system

Abstract

The system according to the embodiment aims to improve the efficiency of bill processing. [Solution] The system according to the embodiment comprises an acquisition unit, an extraction unit, an analysis unit, a registration unit, and a notification unit. The acquisition unit acquires image data of an invoice. The extraction unit converts the image data acquired by the acquisition unit into text data using AI-OCR. The analysis unit analyzes the text data extracted by the extraction unit using generation AI, and classifies and organizes the contents of the invoice. The registration unit registers the data classified and organized by the analysis unit in a database. The notification unit creates a payment schedule based on the data registered by the registration unit, and notifies the relevant departments.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, invoice processing was often done manually, which was inefficient.

[0005] The system according to the embodiment aims to improve the efficiency of bill processing. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, an extraction unit, an analysis unit, a registration unit, and a notification unit. The acquisition unit acquires image data of an invoice. The extraction unit converts the image data acquired by the acquisition unit into text data using AI-OCR. The analysis unit analyzes the text data extracted by the extraction unit using generation AI, and classifies and organizes the contents of the invoice. The registration unit registers the data classified and organized by the analysis unit in a database. The notification unit creates a payment schedule based on the data registered by the registration unit, and notifies the relevant departments. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency of bill processing. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

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

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

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) An invoice processing system according to an embodiment of the present invention acquires image data of an invoice, converts it into text data using AI-OCR, classifies and organizes the invoice content using a generation AI, registers it in a database, creates a payment schedule, and notifies relevant departments. This system significantly improves the efficiency of invoice processing and reduces manual errors. For example, an acquisition unit is provided to acquire image data of the invoice and input the data into the AI-OCR. Image data of the invoice is acquired using a scanner or camera and input into the acquisition unit. This data is converted into text data by the AI-OCR. Next, an extraction unit is provided in which the AI-OCR extracts the text data and passes it to the generation AI. The AI-OCR extracts text data from the image data of the invoice and passes it to the extraction unit. For example, information such as the invoice issue date, amount, and payment deadline is extracted. The generation AI has an analysis unit that analyzes the text data and classifies and organizes the invoice content. The generation AI analyzes the text data received from the extraction unit and classifies and organizes the invoice content. For example, information such as the invoice issue date, amount, and payment deadline is registered in a database. Finally, a registration unit is provided to register the analysis results in a database, and a notification unit is provided to create a payment schedule and notify relevant departments. The analysis unit passes the classified and organized data to the registration unit, which then registers it in the database. The notification unit creates a payment schedule and notifies relevant departments. For example, by notifying relevant departments when the payment deadline is approaching, payment delays can be prevented. This allows the invoice processing system to process invoices efficiently and reduce manual errors.

[0029] The invoice processing system according to the embodiment includes an acquisition unit, an extraction unit, an analysis unit, a registration unit, and a notification unit. The acquisition unit acquires image data of an invoice. Invoice image data may be in formats such as PDF, JPEG, and PNG, but is not limited to these. The acquisition unit acquires the image data of an invoice using, for example, a scanner or a camera. A scanner can acquire image data at high resolution, while a camera can easily acquire image data. The extraction unit converts the image data acquired by the acquisition unit into text data using AI-OCR. The AI-OCR may use technologies such as Tesseract (registered trademark), Google (registered trademark) Cloud Vision, and Amazon Textract (registered trademark). The AI-OCR extracts text data from the image data and passes it to the extraction unit. For example, it extracts information such as the invoice issue date, amount, and payment deadline. The analysis unit uses a generation AI to analyze the text data received from the extraction unit and classify and organize the contents of the invoice. The generation AI may use technologies such as GPT-4 (registered trademark) and Gemini. The generation AI analyzes text data and classifies and organizes the contents of the invoice. For example, it registers information such as the invoice issue date, amount, and payment deadline in a database. The registration unit registers the classified and organized data received from the analysis unit in the database. Examples of databases include, but are not limited to, relational databases and NoSQL databases. Databases can efficiently store and search data. The notification unit creates a payment schedule and notifies relevant departments when the payment deadline is approaching. The notification unit can send notifications using methods such as email, SMS, and push notification. This allows the invoice processing system to process invoices efficiently and reduce manual errors.

[0030] The acquisition unit can acquire image data of an invoice using a scanner or a camera. The acquisition unit can acquire image data of an invoice using, for example, a scanner. The scanner can acquire image data at high resolution. For example, the scanner can acquire image data at a resolution of 300 dpi or higher. The acquisition unit can also acquire image data of an invoice using a camera. The camera can easily acquire image data. For example, the camera can be a camera installed in a smartphone or tablet. This allows for efficient acquisition of image data of an invoice. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input image data acquired by a scanner or camera to a generation AI and cause the generation AI to acquire the image data.

[0031] The extraction unit can extract information such as the invoice issue date, amount, and payment deadline using AI-OCR. The extraction unit extracts information such as the invoice issue date, amount, and payment deadline using, for example, AI-OCR. AI-OCR is a technology for extracting text data from image data, and can use technologies such as Tesseract, Google Cloud Vision, and Amazon Textract. For example, AI-OCR extracts the invoice issue date. The issue date is often listed at the top of the invoice and is extracted based on a date format. For example, formats such as "YYYY / MM / DD" or "DD-MM-YYYY" are used. Next, AI-OCR extracts the invoice amount. The amount is often listed in the center of the invoice and is extracted based on currency symbols and numbers. For example, formats such as "$1000" or "¥5000" are used. Finally, AI-OCR extracts the invoice payment deadline. The payment deadline is often listed at the bottom of the invoice and is extracted based on a date format. For example, formats such as "Payment due date: YYYY / MM / DD" or "Payment due date: DD-MM-YYYY" are used. This allows important information on the invoice to be accurately extracted. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit may input text data extracted by AI-OCR into a generation AI and have the generation AI extract the text data.

[0032] The analysis unit can analyze the text data received from the extraction unit using the generation AI and classify and organize the contents of the invoice. The analysis unit, for example, uses the generation AI to analyze the text data received from the extraction unit. The generation AI can use technologies such as GPT-4 and Gemini. The generation AI analyzes the text data and classifies and organizes the contents of the invoice. For example, the generation AI analyzes information such as the invoice issue date, amount, and payment deadline, and converts it into a format for registration in a database. Next, the generation AI classifies the contents of the invoice into categories. Categories include, for example, "electricity bill," "water bill," and "gas bill." The generation AI analyzes the contents of the invoice and classifies them into the appropriate category. Finally, the generation AI organizes the contents of the invoice. Organization includes, for example, dividing the data by invoice item and converting it into a format for registration in a database. This allows the contents of the invoice to be efficiently classified and organized. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can convert the text data analyzed by the generation AI into a format for registration in a database, and have the generation AI perform classification and organization.

[0033] The registration unit can register the categorized and organized data received from the analysis unit in a database. The registration unit, for example, registers the categorized and organized data received from the analysis unit in a database. Examples of databases include, but are not limited to, relational databases and NoSQL databases. Relational databases manage data in a table format and allow data search and manipulation using SQL queries. NoSQL databases have a schema-less, flexible data model and can efficiently process large amounts of data. The registration unit converts the data received from the analysis unit into an appropriate format and registers it in a database. For example, information such as the invoice issue date, amount, and payment deadline is registered in the corresponding fields of the database. This allows the categorized and organized data to be efficiently registered in the database. Some or all of the above-described processing in the registration unit may be performed using, for example, AI, or may be performed without AI. For example, the registration unit may register the data converted by the generation AI in a database and have the generation AI perform the registration process.

[0034] The notification unit can create a payment schedule and notify relevant departments when the payment deadline approaches. For example, the notification unit creates a payment schedule and notifies relevant departments when the payment deadline approaches. The payment schedule is created based on the invoice payment deadline. For example, if the payment deadline is one week from now, the notification unit creates a payment schedule and notifies relevant departments three days before the payment deadline. The notification unit can send notifications using methods such as email, SMS, and push notification. Email can provide detailed notification content and convey clear instructions to relevant departments. SMS can send quick notifications with short messages and is suitable for urgent notifications. Push notifications can send notifications in real time via a mobile application, providing high immediacy. This can prevent payment delays. Some or all of the above-mentioned processing in the notification unit can be performed using, for example, AI, or without AI. For example, the notification unit can send notifications based on the payment schedule created by the generation AI and have the generation AI execute the notification processing.

