system

Abstract

The system according to this embodiment aims to quickly and accurately review identity verification documents and related documents. [Solution] The system according to the embodiment comprises an image analysis unit, an information extraction unit, an examination unit, a provision unit, and a learning unit. The image analysis unit analyzes images of identity verification documents and related documents. The information extraction unit extracts information from the images analyzed by the image analysis unit. The examination unit performs an examination based on the information extracted by the information extraction unit. The provision unit provides the examination results obtained by the examination unit in real time. The learning unit converts the examination elements into text data for learning.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the review of identification documents and related documents takes time and manpower, and there is a risk of overlooking or bias.

[0005] The system according to the embodiment aims to quickly and accurately review identification documents and related documents.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an image analysis unit, an information extraction unit, an examination unit, a provision unit, and a learning unit. The image analysis unit analyzes images of identity verification documents and related documents. The information extraction unit extracts information from the images analyzed by the image analysis unit. The examination unit performs an examination based on the information extracted by the information extraction unit. The provision unit provides the examination results obtained by the examination unit in real time. The learning unit converts the examination elements into text data for learning. [Effects of the Invention]

[0007] The system according to this embodiment can quickly and accurately review identity verification documents and related documents. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) 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 user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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 "program" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The examination system according to an embodiment of the present invention is a system that uses AI to analyze images of identity verification documents and related documents and automates the examination process to prevent fraud. While conventional human-based examinations require time and manpower and are prone to oversights and biases, this system utilizes the computing power of AI to provide highly accurate examination results in real time, reducing time and improving accuracy. For example, the examination system inputs images of identity verification documents and related documents into the AI. Next, the AI ​​analyzes these images and extracts necessary information. For example, it extracts information such as name, address, and date of birth as text data. In this process, the AI ​​performs the analysis based on pre-trained examination elements, resulting in highly accurate results. Next, the AI ​​performs the examination based on the extracted information. For example, it checks whether the information on the identity verification document matches the information on the related documents and whether any fraudulent information is included. These examination results are provided in real time and immediately reflected in front-end sales. This mechanism enables accurate and immediate examination without human bias, drastically reducing fraud across the industry. For example, it is expected to prevent fraudulent contracts in mobile phone carriers, their sales staff, and sales stores. Furthermore, given the current demand for advanced AI-powered screening tools due to the growth of the smartphone market and the increasing technological advancement of fraudulent activities, this invention is extremely useful. Moreover, the screening system can generate immediate and detailed screening results using an LLM (Large-Scale Language Model) by having the AI ​​learn from text data of the screening elements. This further improves the accuracy of the screening and significantly improves operational efficiency. Thus, this invention aims to prevent fraud throughout the industry by combining AI-based image analysis technology and automated screening technology to achieve time savings and improved accuracy. As a result, the screening system can achieve time savings and improved accuracy by analyzing images of identity verification documents and related documents and automating the screening process to prevent fraud.

[0029] The examination system according to this embodiment comprises an image analysis unit, an information extraction unit, an examination unit, a provision unit, and a learning unit. The image analysis unit analyzes images of identity verification documents and related documents. The image analysis unit recognizes text in the image using, for example, OCR (optical character recognition) technology. The image analysis unit can also analyze facial photographs in identity verification documents using facial recognition technology. For example, the image analysis unit analyzes an image of a passport and extracts facial photographs and text information. The image analysis unit can also analyze an image of a driver's license and extract information such as name and address. Furthermore, the image analysis unit can analyze an image of a resident registration certificate and extract information such as address and name. The information extraction unit extracts information from the images analyzed by the image analysis unit. The information extraction unit extracts information such as name, address, and date of birth as text data. The information extraction unit extracts text in the image using, for example, OCR technology. The information extraction unit can also extract personal information from facial photographs using facial recognition technology. For example, the information extraction unit extracts names and dates of birth from passport images. It can also extract addresses and names from driver's license images. Furthermore, it can extract addresses and names from resident registration images. The review unit conducts a review based on the information extracted by the information extraction unit. For example, the review unit checks whether the information in identity verification documents matches the information in related documents. For example, the review unit uses database matching technology to verify information consistency. The review unit can also check for the presence of fraudulent information. For example, the review unit uses pattern matching technology to detect fraudulent information. The review unit can also use AI to verify information consistency and detect fraud. For example, the review unit uses an AI model to verify information consistency and detect fraudulent information. The provision unit provides the review results obtained by the review unit in real time. For example, the provision unit uses API integration to immediately reflect the review results to front-end sales. For example, the provision unit provides review results in real time using a notification system. The provision unit can also provide review results through web applications and mobile applications.For example, the service provider displays the review results on a web application and immediately reflects them in front-end sales. The service provider can also display the review results on a mobile application and immediately reflect them in front-end sales. The learning unit converts the review elements into text data for training. The learning unit learns the review elements using, for example, a machine learning algorithm. The learning unit converts the review elements into text data using, for example, a data preprocessing method. The learning unit can also learn the review elements using AI. For example, the learning unit learns the review elements using an AI model to improve the accuracy of the review. As a result, the review system according to this embodiment can achieve time savings and improved accuracy by analyzing images of identity verification documents and related documents and automating the review process to prevent fraud.

[0030] The image analysis unit analyzes images of identity verification documents and related documents. For example, the image analysis unit uses OCR (Optical Character Recognition) technology to recognize text within images. OCR technology is a technology for converting characters in an image into digital text, and in order to achieve high-precision character recognition, it uses an AI model that has been trained on a large amount of character data in advance. This allows it to distinguish between handwritten and printed characters and accurately extract text data. The image analysis unit can also analyze facial photographs on identity verification documents using facial recognition technology. Facial recognition technology is a technology that detects faces in an image, extracts feature points to identify individuals, and allows for matching the facial photograph on the identity verification document with the actual face. For example, the image analysis unit analyzes images of passports and extracts facial photographs and text information. In passport image analysis, the position and size of the facial photograph are identified, and facial feature points are extracted using facial recognition technology. In addition, OCR technology is used to accurately extract information such as name, date of birth, and passport number for text information. Furthermore, the image analysis unit can also analyze images of driver's licenses and extract information such as name and address. In driver's license image analysis, text areas are identified based on the license layout, and information such as name, address, date of birth, and license number is extracted using OCR technology. Furthermore, the image analysis unit can also analyze images of resident registration certificates and extract information such as address and name. In resident registration certificate image analysis, text areas are identified based on the format of the resident registration certificate, and information such as address, name, and date of birth is extracted using OCR technology. As a result, the image analysis unit can analyze images of various identity verification documents and related documents and accurately extract the necessary information.

[0031] The information extraction unit extracts information from images analyzed by the image analysis unit. For example, the information extraction unit extracts information such as names, addresses, and dates of birth as text data. For example, the information extraction unit extracts text within images using OCR technology. OCR technology is a technique for converting characters in an image into digital text, and uses an AI model that has been trained on a large amount of character data in advance to achieve high-precision character recognition. This allows for the identification of differences between handwritten and printed characters and the accurate extraction of text data. The information extraction unit can also extract personal information from facial photographs using facial recognition technology. Facial recognition technology detects faces in an image, extracts feature points, and identifies individuals, allowing for the matching of facial photographs on identification documents with actual faces. For example, the information extraction unit extracts names and dates of birth from passport images. In passport image analysis, the position and size of the facial photograph are identified, and facial feature points are extracted using facial recognition technology. Furthermore, for text information, OCR technology is used to accurately extract information such as names, dates of birth, and passport numbers. Furthermore, the information extraction unit can also extract addresses and names from images of driver's licenses. In driver's license image analysis, text areas are identified based on the license layout, and information such as name, address, date of birth, and license number is extracted using OCR technology. In addition, the information extraction unit can also extract addresses and names from images of resident registration certificates. In resident registration certificate image analysis, text areas are identified based on the resident registration certificate format, and information such as address, name, and date of birth is extracted using OCR technology. As a result, the information extraction unit can analyze images of various identity verification documents and related documents and accurately extract the necessary information.

[0032] The review department conducts reviews based on the information extracted by the information extraction department. For example, the review department checks whether the information in identity verification documents matches the information in related documents. For example, the review department uses database matching technology to verify the information's consistency. Database matching technology is a technique that compares the extracted information with an existing database to check for a match, thereby confirming the accuracy of the information in identity verification documents. The review department can also check for the presence of fraudulent information. For example, the review department can use pattern matching technology to detect fraudulent information. Pattern matching technology is a technique that compares the extracted information with existing patterns to check for the presence of fraudulent information, thereby enabling early detection of fraudulent information. Furthermore, the review department can use AI to verify information consistency and detect fraud. For example, the review department can use an AI model to verify information consistency and detect fraudulent information. By training the AI ​​model with a large amount of data, it can achieve highly accurate consistency verification and fraud detection. This allows the review department to perform information consistency verification and fraud detection quickly and accurately. In addition, the review department can improve the accuracy of its reviews by utilizing past review results and statistical information. For example, by analyzing specific patterns and trends based on past audit results, the accuracy of audits can be improved. Furthermore, the audit department can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the audit department to not only understand the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the overall reliability and security of the system.

