Inspection system and information presentation method

Abstract

To provide an inspection system and information presentation method that enable efficient inspection. [Solution] According to the embodiment, the inspection system comprises an information processing device and an inspection device. The information processing device includes a first communication unit, an acquisition unit, a memory, and a first processor. The acquisition unit acquires declaration data indicating the declared contents of the cargo to be inspected. The memory stores reference data indicating judgment criteria for screening the declaration data. The first processor performs screening on the declaration data acquired by the acquisition unit based on the judgment criteria indicated by the reference data, and transmits the declaration data and the screening results to the inspection device. The inspection device comprises a second communication unit and a second processor. The second processor displays the declaration data of the cargo to be inspected acquired from the information processing device and the screening results for said declaration data on a display device.

Description

Technical Field

[0001] Embodiments of the present invention relate to an inspection system and an information presentation method.

Background Art

[0002] Conventionally, at inspection sites such as customs, an inspection operation is performed to inspect the contents within inspection targets such as luggage. It takes a great deal of time and effort for an inspector to open and inspect all of a large number of pieces of luggage. Therefore, in a conventional inspection system, based on the inspection result from a captured image obtained by irradiating electromagnetic waves such as X-rays onto the luggage to be inspected and the content of a notification form in which the applicant has previously notified the contents, an inspector decides whether to perform an opening inspection in which the luggage is actually opened and inspected.

[0003] In a conventional inspection system, not only does it take time for an inspector to visually judge the content of the notification form or to compare and judge the content of the notification form with a table showing predetermined rules, but it may also be troublesome for the inspector to accurately confirm the content of the notification form corresponding to the luggage to be inspected. In addition, in a conventional inspection system, there is also a problem that a large difference may occur in inspection accuracy and inspection speed depending on the ability of individual inspectors.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The problem to be solved by the present invention is to provide an inspection system and an information presentation method that can perform inspections efficiently.

Means for Solving the Problems

[0006] According to one embodiment, the inspection system comprises an information processing device and an inspection device. The information processing device includes a first communication unit, an acquisition unit, a memory, and a first processor. The first communication unit communicates with the inspection device. The acquisition unit acquires declaration data indicating the declared contents of the cargo to be inspected. The memory stores reference data indicating judgment criteria for screening the declaration data acquired by the acquisition unit. The first processor performs screening on the declaration data acquired by the acquisition unit based on the judgment criteria indicated by the reference data, and transmits the declaration data and the screening results to the inspection device. The inspection device comprises a second communication unit and a second processor. The second communication unit communicates with the information processing device. The second processor causes a display device to show the declaration data of the cargo to be inspected and the screening results for the declaration data acquired from the information processing device. [Brief explanation of the drawing]

[0007] [Figure 1] Figure 1 shows an example of the overall configuration of the inspection system according to the embodiment. [Figure 2] Figure 2 is a schematic diagram showing an example of the configuration of the inspection processing system in the inspection system according to the embodiment. [Figure 3] Figure 3 is a block diagram showing an example of the configuration of an inspection device in an inspection system according to an embodiment. [Figure 4] Figure 4 is a block diagram showing an example configuration of a data server as an information processing device in an inspection system according to the embodiment. [Figure 5] Figure 5 is a block diagram showing an example configuration of a learning server as a learning device in the inspection system according to this embodiment. [Figure 6] Figure 6 shows an example of the screening results for customs electronic data by a data server, which acts as an information processing device in the inspection system according to the embodiment. [Figure 7] Figure 7 is a flowchart illustrating an example of the operation in which a data server, acting as an information processing device in the inspection system according to the embodiment, performs screening. [Figure 8] Figure 8 is a flowchart illustrating an example of how an inspection device in an inspection system according to an embodiment displays screening results during package inspection. [Figure 9] Figure 9 is a flowchart illustrating an example of operation in which a learning server, acting as a learning device in the inspection system according to this embodiment, performs machine learning on the inspection results. [Modes for carrying out the invention]

[0008] The embodiments will be described below with reference to the drawings. First, the configuration of the inspection system 1 according to this embodiment will be described. Figure 1 is a diagram illustrating an example of the overall configuration of the inspection system 1 according to the embodiment. Inspection System 1 is a system for inspecting packages as objects to be inspected. Inspections conducted using Inspection System 1 include not only inspection of the package's appearance and photographic images of the package, but also open inspections (detailed inspections) in which inspectors examine the contents inside the package.

[0009] The cargo subject to inspection only needs to have declaration data (e.g., customs electronic data) that shows the declaration details of the cargo made by the declarant (notifier). Furthermore, the customs electronic data, as declaration data, includes information that shows the declaration details of the contents of the cargo. For example, the cargo subject to inspection may be a delivery item including postal items, or it may be hand luggage. In this embodiment, the cargo subject to inspection is assumed to be a delivery item being exported or imported, and the declaration data showing the declaration details of the cargo is customs electronic data (EAD).

[0010] The inspection system 1 according to this embodiment includes an inspection processing system 2, which includes an inspection device 11 that is actually placed in an inspection area where packages are inspected, and an information processing system 3, which includes a data server (information processing device) 16 that manages information. In the configuration shown in Figure 1, the inspection processing system 2 consists of an inspection device 11, a camera 12, a display device 13, an operating device 14, and an inspection result input device (information input device) 15, etc., and the information processing system 3 consists of a data server (information processing device) 16 and a learning server (learning device) 17, etc.

[0011] The inspection system 1 according to this embodiment is not limited to the device configuration shown in Figure 1. For example, the inspection system 1 may consist of a data server 16 and a learning server 17 in a single device, or the inspection device 11 may have the configuration and functions of the data server 16 or learning server 17 described later. The inspection system 1 with the device configuration shown in Figure 1 will be described below.

[0012] In the inspection area where inspectors actually inspect packages, each device constituting the inspection processing system 2 for inspecting the packages to be inspected is installed. The inspection processing system 2 installed in the inspection area acquires information such as photographic images of the packages to be inspected and declaration data indicating the contents of the packages, and provides the inspectors with information for inspecting the contents of the packages. The inspectors refer to the information on the packages to be inspected presented in the inspection area to determine whether an open inspection of the packages is necessary. If an open inspection is determined to be necessary, the inspectors open the packages to check for the presence of specific items (items to be seized) inside the packages, and to check whether the amount of tax on the goods (taxable items) inside the packages is appropriate.

[0013] Examples of items subject to inspection (hereinafter referred to as "items subject to seizure") include hazardous materials, substances whose handling is prohibited, and substances whose import or export into or out of a designated area (e.g., within Japan) is prohibited. Duty goods are items on which taxes (e.g., customs duties) are levied at an amount determined by the tax rate set according to the prescribed tax rules. The amount of tax on duty goods is shown to the inspector, for example, by a tax amount table.

