Parking lot management system, parking lot management method, and program

Abstract

To provide a parking lot management system, a parking lot management method, and a program that can improve convenience of a parking lot user.SOLUTION: A parking lot management system according to one embodiment of the present invention includes a voice data acquisition unit and an inquiry response unit. The voice data acquisition unit acquires voice data of an inquiry related to use of a parking lot input by voice from a parking lot user. The inquiry response unit executes, on the basis of the acquired voice data of the inquiry, predetermined response processing related to use of the parking lot. In addition, the inquiry response unit is configured to generate, on the basis of the voice data of the inquiry, response data for realizing dialogue with the user, and to execute, on the basis of contents of the dialogue with the user, the response processing.SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] The present invention relates to a parking lot management system, a parking lot management method, and a program. [Background technology]

[0002] Patent Document 1 discloses a parking lot system that does not require the issuance of parking tickets. In this parking lot system, when a user attempts to enter or exit a vehicle, the vehicle number is recognized by a vehicle recognition device. The recognized vehicle number is displayed to the user, who can check whether it was recognized correctly. If the user determines that the displayed vehicle number is incorrect, the user can correct it on the spot, or an attendant can correct it remotely. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2003-132379 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a demand for technology that can improve the convenience of parking lot users.

[0005] In view of the above circumstances, an object of the present invention is to provide a parking lot management system, a parking lot management method, and a program that can improve the convenience of users of parking lots. [Means for solving the problem]

[0006] In order to achieve the above object, a parking lot management system according to one embodiment of the present invention comprises a voice data acquisition unit and an inquiry response unit. The voice data acquisition unit acquires voice data of an inquiry about use of the parking lot input by voice from a user of the parking lot. The inquiry response unit executes a predetermined response process regarding use of the parking lot based on the acquired voice data of the inquiry. The inquiry response unit is configured to generate response data for realizing a dialogue with the user based on the voice data of the inquiry, and to execute the response processing based on the content of the dialogue with the user.

[0007] The parking lot management system may further include a fee presentation unit that calculates a parking fee for the vehicle based on entering vehicle information extracted from an entering vehicle image taken when the vehicle enters the parking lot and exiting vehicle information extracted from an exiting vehicle image taken when the vehicle leaves the parking lot, and presents the calculated parking fee to the user. In this case, the inquiry response unit may determine whether or not the entering vehicle information matches the exiting vehicle information of the user's vehicle based on the inquiry voice data input by the user, indicating that the parking fee presentation unit will not present the parking fee, and if the determination is negative, may generate the answer data including a question regarding the circumstances when the user entered the vehicle or a question regarding the characteristics of the user's vehicle.

[0008] The inquiry response unit may identify the vehicle of the user based on the content of a dialogue with the user realized using the answer data, which includes a question about the situation when the user entered the parking lot or a question about the characteristics of the vehicle of the user. In this case, the fee presentation unit may calculate the parking fee for the identified vehicle of the user and present it to the user.

[0009] The parking lot management system may further include a settlement execution unit that executes settlement of the parking fee for the vehicle based on entering vehicle information extracted from an entering vehicle image taken when the vehicle enters the parking lot and vehicle information regarding the user's vehicle input by the user. In this case, the inquiry response unit may determine whether the vehicle information input by the user is correct based on voice data of the inquiry input by the user indicating that the parking fee has been settled based on the input of the vehicle information but the vehicle's status is not settled, and if the determination is negative, may generate the response data including an indication that the vehicle information input by the user is incorrect.

[0010] If the determination as to whether the vehicle information entered by the user is correct is negative, the inquiry response unit may generate the response data including information regarding the method of settling the parking fee for the user's vehicle.

[0011] The inquiry response unit may determine whether or not a fee has been incurred for the excess parking time based on the voice data of the inquiry input by the user, which indicates that the parking fee has been settled based on the input of the vehicle information but the vehicle has not yet reached the settled state, and if the determination is positive, may generate the response data including information that a fee has been incurred for the excess parking time.

[0012] The inquiry response unit may calculate the parking fee for an unexited vehicle that matches the vehicle information entered by the user based on the inquiry voice data input by the user, informing the user that there is no vehicle of the user that is eligible for settlement when the vehicle information is entered, and generate the response data including information regarding the settlement method for the calculated parking fee.

[0013] The inquiry response unit may generate the response data including the reason why the user is notified that the user's vehicle does not exist, based on the voice data of the inquiry input by voice from the user, informing the user that the user's vehicle that is eligible for settlement will not exist when the vehicle information is input.

[0014] The inquiry response unit may generate the response data including information on how to pay the parking fee at a later time based on the voice data of the inquiry input by the user, which instructs that payment of the parking fee at the current time is impossible.

[0015] The inquiry response unit may generate the response data indicating that the user will be contacted at a later time, based on voice data of the inquiry including a complaint input by voice from the user.

[0016] The inquiry response unit may execute a report to a predetermined report destination based on voice data of the inquiry input by the user, the voice data including an indication that the emergency situation exists.

[0017] The parking lot management system may further include a dialogue execution unit that executes a dialogue with the user by outputting the response data as at least one of audio and image, and a photographing unit that photographs the user who is having a dialogue with the dialogue execution unit.

[0018] The dialogue execution unit may have an image display unit, and may display text data corresponding to voice data input by voice from the user during the dialogue, including the voice data of the inquiry, on the image display unit.

[0019] The parking lot management system may further include a storage unit that stores information on at least one of the content of the dialogue including the user's inquiry and the content of the response processing as response history information.

[0020] The parking lot management system may further include an issuing unit that issues a receipt or invoice displaying information regarding at least one of the content of the dialogue, including the user's inquiry, and the content of the response processing.

[0021] The issuing unit may issue the receipt or invoice displaying information on a method for paying the unpaid parking fee.

[0022] The issuing unit may issue the receipt or invoice on which a code image is displayed that stores a URL of a website that includes the response history information.

[0023] The inquiry response unit may connect the user making the inquiry to an operator so that the user can have a conversation with the operator when a predetermined operator connection condition is satisfied.

[0024] A parking lot management method according to one embodiment of the present invention is a parking lot management method executed by a computer system, and includes a voice data acquisition step of acquiring voice data of an inquiry regarding use of the parking lot input by voice from a parking lot user, and an inquiry response step of executing a predetermined response process regarding use of the parking lot based on the acquired voice data of the inquiry. The inquiry response step generates response data for realizing a dialogue with the user based on the voice data of the inquiry, and executes the response process based on the content of the dialogue with the user.

[0025] A program according to one aspect of the present invention is a program for causing a computer system to execute the parking lot management method. [Effects of the Invention]

[0026] As described above, according to the present invention, it is possible to improve the convenience of users who use parking lots. [Brief explanation of the drawings]

[0027] [Figure 1] 1 is a schematic diagram showing an example of the configuration of a parking lot management system according to an embodiment of the present invention; [Figure 2] FIG. 1 is a schematic diagram showing a specific example of the configuration of a parking lot. [Figure 3] FIG. 2 is a block diagram showing an example of the hardware configuration of the settlement device. [Figure 4] FIG. 2 is a block diagram showing an example of the functional configuration of the settlement device. [Figure 5] FIG. 2 is a block diagram illustrating an example of a functional configuration of a machine response device. [Figure 6] 10 is a flowchart showing an example of a basic operation when a vehicle enters. [Figure 7] FIG. 2 is a schematic diagram showing an example of parking information. [Figure 8] 10 is a flowchart showing an example of the basic operation of the prepayment device at the time of prepayment. [Figure 9] 10 is a flowchart showing an example of the basic operation of the settlement device when exiting. [Figure 10] 10 is a flowchart illustrating an example of a basic operation of responding to an inquiry. [Figure 11] FIG. 2 is a schematic diagram showing an example of information and data stored in a DB for executing a response process and generating response data. [Figure 12] 10A and 10B are diagrams illustrating an example of a settlement screen and a response image displayed on the touch panel of the settlement device. [Figure 13] FIG. 10 is a diagram showing another example of a response image displayed on the touch panel of the settlement device. [Figure 14] FIG. 10 is a schematic diagram showing an example of an issued receipt. [Figure 15] FIG. 1 is a block diagram showing an example of the hardware configuration of a computer that can be used as a machine response device or the like. DETAILED DESCRIPTION OF THE INVENTION

[0028] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0029] [Parking lot management system] 1 is a schematic diagram showing an example of the configuration of a parking lot management system according to one embodiment of the present invention. The parking lot management system 1 includes a mobile terminal 2, a parking lot management device 3, a management institution terminal 4, a payment server device (not shown) owned by a payment institution 5, a store terminal 7 located in a store 6, and an owner terminal 8. The parking lot management system 1 also includes a mechanical response device 10 located in a parking lot 9.

[0030] 1, these devices are connected to each other so that they can communicate with each other via a network 11. The network 11 is constructed, for example, by the Internet or a wide area communication network. Alternatively, any WAN (Wide Area Network) or LAN (Local Area Network) may be used, and the protocol for constructing the network 11 is not limited.

[0031] The mobile terminal 2 is a terminal used by a user 12 who uses the parking lot 9. A smartphone is typically used as the mobile terminal 2, but the mobile terminal 2 is not limited to this and various PDAs (Personal Digital Assistants) such as tablet terminals may also be used.

[0032] The owner terminal 8 is a terminal used by the owner of the parking lot 9. As the owner terminal 8, any computer such as a smartphone, a tablet terminal, or various types of PC (Personal Computer) may be used.

[0033] The parking lot management device 3 is a device that manages the parking lot 9, and is capable of providing the parking lot management service according to this embodiment as a Web service.

[0034] The parking lot management device 3 has hardware necessary for a computer, such as processors such as a CPU, GPU, and DSP, memories such as a ROM and RAM, and storage devices such as an HDD.

[0035] The parking lot management device 3 also has a communication unit for communicating with other terminals and devices via the network 11. The communication unit may be, for example, a wireless LAN module such as WiFi, or a communication device such as a modem or a router. The parking lot management device 3 may be, for example, any computer such as a PC.

[0036] As shown in Fig. 1, a database (DB) 13 is connected to the parking lot management device 3. DB 13 functions as a storage unit and stores various information related to the parking lot management service. For example, various DBs can be created in DB 13, such as a vehicle presence DB, parking information DB, parking lot DB, store usage DB, shopping information DB, discount DB, departure information DB, user DB, owner information DB, various history DBs, vehicle information DB, and response history information DB.

[0037] The various databases are comprehensively managed by the parking lot management device 3, and for example, the databases perform functions such as registering and canceling membership for users 12 who use the parking lot management service, registering and storing owner information for each parking lot 9, and recording and storing operating income and expenditure information.