[0033] The service provider will provide the review results obtained by the review department in real time. The service provider can, for example, use API integration to immediately reflect the review results to front-end sales. API integration is a technology for exchanging data between different systems, which enables the rapid reflection of review results to front-end sales. The service provider can also provide review results in real time using a notification system. A notification system is a technology for quickly notifying users of review results, which enables the real-time provision of review results. The service provider can also provide review results through web applications and mobile applications. For example, the service provider can display review results on a web application and immediately reflect them to front-end sales. A web application is an application that can be accessed via the internet, which enables the rapid provision of review results. The service provider can also display review results on a mobile application and immediately reflect them to front-end sales. A mobile application is an application that can be used on mobile devices such as smartphones and tablets, which enables the rapid provision of review results. Furthermore, the service provider can also provide review results using communication methods such as email and SMS. This allows the service provider to deliver review results quickly and reliably, improving the efficiency of front-end sales.

[0034] The learning unit trains on the evaluation elements by converting them into text data. For example, the learning unit trains on the evaluation elements using a machine learning algorithm. A machine learning algorithm is a technology that identifies patterns and trends by training on large amounts of data, and performs predictions and classifications, thereby improving the accuracy of the evaluation. The learning unit trains on the evaluation elements by converting them into text data using a data preprocessing method. A data preprocessing method is a technology that converts data into a format that is easy to analyze, thereby enabling accurate conversion of evaluation elements into text data. The learning unit can also train on the evaluation elements using AI. For example, the learning unit trains on the evaluation elements using an AI model to improve the accuracy of the evaluation. An AI model can achieve highly accurate predictions and classifications by training on large amounts of data. This allows the learning unit to accurately learn on the evaluation elements and improve the accuracy of the evaluation. Furthermore, the learning unit can also improve the accuracy of the evaluation by utilizing past evaluation results and statistical information. For example, it can analyze specific patterns and trends based on past evaluation results to improve the accuracy of the evaluation. In addition, the learning unit can use anomaly detection algorithms to detect patterns that are different from the norm or abnormal data and issue warnings early. This allows the learning unit to not only grasp the situation in real time, but also to handle long-term risk management and anomaly detection, thereby improving the reliability and security of the entire system.

[0035] The image analysis unit can analyze images of identity verification documents and related documents. For example, the image analysis unit can recognize text within images using OCR (optical character recognition) technology. It can also analyze facial photographs in identity verification documents using facial recognition technology. For example, the image analysis unit can analyze a passport image and extract facial photographs and text information. It can also analyze a driver's license image and extract information such as name and address. Furthermore, it can analyze a resident registration image and extract information such as address and name. This prepares the image analysis unit to extract necessary information by analyzing document images. Some or all of the above processing in the image analysis unit may be performed using AI, or not. For example, the image analysis unit can recognize text within images using OCR technology and analyze facial photographs using an AI model.

[0036] The information extraction unit can extract information such as names, addresses, and dates of birth as text data from images analyzed by the image analysis unit. For example, the information extraction unit can extract text from images using OCR technology. The information extraction unit can also extract personal information from facial photographs using facial recognition technology. For example, the information extraction unit can extract names and dates of birth from passport images. It can also extract addresses and names from driver's license images. Furthermore, it can extract addresses and names from resident registration images. This allows the information extraction unit to extract the necessary information as text data, preparing the application for review. Some or all of the above-described processes in the information extraction unit may be performed using AI, for example, or without AI. For example, the information extraction unit can extract text from images using OCR technology and extract personal information from facial photographs using an AI model.

[0037] The review department can check, based on the information extracted by the information extraction department, whether the information in the identity verification documents matches the information in related documents and whether any fraudulent information is included. The review department can, for example, use database matching technology to verify the consistency of the information. The review department can also check for the presence of fraudulent information. For example, the review department can detect fraudulent information using pattern matching technology. The review department can also use AI to verify the consistency of information and detect fraud. For example, the review department can use an AI model to verify the consistency of information and detect fraudulent information. This enables the review department to perform highly accurate reviews by checking for both consistency and fraud. Some or all of the above processes in the review department may be performed using AI, or they may not. For example, the review department can verify the consistency of information using database matching technology and detect fraudulent information using an AI model.

[0038] The service provider can provide the review results obtained by the review provider in real time and immediately reflect them in front-end sales. For example, the service provider can immediately reflect the review results in front-end sales using API integration. For example, the service provider can provide the review results in real time using a notification system. The service provider can also provide the review results through web applications or mobile applications. For example, the service provider can display the review results in a web application and immediately reflect them in front-end sales. The service provider can also display the review results in a mobile application and immediately reflect them in front-end sales. This enables a rapid response by allowing the service provider to provide review results in real time. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can immediately reflect the review results in front-end sales using API integration and can provide the review results in real time using an AI model.

[0039] The image analysis unit can apply different analysis algorithms depending on the type of document during image analysis. For example, the image analysis unit can apply a facial recognition algorithm to passport image analysis. For example, the image analysis unit can apply a character recognition algorithm to driver's license image analysis. Furthermore, the image analysis unit can apply an address and name recognition algorithm to resident registration image analysis. By applying an analysis algorithm appropriate to the type of document, the accuracy of the analysis is improved. Some or all of the above-described processes in the image analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the image analysis unit can input a passport image into a generative AI and perform analysis by applying a facial recognition algorithm.

[0040] The image analysis unit can adjust its analysis method during image analysis, taking into account the degree of deterioration of the document. For example, the image analysis unit can apply a noise reduction algorithm to the image analysis of a deteriorated document. For example, the image analysis unit can apply a color correction algorithm to the image analysis of a faded document. Furthermore, the image analysis unit can apply an algorithm to fill in missing parts to the image analysis of a damaged document. This allows for accurate analysis even of deteriorated documents by taking into account the degree of deterioration of the document. Some or all of the above processing in the image analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image analysis unit can input an image of a deteriorated document into a generation AI and perform analysis by applying a noise reduction algorithm.

[0041] The image analysis unit can improve the accuracy of its analysis by considering the document's issuer information during image analysis. For example, the image analysis unit can analyze government-issued documents while considering specific security elements. For example, it can analyze corporate-issued documents while considering the company logo and specific format. Furthermore, it can analyze school-issued documents while considering specific student ID numbers and school emblems. This improves the accuracy of the analysis by considering the document's issuer information. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input government-issued documents into a generative AI and perform analysis while considering specific security elements.

[0042] The image analysis unit can apply different analysis methods depending on the language of the document during image analysis. For example, the image analysis unit can apply an English-specific character recognition algorithm to an English document. For example, the image analysis unit can apply a Japanese-specific character recognition algorithm to a Japanese document. Furthermore, the image analysis unit can apply character recognition algorithms corresponding to each language to multilingual documents. This enables multilingual analysis by applying analysis methods according to the language of the document. Some or all of the above-described processes in the image analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the image analysis unit can input an English document into a generative AI and perform analysis by applying an English-specific character recognition algorithm.

[0043] The information extraction unit can apply different extraction algorithms depending on the document format during information extraction. For example, when extracting information from a passport, the information extraction unit can apply an algorithm that extracts facial photographs and text information. For example, when extracting information from a driver's license, the information extraction unit can apply a character recognition algorithm. Furthermore, when extracting information from a resident registration certificate, the information extraction unit can apply an address and name recognition algorithm. This improves the accuracy of extraction by applying an extraction algorithm according to the document format. Some or all of the above processing in the information extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the information extraction unit can input passport information into a generation AI and perform extraction by applying an algorithm that extracts facial photographs and text information.

[0044] The information extraction unit can improve the accuracy of information extraction by evaluating the reliability of the document's contents during the extraction process. For example, the information extraction unit can evaluate the reliability of the document's issuer and prioritize the extraction of highly reliable information. For example, the information extraction unit can consider the document's issue date and time and prioritize the extraction of the most recent information. The information extraction unit can also check for inconsistencies in the document's contents and extract highly reliable information. In this way, highly reliable information can be extracted by evaluating the reliability of the document's contents. Some or all of the above-described processes in the information extraction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the information extraction unit can input the reliability of the document's issuer into the generating AI and prioritize the extraction of highly reliable information.

[0045] The information extraction unit can improve the accuracy of information extraction by considering the document's issuance date and time. For example, if the document's issuance date and time are recent, the information extraction unit will prioritize extracting the latest information. If the document's issuance date and time are old, the information extraction unit can extract information by referring to past information. The information extraction unit can also apply an appropriate extraction algorithm based on the document's issuance date and time. This allows for the priority extraction of the latest information by considering the document's issuance date and time. Some or all of the above processing in the information extraction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the information extraction unit can input the document's issuance date and time into a generating AI and prioritize extracting the latest information.