[0014] Inspection system 1 includes information processing system 3, which manages data related to the cargo to be inspected. Information processing system 3 in inspection system 1 obtains declaration data, such as customs electronic data showing the contents of the declaration form regarding the contents of the cargo, from an external system 18. Information processing system 3 performs screening on the declaration data regarding the contents of the cargo (hereinafter referred to as customs electronic data) before conducting inspection at the inspection site. Screening is a process to determine whether the cargo contains items that may be subject to seizure based on the contents indicated by the customs electronic data, or whether an open inspection is recommended for the cargo. Information processing system 3 provides information including the customs electronic data for the cargo to be inspected and the results of its screening to the inspection processing system 2.

[0015] Furthermore, the information processing system 3 of the inspection system 1 has the function of collecting and managing inspection results for packages, and generating data that includes standard data used for screening by learning from the collected inspection results. The information processing system 3 collects the inspection results for each package performed by inspectors at the inspection site. The information processing system 3 generates conditions to be used for screening by performing machine learning using the inspection results for packages and the electronic customs data corresponding to those inspection results.

[0016] Figure 2 shows an example of the configuration of a system installed in an inspection area where the inspection system 1 according to the embodiment inspects the packages to be inspected. As shown in FIG. 2, the inspection device 11, the conveyor C, the imaging device 12, the display device 13, and the operation device 14 are installed at an inspection site for determining the necessity of open inspection of a package. The inspection device 11 is connected to the imaging device 12, the display device 13, and the operation device 14 via an interface. Further, as shown in FIG. 1, the inspection device 11 is communicatively connected to an inspection result input device 15, a data server 16, a learning server 17, etc. The inspection result input device 15 shown in FIG. 1 is an information input device for an inspector to input inspection results obtained by open inspection, and is arranged at an inspection site for performing open inspection on a package for which open inspection has been determined to be necessary.

[0017] In the configuration example shown in FIG. 2, the conveyor C is a device for conveying a package M to be inspected. The conveyor C conveys the package M to be inspected to the imaging position (reading position) of an image by the imaging device 12. For example, the conveyor C conveys the package M supplied by an inspector. Also, the conveyor C may be configured to convey the package M supplied by a robot arm or the like.

[0018] The imaging device 12 irradiates the package M to be inspected conveyed by the conveyor C with electromagnetic waves to image the package M. The imaging device 12 may be any device that can obtain a captured image in which articles inside the package M to be inspected can be visually recognized. The imaging device 12 may obtain two-dimensional image data as the captured image, or may obtain three-dimensional image data. Further, the imaging device 12 shall obtain captured image data including the captured image of the package M to be inspected irradiated with electromagnetic waves and the physical property information indicating the physical properties of each part (e.g., pixel or voxel) of the captured image. The imaging device 12 supplies the captured image data of the package M to the inspection device 11. Note that a pixel is a pixel constituting two-dimensional image data. A voxel is the minimum unit data constituting three-dimensional data and represents a value in a regular grid unit.

[0019] The imaging device 12 is, for example, an X-ray CT scanner (CT scanner). An example of an imaging device 12, an X-ray CT scanner, acquires three-dimensional X-ray image data as an image by irradiating X-rays around the cargo M being transported by the conveyor C. The X-ray CT scanner, as imaging device 12, also acquires image data that includes a three-dimensional X-ray image (image) of the cargo M taken using X-rays, and physical property information indicating the physical properties of each constituent unit (voxel) that makes up the X-ray image. The X-ray CT scanner, as imaging device 12, supplies the image data acquired from the cargo M to the inspection device 11. However, the imaging device 12 is not limited to an X-ray CT scanner.

[0020] The inspection device 11 consists of a computer and other components equipped with interfaces for connecting to each device. The inspection device 11 has functions such as acquiring information about luggage M from the data server 16, acquiring image data of luggage M from the camera 12, displaying information about luggage M and image data on the display device 13, acquiring information such as inspection results (determination results of whether or not an open inspection is necessary) entered by the inspector using the operating device 14, and outputting the inspection results entered by the inspector.

[0021] The inspection device 11 displays information about the package to be inspected on the display device 13 and accepts input of inspection results from the inspector via the operating device 14. For example, the inspection device 11 identifies the package M to be inspected being transported by the conveyor C and obtains information such as customs electronic data and screening results as information about the identified package M from the data server 16. The inspection device 11 also obtains data (image data) as a result of photographing the package M by the photographing device 12 from the photographing device 12.

[0022] The inspection device 11 displays information about the package M obtained from the data server 16, as well as images of the package M taken by the camera 12, on the display device 13, and accepts input of the inspection results for the package from the inspector to the operation device 14. The inspector performs an inspection, including determining whether or not an open inspection of the package M is necessary, based on the information displayed on the display device 13, and inputs the inspection results into the inspection device 11 using the operation device 14.

[0023] The inspection device 11 transmits the inspection results for the package M, which are entered by the inspector using the operating device 14, to the data server 16 or the like. The inspection device 11 adds the identification information of the package M and the identification information of the inspector who performed the inspection to the inspection results of the package M, so that the inspection results are associated with the customs electronic data and the inspector who performed the inspection. The inspection device 11 may also transfer the inspection results for the package M and the captured image of the package M to a device installed in the inspection area where the open inspection is performed, such as the information input device 15.

[0024] The display device 13's display content is controlled by the inspection device 11. For example, the display device 13 displays information such as photographic image data of the package M to be inspected, the customs electronic data of the package M, and the results of the screening of the customs electronic data of the package M. The display device 13 may also display past photographic images and customs electronic data extracted by the screening of the customs electronic data of the package M.

[0025] The operating device 14 generates an operation signal in response to the operator's input and supplies the operation signal to the inspection device 11. The operating device 14 consists of an operation device such as a keyboard and a pointing device. Alternatively, the operating device 14 may be configured as a touch panel or the like on the display screen of the display device 13.

[0026] Next, the configuration of the information processing system 3 that manages information in the inspection system 1 according to this embodiment will be described. The inspection system 1 according to this embodiment includes an information processing system 3 for managing information about the luggage M to be inspected. In the configuration example shown in Figure 1, the information processing system 3 in the inspection system 1 has a data server (information processing device) 16 and a learning server (learning device) 17. However, the data server 16 and the learning server 17 may be implemented by a single information processing device, or each may be composed of multiple information processing devices.

[0027] The data server 16 consists of one or more computer devices, such as server equipment. The data server 16 is an example of an information processing device. The data server 16 is connected to the inspection device 11, the information input device 15, the learning server 17, and the external system 18. The data server 16 acquires inspection results for packages from the inspection device 11 and the information input device 15, etc., and manages the inspection results for each package.

[0028] Furthermore, the data server 16 acquires customs electronic data, which is declaration data indicating the declared contents of the cargo, from the external system 18. The data server 16 performs screening on the customs electronic data acquired from the external system 18. The screening by the data server 16 is a process that determines, based on the customs electronic data, whether the cargo may contain items subject to seizure, or whether it is cargo for which an open inspection is recommended. For each cargo to be inspected, the data server 16 supplies the customs electronic data and the results of the screening process on the customs electronic data to the inspection device 11.

