Data processing device, data processing method and data processing program

Abstract

To provide a data processing device, a data processing method and a data processing program in which forgery or alteration of a personal identification document and the like can be discovered.SOLUTION: A data processing device comprises: an input unit that inputs user data; and a processing unit that performs a specific processing using a data generation model which generates a predetermined inference result according to the user data. The input unit inputs an image that includes a personal identification document which becomes an illegal estimation target and a background which is existent at a backside of the personal identification document as the user data. The processing unit extracts a first background image corresponding to the background out of the image, and performs processing to determine whether or not there is possibility of the forgery of the personal identification document as the specific processing on the basis of the extracted first background image and a known second background image corresponding to the background.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing program. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] When applying for a mobile phone or other device, examiners review identification documents. Many applications are malicious and fraudulent, and many forged or altered identification documents are discovered during the screening process, especially in online applications. The accuracy of forgery and alteration is improving every year, and the image quality and size of photos taken by prospective customers vary. Even experienced examiners are increasingly unable to identify forgeries, posing a major problem. While it would be desirable to use artificial intelligence (AI) to determine the authenticity of identification documents, the above-mentioned issues make it difficult to distinguish between genuine and counterfeit identification documents in images, making automatic matching difficult. As such, there is room for improvement in conventional methods for detecting forged or altered identification documents. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein is a data processing device comprising an input unit for inputting user data, and a processing unit for performing a specific processing using a data generation model that generates a predetermined inference result according to the user data, wherein the input unit inputs, as the user data, an image including an identification document that is suspected to be fraudulent and a background behind the identification document, and the processing unit extracts a first background image corresponding to the background from the image, and performs, as the specific processing, a process for determining whether or not the identification document is likely to be counterfeit based on the extracted first background image and a known second background image corresponding to the background.

[0006] A second aspect of the technology disclosed herein is a data processing method in which a computer inputs user data and executes a specific process using a data generation model that generates a predetermined inference result according to the user data, wherein the computer inputs an image including an identification document that is suspected to be fraudulent and a background behind the identification document as the user data, extracts a first background image corresponding to the background from the image, and determines whether or not the identification document is likely to be counterfeit based on the extracted first background image and a known second background image corresponding to the background.

[0007] A third aspect of the technology of the present disclosure is a data processing program that causes a computer to execute a specific process using a data generation model that inputs user data and generates a predetermined inference result according to the user data, wherein the specific process inputs an image including an identification document that is suspected to be fraudulent and a background behind the identification document, extracts a first background image corresponding to the background from the image, and determines whether or not the identification document is likely to be counterfeit based on the extracted first background image and a known second background image corresponding to the background. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram showing an example of the configuration of a data processing system. [Figure 2] FIG. 2 is a conceptual diagram showing an example of the main functions of a data processing device and a smart device. [Figure 3A] FIG. 3A is a diagram for explaining an outline of the specific processing by specific processing unit 290. In FIG. [Figure 3B] FIG. 3B is a diagram for explaining an outline of the specific processing by the specific processing unit 290. In FIG. [Figure 4] FIG. 4 is a diagram showing an outline of the functional configuration of the specific processing unit 290. As shown in FIG. [Figure 5A] FIG. 5A is a flowchart showing an example of the operation flow of the specific processing by the data processing device 12. [Figure 5B] FIG. 5B is a flowchart showing an example of the operation flow of the specific processing by the data processing device 12. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, exemplary embodiments of a data processing device, a data processing method, and a data processing program according to the techniques of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. An example of the smart device 14 is a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure, and the smart device 14 is a terminal carried by a user.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the person 20 by outputting the data in a form of expression that the person 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in FIG. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "data processing program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58. The data generation model 58 is used by a specific processing unit 290. The processing of the specific processing unit 290 will be described in detail later.

[0026] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 62. The reception output program 62 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 62 from the storage 50 and executes the read reception output program 62 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0027] Next, the identification process of the identification processing unit 290 when the data processing device 12 performs the identification process to determine whether or not there is a possibility that the personal identification document is forged will be described.