[0046] The information extraction unit can apply different extraction methods depending on the language of the document during information extraction. For example, the information extraction unit can apply an English-specific character recognition algorithm to an English document. For example, the information extraction unit can apply a Japanese-specific character recognition algorithm to a Japanese document. Furthermore, the information extraction unit can apply character recognition algorithms corresponding to each language to a multilingual document. This enables multilingual information extraction by applying an extraction method according to the language of the document. Some or all of the above processing in the information extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the information extraction unit can input an English document into a generation AI and extract information by applying an English-specific character recognition algorithm.

[0047] The review unit can optimize its review algorithm by referring to past review results during the review process. For example, the review unit can adjust the review algorithm based on past review results to improve accuracy. For example, the review unit can extract specific patterns from past review results and reflect them in the review algorithm. The review unit can also analyze past review results and identify areas for improvement in the review algorithm. This improves the accuracy of the review algorithm by referring to past review results. Some or all of the above processes in the review unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the review unit can input past review results into a generative AI to optimize the review algorithm.

[0048] The review department can improve the accuracy of its review process by evaluating the reliability of the document issuer during the review process. For example, the review department can apply highly reliable review criteria to documents issued by the government. For example, the review department can evaluate the reliability of a company and adjust its review criteria for documents issued by a company. Furthermore, the review department can evaluate the reliability of a school and adjust its review criteria for documents issued by a school. This improves the accuracy of the review process by evaluating the reliability of the document issuer. Some or all of the above processes in the review department may be performed using, for example, a generative AI, or not using a generative AI. For example, the review department can input government-issued documents into a generative AI and apply highly reliable review criteria.

[0049] The review department can improve the accuracy of its review process by considering the region where the documents were issued. For example, if the documents are issued in different regions, the review department will consider region-specific information during the review. For example, the review department can apply appropriate review criteria based on the region where the documents were issued. The review department can also evaluate the reliability of the region where the documents were issued and adjust the review criteria accordingly. This makes it possible to conduct a review that reflects region-specific information by considering the region where the documents were issued. Some or all of the above processes in the review department may be performed using, for example, a generative AI, or not using a generative AI. For example, the review department can input the region where the documents were issued into a generative AI and conduct a review that considers region-specific information.

[0050] The review department can improve the accuracy of its review by referring to the relevant laws and regulations of the documents during the review process. For example, the review department can refer to the relevant laws and regulations of the documents and apply appropriate review criteria. For example, the review department can adjust its review algorithm based on the relevant laws and regulations of the documents. The review department can also improve the accuracy of its review by taking into account the relevant laws and regulations of the documents. This makes it possible to conduct a legally accurate review by referring to the relevant laws and regulations of the documents. Some or all of the above processes in the review department may be performed using, for example, a generative AI, or not using a generative AI. For example, the review department can input the relevant laws and regulations of the documents into a generative AI and apply appropriate review criteria.

[0051] The information provider can determine the display priority based on the importance of the review results at the time of provision. For example, the provider can prioritize the display of important review results and quickly notify the user. For example, the provider can postpone the display of less important review results. The provider can also adjust the display order based on the importance of the review results. This allows for the rapid provision of important information by determining the display priority based on the importance of the review results. Some or all of the above processing in the information provider may be performed using, for example, a generating AI, or without using a generating AI. For example, the provider can input the importance of the review results into a generating AI and prioritize the display of important review results.

[0052] The service provider can apply different display methods depending on the category of the review results at the time of provision. For example, the service provider can apply a specific display method to the review results of identity verification documents. For example, the service provider can apply a different display method to the review results of related documents. The service provider can also provide the most suitable display method for each category. This improves the visibility of the information by applying a display method appropriate to the category of the review results. Some or all of the above processing in the service provider may be performed using, for example, a generation AI, or without a generation AI. For example, the service provider can input the review results of identity verification documents into a generation AI and apply a specific display method.

[0053] The service provider can determine the display priority based on the submission date of the review results at the time of provision. For example, the service provider can prioritize the display of the latest review results to quickly notify the user. For example, the service provider can postpone the display of older review results. The service provider can also adjust the display order based on the submission date. This allows for the rapid provision of the latest information by prioritizing the display based on the submission date of the review results. Some or all of the above processing in the service provider may be performed using, for example, a generating AI, or not using a generating AI. For example, the service provider can input the submission dates of the review results into a generating AI and prioritize the display of the latest review results.

[0054] The information provider can adjust the display order based on the relevance of the review results at the time of provision. For example, the information provider can prioritize displaying highly relevant review results and quickly notify the user. For example, the information provider can postpone displaying less relevant review results. The information provider can also adjust the display order based on the relevance of the review results. This allows for the priority provision of highly relevant information by adjusting the display order based on the relevance of the review results. Some or all of the above processing in the information provider may be performed using, for example, a generating AI, or without using a generating AI. For example, the information provider can input the relevance of the review results into a generating AI and prioritize displaying highly relevant review results.

[0055] The learning unit can optimize its learning algorithm by referring to past learning data during the learning process. For example, the learning unit can adjust the learning algorithm based on past learning data to improve accuracy. For example, the learning unit can extract specific patterns from past learning data and reflect them in the learning algorithm. The learning unit can also analyze past learning data and identify areas for improvement in the learning algorithm. As a result, the accuracy of the learning algorithm is improved by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past learning data into a generative AI to optimize the learning algorithm.

[0056] The learning unit can evaluate the accuracy of the review results and weight the training data during training. For example, the learning unit can prioritize training on data with high accuracy in the review results. For example, the learning unit can train on data with low accuracy in the review results with lower weighting. The learning unit can also adjust the weighting of the training data based on the accuracy of the review results. This allows the learning unit to prioritize training on high-accuracy data by evaluating the accuracy of the review results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the accuracy of the review results into a generative AI and prioritize training on high-accuracy data.

[0057] The learning unit can weight the training data based on the submission date of the review results during training. For example, the learning unit can prioritize learning the most recent review results. For example, the learning unit can lower the weight of older review results during training. The learning unit can also adjust the weighting of the training data based on the submission date. This allows for prioritizing the learning of the latest information by weighting the training data based on the submission date of the review results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input the submission date of the review results into a generative AI and prioritize learning the most recent review results.

[0058] The learning unit can evaluate the relevance of the review results and select training data during the learning process. For example, the learning unit can prioritize learning review results that are highly relevant. For example, the learning unit can postpone learning review results that are less relevant. The learning unit can also select training data based on the relevance of the review results. This allows it to prioritize learning highly relevant data by evaluating the relevance of the review results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the relevance of the review results into a generative AI and prioritize learning highly relevant data.

[0059] The learning unit can evaluate the accuracy of the review results and weight the training data during training. For example, the learning unit can prioritize training on data with high accuracy in the review results. For example, the learning unit can train on data with low accuracy in the review results with lower weighting. The learning unit can also adjust the weighting of the training data based on the accuracy of the review results. This allows the learning unit to prioritize training on high-accuracy data by evaluating the accuracy of the review results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the accuracy of the review results into a generative AI and prioritize training on high-accuracy data.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The review system can further improve the accuracy of its reviews by referring to the user's past review history. For example, stricter criteria can be applied to users who have been found to have committed fraud in the past. Conversely, normal criteria can be applied to users who have had no problems in the past. It can also extract specific patterns based on past review history and incorporate them into the review algorithm. In this way, the accuracy of the review is improved by utilizing past review history. Some or all of the above processes in the review system may be performed using, for example, generative AI, or not using generative AI. For example, the review system can input past review history into generative AI to optimize the review algorithm.

[0062] The review system can further evaluate the reliability of the document issuer and prioritize the review of highly reliable documents. For example, a high reliability review standard can be applied to documents issued by the government. For documents issued by companies, the review standard can be adjusted based on an evaluation of the company's reliability. Similarly, for documents issued by schools, the review standard can be adjusted based on an evaluation of the school's reliability. This improves the accuracy of the review by evaluating the reliability of the document issuer. Some or all of the above processes in the review system may be performed using, for example, generative AI, or not. For example, the review system can input the reliability of the document issuer into a generative AI and prioritize the review of highly reliable documents.

[0063] The review system can further improve the accuracy of its review by considering the region where the documents were issued. For example, if the documents are issued in different regions, the review can be conducted while considering region-specific information. Appropriate review criteria can be applied based on the region where the documents were issued. The reliability of the region where the documents were issued can also be evaluated, and the review criteria can be adjusted accordingly. This makes it possible to conduct a review that reflects region-specific information by considering the region where the documents were issued. Some or all of the above processes in the review system may be performed using, for example, a generative AI, or not using a generative AI. For example, the review system can input the region where the documents were issued into a generative AI and conduct a review while considering region-specific information.

