To do. Examples of lines are:
"We are looking forward to seeing you again." When the above visitor guidance is completed, the process returns to the visitor recognition part in FIG. In this way, it is possible to provide the visitor with the same detailed guidance as the receptionist.

FIG. 10 shows changes in the facial expression of the face image at each processing stage described above. The expression of the face image displayed on the display 1 is usually expressionless as shown in FIG.
However, when it is recognized that the visitor appears by the image taken by the CCD camera 3, FIG.
A face image with a smiling face like is displayed. Following this, when the visitor completes the designated input of the visitor,
As shown in 0 (b), he returns to expressionless again. During this time, the person to be visited is called, and the person in the office informs the knowledge processing unit 9 whether or not there is the person to visit. When the person to be visited is present, the smiling expression of FIG. 10 (a) is displayed. When there is no person to visit, a slight expression of sadness is displayed as shown in FIG. After that, the face image of the substitute respondent is displayed.

Further, when the person himself or his or herself or a substitute respondent chooses to respond by telephone, the position of the telephone 5 is indicated by the line of sight as shown in FIG. 10 (d). In this way, according to the change in the facial image, the same guidance as that of the receptionist is given, and the substitute respondent is also introduced. The present invention is not limited to the above-mentioned embodiment,
Of course, various modifications are possible. For example, in the above-described embodiment, the photographing means is used only to detect the presence or absence of a visitor at a predetermined place, but in order to photograph the face of the visitor and send the image to the visitor. You may use.

[0026]

As described above in detail, in the present invention, the display of the facial image having the facial expression is introduced in the visitor guidance system which has been conventionally performed only by the characters and the voices. Even if the user is not accustomed to the machine, it is possible to reduce anxiety about the operation of the machine and use the machine with peace of mind. Also, since the system directly processes signals from people in the office, the procedure for visitors can be simplified. Furthermore, by presenting the face and voice of the respondent to the visitor, the visitor can easily identify the respondent even if the visitor and the respondent do not know each other.

[Brief description of drawings]

FIG. 1 is a block diagram of an embodiment of a visitor guidance system of the present invention.

FIG. 2 is an external view of a visitor reception device of the system of the present invention.

FIG. 3 is a flowchart illustrating a processing procedure of the entire system.

FIG. 4 is a flowchart illustrating a processing procedure of a recognition portion of a visitor.

FIG. 5 is a flowchart illustrating a processing procedure of a designated portion of a visiting party.

FIG. 6 is a flowchart (No. 1) for explaining the processing procedure of the calling portion of the called party.

FIG. 7 is a flowchart (No. 2) for explaining the processing procedure of the calling portion of the called party.

FIG. 8 is a flowchart (No. 3) for explaining the processing procedure of the calling portion of the called party.

FIG. 9 is a flowchart (No. 4) for explaining the processing procedure of the calling portion of the called party.

FIG. 10 is an explanatory diagram of changes in facial expressions of a face image.

[Explanation of symbols]

 1 Display 4 Speaker 9 Knowledge Processing Section 10 Voice Synthesis Section 11 Image Synthesis Section 12 Telephone Control Section 13 Face Image Database 14 Voice Database

Claims (3)

[Claims] 1. A face image database storing face image data, a face image synthesizing unit for synthesizing a face image with data extracted from the face image database, and a face image output from the face image synthesizing unit. A display, a voice database storing voice data corresponding to the face image, a voice synthesizing unit for synthesizing voices by the data extracted from the voice database, and a speaker for outputting voices output from the voice synthesizing unit. And, the voice of the speech corresponding to the processing result for the instruction input from the input operation unit is retrieved from the voice database,
The voice is synthesized by the voice synthesizer and output from the speaker, and a face image having an expression corresponding to the dialogue is taken out from the face image database, and the face image synthesizer synthesizes the face image to display on the display. The knowledge processing unit that performs a display process and the telephone data of the other party designated by the input from the input operation unit transmit the voice data extracted from the voice database through the voice synthesis unit to the other party's telephone. A visitor guidance system, comprising: a telephone control unit that sends a response input from the device to the knowledge processing unit. 2. The face image database stores data of face images of a responder who responds to the visitor, the voice database stores data of voice of the respondent, and the knowledge processing unit stores the visitor's voice. When the visitor of the visitor is absent, the display and the speaker are used to introduce the visitor to the visitor through the image synthesizer and the voice synthesizer instead of the visitor of the visitor. The visitor guidance system according to claim 1. 3. A face image database storing face image data, a face image synthesizing unit for synthesizing a face image with data extracted from the face image database, a message database storing message data in characters, A character synthesizing unit for synthesizing display characters based on the data retrieved from the message database, a display for displaying a face image output from the face image synthesizing unit and characters output from the character synthesizing unit, and an input operation unit. Take out the serif characters according to the processing result for the specified instruction from the message database,
The character is synthesized by the character synthesizing unit and displayed on the display, and a face image having an expression corresponding to the serif is taken out from the face image database, and the face image synthesizing unit synthesizes the face image on the display. The knowledge processing unit that performs the display process, and the voice data extracted from the voice database is transmitted to the destination telephone device specified by the input from the input operation unit through the voice synthesis unit, and the destination telephone device transmits the voice data. A visitor guidance system, comprising: a telephone control unit for sending an input response to the knowledge processing unit.