JP2023123165A - intercom device - Google Patents

Abstract

To provide an intercom device that can ensure the privacy and security of residents.SOLUTION: An intercom device 1 includes an image acquisition unit 32 that acquires a captured image captured by an imaging unit 11 that captures an image of a visitor, a determination unit 33 that determines at least one of whether the visitor has been recognized and whether the visitor is a registrant who has been registered in advance, on the basis of the captured image acquired by the image acquisition unit 32, and a response voice selection unit 34 that selects a response voice to be output from a slave unit side audio output unit 14 of a slave unit 10 according to a result of the determination from the determination unit 33, and outputs the selected response voice to the slave unit side audio output unit 14.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to an intercom device.

2. Description of the Related Art There is known an intercom device that authenticates a visitor based on a captured image captured by a camera of a visitor performing a calling operation for calling a resident using an intercom handset installed outside the residence.

In Patent Document 1, after a certain period of time has passed without a response from the resident after receiving a calling operation, the CPU of the base unit shifts to a special operation mode and authenticates the visitor using the captured image of the camera provided in the entrance cordless handset. and, after authenticating the visitor, forming a communication path between the entrance slave unit and the handy base unit, and then unlocking the electric lock after a certain period of time without any response. According to the technique described in Patent Document 1, if the visitor is a welfare worker, when the call is made from the entrance handset, the call can be made even without the resident's answering operation, and the electric lock of the entrance is enabled. Unlocking is also possible, enabling quick response without waiting for the response of the resident's family or the like.

Further, in Patent Document 2, an interphone system includes an interphone base unit provided in a first management area, an interphone slave unit provided in a second management area, and a signal output unit, a control method, and a program are disclosed. The signal output unit outputs an unlock signal for unlocking the opening/closing member that separates the first management area and the second management area. The interphone base unit has at least one of a base unit side display unit and a recording unit. The master-side display unit displays at least one of the first image and the second image, and the recording unit records at least one of the first image and the second image. When the signal output unit outputs the unlocking signal, the intercom master unit performs at least one of display by the master unit side display unit and recording by the recording unit during the extension period. According to the technology described in Patent Literature 2, it is possible to strengthen the monitoring of the second management area.

JP 2016-32212 A

JP 2019-140618 A

However, in the technique described in Patent Document 1, when a visitor is registered in advance, it is possible to make a call even if the resident does not respond. has not been disclosed.

In the technique described in Patent Document 2, it is described that the captured video is recorded based on the result of face authentication. It does not disclose how to deal with a suspicious person who takes action.

Therefore, with these technologies, if the visitor is a person who is not registered in advance (a person who is not an acquaintance or a suspicious person), by listening to the voice uttered by the resident, it is possible to identify the resident's individual such as gender. There is a security problem that the information may be guessed and the fact that the resident is at home may be known.

The present disclosure has been made to solve such problems, and aims to provide an intercom device capable of ensuring the privacy and security of residents.

An intercom device according to one embodiment is an intercom device that includes an intercom slave unit used by a visitor, and includes an image acquisition unit that acquires an image captured by an imaging unit that captures an image of the visitor, and an image acquisition unit. a determination unit that determines at least one of whether the visitor has been recognized and whether the visitor is a pre-registered registrant based on the captured image acquired by; a response voice selector that selects a response voice to be output from the slave unit side voice output unit of the intercom slave unit and outputs the selected response voice to the slave unit side voice output unit.

According to the present disclosure, it is possible to provide an intercom device that can ensure the privacy and security of residents.

1 is a block diagram showing a configuration of an intercom device according to Embodiment 1; FIG. 2 is a flowchart for explaining the operation of the intercom device shown in FIG. 1;

Embodiment 1
Hereinafter, this embodiment will be described with reference to the drawings. Also, for clarity of explanation, the following description and drawings are simplified as appropriate. What is shown in the drawing is a part of the whole, and actually includes many other configurations not shown. Furthermore, in the following description, the same or equivalent elements are denoted by the same reference numerals, and overlapping descriptions are omitted.

As one preferred embodiment of the intercom device according to the present embodiment, an intercom device 1 applied to a detached house will be described. In addition, the intercom device 1 may be applied to collective housing such as condominiums, and may be applied to non-residential facilities, etc., in addition to detached houses.