[0064] The review system can further improve the accuracy of its review by referring to the relevant laws and regulations of the documents. For example, it can refer to the relevant laws and regulations of the documents and apply appropriate review criteria. Based on the relevant laws and regulations of the documents, the review algorithm can be adjusted. It can also improve the accuracy of its review by taking the relevant laws and regulations of the documents into consideration. This makes it possible to perform accurate, law-based reviews by referring to the relevant laws and regulations of the documents. Some or all of the above processes in the review system may be performed using, for example, a generative AI, or not using a generative AI. For example, the review system can input the relevant laws and regulations of the documents into a generative AI and apply appropriate review criteria.

[0065] The review system can further improve the accuracy of its review by considering the document's issuance date and time. For example, if the document's issuance date and time are recent, the most recent information will be prioritized in the review. If the document's issuance date and time are old, past information can be used as a reference during the review. The system can also apply an appropriate review algorithm based on the document's issuance date and time. This allows for prioritizing the review of the most recent information by considering the document's issuance date and time. Some or all of the above processes in the review system may be performed using, for example, a generative AI, or not using a generative AI. For example, the review system can input the document's issuance date and time into a generative AI and prioritize the review of the most recent information.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The image analysis unit analyzes images of identity verification documents and related documents. For example, it uses OCR (optical character recognition) technology to recognize text within images and facial recognition technology to analyze facial photographs on identity verification documents. Specifically, it analyzes passport images to extract facial photographs and text information. It also analyzes images of driver's licenses and resident registration certificates to extract information such as names and addresses. Step 2: The information extraction unit extracts information from the image analyzed by the image analysis unit. For example, it extracts information such as name, address, and date of birth as text data. Using OCR technology and facial recognition technology, it extracts necessary information from images of passports, driver's licenses, and resident registration certificates. Step 3: The review department conducts a review based on the information extracted by the information extraction department. For example, they check whether the information on the identity verification documents matches the information on related documents and confirm that no fraudulent information is included. Database matching technology, pattern matching technology, and AI models are used to verify information consistency and detect fraud. Step 4: The service provider provides the review results obtained by the review department in real time. For example, the review results are immediately reflected in front-end sales using API integration or notification systems and provided through web applications and mobile applications. Step 5: The learning unit converts the evaluation elements into text data for training. For example, it uses machine learning algorithms or AI models to learn the evaluation elements and improve the accuracy of the evaluation.

[0068] (Example of form 2) The examination system according to an embodiment of the present invention is a system that uses AI to analyze images of identity verification documents and related documents and automates the examination process to prevent fraud. While conventional human-based examinations require time and manpower and are prone to oversights and biases, this system utilizes the computing power of AI to provide highly accurate examination results in real time, reducing time and improving accuracy. For example, the examination system inputs images of identity verification documents and related documents into the AI. Next, the AI ​​analyzes these images and extracts necessary information. For example, it extracts information such as name, address, and date of birth as text data. In this process, the AI ​​performs the analysis based on pre-trained examination elements, resulting in highly accurate results. Next, the AI ​​performs the examination based on the extracted information. For example, it checks whether the information on the identity verification document matches the information on the related documents and whether any fraudulent information is included. These examination results are provided in real time and immediately reflected in front-end sales. This mechanism enables accurate and immediate examination without human bias, drastically reducing fraud across the industry. For example, it is expected to prevent fraudulent contracts in mobile phone carriers, their sales staff, and sales stores. Furthermore, given the current demand for advanced AI-powered screening tools due to the growth of the smartphone market and the increasing technological advancement of fraudulent activities, this invention is extremely useful. Moreover, the screening system can generate immediate and detailed screening results using an LLM (Large-Scale Language Model) by having the AI ​​learn from text data of the screening elements. This further improves the accuracy of the screening and significantly improves operational efficiency. Thus, this invention aims to prevent fraud throughout the industry by combining AI-based image analysis technology and automated screening technology to achieve time savings and improved accuracy. As a result, the screening system can achieve time savings and improved accuracy by analyzing images of identity verification documents and related documents and automating the screening process to prevent fraud.

[0069] The examination system according to this embodiment comprises an image analysis unit, an information extraction unit, an examination unit, a provision unit, and a learning unit. The image analysis unit analyzes images of identity verification documents and related documents. The image analysis unit recognizes text in the image using, for example, OCR (optical character recognition) technology. The image analysis unit can also analyze facial photographs in identity verification documents using facial recognition technology. For example, the image analysis unit analyzes an image of a passport and extracts facial photographs and text information. The image analysis unit can also analyze an image of a driver's license and extract information such as name and address. Furthermore, the image analysis unit can analyze an image of a resident registration certificate and extract information such as address and name. The information extraction unit extracts information from the images analyzed by the image analysis unit. The information extraction unit extracts information such as name, address, and date of birth as text data. The information extraction unit extracts text in the image using, for example, OCR technology. The information extraction unit can also extract personal information from facial photographs using facial recognition technology. For example, the information extraction unit extracts names and dates of birth from passport images. It can also extract addresses and names from driver's license images. Furthermore, it can extract addresses and names from resident registration images. The review unit conducts a review based on the information extracted by the information extraction unit. For example, the review unit checks whether the information in identity verification documents matches the information in related documents. For example, the review unit uses database matching technology to verify information consistency. The review unit can also check for the presence of fraudulent information. For example, the review unit uses pattern matching technology to detect fraudulent information. The review unit can also use AI to verify information consistency and detect fraud. For example, the review unit uses an AI model to verify information consistency and detect fraudulent information. The provision unit provides the review results obtained by the review unit in real time. For example, the provision unit uses API integration to immediately reflect the review results to front-end sales. For example, the provision unit provides review results in real time using a notification system. The provision unit can also provide review results through web applications and mobile applications.For example, the service provider displays the review results on a web application and immediately reflects them in front-end sales. The service provider can also display the review results on a mobile application and immediately reflect them in front-end sales. The learning unit converts the review elements into text data for training. The learning unit learns the review elements using, for example, a machine learning algorithm. The learning unit converts the review elements into text data using, for example, a data preprocessing method. The learning unit can also learn the review elements using AI. For example, the learning unit learns the review elements using an AI model to improve the accuracy of the review. As a result, the review system according to this embodiment can achieve time savings and improved accuracy by analyzing images of identity verification documents and related documents and automating the review process to prevent fraud.

[0070] The image analysis unit analyzes images of identity verification documents and related documents. For example, the image analysis unit uses OCR (Optical Character Recognition) technology to recognize text within images. OCR technology is a technology for converting characters in an image into digital text, and in order to achieve high-precision character recognition, it uses an AI model that has been trained on a large amount of character data in advance. This allows it to distinguish between handwritten and printed characters and accurately extract text data. The image analysis unit can also analyze facial photographs on identity verification documents using facial recognition technology. Facial recognition technology is a technology that detects faces in an image, extracts feature points to identify individuals, and allows for matching the facial photograph on the identity verification document with the actual face. For example, the image analysis unit analyzes images of passports and extracts facial photographs and text information. In passport image analysis, the position and size of the facial photograph are identified, and facial feature points are extracted using facial recognition technology. In addition, OCR technology is used to accurately extract information such as name, date of birth, and passport number for text information. Furthermore, the image analysis unit can also analyze images of driver's licenses and extract information such as name and address. In driver's license image analysis, text areas are identified based on the license layout, and information such as name, address, date of birth, and license number is extracted using OCR technology. Furthermore, the image analysis unit can also analyze images of resident registration certificates and extract information such as address and name. In resident registration certificate image analysis, text areas are identified based on the format of the resident registration certificate, and information such as address, name, and date of birth is extracted using OCR technology. As a result, the image analysis unit can analyze images of various identity verification documents and related documents and accurately extract the necessary information.

[0071] The information extraction unit extracts information from images analyzed by the image analysis unit. For example, the information extraction unit extracts information such as names, addresses, and dates of birth as text data. For example, the information extraction unit extracts text within images using OCR technology. OCR technology is a technique for converting characters in an image into digital text, and uses an AI model that has been trained on a large amount of character data in advance to achieve high-precision character recognition. This allows for the identification of differences between handwritten and printed characters and the accurate extraction of text data. The information extraction unit can also extract personal information from facial photographs using facial recognition technology. Facial recognition technology detects faces in an image, extracts feature points, and identifies individuals, allowing for the matching of facial photographs on identification documents with actual faces. For example, the information extraction unit extracts names and dates of birth from passport images. In passport image analysis, the position and size of the facial photograph are identified, and facial feature points are extracted using facial recognition technology. Furthermore, for text information, OCR technology is used to accurately extract information such as names, dates of birth, and passport numbers. Furthermore, the information extraction unit can also extract addresses and names from images of driver's licenses. In driver's license image analysis, text areas are identified based on the license layout, and information such as name, address, date of birth, and license number is extracted using OCR technology. In addition, the information extraction unit can also extract addresses and names from images of resident registration certificates. In resident registration certificate image analysis, text areas are identified based on the resident registration certificate format, and information such as address, name, and date of birth is extracted using OCR technology. As a result, the information extraction unit can analyze images of various identity verification documents and related documents and accurately extract the necessary information.

