JP7378042B2 - Delivery agent authentication method, delivery agent authentication system, and server device - Google Patents

Description

The present disclosure relates to a delivery agent authentication method, a delivery agent authentication system, a server device, and a control device.

In Patent Document 1, in an apartment complex in which an entrance management system for managing entrance is installed, facial images of people who are permitted to enter the apartment complex are stored in advance, and the facial images of people who are allowed to enter the apartment complex are stored in advance. The face image detected from the image taken is compared with the stored face image of the person, and if the person whose face image is stored is the person, entry is permitted and the delivery person is allowed to deposit the goods. An article management system is disclosed.

Japanese Patent Application Publication No. 2003-276849

However, with the configuration of Patent Document 1, for example, in an existing private residence or an apartment complex that is not equipped to authenticate facial images, it is not possible to allow a delivery company to deposit goods. Further, in such a case, the delivery company has to re-deliver the goods, which increases the load on the delivery company and reduces operational efficiency.

The present disclosure was devised in view of the conventional circumstances described above, and provides a delivery agent authentication method, a delivery agent authentication system, a server device, and a control device that can reduce the workload of the delivery agent due to redelivery due to the absence of the recipient. The purpose is to

The present disclosure is a delivery agent authentication method using the voice uttered by a delivery person performed by a server device , in which a voice input signal based on the voice uttered by the delivery person collected by a voice input terminal is received. Identification information that can identify the delivery person is extracted based on the voice input signal, and the extracted delivery is performed by referring to a database that includes identification information of each delivery person of a plurality of delivery companies registered in advance. It is determined whether the person's identification information is registered, and if the delivery person's identification information is registered , an instruction regarding the utterance content is output to the delivery person via the voice input terminal, and the utterance content is outputted to the delivery person via the voice input terminal. receive another audio input signal based on the voice of the delivery person speaking the content of the utterance, and a captured image of the delivery person uttering the content of the utterance captured by the audio input terminal, and based on the captured image, The movement of the delivery person's mouth is detected, and the movement period during which the delivery person's mouth is moving and the output period of the delivery person's audio signal based on the other audio input signal are output in approximately the same time period. If it is determined that the operation period and the output period of the audio signal are output in approximately the same time period, the audio signal is delivered to a predetermined area that is accessible in front of the entrance of the destination house. To provide a delivery agent authentication method that controls unlocking of an automatic locking system that controls entry permission.

The present disclosure also provides a delivery agent authentication system in which a control device that controls an automatic locking system and a server device can communicate with each other, wherein the control device receives voice uttered by a delivery person collected by a voice input terminal. and transmitting the received voice input signal to the server device, and the server device extracts identification information capable of identifying the delivery person based on the received voice input signal. , refers to a database containing identification information of each delivery person of a plurality of pre-registered delivery companies, determines whether or not the extracted delivery person identification information is registered, and identifies the delivery person. If the identification information is registered, an instruction regarding the utterance content is output to the delivery person via the voice input terminal, and another audio input signal based on the utterance voice of the delivery person who utters the utterance content; A captured image of the delivery person speaking the utterance content captured by a voice input terminal is received, a movement of the delivery person's mouth is detected based on the captured image, and a movement of the delivery person's mouth is detected based on the captured image. The operation period and the output period of the voice signal of the delivery person based on the other voice input signal are checked to see if they are output in substantially the same time zone, and the operation period and the output period of the voice signal are checked. If it is determined that the signals are output in substantially the same time zone, an unlock signal for permitting unlocking of the automatic locking system is generated and transmitted to the control device, and the control device transmits the received signal to the control device. A delivery company authentication system is provided that controls unlocking of the automatic locking system based on an unlock signal.

The present disclosure also includes a speech instruction unit that instructs the delivery person to speak, and an identification device that extracts the delivery person's identification information based on a voice input signal based on the voice spoken by the delivery person received by a voice input terminal. Registration for determining whether or not the extracted delivery person identification information is registered by referring to the information extraction unit and a database containing identification information of each delivery person of a plurality of pre-registered delivery companies. a detection unit that detects a movement of the delivery person's mouth based on an image of the delivery person taken by the voice input terminal; and an operation period during which the delivery person's mouth is moving. , a verification unit that verifies whether the output period of the delivery person's audio signal based on the audio input signal is output in substantially the same time period; and a predetermined area that is accessible in front of the entrance of the delivery destination's residence. an unlocking permission unit for unlocking an automatic locking system that controls entry permission to the delivery person; The detection unit outputs an instruction regarding the contents of the utterance to the delivery person via the voice input terminal, and the detection unit outputs another audio input signal based on the voice uttered by the delivery person after the instruction, and outputs an instruction regarding the utterance content of the delivery person captured by the audio input terminal. and detects the movement of the delivery person's mouth based on the captured image; A server device is provided that generates an unlocking permission signal when it is determined that the unlocking permission signal has been output .

The present disclosure also includes a receiving unit that receives an audio input signal based on the voice uttered by a delivery person using an audio input terminal; a transmission unit that transmits the voice input signal to a server device that determines the locking system and generates an unlocking permission signal for the automatic locking system; A control device is provided that includes an unlocking control unit that controls unlocking of an automatic locking system that controls permission to enter an accessible predetermined area.

According to the present disclosure, it is possible to reduce the workload of a delivery company due to redelivery due to the absence of a recipient.

A diagram illustrating a configuration example of a delivery agent authentication system according to Embodiment 1 A diagram showing an example of a system configuration of a server device according to Embodiment 1. Flowchart showing an example of the one-way authentication procedure of the delivery agent authentication system Diagram showing an example of identification information of registered delivery companies A diagram showing an example of a system configuration of a server device according to Embodiment 2 Flowchart showing an example of the two-way authentication procedure of the delivery agent authentication system Flowchart showing an example of the utterance detection procedure of the delivery company authentication system Flowchart showing an example of the authentication procedure using speech detection in the delivery agent authentication system Diagram explaining an example of speech detection by the delivery company authentication system

EMBODIMENT OF THE INVENTION Hereinafter, each embodiment which specifically disclosed the structure and operation|movement of the delivery agent authentication method, delivery agent authentication system, server apparatus, and control apparatus based on this indication is described in detail, referring drawings suitably. However, more detailed explanation than necessary may be omitted. For example, detailed explanations of well-known matters or redundant explanations of substantially the same configurations may be omitted. This is to avoid unnecessary redundancy in the following description and to facilitate understanding by those skilled in the art. The accompanying drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter recited in the claims.