First, the configuration of the intercom device 1 will be described with reference to FIG. FIG. 1 is a block diagram showing the configuration of an intercom device according to a first embodiment. As shown in FIG. 1, the intercom device 1 includes an intercom master unit (hereinafter referred to as master unit 20) installed in a living room or the like in a dwelling and an intercom slave unit (hereinafter referred to as slave unit 20) installed in an entrance or the like outside the dwelling. 10) and The parent device 20 is a user interface used by the resident to respond to a call from the child device 10 or the like. The handset 10 is a user interface used by a visitor to call and talk to a resident.

Parent device 20 and child device 10 are configured to be able to communicate with each other. Also, the intercom device 1 may include one or a plurality of slave units 10 . In the intercom device 1, after the visitor presses the call button of the handset 10, when the resident presses the call start button of the master device 20 to answer the call, a call path is formed to connect the master device 20 and the slave device. It is possible to talk with 10.

The intercom device 1 according to the present embodiment has a response voice control device 30 including an image acquisition section 32 , a determination section 33 and a response voice selection section 34 . The image acquisition unit 32 acquires a captured image captured by the imaging unit 11 that captures an image of the visitor. Based on the captured image acquired by the image acquisition unit 32, the determination unit 33 determines at least one of whether the visitor has been recognized and whether the visitor is a registrant registered in advance. The response voice selection unit 34 selects a response voice to be output from the slave device side voice output unit 14 of the slave device 10 according to the determination result of the determination unit 33, and outputs the selected response voice to the slave device side voice output unit 14. do.

Details of the intercom device 1 will be described below by exemplifying a case where the function of the response voice control device 30 is configured integrally with the master device 20 . However, the function of the response voice control device 30 may be provided in a device independent of each of the parent device 20 and the child device 10, or may be distributed and provided in a plurality of devices. At least part of the functions of the response voice control device 30 may be implemented by, for example, a cloud (cloud computing) or the like.

(Handset 10)
The child device 10 includes an imaging unit 11, a child device side operation unit 12, a child device side sound pickup unit 13, a child device side audio output unit 14, a child device side communication unit 15, and a child device side control unit 16. there is

The imaging unit 11 is a camera for imaging an imaging area. The imaging unit 11 has an imaging element such as a CCD (Charge Coupled Devices) or a CMOS (Complementary Metal-Oxide Semiconductor) and an optical system such as a lens. The imaging unit 11 is provided at a position where the face of the visitor who operates the handset 10 can be imaged. The imaging unit 11 generates a captured image of calling. "During a call" is a period from the start to the end of a call, and is set, for example, to a period from when the call button is pressed by the visitor until a predetermined period elapses. The imaging unit 11 transmits the captured image as an image signal to the parent device 20 or the response voice control device 30 via the child device side communication unit 15 .

Further, although the imaging unit 11 of the present embodiment is a camera that captures moving images, it may be a camera that captures still images. Furthermore, although the imaging unit 11 of the present embodiment is a camera that captures color images, it may be a camera that captures monochrome images. Note that the imaging unit 11 may be provided separately from the housing of the child device 10 .

The handset-side operation unit 12 accepts the visitor's input operation. The handset side operation unit 12 has input devices such as buttons including a call button. The handset-side operation unit 12 allows the visitor to call the resident by pressing a call button included in the handset-side operation unit 12 . When accepting the operation of the call button by the visitor, the handset 10 transmits a call signal (control signal) for calling the resident in the residence from the handset side communication unit 15 to the master device 20 . Note that the handset-side operation unit 12 may be configured by a touch panel display.

The slave-side sound pickup unit 13 includes a microphone. The child device-side sound pickup unit 13 transmits the sound obtained by collecting the voice uttered by the visitor with a microphone to the parent device 20 via the child device-side communication unit 15 .

The handset-side audio output unit 14 outputs a response sound based on the sound signal received from the base unit 20 via the handset-side communication unit 15 or the output sound of the response sound control device 30 from the speaker. The child device side audio output unit 14 outputs the input audio signal from the speaker.