[0028] 3A and 3B are diagrams for explaining an overview of the identification process performed by the identification processing unit 290. An overview of the identification process according to this embodiment is shown in FIGS. 3A and 3B. As shown in FIGS. 3A and 3B, the identification process according to this embodiment may be broadly divided into two stages. Specifically, the identification process may involve creating a background image list based on the background of the identification document entered at the time of application as a first stage, as shown in FIG. 3A, and using the background image list as a second stage, as shown in FIG. 3B, to identify identification documents that may be counterfeit.

[0029] The specific content of the identification process will be described with reference to Fig. 4. Fig. 4 is a diagram schematically showing the functional configuration of the identification process unit 290. The identification process unit 290 may include an input unit 291, a process unit 292, and an output unit 293.

[0030] (input section 291) The input unit 291 may input user data received by the smart device 14. Specifically, the input unit 291 may input at least one of text, voice, and image data of the user received by the smart device 14. For example, the input unit 291 may input image data including an identification document suspected to be fraudulent and the background behind the identification document as user data.

[0031] Fraud may include falsifying identification documents or attempting to use falsified identification documents.

[0032] An identification document may be interpreted as a document with a photograph that proves the identity of a user who is making a specific contract or application for a mobile phone or the like, and specifically includes a driver's license, disability certificate, My Number card, passport, etc. The background may be interpreted as an object that exists behind the identification document when the identification document is photographed, and specifically includes a handkerchief, towel, table, tablecloth, wall, floor, etc.

[0033] The background image of a fraudulent identification document (fraudulent document) is often the same as or similar to an image of an object or the like in the background of a previously forged identification document. In the present disclosure, the processing unit 292 may extract a distinctive pattern or the like contained in the background image of the identification document from an image containing the identification document that has been photographed using the smart device 14 or the like and uploaded.

[0034] Furthermore, in the present disclosure, the processing unit 292 may generate a modified version of the extracted characteristic pattern, for example, by rotating the original image by a predetermined angle and enlarging or reducing the entire or partial image. The processing unit 292 may record the generated image in a specific storage unit as a background image list (e.g., a blacklist) for predicting fraudulent identification documents, as shown in FIG. 3A . The processing unit 292 may then use the background image list as useful information for predicting fraud (e.g., forgery or falsification) of newly applied identification documents. For example, when a new application for mobile phone service is made, the processing unit 292 may extract a background image of the identification document from images including the identification document used in the application and compare the extracted background image with images included in the fraudulent background image list to predict whether the identification document is fraudulent. A specific example of the identification process performed by the processing unit 292 is described below.

[0035] (Processing unit 292) The processing unit 292 performs a specific process using the data generation model 58. Specifically, character, voice, and image data input by the user is input to the data generation model 58, and a generation result is obtained.

[0036] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0037] (Extraction of first background image by processing unit 292) The processing unit 292 may extract a first background image (image of the background of the identification document) corresponding to the background of the identification document from the image (image including the uploaded identification document) input by the input unit 291. For example, the processing unit 292 identifies the type of identification document (e.g., My Number card, driver's license, etc.) by identifying information written on the identification document in the image including the identification document, and extracts a characteristic pattern of the background by subjecting the area excluding the area corresponding to the identified identification document (the background area shown in FIG. 3A) to character recognition processing such as OCR.

[0038] (Generation of second background image by processing unit 292) The processing unit 292 may generate a plurality of transformed images having different transformation modes by transforming the extracted first background image, and record the generated plurality of transformed images in a specific recording unit as second background images.

[0039] (Image generation example 1) For example, the processing unit 292 may enlarge a specific region of the extracted first background image, as in images c, d, and f in FIG. 3A, to generate a plurality of enlarged images with different enlargement ratios of the specific region as a plurality of transformed images. For example, the processing unit 292 may generate images in which the overall enlargement ratio of the first background image exceeds 1 (e.g., images with enlargement ratios of 2, 4, etc.), using the center of the extracted first background image as a reference position. The enlargement ratio refers to the degree of enlargement, and the larger the enlargement ratio, the larger the enlargement target. For example, an enlargement ratio of 2 means that the enlargement target is enlarged twice as large. An enlargement ratio of 4 is larger than an enlargement ratio of 2.