[0029] Furthermore, the data server 16 performs screening to evaluate the electronic customs data based on the conditions (judgment criteria) indicated by the reference data. The judgment criteria indicated by the reference data used for screening include warning criteria set according to general rules and warning criteria obtained by machine learning from past inspection results. In addition, the judgment criteria indicated by the reference data used for screening may also include criteria for inspection obtained by machine learning from the judgment results of whether an inspection is necessary for packages extracted under specific conditions (for example, the judgment results of whether an inspection is necessary by a specific inspector).

[0030] For example, the data server 16 stores reference data in memory that indicates the conditions used for screening, and performs screening of the customs electronic data of the cargo based on that reference data. When the data server 16 obtains learning-generated data, such as inspection results or judgment results on whether an unpacking inspection is necessary, from the learning server 17, it updates the reference data stored in memory based on the learning-generated data obtained from the learning server 17. In this way, the data server 16 can update the judgment criteria (reference data) used for screening the customs electronic data using machine learning of actual inspection results.

[0031] The learning server 17 is composed of one or more computers, such as server devices. The learning server 17 is an example of a learning device. The learning server 17 is connected to the inspection device 11 and the data server 16. The learning server 17 obtains inspection results for packages (including the results of opening and closing inspections and the determination of whether or not an opening and closing inspection is necessary) from the inspection device 11 and the like. The learning server 17 learns the trends in customs electronic data of packages that should be subject to opening and closing inspections from the actual inspection results of the packages, and generates data to be added to the judgment criteria in screening (data for updating the standard data). For example, the learning server 17 generates data to be added to the judgment criteria used for screening by classifying and learning the customs electronic data of packages that were subject to seizure, customs electronic data of packages that were not subject to seizure, and customs electronic data of packages that a particular inspector determined should be opened and closed, etc.

[0032] External system 18 is a system that manages customs electronic data, which is declaration data showing the contents of declarations (e.g., notices) regarding goods subject to inspection. For example, external system 18 accepts goods such as delivery items and obtains customs electronic data from the declarant showing the declaration contents, including information indicating the contents of the accepted goods. External system 18 stores and manages the customs electronic data obtained from the declarant and supplies the customs electronic data of the goods to the information processing devices of each system that handles the goods.

[0033] In this embodiment, the external system 18 supplies the customs electronic data to the inspection system 1, which performs inspections of the corresponding packages. For example, the external system 18 supplies the customs electronic data of the packages to the data server 16 of the inspection system 1, which performs inspections of the packages.

[0034] Next, the configuration of the control system in the inspection device 11, which constitutes the inspection processing system 2 in the inspection system 1 according to the embodiment, will be described. Figure 3 is a block diagram showing an example of the configuration of the control system in the inspection device 11 of the inspection processing system 2 in the inspection system 1 according to the embodiment. As shown in Figure 3, the inspection device 11 includes a processor (second processor) 31, ROM 32, RAM 33, storage unit 34, communication unit (second communication unit) 35, display interface (I / F) 36, operation interface (I / F) 37, and image interface (I / F) 39.

[0035] The processor 31 performs arithmetic processing. The processor 31 is, for example, a CPU (Central Processing Unit). The processor 31 functions as a processing unit that performs various operations by executing programs stored in the ROM 32 or storage unit 34 using the RAM 33.

[0036] ROM32 is a read-only, non-volatile memory. ROM32 stores program data and control data, among other things. RAM33 is a volatile memory that functions as working memory. RAM33 temporarily stores data.

[0037] The memory unit 34 is a rewritable non-volatile memory. The memory unit 34 is composed of a hard disk drive (HDD), a solid-state drive (SSD), etc. The memory unit 34 stores information such as program data, setting values ​​as control data, and the results of inspection processing. For example, the memory unit 34 stores image data of the luggage to be inspected acquired from the imaging device 12 and information about the luggage acquired from the data server 16.

[0038] The communication unit 35 is a communication interface for communicating with the data server 16 and the learning server 17. The processor 31 obtains electronic customs clearance data and screening results from the data server 16 by communicating with the data server 16 via the communication unit 35. The processor 31 also transmits data such as inspection results to the learning server 16 by communicating with the learning server 17 via the communication unit 35.

[0039] The display interface 36 is an interface for connecting to the display device 13. The display interface 36 only needs to be compatible with the interfaces provided by the display device 13. The processor 31 controls the display content to be shown on the display device 13 via the display interface 36.

[0040] The operation interface 37 is an interface for connecting to the operating device 14. The operation interface 37 only needs to correspond to the interfaces provided by the operating device 14. The processor 31 acquires information input by the operating device 14 via the operation interface 37.

[0041] The image interface 39 is an interface for connecting to the imaging device 12. The image interface 39 can be any interface that is compatible with the imaging device 12, such as an X-ray CT scanner. The processor 31 acquires imaging image data obtained from the X-ray images taken by the X-ray CT scanner, which is the imaging device 12, via the image interface 39. The processor 31 may also control the imaging operation of the imaging device 12 on the luggage M via the image interface 39.

[0042] Furthermore, the inspection device 11 may also be equipped with a device for notifying inspectors of warnings or alerts. For example, the inspection device 11 may be equipped with a speaker that outputs sound as a warning or alert, or it may be equipped with a light-emitting device that outputs light as a warning or alert.

[0043] Next, the configuration of the data server 16 of the information processing system 3 in the inspection system 1 according to the embodiment will be described. Figure 4 is a block diagram showing an example configuration of the data server 16 of the information processing system 3 in the inspection system 1 according to the embodiment. The data server 16 is an information processing device that manages information in the entire inspection system 1. The data server 16 is composed of one or more computers. In the configuration example shown in Figure 4, the data server 16 has a processor (first processor) 41, ROM 42, RAM 43, storage unit 44, communication unit (first communication unit) 45, and external communication unit (acquisition unit) 46.

[0044] The processor 41 performs arithmetic processing. The processor 41 is, for example, a CPU. The processor 41 functions as a processing unit that performs various operations by executing programs stored in the ROM 42 or storage unit 44 using the RAM 43.

[0045] ROM42 is a read-only non-volatile memory. ROM42 stores program data and control data, etc. RAM43 is a volatile memory that functions as working memory. RAM43 temporarily stores data.

[0046] The storage unit 44 is a rewritable non-volatile memory. The storage unit 44 is composed of a hard disk drive (HDD), a solid-state drive (SSD), etc. The storage unit 44 stores information such as program data, setting values ​​as control data, and data acquired from the inspection device 11, the learning server 17, or an external system 18. For example, the storage unit 44 stores the electronic customs clearance data of each package to be inspected, which is acquired from the external system 18. The storage unit 44 also includes a storage area 44a as memory for storing reference data that indicates the judgment criteria (conditions) used for screening the electronic customs clearance data of the packages.

[0047] The communication unit 45 includes a communication interface for communicating with the inspection device 11. For example, the processor 41 supplies information about the package, such as customs electronic data and screening results, to the inspection device 11 via the communication unit 45, and obtains inspection results for the package from the inspection device 11 (including the determination of whether or not an open inspection is necessary).