The child device side communication unit 15 is used to exchange various signals (video signal, control signal, audio signal, etc.) with the parent device 20 or the response voice control device 30 . The child device side communication unit 15 is electrically connected to the master device 20 or the response voice control device 30 by wire or wirelessly, and is configured to be able to communicate bidirectionally with the master device 20 or the response voice control device 30. there is

The handset-side controller 16 is composed of, for example, a microcomputer mainly composed of a processor and a memory. Then, the microcomputer functions as the child device side control section 16 by executing the program stored in the memory by the processor. Thereby, a function of controlling the imaging unit 11, the slave-side operation unit 12, the slave-side sound pickup unit 13, the slave-side audio output unit 14, and the slave-side communication unit 15 is realized. The program executed by the processor is recorded in advance in the memory of the microcomputer here, but may be recorded in a non-temporary recording medium such as a memory card and provided, or may be provided through an electric communication line such as the Internet. may be

Upon receiving the operation of the call button by the visitor, slave device 10 starts imaging by imaging unit 11 and transmits the captured image captured by imaging unit 11 to master device 20 or response voice control device 30 . Further, when receiving an operation for a call (operation of a call start button) from the resident, the child device 10 receives the voice uttered by the resident from the master device 20 and outputs it to the visitor. to transmit the voices uttered by the residents. Further, when not accepting an operation for making a call from the resident, the handset 10 outputs the response voice selected by the response voice control device 30 to the visitor by outputting the response voice of the resident (for example, voice messages).

(Master device 20)
The base unit 20 includes a display unit 21 , a base unit side operation unit 22 , a base unit side sound pickup unit 23 , a base unit side audio output unit 24 , a base unit side communication unit 25 , a storage unit 26 , and a base unit side control unit 27 . have. In addition to these, the master device 20 further has a response voice control device 30 .

The display unit 21 is a display such as an LCD (Liquid Crystal Display) that displays various images such as captured images received from the child device 10 and recorded images stored in the storage memory. The display unit 21 may display various operation menus and the like in addition to various images.

The main unit side operation unit 22 has buttons such as a call start button and a call end button, and an input device such as a numeric keypad, and receives input operations of the resident. The resident can input various settings and operations to the master device 20 via the master device-side operation unit 22 . For example, the resident inputs to the master device 20 through the master device side operation unit 22 home information indicating whether the resident is at home or not in the house. Specifically, the resident can input the stay-at-home information to the master device 20 by pressing an at-home button or an absent button included in the master device-side operation unit 22 .

Also, the resident can make a call with the visitor by pressing a call start button included in the base unit side operation unit 22 . When receiving the operation of the call start button by the resident, the master device 20 forms a communication path between the master device 20 and the slave device 10, and the resident whose sound is collected by the master device side sound collection unit 23 emits. An audio signal of voice is transmitted to the slave device 10 via the master device side communication unit 25 . The child device 10 that has received the audio signal from the parent device 20 outputs the voice uttered by the resident based on the received audio signal from the child device side audio output section 14 .

Also, the resident can end the call with the visitor (cut off the call path between the master device 20 and the slave device 10) by pressing the call termination button. Master device 20 terminates the display of the captured image by display unit 21 upon receiving the operation of the call end button by the resident. At the same time, the child device 10 stops the imaging by the imaging unit 11 .

Note that the display unit 21 and the parent device side operation unit 22 may be integrally configured by a touch panel display.

Base-side sound pickup unit 23 includes a microphone. The master-side sound pickup unit 23 picks up the voice uttered by the resident with a microphone.

Base-side audio output unit 24 outputs, from a speaker, the visitor's voice based on the audio signal received from child device 10 via base-side communication unit 25 .

The parent device side communication unit 25 is used to exchange various signals (control signal, audio signal, image signal, etc.) with the child device 10 or the response voice control device 30 . The parent device side communication unit 25 is electrically connected to the child device 10 and the response voice control device 30 by wire or wirelessly, and is configured to be able to communicate bidirectionally with the child device 10 .