[0072] The review department conducts reviews based on the information extracted by the information extraction department. For example, the review department checks whether the information in identity verification documents matches the information in related documents. For example, the review department uses database matching technology to verify the information's consistency. Database matching technology is a technique that compares the extracted information with an existing database to check for a match, thereby confirming the accuracy of the information in identity verification documents. The review department can also check for the presence of fraudulent information. For example, the review department can use pattern matching technology to detect fraudulent information. Pattern matching technology is a technique that compares the extracted information with existing patterns to check for the presence of fraudulent information, thereby enabling early detection of fraudulent information. Furthermore, the review department can use AI to verify information consistency and detect fraud. For example, the review department can use an AI model to verify information consistency and detect fraudulent information. By training the AI ​​model with a large amount of data, it can achieve highly accurate consistency verification and fraud detection. This allows the review department to perform information consistency verification and fraud detection quickly and accurately. In addition, the review department can improve the accuracy of its reviews by utilizing past review results and statistical information. For example, by analyzing specific patterns and trends based on past audit results, the accuracy of audits can be improved. Furthermore, the audit department can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the audit department to not only understand the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the overall reliability and security of the system.

[0073] The service provider will provide the review results obtained by the review department in real time. The service provider can, for example, use API integration to immediately reflect the review results to front-end sales. API integration is a technology for exchanging data between different systems, which enables the rapid reflection of review results to front-end sales. The service provider can also provide review results in real time using a notification system. A notification system is a technology for quickly notifying users of review results, which enables the real-time provision of review results. The service provider can also provide review results through web applications and mobile applications. For example, the service provider can display review results on a web application and immediately reflect them to front-end sales. A web application is an application that can be accessed via the internet, which enables the rapid provision of review results. The service provider can also display review results on a mobile application and immediately reflect them to front-end sales. A mobile application is an application that can be used on mobile devices such as smartphones and tablets, which enables the rapid provision of review results. Furthermore, the service provider can also provide review results using communication methods such as email and SMS. This allows the service provider to deliver review results quickly and reliably, improving the efficiency of front-end sales.

[0074] The learning unit trains on the evaluation elements by converting them into text data. For example, the learning unit trains on the evaluation elements using a machine learning algorithm. A machine learning algorithm is a technology that identifies patterns and trends by training on large amounts of data, and performs predictions and classifications, thereby improving the accuracy of the evaluation. The learning unit trains on the evaluation elements by converting them into text data using a data preprocessing method. A data preprocessing method is a technology that converts data into a format that is easy to analyze, thereby enabling accurate conversion of evaluation elements into text data. The learning unit can also train on the evaluation elements using AI. For example, the learning unit trains on the evaluation elements using an AI model to improve the accuracy of the evaluation. An AI model can achieve highly accurate predictions and classifications by training on large amounts of data. This allows the learning unit to accurately learn on the evaluation elements and improve the accuracy of the evaluation. Furthermore, the learning unit can also improve the accuracy of the evaluation by utilizing past evaluation results and statistical information. For example, it can analyze specific patterns and trends based on past evaluation results to improve the accuracy of the evaluation. In addition, the learning unit can use anomaly detection algorithms to detect patterns that are different from the norm or abnormal data and issue warnings early. This allows the learning unit to not only grasp the situation in real time, but also to handle long-term risk management and anomaly detection, thereby improving the reliability and security of the entire system.

[0075] The image analysis unit can analyze images of identity verification documents and related documents. For example, the image analysis unit can recognize text within images using OCR (optical character recognition) technology. It can also analyze facial photographs in identity verification documents using facial recognition technology. For example, the image analysis unit can analyze a passport image and extract facial photographs and text information. It can also analyze a driver's license image and extract information such as name and address. Furthermore, it can analyze a resident registration image and extract information such as address and name. This prepares the image analysis unit to extract necessary information by analyzing document images. Some or all of the above processing in the image analysis unit may be performed using AI, or not. For example, the image analysis unit can recognize text within images using OCR technology and analyze facial photographs using an AI model.

[0076] The information extraction unit can extract information such as names, addresses, and dates of birth as text data from images analyzed by the image analysis unit. For example, the information extraction unit can extract text from images using OCR technology. The information extraction unit can also extract personal information from facial photographs using facial recognition technology. For example, the information extraction unit can extract names and dates of birth from passport images. It can also extract addresses and names from driver's license images. Furthermore, it can extract addresses and names from resident registration images. This allows the information extraction unit to extract the necessary information as text data, preparing the application for review. Some or all of the above-described processes in the information extraction unit may be performed using AI, for example, or without AI. For example, the information extraction unit can extract text from images using OCR technology and extract personal information from facial photographs using an AI model.

[0077] The review department can check, based on the information extracted by the information extraction department, whether the information in the identity verification documents matches the information in related documents and whether any fraudulent information is included. The review department can, for example, use database matching technology to verify the consistency of the information. The review department can also check for the presence of fraudulent information. For example, the review department can detect fraudulent information using pattern matching technology. The review department can also use AI to verify the consistency of information and detect fraud. For example, the review department can use an AI model to verify the consistency of information and detect fraudulent information. This enables the review department to perform highly accurate reviews by checking for both consistency and fraud. Some or all of the above processes in the review department may be performed using AI, or they may not. For example, the review department can verify the consistency of information using database matching technology and detect fraudulent information using an AI model.

[0078] The service provider can provide the review results obtained by the review provider in real time and immediately reflect them in front-end sales. For example, the service provider can immediately reflect the review results in front-end sales using API integration. For example, the service provider can provide the review results in real time using a notification system. The service provider can also provide the review results through web applications or mobile applications. For example, the service provider can display the review results in a web application and immediately reflect them in front-end sales. The service provider can also display the review results in a mobile application and immediately reflect them in front-end sales. This enables a rapid response by allowing the service provider to provide review results in real time. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can immediately reflect the review results in front-end sales using API integration and can provide the review results in real time using an AI model.

[0079] The image analysis unit can estimate the user's emotions and adjust the accuracy of the image analysis based on the estimated emotions. For example, if the user is nervous, the image analysis unit can increase the accuracy of the image analysis to perform a more detailed analysis. For example, if the user is relaxed, the image analysis unit can maintain the accuracy of the image analysis at a normal level and perform a rapid analysis. Furthermore, if the user is in a hurry, the image analysis unit can adjust the accuracy of the image analysis to perform a rapid and appropriate analysis. In this way, by adjusting the accuracy of the image analysis according to the user's emotions, a more appropriate analysis becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the image analysis unit may be performed using AI, for example, or without using AI. For example, the image analysis unit can estimate the user's emotions using an emotion engine and adjust the accuracy of the image analysis based on the estimated emotions.

[0080] The image analysis unit can apply different analysis algorithms depending on the type of document during image analysis. For example, the image analysis unit can apply a facial recognition algorithm to passport image analysis. For example, the image analysis unit can apply a character recognition algorithm to driver's license image analysis. Furthermore, the image analysis unit can apply an address and name recognition algorithm to resident registration image analysis. By applying an analysis algorithm appropriate to the type of document, the accuracy of the analysis is improved. Some or all of the above-described processes in the image analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the image analysis unit can input a passport image into a generative AI and perform analysis by applying a facial recognition algorithm.

[0081] The image analysis unit can adjust its analysis method during image analysis, taking into account the degree of deterioration of the document. For example, the image analysis unit can apply a noise reduction algorithm to the image analysis of a deteriorated document. For example, the image analysis unit can apply a color correction algorithm to the image analysis of a faded document. Furthermore, the image analysis unit can apply an algorithm to fill in missing parts to the image analysis of a damaged document. This allows for accurate analysis even of deteriorated documents by taking into account the degree of deterioration of the document. Some or all of the above processing in the image analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image analysis unit can input an image of a deteriorated document into a generation AI and perform analysis by applying a noise reduction algorithm.

[0082] The image analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is tense, the image analysis unit can provide a simple and highly visible display method. For example, if the user is relaxed, the image analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the image analysis unit can provide a display method that gets straight to the point. By adjusting the display method of the analysis results according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the image analysis unit may be performed using AI, for example, or without using AI. For example, the image analysis unit can estimate the user's emotions using an emotion engine and adjust the display method of the analysis results based on the estimated emotions.

[0083] The image analysis unit can improve the accuracy of its analysis by considering the document's issuer information during image analysis. For example, the image analysis unit can analyze government-issued documents while considering specific security elements. For example, it can analyze corporate-issued documents while considering the company logo and specific format. Furthermore, it can analyze school-issued documents while considering specific student ID numbers and school emblems. This improves the accuracy of the analysis by considering the document's issuer information. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input government-issued documents into a generative AI and perform analysis while considering specific security elements.

