System

Abstract

An object of a system according to an embodiment is to automate an inspection and payment procedure based on a bill.SOLUTION: A system includes a bill upload part, a data extraction part, an inspection automation part, and a payment automation part. The bill uploading unit uploads a bill. The data extraction unit analyzes the content of the bill uploaded by the bill upload unit and extracts necessary data. The inspection automation unit automates an inspection process based on the data extracted by the data extraction unit. The payment automation unit automates a payment procedure after the inspection is completed by the inspection automation unit.SELECTED DRAWING: Figure 1

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, inspection and payment procedures based on invoices were done manually, which was time-consuming and labor-intensive.

[0005] The system according to the embodiment aims to automate the inspection and payment procedures based on an invoice. [Means for solving the problem]

[0006] The system according to the embodiment includes an invoice upload unit, a data extraction unit, an inspection automation unit, and a payment automation unit. The invoice upload unit uploads invoices. The data extraction unit analyzes the contents of the invoices uploaded by the invoice upload unit and extracts necessary data. The inspection automation unit automates the inspection process based on the data extracted by the data extraction unit. The payment automation unit automates the payment procedure after inspection is completed by the inspection automation unit. [Effects of the Invention]

[0007] The system according to the embodiment can automate the acceptance and payment procedures based on the invoice. [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) The automation system according to an embodiment of the present invention automates the acceptance inspection and payment procedures based on invoices. This system automates the acceptance inspection and payment procedures simply by uploading an invoice. As a result, the automation system automates everything from uploading an invoice to the payment procedures, thereby improving work efficiency and saving time.

[0029] The automated system according to the embodiment includes an invoice upload unit, a data extraction unit, an inspection automation unit, and a payment automation unit. The invoice upload unit uploads invoices. For example, it can upload images or PDF files of invoices to the system. The invoice upload unit can also scan handwritten invoices and convert them into digital data. The data extraction unit analyzes the uploaded invoice content and extracts necessary data. For example, the generation AI can automatically read the invoice issue date, invoice amount, payee information, etc. using OCR technology. The generation AI can also analyze the invoice content and extract necessary data using text mining technology. The inspection automation unit automates the inspection process based on the extracted data. For example, the generation AI can compare the invoice content with the purchase order content to confirm that they match. The generation AI can also compare the invoice content with delivery notes and receipts to confirm that the actually delivered goods or services match the details listed on the invoice. The payment automation unit automates the payment procedure after inspection is complete. For example, the generation AI can generate a payment instruction based on the payee's bank account information and send it to the bank system. The generation AI can also manage payment schedules to ensure payments are made on time. As a result, the automated system according to the embodiment automates everything from uploading invoices to payment procedures, thereby improving work efficiency and saving time.

[0030] The data extraction unit can automatically read the invoice issue date, invoice amount, and payee information. For example, when an image or PDF file of an invoice is uploaded, the data extraction unit allows the generation AI to analyze its contents and extract data such as the issue date, invoice amount, and payee information. The extracted data is then automatically translated into different languages ​​to accommodate international transactions. For example, a Japanese invoice can be translated into English or Chinese. The data extraction unit also automatically translates the invoice into different languages ​​and provides an interface for checking the translation results. For example, the content of the invoice translated into English can be checked and corrected as necessary. The data extraction unit also automatically translates the invoice into different languages ​​in real time. For example, when an invoice is uploaded, the translation results are displayed within seconds, enabling quick response to international transactions. This automatically extracts important invoice information, eliminating the need for manual work.

[0031] The automated inspection department can compare the contents of an invoice with the contents of a purchase order to confirm that they match. For example, when an invoice is uploaded, the generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. The extracted data is compared with past transaction data to automatically detect fraudulent invoices. For example, invoice amounts and payee information that do not match past transaction data are detected. The automated inspection department also performs a real-time process in which the generation AI compares the data with past transaction data to automatically detect fraudulent invoices. For example, when an invoice is uploaded, a fraudulent invoice is detected within a few seconds and an alert is issued. The automated inspection department also builds a system in which the generation AI compares the data with past transaction data to automatically detect fraudulent invoices. For example, it references a past transaction database and sends a notification if a fraudulent invoice is detected. This automatically compares the contents of invoices and purchase orders, improving the accuracy of inspection work.