[0048] Furthermore, the communication unit 45 also includes a communication interface for communicating with the information input device 15. For example, the processor 41 obtains inspection results from actual unpacking and inspection of packages input to the information input device 15 by communicating with the information input device 15 via the communication unit 45.

[0049] Furthermore, the communication unit 45 includes a communication interface for communicating with the learning server 17. For example, the processor 41 communicates with the learning server 17 via the communication unit 45 to obtain data generated by machine learning performed by the learning server 17 using the inspection results of the packages.

[0050] The external communication unit 46 includes a communication interface for communicating with the external system 18. The external communication unit 46 is an example of an acquisition unit that acquires electronic customs clearance data of the cargo to be inspected by the inspection system 1. For example, the processor 41 acquires the electronic customs clearance data of the cargo by communicating with the external system 18 via the external communication unit 46. However, the external communication unit 46 as an acquisition unit only needs to include an interface that acquires electronic customs clearance data of the cargo to be inspected by the inspection system 1.

[0051] Next, the configuration of the learning server 17 of the information processing system 3 in the inspection system 1 according to the embodiment will be described. Figure 5 is a block diagram showing an example configuration of the learning server 17 of the information processing system 3 in the inspection system 1 according to the embodiment. The learning server 17 is a learning device (information processing device) that performs machine learning to generate data used for screening customs electronic data using inspection results for packages actually inspected by the inspection system 1. The learning server 17 collects the results of the determination of whether or not an open inspection is necessary for the packages, and the inspection results from the actual open inspections of the packages. By performing machine learning using the inspection results, including the determination of whether or not an open inspection is necessary and the inspection results from the actual open inspections, the learning server 17 generates data (data for updating the standard data) that indicates the judgment criteria (warning criteria, criteria for open inspection) used for screening customs electronic data.

[0052] In the configuration example shown in Figure 5, the learning server 17 includes a processor (third processor) 51, ROM 52, RAM 53, storage unit 54, and communication unit (third communication unit) 55. The processor 51 performs arithmetic processing. The processor 51 is, for example, a CPU. The processor 51 functions as a processing unit that performs various operations by executing programs stored in the ROM 52 or storage unit 54 using the RAM 53.

[0053] ROM52 is a read-only non-volatile memory. ROM52 stores program data and control data, etc. RAM53 is a volatile memory that functions as working memory. RAM53 temporarily stores data.

[0054] The memory unit 54 is a rewritable non-volatile memory. The memory unit 54 is composed of a hard disk drive (HDD), a solid-state drive (SSD), etc. The memory unit 54 stores information such as program data, setting values ​​as control data, and inspection results collected from the inspection device 11, etc.

[0055] For example, the storage unit 54 stores information indicating the inspection results for packages performed by the inspection system 1. The inspection results stored in the storage unit 54 include, for example, not only the inspection results from opening and inspecting packages, but also the results of each inspector's judgment on whether or not an opening and inspection of a package is necessary. The inspection results stored in the storage unit 54 include information that identifies the electronic customs data corresponding to the package (e.g., package identification information) and information that identifies the inspector who performed the inspection (e.g., inspector identification information).

[0056] The communication unit 55 is a communication interface for communicating with the inspection device 11, the information input device 15, and the data server 16. For example, the processor 51 obtains inspection results, which are the determination results of whether or not an open inspection is necessary for a package, from the inspection device 11, which communicates via the communication unit 55. The communication unit 55 also includes a communication interface for obtaining inspection results from an information processing device (not shown) for packages that have been determined to require an open inspection in the inspection processing system 2. The communication unit 55 also includes a communication interface for communicating with the data server 16. The processor 51 supplies learning results for the inspection results to the data server 16, which communicates via the communication unit 55.

[0057] Next, we will describe the screening of customs clearance electronic data of packages performed by the data server 16, which acts as an information processing device for the inspection system 1 according to this embodiment. The electronic customs data that the data server 16, acting as an information processing device, screens is declaration data that shows the declared (notified) contents of the cargo to be inspected by the inspection system 1. However, the electronic customs data is information entered by the applicant and is not guaranteed to accurately represent the contents of the cargo.

[0058] Customs electronic data includes identification information attached to (inscribed on) the package and corresponding identification information, as well as information indicating the contents of the package. For example, customs electronic data may include information such as package identification information, recipient information (recipient address, name), sender information (sender address, name), product name of each item (contents), unit price of each item, country of origin of each item, weight per item (g / item), item identification information of each item (e.g., HS code), number of each item, type of each item, total value of the items, and total weight.

[0059] In this embodiment, the data server 16 in the inspection system 1 acquires customs electronic data of the cargo to be inspected from an external system 18. The data server 16 performs screening of the customs electronic data based on reference data. In the screening, the processor 41 of the data server 16 selects cargo that may be subject to seizure based on the contents indicated by the customs electronic data, and selects cargo for which opening and inspection is recommended. The data server 16 stores reference data indicating the criteria (conditions) for screening the customs electronic data in the storage area 44a of the storage unit 44. The processor 41 of the data server 16 performs screening to select the customs electronic data based on the criteria indicated by the reference data.

[0060] The criteria used for screening in the data server 16 include, for example, warning criteria for selecting customs electronic data that should alert inspectors conducting cargo inspections. The warning criteria indicated by the criteria include not only warning criteria set by known information such as regulations (general warning criteria), but also warning criteria obtained by machine learning from past inspection results, etc. (learned warning criteria).

[0061] Furthermore, the warning criteria used as judgment criteria in the reference data may be set for each warning level in order to select customs electronic data according to the warning level of the warning to be notified. By setting warning criteria for each of these multiple warning levels, customs electronic data can be selected according to the warning level through screening, and warnings corresponding to the warning level can be notified as warnings based on the screening results by the inspection device 11 described later.

[0062] For example, warning levels may be set for each category of items in the shipment subject to seizure. Specifically, the criteria for identifying potentially dangerous goods could be set as Warning Level 1 (Warning 1), the criteria for identifying potentially prohibited items such as drugs could be set as Warning Level 2 (Warning 2), and the criteria for identifying items that are highly likely to require tax verification could be set as Warning Level 3 (Warning 3).

[0063] Furthermore, the criteria indicated by the reference data used for screening in the data server 16 include criteria for selecting customs clearance electronic data for packages that warrant an inspection, which is recommended to inspectors who determine whether an inspection is necessary. The criteria for inspection indicated by the reference data include criteria for inspection obtained by machine learning from the results of inspection requirements extracted under specific conditions (for example, the results of inspection requirements for packages by specific inspectors).

[0064] Figure 6 shows an example of the customs electronic data of a package to be inspected by the inspection system 1 according to this embodiment, and the screening results for that customs electronic data. In the example shown in Figure 6, the customs electronic data includes information for each item in the package, such as the item name, weight, country of origin, quantity, and tax amount. However, the customs electronic data also includes information such as package identification information, recipient information (recipient address, name), and sender information (sender address, name). In addition to the items exemplified in Figure 6, it may also include the unit price of each item, the weight per item of each item, the identification code of each item, the type of each item, the total value of the items, and the total weight of the items.