[0084] The image analysis unit can apply different analysis methods depending on the language of the document during image analysis. For example, the image analysis unit can apply an English-specific character recognition algorithm to an English document. For example, the image analysis unit can apply a Japanese-specific character recognition algorithm to a Japanese document. Furthermore, the image analysis unit can apply character recognition algorithms corresponding to each language to multilingual documents. This enables multilingual analysis by applying analysis methods according to the language of the document. Some or all of the above-described processes in the image analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the image analysis unit can input an English document into a generative AI and perform analysis by applying an English-specific character recognition algorithm.

[0085] The information extraction unit can estimate the user's emotions and determine the priority of information to extract based on the estimated emotions. For example, if the user is tense, the information extraction unit will prioritize extracting important information. If the user is relaxed, the information extraction unit can extract detailed information. Furthermore, if the user is in a hurry, the information extraction unit can quickly extract the necessary information. This allows for more appropriate information extraction by prioritizing information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information extraction unit may be performed using AI, for example, or without AI. For example, the information extraction unit can estimate the user's emotions using an emotion engine and determine the priority of information to extract based on the estimated emotions.

[0086] The information extraction unit can apply different extraction algorithms depending on the document format during information extraction. For example, when extracting information from a passport, the information extraction unit can apply an algorithm that extracts facial photographs and text information. For example, when extracting information from a driver's license, the information extraction unit can apply a character recognition algorithm. Furthermore, when extracting information from a resident registration certificate, the information extraction unit can apply an address and name recognition algorithm. This improves the accuracy of extraction by applying an extraction algorithm according to the document format. Some or all of the above processing in the information extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the information extraction unit can input passport information into a generation AI and perform extraction by applying an algorithm that extracts facial photographs and text information.

[0087] The information extraction unit can improve the accuracy of information extraction by evaluating the reliability of the document's contents during the extraction process. For example, the information extraction unit can evaluate the reliability of the document's issuer and prioritize the extraction of highly reliable information. For example, the information extraction unit can consider the document's issue date and time and prioritize the extraction of the most recent information. The information extraction unit can also check for inconsistencies in the document's contents and extract highly reliable information. In this way, highly reliable information can be extracted by evaluating the reliability of the document's contents. Some or all of the above-described processes in the information extraction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the information extraction unit can input the reliability of the document's issuer into the generating AI and prioritize the extraction of highly reliable information.

[0088] The information extraction unit can estimate the user's emotions and adjust the display method of the extracted information based on the estimated emotions. For example, if the user is tense, the information extraction unit can provide a simple and highly visible display method. For example, if the user is relaxed, the information extraction unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the information extraction unit can provide a display method that gets straight to the point. By adjusting the display method of the extracted information according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the information extraction unit may be performed using AI, for example, or without using AI. For example, the information extraction unit can estimate the user's emotions using an emotion engine and adjust the display method of the extracted information based on the estimated emotions.

[0089] The information extraction unit can improve the accuracy of information extraction by considering the document's issuance date and time. For example, if the document's issuance date and time are recent, the information extraction unit will prioritize extracting the latest information. If the document's issuance date and time are old, the information extraction unit can extract information by referring to past information. The information extraction unit can also apply an appropriate extraction algorithm based on the document's issuance date and time. This allows for the priority extraction of the latest information by considering the document's issuance date and time. Some or all of the above processing in the information extraction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the information extraction unit can input the document's issuance date and time into a generating AI and prioritize extracting the latest information.

[0090] The information extraction unit can apply different extraction methods depending on the language of the document during information extraction. For example, the information extraction unit can apply an English-specific character recognition algorithm to an English document. For example, the information extraction unit can apply a Japanese-specific character recognition algorithm to a Japanese document. Furthermore, the information extraction unit can apply character recognition algorithms corresponding to each language to a multilingual document. This enables multilingual information extraction by applying an extraction method according to the language of the document. Some or all of the above processing in the information extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the information extraction unit can input an English document into a generation AI and extract information by applying an English-specific character recognition algorithm.

[0091] The review unit can estimate the user's emotions and adjust the review criteria based on the estimated emotions. For example, if the user is nervous, the review unit can tighten the review criteria and conduct a more detailed review. For example, if the user is relaxed, the review unit can maintain the review criteria at a normal level and conduct a quick review. The review unit can also adjust the review criteria to conduct a quick and appropriate review if the user is in a hurry. This allows for a more appropriate review by adjusting the review criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review unit may be performed using AI, for example, or not using AI. For example, the review unit can estimate the user's emotions using an emotion engine and adjust the review criteria based on the estimated emotions.

[0092] The review unit can optimize its review algorithm by referring to past review results during the review process. For example, the review unit can adjust the review algorithm based on past review results to improve accuracy. For example, the review unit can extract specific patterns from past review results and reflect them in the review algorithm. The review unit can also analyze past review results and identify areas for improvement in the review algorithm. This improves the accuracy of the review algorithm by referring to past review results. Some or all of the above processes in the review unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the review unit can input past review results into a generative AI to optimize the review algorithm.

[0093] The review department can improve the accuracy of its review process by evaluating the reliability of the document issuer during the review process. For example, the review department can apply highly reliable review criteria to documents issued by the government. For example, the review department can evaluate the reliability of a company and adjust its review criteria for documents issued by a company. Furthermore, the review department can evaluate the reliability of a school and adjust its review criteria for documents issued by a school. This improves the accuracy of the review process by evaluating the reliability of the document issuer. Some or all of the above processes in the review department may be performed using, for example, a generative AI, or not using a generative AI. For example, the review department can input government-issued documents into a generative AI and apply highly reliable review criteria.

[0094] The review unit can estimate the user's emotions and adjust the display method of the review results based on the estimated emotions. For example, if the user is nervous, the review unit can provide a simple and highly visible display method. For example, if the user is relaxed, the review unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the review unit can provide a concise display method. By adjusting the display method of the review results according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review unit may be performed using AI, for example, or without AI. For example, the review unit can estimate the user's emotions using an emotion engine and adjust the display method of the review results based on the estimated emotions.

[0095] The review department can improve the accuracy of its review process by considering the region where the documents were issued. For example, if the documents are issued in different regions, the review department will consider region-specific information during the review. For example, the review department can apply appropriate review criteria based on the region where the documents were issued. The review department can also evaluate the reliability of the region where the documents were issued and adjust the review criteria accordingly. This makes it possible to conduct a review that reflects region-specific information by considering the region where the documents were issued. Some or all of the above processes in the review department may be performed using, for example, a generative AI, or not using a generative AI. For example, the review department can input the region where the documents were issued into a generative AI and conduct a review that considers region-specific information.

[0096] The review department can improve the accuracy of its review by referring to the relevant laws and regulations of the documents during the review process. For example, the review department can refer to the relevant laws and regulations of the documents and apply appropriate review criteria. For example, the review department can adjust its review algorithm based on the relevant laws and regulations of the documents. The review department can also improve the accuracy of its review by taking into account the relevant laws and regulations of the documents. This makes it possible to conduct a legally accurate review by referring to the relevant laws and regulations of the documents. Some or all of the above processes in the review department may be performed using, for example, a generative AI, or not using a generative AI. For example, the review department can input the relevant laws and regulations of the documents into a generative AI and apply appropriate review criteria.

[0097] The service provider can estimate the user's emotions and adjust the display method of the review results based on the estimated emotions. For example, if the user is nervous, the service provider can provide a simple and highly visible display method. For example, if the user is relaxed, the service provider can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the service provider can provide a concise display method. By adjusting the display method of the review results according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider can estimate the user's emotions using an emotion engine and adjust the display method of the review results based on the estimated emotions.

[0098] The information provider can determine the display priority based on the importance of the review results at the time of provision. For example, the provider can prioritize the display of important review results and quickly notify the user. For example, the provider can postpone the display of less important review results. The provider can also adjust the display order based on the importance of the review results. This allows for the rapid provision of important information by determining the display priority based on the importance of the review results. Some or all of the above processing in the information provider may be performed using, for example, a generating AI, or without using a generating AI. For example, the provider can input the importance of the review results into a generating AI and prioritize the display of important review results.

[0099] The service provider can apply different display methods depending on the category of the review results at the time of provision. For example, the service provider can apply a specific display method to the review results of identity verification documents. For example, the service provider can apply a different display method to the review results of related documents. The service provider can also provide the most suitable display method for each category. This improves the visibility of the information by applying a display method appropriate to the category of the review results. Some or all of the above processing in the service provider may be performed using, for example, a generation AI, or without a generation AI. For example, the service provider can input the review results of identity verification documents into a generation AI and apply a specific display method.

[0100] The service provider can estimate the user's emotions and adjust the level of detail in the review results based on the estimated emotions. For example, if the user is nervous, the service provider can provide concise and to-the-point review results. If the user is relaxed, the service provider can provide detailed review results. Furthermore, if the user is in a hurry, the service provider can provide quickly understandable review results. This allows for the provision of appropriate information to the user by adjusting the level of detail in the review results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can estimate the user's emotions using an emotion engine and adjust the level of detail in the review results based on the estimated emotions.