[0032] The payment automation unit can generate payment instructions based on the payee's bank account information and send them to the bank system. For example, when an invoice is uploaded, the payment automation unit's generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. At the same time, it uses an emotion estimation function to analyze employees' emotions regarding the invoice contents. For example, it detects stress or dissatisfaction regarding the invoice contents. After extracting the invoice data, the payment automation unit also uses the emotion estimation function to analyze employees' emotions in real time. For example, it calculates an emotion score regarding the invoice contents and identifies stressful tasks. The payment automation unit also uses the emotion estimation function to build a system that analyzes employees' emotions regarding the invoice contents and identifies stressful tasks. For example, it makes improvement suggestions for tasks with high emotion scores, reducing workloads. This automates payment procedures, thereby improving the efficiency and accuracy of payments.

[0033] The payment automation unit can notify users when payments are late or when payments are completed. For example, when an invoice is uploaded, the generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. Based on the extracted data, the generation AI automatically displays a message prompting users to simultaneously upload related contracts and purchase orders. For example, the system instructs users to select the contract or purchase order files related to the invoice. The payment automation unit also builds a system in which, when uploading an invoice, the generation AI automatically searches for and prompts users to upload related contracts and purchase orders. For example, the system automatically suggests related files based on the invoice contents. The payment automation unit also provides an interface that prompts the generation AI to simultaneously upload related contracts and purchase orders when uploading an invoice. For example, the system adds an upload button for related files to the invoice upload screen. This allows users to monitor payment status in real time and respond quickly if an abnormality occurs.

[0034] The data extraction unit can predict future payment schedules based on past payment history. For example, when an invoice is uploaded, the generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. Based on the extracted data, the generation AI automatically performs related tax processing. For example, it automates the calculation of consumption tax and the preparation of tax returns. The data extraction unit also builds a system in which, after extracting invoice data, the generation AI automatically performs related tax processing. For example, it automatically generates a tax return based on the invoice content and submits it to the tax office. Furthermore, when an invoice is uploaded, the data extraction unit allows the generation AI to automatically execute the process of related tax processing in real time. For example, it analyzes the invoice content and generates a tax return within seconds. This allows for the prediction of future payment schedules, thereby improving the efficiency of cash management.

[0035] The data extraction unit extracts invoice data, which the generation AI can automatically translate into different languages. For example, when an image or PDF file of an invoice is uploaded, the data extraction unit allows the generation AI to analyze its contents and extract data such as the issue date, invoice amount, and payee information. The extracted data is automatically translated into different languages ​​to accommodate international transactions. For example, a Japanese invoice can be translated into English or Chinese. The data extraction unit also allows the generation AI to automatically translate into different languages ​​and provides an interface for checking the translation results. For example, the content of the invoice translated into English can be checked and corrected as necessary. The data extraction unit also allows the generation AI to automatically translate into different languages ​​in real time. For example, when an invoice is uploaded, the translation results are displayed within a few seconds, allowing for quick response to international transactions. This allows invoice data to be automatically translated to accommodate international transactions.

[0036] The data extraction unit compares invoice data with past transaction data when extracting it, enabling the automatic detection of fraudulent invoices. For example, when an invoice is uploaded, the generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. The extracted data is compared with past transaction data to automatically detect fraudulent invoices. For example, invoice amounts and payee information that do not match past transaction data are detected. The data extraction unit also performs a real-time process in which the generation AI compares the data with past transaction data to automatically detect fraudulent invoices. For example, when an invoice is uploaded, a fraudulent invoice is detected within seconds, and an alert is issued. The data extraction unit also builds a system in which the generation AI compares the data with past transaction data to automatically detect fraudulent invoices. For example, it references a past transaction database and notifies users if a fraudulent invoice is detected. This automatic detection of fraudulent invoices helps prevent fraud and errors.