[0040] (Image generation example 2) Furthermore, the processing unit 292 may generate, as a plurality of transformed images, a plurality of reduced images with different reduction ratios of the specific region by reducing the extracted specific region of the first background image, as in images b and e in FIG. 3A. For example, the processing unit 292 may generate images in which the overall reduction ratio of the first background image is less than 1 (e.g., images with a reduction ratio of 1 / 2, 1 / 4, etc.) using the center of the extracted first background image as a reference position. The reduction ratio refers to the degree of reduction, and the larger the reduction ratio, the smaller the object to be reduced. For example, a reduction ratio of 1 / 2 means that the object to be reduced is reduced to 1 / 2. A reduction ratio of 1 / 4 is larger than a reduction ratio of 1 / 2 (numerically, the denominator is used for comparison).

[0041] (Image generation example 3) Furthermore, the processing unit 292 may generate a plurality of transformed images, each of which has a different rotation angle, by rotating the extracted first background image by a specific angle, as in images b, c, e, and f in Fig. 3A. For example, the processing unit 292 may generate a plurality of transformed images by rotating the first background image by a rotation angle of 45°, 90°, 180°, etc., with the center of the extracted first background image as a reference position.

[0042] (Image generation example 4) Furthermore, the processing unit 292 may enlarge a partial image included in the extracted specific region of the first background image more than the images surrounding the partial image included in the specific region, as in images g and h in FIG. 3A, thereby generating a plurality of images with different magnification ratios of the partial image as a plurality of deformed images. Specifically, for example, as in image g, the processing unit 292 may enlarge a partial image (heart image) included in the extracted specific region of the first background image more than the images surrounding the partial image included in the specific region (images of clovers, spades, and diamonds). Furthermore, as in image h, the processing unit 292 may enlarge a partial image (clover image) included in the extracted specific region of the first background image more than the images surrounding the partial image included in the specific region (e.g., images of spades, diamonds, and hearts). The magnification ratio of the partial image may be a value greater than 1 (e.g., magnification ratio 2, 4, etc.), with the images surrounding the partial image used as a reference position. In this way, a plurality of images with different magnification ratios of the heart image and the clover image can be generated as a plurality of deformed images.

[0043] (Image generation example 5) Furthermore, the processing unit 292 may generate, as a plurality of transformed images, a plurality of images with different reduction ratios of the partial image, by reducing a partial image included in a specific region of the extracted first background image compared to the images surrounding the partial image included in the specific region, as in images i and j in FIG. 3A . Specifically, the processing unit 292 may reduce, for example, a partial image (heart image) included in a specific region of the extracted first background image compared to the images surrounding the partial image included in the specific region (images of clovers, spades, and diamonds), as in image i. Furthermore, the processing unit 292 may reduce, as in image j, a partial image (clover image) included in a specific region of the extracted first background image compared to the images surrounding the partial image included in the specific region (e.g., images of spades, diamonds, and hearts). The reduction ratio of the partial image may be a value less than 1 (e.g., 1 / 2 or 1 / 4 magnification ratio), with the images surrounding the partial image set as the reference position. In this way, a plurality of images with different reduction ratios of the heart image and the clover image can be generated as a plurality of transformed images.

[0044] The processing unit 292 may record the images generated in this manner in a specific recording unit as a background image list (such as a blacklist) for estimating fraudulent identification documents, as shown in Fig. 3A. The processing unit 292 may use the images included in the background image list as useful information for estimating fraud (such as forgery or falsification) of newly applied identification documents.

[0045] (Counterfeit determination by processing unit 292) The processing unit 292 may perform, as the identification process, a process of determining whether or not the identification document is likely to be counterfeit, based on the extracted first background image and a known second background image corresponding to the background. The known second background image may be interpreted as an image recorded in a specific recording unit, specifically, an image included in the background image list shown in Figures 3A and 3B.

[0046] For example, the processing unit 292 may record the background image in the recording unit, and then compare the background image of the newly uploaded identification document with the images included in the background image list to calculate the matching rate. Specifically, the processing unit 292 may use feature quantities such as Haar-like, color histogram, and color moment to calculate a specific score indicating the degree of similarity of the image patterns of the background images, the similarity of the colors of the background images, etc., as the matching rate. A higher specific score indicates a higher matching rate (degree of matching). If the calculated matching rate is equal to or greater than a specific threshold, the processing unit 292 may determine that there is a possibility that the identification document is forged.