[0065] Furthermore, in the example shown in Figure 6, screening results based on the criteria shown in the reference data are displayed for each item indicated in the customs electronic data. In the example shown in Figure 6, the screening results indicate the category and whether or not a warning or recommended inspection is issued. In addition, the presence or absence of a warning or recommended inspection is indicated as one of the following: "○ (no warning)", "warning level", or "open (inspection recommended)". The criteria shown in the reference data for obtaining such screening results may be, for example, conditions set for each item in the customs electronic data, or conditions set for combinations of multiple items in the customs electronic data.

[0066] For example, as a concrete example of setting judgment criteria for each item in customs electronic data, if a weight of 1000 kg or more is set as the warning criterion for warning level 1, then customs electronic data weighing 1000 kg can be screened and determined to be warning level 1. Also, if the product name is set as the warning criterion for warning level 2, then customs electronic data with the product name "sample" can be screened and determined to be warning level 2.

[0067] Furthermore, criteria for determining the suitability of combinations of multiple items in electronic customs data include conditions for determining whether there are any inconsistencies in the relationships between the information of the multiple items. For example, if a warning level 3 criterion is set for items with the item name "alcohol" and a tax amount of 100 yen or less, then electronic customs data for alcohol with a tax amount of 10 yen (100 yen or less) can be screened and determined to be warning level 3. Similarly, if a warning level 1 criterion is set for items with the item name "clothing" and a weight of 500 kg or more, then electronic customs data for clothing weighing 500 kg or more can be screened and determined to be warning level 1.

[0068] Furthermore, the criteria used for screening, as indicated by the reference data, may not be limited to the criteria for individual items within a package as shown in the electronic customs data, but may also include criteria for the characteristics of the electronic customs data as a whole. For example, criteria for open inspection may be set to recommend an open inspection for combinations of multiple items present in a package as indicated in the electronic customs data.

[0069] Next, the process by which the data server 16 in the inspection system 1 according to the embodiment performs screening of customs electronic data will be described. Figure 7 is a flowchart illustrating an example of how the data server 16 performs screening on customs electronic data. The data server 16 receives (acquires) customs electronic data of the cargo to be inspected by the inspection system 1 from the external system 18 via the external communication unit 46, which acts as an acquisition unit (step ST11). For example, the processor 41 of the data server 16 stores the customs electronic data received from the external system 18 in the storage unit 44.

[0070] When the processor 41 of the data server 16 acquires the electronic customs clearance data of the cargo to be inspected, it performs a screening of the acquired electronic customs clearance data based on the judgment criteria indicated by the reference data stored in the storage area 44a of the storage unit 44.

[0071] In the example operation shown in Figure 7, the processor 41 of the data server 16 first performs a screening of the customs electronic data based on the warning criteria indicated by the reference data (step ST12). For example, the warning criteria indicated by the reference data are set for each warning level and include general warning criteria generated from general regulations, etc., and learned warning criteria generated by machine learning on the inspection results of the cargo. The learned warning criteria are obtained by machine learning on the actual inspection results by the learning server 17, which will be described later. When the learning server 17 generates warning criteria by machine learning, the processor 41 of the data server 16 updates the learned warning criteria stored in the storage unit 44.

[0072] The processor 41 of the data server 16 determines whether the customs electronic data is subject to a warning in the screening based on the warning criteria indicated by the reference data (step ST13). If the processor 41 determines that the customs electronic data is subject to a warning (step ST13, YES), it determines the warning level of the customs electronic data based on the warning criteria for each warning level indicated by the reference data, and sets the determined warning level as the screening result for the customs electronic data (step ST14).

[0073] If the processor 41 of the data server 16 determines that the customs electronic data is not subject to a warning (step ST13, NO), it performs screening based on the criteria for opening and inspecting the goods indicated by the reference data (step ST15). For example, the criteria for opening and inspecting the goods indicated by the reference data are generated by machine learning on the results of past opening and inspecting of goods by a specific inspector (the results of opening and inspecting the goods extracted under specific conditions). The criteria for opening and inspecting the goods are obtained by machine learning performed by the learning server 17, which will be described later. The processor 41 of the data server 16 is configured to update the criteria for opening and inspecting the goods stored in the storage unit 44 with the criteria for opening and inspecting the goods generated by the learning server 17 through machine learning.

[0074] The processor 41 of the data server 16 determines whether or not the customs electronic data is subject to a recommendation for inspection by screening based on the criteria for inspection (step ST16).

[0075] If the processor 41 of the data server 16 determines that the customs electronic data is subject to a recommendation for inspection (step ST16, YES), it sets the screening result for the customs electronic data as a recommendation for inspection (step ST17).

[0076] If the processor 41 of the data server 16 determines that the customs electronic data is not subject to a recommendation for inspection (step ST16), it terminates the screening for the customs electronic data, setting the screening result to a warning and no recommendation for inspection.

[0077] Furthermore, if the data server 16's processor 41 sets a warning level as a screening result, or recommends opening and inspecting the package, it sets a photograph of a previously inspected package and its inspection result as reference images for inspecting the package in question (step ST18). Based on the customs electronic data for which a warning level or recommendation for opening and inspecting has been set as a screening result, the processor 41 sets a photograph of an inspected package and its inspection result, which can serve as reference information when performing an inspection of the package corresponding to the customs electronic data.

[0078] For example, if a warning level is set, the processor 41 sets a predetermined number of images of packages corresponding to customs electronic data that were previously determined to meet the same warning criteria as the customs electronic data in question. Also, if a recommendation for opening and inspecting is set, the processor 41 sets a predetermined number of images of packages corresponding to customs electronic data that were previously determined to meet the same criteria as the customs electronic data for opening and inspecting that the customs electronic data in question met. Furthermore, the processor 41 may extract customs electronic data of inspected packages similar to the customs electronic data for which a warning level or a recommendation for opening and inspecting has been set, and set the images taken during the inspection of the extracted customs electronic data packages as past images.

[0079] Through the above process, the data server 16 performs screening of the customs electronic data. The data server 16 stores the customs electronic data and the screening results in the storage unit 44, associating them. The processor 41 of the data server 16 supplies the customs electronic data of the cargo to be inspected and the screening results for that customs electronic data to the inspection device 11 that performs the cargo inspection.

[0080] Next, the inspection process of packages by the inspection device 11 in the inspection system 1 according to this embodiment will be described. Figure 8 is a flowchart illustrating an example of the operation of the inspection process of packages by the inspection device 11 in the inspection system 1 according to this embodiment. In the inspection processing system 2 configured as shown in Figure 2, packages to be inspected are sequentially fed onto the conveyor C. The conveyor C transports the fed packages to the position where the image capture device 12 takes place. The inspection device 11 performs inspections on the packages transported on the conveyor C in the inspection processing system 2 as shown in Figure 2.