[0037] The data extraction unit can prompt the generation AI to automatically upload related contracts or purchase orders at the same time when uploading an invoice. For example, when an invoice is uploaded, the data extraction unit analyzes the contents of the invoice and displays a message prompting the generation AI to also upload related contracts and purchase orders at the same time. For example, the data extraction unit instructs the user to select files of contracts or purchase orders related to the invoice. The data extraction unit also builds a system in which, when an invoice is uploaded, the generation AI automatically searches for related contracts and purchase orders and prompts the user to upload them. For example, the data extraction unit automatically suggests related files based on the content of the invoice. The data extraction unit also provides an interface that prompts the generation AI to also upload related contracts and purchase orders at the same time when uploading an invoice. For example, the data extraction unit adds an upload button for related files to the invoice upload screen. This allows the simultaneous upload of related contracts and purchase orders, thereby streamlining the inspection process.

[0038] After the data extraction unit extracts invoice data, the generation AI automatically performs the relevant tax processing, reducing the effort required for tax returns. For example, when an invoice is uploaded, the data extraction unit allows the generation AI to analyze its contents and extract data such as the issue date, invoice amount, and payee information. Based on the extracted data, the generation AI automatically performs the relevant tax processing. For example, it automates the calculation of consumption tax and the preparation of tax returns. The data extraction unit also builds a system in which the generation AI automatically performs the relevant tax processing after extracting invoice data. For example, it automatically generates a tax return based on the invoice content and submits it to the tax office. Furthermore, when an invoice is uploaded, the data extraction unit allows the generation AI to automatically execute the process of performing the relevant tax processing in real time. For example, it analyzes the content of the invoice and generates a tax return within seconds. This automates tax processing, reducing the effort required for tax returns.

[0039] The inspection automation unit can detect anomalies during the inspection process by comparing it with past inspection data and automatically issue an alert. For example, during the inspection process, the generation AI compares it with past inspection data to detect anomalies. For example, it compares the contents of the delivery note with past inspection data and automatically issues an alert if there is a discrepancy. The inspection automation unit also builds a system in which the generation AI references past inspection data in real time during the inspection process to detect anomalies. For example, it detects anomalies based on the inspection database and immediately notifies the user. The inspection automation unit also executes a process in real time during the inspection process in which the generation AI compares it with past inspection data to detect anomalies and automatically issue an alert. For example, if an anomaly is detected during the inspection process, an alert is issued within a few seconds. This allows anomalies to be detected during the inspection process and a prompt response can be made.

[0040] The inspection automation unit allows the generation AI to automatically check relevant laws and regulations during the inspection process, preventing compliance violations. For example, the inspection automation unit allows the generation AI to automatically check relevant laws and regulations during the inspection process. For example, it checks whether the contents of the delivery note comply with laws and regulations and automatically issues an alert if there is a violation. The inspection automation unit also builds a system in which the generation AI references relevant laws and regulations in real time during the inspection process to prevent compliance violations. For example, it checks inspection data based on a legal regulations database and issues a notification if a violation is detected. The inspection automation unit also allows the generation AI to automatically check relevant laws and regulations during the inspection process and executes a process in real time to prevent compliance violations. For example, if a legal violation is detected during the inspection process, an alert is issued within a few seconds. This makes it possible to automatically check laws and regulations and prevent compliance violations.

[0041] The inspection automation department can support quality assurance by having the generation AI automatically refer to relevant quality control data during the inspection process. For example, the inspection automation department has the generation AI automatically refer to relevant quality control data during the inspection process. For example, it compares the contents of the delivery note with the quality control data to confirm whether quality is being ensured. The inspection automation department also builds a system in which the generation AI refers to quality control data in real time during the inspection process to support quality assurance. For example, it checks the inspection data based on a quality control database to confirm whether quality is being ensured. The inspection automation department also executes a process in real time in which the generation AI automatically refers to relevant quality control data during the inspection process to support quality assurance. For example, it refers to quality control data during inspection work to confirm whether quality is being ensured. This makes it possible to refer to quality control data and support quality assurance.

[0042] The inspection automation unit allows the generation AI to automatically update related inventory data during the inspection process, thereby improving the efficiency of inventory management. For example, the inspection automation unit allows the generation AI to automatically update related inventory data during the inspection process. For example, it automatically updates inventory data based on the contents of a delivery note, improving the efficiency of inventory management. The inspection automation unit also builds a system where the generation AI updates inventory data in real time during the inspection process. For example, it updates an inventory database based on the contents of a delivery note, keeping the inventory status up to date at all times. The inspection automation unit also runs a process in real time where the generation AI automatically updates related inventory data during the inspection process, improving the efficiency of inventory management. For example, it automatically updates inventory data during inspection work, reducing the effort required for inventory management. This automatically updates inventory data, improving the efficiency of inventory management.