[0035] The acquisition unit can select the optimal acquisition method based on the type and issuer of the invoice. The acquisition unit selects the optimal acquisition method based on, for example, the type and issuer of the invoice. Invoice types include, for example, electronic invoices, paper invoices, and invoices downloadable from a web portal. In the case of electronic invoices, the acquisition unit can acquire image data directly from email. In the case of paper invoices, the acquisition unit can acquire high-resolution image data using a scanner. In the case of invoices downloadable from a web portal, the acquisition unit can automatically acquire image data using an API. The issuer includes, for example, the company name, industry, and invoice format. The acquisition unit selects the optimal acquisition method based on the issuer. For example, a dedicated acquisition method can be used for invoices from a specific company. This allows image data to be acquired using the optimal method depending on the type and issuer of the invoice. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input data on the type and issuer of the invoice into the generation AI and cause the generation AI to select the optimal acquisition method.

[0036] The acquisition unit may have a function for automatically adjusting the image resolution and quality. The acquisition unit may, for example, have a function for automatically adjusting the image resolution and quality. Because image resolution and quality significantly affect the accuracy of invoice reading, it is important to adjust them appropriately. For example, if low-resolution image data is acquired, the acquisition unit may automatically improve the resolution. To improve the resolution, for example, super-resolution technology may be used. Furthermore, if the image quality is low, the acquisition unit may perform noise removal and contrast adjustment to make the image easier to read. For noise removal, for example, a Gaussian filter or a median filter may be used. For contrast adjustment, for example, histogram equalization or gamma correction may be used. Furthermore, if the image is distorted, the acquisition unit may automatically correct it to obtain accurate data. For distortion correction, for example, a geometric transformation or a homography transformation may be used. This allows accurate data to be obtained by automatically adjusting the image resolution and quality. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI, or may be performed without AI. For example, the acquisition unit can input image data into the generation AI and have the generation AI adjust the resolution and quality.

[0037] The acquisition unit can prioritize acquisition of highly relevant invoices by taking into account the user's geographical location information. The acquisition unit, for example, prioritizes acquisition of highly relevant invoices by taking into account the user's geographical location information. Geographical location information can be acquired using, for example, GPS data, an IP address, a location information service, etc. For example, if the user is in a specific area, invoices related to that area can be prioritized. If the user is on a business trip, invoices related to the business trip destination can be prioritized. If the user is at home, invoices related to the home can be prioritized. This makes it possible to prioritize acquisition of highly relevant invoices based on the user's geographical location information. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the user's geographical location information to the generation AI and cause the generation AI to prioritize acquisition of highly relevant invoices.

[0038] The acquisition unit can analyze a user's social media activity and acquire related invoices. The acquisition unit, for example, analyzes a user's social media activity and acquires related invoices. Social media activity can be analyzed, for example, by analyzing post content, number of followers, engagement rate, etc. For example, if a user posts on social media that they have used a specific service, invoices related to that service can be acquired preferentially. If a user posts on social media that they have attended a specific event, invoices related to that event can be acquired preferentially. If a user posts on social media that they have purchased a specific product, invoices related to that product can be acquired preferentially. This makes it possible to acquire related invoices based on the user's social media activity. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the user's social media data into a generation AI and cause the generation AI to acquire related invoices.

[0039] The extraction unit can apply the optimal extraction algorithm depending on the layout and format of the invoice when extracting text data using AI-OCR. For example, when extracting text data using AI-OCR, the extraction unit applies the optimal extraction algorithm depending on the layout and format of the invoice. Because the layout and format of invoices vary from invoice to invoice, it is important to select an appropriate extraction algorithm. For example, when the invoice layout differs, an appropriate extraction algorithm can be automatically selected. The optimal extraction algorithm can be applied to invoices with different formats. For handwritten invoices, an extraction algorithm specialized for handwritten character recognition can be applied. This improves extraction accuracy by applying the optimal extraction algorithm depending on the layout and format of the invoice. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input invoice layout and format data to the generation AI and have the generation AI apply the optimal extraction algorithm.

[0040] The extraction unit may have a function for improving the recognition accuracy of handwritten characters and special characters when extracting text data using AI-OCR. The extraction unit may have a function for improving the recognition accuracy of handwritten characters and special characters when extracting text data using AI-OCR. Because handwritten characters and special characters are more difficult to recognize than regular printed characters, improving recognition accuracy is important. For example, to improve the recognition accuracy of handwritten characters, the handwritten character recognition algorithm may be enhanced. For example, a recurrent neural network (RNN) or a convolutional neural network (CNN) may be used as the handwritten character recognition algorithm. Furthermore, to improve the recognition accuracy of special characters, a special character recognition algorithm may be added. For example, a support vector machine (SVM) or a random forest may be used as the special character recognition algorithm. Furthermore, to improve recognition accuracy, the AI-OCR training data may be increased to improve accuracy. This improves the recognition accuracy of handwritten characters and special characters, thereby enabling accurate data extraction. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on handwritten characters and special characters into the generation AI and have the generation AI improve its recognition accuracy.

[0041] The extraction unit can improve extraction accuracy by taking into account the issuer and issuance date of the invoice when extracting text data using AI-OCR. For example, the extraction unit can improve extraction accuracy by taking into account the issuer and issuance date of the invoice when extracting text data using AI-OCR. The issuer and issuance date of the invoice are important information for accurately understanding the contents of the invoice. For example, an extraction algorithm compatible with a specific format can be applied based on the issuer of the invoice. An extraction algorithm compatible with the latest format can be applied based on the issuance date of the invoice. This improves extraction accuracy by taking into account the issuer and issuance date of the invoice. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the issuer and issuance date of the invoice into the generation AI and cause the generation AI to improve extraction accuracy.

[0042] The extraction unit can improve the accuracy of extraction by referring to related literature and databases when extracting text data using AI-OCR. For example, the extraction unit can improve the accuracy of extraction by referring to related literature and databases when extracting text data using AI-OCR. The related literature and databases are used as reference information for accurately understanding the contents of an invoice. For example, the accuracy of the extraction algorithm can be improved by referring to related literature. The accuracy of the extraction algorithm can be improved by referring to a database. As a result, the extraction accuracy is improved by referring to related literature and databases. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input data from related literature and databases into the generation AI and cause the generation AI to improve the extraction accuracy.

[0043] The analysis unit can apply different analysis algorithms depending on the content and category of the invoice when the generation AI analyzes the text data. For example, when the generation AI analyzes the text data, the analysis unit applies different analysis algorithms depending on the content and category of the invoice. Since the content and category of an invoice differ for each invoice, it is important to select an appropriate analysis algorithm. For example, an optimal analysis algorithm can be selected depending on the content of the invoice. Different analysis algorithms can be applied depending on the category of the invoice. This improves the accuracy of analysis by applying the optimal analysis algorithm depending on the content and category of the invoice. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the content and category of the invoice into the generation AI and cause the generation AI to apply the optimal analysis algorithm.

[0044] The analysis unit can improve the analysis accuracy by referring to past analysis results when analyzing text data using the generation AI. For example, when analyzing text data using the generation AI, the analysis unit improves the analysis accuracy by referring to past analysis results. Past analysis results are used as reference information for accurately understanding the contents of invoices. For example, the accuracy of the analysis algorithm can be improved by referring to past analysis results. An optimal analysis algorithm can be selected based on past analysis results. In this way, the analysis accuracy is improved by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input data of past analysis results into the generation AI and cause the generation AI to improve the analysis accuracy.