[0101] The service provider can determine the display priority based on the submission date of the review results at the time of provision. For example, the service provider can prioritize the display of the latest review results to quickly notify the user. For example, the service provider can postpone the display of older review results. The service provider can also adjust the display order based on the submission date. This allows for the rapid provision of the latest information by prioritizing the display based on the submission date of the review results. Some or all of the above processing in the service provider may be performed using, for example, a generating AI, or not using a generating AI. For example, the service provider can input the submission dates of the review results into a generating AI and prioritize the display of the latest review results.

[0102] The information provider can adjust the display order based on the relevance of the review results at the time of provision. For example, the information provider can prioritize displaying highly relevant review results and quickly notify the user. For example, the information provider can postpone displaying less relevant review results. The information provider can also adjust the display order based on the relevance of the review results. This allows for the priority provision of highly relevant information by adjusting the display order based on the relevance of the review results. Some or all of the above processing in the information provider may be performed using, for example, a generating AI, or without using a generating AI. For example, the information provider can input the relevance of the review results into a generating AI and prioritize displaying highly relevant review results.

[0103] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is nervous, the learning unit can prioritize selecting important training data. If the user is relaxed, the learning unit can select detailed training data. Also, if the user is in a hurry, the learning unit can select data that allows for quick learning. This enables more appropriate learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can estimate the user's emotions using an emotion engine and select training data based on the estimated emotions.

[0104] The learning unit can optimize its learning algorithm by referring to past learning data during the learning process. For example, the learning unit can adjust the learning algorithm based on past learning data to improve accuracy. For example, the learning unit can extract specific patterns from past learning data and reflect them in the learning algorithm. The learning unit can also analyze past learning data and identify areas for improvement in the learning algorithm. As a result, the accuracy of the learning algorithm is improved by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past learning data into a generative AI to optimize the learning algorithm.

[0105] The learning unit can evaluate the accuracy of the review results and weight the training data during training. For example, the learning unit can prioritize training on data with high accuracy in the review results. For example, the learning unit can train on data with low accuracy in the review results with lower weighting. The learning unit can also adjust the weighting of the training data based on the accuracy of the review results. This allows the learning unit to prioritize training on high-accuracy data by evaluating the accuracy of the review results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the accuracy of the review results into a generative AI and prioritize training on high-accuracy data.

[0106] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can increase the learning frequency to perform more detailed learning. For example, if the user is relaxed, the learning unit can maintain a normal learning frequency for efficient learning. The learning unit can also adjust the learning frequency to perform quick and appropriate learning if the user is in a hurry. This allows for more appropriate learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can estimate the user's emotions using an emotion engine and adjust the learning frequency based on the estimated emotions.

[0107] The learning unit can weight the training data based on the submission date of the review results during training. For example, the learning unit can prioritize learning the most recent review results. For example, the learning unit can lower the weight of older review results during training. The learning unit can also adjust the weighting of the training data based on the submission date. This allows for prioritizing the learning of the latest information by weighting the training data based on the submission date of the review results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input the submission date of the review results into a generative AI and prioritize learning the most recent review results.

[0108] The learning unit can evaluate the relevance of the review results and select training data during the learning process. For example, the learning unit can prioritize learning review results that are highly relevant. For example, the learning unit can postpone learning review results that are less relevant. The learning unit can also select training data based on the relevance of the review results. This allows it to prioritize learning highly relevant data by evaluating the relevance of the review results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the relevance of the review results into a generative AI and prioritize learning highly relevant data.

[0109] The learning unit can evaluate the accuracy of the review results and weight the training data during training. For example, the learning unit can prioritize training on data with high accuracy in the review results. For example, the learning unit can train on data with low accuracy in the review results with lower weighting. The learning unit can also adjust the weighting of the training data based on the accuracy of the review results. This allows the learning unit to prioritize training on high-accuracy data by evaluating the accuracy of the review results. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the accuracy of the review results into a generative AI and prioritize training on high-accuracy data.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The review system can further estimate the user's emotions and adjust the review priority based on the estimated emotions. For example, if the user is nervous, the review system will prioritize important review items. If the user is relaxed, the review system can proceed with the review in the normal order. Also, if the user is in a hurry, the review system can prioritize items that need to be processed quickly. This enables flexible review that responds to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review system may be performed using AI or not. For example, the review system can estimate the user's emotions using an emotion engine and adjust the review priority based on the estimated emotions.

[0112] The review system can further improve the accuracy of its reviews by referring to the user's past review history. For example, stricter criteria can be applied to users who have been found to have committed fraud in the past. Conversely, normal criteria can be applied to users who have had no problems in the past. It can also extract specific patterns based on past review history and incorporate them into the review algorithm. In this way, the accuracy of the review is improved by utilizing past review history. Some or all of the above processes in the review system may be performed using, for example, generative AI, or not using generative AI. For example, the review system can input past review history into generative AI to optimize the review algorithm.

[0113] The review system can further estimate the user's emotions and adjust the notification method of the review results based on the estimated emotions. For example, if the user is nervous, the review system can provide a simple and highly visible notification method. If the user is relaxed, it can provide a notification method that includes detailed information. If the user is in a hurry, it can provide a notification method that gets straight to the point. This enables appropriate notifications according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review system may be performed using AI, for example, or not using AI. For example, the review system can estimate the user's emotions using an emotion engine and adjust the notification method of the review results based on the estimated emotions.

[0114] The review system can further evaluate the reliability of the document issuer and prioritize the review of highly reliable documents. For example, a high reliability review standard can be applied to documents issued by the government. For documents issued by companies, the review standard can be adjusted based on an evaluation of the company's reliability. Similarly, for documents issued by schools, the review standard can be adjusted based on an evaluation of the school's reliability. This improves the accuracy of the review by evaluating the reliability of the document issuer. Some or all of the above processes in the review system may be performed using, for example, generative AI, or not. For example, the review system can input the reliability of the document issuer into a generative AI and prioritize the review of highly reliable documents.

[0115] The review system can further estimate the user's emotions and adjust the level of detail in the review based on the estimated emotions. For example, if the user is nervous, the review system can perform a detailed review and provide more information. If the user is relaxed, the review system can perform a normal review and provide only the necessary minimum information. Also, if the user is in a hurry, the review system can perform a quick review and provide concise information. This enables appropriate review tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review system may be performed using AI or not. For example, the review system can estimate the user's emotions using an emotion engine and adjust the level of detail in the review based on the estimated emotions.

[0116] The review system can further improve the accuracy of its review by considering the region where the documents were issued. For example, if the documents are issued in different regions, the review can be conducted while considering region-specific information. Appropriate review criteria can be applied based on the region where the documents were issued. The reliability of the region where the documents were issued can also be evaluated, and the review criteria can be adjusted accordingly. This makes it possible to conduct a review that reflects region-specific information by considering the region where the documents were issued. Some or all of the above processes in the review system may be performed using, for example, a generative AI, or not using a generative AI. For example, the review system can input the region where the documents were issued into a generative AI and conduct a review while considering region-specific information.

[0117] The review system can further estimate the user's emotions and adjust the display method of the review results based on the estimated emotions. For example, if the user is nervous, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Also, if the user is in a hurry, a display method that gets straight to the point can be provided. In this way, by adjusting the display method of the review results according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the review system may be performed using AI, for example, or not using AI. For example, the review system can estimate the user's emotions using an emotion engine and adjust the display method of the review results based on the estimated emotions.

[0118] The review system can further improve the accuracy of its review by referring to the relevant laws and regulations of the documents. For example, it can refer to the relevant laws and regulations of the documents and apply appropriate review criteria. Based on the relevant laws and regulations of the documents, the review algorithm can be adjusted. It can also improve the accuracy of its review by taking the relevant laws and regulations of the documents into consideration. This makes it possible to perform accurate, law-based reviews by referring to the relevant laws and regulations of the documents. Some or all of the above processes in the review system may be performed using, for example, a generative AI, or not using a generative AI. For example, the review system can input the relevant laws and regulations of the documents into a generative AI and apply appropriate review criteria.

[0119] The review system can further estimate the user's emotions and adjust the review criteria based on the estimated emotions. For example, if the user is nervous, the review criteria can be made stricter and a more detailed review can be conducted. If the user is relaxed, the review criteria can be kept at a normal level and a quick review can be conducted. Also, if the user is in a hurry, the review criteria can be adjusted to conduct a quick and appropriate review. In this way, adjusting the review criteria according to the user's emotions enables a more appropriate review. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review system may be performed using AI, for example, or not using AI. For example, the review system can estimate the user's emotions using an emotion engine and adjust the review criteria based on the estimated emotions.