The master-side controller 27 is composed of, for example, a microcomputer mainly composed of a processor and a memory. The microcomputer functions as the master-side controller 27 by executing the program stored in the memory by the processor. Thereby, the function of controlling the display unit 21, the master-side operation unit 22, the master-side sound pickup unit 23, the master-side audio output unit 24, and the master-side communication unit 25 is realized. The program executed by the processor is recorded in advance in the memory of the microcomputer here, but may be recorded in a non-temporary recording medium such as a memory card and provided, or may be provided through an electric communication line such as the Internet. may be

In the intercom device 1 , when the resident presses the call start button of the master device 20 , a communication path is formed between the master device 20 and the slave device 10 . Thereby, a call is started between the master device 20 and the slave device 10 . When a communication path is formed between the base unit 20 and the slave unit 10, the intercom device 1 transmits and receives an audio signal of the voice uttered by the visitor and an audio signal of the voice uttered by the resident. do.

The response voice control device 30 has an at-home information acquisition unit 31 , an image acquisition unit 32 , a judgment unit 33 , a response voice selection unit 34 and a recording control unit 35 . The answering voice control device 30 has two operation modes, an automatic answering mode and a call answering mode. Normally, the automatic answering mode is set, and when the call start button is pressed, the mode is switched to the call answering mode. It's becoming

The response voice control device 30 in the automatic response mode recognizes and authenticates the visitor based on the captured image received from the child device 10, and then transmits the response voice selected according to the result of at least one of the recognition and authentication. to the machine 10. On the other hand, the response voice control device 30 that has shifted to the call response mode ends the processing.

The stay-at-home information acquisition unit 31 acquires stay-at-home information indicating whether a resident is at home or not in the residence. For example, the stay-at-home information acquisition unit 31 acquires the stay-at-home information previously input by the resident via the base unit-side operation unit 22 .

Alternatively, if the response voice control device 30 is configured to be able to communicate wirelessly with a pre-registered mobile terminal, the home information acquisition unit 31 obtains the current location information of the mobile terminal carried by the resident via a network or the like. may be obtained. When acquiring the current location information from the mobile terminal, the presence information acquisition unit 31 determines that the resident is at home when the current location information of the mobile terminal indicates that the resident is within a predetermined distance range from the address of the resident. If the current location information of the portable terminal indicates that the mobile terminal is not within a predetermined distance range from the resident address, it may be determined that the resident is absent.

Portable terminals include, for example, electronic devices such as notebook PCs, tablet terminals, and smart phones. The at-home information acquisition unit 31 acquires current location information from a mobile terminal carried by the resident. The current location information is, for example, location information of the mobile terminal acquired by a location information acquisition function built into the mobile terminal. The position information acquisition function includes GNSS (Global Navigation Satellite System) such as GPS (Global Positioning System). The location information may be location information such as an access point with which the mobile terminal communicates.

In addition, when the response voice control device 30 is configured to be able to communicate with an electric lock provided at the entrance door by wire or wirelessly, the presence-at-home information acquisition unit 31 obtains information regarding the state of the electric lock as presence-at-home information. Can be obtained from tablets. The entrance door is the entrance door of the residence where the intercom device 1 is installed. When the stay-at-home information is acquired from the electric lock, the stay-at-home information acquiring unit 31 acquires the stay-at-home information indicating the absence of the resident during the period from when the electric lock is locked from the outside of the residence to when it is unlocked from the outside of the residence. It should be configured to obtain In this case, stay-at-home information indicating that the resident is at home is acquired outside the period.

The image acquisition unit 32 acquires the captured image received from the child device 10 .

The determination unit 33 has a recognition unit 41 that recognizes the visitor based on the captured image, and an authentication unit 42 that authenticates the visitor based on the captured image. For example, the recognizing unit 41 extracts the feature amounts of the eyes, nose, mouth, etc., which are the feature parts of the visitor's face, from the captured image, and recognizes the region where these feature amounts are extracted as the face image of the person. Recognition is performed, and it is determined whether or not the visitor's face has been recognized, in other words, whether or not the visitor has been recognized as a person. The recognition unit 41 determines that the recognition is established when the face image of the person can be recognized. On the other hand, the recognizing unit 41 recognizes when the face image of the person cannot be recognized because the visitor is outside the imaging area or the face is hidden, or when the face (person) cannot be recognized in the captured image. Then, it is determined that the recognition is not established.

The authentication unit 42 compares the face image extracted by the recognition unit 41 with the registrant data read from the storage unit 26 to perform face authentication of the visitor. If the registrant data includes a face image that matches the face image extracted from the captured image, the authentication unit 42 determines that the authentication is successful. On the other hand, if the registrant data does not include a face image that matches the face image extracted from the captured image, the authentication unit 42 determines that the authentication has failed.