[0047] The processing unit 292 may also record the extracted first background image in a specific recording unit as a second background image, and calculate a similarity score representing the degree of similarity between the newly extracted first background image and the multiple second background images recorded in the recording unit after recording the extracted first background image in the recording unit. Furthermore, the processing unit 292 may perform, as the identification process, a process of determining that the identification document in the foreground of the newly extracted first background image may be counterfeit if the multiple second background images include an image with a similarity score equal to or greater than a specific threshold. Specifically, after recording the background image in the recording unit, the processing unit 292 may calculate a similarity score representing the similarity between the background image of the newly uploaded identification document and an image included in the background image list, and determine that the identification document in the foreground of the newly extracted first background image may be counterfeit if the multiple images included in the background image list include an image with a similarity score equal to or greater than a specific threshold. For example, the processing unit 292 may set a plurality of specific areas of the background image of the newly uploaded identification document, and calculate the similarity between each of the set specific areas and the specific areas of the background image of the image included in the background image list by weighting and adding the similarities using a weighting coefficient set for each area. If the calculated similarity is equal to or greater than a specific threshold, the processing unit 292 may determine that there is a possibility that the identification document is forged.

[0048] (Output unit 293) The output unit 293 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A may cause the output device 40 to output the result of the specific processing.

[0049] For example, when the processing unit 292 determines that there is a possibility that the identification document is forged, the output unit 293 may output information indicating that there is a possibility that the identification document is forged. Specifically, as shown in Fig. 3B, the output unit 293 may notify the review team performing the visual review of information indicating that the identification document is suspected to be forged, for example, an image of the identification document with a message saying "Possible forgery."

[0050] Next, a description will be given of the operation of the data processing system 10. An example of the flow of the specific processing will be described with reference to Figures 5A and 5B. Note that the flow of the specific processing shown in Figures 5A and 5B is an example of a "data processing method" according to the technology of the present disclosure.

[0051] 5A and 5B are flowcharts schematically illustrating an example of an operational flow of the identification process by the data processing device 12. Fig. 5A shows the operational flow for the first stage of the identification process shown in Fig. 3A. Fig. 5B shows the operational flow for the second stage of the identification process shown in Fig. 3B.

[0052] As shown in FIG. 5A, in step S11, the input unit 291 may input, as user data, image data including an identification document that is suspected to be fraudulent and the background behind the identification document.

[0053] In step S12, the processing unit 292 may extract, from the image input by the input unit 291, a first background image (an image of the background of the identification document) corresponding to the background of the identification document.

[0054] In step S13, the processing unit 292 may generate a plurality of transformed images with different transformation modes by transforming the extracted first background image.

[0055] In step S14, the processing unit 292 may record the generated image in a specific recording unit as a background image list for inferring fraudulent identification documents.

[0056] As shown in FIG. 5B, in step S21, the input unit 291 may input, as user data, image data including the newly applied-for personal identification document and the background behind the personal identification document.

[0057] In step S22, the processing unit 292 may extract, from the image input by the input unit 291, a first background image (an image of the background of the identification document) corresponding to the background of the identification document.

[0058] In step S23, the processing unit 292 may compare the extracted first background image with an image (second background image) included in a background image list read from a specific recording unit.

[0059] In step S24, the processing unit 292 may determine whether the matching rate, similarity score, etc. are equal to or greater than a specific threshold. For example, if the matching rate is less than a specific threshold (step S24 NO), in step S25, the processing unit 292 may determine that there is no possibility or a low possibility that the identification document in the foreground of the newly extracted first background image is a forgery. Thereafter, in step S26, the processing unit 292 may output the determination result as the result of the identification process.

[0060] Returning to step S24, for example, if the matching rate is equal to or greater than a specific threshold (step S24 YES), in step S27, the processing unit 292 may determine that there is a possibility or a high probability that the identification document in the foreground of the newly extracted first background image is a forgery. Thereafter, in step S28, the processing unit 292 may output the determination result as the result of the identification process. By transmitting the determination result to, for example, a terminal device used by the review team, the identification document that passed the visual review by the review team, the identification document that slipped through the visual review, etc. can be re-examined as being highly likely to be a forgery.