[0045] The analysis unit can improve the accuracy of analysis by taking into account the issuer and issuance date of the invoice when analyzing text data using the generation AI. For example, the analysis unit improves the accuracy of analysis by taking into account the issuer and issuance date of the invoice when analyzing text data using the generation AI. The issuer and issuance date of the invoice are important information for accurately understanding the contents of the invoice. For example, an analysis algorithm corresponding to a specific format can be applied based on the issuer of the invoice. An analysis algorithm corresponding to the latest format can be applied based on the issuance date of the invoice. This improves the analysis accuracy by taking into account the issuer and issuance date of the invoice. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the issuer and issuance date of the invoice into the generation AI and cause the generation AI to improve the analysis accuracy.

[0046] The analysis unit can improve the accuracy of the analysis by referring to related literature and databases when analyzing text data using the generation AI. For example, the analysis unit can improve the accuracy of the analysis by referring to related literature and databases when analyzing text data using the generation AI. The related literature and databases are used as reference information for accurately understanding the contents of the invoice. For example, the accuracy of the analysis algorithm can be improved by referring to related literature. The accuracy of the analysis algorithm can be improved by referring to databases. Thus, by referring to related literature and databases, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data from related literature and databases into the generation AI and cause the generation AI to improve the analysis accuracy.

[0047] The registration unit can apply different registration algorithms depending on the importance and category of the data when registering the data in the database. For example, the registration unit applies different registration algorithms depending on the importance and category of the data when registering the data in the database. Since the importance and category of data differ for each piece of data, it is important to select an appropriate registration algorithm. For example, an optimal registration algorithm can be selected depending on the importance of the data. Different registration algorithms can be applied depending on the category of the data. This improves registration accuracy by applying the optimal registration algorithm depending on the importance and category of the data. Some or all of the above-mentioned processing in the registration unit may be performed using, for example, AI, or may be performed without using AI. For example, the registration unit can input data on the importance and category of the data to the generation AI and cause the generation AI to apply the optimal registration algorithm.

[0048] The registration unit can improve registration accuracy by referring to past registration data when registering data in the database. The registration unit can improve registration accuracy by referring to past registration data, for example, when registering data in the database. The past registration data is used as reference information for accurately registering data. For example, the accuracy of the registration algorithm can be improved by referring to the past registration data. An optimal registration algorithm can be selected based on the past registration data. In this way, registration accuracy is improved by referring to the past registration data. Some or all of the above-mentioned processing in the registration unit can be performed using, for example, AI, or can be performed without using AI. For example, the registration unit can input data of the past registration data into the generation AI and cause the generation AI to improve registration accuracy.

[0049] The registration unit can improve the accuracy of registration by taking into account the issuer and publication date of the data when registering the data in the database. For example, the registration unit improves the accuracy of registration by taking into account the issuer and publication date of the data when registering the data in the database. The issuer and publication date of the data are important information for accurately registering data. For example, a registration algorithm corresponding to a specific format can be applied based on the issuer of the data. A registration algorithm corresponding to the latest format can be applied based on the publication date of the data. In this way, by taking into account the issuer and publication date of the data, the registration accuracy is improved. Some or all of the above-mentioned processing in the registration unit may be performed using, for example, AI, or may be performed without using AI. For example, the registration unit can input data on the issuer and publication date of the data to the generation AI and cause the generation AI to improve the registration accuracy.

[0050] The registration unit can improve the accuracy of registration by referring to related literature and databases when registering data in the database. The registration unit, for example, improves the accuracy of registration by referring to related literature and databases when registering data in the database. The related literature and databases are used as reference information for accurately registering data. For example, the accuracy of the registration algorithm can be improved by referring to related literature. The accuracy of the registration algorithm can be improved by referring to databases. As a result, the registration accuracy is improved by referring to related literature and databases. Some or all of the above-mentioned processing in the registration unit may be performed using, for example, AI, or may be performed without using AI. For example, the registration unit can input data from related literature and databases into the generation AI and cause the generation AI to improve the registration accuracy.

[0051] When creating a payment schedule, the notification unit can create an optimal schedule by referring to past payment history. When creating a payment schedule, the notification unit, for example, creates an optimal schedule by referring to past payment history. The past payment history is used as reference information for determining payment priorities. For example, an optimal payment schedule can be created by referring to past payment history. Payment priorities can be determined based on the past payment history. In this way, an optimal payment schedule can be created by referring to the past payment history. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can input data of past payment history into a generation AI and cause the generation AI to create an optimal schedule.

[0052] The notification unit can apply different notification methods depending on the importance and payment deadline of an invoice when creating a payment schedule. For example, the notification unit applies different notification methods depending on the importance and payment deadline of an invoice when creating a payment schedule. The importance and payment deadline of an invoice are important information for determining the priority of notifications. For example, the optimal notification method can be selected depending on the importance of the invoice. Different notification methods can be applied depending on the payment deadline. This improves notification accuracy by applying the optimal notification method depending on the importance and payment deadline of the invoice. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input data on the importance and payment deadline of an invoice into the generation AI and have the generation AI apply the optimal notification method.

[0053] The notification unit can select the optimal notification method by taking into account the user's geographical location information when creating a payment schedule. For example, when creating a payment schedule, the notification unit selects the optimal notification method by taking into account the user's geographical location information. The geographical location information can be obtained using, for example, GPS data, an IP address, a location information service, etc. For example, if the user is in a specific area, notifications related to that area can be displayed preferentially. If the user is on a business trip, notifications related to the business trip destination can be displayed preferentially. If the user is at home, notifications related to the home can be displayed preferentially. This improves notification accuracy by selecting the optimal notification method based on the user's geographical location information. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's geographical location information to a generation AI and cause the generation AI to select the optimal notification method.

[0054] The notification unit can improve the accuracy of notifications by referring to related literature and databases when creating a payment schedule. The notification unit can improve the accuracy of notifications by referring to related literature and databases, for example, when creating a payment schedule. The related literature and databases are used as reference information for improving the accuracy of notifications. For example, the accuracy of the notification algorithm can be improved by referring to related literature. The accuracy of the notification algorithm can be improved by referring to a database. As a result, notification accuracy is improved by referring to related literature and databases. Some or all of the above-mentioned processing in the notification unit can be performed using AI, for example, or without using AI. For example, the notification unit can input data from related literature and databases into the generation AI and cause the generation AI to improve the accuracy of notifications.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The acquisition unit can select the optimal acquisition method based on the type and issuer of the invoice. For example, for electronic invoices, the acquisition unit can acquire image data directly from email. For paper invoices, the acquisition unit can acquire high-resolution image data using a scanner. For invoices that can be downloaded from a web portal, the acquisition unit can automatically acquire image data using an API. This allows the acquisition unit to acquire image data in the optimal way depending on the type and issuer of the invoice.

[0057] The acquisition unit can have a function to automatically adjust the resolution and quality of the image. For example, when low-resolution image data is acquired, the acquisition unit can automatically perform processing to improve the resolution. Super-resolution technology can be used to improve the resolution. Also, when the image quality is low, the acquisition unit can perform noise removal and contrast adjustment to make the image easier to read. Furthermore, when the image is distorted, the acquisition unit can automatically correct it to acquire accurate data. As a result, accurate data can be acquired by automatically adjusting the image resolution and quality.

[0058] The acquisition unit can prioritize acquisition of highly relevant invoices in consideration of the user's geographical location information. For example, if the user is in a specific area, it can prioritize acquisition of invoices related to that area. If the user is on a business trip, it can prioritize acquisition of invoices related to the business trip destination. If the user is at home, it can prioritize acquisition of invoices related to the home. This makes it possible to prioritize acquisition of highly relevant invoices based on the user's geographical location information.

[0059] The acquisition unit can analyze the user's social media activity and acquire related invoices. For example, if a user posts on social media that they have used a specific service, invoices related to that service can be acquired preferentially. If a user posts on social media that they have attended a specific event, invoices related to that event can be acquired preferentially. If a user posts on social media that they have purchased a specific product, invoices related to that product can be acquired preferentially. In this way, related invoices can be acquired based on the user's social media activity.

[0060] When extracting text data using AI-OCR, the extraction unit can apply the optimal extraction algorithm depending on the invoice layout and format. For example, if the invoice layout is different, the appropriate extraction algorithm can be automatically selected. The optimal extraction algorithm can be applied to invoices with different formats. For handwritten invoices, an extraction algorithm specialized for handwritten character recognition can be applied. This improves extraction accuracy by applying the optimal extraction algorithm depending on the invoice layout and format.