The authentication unit 42 authenticates that the visitor is an acquaintance of the resident by using acquaintance data described later as registrant data. For example, the authentication unit 42 compares the captured image with acquaintance data of the resident read out from the storage unit 26, and if the degree of matching between the two, which is quantified, exceeds a predetermined threshold, the visitor is an acquaintance of the resident. can be authenticated. The authentication unit 42 uses a trained acquaintance model learned by machine learning using a neural network, for example, inputs the captured image to the trained acquaintance model, and outputs the degree of acquaintance of the resident in the captured image as a numerical value. A visitor may be authenticated as an acquaintance of a resident by deep learning technology. An acquaintance trained model is, for example, a trained model that has been machine-learned by inputting input data, which is a set of a photographed image and teacher data indicating whether or not an acquaintance is included in the image, into a neural network. . In addition, known techniques can be used to authenticate that the visitor is an acquaintance of the resident.

The authentication unit 42 can also authenticate that the visitor is a specific trader, such as a delivery company, by using specific trader data, which will be described later, as registrant data. For example, the authentication unit 42 authenticates that the visitor is the specific trader when the degree of matching between the captured image and the specific trader data read out from the storage unit 26 exceeds a predetermined threshold. can be done. The authentication unit 42 may authenticate that the visitor is the specific trader by deep learning technology using the specific trader trained model learned by machine learning using the neural network described above.

Furthermore, the authentication unit 42 can also authenticate that the visitor is a suspicious person using suspicious person data, which will be described later, as registrant data. For example, the authentication unit 42 compares the captured image with the suspicious person data read from the storage unit 26 and authenticates the visitor as a suspicious person when the quantified degree of matching between the two exceeds a predetermined threshold. can be done. The authentication unit 42 may authenticate that the visitor is a suspicious person by deep learning technology using a suspicious person trained model learned by machine learning using the neural network described above.

The authentication unit 42 of the present embodiment can set the security level divided into the following four levels according to the content of the registrant registered in advance.

Level 1: acquaintance Level 2: acquaintance + specific trader Level 3: acquaintance + specific trader + non-suspicious person Level 4: acquaintance + specific trader + non-suspicious person + suspicious person

When the security level is set to level 1, the authentication unit 42 determines that the visitor is a registrant if the visitor is an acquaintance.

When the security level is set to level 2, the authentication unit 42 determines that the visitor is a registrant if the visitor is an acquaintance or a specific trader.

When the security level is set to level 3, the authentication unit 42 determines that the visitor is a registrant if the visitor is an acquaintance, a specific trader, or a non-suspicious person.

When the security level is set to level 4, the authentication unit 42 does not authenticate any visitors (acquaintances, specific traders, non-suspicious persons, and suspicious persons).

The recording control unit 35 performs a process of storing or discarding a recorded image obtained by recording the captured image captured by the imaging unit 11 . In the automatic response mode, if the determination unit 33 determines that the visitor is not a registered person but an unregistered person, or if the stay-at-home information acquired by the stay-at-home information acquisition unit 31 indicates that the resident is absent, the recording control unit 35 stores the recorded image in the storage memory of the storage unit 26 .

Then, when a reproduction request is made by an input operation of the resident, the response voice control device 30 reads the recorded image from the storage unit 26 and displays it on the display unit 21, and interlocks with the recorded image to pick up the slave unit side sound. The voice of the visitor recorded via the unit 13 is output from the main unit side voice output unit 24 . This allows the resident to check the recorded image and the visitor's business. In this embodiment, the recording control unit 35 is configured to discard the recorded image when switching to the call response mode, but may be configured to save the recorded image even in the call response mode.

The response voice selection unit 34 selects a response voice to be output from the child device side voice output unit 14 according to the determination result of the determination unit 33, and transmits the selected response voice to the child device side voice output unit 14. 25 (output). The response voice selection unit 34 determines whether or not the visitor has been recognized and whether or not the visitor is a registrant based on at least one of recognition and authentication by the determination unit 33 . For example, when the visitor cannot be recognized or when the visitor is not a registrant, the response voice selection unit 34 outputs the synthesized voice to the child device side voice output unit 14 . Further, for example, when the visitor is a registrant, the response voice selection unit 34 outputs the voice uttered by the resident or the recorded voice of the resident to the slave unit side voice output unit 14 .