[0081] The processor 31 of the inspection device 11 first acquires identification information of the package to be inspected (step ST31). The processor 31 of the inspection device 11 may acquire the identification information of the package by reading a label or the like attached to the package being transported on the conveyor C by a reading device (not shown), or it may acquire the identification information of the package entered by the inspector using the operating device 14.

[0082] When the processor 31 of the inspection device 11 acquires identification information of the cargo to be inspected, it acquires the customs electronic data of the cargo identified by the identification information and the screening results for that customs electronic data (step ST32). For example, the processor 31 of the inspection device 11 communicates with the data server 16 via the communication unit 35, specifies the identification information of the cargo to be inspected, and acquires the customs electronic data of the cargo and its screening results from the data server 16. Alternatively, the inspection device 11 may store the customs electronic data and its screening results supplied from the data server 16 in the storage unit 34 at any time, and read the customs electronic data and its screening results identified by the identification information of the cargo to be inspected from the storage unit 34.

[0083] Meanwhile, the imaging device 12 in the inspection processing system 2 detects packages being transported to the imaging position by the conveyor C and captures an image of the package transported to the imaging position. For example, the imaging device 12 captures an image showing the internal state of the package by irradiating it with electromagnetic waves (X-rays). The imaging device 12 supplies the captured image (for example, a three-dimensional image) of the package to the inspection device 11. Here, the imaging device 12 may also acquire physical property information indicating the physical properties of each part of the captured image and supply the imaging image data, which includes the captured image and the physical property information indicating the physical properties of each part of the captured image, to the inspection device 11.

[0084] The processor 31 of the inspection device 11 acquires the image of the package to be inspected, which has been captured by the camera 12, via the image interface 39 (step ST33). Once the processor 31 of the inspection device 11 has acquired the image of the package to be inspected, it displays the image of the package, the customs electronic data, and information such as the screening results for the customs electronic data (information related to the package) on the display device 13 (step S34).

[0085] When displaying the screening results, the processor 31 of the inspection device 11 determines whether a warning (warning level) or a recommendation for opening and inspecting has been set for the customs electronic data. In the example operation shown in Figure 8, the processor 31 of the inspection device 11 determines whether a warning (warning level) has been set as the screening result for the customs electronic data (step ST35).

[0086] If a warning is set in the customs electronic data (step ST35, YES), the processor 31 of the inspection device 11 identifies the warning level set in the customs electronic data and notifies the user of a warning corresponding to that level (step ST36). For example, the processor 31 displays a warning corresponding to the warning level set in the customs electronic data on the display device 13. The display of a warning corresponding to the warning level may be by displaying the wording of the warning, or by changing the display state of the display screen on the display device 13 to a display state corresponding to the warning level (for example, the background color to a color set according to the warning level). The notification of a warning corresponding to the warning level is not limited to displaying it on the display device 13, but may also be by emitting a sound or light set according to the warning level.

[0087] This allows inspectors conducting inspections of packages to determine whether or not to open the package if a warning level has been set based on the screening results of the electronic customs data, while receiving a warning corresponding to the warning level. As a result, the screening results of the electronic customs data, which can be obtained in advance, can assist inspectors in their actual inspections of packages, and the warnings given to inspectors can be tailored to the warning level.

[0088] If no warning is set for the customs electronic data (step ST35, NO), the processor 31 of the inspection device 11 determines whether or not a recommendation for opening and inspecting the customs electronic data has been set as a screening result for the said customs electronic data (step ST37).

[0089] If the customs electronic data of the package to be inspected indicates that an open inspection is recommended (step ST37, YES), the processor 31 of the inspection device 11 issues a warning recommending an open inspection of the package (step ST38). For example, the processor 31 displays a warning on the display device 13 recommending an open inspection of the package to be inspected. Note that the warning recommending an open inspection is not limited to being displayed on the display device 13; it may also be expressed by emitting sound or light intended to recommend an open inspection.

[0090] This allows inspectors conducting inspections of packages to determine whether or not to open and inspect packages that are recommended for inspection based on screening results against electronic customs data, by considering the warning about opening and inspecting displayed on a display device connected to the inspection device.

[0091] Furthermore, in the screening by the data server 16 described above, if a warning level or a recommendation for opening and inspecting is set for the customs electronic data, past images of packages may be set as reference information that can be presented during the actual inspection of the packages in question. In response to this, when the processor 31 of the inspection device 11 issues a warning or a notice to open and inspect, if reference information such as past images of packages has been set as a screening result for the customs electronic data, it will display the past images of packages and the inspection results for those packages on the display device 13 along with the warning or notice to open and inspect (step ST39).

[0092] This allows inspectors conducting inspections of packages to not only receive warnings and alerts as screening results for electronic customs data, but also to refer to images of previously inspected packages and their inspection results. Furthermore, the processor 31 of the inspection device 11 displays information about the package, such as the captured image of the package, customs electronic data, and screening results, on the display device 13, and also issues a warning and prompts the inspector to open and inspect the package. It then accepts input of the judgment (inspection) result for the package from the inspector (step ST40).

[0093] Furthermore, if no warnings or recommendations for opening and inspecting are set in the customs electronic data (step ST37, NO), the processor 31 of the inspection device 11 proceeds to step ST40 without issuing any warnings or alerts based on the screening results, and waits for the inspector to input the judgment result.

[0094] In other words, the inspector, after receiving information about the package on the display device 13 and being notified of screening-based warnings and reminders about opening and inspecting the package, determines whether or not an opening and inspection is necessary for the package. If the inspector determines that an opening and inspection is necessary for the package, they input the determination that an opening and inspection result is necessary into the operating device 14. If the inspector determines that an opening and inspection is not necessary, they input the determination that an opening and inspection result is not necessary into the operating device 14.

[0095] When the processor 31 of the inspection device 11 receives a judgment result input by the inspector using the operating device 14, it adds identification information of the package and identification information of the inspector who performed the inspection to the acquired judgment result and outputs it to the data server 16 and the learning server 17 (step ST41). Alternatively, the judgment result by the inspector in the inspection device 11 may also be provided to an information input device 15 installed in the inspection area where the open inspection is performed.

[0096] Furthermore, packages that the inspection device 11 determines require an inspection are transported to an inspection area where an inspection is to be conducted. At the inspection area, inspectors open the packages and inspect their contents. The inspection results of the package inspection are entered by the inspectors into the information input device 15. For example, if there are items to be seized in the package, the inspector enters an inspection result indicating that the package is subject to seizure into the information input device 15. If there are no items to be seized in the package, the inspector enters an inspection result indicating that the package was not subject to seizure into the information input device 15.

[0097] When the information input device 15 receives the inspection results entered by the inspector, it outputs information indicating the inspection results, along with the identification information of the package and the identification information of the inspector who performed the inspection, to the data server 16 and the learning server 17 as the inspection result.