[0043] The payment automation unit allows the generation AI to automatically check exchange rates during payment procedures and make payments at the optimal time. For example, the generation AI automatically checks exchange rates during payment procedures. For example, to optimize the timing of payments, it monitors exchange rates in real time and makes payments at the most favorable rate. The payment automation unit also builds a system in which the generation AI checks exchange rates in real time during payment procedures and makes payments at the optimal time. For example, it automatically makes payments when the exchange rate is favorable. The payment automation unit also executes a process in real time in which the generation AI automatically checks exchange rates during payment procedures and makes payments at the optimal time. For example, it adjusts the timing of payments based on the exchange rate to reduce costs. This makes it possible to check exchange rates and make payments at the optimal time.

[0044] The payment automation unit allows the generation AI to automatically check the credit information of the payee during the payment procedure, thereby minimizing risk. For example, the payment automation unit allows the generation AI to automatically check the credit information of the payee during the payment procedure. For example, it checks the payee's credit score and withholds payment if the risk is high. The payment automation unit also builds a system in which the generation AI checks the payee's credit information in real time during the payment procedure, thereby minimizing risk. For example, it references a credit information database and issues an alert for payees who are high risk. The payment automation unit also allows the generation AI to automatically check the payee's credit information during the payment procedure, thereby executing a process in real time to minimize risk. For example, it withholds payment if the payee's credit score is low, thereby avoiding risk. This makes it possible to check the payee's credit information and minimize risk.

[0045] The payment automation unit allows the generation AI to automatically check related insurance policies during payment procedures, thereby supporting risk management. For example, the payment automation unit allows the generation AI to automatically check related insurance policies during payment procedures. For example, it checks whether the payee is covered under the insurance policies and supports risk management. The payment automation unit also builds a system in which the generation AI checks insurance policies in real time during payment procedures and supports risk management. For example, it references an insurance policy database and checks whether the payee is covered by insurance. The payment automation unit also allows the generation AI to automatically check related insurance policies during payment procedures and executes a process in real time to support risk management. For example, it issues an alert if the payee is not covered by insurance. This makes it possible to check insurance policies and support risk management.

[0046] The payment automation unit allows the generation AI to automatically update relevant financial data during payment procedures, thereby improving the efficiency of financial management. For example, the payment automation unit allows the generation AI to automatically update relevant financial data during payment procedures. For example, it automatically updates financial data based on the payment amount and payee information, improving the efficiency of financial management. The payment automation unit also builds a system in which the generation AI updates financial data in real time during payment procedures. For example, it updates financial data based on a payment database, keeping the financial situation always up to date. The payment automation unit also runs a process in real time in which the generation AI automatically updates relevant financial data during payment procedures, improving the efficiency of financial management. For example, it automatically updates financial data during payment operations, reducing the effort required for financial management. This automatically updates financial data and improves the efficiency of financial management.

[0047] The payment automation unit allows the generation AI to automatically detect anomalies while monitoring the payment status and issue alerts in real time. For example, the payment automation unit allows the generation AI to automatically detect anomalies while monitoring the payment status. For example, it issues an alert if a payment is late or if the payment amount is abnormally high. The payment automation unit also builds a system that detects anomalies in real time while the generation AI is monitoring the payment status and issues an alert. For example, it detects anomalies based on a payment database and immediately notifies the user. The payment automation unit also executes a process in real time where the generation AI automatically detects anomalies while monitoring the payment status and issues an alert in real time. For example, if an anomaly is detected during payment processing, an alert will be issued within a few seconds. This allows anomalies to be detected while monitoring the payment status and a prompt response can be made.