The response voice selection unit 34 selects different voice messages from multiple types of voice messages according to the type of visitor (registrant, specific trader, non-suspicious person, suspicious person) determined by recognition and authentication by the determination unit 33. A voice message may be selected and output to the handset side voice output section 14 . When the response voice control device 30 is in the call response mode, a call can be made between the master device 20 and the slave device 10. Therefore, the voice uttered by the resident is output from the voice output unit 14 on the slave device side. output.

The storage unit 26 is configured by a memory selected from ROM (Read Only Memory), RAM (Random Access Memory), nonvolatile memory, and the like.

The storage unit 26 has a storage memory that stores recorded images. The storage unit 26 stores the recorded image in the storage memory in association with the recorded voice of the visitor. The storage unit 26 may be provided in the master device 20 as well as in the response voice control device 30 .

Further, the storage unit 26 stores registrant data in the authentication memory in advance. The registrant data is automatically generated based on photo data including face images of each registrant stored in the image folder of the mobile terminal. The resident can store the registrant data in the storage unit 26 by transmitting the registrant data from the portable terminal to the response voice control device 30 via the network. The data received by the response voice control device 30 from the portable terminal can be edited by adding, changing, and deleting facial images via the master device side operation unit 22 . Therefore, for example, when the data received from the portable terminal includes a face image of a person who is not desired to be registered in the registrant data, the face image of the person can be deleted and the registrant data can be managed.

In addition, the storage unit 26 stores in the authentication memory in advance specific trader data of a specific trader such as a delivery trader. The specific trader data is data for identifying the specific trader. As the data for identifying the specific trader, image information (color, pattern, etc.) related to uniforms and hats worn by the specific trader, image information related to the unique symbol mark of the company to which the specific trader belongs, etc. are preferable.

Further, the storage unit 26 stores suspicious person data regarding suspicious persons in the authentication memory in advance. As the condition of the suspicious person, for example, a physical feature (for example, face) of the person who is judged by many people as "suspicious" or "dangerous" is used. Specific examples of the suspicious person include a person who hides his or her face by covering it with a mask, sunglasses, hands, or the like, and a person who turns his face away (a person with a profile).

Further, the storage unit 26 stores at least one of the recorded voice and the synthesized voice in the response voice memory in advance. The recorded voice is, for example, voice recorded in advance by the resident through the master unit side sound pickup unit 23 . Synthetic speech is, for example, speech mechanically generated in advance. The recorded voice and synthesized voice may be configured so that the response voice control device 30 acquires them from an external device. The recorded voice and synthesized voice may be a voice message asking the visitor's requirements, a voice message conveying the request to the visitor, or the like.

Specific examples of such voice messages include "Who are you?", "What is your business?" A resident can set a voice message as a candidate for a response voice from among a plurality of types of voice messages stored in a response voice memory of a storage part 26 via the main unit side operation part 22.例文帳に追加

The storage memory, authentication memory, and response voice memory described above are rewritable memories, and are preferably non-volatile memories such as HDDs (Hard Disk Drives) and flash memories (SSDs: Solid State Drives). . Moreover, when the intercom device 1 is equipped with artificial intelligence (AI: Artificial Intelligence), the response voice control device 30 can accumulate a plurality of data and learned models accumulated in the past. In addition, the response voice control device 30 is also capable of machine learning using frameworks such as neural networks and deep learning.

Next, an example of the operation of the intercom device 1 will be described, centering on the processing performed by the response voice control device 30. FIG. FIG. 2 is a flow chart for explaining the operation of the intercom device shown in FIG. In the processing flow shown in FIG. 2, an example will be described in which synthesized speech is selected and output as a response speech when the visitor is not a registrant and the home information indicates absence. However, if there is no security problem, voices other than synthesized voices (for example, recorded voices of residents) may be selected and output.