(Embodiment 1)
FIG. 1 is a diagram illustrating a configuration example of a delivery company authentication system according to the first embodiment. The delivery agent authentication system is installed, for example, in a private residence or an apartment complex. The delivery agent authentication system executes voice authentication based on the voice of the delivery person H1 of the delivery company, and if the delivery person H1 of the delivery company is a delivery person of a delivery company registered in advance, the delivery agent authentication system performs voice authentication based on the voice of the delivery person H1 of the delivery company, and if the delivery person H1 of the delivery company is a delivery person of a delivery company registered in advance, the delivery agent authentication system performs voice authentication based on the voice of the delivery person H1 of the delivery company. Alternatively, it controls the unlocking of an automatic locking system GT provided at an entrance GT1 of a common part of an apartment complex.

In addition, in the following explanation, the delivery agent authentication system will be explained as a system for unlocking the automatic locking system GT installed at the entrance GT1 of a common part of an apartment complex. It may be provided in a gate GT2 or a delivery box GT3 installed in an apartment complex. Further, the delivery agent authentication system according to the first embodiment will be described as a system that controls unlocking of the automatic locking system GT assuming that the recipient who receives the goods delivered by the delivery person H1 of the delivery agent is absent. However, the present invention is not limited to this, and the authentication of the delivery person H1 of the delivery company may be performed when the recipient is at home, and the authentication result may be provided to the recipient. Note that the delivery company according to the first embodiment refers to a company that operates a business that delivers goods, such as a delivery business.

The delivery company authentication system shown in FIG. 1 includes an intercom Int1, a control device CD1, a server device S1, a business registrant database DB1, and an automatic locking system GT.

The intercom Int1 is installed at the common entrance GT1 of the housing complex, and is communicably connected to each of a plurality of intercoms (not shown) installed in each residence in the housing complex. The interphone Int1 includes a communication section 10, a control section 11, a memory 12, an input section 13, an output section 14, and an imaging section 15.

The communication unit 10 is configured using a circuit capable of transmitting and receiving data or information to and from the control unit 11. The communication unit 10 transmits a voice input signal based on the voice Msg1 uttered by the delivery person H1 of the delivery company, which is collected by the input unit 13, to the control device CD1. Note that the communication unit 10 is communicably connected to the control device CD1 via a wired LAN (Local Area Network).

The control unit 11 includes, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a DSP (Digital Signal Processor), or an FPGA (Field Programmable Gate). e Array). The control unit 11 functions as a controller that controls the overall operation of the interphone Int1, and cooperates with the memory 12 to perform control processing for unifying the operation of each part of the intercom Int1, and performs data transfer between each part of the intercom Int1. Performs input/output processing, data arithmetic (calculation) processing, and data storage processing. The control unit 11 operates according to programs and data stored in the memory 12. The control unit 11 uses the memory 12 during operation, and causes the memory 12 to temporarily store data or information created or acquired by the control unit 11.

The memory 12 includes, for example, a RAM (Random Access Memory) as a work memory used when executing each process of the control unit 11, and a ROM (Read Only Memory) that stores programs and data that define the operation of the control unit 11. and has. Data or information created or acquired by the control unit 11 is temporarily stored in the RAM. A program that defines the operation of the control unit 11 is written in the ROM. Further, the memory 12 stores data of the speech Msg1 of the delivery person H1 of the delivery company inputted to the input unit 13, captured image data captured by the imaging unit 15, etc. together with time information.

The input unit 13 is, for example, an array microphone composed of a plurality of microphones (not shown), and picks up speech Msg1 (for example, "Hello, this is XX Transport") of a delivery person H1 of a delivery company. The input unit 13 outputs the speech Msg1 of the delivery person H1 of the delivery company, which is collected from each of the plurality of microphones, to the control unit 11. Note that each of the plurality of microphones may be an omnidirectional microphone, a unidirectional microphone, or a phase directional microphone, or may be a combination of these.

The output unit 14 includes a speaker 16 and outputs the voice of a resident, a manager of an apartment complex, etc. using an intercom installed in a residence designated by a visitor, such as a delivery person H1 of a delivery company.

The imaging unit 15 includes at least a lens 18 and an image sensor (not shown). The image sensor is a solid-state imaging device such as a CCD (Charged-Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor), and converts an optical image formed on an imaging surface into an electrical signal.

The imaging unit 15 is equipped to be able to image a predetermined imaging area in front of the intercom Int1, and images the delivery person H1 of the delivery company within the imaging area. The imaging unit 15 outputs captured image data to the control unit 11 .

Next, the configuration of the control device CD1 will be explained. The control device CD1 is a device that can perform unlocking control of the automatic locking system GT.

The communication unit 20, which is an example of a receiving unit and a transmitting unit, is configured using a circuit capable of transmitting and receiving data or information between the intercom Int1 and the server device S1. The communication unit 20 transmits the voice input signal received from the intercom Int1 to the server device S1. Note that the communication unit 20 is communicably connected to the intercom Int1 and the server device S1 via a wired LAN.

The unlocking control unit 21 is configured using, for example, a CPU, a DSP, or an FPGA. The control unit 11 functions as a controller that controls the overall operation of the intercom Int1, and cooperates with the memory 22 to perform control processing for unifying the operation of each part of the control device CD1, and performs control processing between each part of the control device CD1. Performs data input/output processing, data arithmetic (calculation) processing, and data storage processing. The unlocking control unit 21 operates according to the program and data stored in the memory 22. The unlocking controller 21 uses the memory 22 during operation, and causes the memory 22 to temporarily store data or information created or acquired by the unlocking controller 21. The unlocking control unit 21 generates an unlocking control signal as an example of an unlocking signal for unlocking the automatic locking system GT based on the unlocking permission received from the server device S1, and transmits the unlocking control signal to the automatic locking system. Send to GT.