[0061] The extraction unit can be equipped with a function to improve the recognition accuracy of handwritten characters and special characters when extracting text data using AI-OCR. For example, the handwritten character recognition algorithm can be enhanced to improve the recognition accuracy of handwritten characters. Recurrent neural networks (RNN) and convolutional neural networks (CNN) can be used as the handwritten character recognition algorithm. In addition, a special character recognition algorithm can be added to improve the recognition accuracy of special characters. Support vector machines (SVM) and random forests can be used as the special character recognition algorithm. This improves the recognition accuracy of handwritten characters and special characters, allowing for accurate data extraction.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The acquisition unit acquires image data of the invoice. Invoice image data may be in any format, including, but not limited to, PDF, JPEG, or PNG. The acquisition unit acquires the image data of the invoice using, for example, a scanner or a camera. A scanner can acquire image data at high resolution, while a camera can easily acquire image data. Step 2: The extraction unit uses AI-OCR to convert the image data acquired by the acquisition unit into text data. AI-OCR can use technologies such as Tesseract, Google Cloud Vision, and Amazon Textract. The AI-OCR extracts text data from the image data and passes it to the extraction unit. For example, it extracts information such as the invoice issue date, amount, and payment deadline. Step 3: The analysis unit uses the generation AI to analyze the text data received from the extraction unit and classify and organize the contents of the invoice. The generation AI can use technologies such as GPT-4 and Geminir. The generation AI analyzes the text data and classifies and organizes the contents of the invoice. For example, it registers information such as the invoice issue date, amount, and payment deadline in a database. Step 4: The registration unit registers the classified and organized data received from the analysis unit in a database. The database may be, for example, a relational database, a NoSQL database, etc., but is not limited to such examples. The database can efficiently store and search data. Step 5: The notification department creates a payment schedule and notifies relevant departments when the payment deadline approaches. The notification department can send notifications using methods such as email, SMS, and push notifications. This allows the invoice processing system to process invoices efficiently and reduce manual errors.

[0064] (Example 2) An invoice processing system according to an embodiment of the present invention acquires image data of an invoice, converts it into text data using AI-OCR, classifies and organizes the invoice content using a generation AI, registers it in a database, creates a payment schedule, and notifies relevant departments. This system significantly improves the efficiency of invoice processing and reduces manual errors. For example, an acquisition unit is provided to acquire image data of the invoice and input the data into the AI-OCR. Image data of the invoice is acquired using a scanner or camera and input into the acquisition unit. This data is converted into text data by the AI-OCR. Next, an extraction unit is provided in which the AI-OCR extracts the text data and passes it to the generation AI. The AI-OCR extracts text data from the image data of the invoice and passes it to the extraction unit. For example, information such as the invoice issue date, amount, and payment deadline is extracted. The generation AI has an analysis unit that analyzes the text data and classifies and organizes the invoice content. The generation AI analyzes the text data received from the extraction unit and classifies and organizes the invoice content. For example, information such as the invoice issue date, amount, and payment deadline is registered in a database. Finally, a registration unit is provided to register the analysis results in a database, and a notification unit is provided to create a payment schedule and notify relevant departments. The analysis unit passes the classified and organized data to the registration unit, which then registers it in the database. The notification unit creates a payment schedule and notifies relevant departments. For example, by notifying relevant departments when the payment deadline is approaching, payment delays can be prevented. This allows the invoice processing system to process invoices efficiently and reduce manual errors.

[0065] The invoice processing system according to the embodiment includes an acquisition unit, an extraction unit, an analysis unit, a registration unit, and a notification unit. The acquisition unit acquires image data of an invoice. Invoice image data may be in formats such as PDF, JPEG, and PNG, but is not limited to these. The acquisition unit acquires the image data of an invoice using, for example, a scanner or a camera. A scanner can acquire image data at high resolution, while a camera can easily acquire image data. The extraction unit converts the image data acquired by the acquisition unit into text data using AI-OCR. The AI-OCR may use technologies such as Tesseract, Google Cloud Vision, and Amazon Textract. The AI-OCR extracts text data from the image data and passes it to the extraction unit. For example, the AI-OCR extracts information such as the invoice issue date, amount, and payment deadline. The analysis unit uses a generation AI to analyze the text data received from the extraction unit and classify and organize the contents of the invoice. The generation AI may use technologies such as GPT-4 and Gemini. The generation AI analyzes the text data and classifies and organizes the contents of the invoice. For example, the registration unit registers information such as the invoice issue date, amount, and payment deadline in a database. The registration unit registers the classified and organized data received from the analysis unit in a database. Examples of databases include, but are not limited to, relational databases and NoSQL databases. Databases can efficiently store and search data. The notification unit creates a payment schedule and notifies relevant departments when the payment deadline is approaching. The notification unit can send notifications using methods such as email, SMS, and push notification. This allows the invoice processing system to process invoices efficiently and reduce manual errors.

[0066] The acquisition unit can acquire image data of an invoice using a scanner or a camera. The acquisition unit can acquire image data of an invoice using, for example, a scanner. The scanner can acquire image data at high resolution. For example, the scanner can acquire image data at a resolution of 300 dpi or higher. The acquisition unit can also acquire image data of an invoice using a camera. The camera can easily acquire image data. For example, the camera can be a camera installed in a smartphone or tablet. This allows for efficient acquisition of image data of an invoice. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input image data acquired by a scanner or camera to a generation AI and cause the generation AI to acquire the image data.

[0067] The extraction unit can extract information such as the invoice issue date, amount, and payment deadline using AI-OCR. The extraction unit extracts information such as the invoice issue date, amount, and payment deadline using, for example, AI-OCR. AI-OCR is a technology for extracting text data from image data, and can use technologies such as Tesseract, Google Cloud Vision, and Amazon Textract. For example, AI-OCR extracts the invoice issue date. The issue date is often listed at the top of the invoice and is extracted based on a date format. For example, formats such as "YYYY / MM / DD" or "DD-MM-YYYY" are used. Next, AI-OCR extracts the invoice amount. The amount is often listed in the center of the invoice and is extracted based on currency symbols and numbers. For example, formats such as "$1000" or "¥5000" are used. Finally, AI-OCR extracts the invoice payment deadline. The payment deadline is often listed at the bottom of the invoice and is extracted based on a date format. For example, formats such as "Payment due date: YYYY / MM / DD" or "Payment due date: DD-MM-YYYY" are used. This allows important information on the invoice to be accurately extracted. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit may input text data extracted by AI-OCR into a generation AI and have the generation AI extract the text data.

[0068] The analysis unit can analyze the text data received from the extraction unit using the generation AI and classify and organize the contents of the invoice. The analysis unit, for example, uses the generation AI to analyze the text data received from the extraction unit. The generation AI can use technologies such as GPT-4 and Gemini. The generation AI analyzes the text data and classifies and organizes the contents of the invoice. For example, the generation AI analyzes information such as the invoice issue date, amount, and payment deadline, and converts it into a format for registration in a database. Next, the generation AI classifies the contents of the invoice into categories. Categories include, for example, "electricity bill," "water bill," and "gas bill." The generation AI analyzes the contents of the invoice and classifies them into the appropriate category. Finally, the generation AI organizes the contents of the invoice. Organization includes, for example, dividing the data by invoice item and converting it into a format for registration in a database. This allows the contents of the invoice to be efficiently classified and organized. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can convert the text data analyzed by the generation AI into a format for registration in a database, and have the generation AI perform classification and organization.

[0069] The registration unit can register the categorized and organized data received from the analysis unit in a database. The registration unit, for example, registers the categorized and organized data received from the analysis unit in a database. Examples of databases include, but are not limited to, relational databases and NoSQL databases. Relational databases manage data in a table format and allow data search and manipulation using SQL queries. NoSQL databases have a schema-less, flexible data model and can efficiently process large amounts of data. The registration unit converts the data received from the analysis unit into an appropriate format and registers it in a database. For example, information such as the invoice issue date, amount, and payment deadline is registered in the corresponding fields of the database. This allows the categorized and organized data to be efficiently registered in the database. Some or all of the above-described processing in the registration unit may be performed using, for example, AI, or may be performed without AI. For example, the registration unit may register the data converted by the generation AI in a database and have the generation AI perform the registration process.