[0061] This will enable the system to check for identity verification documents that are likely to be forged from among a large number of applications, thereby significantly improving the efficiency of screening.

[0062] Furthermore, even if an identification document is determined to be unlikely to be a forgery, that is, an identification document that has slipped through visual inspection, the accuracy of the inspection can be improved by passing it through visual inspection again as it is deemed to be highly likely to be a forgery through the specific processing disclosed herein.

[0063] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0064] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0065] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0066] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0067] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0068] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0069] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[0070] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0071] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0072] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0073] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0074] In addition, the following supplementary notes are provided in relation to the above description.

[0075] (Appendix 1) an input unit for inputting user data; a processing unit that performs a specific process using a data generation model that generates a predetermined inference result according to the user data, the input unit inputs, as the user data, an image including an identification document that is a suspected target of fraud and a background behind the identification document; The processing unit extracts a first background image corresponding to the background from the image, and performs, as the identification process, a process of determining whether or not the identification document is likely to be counterfeit based on the extracted first background image and a known second background image corresponding to the background.

[0076] (Appendix 2) The data processing device of claim 1, wherein the processing unit calculates a matching rate by comparing the first background image with the second background image, and determines that there is a possibility that the identification document is counterfeit if the calculated matching rate is equal to or greater than a specific threshold.

[0077] (Appendix 3) 3. The data processing device according to claim 2, further comprising an output unit that outputs information indicating that the identification document may be counterfeit if the processing unit determines that the identification document may be counterfeit.

[0078] (Appendix 4) 2. The data processing device of claim 1, wherein the processing unit performs the identification process by transforming the extracted first background image to generate multiple transformed images with different transformation patterns, recording the multiple generated transformed images in a specific recording unit as the second background image, and comparing the newly extracted first background image after recording the multiple generated transformed images in the recording unit with the transformed images recorded in the recording unit to determine whether or not there is a possibility of counterfeiting.

[0079] (Appendix 5) The data processing device described in Appendix 4, wherein the processing unit enlarges a specific area of ​​the extracted first background image to generate multiple enlarged images having different enlargement rates for the specific area as multiple transformed images.

[0080] (Appendix 6) The data processing device described in Appendix 5, wherein the processing unit generates multiple images of the partial images having different magnification ratios as multiple deformed images by enlarging a partial image included in the specific area more than the images surrounding the partial image included in the specific area.

[0081] (Appendix 7) The data processing device described in Appendix 4, wherein the processing unit generates multiple reduced images of the specific area having different reduction rates for the specific area as multiple transformed images by reducing the extracted specific area of ​​the first background image.

[0082] (Appendix 8) The data processing device described in Appendix 7, wherein the processing unit generates multiple images of the partial images with different reduction rates as multiple transformed images by reducing a partial image included in the specific area more than the images surrounding the partial image included in the specific area.

[0083] (Appendix 9) 5. The data processing device according to claim 4, wherein the processing unit generates a plurality of rotated images having different rotation angles as the plurality of transformed images by rotating the extracted first background image by a specific angle.

[0084] (Appendix 10) 2. The data processing device according to claim 1, wherein the processing unit performs the identification process by recording the extracted first background image in a specific recording unit as the second background image, calculating a similarity score representing a degree of similarity between the newly extracted first background image after recording the extracted first background image in the recording unit and the plurality of second background images recorded in the recording unit, and determining, if the plurality of second background images includes an image with the similarity score equal to or greater than a specific threshold, that there is a possibility that the identification document in the foreground of the newly extracted first background image is a counterfeit.

[0085] (Appendix 11) A data processing method in which a computer executes a specific process using a data generation model that receives user data and generates a predetermined inference result according to the user data, comprising: inputting, as the user data, an image including an identification document that is suspected to be fraudulent and a background behind the identification document; extracting a first background image corresponding to the background from the image, and determining whether or not there is a possibility that the identification document is forged based on the extracted first background image and a known second background image corresponding to the background, as the identification process; A data processing method executed by the computer.