[0038] In this embodiment, a web page is generated by the parking lot management device 3. The generated web page is displayed on the screen by web browsers provided in the mobile terminal 2, the parking lot management device 3, the management institution terminal 4, the payment server device owned by the payment institution 5, the store terminal 7, and the owner terminal 8 via the network 11 shown in Fig. 1. For example, a user 12 who uses the parking lot 9 or the owner of the parking lot 9 can view various web pages and use various web applications by operating the mobile terminal 2 or the owner terminal 8.

[0039] The management agency terminal 4 is used by an operator 14 of the management agency who has been entrusted with the management of the parking lot 9 by the owner of the parking lot 9. The operator 14 handles, for example, daily inquiries, responds to users, and provides information on maintenance work in the event of a malfunction of each device installed in the parking lot 9. A PC, tablet terminal, or the like is used as the management agency terminal 4.

[0040] In some cases, the owner of the parking lot 9 may manage the parking lot 9 himself. In this case, a terminal owned by the owner may function as the management agency terminal 4. It is also possible that the management agency entrusted with the management operations may own the parking lot management device 3 and provide the parking lot management service according to this embodiment.

[0041] The settlement institution 5 is, for example, a bank or a credit company, and executes payment (settlement) of parking fees by bank transfer, credit card payment, etc. The parking lot management device 3 executes instructions to settle parking fees to the settlement server device of the settlement institution 5, inquiries about settlement information such as whether the settlement has been completed, etc.

[0042] The store terminal 7 is installed in each store 6 that has a partnership with the parking lot 9 regarding discount services. For example, a partnership regarding discount services may be formed with a nearby commercial facility, but the present invention is not limited to this.

[0043] The store terminal 7 may be, for example, a POS register with a communication function. The store terminal 7 and the parking lot management device 3 may indirectly (via a POS register server, etc.) share information about parking fee discounts. The specific configuration and type of the store terminal 7 are not limited.

[0044] In this embodiment, the store 6 affiliated with the parking lot 9 corresponds to one embodiment of a facility affiliated with the parking lot. The present technology can also be applied to any facility that may not be classified as a so-called store, such as a hospital or public facility. The store terminal 7 is a terminal of a facility affiliated with the parking lot.

[0045] Fig. 2 is a schematic diagram showing a specific configuration example of a parking lot 9. The parking lot 9 has an entrance 15 and an exit 16. As shown in Fig. 2, a central island 17 is installed between the entrance 15 and the exit 16. In addition, an entrance island 18 and an exit island 19 are installed on either side of the central island 17.

[0046] The area between the central island 17 and the entrance island 18 is the entrance lane 20 of the parking lot 9. The area between the central island 17 and the exit island 19 is the exit lane 21 of the parking lot 9.

[0047] A prepayment device 23, a prepayment monitoring camera 24, and a mechanical response device 10 are installed within the parking lot 9 premises 22. A payment device 25, an exit gate 26, an entrance camera 27, and an exit camera 28 are also installed within the central island 17. Although not shown in the figure, a premises monitoring camera is also installed within the premises 22.

[0048] The prepayment device 23 is a device that allows the user 12 to prepay for parking fees. The prepayment monitoring camera 24 is placed in a position that allows it to capture an image of the user 12 making prepayment. The prepayment monitoring camera 24 can also capture an image of the user 12 making a voice inquiry to the prepayment device 23.

[0049] The mechanical response device 10 is a device for realizing a mechanical response to an inquiry from a user 12, and will be described in detail later.

[0050] The settlement device 25 is a device that allows users 12 who have not paid in advance to settle the parking fee while they are in their vehicles when they exit the vehicle. The exit gate 26 is a device that restricts the exit of vehicles from the parking lot 9.

[0051] The entrance camera 27 is placed in a position where it can capture an image of the entering vehicle 30 (hereinafter referred to as the entering vehicle image) entering the entrance lane 20. The entering vehicle image is an image captured when the vehicle enters the parking lot 9.

[0052] The exit camera 28 is disposed in a position where it can capture an image of the exit vehicle 31 (hereinafter referred to as an exit vehicle image) entering the exit lane 21. The exit vehicle image is an image captured when the vehicle exits the parking lot 9.

[0053] The exit camera 28 is also placed in a position where it can capture an image of the user 12 making the payment. The exit camera 28 can also capture an image of the user 12 making a voice inquiry to the payment device 25.

[0054] Digital cameras equipped with image sensors such as CMOS (Complementary Metal-Oxide Semiconductor) sensors or CCD (Charge Coupled Device) sensors are used as the pre-payment monitoring cameras 24, entrance cameras 27, and exit cameras 28. Other types of cameras may also be used.

[0055] The pre-payment device 23, pre-payment monitoring camera 24, machine response device 10, payment device 25, exit gate 26, entrance camera 27, and exit camera 28 are connected by on-site wiring 32 (see Figures 1 and 3) installed within the premises 22 of the parking lot 9.

[0056] A first entrance loop coil 33 and a second entrance loop coil 34 are buried in the ground of the entrance lane 20. A first exit loop coil 35 and a second exit loop coil 36 are buried in the ground of the exit lane 21.

[0057] 3 is a block diagram showing an example of the hardware configuration of the settlement device 25. The settlement device 25 has a CPU 38, a memory 39, and an interface 41 connected to these via a bus 40. The memory 39 is composed of, for example, ROM, RAM, flash memory, etc., and stores various programs, various parking data, etc. Of course, the settlement device 25 may also be equipped with a storage device such as an HDD.

[0058] Connected to the interface 41 are a touch panel 42, a speaker 43, a microphone 44, a bill and coin management unit 45, a receipt printer 46, a short-range wireless communication unit 47, and an in-house communication unit 48. The operation of each block is controlled by the CPU 38, which operates according to a program.

[0059] The touch panel 42 has an image display function and a function of accepting various touch operations from the user. The speaker 43 has an audio output function. The microphone 44 has a sound collection function. The specific configurations of the touch panel 42, the speaker 43, and the microphone 44 are not limited, and any configuration may be adopted.

[0060] The bill and coin management unit 45 receives bills and coins inserted into the bill insertion slot and coin insertion slot, counts them, calculates the inserted amount, and also counts the change required for settlement and dispenses it into the coin / receipt outlet.

[0061] The receipt printer 46 prints the settlement amount, date and time, etc. on receipt paper and issues a receipt. The issued receipt can be collected from the coin / receipt outlet. In this embodiment, the receipt printer 46 also prints information related to the machine response, which will be described in detail later.

[0062] The short-range wireless communication unit 47 is a module for performing short-range wireless communication with other devices. For example, the short-range wireless communication unit 47 may be provided with a Bluetooth (registered trademark) module, an NFC (Near Field Communication) module, or the like.

[0063] The on-site communication unit 48 is equipped with a communication circuit and is communicatively connected via on-site wiring 32 to the pre-payment device 23, the pre-payment monitoring camera 24, the machine response device 10, the payment device 25, the exit gate 26, the entrance camera 27, and the exit camera 28.

[0064] 4 is a block diagram showing an example of the functional configuration of the settlement device 25. The settlement device 25 has a vehicle detection unit 50, a gate control unit 51, a settlement unit 52, an input reception unit 53, a voice data acquisition unit 54, and a display control unit 55. These blocks are configured by the CPU 38 executing a predetermined program, and processing for realizing the parking lot management method according to this embodiment is realized. Note that dedicated hardware such as an IC (integrated circuit) may be used as appropriate to configure each block.

[0065] The vehicle detection unit 50 detects the entry of a vehicle into the entrance lane 20 and the entry of a vehicle into the premises 22 based on signals output from the first and second entrance loop coils 33 and 34. The vehicle detection unit 50 also detects the entry of a vehicle into the exit lane 21 and the exit of a vehicle to the outside based on signals output from the first and second exit loop coils 35 and 36.

[0066] Any other configuration may be adopted as the configuration for detecting vehicles entering the entrance lane 20 and the exit lane 21. For example, an optical sensor using infrared rays or the like may be used.

[0067] The gate control unit 51 controls the operation of the exit gate 26. The settlement unit 52 executes the settlement of parking fees. The input reception unit 53 receives various touch operations input to the touch panel 42 and outputs operation signals corresponding to the touch operations to each block. The voice data acquisition unit 54 acquires voice data (voice signals) converted into electrical signals by the microphone 44. The display control unit 55 controls image display on the touch panel 42.

[0068] In this embodiment, the hardware configuration and functional configuration of the pre-payment device 23 are substantially the same as the hardware configuration of the payment device 25 shown in Fig. 3 and the functional configuration of the payment device 25 shown in Fig. 4. The difference is that the payment device 25 has a vehicle detection function, but the pre-payment device 23 has a user detection function instead of the vehicle detection function.

[0069] For example, the pre-payment device 23 may be equipped with an arbitrary human presence sensor. Then, instead of the vehicle detection unit 50 shown in FIG. 4, a user detection unit may be configured as a functional block. This makes it possible to realize a user detection function. Any configuration may be adopted to realize the user detection function. Furthermore, the pre-payment device 23 does not have a gate control unit 51.

[0070] 3 and 4, blocks that are common to the settlement device 25 and the pre-settlement device 23 will be described using the same reference numerals. For example, expressions such as "the settlement unit 52 of the settlement device 25" and "the settlement unit 52 of the pre-settlement device 23" will be used.

[0071] The settlement device 25 and the pre-settlement device 23 can perform settlement processes including, for example, calculating parking fees, displaying on the touch panel 42 and outputting audio from the speaker 43, counting the coins and banknotes inserted, calculating whether or not change is available, and paying out change.

[0072] In this embodiment, the settlement device 25 and the pre-settlement device 23 are controlled by the mechanical response device 10, thereby realizing a mechanical response to an inquiry from the user 12.

[0073] 5 is a block diagram showing an example of the functional configuration of the mechanical response device 10. The mechanical response device 10 has hardware necessary for a computer, such as a processor such as a CPU, GPU, or DSP, memory such as a ROM or RAM, and a storage device such as an HDD.

[0074] The mechanical response device 10 also has a communication unit for communicating with other terminals and devices via the network 11. The communication unit may be, for example, a wireless LAN module such as WiFi, or a communication device such as a modem or router. The mechanical response device 10 may be, for example, any computer such as a PC.

[0075] The machine response device 10 is communicatively connected to the prepayment device 23, the prepayment monitoring camera 24, the payment device 25, the exit gate 26, the entrance camera 27, and the exit camera 28 via the on-site wiring 32.

[0076] For example, the machine response device 10 can be used to connect the pre-payment device 23, pre-payment monitoring camera 24, payment device 25, exit gate 26, entrance camera 27, and exit camera 28 to devices on the network 11 such as the parking lot management device 3 and management agency terminal 4 so that they can communicate with each other.