[0120] The review system can further improve the accuracy of its review by considering the document's issuance date and time. For example, if the document's issuance date and time are recent, the most recent information will be prioritized in the review. If the document's issuance date and time are old, past information can be used as a reference during the review. The system can also apply an appropriate review algorithm based on the document's issuance date and time. This allows for prioritizing the review of the most recent information by considering the document's issuance date and time. Some or all of the above processes in the review system may be performed using, for example, a generative AI, or not using a generative AI. For example, the review system can input the document's issuance date and time into a generative AI and prioritize the review of the most recent information.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The image analysis unit analyzes images of identity verification documents and related documents. For example, it uses OCR (optical character recognition) technology to recognize text within images and facial recognition technology to analyze facial photographs on identity verification documents. Specifically, it analyzes passport images to extract facial photographs and text information. It also analyzes images of driver's licenses and resident registration certificates to extract information such as names and addresses. Step 2: The information extraction unit extracts information from the image analyzed by the image analysis unit. For example, it extracts information such as name, address, and date of birth as text data. Using OCR technology and facial recognition technology, it extracts necessary information from images of passports, driver's licenses, and resident registration certificates. Step 3: The review department conducts a review based on the information extracted by the information extraction department. For example, they check whether the information on the identity verification documents matches the information on related documents and confirm that no fraudulent information is included. Database matching technology, pattern matching technology, and AI models are used to verify information consistency and detect fraud. Step 4: The service provider provides the review results obtained by the review department in real time. For example, the review results are immediately reflected in front-end sales using API integration or notification systems and provided through web applications and mobile applications. Step 5: The learning unit converts the evaluation elements into text data and uses it for training. For example, it uses machine learning algorithms or AI models to learn the evaluation elements and improve the accuracy of the evaluation.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the image analysis unit, information extraction unit, review unit, provision unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the image analysis unit uses the camera 42 of the smart device 14 to acquire images of identity verification documents and related documents, and these are analyzed by the specific processing unit 290 of the data processing unit 12. The information extraction unit is implemented in the specific processing unit 290 of the data processing unit 12 and extracts necessary information from the images analyzed by the image analysis unit. The review unit is implemented in the specific processing unit 290 of the data processing unit 12 and performs a review based on the extracted information. The provision unit is implemented in the control unit 46A of the smart device 14 and provides the review results in real time. The learning unit is implemented in the specific processing unit 290 of the data processing unit 12 and learns the review elements by converting them into text data. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the image analysis unit, information extraction unit, examination unit, provision unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the image analysis unit uses the camera 42 of the smart glasses 214 to acquire images of identity verification documents and related documents, and these are analyzed by the identification processing unit 290 of the data processing unit 12. The information extraction unit is implemented in the identification processing unit 290 of the data processing unit 12 and extracts necessary information from the images analyzed by the image analysis unit. The examination unit is implemented in the identification processing unit 290 of the data processing unit 12 and performs an examination based on the extracted information. The provision unit is implemented in the control unit 46A of the smart glasses 214 and provides the examination results in real time. The learning unit is implemented in the identification processing unit 290 of the data processing unit 12 and learns the examination elements by converting them into text data. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the image analysis unit, information extraction unit, examination unit, provision unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the image analysis unit uses the camera 42 of the headset terminal 314 to acquire images of identity verification documents and related documents, and these are analyzed by the specific processing unit 290 of the data processing unit 12. The information extraction unit is implemented in the specific processing unit 290 of the data processing unit 12 and extracts necessary information from the images analyzed by the image analysis unit. The examination unit is implemented in the specific processing unit 290 of the data processing unit 12 and performs an examination based on the extracted information. The provision unit is implemented in the control unit 46A of the headset terminal 314 and provides the examination results in real time. The learning unit is implemented in the specific processing unit 290 of the data processing unit 12 and learns the examination elements by converting them into text data. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the image analysis unit, information extraction unit, examination unit, provision unit, and learning unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the image analysis unit uses the camera 42 of the robot 414 to acquire images of identity verification documents and related documents, which are then analyzed by the specific processing unit 290 of the data processing unit 12. The information extraction unit is implemented in the specific processing unit 290 of the data processing unit 12 and extracts necessary information from the images analyzed by the image analysis unit. The examination unit is implemented in the specific processing unit 290 of the data processing unit 12 and performs an examination based on the extracted information. The provision unit is implemented in the control unit 46A of the robot 414 and provides the examination results in real time. The learning unit is implemented in the specific processing unit 290 of the data processing unit 12 and learns the examination elements by converting them into text data. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] 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.

[0186] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) The image analysis department analyzes images of identity verification documents and related documents, An information extraction unit that extracts information from the image analyzed by the aforementioned image analysis unit, A review unit performs a review based on the information extracted by the aforementioned information extraction unit, A provision unit that provides the review results obtained by the aforementioned review unit in real time, It comprises a learning unit that converts the evaluation elements into text data and uses it for learning. A system characterized by the following features. (Note 2) The aforementioned image analysis unit, Analyze images of identity verification documents and related documents. The system described in Appendix 1, characterized by the features described herein. (Note 3) The information extraction unit, The image analysis unit extracts information such as names, addresses, and dates of birth as text data from the analyzed images. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned review department, Based on the information extracted by the aforementioned information extraction unit, it is checked whether the information in the identity verification document matches the information in the related documents and whether any fraudulent information is included. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, The review results obtained by the aforementioned review department will be provided in real time and immediately reflected in front-end sales. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, The evaluation criteria are converted into text data and used for training. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned image analysis unit, It estimates the user's emotions and adjusts the accuracy of image analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned image analysis unit, When analyzing images, different analysis algorithms are applied depending on the type of document. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned image analysis unit, During image analysis, the analysis method is adjusted to take into account the degree of deterioration of the document. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned image analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned image analysis unit, When analyzing images, consider the document's issuer information to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned image analysis unit, When analyzing images, different analysis methods are applied depending on the language of the document. The system described in Appendix 1, characterized by the features described herein. (Note 13) The information extraction unit, It estimates the user's emotions and determines the priority of information to extract based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The information extraction unit, When extracting information, different extraction algorithms are applied depending on the document format. The system described in Appendix 1, characterized by the features described herein. (Note 15) The information extraction unit, During information extraction, the reliability of the document's contents is evaluated to improve the accuracy of the extraction. The system described in Appendix 1, characterized by the features described herein. (Note 16) The information extraction unit, It estimates the user's emotions and adjusts how the extracted information is displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The information extraction unit, When extracting information, consider the document's issuance date to improve extraction accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 18) The information extraction unit, When extracting information, different extraction methods are applied depending on the language of the document. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned review department, We estimate the user's emotions and adjust the review criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned review department, During the review process, the review algorithm is optimized by referring to past review results. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned review department, During the review process, we evaluate the reliability of the document issuer to improve the accuracy of the review. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned review department, The system estimates the user's emotions and adjusts how the review results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned review department, During the review process, we take into account the region where the documents were issued to improve the accuracy of the review. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned review department, During the review process, we refer to the relevant laws and regulations in the documents to improve the accuracy of the review. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, We estimate the user's emotions and adjust how the review results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing the information, the display priority will be determined based on the importance of the review results. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing the results, different display methods will be applied depending on the category of the review results. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, We estimate the user's emotions and adjust the level of detail in the review results provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, At the time of provision, the priority of display will be determined based on the timing of the submission of the review results. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing the content, adjust the display order based on the relevance of the review results. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned learning unit, During training, the accuracy of the evaluation results is assessed and the training data is weighted accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned learning unit, During training, the training data is weighted based on the timing of the submission of the review results. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned learning unit, During training, the relevance of the evaluation results is assessed to select training data. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The image analysis department analyzes images of identity verification documents and related documents, An information extraction unit that extracts information from the image analyzed by the aforementioned image analysis unit, A review unit performs a review based on the information extracted by the aforementioned information extraction unit, A provision unit that provides the review results obtained by the aforementioned review unit in real time, It comprises a learning unit that converts the evaluation elements into text data and uses it for learning. A system characterized by the following features.

2. The aforementioned image analysis unit, Analyze images of identity verification documents and related documents. The system according to feature 1.

3. The information extraction unit, The image analysis unit extracts information such as names, addresses, and dates of birth as text data from the analyzed images. The system according to feature 1.

4. The aforementioned review department, Based on the information extracted by the aforementioned information extraction unit, it is checked whether the information in the identity verification document matches the information in the related documents and whether any fraudulent information is included. The system according to feature 1.

5. The aforementioned supply unit is, The review results obtained by the aforementioned review department will be provided in real time and immediately reflected in front-end sales. The system according to feature 1.

6. The aforementioned learning unit, The evaluation criteria are converted into text data and used for training. The system according to feature 1.

7. The aforementioned image analysis unit, It estimates the user's emotions and adjusts the accuracy of image analysis based on the estimated user emotions. The system according to feature 1.

8. The aforementioned image analysis unit, When analyzing images, different analysis algorithms are applied depending on the type of document. The system according to feature 1.

Images