[0086] (Appendix 12) A data processing program that causes a computer to execute a specific process using a data generation model that receives user data and generates a predetermined inference result according to the user data, inputting, as the user data, an image including an identification document that is suspected to be fraudulent and a background behind the identification document; extracting a first background image corresponding to the background from the image, and determining whether or not there is a possibility that the identification document is forged based on the extracted first background image and a known second background image corresponding to the background, as the identification process; A data processing program to be executed by the computer. [Explanation of symbols]

[0087] 10 Data Processing System 12 Data Processing Device 14 Smart Devices 290 Special Processing Department 291 Input section 292 Processing section 293 Output Section< / url:>

Claims

1. an input unit for inputting user data; a processing unit that performs a specific process using a data generation model that generates a predetermined inference result according to the user data, the input unit inputs, as the user data, an image including an identification document that is a suspected target of fraud and a background behind the identification document; The processing unit extracts a first background image corresponding to the background from the image, and performs, as the identification process, a process of determining whether or not the identification document is likely to be counterfeit based on the extracted first background image and a known second background image corresponding to the background.

2. 2. The data processing device according to claim 1, wherein the processing unit calculates a matching rate by matching the first background image with the second background image, and determines that there is a possibility that the identification document is counterfeit if the calculated matching rate is equal to or greater than a specific threshold.

3. 3. The data processing device according to claim 2, further comprising an output unit that outputs information indicating that the personal identification document is likely to be forged when the processing unit determines that the personal identification document is likely to be forged.

4. 2. The data processing device according to claim 1, wherein the processing unit performs the identification process by transforming the extracted first background image to generate multiple transformed images with different transformation patterns, recording the multiple generated transformed images in a specific recording unit as the second background image, and comparing the newly extracted first background image after recording the multiple generated transformed images in the recording unit with the transformed images recorded in the recording unit to determine whether or not there is a possibility of counterfeiting.

5. The data processing device according to claim 4 , wherein the processing unit enlarges the extracted specific region of the first background image to generate, as the multiple transformed images, multiple enlarged images having different enlargement rates for the specific region.

6. 6. The data processing device according to claim 5, wherein the processing unit generates a plurality of images of the partial image having different magnification ratios as a plurality of transformed images by enlarging the partial image included in the specific region more than the images surrounding the partial image included in the specific region.

7. The data processing device according to claim 4 , wherein the processing unit reduces the extracted specific region of the first background image to generate, as the multiple transformed images, multiple reduced images having different reduction rates for the specific region.

8. 8. The data processing device according to claim 7, wherein the processing unit generates a plurality of images of the partial images having different reduction ratios as a plurality of transformed images by reducing the partial image included in the specific area more than the images surrounding the partial image included in the specific area.

9. The data processing device according to claim 4 , wherein the processing unit rotates the extracted first background image by a specific angle to generate a plurality of rotated images having different rotation angles as the plurality of transformed images.

10. 2. The data processing device according to claim 1, wherein the processing unit performs the identification process by recording the extracted first background image in a specific recording unit as the second background image, calculating a similarity score representing a degree of similarity between the newly extracted first background image after recording the extracted first background image in the recording unit and the plurality of second background images recorded in the recording unit, and determining, if the plurality of second background images includes an image with the similarity score equal to or greater than a specific threshold, that there is a possibility that the identification document in the foreground of the newly extracted first background image is a counterfeit.

11. A data processing method in which a computer executes a specific process using a data generation model that receives user data and generates a predetermined inference result according to the user data, comprising: inputting, as the user data, an image including an identification document that is suspected to be fraudulent and a background behind the identification document; extracting a first background image corresponding to the background from the image, and determining whether or not there is a possibility that the identification document is counterfeit based on the extracted first background image and a known second background image corresponding to the background, as the identification process; A data processing method executed by the computer.

12. A data processing program that causes a computer to execute a specific process using a data generation model that receives user data and generates a predetermined inference result according to the user data, inputting, as the user data, an image including an identification document that is suspected to be fraudulent and a background behind the identification document; extracting a first background image corresponding to the background from the image, and determining whether or not there is a possibility that the identification document is counterfeit based on the extracted first background image and a known second background image corresponding to the background, as the identification process; A data processing program to be executed by the computer.

Images