[0077] For example, the machine response device 10 can connect the user 12 and the operator 14 using the management institution terminal 4 via the settlement device 25 and the pre-settlement device 23 so that they can converse with each other. In other words, the machine response device 10 can connect each of the settlement device 25 and the pre-settlement device 23 with the management institution terminal 4 so that the user 12 and the operator 14 can converse with each other.

[0078] As shown in Figures 1 and 5, a DB 57 is connected to the mechanical response device 10. The DB 57 functions as a storage unit and stores various information related to the parking lot management service. In this embodiment, the DB 57 stores various captured images, parking information, response pattern information, response history information, FAQs, manuals, etc. Of course, there may be cases where the data stored in the DB 13 of the parking lot management device 3 shown in Figure 1 is shared.

[0079] As shown in FIG. 5, the mechanical response device 10 includes an image management unit 59, a vehicle information recognition unit 60, a voice data acquisition unit 61, a speech intention analysis unit 62, a response data generation unit 63, a response processing execution unit 64, and a response image generation unit 65.

[0080] These blocks are configured by the processor of the machine response device 10 executing a predetermined program and cooperating with the hardware resources within the device, thereby realizing the processing for realizing the parking lot management method according to this embodiment. Note that dedicated hardware such as an IC (integrated circuit) may be used as appropriate to configure each block.

[0081] The program is installed in the mechanical response device 10, for example, via various recording media. Alternatively, the program may be installed via the Internet or the like. There are no limitations on the type of recording medium on which the program is recorded, and any computer-readable recording medium may be used. For example, any computer-readable non-transitory storage medium may be used.

[0082] The image management unit 59 manages images taken by cameras arranged in the parking lot 9. In this embodiment, images of users 12 making prepayments taken by the prepayment monitoring camera 24 and images of users 12 making voice inquiries to the prepayment device 23 are managed. Images of entering vehicles taken by the entrance camera 27 are also managed. Images of exiting vehicles taken by the exit camera 28, images of users 12 making payment, and images of users 12 making voice inquiries to the payment device 25 are also managed.

[0083] The vehicle information recognition unit 60 extracts vehicle information about entering vehicles (hereinafter referred to as entering vehicle information) from the entering vehicle images. The vehicle information recognition unit 60 also extracts vehicle information about entering vehicles (hereinafter referred to as exiting vehicle information) from the exiting vehicle images.

[0084] For example, the vehicle information extracted may include at least a part of the vehicle number, the vehicle name, the vehicle color, the vehicle manufacturer, etc. A combination of these or other information related to the vehicle may also be extracted as the vehicle information.

[0085] At least some of the information in the vehicle number (such as the name of the local land transport bureau, classification number, hiragana characters, and a four-digit serial number) can be recognized by techniques such as image processing that extracts a portion of the license plate, OCR (Optical Character Recognition) processing, etc. Of course, any other techniques may also be used.

[0086] The voice data acquisition unit 61 receives voice data acquired by the voice data acquisition unit 54 of the settlement device 25 or the pre-payment device 23. In this embodiment, the voice data acquisition unit 61 acquires voice data of inquiries about use of the parking lot 9 input by voice from users 12 of the parking lot 9 via the settlement device 25 or the pre-payment device 23.

[0087] The speech intention analysis unit 62 analyzes the intention of the inquiry made by the user 12 based on the voice data of the inquiry acquired by the voice data acquisition unit 61.

[0088] When a dialogue with the user 12 continues, including an inquiry from the user 12, the voice data acquisition unit 61 acquires voice data of the utterances of the user 12 in the dialogue. Then, the utterance intention analysis unit 62 analyzes the intention of each utterance of the user 12 in the dialogue. Of course, the same inquiry or a different inquiry may be made in the dialogue. In that case, the intention of each inquiry is analyzed.

[0089] In the present disclosure, the dialogue is not limited to a dialogue between voices. For example, a dialogue may be conducted using only messages exchanged between the parties without using voices. Of course, a dialogue may also be conducted using both voices and messages.

[0090] The response data generating unit 63 generates response data for realizing a dialogue with the user 12 based on the voice data of the inquiry from the user 12 and the intention of the inquiry (utterance intention).

[0091] The response processing execution unit 64 executes a predetermined response processing regarding the use of the parking lot 9 based on the voice data of the inquiry of the user 12 and the intention of the inquiry (utterance intention). The response processing includes any processing for responding to the inquiry of the user 12. In this embodiment, the response processing execution unit 64 is configured to be able to execute the response processing based on the content of the dialogue held with the user 12.

[0092] The response image generation unit 65 generates a response image and transmits it to the settlement device 25 or the pre-settlement device 23. The transmitted response image is displayed on the touch panel 42 by the display control unit 55 of the settlement device 25 and the pre-settlement device 23.

[0093] The response image is an image to be viewed by the user 12 who made the voice inquiry, and for example, the content of the inquiry from the user 12, the content of the dialogue including the inquiry and the answer, the content of the response process, etc. are displayed as appropriate using text data. Of course, it is also possible to display GUIs such as icons and buttons.

[0094] Before explaining the machine response to inquiries according to the present invention, the basic operations of the parking lot management system 1 when a vehicle enters, when a prepayment is made, and when a vehicle leaves will be explained.

[0095] 6 is a flowchart showing an example of the basic operation when a vehicle enters. The vehicle detection unit 50 of the settlement device 25 monitors the detection of an entering vehicle 30 (step 101). If an entering vehicle 30 is detected (YES in step 101), an image of the entering vehicle is taken by the entrance camera 27 (step 102).

[0096] The captured image of the entering vehicle is transmitted to the mechanical response device 10 and managed by the image management unit 59. The vehicle information recognition unit 60 of the mechanical response device 10 extracts the entering vehicle information (step 103). In this embodiment, the extracted entering vehicle information includes the vehicle number, vehicle name information, vehicle body color information, vehicle manufacturer information, etc.

[0097] The vehicle detection unit 50 monitors the entry of a vehicle into the premises 22 of the parking lot 9 (step 104). If entry into the premises 22 of the parking lot 9 is detected (YES in step 104), the parking information is registered.

[0098] 7 is a schematic diagram showing an example of parking information. Parking information 66 is generated in response to the entry of a vehicle into a parking lot 9, and is managed with an ID (not shown) assigned. In this embodiment, the following information (data) is stored as the parking information 66:

[0099] "Entering vehicle image": A link to an entering vehicle image managed by the image management unit 59 is stored. "Parking status": Information indicating the usage status of the parking lot 9. For example, information such as "entered (not yet exited)", "exited", and "unauthorized use" is stored. "Payment status": Information indicating the payment status of the parking fee. For example, information such as "paid" or "unpaid" is stored. "Entry date and time": Information on the entry date and time of the vehicle of the user 12. In this embodiment, the date and time when the image of the entering vehicle was taken by the entrance camera 27 is stored as the entry date and time. "Departure date and time": Information on the departure date and time of the vehicle of the user 12. In this embodiment, the date and time when the image of the exiting vehicle was taken by the exit camera 28 is stored as the departure date and time. "Vehicle number": The vehicle number of user 12's vehicle. "Vehicle-related information": Vehicle information other than the vehicle number of the vehicle of the user 12. In this embodiment, vehicle name information, vehicle body color information, vehicle manufacturer information, etc. are stored.

[0100] In step 105 shown in Figure 6, a link to the entering vehicle image is stored in "entering vehicle image," and "entered (not yet exited)" is stored in "parking status." Also, "unsettled" is stored in "payment status," and the date and time the entering vehicle image was taken is stored in "entry date and time." Note that "exit date and time" is left blank.

[0101] The "vehicle number" stores the vehicle number of the vehicle of the user 12 extracted in step 103, and the "vehicle related information" stores vehicle information other than the vehicle number.

[0102] 8 is a flowchart showing an example of the basic operation of the pre-payment device 23 during pre-payment. The user detection unit of the pre-payment device 23 monitors the detection of the user 12 (step 201). If the user 12 is detected (YES in step 201), a vehicle number input screen is displayed on the touch panel 42 of the pre-payment device 23 (step 202).

[0103] The vehicle number input screen displays, for example, text data such as "Please enter a four-digit vehicle number," a numeric keypad for inputting the vehicle number, and four display fields in which the input four-digit vehicle numbers are displayed one by one. The user 12 can operate the numeric keypad to input the four-digit vehicle number of his / her vehicle.

[0104] The input of the vehicle number by the user 12 is monitored (step 203), and when the vehicle number is input (YES in step 203), the settlement process is executed (step 204).

[0105] Before the payment process, the parking information 66 shown in FIG. 7 may be searched in response to the input of the vehicle number, and an image of the entering vehicle may be displayed on the touch panel 42 based on the parking information 66 with a matching vehicle number. Then, text data or a voice message such as "Is this the correct vehicle?" may be output, allowing the user to confirm the vehicle.

[0106] 7 is searched in response to the input of the vehicle number, and parking information 66 with a matching vehicle number is displayed. If multiple entering vehicle images are displayed, the parking fee is calculated based on the "entry date and time" of the parking information 66 linked to the entering vehicle image selected by the user 12 from among them and the current date and time, and is displayed to the user 12.

[0107] Specifically, a payment screen including the calculated parking fee is displayed on the touch panel 42 of the prepayment device 23. The parking fee may be output by voice from the speaker 43 of the prepayment device 23.

[0108] The bill and coin management unit 45 and receipt printer 46 of the pre-payment device 23 operate, and the payment operation by the user 12 is accepted. When the payment of the parking fee is completed, the parking information 66 is updated (step 205). Specifically, the "payment status" of the parking information 66 shown in Figure 7 is updated from "unpaid" to "paid."

[0109] 9 is a flowchart showing an example of the basic operation of the adjustment device 25 at the time of exit. The vehicle detection unit 50 of the adjustment device 25 monitors the detection of an exiting vehicle 31 (step 301). If an exiting vehicle 31 is detected (YES in step 301), an image of the exiting vehicle is taken by the exit camera 28 (step 302).

[0110] The captured images of the participating vehicles are transmitted to the mechanical response device 10 and managed by the image management unit 59. The vehicle information recognition unit 60 of the mechanical response device 10 extracts participating vehicle information (step 303). In this embodiment, the extracted participating vehicle information includes the vehicle number, vehicle name information, vehicle body color information, vehicle manufacturer information, etc.

[0111] It is determined whether the parking fee for the exiting vehicle 31 has been paid (step 304). In this embodiment, the parking information 66 that matches the exiting vehicle information extracted in step 303 is searched for and automatically selected. The "payment status" of the selected parking information 66 is referenced, and if it is "unpaid," the determination is negative, and if it is "paid," the determination is positive.

[0112] If the parking fee for the exiting vehicle 31 has not been settled (NO in step 304), the settlement process is executed (step 304). In this embodiment, as the settlement process, the parking fee is calculated based on the "entry date and time" of the selected parking information 66 and the current date and time, and is presented to the user 12.