The memory 22 includes, for example, a RAM as a work memory used when executing each process of the unlocking controller 21, and a ROM that stores programs and data that define the operation of the unlocking controller 21. Data or information created or acquired by the unlocking control unit 21 is temporarily stored in the RAM. A program that defines the operation of the unlocking control section 21 is written in the ROM. Further, the memory 22 stores history information of unlocking control performed by the unlocking control unit 21 together with time information.

Next, the configuration of the server device S1 will be explained. The server device S1 refers to each of the data D1, D2, ..., Dn stored (registered) in the business registrant database DB1 based on the voice input signal of the delivery person H1 of the delivery company picked up by the intercom Int1. do. The server device S1 includes a communication section 30, a control section 31, and a memory 32.

The communication unit 30 is configured using a circuit capable of transmitting and receiving data or information between the server device S1 and the business registrant database DB1. The communication unit 30 receives a voice input signal from the intercom Int1 via the control device CD1. The communication unit 30 is communicably connected to the server device S1 and the business registrant database DB1 via a wired LAN.

The control unit 31 is configured using, for example, a CPU, a DSP, or an FPGA. The control unit 31 functions as a controller that controls the overall operation of the server device S1, and cooperates with the memory 32 to perform control processing for unifying the operation of the unlock determination unit 312 of the server device S1. Performs data input/output processing between each section, data arithmetic (calculation) processing, and data storage processing. The control unit 31 operates according to programs and data stored in the memory 32. The control unit 31 uses the memory 32 during operation, and causes the memory 32 to temporarily store data or information created or acquired by the control unit 31. Note that the unlock determination unit 312 will be described later.

The memory 32 includes, for example, a RAM as a work memory used when executing each process of the control unit 31, and a ROM that stores programs and data that define the operation of the control unit 31. Data or information created or acquired by the control unit 31 is temporarily stored in the RAM. A program that defines the operation of the control unit 31 is written in the ROM. The memory 32 also stores identification information (for example, company name) regarding a plurality of delivery companies registered in advance in the company registrant database DB1.

Next, the business registrant database DB1 will be explained. The business registrant database DB1 is configured to include each of a plurality of data D1, D2, . . . , Dn. Note that the identification information includes, for example, the company name of the delivery company, the name of the business office, and a personally identifiable number given to each delivery person (e.g., employee number), and may be one piece of identification information or a combination of multiple pieces of identification information. This is information that allows the delivery person to be identified. Each of the plurality of data D1, D2, . . . , Dn is data in which identification information of a plurality of delivery companies registered in advance when using the delivery company authentication system is stored. Each of the plurality of data D1, D2, ..., Dn is data storing identification information of each of a plurality of delivery companies sorted by each delivery company, each delivery company office, or each delivery area managed by the delivery company. It is.

Next, the automatic locking system GT will be explained. The automatic locking system GT is installed between a common area that outsiders can enter in an apartment complex and a passageway that includes a route from the common area to the entrance of each residence, and automatically locks the door when the door is closed. This is a system that locks the doors. The automatic locking system GT is provided, for example, at a gate GT2 of a private residence, a common entrance GT1 of a housing complex, or a delivery box GT3.

The automatic locking system GT executes unlocking control of the common area entrance GT1 of the apartment complex based on the unlocking control signal received from the control device CD1. The automatic locking system GT also controls the unlocking of the common entrance GT1 of the apartment complex even if unlocking permission is obtained from the resident of the apartment through each of the multiple intercoms installed in each apartment. Execute.

In addition, in the description of the configuration of FIG. 1 above, each of the server device S1, the control device CD1, and the intercom Int1 uses a wired LAN (Local Area Network) for connection between communication units. The connection is not limited to a wired LAN, but may be any other way as long as the required communication is possible; for example, the connection may be made using a communication path such as a wireless LAN (Local Area Network).

FIG. 2 is a diagram showing an example of the system configuration of the server device S1 according to the first embodiment. Each unit constituting the server device S1 will be described with reference to FIG. 2. Note that the explanation of the contents explained in FIG. 1 will be omitted.

The communication unit 30 receives a voice input signal from the intercom Int1 via the control device CD1. Furthermore, based on the received voice input signal, the communication unit 30 receives data including identification information regarding the delivery person H1 of the delivery company included in the voice input signal from the business registrant database DB1.

The control section 31 is configured to include an unlock determination section 312. The control unit 31 transmits unlock permission to the control device CD1 based on the determination result by the unlock determination unit 312.

The unlock determination unit 312, which is an example of an unlock permission unit, is a delivery company in which the delivery person H1 of the delivery company is registered using the voice input signal based on the received voice Msg1 uttered by the delivery person H1 of the delivery company. Based on the determination result, unlocking control of the automatic locking system GT is permitted, and an unlocking permission signal is generated. The unlock determination unit 312 includes a voice analysis unit 312a and an identification information determination unit 312b.

The voice analysis unit 312a, which is an example of an identification information extraction unit, analyzes the received voice input signal and first extracts a predetermined uttered word that includes identification information regarding the company (for example, company name) included in the voice input signal. Extract. Furthermore, the voice analysis unit 312a analyzes the received voice input signal and extracts other predetermined utterance words. The speech analysis unit 312a outputs each of the plurality of extracted predetermined utterance words to the identification information determination unit 312b. Note that the voice analysis unit 312a may extract at least one predetermined utterance word from the received voice input signal. In addition, even if the predetermined utterance word extracted at this time is identification information about the company, other identification information (for example, the name of the delivery person, the name of the business office, and a personally identifiable number assigned to each delivery person) may be used. etc.).

Note that the predetermined utterance words are set based on identification information registered in advance in the business registrant database DB1, such as the name of the delivery person, company name, business office name, and personally identifiable information given to each delivery person. This may be a number, etc. Predetermined utterance words extracted by the speech analysis section 312a are stored in the memory 32 in advance.