When the visitor presses the call button to perform a calling operation on the child device 10, a call signal is transmitted from the child device 10 to the parent device 20, and the processing flow shown in FIG. 2 is started. The slave device 10 activates the imaging unit 11 to start imaging, and transmits an image signal of the captured image to the image acquisition unit 32 of the response voice control device 30 . At the same time, the base unit 20 that has received the call signal and the image signal sounds the ring tone from the speaker of the base unit side audio output unit 24 and displays the captured image on the display unit 21 .

In step S11, when the stay-at-home information acquisition unit 31 acquires the stay-at-home information, it is determined whether or not the resident is at home based on the acquired stay-at-home information. If the at-home information indicates that the resident is at home, the process proceeds to step S12. If the presence-at-home information indicates that the resident is absent, the process proceeds to step S21.

If the at-home information indicates that the visitor is at home, the determination unit 33 recognizes and authenticates the visitor based on the captured image acquired by the image acquisition unit 32 in step S12.

If the determination unit 33 determines that the visitor cannot be recognized or that the visitor is not a registrant (step S12: YES), the process proceeds to step S13. If the determination unit 33 determines that the visitor is a registrant (step S12: NO), the process proceeds to step S31.

In step S<b>13 , the response voice selection unit 34 selects a synthetic voice from the response voice candidates stored in the storage unit 26 . The response voice control device 30 transmits the synthesized voice selected by the response voice selection unit 34 to the child device 10 . At the same time, the recording control unit 35 starts recording the captured image. Then, the process proceeds to step S14.

In step S14, it is determined whether or not a call has been started between the master device 20 and the slave device 10. FIG. This determination can be made based on whether or not the base unit side operation unit 22 has received that the call start button has been operated by the resident. If it is determined that the call has started (step S14: YES), the process proceeds to step S15. If it is determined that the call has not started (step S14: NO), the process proceeds to step S22.

When it is determined that the call has started, the recording control unit 35 performs processing of discarding the recorded image in step S15. Then, the processing flow shown in FIG. 2 ends.

On the other hand, if the at-home information indicates absence in step S11, the response voice selection unit 34 selects a synthetic voice from the response voice candidates stored in the response voice memory of the storage unit 26 in step S21. The response voice control device 30 transmits the synthesized voice selected by the response voice selection unit 34 to the child device 10 . At the same time, the recording control unit 35 starts recording the captured image. Then, in step S22, the recording control unit 35 performs processing for saving the recorded image, and the processing flow shown in FIG. 2 ends.

Further, when it is determined in step S12 that the visitor is a registrant, in step S31, the response voice selection unit 34 switches from the automatic response mode to the call response mode, thereby The voice uttered by the resident who made the sound is selected, and the processing flow shown in FIG. 2 ends.

As described above, the intercom device 1 according to the present embodiment has the image acquiring section 32, the determining section 33, and the response voice selecting section 34 described above.

With such a configuration, different voice messages can be output according to the type of visitor. Therefore, it is possible to ask the visitor what to do without knowing whether the resident is at home or not. As a result, you can protect yourself from suspicious visitors.

Further, in the intercom device 1, when the determination unit 33 determines that the visitor is not the registrant, the response voice selection unit 34 uses the pre-stored synthesized voice as the response voice.

According to such a configuration, a response by a resident's spoken voice or a resident's recorded voice is realized in the case of a registered visitor, and a response is realized in the case of an unrecognized visitor or an unregistered visitor. In some cases, synthetic speech responses are implemented. Therefore, there is no risk that visitors other than recognizable registrants will hear the voice uttered by the resident. It is possible to avoid revealing the personal information of the residents, such as the presence of the residents.

Further, in the intercom device 1, the determination unit 33 further authenticates that the visitor is a suspicious person using the suspicious person data related to the suspicious person stored in advance, and the response voice selection unit 34 causes the determination unit 33 to When the person is authenticated as a suspicious person, the synthetic voice is used as a response voice.

According to such a configuration, it is possible to detect a suspicious person, and there is no fear that the suspicious person will hear the voice uttered by the resident, and the personal information of the resident such as gender can be guessed. It is possible to avoid the possibility that the resident's personal information such as that the resident is at home will be known. As a result, it is possible to further protect oneself from suspicious persons.