[0113] Specifically, a payment screen including the calculated parking fee is displayed on the touch panel 42 of the payment device 25. The parking fee may be output by voice from the speaker 43 of the payment device 25.

[0114] The bill and coin management unit 45 and receipt printer 46 of the settlement device 25 operate to accept the settlement operation by the user 12. When the parking fee settlement is complete, the gate control unit 51 opens the exit gate 26 (step 306).

[0115] If the parking fee for the exiting vehicle 31 has already been paid (YES in step 304), the payment process is not carried out and the exit gate 26 is opened by the gate control unit 51 (step 306).

[0116] The vehicle detection unit 50 of the settlement device 25 monitors the exit of the vehicle from the parking lot 9 (step 307). If the exit of the vehicle is detected (YES in step 307), the gate control unit 51 closes the exit gate 26 (step 308).

[0117] The parking information 66 is updated (step 309). Specifically, the "parking status" of the parking information 66 shown in Fig. 7 is updated from "entered (not yet exited)" to "exited."

[0118] In this embodiment, no gate is provided in the entrance lane 20. Therefore, the user 12 can enter the parking lot without stopping the vehicle at the entrance. Furthermore, the parking lot 9 according to this embodiment is a so-called ticketless parking lot, in that no medium such as a parking ticket is required from entry to exit. These points are advantageous in improving convenience for the user 12.

[0119] In this embodiment, the settlement device 25 functions as an embodiment of a fee presentation unit according to the present invention that calculates and presents to the user the parking fee for a vehicle based on entering vehicle information extracted from an entering vehicle image taken when the vehicle enters the parking lot and exiting vehicle information extracted from an exiting vehicle image taken when the vehicle leaves the parking lot.

[0120] The pre-payment device 23 functions as one embodiment of a payment execution unit according to the present invention that performs payment of vehicle parking fees based on entering vehicle information extracted from an entering vehicle image taken when the vehicle enters the parking lot and vehicle information regarding the user's vehicle input by the user.

[0121] [Machine response to user 12's inquiry] In this embodiment, the voice data acquisition unit 61 of the mechanical response device 10 shown in Fig. 5 functions as the voice data acquisition unit according to the present invention, and acquires voice data of an inquiry about use of the parking lot 9 input by voice from a user 12 of the parking lot 9. Of course, the voice data acquisition unit 45 of the settlement device 25 (pre-settlement device 23) shown in Fig. 4 also functions as the voice data acquisition unit according to the present invention.

[0122] In this embodiment, the utterance intention analysis unit 62, the response data generation unit 63, the response processing execution unit 64, and the response image generation unit 65 shown in FIG. 5 function as an inquiry response unit according to the present invention, and executes a predetermined response process regarding the use of the parking lot 9 based on the voice data of the inquiry acquired by the voice data acquisition unit 61.

[0123] In addition, the response data generation unit 63, the response processing execution unit 64, and the response image generation unit 65 generate response data for realizing a dialogue with the user 12 based on the voice data of the inquiry, and it is possible to execute response processing based on the content of the dialogue with the user 12.

[0124] In addition, in this embodiment, when executing a mechanical response to an inquiry, the settlement device 25 and the pre-settlement device 23 function as an embodiment of a dialogue execution unit that executes a dialogue with the user by outputting response data using at least one of voice and image.

[0125] In this embodiment, the response data generated by the mechanical response device 10 is output by both voice and image (message) by the settlement device 25 and the pre-settlement device 23. The message is displayed in the response image generated by the response image generation unit 65.

[0126] In addition, in this embodiment, the pre-payment monitoring camera 24 and the exit camera 28 function as an embodiment of a photographing unit that photographs the user 12 who is having a dialogue with the dialogue execution unit (payment device 25 and pre-payment device 23).

[0127] In addition, in this embodiment, the DB 57 connected to the machine response device 10 functions as an embodiment of a memory unit that stores information regarding at least one of the content of the dialogue including the user's inquiry and the content of the response processing as response history information.

[0128] Furthermore, in this embodiment, the settlement device 25 also functions as an embodiment of an issuing unit that issues a receipt or invoice that displays information about at least one of the contents of the dialogue, including the user's inquiry, and the contents of the response process. Note that a receipt and an invoice are not clearly distinguished and may be treated as the same thing.

[0129] The machine response to the inquiry of the user 12 will be described in detail below.

[0130] 10 is a flowchart showing an example of a basic operation for responding to an inquiry. Input of a desired inquiry from the user 12 is monitored (step 401). For example, an inquiry request button for inputting a desired inquiry is displayed on the touch panel 42 of the settlement device 25 and the pre-settlement device 23. When the inquiry request button is selected by the user 12, it is determined that a desired inquiry has been input. Alternatively, the desire to make an inquiry may be input by voice.

[0131] If the user 12 inputs a request for an inquiry (YES in step 401), the voice data acquisition unit 61 acquires voice data of the inquiry from the user 12 via the settlement device 25 and the pre-settlement device 23 (step 402).

[0132] The utterance intention analysis unit 62 analyzes the intention of the inquiry made by the user 12 based on the acquired voice data of the inquiry (step 403). For example, the utterance intention analysis unit 62 performs a voice recognition process on the voice data and converts the voice data into text data. Then, a natural language understanding process is performed on the converted text data and the intention of the inquiry is analyzed from the text data.

[0133] The specific algorithm for analyzing the intent of a query (understanding the intent) is not limited. For example, for analyzing the intent of a query, dictionary data that compiles various words and vocabulary may be stored in DB 57 and may be referenced as appropriate.

[0134] To analyze the intent of a query, any machine learning algorithm may be used, such as a DNN (Deep Neural Network), an RNN (Recurrent Neural Network), or a CNN (Convolutional Neural Network). For example, by using AI (artificial intelligence) that performs deep learning, it becomes possible to analyze the intent of a query with high accuracy.

[0135] For example, by inputting voice data or text data into a trained learning model that has undergone machine learning to output the intent of a query, it is possible to obtain the intent of the query of user 12 from the learning model.

[0136] The backpropagation method is one example of a learning method used for learning models. Backpropagation is a commonly used learning method for training neural networks. A neural network is a model that originally imitates the neural circuits of the human brain, and has a layered structure consisting of three types of layers: an input layer, an intermediate layer (hidden layer), and an output layer.

[0137] Neural networks with many hidden layers are called deep neural networks, and the deep learning techniques used to train them are known as models that can learn complex patterns hidden in large amounts of data. Backpropagation is one such learning method, and is often used, for example, in training CNNs, which are used to recognize images and videos.

[0138] Furthermore, as a hardware structure for realizing such machine learning, a neurochip / neuromorphic chip incorporating the concept of neural networks can be used.

[0139] The algorithm for training the learning model is not limited, and any machine learning algorithm may be used. For example, machine learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, inverse reinforcement learning, active learning, and transfer learning. Furthermore, machine learning models such as HMM (Hidden Markov Model) and SVM (Support Vector Machine) may be used.

[0140] A learning block (learning unit) for learning the learning model may be configured in the machine response device 10. Alternatively, the learning block (learning unit) may be configured in a computer different from the machine response device 10, and the learned learning model after learning has been executed may be installed in the machine response device 10. In addition, the specific configuration of the learning model and the learning block (learning unit) for learning the learning model is not limited.

[0141] The application of a machine learning algorithm may be performed for any process within the present disclosure, i.e., any process described within the present disclosure may be subjected to a process using machine learning.

[0142] Based on the analyzed inquiry intent, the response processing execution unit 64 executes various response processes related to the use of the parking lot 9. Also, based on the inquiry intent, the response data generation unit 63 generates response data for realizing a dialogue with the user 12.

[0143] For example, there may be a pattern in which only a predetermined response process is executed based on the intent of the inquiry of the user 12. There may also be a pattern in which only the generation of answer data is executed based on the intent of the inquiry. There may also be a pattern in which both a predetermined response process and the generation of answer data are executed based on the intent of the inquiry.

[0144] In addition, response data may be generated based on the content and results of a predetermined response process executed based on the intent of the inquiry. For example, if the intent of the inquiry is a question about how to operate the pre-payment device 23, the predetermined response process may search the manual for the pre-payment device 23. Then, response data may be generated based on the content of the searched manual. Such processing is also possible.

[0145] In the present parking lot management system 1, the execution of response processing and the generation of response data are executed in cooperation with each other in response to various inquiries made by voice of the user 12. For example, it is possible to execute processing such as responding to inquiries according to multiple scenarios, or processing such as moving back and forth between different search steps as appropriate. This makes it possible to realize highly accurate and flexible responses to various inquiries.

[0146] In the present disclosure, "processing based on the intention of an inquiry (utterance intention) analyzed based on the voice data of an inquiry (utterance)" is included in "processing based on the voice data of an inquiry (utterance)."

[0147] The response image generating unit 65 generates a response image and outputs it to the device that is currently interacting with the user 12, either the settlement device 25 or the pre-payment device 23 (step 406).

[0148] The response image is displayed, for example, in a chat (dialogue) format, and includes a message from the user 12 and a message from the parking lot management system 1 (hereinafter simply referred to as a system-side message). The message from the user 12 is the content of the user 12's utterance in the dialogue, including the user's inquiry, converted into text data. The message from the system is response data in the dialogue generated by the response data generation unit 63.

[0149] It is also possible to display various images captured by the prepayment monitoring camera 24, the entrance camera 27, and the exit camera 28 and managed by the image management unit 59 within the response image.

[0150] It is determined whether the inquiry by the user 12 has ended (step 406). For example, if the user 12 speaks in response to the display of the response image, it is determined that the inquiry has not ended (NO in step 406), and the process returns to step 402 to continue the dialogue.

[0151] In this case, voice data is acquired in response to utterances made by the user 12 during the dialogue, and the intention of the utterance is analyzed. Then, the response process and the generation of answer data are executed in cooperation with each other.

[0152] On the other hand, if there is no utterance from the user 12 until a predetermined time has elapsed since the display of the response image, it is determined that the inquiry has ended (YES in step 406). Alternatively, it is also possible to determine that the inquiry has ended when the user 12 moves away from the prepayment device 23 or when the vehicle leaves.

[0153] When the inquiry is completed, the response content is stored in the DB 57 (step 407). In this embodiment, information on at least one of the content of the dialogue including the inquiry from the user 12 and the content of the response processing is stored as response history information.

[0154] The information about the content of the dialogue, including the inquiry of the user 12, includes, for example, information about all or part of the voice data of each utterance, including the voice data of the inquiry. The information about the content of the dialogue also includes text data of the voice data of each utterance, including the voice data of the inquiry. For example, the voice data or text data of the initial inquiry of the user 12 and the final voice data or text data that constitutes the conclusion may be stored as response history information.