[0070] The notification unit can create a payment schedule and notify relevant departments when the payment deadline approaches. For example, the notification unit creates a payment schedule and notifies relevant departments when the payment deadline approaches. The payment schedule is created based on the invoice payment deadline. For example, if the payment deadline is one week from now, the notification unit creates a payment schedule and notifies relevant departments three days before the payment deadline. The notification unit can send notifications using methods such as email, SMS, and push notification. Email can provide detailed notification content and convey clear instructions to relevant departments. SMS can send quick notifications with short messages and is suitable for urgent notifications. Push notifications can send notifications in real time via a mobile application, providing high immediacy. This can prevent payment delays. Some or all of the above-mentioned processing in the notification unit can be performed using, for example, AI, or without AI. For example, the notification unit can send notifications based on the payment schedule created by the generation AI and have the generation AI execute the notification processing.

[0071] The acquisition unit can estimate a user's emotions and adjust the timing of acquiring invoice image data based on the estimated user emotions. The acquisition unit, for example, estimates a user's emotions and adjusts the timing of acquiring invoice image data based on the estimated user emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes a user's facial expressions captured by a camera to estimate emotions. For example, if a user is stressed, the acquisition timing can be delayed to acquire the image data when the user is relaxed. Voice analysis is a technology that analyzes the tone and speed of a user's voice to estimate emotions. For example, if a user is in a hurry, the invoice image data can be acquired immediately and processing can be started quickly. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if a user is relaxed, the acquisition timing can be adjusted to reduce the user's workload. This allows the invoice image data to be acquired at the optimal timing depending on the user's emotions. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or without AI. For example, the acquisition unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the acquisition timing based on the emotion.

[0072] The acquisition unit can select the optimal acquisition method based on the type and issuer of the invoice. The acquisition unit selects the optimal acquisition method based on, for example, the type and issuer of the invoice. Invoice types include, for example, electronic invoices, paper invoices, and invoices downloadable from a web portal. In the case of electronic invoices, the acquisition unit can acquire image data directly from email. In the case of paper invoices, the acquisition unit can acquire high-resolution image data using a scanner. In the case of invoices downloadable from a web portal, the acquisition unit can automatically acquire image data using an API. The issuer includes, for example, the company name, industry, and invoice format. The acquisition unit selects the optimal acquisition method based on the issuer. For example, a dedicated acquisition method can be used for invoices from a specific company. This allows image data to be acquired using the optimal method depending on the type and issuer of the invoice. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input data on the type and issuer of the invoice into the generation AI and cause the generation AI to select the optimal acquisition method.

[0073] The acquisition unit may have a function for automatically adjusting the image resolution and quality. The acquisition unit may, for example, have a function for automatically adjusting the image resolution and quality. Because image resolution and quality significantly affect the accuracy of invoice reading, it is important to adjust them appropriately. For example, if low-resolution image data is acquired, the acquisition unit may automatically improve the resolution. To improve the resolution, for example, super-resolution technology may be used. Furthermore, if the image quality is low, the acquisition unit may perform noise removal and contrast adjustment to make the image easier to read. For noise removal, for example, a Gaussian filter or a median filter may be used. For contrast adjustment, for example, histogram equalization or gamma correction may be used. Furthermore, if the image is distorted, the acquisition unit may automatically correct it to obtain accurate data. For distortion correction, for example, a geometric transformation or a homography transformation may be used. This allows accurate data to be obtained by automatically adjusting the image resolution and quality. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI, or may be performed without AI. For example, the acquisition unit can input image data into the generation AI and have the generation AI adjust the resolution and quality.

[0074] The acquisition unit can estimate the user's emotions and determine the priority of invoices to be acquired based on the estimated user emotions. The acquisition unit, for example, estimates the user's emotions and determines the priority of invoices to be acquired based on the estimated user emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes the user's facial expressions captured by a camera to estimate emotions. For example, if a user is stressed, less important invoices can be postponed and more important invoices can be acquired first. Voice analysis is a technology that analyzes the tone and speed of a user's voice to estimate emotions. For example, if a user is in a hurry, invoices with upcoming due dates can be acquired first. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if a user is relaxed, all invoices can be acquired equally. This enables efficient processing by determining the priority of invoices according to the user's emotions. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or without AI. For example, the acquisition unit can input the user's emotion data into the generation AI and cause the generation AI to determine priorities based on emotions.

[0075] The acquisition unit can prioritize acquisition of highly relevant invoices by taking into account the user's geographical location information. The acquisition unit, for example, prioritizes acquisition of highly relevant invoices by taking into account the user's geographical location information. Geographical location information can be acquired using, for example, GPS data, an IP address, a location information service, etc. For example, if the user is in a specific area, invoices related to that area can be prioritized. If the user is on a business trip, invoices related to the business trip destination can be prioritized. If the user is at home, invoices related to the home can be prioritized. This makes it possible to prioritize acquisition of highly relevant invoices based on the user's geographical location information. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the user's geographical location information to the generation AI and cause the generation AI to prioritize acquisition of highly relevant invoices.

[0076] The acquisition unit can analyze a user's social media activity and acquire related invoices. The acquisition unit, for example, analyzes a user's social media activity and acquires related invoices. Social media activity can be analyzed, for example, by analyzing post content, number of followers, engagement rate, etc. For example, if a user posts on social media that they have used a specific service, invoices related to that service can be acquired preferentially. If a user posts on social media that they have attended a specific event, invoices related to that event can be acquired preferentially. If a user posts on social media that they have purchased a specific product, invoices related to that product can be acquired preferentially. This makes it possible to acquire related invoices based on the user's social media activity. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the user's social media data into a generation AI and cause the generation AI to acquire related invoices.

[0077] The extraction unit can estimate a user's emotions and prioritize the text data to be extracted based on the estimated user emotions. The extraction unit, for example, estimates a user's emotions and prioritizes the text data to be extracted based on the estimated user emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes a user's facial expressions captured by a camera to estimate emotions. For example, if a user is feeling stressed, text data of high importance can be preferentially extracted. Voice analysis is a technology that analyzes the tone and speed of a user's voice to estimate emotions. For example, if a user is in a hurry, text data with an upcoming payment deadline can be preferentially extracted. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if a user is relaxed, all text data can be extracted equally. This allows efficient processing by prioritizing text data according to the user's emotions. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without AI. For example, the extraction unit can input user emotion data into the generation AI and have the generation AI determine priorities based on emotions.

[0078] The extraction unit can apply the optimal extraction algorithm depending on the layout and format of the invoice when extracting text data using AI-OCR. For example, when extracting text data using AI-OCR, the extraction unit applies the optimal extraction algorithm depending on the layout and format of the invoice. Because the layout and format of invoices vary from invoice to invoice, it is important to select an appropriate extraction algorithm. For example, when the invoice layout differs, an appropriate extraction algorithm can be automatically selected. The optimal extraction algorithm can be applied to invoices with different formats. For handwritten invoices, an extraction algorithm specialized for handwritten character recognition can be applied. This improves extraction accuracy by applying the optimal extraction algorithm depending on the layout and format of the invoice. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input invoice layout and format data to the generation AI and have the generation AI apply the optimal extraction algorithm.