The identification information determination unit 312b, which is an example of the registrant determination unit, uses the information stored in the memory 32 (in other words, the business registrant database It is determined whether the company is a company (registered in advance in DB1). If the identification information determining unit 312b determines that the company is a registered company, it refers to the business registrant database DB1 based on other predetermined uttered words extracted by the voice analyzing unit 312a, and determines the delivery company's delivery information. It is determined whether the person H1 is a pre-registered delivery person. If the delivery person H1 of the delivery company is a registered delivery person, the identification information determination unit 312b outputs unlocking permission to the control device CD1. On the other hand, if the delivery person H1 of the delivery company is an unregistered delivery person, the identification information determination unit 312b outputs to the control device CD1 that unlocking is not permitted.

The memory 32 is preset and stores predetermined utterance words extracted by the speech analysis unit 312a and identification information (for example, company names) regarding a plurality of companies registered in advance in the business registrant database DB1. The memory 32 also stores the visiting time (receiving time of the voice input signal) of the delivery person H1 of the delivery company who visited for delivery, predetermined utterance words extracted by the voice analysis unit 312a, and delivery information determined by the identification information determination unit 312b. The determination result of the delivery person H1 of the business and the presence or absence of unlocking permission are stored.

FIG. 3 is a flowchart showing an example of a one-way authentication procedure of the delivery agent authentication system. Hereinafter, with reference to FIG. 3, a one-way authentication procedure based on the voice Msg1 uttered by the delivery person H1 of the delivery company, which is executed by the server device S1, will be described.

The communication unit 30 receives an audio input signal based on the voice Msg1 uttered by the delivery person H1 of the delivery company from the intercom Int1 via the control device CD1 (St10).

The audio analysis unit 312a analyzes the received audio input signal. The voice analysis unit 312a determines whether the voice input signal includes a predetermined utterance word that includes identification information regarding the delivery company (for example, a company name) and another predetermined utterance word that includes identification information other than the identification information regarding the company. It is determined whether or not it is, and extracted (St11).

The identification information determination unit 312b determines whether the predetermined utterance word including the extracted identification information regarding the company is a pre-registered delivery company stored in the memory 32 (St12).

If the predetermined utterance word including the identification information regarding the company extracted in step St12 is the identification information stored in the memory 32, the identification information determination unit 312b determines that the word is a registered delivery company (St12, YES). ), connects to the business registrant database DB1 (St13).

On the other hand, if the predetermined utterance word including the identification information regarding the company extracted in step St12 is not the identification information stored in the memory 32, the identification information determination unit 312b determines that the delivery person is not a registered delivery person (St12 , NO). The unlocking determining unit 132 outputs to the control device CD1 that the automatic locking system GT is not permitted to be unlocked, based on the determination result of the identification information determining unit 312b in step St12 (St14).

The identification information determination unit 312b connects to the business registrant database DB1 in step St13, and selects delivery people of a plurality of delivery companies registered in predetermined data (for example, data D1) that stores identification information regarding the extracted company. (St15).

The identification information determination unit 312b refers to each of the identification information of the delivery person of the plurality of delivery companies and determines whether the identification information of the delivery person H1 of the delivery company included in another predetermined utterance word is registered ( In other words, it is determined whether the person is registered in the business registrant database DB1 (St16).

The identification information determination unit 312b determines, in step St16, if the identification information of the delivery person H1 of the delivery company included in the other predetermined uttered word is the identification information registered in predetermined data (for example, data D1). determines that the delivery person H1 of the delivery company is a registered delivery company (registrant) (St16, YES). Based on the determination result of the identification information determining section 312b in step St16, the unlocking determining section 132 outputs to the control device CD1 that the automatic locking system GT is permitted to be unlocked (St17).

On the other hand, the identification information determination unit 312b determines in step St16 that the identification information of the delivery person H1 of the delivery company included in the other predetermined utterance word is identification information that is not registered in the predetermined data (for example, data D1). If so, it is determined that the delivery person H1 of the delivery company is not a registered delivery person (St16, NO). The unlocking determining unit 132 outputs to the control device CD1 that the automatic locking system GT is not permitted to be unlocked, based on the determination result of the identification information determining unit 312b in step St16 (St14).

Note that the one-way authentication procedure for the delivery person H1 of the delivery company is not limited to the procedure shown in FIG. For example, in the one-way authentication procedure for the delivery person H1 of the delivery company, the determination of the identification information regarding the delivery company in step St12 and the determination of other identification information with reference to the business registrant database DB1 may be performed simultaneously; , the determination may be made with reference to the trader registrant database DB1 in step St12.

FIG. 4 is a diagram showing an example of identification information TA1 of a registered delivery company. Note that the identification information TA1 shown in FIG. 4 is an example, and the identification information is not limited to this, and may include identification information regarding a business office, for example. In addition, the identification information TA1 may include identification information of delivery persons of a plurality of delivery companies and a delivery company of a business office. and the delivery person of the delivery company at the business office may be registered by giving an identification number (for example, a user number or an employee number) that allows identification.

Further, the identification information may include a feature amount representing the individuality of the voice of the delivery person H1 of the delivery company (in other words, information that allows the individual delivery person to be identified based on the voice). The feature amount indicating the individuality of the voice is, for example, identification information based on the frequency characteristics and temporal characteristics of the voice that differ from person to person, and can be used as identification information that allows individual identification.

The registered delivery company identification information TA1 shown in FIG. 4 includes, for example, the company name, the area in charge, a personally identifiable number (for example, an employee number) assigned to each delivery person, and the name of the delivery person. This is information that allows the delivery person to be identified by one piece of identification information or a combination of pieces of identification information. Identification information TA1 of registered delivery companies is stored in the company registrant database DB1 in association with each delivery company. Further, the registered delivery agent identification information TA1 may be classified by company, office, or delivery area, and managed as each of a plurality of pieces of data D1, D2, . . . , Dn.