[0155] The information about the content of the response process includes information indicating what kind of response process was executed. Information indicating the result of the response process also includes information about the content of the response process. Information about whether the response process was successful or failed is also included in the information about the content of the response process.

[0156] In addition, various captured images displayed as response images may be stored as response history information.

[0157] There are no specific limitations on the algorithm for cooperatively executing the response process and generating the answer data based on the query intention or the utterance intention of the user 12 in the dialogue. For example, the response process and the answer data may be executed using a learning model trained by a machine learning algorithm.

[0158] FIG. 11 is a schematic diagram showing an example of information and data stored in the DB 57 for executing the response process and generating response data.

[0159] 11A, it is possible to execute response processing and generate answer data by referring to response pattern information 68. The response pattern information 68 is managed with an ID (not shown), and stores "intention of inquiry (utterance intention)," "answer pattern," "response processing," etc.

[0160] For example, the response pattern information 68 shown in Fig. 11A is searched for and selected based on the inquiry intention (utterance intention) analyzed by the utterance intention analysis unit 62. Based on the "answer pattern" and "response process" stored in the selected response pattern information 68, the response process is executed and the response data is generated.

[0161] 11B, response history information 69 may be referenced. The response history information 69 is managed with an ID (not shown) assigned, and stores information such as "intention of inquiry (utterance intention)," "content of dialogue," "response processing," and "captured image."

[0162] For example, the response history information 69 shown in Fig. 11B is searched and selected based on the inquiry intention (utterance intention) analyzed by the utterance intention analysis unit 62. Based on the "dialogue content," "response processing," "captured image," etc. stored in the selected response history information 69, the response processing is executed and answer data is generated.

[0163] As shown in Fig. 11C, FAQs 70 may be referenced. For example, the FAQs 70 are categorized and managed for each item related to the use of the parking lot 9. In the example shown in Fig. 11C, the FAQ 70 for "Regarding unopened exit gates" is illustrated as one example.

[0164] For example, the FAQ 70 shown in Fig. 11C is searched for and selected based on the inquiry intention (utterance intention) analyzed by the utterance intention analysis unit 62. Based on the questions and answers in the selected FAQ 70, a response process is executed and answer data is generated.

[0165] As shown in Fig. 11D, a manual 71 regarding the use of the parking lot 9 may be referenced. For example, the manual 71 is categorized and managed for each item regarding the use of the parking lot 9. In the example shown in Fig. 11D, a manual 71 regarding "exit method" is illustrated as one example.

[0166] For example, the manual 71 shown in Fig. 11D is searched and selected based on the inquiry intention (utterance intention) analyzed by the utterance intention analysis unit 62. Based on the contents of the selected manual 71, a response process is executed and answer data is generated.

[0167] A machine learning algorithm may be used to select the response pattern information 68, response history information 69, FAQ 70, and manual 71 illustrated in Figures 11A to 11D. For example, a learning model may be used that is trained by machine learning to input the intention of the inquiry (utterance intention) and output optimal response pattern information 68, optimal response history information 69, optimal FAQ 70, or optimal manual 71.

[0168] In this case, it is also possible to omit the query intent (utterance intent), input the query voice data (voice data of each utterance), and train the learning model to output optimal response pattern information 68, optimal response history information 69, optimal FAQ 70, or optimal manual 71.

[0169] 11A to 11D, the learning model may be trained using response pattern information 68, response history information 69, FAQ 70, and manual 71. For example, it is possible to construct a learning model that takes the intention of an inquiry (utterance intention) as input and outputs a response process to be executed or answer data to be generated. It is also possible to construct a learning model that takes the voice data of an inquiry (voice data of each utterance) as input and outputs a response process to be executed or answer data to be generated.

[0170] Furthermore, the learning model may be trained using various information and data stored in the DB 13 shown in FIG.

[0171] [Specific operational examples] An example of operation of the parking lot management system 1 for mechanical response to inquiries will be described.

[0172] FIG. 12 is a diagram showing an example of a settlement screen and a response image displayed on touch panel 42 of settlement device 25.

[0173] 12A shows the settlement screen 73. The settlement screen 73 displays the "parking fee," "entry date and time," "parking time," an image 74 of the entering vehicle, and the vehicle number calculated by the settlement unit 52. The settlement screen 73 also displays an inquiry request button 75 and an explanation of the operation to be performed when making an inquiry.

[0174] Here, assume that user 12 has already paid for the fare using advance payment device 23. That is, user 12, who has driven his vehicle into exit lane 21, expects that exit gate 26 will open. However, exit gate 26 does not open, and payment screen 73 is displayed on touch panel 42 of payment device 25.

[0175] When the user 12 looks at the payment screen 73, the entering vehicle image 74 and the vehicle number of the user's vehicle are certainly displayed. In other words, from the user 12's point of view, it can be said that the parking fee has been charged twice.

[0176] The user 12 selects the inquiry request button 75 on the payment screen 73. Alternatively, the user 12 inputs a voice message indicating that he or she wishes to make an inquiry.

[0177] 12B, the display control unit 55 of the settlement device 25 displays an initial response image 76. The initial response image 76 displays text data indicating that the machine is responding. The system also displays a message in chat format prompting the user to input a voice inquiry, such as "Please tell us your business."

[0178] Also, a message saying "Please tell us your business" is output by voice. In this way, in this embodiment, when a message from the system side is displayed, the same message is also output by voice. For this purpose, the settlement device 25 and the pre-settlement device 23 may be equipped with a voice synthesis function or the like. Note that in the following explanation, the voice output of the message from the system side may be omitted.

[0179] The user 12 makes an inquiry saying, "I've paid in advance." The voice data of the inquiry is acquired by the voice data acquisition unit 61 of the mechanical response device 10, and the intention of the inquiry is analyzed by the speech intention analysis unit 62.

[0180] 12B, text data generated from the voice data of the inquiry is transmitted to the settlement device 25. Then, the display control unit 55 displays text that is the same as the voice of the inquiry, "I've prepaid," as a message from the user 12.

[0181] In this way, the content of the dialogue, including the inquiry of the user 12, is displayed as text data. That is, the settlement device 25 (pre-settlement device 23) can display text data corresponding to the voice data input by voice from the user 12 in the dialogue, including the voice data of the inquiry, on the touch panel 42, which is an image display unit.

[0182] As a result, the user 12 can see messages from the system and messages corresponding to the content of his / her own speech in a chat format on the touch panel 42. As a result, the user 12 can easily understand the content of the conversation. In addition, the user 12 can understand whether his / her own speech is being properly conveyed to the system.

[0183] Furthermore, by displaying the system's response as text data, the user 12 can easily understand the system's response even when outdoors or in other noisy surroundings. Furthermore, the content of the conversation can be saved by saving the conversation image, which displays the system's message and a message corresponding to the user's own speech in a chat format, as data or by printing it on paper. This avoids the issue of whether something was said or not.

[0184] When saving the contents of a conversation in print or other form, it is possible to appropriately summarize and save the contents of the conversation. For example, it is effective to save only the conclusion of the conversation or important exchanges. Generative AI may be used to create the summarized text data.

[0185] The utterance intention analysis unit 62 analyzes the intention of the inquiry, "I paid in advance," to mean that the parking fee has been paid but the vehicle is not yet in a paid-for state. Then, based on the intention of the inquiry, a response process is executed and response data is generated.

[0186] As shown in Figure 12B, below the message from user 12 saying "I've prepaid," a message from the system, "...", is displayed. It is also preferable to have the "..." displayed in a scrolling manner, and this message indicates that the system is currently responding to an inquiry.

[0187] In this embodiment, as the response process, the pre-payment device 23 determines whether the vehicle number entered by the user 12 is correct. This determination can be made, for example, by searching for vehicle numbers entered into the pre-payment device 23 in a relatively recent time period, or based on video footage of the user 12 entering the vehicle number captured by the pre-payment monitoring camera 24. For example, the vehicle number input screen can be saved as image data, and the saved vehicle number input screen can be used for the determination.

[0188] 12, it is assumed that the determination as to whether the vehicle number entered by user 12 is correct is negative based on the video image of user 12 entering the vehicle number and the saved image of the vehicle number entry screen. In this case, the response data generation unit 63 generates response data indicating that the vehicle information entered by user 12 is incorrect. Furthermore, if the determination as to whether the vehicle number entered by user 12 is correct is negative, response data including information regarding the payment method for the parking fee for user 12's vehicle is generated.

[0189] The response image generation unit 65 generates a response image and transmits it to the settlement device 25. The display control unit 55 of the settlement device 25 displays the response image on the touch panel .

[0190] In the example shown in FIG. 12C, a message stating "It appears you entered the wrong vehicle number" is displayed as response image 77. This message corresponds to response data indicating that the vehicle information entered by user 12 is incorrect. In the example shown in FIG. 12C, a message stating "Please pay only the difference" is displayed. This message corresponds to response data including information regarding the payment method for the parking fee for user 12's vehicle (2,300 yen shown in FIG. 12A).

[0191] 12C, a moving image 78 of the user 12 entering the vehicle number and a saved image 79 of the vehicle number entry screen are displayed next to the message from the system. By checking these images, the user 12 can understand that he or she has entered the wrong vehicle number.

[0192] User 12 replies, "Thank you for that," and pays the difference between the amount he paid by mistake (the parking fee for the other user 12) and the actual parking fee for his own vehicle (2,300 yen) at the prepayment device 23.

[0193] If the fee paid at the prepayment device 23 is less than 2,300 yen, the shortfall is paid as the difference. If the fee paid at the prepayment device 23 is more than 2,300 yen, the overpaid amount is refunded and received. For example, if the fee paid at the prepayment device 23 is the same as 2,300 yen, a transfer process is executed and it can be processed as having been paid.

[0194] Once the payment of the difference has been completed, the exit gate 26 opens and the vehicle is allowed to exit. This marks the end of the inquiry, and the response is stored in the DB 57 as response history information.

[0195] As shown in Figure 12, in this parking lot management system 1, based on the voice data of an inquiry input by user 12 that the parking fee has been settled based on the input vehicle information (vehicle number), but the vehicle is not in a settled state, it is possible to determine whether the vehicle number input by user 12 is correct, and if the determination is negative, it is possible to generate response data indicating that the vehicle information input by user 12 is incorrect.

[0196] In addition, in this parking lot management system 1, if the determination as to whether the vehicle information entered by user 12 is correct is negative, it is possible to generate response data including information regarding the method of settling the parking fee for user 12's vehicle.

[0197] FIG. 13 is a diagram showing another example of a response image displayed on the touch panel 42 of the settlement device 25. As shown in FIG.

[0198] In the example shown in FIG. 13A, the user 12 makes an inquiry saying, "I forgot my wallet." The utterance intention analysis unit 62 analyzes the intention of the inquiry, which is that it is impossible to pay the parking fee at the current timing. The answer data generation unit 63 generates answer data including suggestions for other payment methods. Specifically, as shown in the response image 80 shown in FIG. 13A, a message saying, "You can also pay by smartphone" is displayed.