[0079] The extraction unit may have a function for improving the recognition accuracy of handwritten characters and special characters when extracting text data using AI-OCR. The extraction unit may have a function for improving the recognition accuracy of handwritten characters and special characters when extracting text data using AI-OCR. Because handwritten characters and special characters are more difficult to recognize than regular printed characters, improving recognition accuracy is important. For example, to improve the recognition accuracy of handwritten characters, the handwritten character recognition algorithm may be enhanced. For example, a recurrent neural network (RNN) or a convolutional neural network (CNN) may be used as the handwritten character recognition algorithm. Furthermore, to improve the recognition accuracy of special characters, a special character recognition algorithm may be added. For example, a support vector machine (SVM) or a random forest may be used as the special character recognition algorithm. Furthermore, to improve recognition accuracy, the AI-OCR training data may be increased to improve accuracy. This improves the recognition accuracy of handwritten characters and special characters, thereby enabling accurate data extraction. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on handwritten characters and special characters into the generation AI and have the generation AI improve its recognition accuracy.

[0080] The extraction unit can estimate a user's emotion and adjust the display method of the extracted text data based on the estimated user emotion. The extraction unit, for example, estimates a user's emotion and adjusts the display method of the extracted text data based on the estimated user emotion. The user's emotion can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes a user's facial expression captured by a camera to estimate their emotion. For example, if a user is feeling stressed, a simple and highly visible display method can be provided. Voice analysis is a technology that analyzes the tone and speed of a user's voice to estimate their emotion. For example, if a user is relaxed, a display method including detailed information can be provided. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if a user is in a hurry, a display method that focuses on the main points can be provided. This improves visibility by adjusting the display method of the text data according to the user's emotion. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or without AI. For example, the extraction unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0081] The extraction unit can improve extraction accuracy by taking into account the issuer and issuance date of the invoice when extracting text data using AI-OCR. For example, the extraction unit can improve extraction accuracy by taking into account the issuer and issuance date of the invoice when extracting text data using AI-OCR. The issuer and issuance date of the invoice are important information for accurately understanding the contents of the invoice. For example, an extraction algorithm compatible with a specific format can be applied based on the issuer of the invoice. An extraction algorithm compatible with the latest format can be applied based on the issuance date of the invoice. This improves extraction accuracy by taking into account the issuer and issuance date of the invoice. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the issuer and issuance date of the invoice into the generation AI and cause the generation AI to improve extraction accuracy.

[0082] The extraction unit can improve the accuracy of extraction by referring to related literature and databases when extracting text data using AI-OCR. For example, the extraction unit can improve the accuracy of extraction by referring to related literature and databases when extracting text data using AI-OCR. The related literature and databases are used as reference information for accurately understanding the contents of an invoice. For example, the accuracy of the extraction algorithm can be improved by referring to related literature. The accuracy of the extraction algorithm can be improved by referring to a database. As a result, the extraction accuracy is improved by referring to related literature and databases. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input data from related literature and databases into the generation AI and cause the generation AI to improve the extraction accuracy.

[0083] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions and adjusts the display method of the analysis results based on the estimated user emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes the user's facial expressions captured by a camera to estimate emotions. For example, if a user is feeling stressed, a simple and highly visible display method can be provided. Voice analysis is a technology that analyzes the tone and speed of the user's voice to estimate emotions. For example, if a user is relaxed, a display method including detailed information can be provided. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if a user is in a hurry, a display method that focuses on the main points can be provided. This improves visibility by adjusting the display method of the analysis results according to the user's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0084] The analysis unit can apply different analysis algorithms depending on the content and category of the invoice when the generation AI analyzes the text data. For example, when the generation AI analyzes the text data, the analysis unit applies different analysis algorithms depending on the content and category of the invoice. Since the content and category of an invoice differ for each invoice, it is important to select an appropriate analysis algorithm. For example, an optimal analysis algorithm can be selected depending on the content of the invoice. Different analysis algorithms can be applied depending on the category of the invoice. This improves the accuracy of analysis by applying the optimal analysis algorithm depending on the content and category of the invoice. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the content and category of the invoice into the generation AI and cause the generation AI to apply the optimal analysis algorithm.

[0085] The analysis unit can improve the analysis accuracy by referring to past analysis results when analyzing text data using the generation AI. For example, when analyzing text data using the generation AI, the analysis unit improves the analysis accuracy by referring to past analysis results. Past analysis results are used as reference information for accurately understanding the contents of invoices. For example, the accuracy of the analysis algorithm can be improved by referring to past analysis results. An optimal analysis algorithm can be selected based on past analysis results. In this way, the analysis accuracy is improved by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input data of past analysis results into the generation AI and cause the generation AI to improve the analysis accuracy.

[0086] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes the user's facial expressions captured by a camera to estimate emotions. For example, if the user is feeling stressed, analysis results with high importance can be displayed preferentially. Voice analysis is a technology that analyzes the tone and speed of the user's voice to estimate emotions. For example, if the user is in a hurry, analysis results with upcoming payment deadlines can be displayed preferentially. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if the user is relaxed, all analysis results can be displayed equally. This enables efficient processing by prioritizing the analysis results according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's emotional data into the generation AI and have the generation AI determine priorities based on emotions.

[0087] The analysis unit can improve the accuracy of analysis by taking into account the issuer and issuance date of the invoice when analyzing text data using the generation AI. For example, the analysis unit improves the accuracy of analysis by taking into account the issuer and issuance date of the invoice when analyzing text data using the generation AI. The issuer and issuance date of the invoice are important information for accurately understanding the contents of the invoice. For example, an analysis algorithm corresponding to a specific format can be applied based on the issuer of the invoice. An analysis algorithm corresponding to the latest format can be applied based on the issuance date of the invoice. This improves the analysis accuracy by taking into account the issuer and issuance date of the invoice. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the issuer and issuance date of the invoice into the generation AI and cause the generation AI to improve the analysis accuracy.

[0088] The analysis unit can improve the accuracy of the analysis by referring to related literature and databases when analyzing text data using the generation AI. For example, the analysis unit can improve the accuracy of the analysis by referring to related literature and databases when analyzing text data using the generation AI. The related literature and databases are used as reference information for accurately understanding the contents of the invoice. For example, the accuracy of the analysis algorithm can be improved by referring to related literature. The accuracy of the analysis algorithm can be improved by referring to databases. Thus, by referring to related literature and databases, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data from related literature and databases into the generation AI and cause the generation AI to improve the analysis accuracy.

[0089] The registration unit can estimate the user's emotion and adjust the registration method to the database based on the estimated user's emotion. The registration unit, for example, estimates the user's emotion and adjusts the registration method to the database based on the estimated user's emotion. The user's emotion can be estimated using, for example, facial expression recognition, voice analysis, questionnaire results, etc. Facial expression recognition is a technology that analyzes the user's facial expression captured by a camera to estimate the emotion. For example, if the user is feeling stressed, a simple and quick registration method can be provided. Voice analysis is a technology that analyzes the tone and speed of the user's voice to estimate the emotion. For example, if the user is relaxed, a registration method including detailed information can be provided. The questionnaire results are a method of estimating the emotion based on the content of the questionnaire answered by the user. For example, if the user is in a hurry, a registration method that focuses on the main points can be provided. This allows efficient registration by adjusting the registration method to the database according to the user's emotion. Some or all of the above-mentioned processing in the registration unit may be performed, for example, using AI or without AI. For example, the registration unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the registration method based on the emotion.

[0090] The registration unit can apply different registration algorithms depending on the importance and category of the data when registering the data in the database. For example, the registration unit applies different registration algorithms depending on the importance and category of the data when registering the data in the database. Since the importance and category of data differ for each piece of data, it is important to select an appropriate registration algorithm. For example, an optimal registration algorithm can be selected depending on the importance of the data. Different registration algorithms can be applied depending on the category of the data. This improves registration accuracy by applying the optimal registration algorithm depending on the importance and category of the data. Some or all of the above-mentioned processing in the registration unit may be performed using, for example, AI, or may be performed without using AI. For example, the registration unit can input data on the importance and category of the data to the generation AI and cause the generation AI to apply the optimal registration algorithm.

[0091] The registration unit can improve registration accuracy by referring to past registration data when registering data in the database. The registration unit can improve registration accuracy by referring to past registration data, for example, when registering data in the database. The past registration data is used as reference information for accurately registering data. For example, the accuracy of the registration algorithm can be improved by referring to the past registration data. An optimal registration algorithm can be selected based on the past registration data. In this way, registration accuracy is improved by referring to the past registration data. Some or all of the above-mentioned processing in the registration unit can be performed using, for example, AI, or can be performed without using AI. For example, the registration unit can input data of the past registration data into the generation AI and cause the generation AI to improve registration accuracy.