As described above, in the delivery company authentication method according to the first embodiment, the server device S1 receives the voice input signal based on the voice Msg1 uttered by the delivery person H1 of the delivery company, which is picked up by the intercom Int1 (an example of a voice input terminal). Then, based on the voice input signal, identification information that can identify the delivery person H1 of the delivery company is extracted. The server device S1 refers to a trader registrant database DB1 (an example of a database) that includes identification information of each delivery person of a plurality of delivery companies registered in advance, and identifies the delivery person H1 of the extracted delivery company. Determine whether the information is registered. When the server device S1 determines that the identification information of the delivery person H1 of the delivery company is registered, the control device CD1 controls permission to enter a predetermined area that is accessible in front of the entrance of the residence of the delivery destination. Controls the unlocking of the automatic locking system GT.

As a result, the delivery agent authentication method according to the first embodiment can reduce the workload of the delivery agent H1 due to redelivery due to the recipient's absence.

(Embodiment 2)
The delivery agent authentication system according to the first embodiment analyzes a voice input signal based on the spoken voice Msg1 input from the delivery person H1 of the delivery company, and registers the delivery person H1 of the delivery company in advance in the company registrant database DB1. A case is shown in which it is determined whether the delivery company is a designated delivery company. In the delivery agent authentication system according to the second embodiment described below, an example will be described in which a false utterance by another person (for example, when a recorded voice of a delivery person H1 of a delivery agent is used) is detected.

With reference to FIG. 1, a configuration example of a delivery company authentication system in Embodiment 2 will be described. Note that the configuration example of the delivery agent authentication system according to the second embodiment has the same configuration as the configuration example of the delivery agent authentication system shown in FIG. 1, but has a different operation. Hereinafter, regarding the delivery agent authentication system according to Embodiment 2, different effects from Embodiment 1 will be explained.

First, intercom Int1 according to Embodiment 2 will be described.

The imaging unit 15 according to the second embodiment images a delivery person H1 of a delivery company. The imaging unit 15 transmits the captured image to the server device S1 via the control device CD1.

As a result, the courier authentication system prevents impersonation by another person, even if the other person impersonating the courier company's delivery person H1 uses a recorded voice Msg1 of the courier company's delivery person H1. It is possible to determine whether the

Each of the plurality of utterance instruction data is data for instructing the delivery person H1 of the delivery company what to utter. For example, an instruction to utter today's date, an instruction to utter a predetermined sentence from among a plurality of stored documents, etc. This data includes an instruction to repeat, an instruction to utter other identification information that is not included in the utterance voice Msg1 of the delivery person H1 of the delivery company, and the like.

The control unit 11 according to the second embodiment uses the speaker 16 included in the output unit 14 to instruct the delivery person H1 of the delivery company about the content of the utterance based on the utterance instruction control signal received from the server device S1. do. Furthermore, if the output unit 14 includes a monitor 17, the control unit 11 may display the content of the utterance on the monitor 17.

After the above-mentioned utterance instruction, the input unit 13 again picks up another utterance voice of the delivery person H1 of the delivery company. The input unit 13 converts other collected speech sounds into audio input signals and transmits them to the server device S1 via the control device CD1.

As a result, the courier authentication system prevents impersonation by another person, even if the other person impersonating the courier company's delivery person H1 uses a recorded voice Msg1 of the courier company's delivery person H1. It is possible to determine whether the

In the following description, the delivery agent authentication system according to the second embodiment will be described as a system that allows the delivery person H1 of the delivery company to determine whether or not someone else is impersonating the person. It is only necessary to be able to perform a camouflage determination using an intercom installed in a newly built private residence or an apartment complex, or to be able to perform a camouflage determination using either a captured image or other uttered audio.

FIG. 5 is a diagram showing an example of the system configuration of the server device S1 according to the second embodiment. Server device S1 according to Embodiment 2 has the same configuration as server device S1 according to Embodiment 1, and description of the same configuration and operation will be omitted.

The server device S1 includes a communication section 30, a control section 31, and a memory 32.

In addition to the operations described in Embodiment 1, the communication unit 30 according to the second embodiment receives an audio input signal based on the voice spoken by the delivery person H1 of the delivery company and which is collected by the input unit 13 included in the intercom Int1. The captured image data of the delivery person H1 of the delivery company captured by the imaging unit 15 is received.

The control unit 31 according to the second embodiment is configured to include an unlock determination unit 312 and a camouflage determination unit 313. When executing the impersonation determination, the control unit 31 generates an utterance instruction control signal that instructs the delivery person H1 of the delivery company about the content of the utterance, and transmits it to the intercom Int1.

The unlocking determination unit 312 according to the second embodiment determines whether or not to permit unlocking of the automatic locking system GT based on the determination results of the identification information determining unit 312b, the position verification unit 314c, and the operation verification unit 315c. Determine. Note that the unlocking determination unit 312 determines whether or not to permit unlocking of the automatic locking system GT based on the identification information determination unit 312b and the determination result of either the position verification unit 314c or the operation verification unit 315c. may be determined.

The falsification determination unit 313 determines whether the delivery person H1 of the delivery company is impersonating another person pretending to be the delivery person H1 of the delivery company, based on the uttered voice Msg1 of the delivery person H1 of the delivery company and the captured image of the delivery person H1 of the delivery company. Determine whether the person is a person. The camouflage determination unit 313 includes a face position estimation unit 314a, a speech position estimation unit 314b, a position verification unit 314c, a mouth movement detection unit 315a, an utterance detection unit 315b, and a movement verification unit 315c. Ru.

The face position estimating unit 314a estimates the position of the face of the delivery person H1 of the delivery company in the captured image based on the captured image captured by the imaging unit 15 of the intercom Int1. The face position estimation section 314a outputs the estimation result to the position matching section 314c.

The utterance position estimation unit 314b estimates the utterance position of the delivery person H1 of the delivery company based on the voice input signal generated by the input unit 13 of the intercom Int1. The input unit 13 is, for example, an array microphone, and is composed of a plurality of microphones, so that it can generate an audio input signal including information such as the direction of the uttered sound. The utterance position estimation unit 314b outputs the estimation result to the position matching unit 314c.