[0199] In response to the response image 80, the user 12 utters, "I don't have it." As shown in Fig. 13A, if the dialogue continues, the response image 80 scrolls and new messages are displayed in order below.

[0200] The intention of the utterance is analyzed by the utterance intention analysis unit 62. Then, as a response process, a process is executed to connect the inquiring user 12 to an operator 14 of the management institution so that they can have a conversation. Response data including this information is also generated.

[0201] In response image 81 shown in Fig. 13B, a message "Connecting to an operator" is displayed from the system side. Then, the user is ready to talk to operator 14 of the management institution via settlement device 25, and an image indicating that a call is in progress is displayed.

[0202] Furthermore, in the example shown in FIG. 13B, a video 82 is displayed that captures the user 12 talking to an operator 14 of the management institution via the settlement device 25. In this way, by displaying a video of the user 12 in real time, it is possible to make the user 12 aware that he or she is being filmed. As a result, it is possible to prevent the user 12 from engaging in actions such as hitting the settlement device 25 or uttering abusive language. Note that the image of the operator 14 may not be a real image, but may instead be an illustration or the like.

[0203] It is possible to set operator connection conditions for executing a process to connect the user 12 so that the user can converse with the operator 14 of the management institution. For example, conditions that can be set as operator connection conditions include the user being unable to pay the parking fee at the current timing, the other proposed payment methods being unavailable, or the user uttering a statement that they will not pay the parking fee.

[0204] In addition, it is possible to set conditions such as when a solution cannot be expected through a machine response, when the user's 12 inquiry intent (utterance intent) is not properly analyzed, when it is impossible to execute a response process based on the inquiry intent (utterance intent), when the user 12 has performed an action such as hitting the settlement device 25, when the user 12 has used abusive language, or when the conversation time with the user 12 exceeds a specified time as operator connection conditions.

[0205] In the example shown in Figure 13B, for example, user 12 interacts with operator 14 of the management agency to obtain consent to pay the parking fee at a later time. This opens exit gate 26, allowing the vehicle to exit. Of course, various countermeasures are possible.

[0206] As shown in response image 83 in Figure 13C, when an inquiry or utterance from user 12 is analyzed to indicate that it is not possible to pay the parking fee at the current time, it is possible to generate response data that includes information on how to pay the parking fee at a later time.

[0207] In the example shown in Figure 13C, the system displays the following messages: "Please provide your name and phone number" and "We will print out and issue a payment method (bank transfer) for you." This message corresponds to the answer data that includes information on how to pay the parking fee at a later time.

[0208] 13C, a moving image 82 is displayed, which captures the user 12 interacting with the payment device 25. That is, the moving image is displayed to the user 12 in real time.

[0209] User 12 enters their name and phone number by voice. Once the text data of the voice is acquired, a receipt or invoice is issued showing information on how to pay any outstanding parking fees. Then, exit gate 26 opens, allowing the vehicle to exit.

[0210] Fig. 14 is a schematic diagram showing an example of an issued receipt. In the example shown in Fig. 14, the "Parking Lot Name," "Contact Information," "Support Details," "Payment Information," "User Information," code image 87, and "Comments Regarding Access to the Support Site Using Code Image 87" are printed on receipt 86.

[0211] The "support content" includes the date and time of the unpaid fee, the unpaid amount, and instructions for transferring the money to your account.

[0212] The code image 87 stores a URL (link) to a dedicated support site (website) constructed by the parking lot management system 1. The user 12 reads the code image 87 using a code image reading function of a mobile terminal or the like, thereby being able to access the support site.

[0213] The support site allows the user 12 to check response history information. For example, the website is constructed so that the user can check the response image displayed on the touch panel 42, the voice data of each utterance including the voice data of the inquiry, the text data of the voice data of each utterance including the voice data of the inquiry, the content of the response processing that was executed, the result of the response processing, various captured images displayed in the response image, and the like.

[0214] In this way, by issuing a receipt or invoice with the details of the machine response printed on it, it is possible to prevent the user 12 from forgetting the details of the machine response. In this example, it is possible to prevent the user 12 from forgetting important information such as the bank account to which unpaid parking fees should be transferred.

[0215] In addition, a code image 87 storing a URL (link) to a dedicated support site (website) including the contents of the machine response is printed on the receipt, allowing the user 12 to easily access the support site, check the contents of the conversation, and refer to explanations of how to deal with the situation.

[0216] 13, the parking lot management system 1 can generate response data including information on how to pay the parking fee at a later time based on voice data of an inquiry input by the user 12 that the parking fee cannot be paid at the current time. Note that it is also possible to set it so that if personal information such as the name, address, and telephone number of the user 12 can be obtained, response data including information on how to pay the parking fee at a later time is generated.

[0217] Furthermore, in the present parking lot management system 1, when a predetermined operator connection condition is met, it is also possible to connect the user 12 making an inquiry so that the user 12 can converse with the operator 14.

[0218] As shown in FIG. 14, the parking lot management system 1 can issue a receipt 86 that displays information regarding at least one of the content of the dialogue, including the inquiry of the user 12, and the content of the response processing.

[0219] 14, the parking lot management system 1 can issue a receipt 86 that displays information about how to pay unpaid parking fees. The parking lot management system 1 can also issue a receipt 86 that displays a code image 87 that stores the URL of a website that includes response history information.

[0220] In addition, this parking lot management system 1 can realize a machine response to various inquiries from users 12.

[0221] For example, the user 12 attempts to pay the parking fee at the payment device 25 without paying in advance, and drives the vehicle in front of the payment device 25. While the user expects the parking fee to be displayed on the touch panel 42 of the payment device 25, the parking fee is not displayed and the user is unable to pay.

[0222] For example, when a user 12 enters a vehicle, a problem may occur in capturing an image of the entering vehicle, making it impossible to properly recognize the entering vehicle information. For example, a strong afternoon sun may create backlighting, causing the image of the entering vehicle to be overexposed, making it impossible to recognize the vehicle information. Or, a very heavy rain may fall, making it impossible to properly capture an image of the entering vehicle, making it impossible to recognize the vehicle information.

[0223] In this case, it becomes impossible to search for entering vehicle information that matches the exiting vehicle information extracted from the exiting vehicle image captured by the exit camera 28, and it becomes impossible to calculate the parking fee and present it to the user 12.

[0224] In such a case, the user 12 selects the inquiry button 75 and makes a voice inquiry such as "My parking fee isn't being calculated" or "The payment screen isn't showing up."

[0225] The utterance intention analysis unit 62 analyzes the intention of the inquiry that the parking fee will not be presented by the settlement device 25. Based on the intention of the inquiry, a response process is performed to determine whether or not there is entering vehicle information that matches the exiting vehicle information of the user 12's vehicle. If the determination is negative, response data is generated that includes a question about the situation when the user 12 entered the vehicle or a question about the characteristics of the user 12's vehicle.

[0226] The questions regarding the situation when the user 12 entered the vehicle include questions regarding the time when the vehicle entered, the weather, whether there were any vehicles ahead or behind, etc. Of course, the questions are not limited to these.

[0227] Questions regarding the characteristics of the vehicle of the user 12 include, for example, questions regarding "vehicle-related information" in the parking information 66 shown in Fig. 7, such as vehicle name information, vehicle color information, vehicle manufacturer information, etc. Of course, the questions are not limited to these.

[0228] User 12 responds to the questions by voice by inputting responses such as "I pulled in around XX o'clock," "It was raining really hard," "The body is red," and "There was a big car in front of me."

[0229] The speech data of the response is acquired and the intention of the speech is analyzed. Based on the intention of the speech, the parking information 66 related to the vehicle of the user 12 is searched as a response process, and the vehicle of the user 12 is identified.

[0230] For example, the response image may be an image of the entering vehicle of the identified user 12 and a message to confirm the vehicle, such as "Is this your vehicle?" If the user 12 replies, "Yes, that vehicle," the settlement device 25 calculates the parking fee based on the parking information 66 of the identified vehicle and presents it to the user 12.

[0231] In this way, in this parking lot management system 1, based on the voice data of an inquiry input by user 12 that the settlement device 25 will not present the parking fee, it is possible to determine whether or not there is entry vehicle information that matches the exit vehicle information of user 12's vehicle, and if the determination is negative, it is possible to generate answer data that includes questions regarding the circumstances when user 12 entered the vehicle, or questions regarding the characteristics of user 12's vehicle.

[0232] Furthermore, the parking lot management system 1 can identify the vehicle of the user 12 based on the content of the dialogue with the user 12, which is realized using answer data including questions about the circumstances when the user 12 entered the vehicle or questions about the characteristics of the vehicle of the user 12. Then, it can calculate the parking fee for the vehicle of the identified user 12 and present it to the user 12.

[0233] This makes it possible to deal with misrecognition of vehicle license plates and the like without requiring the assistance of staff, etc. Also, it becomes possible to estimate the entering vehicle from the user's 12 response to questions about the circumstances under which the user 12 entered the vehicle or questions about the characteristics of the user's 12 vehicle.

[0234] If the entering vehicle information cannot be properly recognized from the entering vehicle image, when the user 12 inputs the vehicle information into the prepayment device 23, the prepayment device 23 notifies the user 12 that there is no vehicle for the user 12 that is subject to payment.

[0235] In such a case, the response process determines whether or not there is entrant vehicle information that matches the vehicle information entered by user 12, based on the intent of the inquiry. If the determination is negative, response data is generated that includes questions about the circumstances under which user 12 entered the vehicle, or questions about the characteristics of user 12's vehicle. Based on the content of the dialogue with user 12 realized using this response data, it is possible to identify an entering vehicle image of user 12's vehicle, and it is possible to calculate the parking fee based on the identified entering vehicle image and present it to user 12. As a result, user 12 can make a prepayment.

[0236] For example, suppose that after user 12 prepaid using prepayment device 23, he or she did not immediately exit the vehicle, resulting in an excess parking fee. User 12 did not realize that an excess fee had been incurred, and when user 12 entered the exit lane 21, exit gate 26, which he or she thought would open, did not open, and the settlement screen was displayed on touch panel 42 of settlement device 25.

[0237] In such a case, the user 12 selects the inquiry button 75 and makes a voice inquiry such as "I paid in advance, but what about now?"

[0238] The utterance intention analysis unit 62 analyzes the intention of the inquiry that the parking fee has not yet been paid for the user's vehicle despite the fact that the parking fee has been paid based on the input vehicle information (vehicle number). Based on the intention of the inquiry, the response process determines whether or not a fee has been charged for the excess parking time, and if the determination is positive, it is possible to generate response data that includes information that a fee has been charged for the excess parking time.