[0092] The registration unit can estimate the user's emotions and determine the priority of data registration in the database based on the estimated user emotions. The registration unit, for example, estimates the user's emotions and determines the priority of data registration in the database based on the estimated user emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes the user's facial expressions captured by a camera to estimate emotions. For example, if the user is feeling stressed, data of high importance can be registered preferentially. Voice analysis is a technology that analyzes the tone and speed of the user's voice to estimate emotions. For example, if the user is in a hurry, data with an upcoming payment deadline can be registered preferentially. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if the user is relaxed, all data can be registered equally. This enables efficient processing by determining the priority of data registration in the database based on the user's emotions. Some or all of the above-described processing in the registration unit may be performed using, for example, AI, or without AI. For example, the registration unit can input the user's emotion data into the generation AI and cause the generation AI to determine priorities based on emotions.

[0093] The registration unit can improve the accuracy of registration by taking into account the issuer and publication date of the data when registering the data in the database. For example, the registration unit improves the accuracy of registration by taking into account the issuer and publication date of the data when registering the data in the database. The issuer and publication date of the data are important information for accurately registering data. For example, a registration algorithm corresponding to a specific format can be applied based on the issuer of the data. A registration algorithm corresponding to the latest format can be applied based on the publication date of the data. In this way, by taking into account the issuer and publication date of the data, the registration accuracy is improved. Some or all of the above-mentioned processing in the registration unit may be performed using, for example, AI, or may be performed without using AI. For example, the registration unit can input data on the issuer and publication date of the data to the generation AI and cause the generation AI to improve the registration accuracy.

[0094] The registration unit can improve the accuracy of registration by referring to related literature and databases when registering data in the database. The registration unit, for example, improves the accuracy of registration by referring to related literature and databases when registering data in the database. The related literature and databases are used as reference information for accurately registering data. For example, the accuracy of the registration algorithm can be improved by referring to related literature. The accuracy of the registration algorithm can be improved by referring to databases. As a result, the registration accuracy is improved by referring to related literature and databases. Some or all of the above-mentioned processing in the registration unit may be performed using, for example, AI, or may be performed without using AI. For example, the registration unit can input data from related literature and databases into the generation AI and cause the generation AI to improve the registration accuracy.

[0095] The notification unit can estimate a user's emotions and adjust the notification display method based on the estimated user's emotions. For example, the notification unit can estimate a user's emotions and adjust the notification display method based on the estimated user's emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes a user's facial expressions captured by a camera to estimate emotions. For example, if a user is feeling stressed, a simple, highly visible display method can be provided. Voice analysis is a technology that analyzes the tone and speed of a user's voice to estimate emotions. For example, if a user is relaxed, a display method including detailed information can be provided. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if a user is in a hurry, a display method that focuses on the main points can be provided. This improves visibility by adjusting the notification display method according to the user's emotions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0096] When creating a payment schedule, the notification unit can create an optimal schedule by referring to past payment history. When creating a payment schedule, the notification unit, for example, creates an optimal schedule by referring to past payment history. The past payment history is used as reference information for determining payment priorities. For example, an optimal payment schedule can be created by referring to past payment history. Payment priorities can be determined based on the past payment history. In this way, an optimal payment schedule can be created by referring to the past payment history. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can input data of past payment history into a generation AI and cause the generation AI to create an optimal schedule.

[0097] The notification unit can apply different notification methods depending on the importance and payment deadline of an invoice when creating a payment schedule. For example, the notification unit applies different notification methods depending on the importance and payment deadline of an invoice when creating a payment schedule. The importance and payment deadline of an invoice are important information for determining the priority of notifications. For example, the optimal notification method can be selected depending on the importance of the invoice. Different notification methods can be applied depending on the payment deadline. This improves notification accuracy by applying the optimal notification method depending on the importance and payment deadline of the invoice. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input data on the importance and payment deadline of an invoice into the generation AI and have the generation AI apply the optimal notification method.

[0098] The notification unit can estimate a user's emotions and determine the priority of notifications based on the estimated user emotions. The notification unit, for example, estimates a user's emotions and determines the priority of notifications based on the estimated user emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice analysis, survey results, etc. Facial expression recognition is a technology that analyzes a user's facial expressions captured by a camera to estimate emotions. For example, if a user is feeling stressed, notifications of high importance can be displayed with priority. Voice analysis is a technology that analyzes the tone and speed of a user's voice to estimate emotions. For example, if a user is in a hurry, notifications with upcoming payment deadlines can be displayed with priority. Survey results are a method of estimating emotions based on the content of a survey answered by the user. For example, if a user is relaxed, all notifications can be displayed equally. This allows for efficient processing by determining the priority of notifications according to the user's emotions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the user's emotion data into the generation AI and have the generation AI determine priorities based on emotions.

[0099] The notification unit can select the optimal notification method by taking into account the user's geographical location information when creating a payment schedule. For example, when creating a payment schedule, the notification unit selects the optimal notification method by taking into account the user's geographical location information. The geographical location information can be obtained using, for example, GPS data, an IP address, a location information service, etc. For example, if the user is in a specific area, notifications related to that area can be displayed preferentially. If the user is on a business trip, notifications related to the business trip destination can be displayed preferentially. If the user is at home, notifications related to the home can be displayed preferentially. This improves notification accuracy by selecting the optimal notification method based on the user's geographical location information. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's geographical location information to a generation AI and cause the generation AI to select the optimal notification method.

[0100] The notification unit can improve the accuracy of notifications by referring to related literature and databases when creating a payment schedule. The notification unit can improve the accuracy of notifications by referring to related literature and databases, for example, when creating a payment schedule. The related literature and databases are used as reference information for improving the accuracy of notifications. For example, the accuracy of the notification algorithm can be improved by referring to related literature. The accuracy of the notification algorithm can be improved by referring to a database. As a result, notification accuracy is improved by referring to related literature and databases. Some or all of the above-mentioned processing in the notification unit can be performed using AI, for example, or without using AI. For example, the notification unit can input data from related literature and databases into the generation AI and cause the generation AI to improve the accuracy of notifications. === Hard Collateral 1-1 === Each of the multiple elements, including the acquisition unit, extraction unit, analysis unit, registration unit, and notification unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit acquires image data of an invoice using the camera 42 or scanner of the smart device 14 and inputs the data to the AI-OCR by the specific processing unit 290 of the data processing device 12. The extraction unit extracts text data using the AI-OCR by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the text data using generated AI by the specific processing unit 290 of the data processing device 12 and classifies and organizes the contents of the invoice. The registration unit registers the analysis results in the database 24 by the specific processing unit 290 of the data processing device 12. The notification unit creates a payment schedule by the specific processing unit 290 of the data processing device 12 and notifies relevant departments. === Hard Collateral 1-2 === Each of the multiple elements, including the acquisition unit, extraction unit, analysis unit, registration unit, and notification unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit acquires image data of an invoice using the camera 42 or scanner of the smart glasses 214 and inputs the image data into the AI-OCR by the specific processing unit 290 of the data processing device 12. The extraction unit extracts text data using the AI-OCR by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the text data using generated AI by the specific processing unit 290 of the data processing device 12 and classifies and organizes the contents of the invoice. The registration unit registers the analysis results in the database 24 by the specific processing unit 290 of the data processing device 12. The notification unit creates a payment schedule by the specific processing unit 290 of the data processing device 12 and notifies relevant departments. === Hard Collateral 1-3 === Each of the multiple elements including the acquisition unit, extraction unit, analysis unit, registration unit, and notification unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the acquisition unit acquires image data of an invoice using the camera 42 or scanner of the headset-type terminal 314 and inputs the image data into the AI-OCR by the specific processing unit 290 of the data processing device 12. The extraction unit extracts text data using the AI-OCR by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the text data using generated AI by the specific processing unit 290 of the data processing device 12 and classifies and organizes the contents of the invoice. The registration unit registers the analysis results in the database 24 by the specific processing unit 290 of the data processing device 12. The notification unit creates a payment schedule by the specific processing unit 290 of the data processing device 12 and notifies the relevant departments. === Hard Collateral 1-4 === Each of the multiple elements including the acquisition unit, extraction unit, analysis unit, registration unit, and notification unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the acquisition unit acquires image data of an invoice using the camera 42 or scanner of the robot 414 and inputs the data to the AI-OCR by the specific processing unit 290 of the data processing device 12. The extraction unit extracts text data using the AI-OCR by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the text data using generated AI by the specific processing unit 290 of the data processing device 12 and classifies and organizes the contents of the invoice. The registration unit registers the analysis results in the database 24 by the specific processing unit 290 of the data processing device 12. The notification unit creates a payment schedule by the specific processing unit 290 of the data processing device 12 and notifies the relevant departments.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring invoice image data based on the estimated user emotions. For example, if the user is feeling stressed, the acquisition timing can be delayed so that the image data is acquired when the user is relaxed. Also, if the user is in a hurry, the image data can be acquired immediately and processing can be started quickly. Furthermore, if the user is relaxed, the acquisition timing can be adjusted to reduce the user's workload. This makes it possible to acquire invoice image data at the optimal timing according to the user's emotions.