[0098] Through the above process, the inspection of the actual cargo subject to inspection in the inspection processing system is completed. According to the process described above, the inspection device displays not only the captured image and customs electronic data of the cargo, but also the results of the screening of the customs electronic data conducted in advance, as information about the cargo on the display device. Furthermore, for cargo that has been set as a warning target or recommended for opening and inspection based on the screening of the customs electronic data, the inspection device will issue a warning or a notice to open and inspect according to the warning level.

[0099] This allows the inspection system to provide inspectors who actually inspect packages with warnings obtained from screening pre-collected electronic customs data, as well as reminders about the results of package opening. As a result, the burden on inspectors can be reduced, and inspection accuracy can be improved without increasing the burden on inspectors.

[0100] Next, we will describe the process by which the learning server 17 in the inspection system 1 according to this embodiment generates criteria for screening the inspection results of packages using machine learning. Figure 9 is a flowchart illustrating an example of the operation of the learning server 17 in the inspection system 1 according to this embodiment, which performs machine learning on the inspection results of packages. The processor 51 of the learning server 17 collects the inspection results for the packages that have been inspected in the inspection processing system 2 (step ST51).

[0101] For example, the processor 51 of the learning server 17 obtains the result of the determination of whether or not an opening inspection of the package is necessary from the inspection device 11, which communicates via the communication unit 55, as the package inspection result. The processor 51 of the learning server 17 also obtains the result of the actual opening inspection of the package from the information input device 15, which communicates via the communication unit 55, as the package inspection result. The processor 51 of the learning server 17 stores the information indicating the package inspection results obtained from the inspection device 11 and the information input device 15 in the storage unit 54.

[0102] The processor 51 of the learning server 17 generates data that will serve as the criteria for screening (data for updating the criteria data) by performing machine learning using the inspection results stored in the memory unit 54 (step ST52). The processor 51 of the learning server 17 extracts the collected inspection results according to predetermined conditions and generates data that will serve as the criteria for screening (data for updating the criteria data) by performing machine learning on the customs electronic data group corresponding to the extracted inspection results.

[0103] In the example shown in Figure 9, three learning methods are illustrated as machine learning based on the test results performed by the processor 51 of the learning server 17 (steps ST52a, 52b, 52c). The learning server 17 may perform all of the first, second, and third learning methods as machine learning on the test results, or it may selectively perform any one of the first, second, and third learning methods.

[0104] As a first learning method, the processor 51 of the learning server 17 generates warning criteria data by machine learning the electronic customs data of the packages that were found to be subject to seizure based on the inspection results (step ST52a). For example, the processor 51 extracts inspection results that were found to be subject to seizure from the collected inspection results, collects the electronic customs data of the packages that were found to be subject to seizure, and generates warning criteria data by machine learning the electronic customs data of the packages that were found to be subject to seizure.

[0105] Alternatively, the processor 51 of the learning server 17 may classify the customs electronic data of the seized goods into categories and generate warning criteria data for each category by using machine learning on the classified customs electronic data of the seized goods. In this case, the learning server 17 supplies the warning criteria data for each category to the data server 16. This allows the data server 16 to update its criteria data with the warning criteria data for each category, and enables it to perform screening of customs electronic data for each category.

[0106] Furthermore, each of the categories mentioned above may be configured to correspond to a warning level. In other words, the learning server 17 may perform machine learning using the warning criteria for each category as the warning criteria for each warning level. In this case, the learning server 17 supplies the data that will serve as the warning criteria for each category generated by machine learning to the data server 16. This allows the data server 16 to update its reference data with the data that will serve as the warning criteria for each warning level corresponding to the category, and enables it to perform screening of electronic customs data based on the warning criteria for each warning level corresponding to each category.

[0107] As a second learning method, the processor 51 of the learning server 17 generates warning criteria data by machine learning the difference between the customs electronic data of packages that were subject to seizure and the customs electronic data of packages that were not subject to seizure (step ST52b). For example, the processor 51 extracts the difference between the customs electronic data of packages subject to seizure and the customs electronic data of packages that were not subject to seizure for each item, and generates warning criteria data by machine learning the extracted difference.

[0108] Similar to the second learning method, by performing machine learning using the difference between customs electronic data subject to detection and customs electronic data not subject to detection, the trends of data that should be subject to warnings become clear, and warning criteria data can be generated that improve the accuracy of selecting customs electronic data that should be subject to warnings. Furthermore, in the second learning method, the processor 51 of the learning server 17 may generate data that serves as warning criteria for each category by performing machine learning using the difference between customs electronic data subject to detection and customs electronic data that is not subject to detection, which have been classified by category.

[0109] As a third learning method, the processor 51 of the learning server 17 generates data that will serve as the criteria for opening and closing inspections by machine learning the judgment results of opening and closing inspections performed by specific inspectors (judgment results of opening and closing inspections extracted under specific conditions) (step ST52c). In this third learning method, for example, specific inspectors such as veterans or inspectors who are evaluated to have high judgment accuracy in opening and closing inspections are designated, and the criteria for opening and closing inspections are generated by learning the judgment results of opening and closing inspections performed by these specific inspectors. With this third learning method, it is expected that criteria for opening and closing inspections can be set that recommend opening and closing inspections to have a judgment accuracy close to that of specific inspectors such as veterans.

[0110] As a concrete example of the third learning method, the processor 51 of the learning server 17 extracts the judgment results of a specific inspector regarding the opening and inspection from the collected inspection results, and collects customs electronic data corresponding to the extracted judgment results of the opening and inspection. The processor 51 generates data that serves as the criteria for the opening and inspection by machine learning the customs electronic data of packages that have been determined by a specific inspector to require an opening and inspection.

[0111] Furthermore, the processor 51 of the learning server 17 may generate data that serves as the criteria for determining whether an inspection is necessary by machine learning the difference between the electronic customs data of packages that have been determined by a specific inspector to require inspection and the electronic customs data of packages that have been determined not to require inspection.

[0112] When the processor 51 of the learning server 17 generates judgment criterion data through machine learning on the inspection results, it updates the reference data stored in the storage area 44a of the storage unit 44 of the data server 16 with the generated data (step ST53). For example, the processor 51 of the learning server 17 communicates with the data server 16 via the communication unit 55 and requests the data server 16 to update the reference data with the judgment criterion data generated by machine learning on the inspection results. As a result, the data server 16 can update the reference data in the storage area 44a with the judgment criterion data generated by the learning server 17 through machine learning.

[0113] Based on the machine learning applied to the inspection results described above, the learning server, acting as a learning device, can generate criteria for screening customs electronic data using the actual inspection results of the packages. As a result, the entire inspection system can update the criteria data that indicates the criteria used for screening customs electronic data of packages before inspection while simultaneously performing inspections of packages using the inspection processing system.

[0114] As described above, the inspection system according to the embodiment performs a screening before inspection on declaration data (customs electronic data) that shows the declared contents of the cargo to be inspected, to determine whether the cargo contains items that are likely to be seized or whether an open inspection is recommended. When an inspection of the cargo is carried out, the system notifies the user of the screening results and any warnings or cautions based on the screening results.