The position matching unit 314c compares the input estimation result by the face position estimation unit 314a and the estimation result by the utterance position estimation unit 314b, and determines the face position of the delivery person H1 of the delivery company (in other words, if there is a face). It is determined whether or not the estimated direction) matches the direction of the uttered voice included in the voice input signal. The position verification unit 314c outputs the determination result to the unlock determination unit 312.

The mouth motion detection unit 315a detects the mouth of the delivery person H1 of the delivery company based on the captured image captured by the imaging unit 15 of the intercom Int1. The mouth movement detection unit 315a detects the detected mouth movements over a predetermined period of time (for example, from immediately before the delivery person H1 of the delivery company starts speaking to immediately after the delivery person H1 finishes speaking). The mouth motion detection section 315a outputs the detection result (see FIG. 9) to the motion verification section 315c.

The utterance detection unit 315b detects the magnitude of the audio signal over a predetermined period of time based on the audio input signal generated by the input unit 13 of the intercom Int1. The utterance detection section 315b outputs the detection result (see FIG. 9) to the motion verification section 315c.

The motion verification unit 315c collates the input detection result by the mouth motion detection unit 315a and the estimation result of the utterance detection unit 315b (see FIG. 9), and determines the amount of mouth motion of the delivery person H1 of the delivery company at a predetermined time. It is determined whether or not the magnitude of the audio signal matches the magnitude of the audio signal. The operation verification unit 315c outputs the determination result to the unlock determination unit 312.

As a result, the courier authentication system prevents impersonation by another person, even if the other person impersonating the courier company's delivery person H1 uses a recorded voice Msg1 of the courier company's delivery person H1. It is possible to determine whether the

FIG. 6 is a flowchart illustrating an example of a two-way authentication procedure of the delivery agent authentication system. In the two-way authentication procedure of the delivery company authentication system shown in FIG. 6, an authentication procedure will be described in which the intercom Int1 outputs a speaking instruction in order to pick up another spoken voice.

The communication unit 30 receives a voice input signal based on the voice Msg1 uttered by the delivery person H1 of the delivery company from the intercom Int1 via the control device CD1 (St20).

The audio analysis unit 312a analyzes the received audio input signal. The speech analysis unit 312a determines a predetermined uttered word containing identification information about the company (for example, company name) included in the speech input signal and another predetermined uttered word containing identification information other than the identification information about the company. , extract (St21).

The identification information determining unit 312b determines whether the predetermined utterance word including the extracted identification information regarding the company is a pre-registered delivery company stored in the memory 32 (St22).

If the predetermined uttered word containing the identification information regarding the company extracted in step St22 is the identification information stored in the memory 32, the identification information determination unit 312b determines that the word is a registered delivery company (St22, YES). ), connects to the business registrant database DB1 (St23).

On the other hand, if the predetermined utterance word containing the identification information regarding the company extracted in step St22 is not the identification information stored in the memory 32, the identification information determination unit 312b determines that the utterance is not a registered delivery company (St22 , NO). The unlocking determining unit 132 outputs to the control device CD1 that the automatic locking system GT is not permitted to be unlocked, based on the determination result of the identification information determining unit 312b in step St12 (St24).

The control unit 31 generates a speech instruction control signal that instructs the delivery person H1 of the delivery company about the content of speech, and transmits it to the intercom Int1. The intercom Int1 outputs the content of the speech instruction from the output unit 14 in accordance with the received speech instruction control signal (St25).

The identification information determination unit 312b receives another voice input signal based on another speech signal of the delivery person H1 of the delivery company after the speech instruction in step St25. The identification information determination unit 312b extracts other identification information of the delivery person H1 of the delivery company included in the other audio input signals, and connects it to the company registrant database DB1. The identification information determination unit 312b connects to the business registrant database DB1 and refers to the identification information of each delivery person of the plurality of registered delivery companies (St26).

The identification information determination unit 312b refers to the identification information of each delivery person of a plurality of delivery companies and determines whether other identification information is registered in the company registrant database DB1 (in other words, if the delivery person of a delivery company It is determined whether H1 is a registrant registered in the business registrant database DB1 (St27).

If the other identification information of the delivery person H1 of the delivery company is the identification information registered in the business registrant database DB1 in step St27, the identification information determination unit 312b determines that the delivery person H1 of the delivery company is not registered. (St27, YES). Based on the determination result of the identification information determining section 312b in step St27, the unlocking determining section 132 outputs to the control device CD1 that the automatic locking system GT is permitted to be unlocked (St28).

On the other hand, in step St27, if the other identification information of the delivery company's delivery person H1 is identification information that is not registered in the business registrant database DB1, the identification information determination unit 312b determines that the delivery company's delivery person H1 is not a registered delivery company (St27, NO). The unlocking determining unit 132 outputs to the control device CD1 that the automatic locking system GT is not permitted to be unlocked, based on the determination result of the identification information determining unit 312b in step St27 (St24).

FIG. 7 is a flowchart showing an example of the utterance detection procedure of the delivery agent authentication system. In the utterance detection procedure of the delivery agent authentication system shown in FIG. 7, the authentication procedure when each part of the impersonation determination unit 313 performs determination will be described.

The communication unit 30 receives a voice input signal based on the voice Msg1 uttered by the delivery person H1 of the delivery company from the intercom Int1 via the control device CD1 (St30).

The utterance position estimating unit 314b estimates the utterance position of the delivery person H1 of the delivery company from the received voice input signal based on the voice uttered by the delivery person H1 of the delivery company (St31).

The face position estimation unit 314a estimates the position of the face of the delivery person H1 of the delivery company based on the received image of the delivery person H1 of the delivery company (St32).

The position matching unit 314c matches the utterance position of the delivery person H1 of the delivery company estimated in Step St31 with the face position of the delivery person H1 of the delivery company estimated in Step St32 (St33).

The position matching unit 314c determines whether or not the utterance position of the delivery person H1 of the delivery company matches the face position of the delivery person H1 of the delivery company, or the utterance position of the delivery person H1 of the delivery company, based on the matching result. It is determined whether the direction including the direction matches the direction in which the face of the delivery person H1 of the delivery company is located (St34).