[0239] For example, response data such as "More than 10 minutes have passed since the advance payment" or "Please pay the excess amount" is generated and displayed on the touch panel 42 of the payment settlement device 25.

[0240] If the user 12 pays the excess fee, the exit gate 26 opens and the vehicle is allowed to exit. Alternatively, if the user 12 is not satisfied, and a predetermined time has passed without the excess fee being paid, or if the user 12 utters an utterance indicating that the excess fee will not be paid, a response process is executed to connect the user to an operator 14 of the management institution so that the user can have a conversation.

[0241] In this way, the parking lot management system 1 determines whether or not a fee has been incurred for the excess parking time based on the voice data of an inquiry input by the user 12, in which the user 12 replies that the parking fee has been settled based on the input of vehicle information (vehicle number) but the vehicle is not yet in a settled state, and if the determination is positive, it is possible to generate response data indicating that a fee has been incurred for the excess parking time.

[0242] In addition, for example, another user 12 may mistakenly enter vehicle information into the prepayment device 23. For example, when a user 12 attempts to make a prepayment using the prepayment device 23, if another user 12 mistakenly prepayments for his / her own vehicle, the user 12 is notified that the vehicle of the user 12 to be settled does not exist.

[0243] In such a case, the user 12 selects the inquiry button 75 and makes a voice inquiry such as "I can't pay in advance?" or "My vehicle isn't coming out?"

[0244] The utterance intention analysis unit 62 analyzes the intention of the inquiry to notify the user 12 that the vehicle for which settlement is required does not exist when the vehicle information is entered. Based on the intention of the inquiry, it is possible to calculate the parking fee for an unexited vehicle that matches the vehicle information entered by the user 12, and generate answer data that includes information on how to settle the calculated parking fee. It is also possible to generate answer data that includes the reason why the notification that the user 12's vehicle does not exist is issued.

[0245] For example, response data such as "Another user has already prepaid for your vehicle" or "Please pay the parking fee here" is generated and displayed on the touch panel 42 of the prepayment device 23.

[0246] The user 12 can settle the fee in advance by paying the parking fee that is presented. In this way, the parking lot management system 1 calculates the parking fee for an unexited vehicle that matches the vehicle information entered by the user 12 based on the voice data of an inquiry input by the user 12, informing the user that the vehicle for which settlement is to be made is not present when the vehicle information is entered, and generates response data that includes information on how to settle the calculated parking fee. It is also possible to generate response data that includes the reason for the notification that the user 12's vehicle is not present.

[0247] For other users 12 who made a mistake in their advance payment, the exit gate 26 will not open and the payment screen will be displayed on the payment device 25. In this case, too, it is possible to respond to inquiries by using the machine response system according to the present invention, as described above.

[0248] Furthermore, when an inquiry including a complaint is made by the user 12, it is possible to generate response data indicating that the user 12 will be contacted at a later time based on the voice data of the inquiry. Note that it is also possible to set it so that when personal information such as the name, address, and telephone number of the user 12 is obtained, response data indicating that the user 12 will be contacted at a later time is generated.

[0249] Furthermore, when the user 12 makes an inquiry about an emergency, a report can be sent to a predetermined reporting destination based on the voice data of the inquiry. For example, when a theft or vehicle break-in is reported, a report is sent to the police or a security company.

[0250] As described above, in the parking lot management system 1 according to this embodiment, the inquiry response unit (the speech intention analysis unit 62, the response data generation unit 63, the response processing execution unit 64, and the response image generation unit 65) executes a predetermined response process regarding the use of the parking lot 9 based on the voice data of the inquiry input by voice from the user 12 who uses the parking lot 9. The inquiry response unit is also configured to generate response data for realizing a dialogue with the user 12 based on the voice data of the inquiry, and to execute the response process based on the content of the dialogue with the user 12. This makes it possible to improve convenience for the user 12.

[0251] Recently, parking lot management systems have been developed that allow entry and exit from paid parking lots without the use of parking tickets. In particular, in order to eliminate congestion in front of the payment device when exiting a parking lot, which is now managed by photographing the vehicle's license plate number, parking lot management systems have been developed that allow users to enter their vehicle's license plate number (car number) in advance while parked and before exiting to settle the payment.

[0252] However, there may be cases where user 12 mistakenly settles using someone else's vehicle license plate number due to reasons such as vehicles with the same four-digit serial number, inputting incorrect or insufficient confirmation of hiragana characters that are easily misread, or the system not recognizing the vehicle license plate number. In this case, the vehicle will be unable to exit the parking lot due to an unsettled fare, which may lead to complaints and inquiries at the settlement device, causing congestion, and although this is not necessarily a problem on the system's side, it may cause user 12 to feel distrustful and discourage repeat use of parking lot 9.

[0253] Furthermore, it would be costly to have a full-time attendant on-site to deal with the user 12's usage errors or lack of understanding. Even if an inquiry desk or service center is set up in a remote location, it is difficult to avoid reducing the personnel costs of the attendant who responds to inquiries unless the inquiries are eliminated there.

[0254] The parking lot system described in Patent Document 1 requires users to confirm the recognition of their vehicle license plate number when entering the parking lot, which is cumbersome, and although the system does not require the issuance of parking tickets, it does not allow non-stop entry, making it inconvenient. Also, the installation of an entrance gate is essential.

[0255] The parking lot management system 1 according to this embodiment can provide a machine response to various inquiries from users 12. As a result, it is possible to deal with cases where the vehicle number is read incorrectly or cannot be recognized, and also to smoothly deal with incorrect settlements, etc., without impairing the convenience of users 12.

[0256] <Other embodiments> The present invention is not limited to the above-described embodiment, and various other embodiments can be realized.

[0257] A code image storing the URL of the support site may be displayed at key locations such as signs in the parking lot 9. The user 12 reads the code image using a mobile terminal or the like to access the support site. The user 12 can then make various inquiries by voice or text input and receive support such as dialogue from the mechanical response device 10. This improves convenience for the user 12.

[0258] By using the mobile terminal of the user 12 to receive support for machine responses such as dialogue, it becomes possible to respond to inquiries from many users 12 at once, and it becomes possible to avoid, for example, queues forming at the settlement device 25 or the pre-settlement device 23.

[0259] The characteristics of the speech (volume, pitch, etc.) from the user 12 during the dialogue, including inquiries input by voice from the user 12, may be analyzed to determine the emotions of the user 12. Then, a machine response may be executed according to the emotions of the user 12. For example, if an inquiry from the user 12 includes anger, it is also possible to change the tone of the response pattern. For example, a response using indecent language or, conversely, a response using firm language may be selected as appropriate.

[0260] 11 may be newly generated and stored based on a machine learning algorithm or the like. For example, it is possible to convert the actual response content of the operator 14 of the management institution into data such as text data, and generate new response pattern information 68 based on that data. It is also possible to build a learning model using the actual response content of the operator 14 as training data, and generate new response pattern information 68 from that learning model.

[0261] It is also possible to construct a learning model using training data such as the content of machine responses made in other parking lots, trouble cases specific to the parking lot, and environmental information at that time, and to generate new response pattern information 68 from the learning model.

[0262] It is also possible to use video images of interactions between the settlement device 25 or pre-payment device 23 and the user 12, which are managed by the image management unit 59, as training data.

[0263] The present invention is applicable not only to ticketless parking lots as shown in Fig. 2, but also to parking lots that issue parking tickets. For example, the mechanical response device 10 according to the present invention can properly determine the user's request and provide appropriate support in situations such as assisting the user in operating the device when the user has lost the parking ticket, or calling an attendant when the gate does not open after payment due to a malfunction of the device and the user is unable to exit.

[0264] The mechanism of the mechanical response device 10 of the present invention can also be installed in a parking lot management device. In that case, if a pre-registered member or provisionally registered member, for example, makes reservations or changes to the parking lot 9, the member may be able to check the record of interactions with the mechanical response device 10 from his / her personal page. Furthermore, not only are these interactions accumulated as machine learning data in the database of the parking lot management device, but a mechanism can also be easily realized that allows information to be shared with operators such as parking lot attendants and management agencies in remote locations.

[0265] Furthermore, various application examples of the present invention are possible. For example, in addition to solving problems related to parking lot settlement, the present invention can also be applied to facility entrance guidance and the like. The mechanical response device may also be mobile. The mechanical response device 10 may also be mounted on an automatic cleaning machine within the facility. The mechanical response device 10 may also be a portable terminal that can be moved within the facility by drone. The mechanical response device 10 may also be included in a parking lot management device. The mechanical response device 10 may also be included in the settlement device 25 or the pre-payment device 23. Furthermore, since the content of the dialogue is converted into text data, it is easy to support multiple languages ​​by utilizing the functions of a general-purpose translation site.

[0266] FIG. 15 is a block diagram showing an example of the hardware configuration of a computer 110 that can be used as the parking lot management device 3, the machine response device 10, and the like.

[0267] The computer 90 includes a CPU 91, a ROM 92, a RAM 93, an input / output interface 95, and a bus 94 that interconnects these components. The input / output interface 95 is connected to a display unit 96, an input unit 97, a storage unit 98, a communication unit 99, a drive unit 100, and the like. The display unit 96 is a display device that uses, for example, a liquid crystal display, an electroluminescent display, etc. The input unit 97 is, for example, a keyboard, a pointing device, a touch panel, or other operating device. When the input unit 97 includes a touch panel, the touch panel can be integrated with the display unit 96. The storage unit 98 is a non-volatile storage device, such as a HDD, flash memory, or other solid-state memory. The drive unit 100 is a device capable of driving a removable storage medium 91, such as an optical storage medium or magnetic recording tape. The communication unit 99 is a modem, router, or other communication device that can be connected to a LAN, WAN, etc. and that communicates with other devices. The communication unit 99 may communicate either wired or wirelessly. The communication unit 99 is often used separately from the computer 90. Information processing by the computer 90 having the hardware configuration described above is realized by the cooperation of software stored in the storage unit 98 or ROM 92, etc., and the hardware resources of the computer 90. Specifically, the parking lot management method (information processing method) according to the present invention is realized by loading a program constituting the software stored in the ROM 92, etc., into the RAM 93 and executing it. The program is installed in the computer 90 via, for example, the recording medium 101. Alternatively, the program may be installed in the computer 90 via a global network or the like. Any other computer-readable non-transitory storage medium may be used.

[0268] The parking lot management method and program of the present invention may be executed by multiple computers connected to each other so as to be able to communicate via a network or the like, thereby constructing a parking lot management system or parking lot management device of the present invention. In other words, the parking lot management method and program according to the present invention can be executed not only in a computer system made up of a single computer, but also in a computer system in which multiple computers operate in conjunction with each other. In this disclosure, a system refers to a collection of multiple components (devices, modules (components), etc.), regardless of whether all the components are in the same housing. Therefore, multiple devices housed in separate housings and connected via a network, and a single device housed in a single housing with multiple modules, are both systems.