[0103] The acquisition unit can select the optimal acquisition method based on the type and issuer of the invoice. For example, for electronic invoices, the acquisition unit can acquire image data directly from email. For paper invoices, the acquisition unit can acquire high-resolution image data using a scanner. For invoices that can be downloaded from a web portal, the acquisition unit can automatically acquire image data using an API. This allows the acquisition unit to acquire image data in the optimal way depending on the type and issuer of the invoice.

[0104] The acquisition unit can have a function to automatically adjust the resolution and quality of the image. For example, when low-resolution image data is acquired, the acquisition unit can automatically perform processing to improve the resolution. Super-resolution technology can be used to improve the resolution. Also, when the image quality is low, the acquisition unit can perform noise removal and contrast adjustment to make the image easier to read. Furthermore, when the image is distorted, the acquisition unit can automatically correct it to acquire accurate data. As a result, accurate data can be acquired by automatically adjusting the image resolution and quality.

[0105] The acquisition unit can prioritize acquisition of highly relevant invoices in consideration of the user's geographical location information. For example, if the user is in a specific area, it can prioritize acquisition of invoices related to that area. If the user is on a business trip, it can prioritize acquisition of invoices related to the business trip destination. If the user is at home, it can prioritize acquisition of invoices related to the home. This makes it possible to prioritize acquisition of highly relevant invoices based on the user's geographical location information.

[0106] The acquisition unit can analyze the user's social media activity and acquire related invoices. For example, if a user posts on social media that they have used a specific service, invoices related to that service can be acquired preferentially. If a user posts on social media that they have attended a specific event, invoices related to that event can be acquired preferentially. If a user posts on social media that they have purchased a specific product, invoices related to that product can be acquired preferentially. In this way, related invoices can be acquired based on the user's social media activity.

[0107] The extraction unit can estimate the user's emotions and determine the priority of text data to be extracted based on the estimated user's emotions. For example, if the user is feeling stressed, text data of high importance can be preferentially extracted. If the user is in a hurry, text data with an upcoming payment deadline can be preferentially extracted. If the user is relaxed, all text data can be extracted equally. This allows for efficient processing by determining the priority of text data according to the user's emotions.

[0108] When extracting text data using AI-OCR, the extraction unit can apply the optimal extraction algorithm depending on the invoice layout and format. For example, if the invoice layout is different, the appropriate extraction algorithm can be automatically selected. The optimal extraction algorithm can be applied to invoices with different formats. For handwritten invoices, an extraction algorithm specialized for handwritten character recognition can be applied. This improves extraction accuracy by applying the optimal extraction algorithm depending on the invoice layout and format.

[0109] The extraction unit can be equipped with a function to improve the recognition accuracy of handwritten characters and special characters when extracting text data using AI-OCR. For example, the handwritten character recognition algorithm can be enhanced to improve the recognition accuracy of handwritten characters. Recurrent neural networks (RNN) and convolutional neural networks (CNN) can be used as the handwritten character recognition algorithm. In addition, a special character recognition algorithm can be added to improve the recognition accuracy of special characters. Support vector machines (SVM) and random forests can be used as the special character recognition algorithm. This improves the recognition accuracy of handwritten characters and special characters, allowing for accurate data extraction.

[0110] The extraction unit can estimate the user's emotion and adjust the display method of the extracted text data based on the estimated user's emotion. For example, if the user is feeling stressed, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. If the user is in a hurry, a display method that focuses on the main points can be provided. In this way, visibility is improved by adjusting the display method of the text data according to the user's emotion.

[0111] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. If the user is in a hurry, a display method that focuses on the main points can be provided. In this way, visibility is improved by adjusting the display method of the analysis results according to the user's emotions.

[0112] The processing flow of the second embodiment will be briefly explained below.

[0113] Step 1: The acquisition unit acquires image data of the invoice. Invoice image data may be in any format, including, but not limited to, PDF, JPEG, or PNG. The acquisition unit acquires the image data of the invoice using, for example, a scanner or a camera. A scanner can acquire image data at high resolution, while a camera can easily acquire image data. Step 2: The extraction unit uses AI-OCR to convert the image data acquired by the acquisition unit into text data. AI-OCR can use technologies such as Tesseract, Google Cloud Vision, and Amazon Textract. The AI-OCR extracts text data from the image data and passes it to the extraction unit. For example, it extracts information such as the invoice issue date, amount, and payment deadline. Step 3: The analysis unit uses the generation AI to analyze the text data received from the extraction unit and classify and organize the contents of the invoice. The generation AI can use technologies such as GPT-4 and Geminir. The generation AI analyzes the text data and classifies and organizes the contents of the invoice. For example, it registers information such as the invoice issue date, amount, and payment deadline in a database. Step 4: The registration unit registers the classified and organized data received from the analysis unit in a database. The database may be, for example, a relational database, a NoSQL database, etc., but is not limited to such examples. The database can efficiently store and search data. Step 5: The notification department creates a payment schedule and notifies relevant departments when the payment deadline approaches. The notification department can send notifications using methods such as email, SMS, and push notifications. This allows the invoice processing system to process invoices efficiently and reduce manual errors.

[0114] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0115] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0116] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0117] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0132] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0134] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0135] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0136] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0141] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0144] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0148] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0150] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0151] 7, a 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.

[0152] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0153] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0154] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0157] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0158] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0159] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0160] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0163] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0164] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0165] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0168] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0169] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0170] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0171] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0172] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0173] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0174] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0175] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0176] 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.

[0177] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0178] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0179] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0180] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0181] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0182] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0183] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0184] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0185] [Explanation of symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an acquisition unit that acquires image data of an invoice; an extraction unit that converts the image data acquired by the acquisition unit into text data using AI-OCR; an analysis unit that analyzes the text data extracted by the extraction unit using a generation AI and classifies and organizes the contents of the invoice; a registration unit that registers the data classified and organized by the analysis unit in a database; a notification unit that creates a payment schedule based on the data registered by the registration unit and notifies the relevant departments; Equipped with A system characterized by:

2. The acquisition unit Capture image data of the invoice using a scanner or camera The system of claim 1 .

3. The extraction unit Extract information such as invoice issue date, amount, and payment deadline using AI-OCR The system of claim 1 .

4. The analysis unit The generation AI analyzes the text data received from the extraction unit and classifies and organizes the contents of the invoice. The system of claim 1 .

5. The registration unit The classified and organized data received from the analysis unit is registered in a database. The system of claim 1 .

6. The notification unit Create a payment schedule and notify relevant departments when payments are due. The system of claim 1 .

7. The acquisition unit The user's emotions are estimated, and the timing of acquiring image data of an invoice is adjusted based on the estimated user's emotions. The system of claim 1 .

8. The acquisition unit Select the best capture method based on the type and origin of the invoice The system of claim 1 .

Images