As a result of the determination by the position matching unit 314c, if the utterance position of the delivery person H1 of the delivery company and the position of the face of the delivery person H1 of the delivery company match, or the utterance of the delivery person H1 of the delivery company If the direction including the position matches the direction in which the face of the delivery person H1 of the delivery company is located (St34, YES), further determination is performed using the mouth motion detection section 315a and the utterance detection section 315b. The mouth motion detection unit 315a detects the mouth motion of the delivery person H1 of the delivery company detected from the captured image captured by the imaging unit 15 of the intercom Int1 over a predetermined period of time. The utterance detection unit 315b detects the magnitude of the audio signal over a predetermined time based on the audio input signal generated by the input unit 13 of the intercom Int1 (St35).

On the other hand, if the utterance position of the delivery company's delivery person H1 matches the face position of the delivery company's delivery person H1 as a result of the judgment by the position matching unit 314c, or If the direction including the utterance position of H1 does not match the direction in which the face of the delivery person H1 of the delivery company is located (St34, NO), it is determined that the audio input signal is not the utterance of the delivery person H1 of the delivery company. (St36). When the utterance detection procedure of the delivery agent authentication system moves to the process of step St36, the process moves to the process of step St43 shown in FIG. 8. The unlocking determination unit 312 outputs to the control device CD1 that the automatic locking system GT is not permitted to be unlocked (St43).

The motion matching section 315c outputs the amount of mouth motion and the magnitude of the audio signal of the delivery person H1 of the delivery company at the same time based on the detection result by the mouth motion detection section 315a and the estimation result of the utterance detection section 315b. It is checked whether or not it is true (St37).

As a result of the verification in step St37, if the amount of mouth movement of the delivery person H1 of the delivery company and the magnitude of the audio signal are output at the same time, the action verification unit 315c determines that the audio input signal is the same as that of the delivery person H1 of the delivery company. It is determined that the utterance is from person H1 (St38, YES).

On the other hand, as a result of the verification in step St37, if the amount of mouth motion of the delivery person H1 of the delivery company and the magnitude of the audio signal are not output at the same time (St38, NO), the motion verification unit 315c determines that It is determined that the voice input signal is not the utterance of the delivery person H1 of the delivery company (St36). When the utterance detection procedure of the delivery agent authentication system moves to the process of step St36, the process moves to the process of step St43 shown in FIG. 8. The unlocking determination unit 312 outputs to the control device CD1 that the automatic locking system GT is not permitted to be unlocked (St43).

If the operation verification unit 315c determines in step St38 that the voice input signal is the utterance of the delivery person H1 of the delivery company, the unlock determination unit 132 determines whether the automatic lock system GT The control device outputs permission to unlock to the control device CD1 (St39). When the utterance detection procedure of the delivery agent authentication system moves to the process of step St39, the process moves to the process of step St40 shown in FIG. 8.

FIG. 8 is a flowchart illustrating an example of an authentication procedure using speech detection in the delivery agent authentication system. Each of the processes of steps St40 to St46 in the second embodiment is the same as each of steps St11 to St17 in FIG. 3 of the first embodiment, so the description thereof will be omitted.

The audio analysis unit 312a analyzes the received audio input signal after executing the process of step St39 in FIG. The speech analysis unit 312a extracts a predetermined uttered word containing identification information about the company (for example, company name) included in the speech input signal and another predetermined uttered word containing identification information other than the identification information about the company ( St40).

After executing the process of step St36 in FIG. 7, the unlocking determination unit 312 outputs to the control device CD1 that the automatic locking system GT is not permitted to be unlocked (St43).

FIG. 9 is a diagram illustrating an example of speech detection by the delivery company authentication system. Referring to FIG. 9, a process of comparing the mouth movement amount of the delivery person H1 of the delivery company and the magnitude of the audio signal in the movement matching unit 315c will be described.

A delivery person H1 of a delivery company outputs an uttered voice Msg1 saying, "Hello, this is XX Transport." In the example shown in FIG. 9, the delivery person H1 of the delivery company utters "Hello" out of the uttered voice Msg1 between time t1 and time t2, and utters "XX transport" out of the uttered voice Msg1 from time t3 to time t2. He speaks during t4.

The mouth movement amount MO1 is the mouth movement amount of the delivery person H1 of the delivery company at a predetermined time, detected by the mouth movement detection unit 315a. The mouth motion detection unit 315a detects a motion amount MO11 from time t1 when the delivery person H1 of the delivery company utters "Hello" in the uttered voice Msg1 to time t2, and utters "XX Transport" in the uttered voice Msg1. The operation amount MO12 is detected from time t3 to time t4.

The audio signal magnitude MO2 is the magnitude of the audio signal of the delivery person H1 of the delivery company at a predetermined time based on the input audio signal detected by the utterance detection unit 315b. The utterance detection unit 315b detects the audio signal MO21 from the time t1 when the delivery person H1 of the delivery company utters "Hello" to the time t2 from the utterance Msg1, and when the delivery person H1 of the delivery company utters "XX transport" from the utterance Msg1. Audio signal MO22 is detected from time t3 to time t4.

The motion matching section 315c matches the mouth motion amount MO1 detected by the mouth motion detection section 315a and the magnitude MO2 of the audio signal detected by the utterance detection section 315b. The motion matching unit 315c determines whether the motion amount MO11 and the audio signal MO21 are detected in the same time period T1, and furthermore, the motion amount MO12 and the audio signal MO22 are detected in the same time period T2. It is determined that the audio input signal is the utterance of the delivery person H1 of the delivery company.

As described above, in the delivery agent authentication method according to the second embodiment, in addition to the delivery agent authentication method according to the first embodiment, the server device S1 further performs the authentication of the delivery agent via the intercom Int1 (an example of a voice input terminal). An instruction regarding the utterance content is output to the delivery person H1, and another voice input signal based on the voice uttered by the delivery person H1 of the delivery company after the instruction is received. The server device S1 extracts other identification information that can identify the delivery person H1 of the delivery company based on the other received voice input signal, and refers to the company registrant database DB1 (an example of a database). It is determined whether other identification information of the extracted delivery person H1 of the delivery company is registered, and if the identification information of the delivery person H1 of the delivery company is registered, the automatic locking system GT is unlocked. Control. As a result, the courier authentication system can reduce the workload of the courier company's delivery person H1 due to redelivery due to the absence of the recipient, and also check whether someone else is impersonating the courier company's delivery person H1. can be determined.