[0269] The execution of the parking lot management method and program according to the present invention by a computer system includes both cases where, for example, acquisition of voice data, execution of response processing, analysis of the intent of the inquiry (utterance intent), generation of answer data, generation of response images, etc. are performed by a single computer, and cases where each process is performed by a different computer. Furthermore, the execution of each process by a specific computer includes having another computer execute part or all of the process and obtaining the results. In other words, the parking lot management method and program according to the present invention can also be applied to a cloud computing configuration in which a single function is shared and processed jointly by multiple devices via a network.

[0270] The parking lot management system, parking lot management device, settlement device, advance settlement device, mechanical response device, and other terminals and devices, various screens such as response images, various GUI configurations, operations by the parking lot management device, settlement device, advance settlement device, mechanical response device, and other devices, and various processing flows such as the generation of various information, which have been described with reference to the drawings, are merely one embodiment and can be modified as desired without departing from the spirit of the present invention. In other words, any other configurations, algorithms, etc. for implementing the present invention may be adopted.

[0271] Furthermore, the technology of the present invention is not limited to the above-described embodiments, and may be variously modified, substituted, or altered within the scope of the spirit of the technical idea. Furthermore, if the technical idea can be realized in a different way due to technological advances or other derived technologies, it may be implemented using that method. Therefore, the claims cover all embodiments that may fall within the scope of the technical idea.

[0272] In this disclosure, to facilitate understanding of the explanation, words such as "approximately," "almost," and "roughly" may be used as appropriate. However, there is no clear difference between using and not using words such as "approximately," "almost," and "roughly." In other words, in the present disclosure, concepts that define shape, size, positional relationship, state, etc., such as "center," "middle," "uniform," and "equal" are concepts that include "substantially center," "substantially central," "substantially uniform," "substantially equal," etc. For example, this also includes a state where the value is within a predetermined range (for example, a range of ±10%) based on the criteria of "perfectly centered," "perfectly central," "perfectly uniform," "perfectly equal," etc. Therefore, even if the words "roughly," "almost," "approximately," etc. are not added, the concept expressed by adding "roughly," "almost," "approximately," etc. may be included. Conversely, a state expressed by adding "roughly," "almost," "approximately," etc. does not necessarily exclude a complete state.

[0273] In this disclosure, expressions using "more than," such as "greater than A" and "smaller than A," are expressions that comprehensively include both concepts that include equivalent to A and concepts that do not include equivalent to A. For example, "greater than A" is not limited to cases that do not include equivalent to A, but also includes "A or greater." Furthermore, "smaller than A" is not limited to "less than A," but also includes "A or less." When implementing the present technology, specific settings and the like may be appropriately adopted from the concepts included in "greater than A" and "smaller than A" so as to achieve the effects described above.

[0274] It is also possible to combine at least two of the features of the present invention described above. That is, the various features described in each embodiment may be combined in any way without distinguishing between the embodiments. Furthermore, the various effects described above are merely examples and are not limiting, and other effects may also be achieved.

[0275] Furthermore, the technology of the present invention is not limited to the above-described embodiments, and may be variously modified, substituted, or altered within the scope of the spirit of the technical idea. Furthermore, if the technical idea can be realized in a different way due to technological advances or other derived technologies, it may be implemented using that method. Therefore, the claims cover all embodiments that may fall within the scope of the technical idea. [Industrial Applicability]

[0276] As described above, the technology of the present invention is suitable for use in pay parking lots that do not use parking tickets. [Explanation of symbols]

[0277] 1. Parking lot management system 9...Parking lot 10...Mechanical response device 12…User 14...Operator 23...Prepayment device 24...Prepayment surveillance camera 25…Payment device 27...Entrance camera 28...Exit camera 30...Entry vehicle 31...Participating vehicle 66...Parking Information 68...Response pattern information 69...Response history information 70...FAQ 71...Manual 73…Payment screen 74...Entry vehicle image 76, 77, 80, 81, 83... Response images 78...Video of a user entering a vehicle number 79...Saved image of vehicle number input screen 82...Video of a user talking to an operator 86...Receipt 87...Code image 90...Computer

Claims

1. a voice data acquisition unit that acquires voice data of an inquiry about use of the parking lot input by voice from a user of the parking lot; an inquiry response unit that executes a predetermined response process regarding the use of the parking lot based on the acquired voice data of the inquiry; Equipped with The inquiry response unit is configured to generate response data for realizing a dialogue with the user based on voice data of the inquiry, and to execute the response process based on the content of the dialogue with the user. Parking management system.

2. The parking lot management system according to claim 1, further comprising: a fee presentation unit that calculates a parking fee for the vehicle and presents it to the user based on entering vehicle information extracted from an entering vehicle image taken when the vehicle enters the parking lot and exiting vehicle information extracted from an exiting vehicle image taken when the vehicle leaves the parking lot; The inquiry response unit determines whether or not there is the entrant vehicle information that matches the exiting vehicle information of the user's vehicle, based on the voice data of the inquiry that is input by voice from the user, indicating that the parking fee will not be presented by the parking fee presentation unit, and if the determination is negative, generates the answer data including a question about the situation when the user let the vehicle enter or a question about the characteristics of the user's vehicle. Parking management system.

3. The parking lot management system according to claim 2, the inquiry response unit identifies the vehicle of the user based on the content of the dialogue with the user realized using the response data, which includes a question about the situation when the user entered the vehicle or a question about the characteristics of the vehicle of the user; The fee presentation unit calculates the parking fee for the vehicle of the identified user and presents it to the user. Parking management system.

4. The parking lot management system according to claim 1, further comprising: a settlement execution unit that executes settlement of parking fees for the vehicle based on entering vehicle information extracted from an entering vehicle image taken when the vehicle enters the parking lot and vehicle information regarding the user's vehicle input by the user; The inquiry response unit determines whether the vehicle information input by the user is correct based on the inquiry voice data that is input by voice from the user, and that indicates that the parking fee has not been paid for the user's vehicle despite the parking fee being paid based on the input of the vehicle information, and if the determination is negative, generates the response data including a statement that the vehicle information input by the user is incorrect. Parking management system.

5. The parking lot management system according to claim 4, When the determination of whether the vehicle information input by the user is correct is negative, the inquiry response unit generates the response data including information on a method of settling the parking fee for the user's vehicle. Parking management system.

6. The parking lot management system according to claim 1, further comprising: a settlement execution unit that executes settlement of parking fees for the vehicle based on entering vehicle information extracted from an entering vehicle image taken when the vehicle enters the parking lot and vehicle information regarding the user's vehicle input by the user; The inquiry response unit determines whether or not a fee for the excess parking time has been incurred based on the inquiry voice data input by the user, which indicates that the parking fee has been settled based on the input of the vehicle information but the vehicle has not yet been settled, and if the determination is positive, generates the response data including information indicating that a fee for the excess parking time has been incurred. Parking management system.

7. The parking lot management system according to claim 1, further comprising: a settlement execution unit that executes settlement of parking fees for the vehicle based on entering vehicle information extracted from an entering vehicle image taken when the vehicle enters the parking lot and vehicle information regarding the user's vehicle input by the user; The inquiry response unit calculates the parking fee for an unexited vehicle that matches the vehicle information input by the user based on voice data of the inquiry that is input by voice from the user and that notifies the user that there is no vehicle of the user that is subject to settlement when the vehicle information is input, and generates the response data including information on a settlement method for the calculated parking fee. Parking management system.

8. The parking lot management system according to claim 7, The inquiry response unit generates the response data including the reason for the notification that the user's vehicle does not exist, based on voice data of the inquiry that is input by voice from the user and that the user will be notified that the user's vehicle that is the subject of settlement when the vehicle information is input. Parking management system.

9. The parking lot management system according to claim 1, The inquiry response unit generates the response data including information on a method for paying the parking fee at a later time based on voice data of the inquiry input by the user, the voice data indicating that the parking fee cannot be paid at the current time. Parking management system.

10. The parking lot management system according to claim 1, The inquiry response unit generates the response data indicating that the user will be contacted at a later time, based on voice data of the inquiry including a complaint input by voice from the user. Parking management system.

11. The parking lot management system according to claim 1, The inquiry response unit executes a report to a predetermined report destination based on voice data of the inquiry, which includes an indication that an emergency situation has occurred, input by voice from the user. Parking management system.

12. The parking lot management system according to claim 1, further comprising: a dialogue execution unit that executes a dialogue with the user by outputting the answer data by at least one of voice and image; an imaging unit that images the user who is having a dialogue with the dialogue execution unit; A parking lot management system comprising:

13. The parking lot management system according to claim 1, The dialogue execution unit has an image display unit, and displays text data corresponding to voice data input by voice from the user in the dialogue, including the voice data of the inquiry, on the image display unit. Parking management system.

14. The parking lot management system according to claim 1, further comprising: The system further includes a storage unit that stores information relating to at least one of the content of the dialogue including the user's inquiry and the content of the response process as response history information. Parking management system.

15. The parking lot management system according to claim 1, further comprising: and an issuing unit that issues a receipt or invoice on which information relating to at least one of the content of the dialogue including the user's inquiry and the content of the response process is displayed. Parking management system.

16. The parking lot management system according to claim 1, The issuing unit issues the receipt or the invoice on which information regarding a payment method for the unpaid parking fee is displayed. Parking management system.

17. The parking lot management system according to claim 1, further comprising: a storage unit that stores information on at least one of the content of the dialogue including the user's inquiry and the content of the response processing as response history information; The issuing unit issues the receipt or invoice on which a code image storing a URL of a website including the response history information is displayed. Parking management system.

18. The parking lot management system according to claim 1, The inquiry response unit connects the user making the inquiry to an operator so that the user can have a conversation with the operator when a predetermined operator connection condition is satisfied. Parking management system.

19. A parking lot management method executed by a computer system, comprising: a voice data acquisition step of acquiring voice data of an inquiry about use of the parking lot input by voice from a user of the parking lot; an inquiry response step of executing a predetermined response process regarding use of the parking lot based on the acquired voice data of the inquiry; Including, The inquiry response step generates response data for realizing a dialogue with the user based on voice data of the inquiry, and executes the response process based on the content of the dialogue with the user. Parking lot management methods.

20. A program for causing a computer system to execute a parking lot management method, The parking lot management method includes: a voice data acquisition step of acquiring voice data of an inquiry about use of the parking lot input by voice from a user of the parking lot; an inquiry response step of executing a predetermined response process regarding use of the parking lot based on the acquired voice data of the inquiry; Including, The inquiry response step generates response data for realizing a dialogue with the user based on voice data of the inquiry, and executes the response process based on the content of the dialogue with the user. program.

Images