The intercom device 1 also has an at-home information acquisition unit 31 that acquires at-home information indicating whether the resident is at home or not in the residence. Further, when the determination unit 33 determines that the visitor is not a registrant, or when the presence-at-home information acquired by the presence-at-home information acquisition unit 31 indicates that the visitor is absent, the intercom device 1 displays the captured image captured by the imaging unit 11. has a recording control unit 35 that saves a recorded image obtained by recording the

According to such a configuration, the resident can grasp the information of the unregistered visitor by confirming the recorded image and the recorded voice of the visitor. Alternatively, even if the resident is not in the residence when the visitor visits, the resident can grasp the information of the visitor who visited during the absence by checking the recorded image and the recorded voice of the visitor. be able to.

Further, in the intercom device 1, the response voice selection unit 34, when the determination unit 33 determines that the visitor is a registrant and when the presence-at-home information acquired by the presence-at-home information acquisition unit 31 indicates absence, pre-records The recorded voice is used as the response voice.

According to such a configuration, even if the resident is not in the residence, if the resident is a registered visitor, he/she can ask for the business. By checking the recorded images and the recorded voice of the visitor, the resident can grasp the information of the visitor during his/her absence, such as presence or absence of the visitor, who the visitor is, and what the visitor is doing. can be done.

As explained in detail above, according to this embodiment, it is possible to provide the intercom device 1 capable of ensuring the privacy and security of the residents.

It should be noted that the present disclosure is not limited to the above embodiments, and can be modified as appropriate without departing from the scope of the present disclosure. For example, in the above embodiment, suspicious person data is used to authenticate a suspicious person, but non-suspicious person data related to a non-suspicious person may be stored in the storage unit 26 instead of suspicious person data. As a condition of a non-suspicious person, for example, a physical feature (for example, face) of a person who is judged by many people to be “calm” can be used. When authenticating a non-suspicious person using non-suspicious person data, for example, the authentication unit 42 compares the captured image with the non-suspicious person data read from the storage unit 26 and digitizes the degree of matching between the two. A non-suspicious person can be authenticated depending on whether or not the threshold is exceeded.

This disclosure includes matters that contribute to the realization of the SDGs's "Sustainable urban development" and contribute to the safety and security of public facilities.

1 intercom device 10 slave unit 11 imaging unit 12 slave unit side operation unit 13 slave unit side sound collection unit 14 slave unit side audio output unit 15 slave unit side communication unit 16 slave unit side control unit 20 master unit 21 display unit 22 master unit Side operation unit 23 Parent device side sound pickup unit 24 Parent device side audio output unit 25 Parent device side communication unit 26 Storage unit 27 Parent device side control unit 30 Response voice control device 31 Presence information acquisition unit 32 Image acquisition unit 33 Judgment unit 34 Response voice selection unit 35 Recording control unit 41 Recognition unit 42 Authentication unit

Claims (5)

An intercom device equipped with an intercom slave unit used by a visitor,
an image acquisition unit that acquires an image captured by an imaging unit that captures an image of the visitor;
a determination unit that determines at least one of whether the visitor has been recognized and whether the visitor is a pre-registered registrant based on the captured image acquired by the image acquisition unit;
a response voice selection unit that selects a response voice to be output from the handset-side voice output unit of the intercom slave unit according to the determination result of the determination unit, and outputs the selected response voice to the handset-side voice output unit; ,
An intercom device having The response voice selection unit
If the determination unit determines that the visitor is not the registrant, a pre-stored synthetic voice is used as the response voice.
The intercom device according to claim 1. The determination unit is
further authenticating that the visitor is the suspicious person using pre-stored suspicious person data relating to the suspicious person;
The response voice selection unit
When the determination unit authenticates that the visitor is the suspicious person, a pre-stored synthetic voice is used as the response voice.
The interphone device according to claim 1 or 2. a stay-at-home information acquisition unit that acquires stay-at-home information indicating whether a resident is at home or not in the residence;
When the determining unit determines that the visitor is not the registrant, or when the at-home information acquired by the at-home information acquiring unit indicates the absence, the captured image captured by the imaging unit is recorded. a recording control unit that saves recorded images;
The intercom device according to any one of claims 1 to 3, further comprising: The response voice selection unit
If the determination unit determines that the visitor is the registrant and if the presence-at-home information acquired by the presence-at-home information acquisition unit indicates that the visitor is absent, pre-recorded voice is used as the response voice. ,
The intercom device according to claim 4.

Images