As described above, in the delivery agent authentication method, the server device S1 receives the captured image of the delivery person H1 of the delivery company taken by the intercom Int1, and based on the received image of the delivery person H1 of the delivery company, the server device S1 Estimate the mouth position of delivery person H1 of the delivery company, estimate the source position of the uttered voice of delivery person H1 of the delivery company based on the received audio input signal, and estimate the mouth position of delivery person H1 of the delivery company. Then, the source position of the voice uttered by the delivery person H1 of the delivery company is compared to determine whether the audio input signal is the voice uttered by the delivery person H1 of the delivery company. As a result, the courier authentication system can reduce the workload of the courier company's delivery person H1 due to redelivery due to the absence of the recipient, and also check whether someone else is impersonating the courier company's delivery person H1. can be determined.

Although various embodiments have been described above with reference to the accompanying drawings, the present disclosure is not limited to such examples. It is clear that those skilled in the art can come up with various changes, modifications, substitutions, additions, deletions, and equivalents within the scope of the claims, and It is understood that it falls within the technical scope of the present disclosure. Further, each of the constituent elements in the various embodiments described above may be arbitrarily combined without departing from the spirit of the invention.

The present disclosure provides a courier authentication method, a courier authentication system, a server device, and a control device that can reduce the workload of a courier due to redelivery caused by the absence of a recipient. It is useful as a server device and a control device.

10, 20, 30 Communication section 11, 31 Control section 12, 22, 32 Memory 13 Input section 14 Output section 15 Imaging section 16 Speaker 17 Monitor 18 Lens 21 Unlocking control section CD1 Control device DB1 Trader registrant database GT Automatic locking system H1 Delivery company's delivery person Int1 Intercom Msg1 Speech voice S1 Server device

Claims (4)

A delivery agent authentication method using the delivery person's uttered voice performed by a server device , the method comprising:
receiving a voice input signal based on the voice uttered by the delivery person collected by a voice input terminal;
extracting identification information that can identify the delivery person based on the received voice input signal;
Determining whether the extracted delivery person identification information is registered by referring to a database containing identification information of each delivery person of a plurality of delivery companies registered in advance;
If the delivery person's identification information is registered , outputting an instruction regarding the content of the utterance to the delivery person via the voice input terminal;
receiving another audio input signal based on the utterance voice of the delivery person uttering the utterance content and a captured image of the delivery person uttering the utterance content captured by the audio input terminal;
detecting the movement of the delivery person's mouth based on the captured image;
verifying whether an operation period in which the delivery person's mouth is operating and an output period of the delivery person's audio signal based on the other audio input signal are output in substantially the same time zone;
If it is determined that the operation period and the output period of the audio signal are output in substantially the same time zone, an automatic locking system is installed to control permission to enter a predetermined area accessible to the front door of the delivery destination residence. control unlocking,
Courier authentication method. estimating the position of the delivery person's mouth based on the received captured image of the delivery person;
estimating a sound source position of the delivery person's speech based on the received audio input signal;
comparing the estimated mouth position of the delivery person and the sound source position of the delivery person's speech to determine whether the audio input signal is the delivery person's speech;
The delivery agent authentication method according to claim 1. A delivery agent authentication system in which a control device that controls an automatic locking system and a server device can communicate,
The control device includes:
Receive a voice input signal based on the delivery person's voice recorded by the voice input terminal,
transmitting the received audio input signal to the server device;
The server device includes:
extracting identification information that can identify the delivery person based on the received voice input signal;
Determining whether the extracted delivery person identification information is registered by referring to a database containing identification information of each delivery person of a plurality of delivery companies registered in advance;
If the delivery person's identification information is registered , outputting an instruction regarding the content of the utterance to the delivery person via the voice input terminal;
receiving another audio input signal based on the utterance voice of the delivery person uttering the utterance content and a captured image of the delivery person uttering the utterance content captured by the audio input terminal;
detecting the movement of the delivery person's mouth based on the captured image;
verifying whether an operation period in which the delivery person's mouth is operating and an output period of the delivery person's audio signal based on the other audio input signal are output in substantially the same time zone;
If it is determined that the operation period and the output period of the audio signal are output in substantially the same time zone, an unlocking signal for permitting unlocking of the automatic locking system is generated and transmitted to the control device. ,
The control device includes:
controlling the automatic locking system to unlock based on the received unlocking signal;
Courier certification system. an utterance instruction unit that instructs the delivery person to utter;
an identification information extraction unit that extracts identification information of the delivery person based on a voice input signal based on the voice uttered by the delivery person received by the voice input terminal;
a registrant determining unit that refers to a database containing identification information of each of delivery persons of a plurality of pre-registered delivery companies and determines whether or not the extracted delivery person identification information is registered;
a detection unit that detects a movement of the delivery person's mouth based on a captured image of the delivery person captured by the voice input terminal;
a verification unit that verifies whether an operating period in which the delivery person's mouth is operating and an output period of the delivery person's audio signal based on the audio input signal are output in substantially the same time zone;
an unlocking permission section for unlocking an automatic locking system that controls entry permission to a predetermined area accessible in front of the entrance of the delivery destination house ;
When the delivery person identification information is registered, the registrant determination unit outputs an instruction regarding the utterance content to the delivery person via the voice input terminal;
The detection unit receives another audio input signal based on the voice uttered by the delivery person after the instruction, and a captured image of the delivery person captured by the audio input terminal, and generates a signal based on the captured image. , detecting the mouth movements of the delivery person;
The unlocking permission unit generates an unlocking permission signal when determining that the operation period and the output period of the audio signal are output in substantially the same time zone.
server equipment.

Images