[0115] As a result, the inspection system according to this embodiment can provide inspectors with information to assist in determining whether an open inspection (detailed inspection) of a package is necessary, not only based on photographed images of the package but also on the declared contents of the package. As a result, the efficiency and accuracy of inspection work by inspectors who conduct package inspections using the inspection system can be improved, and individual differences in inspection accuracy among multiple inspectors can be reduced.

[0116] Furthermore, the inspection system according to the embodiment generates data that serves as a judgment criterion for screening the declared data by performing machine learning using past declared data of packages selected based on inspection results for past packages, and updates the criterion data that indicates the judgment criteria used for screening.

[0117] As a result, according to the inspection system of this embodiment, the standard data used for screening can be updated using past inspection results without the need for administrators to input update data, thereby improving the accuracy of screening. Furthermore, past inspection results include the judgment results of a specific inspector regarding the necessity of an open inspection. By performing machine learning based on the judgment results of a specific inspector regarding the necessity of an open inspection, it becomes possible to set screening criteria that align with the judgment of a specific inspector. In this case, it is possible to provide supplementary information that enables any inspector to make a judgment similar to that of a specific inspector, and it is expected that discrepancies in inspection results due to individual differences among inspectors can be reduced.

[0118] The configuration of the inspection system according to the above embodiment is merely an example of an inspection system, and several devices may be implemented as a single device, or one device may be implemented as multiple devices. For example, the data server and the learning server may be implemented as a single information processing device, or the inspection device may perform the processing that the data server or the learning server would normally perform. Furthermore, the information input device for inputting the results of the inspection may be an operating device connected to the inspection device.

[0119] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of Symbols]

[0120] 1...Inspection system, 2...Inspection processing system, 3...Information processing system, 11...Inspection device, M...Luggage (object to be inspected), C...Conveyor, 12...Photography device, 13...Display device, 14...Operation device, 15...Inspection result input device (information input device), 16...Data server (information processing device), 17...Learning server (learning device), 31...Processor (second processor), 32...ROM, 33...RAM, 34...Storage unit, 35...Communication unit (second 2...Communication unit), 36...Display interface, 37...Operation interface, 39...Image interface, 41...Processor (first processor), 42...ROM, 43...RAM, 44...Storage unit, 44a...Storage area (memory), 45...Communication unit (first communication unit), 46...External communication unit (acquisition unit), 51...Processor (third processor), 52...ROM, 53...RAM, 54...Storage unit, 55...Communication unit (third communication unit).

Claims

1. In an inspection system having an information processing device and an inspection device, The aforementioned information processing device is A first communication unit that communicates with the inspection device, An acquisition unit that acquires declaration data showing the declared contents of the luggage to be inspected, A memory that stores standard data indicating criteria for screening the declaration data acquired by the acquisition unit, The system includes a first processor that performs a screening on the declaration data acquired by the acquisition unit based on the judgment criteria indicated by the aforementioned reference data, and transmits the declaration data and the screening results to the inspection device. The inspection device, A second communication unit that communicates with the aforementioned information processing device, A second processor that displays the declaration data of the cargo to be inspected, obtained from the aforementioned information processing device, and the results of the screening of said declaration data on a display device, is provided. Inspection system.

2. The memory of the information processing device stores reference data, which includes warning criteria for determining whether or not the declared data should be subject to a warning, as the judgment criteria. The first processor of the information processing device performs a screening process that includes determining whether or not the declared data acquired by the acquisition unit is subject to a warning based on the warning criteria. The second processor of the inspection apparatus issues a warning if, as a result of the screening, the declared data of the package to be inspected is determined to be subject to a warning. The inspection system according to claim 1.

3. The memory of the information processing device stores reference data, which includes warning criteria for each of multiple warning levels, as the warning criteria. The first processor of the information processing device performs a screening process that includes determining the warning level of the declared data acquired by the acquisition unit based on the warning criteria for each warning level. The second processor of the inspection device provides a warning corresponding to the warning level of the declaration data of the package to be inspected, as indicated by the screening results. The inspection system according to claim 2.

4. The memory of the information processing device stores reference data, including warning criteria, generated by machine learning using a set of declared data of inspected packages extracted based on past package inspection results. The inspection system according to claim 2.

5. The memory of the information processing device stores standard data, which includes criteria for determining whether or not to recommend opening and inspecting the declared data, as the criteria for determination. The first processor of the information processing device performs a screening process that includes determining whether or not to recommend an open inspection of the declared data acquired by the acquisition unit based on the criteria for the open inspection. The second processor of the inspection device provides a warning recommending an inspection if, as a result of the screening, the declared data of the package to be inspected is determined to be subject to a recommendation for inspection. The inspection system according to claim 1.

6. The memory of the information processing device stores reference data, including criteria for determining whether an inspection is necessary, which are generated by machine learning using a set of declared data of inspected packages extracted based on the determination result of a specific inspector regarding the necessity of opening and inspecting the packages. The inspection system according to claim 5.

7. Furthermore, an inspection system including a learning device, The learning device is A third communication unit that communicates with the aforementioned information processing device, The system includes a third processor that performs machine learning to generate data that serves as a judgment criterion for use in the screening process from the inspection results of the luggage, and supplies the judgment criterion data generated by the machine learning process to the information processing device. The first processor of the information processing device updates the reference data stored in the memory based on the data that serves as the determination criterion, which is obtained from the learning device. The inspection system according to claim 1.

8. The criteria shown in the aforementioned standard data include warning criteria for determining whether or not the declared data should be subject to a warning. The third processor of the learning device performs machine learning to generate warning criteria data from the declared data of the packages whose inspection results were seized. The inspection system according to claim 7.

9. The criteria shown in the aforementioned standard data include warning criteria for determining whether or not the declared data should be subject to a warning. The third processor of the learning device performs machine learning to generate warning criteria data from the difference between the declared data of packages that were subject to seizure and the declared data of packages that were not subject to seizure. The inspection system according to claim 7.

10. The criteria shown in the aforementioned standard data include criteria for determining whether or not to recommend an open inspection of the declared data. The third processor of the learning device performs machine learning to generate data that serves as the criteria for determining whether or not to open and inspect luggage, based on the results of a determination by a specific inspector regarding the necessity of opening and inspecting luggage. The inspection system according to claim 7.

11. A method for presenting information in an inspection system having an information processing device and an inspection device, The aforementioned information processing device acquires declaration data indicating the declared contents of the package to be inspected. The information processing device performs a screening on the declared data based on the criteria indicated by the reference data. The inspection device displays the declaration data of the cargo to be inspected, obtained from the information processing device, and the results of the screening of said declaration data on a display device. Information presentation method.

12. A learning device further included in the inspection system performs machine learning to generate data that serves as a judgment criterion for use in the screening based on the inspection results of the packages. The information processing device updates the standard data based on the judgment criterion data generated by the machine learning obtained from the learning device. The information presentation method according to claim 11.

Images