[0048] The payment automation unit allows the generation AI to automatically check relevant laws and regulations while monitoring the payment status, preventing compliance violations. For example, the payment automation unit allows the generation AI to automatically check relevant laws and regulations while monitoring the payment status. For example, it checks whether the payment details comply with laws and regulations and automatically issues an alert if there is a violation. The payment automation unit also builds a system that references relevant laws and regulations in real time while the generation AI is monitoring the payment status and prevents compliance violations. For example, it checks payment data based on a legal regulations database and issues a notification if a violation is detected. The payment automation unit also allows the generation AI to automatically check relevant laws and regulations while monitoring the payment status and executes a process to prevent compliance violations in real time. For example, if a legal violation is detected during payment operations, an alert is issued within a few seconds. This allows laws and regulations to be automatically checked and compliance violations to be prevented.

[0049] The payment automation unit allows the generation AI to automatically refer to relevant market data while monitoring the payment status and propose a payment plan according to the economic situation. For example, the payment automation unit allows the generation AI to automatically refer to relevant market data while monitoring the payment status. For example, it proposes an optimal payment plan based on the current economic situation and market trends. The payment automation unit also builds a system in which the generation AI refers to market data in real time while monitoring the payment status and proposes a payment plan according to the economic situation. For example, it adjusts the payment schedule based on economic indicators and market trends. The payment automation unit also executes a process in real time in which the generation AI automatically refers to relevant market data while monitoring the payment status and proposes a payment plan according to the economic situation. For example, it adjusts the payment plan based on market data during payment operations to optimize costs. This makes it possible to refer to market data and propose a payment plan according to the economic situation.

[0050] The payment automation unit allows the generation AI to automatically update related contract data while monitoring the payment status, thereby improving the efficiency of contract management. For example, the payment automation unit allows the generation AI to automatically update related contract data while monitoring the payment status. For example, it automatically updates contract data based on payment details, improving the efficiency of contract management. The payment automation unit also builds a system that updates contract data in real time while the generation AI is monitoring the payment status. For example, it updates contract data based on a payment database, keeping the contract status always up to date. The payment automation unit also runs a process in real time where the generation AI automatically updates related contract data while monitoring the payment status, improving the efficiency of contract management. For example, it automatically updates contract data during payment operations, reducing the effort required for contract management. This automatically updates contract data, improving the efficiency of contract management.

[0051] The data extraction unit allows the generation AI to automatically detect anomalies while data is being saved and analyzed, and issue alerts in real time. For example, the data extraction unit allows the generation AI to automatically detect anomalies while data is being saved and analyzed. For example, it issues an alert if there is an inconsistency in the saved data or if an abnormal pattern is detected. The data extraction unit also builds a system that detects anomalies in real time while the generation AI is saving and analyzing data, and issues an alert. For example, it detects anomalies based on a database and immediately notifies the user. The data extraction unit also executes a process in real time where the generation AI automatically detects anomalies while data is being saved and analyzed, and issues an alert in real time. For example, if an anomaly is detected during data saving, an alert is issued within a few seconds. This allows anomalies to be detected while data is being saved and analyzed, and a rapid response can be made.

[0052] The data extraction unit allows the generation AI to automatically check relevant laws and regulations while saving and analyzing data, preventing compliance violations. For example, the data extraction unit checks whether the saved data complies with laws and regulations and automatically issues an alert if a violation is found. The data extraction unit also builds a system in which the generation AI references relevant laws and regulations in real time while saving and analyzing data, preventing compliance violations. For example, it checks saved data against a legal regulations database and issues a notification if a violation is detected. The data extraction unit also allows the generation AI to automatically check relevant laws and regulations while saving and analyzing data, executing a process to prevent compliance violations in real time. For example, if a legal violation is detected during data saving operations, an alert is issued within a few seconds. This allows the generation AI to automatically check laws and regulations and prevent compliance violations.

[0053] The data extraction unit allows the generation AI to automatically refer to relevant market data while storing and analyzing data, and perform analysis according to the economic situation. For example, the data extraction unit allows the generation AI to automatically refer to relevant market data while storing and analyzing data. For example, it analyzes the stored data based on the current economic situation and market trends. The data extraction unit also builds a system where the generation AI refers to market data in real time while storing and analyzing data, and performs analysis according to the economic situation. For example, it analyzes data based on economic indicators and market trends. The data extraction unit also executes a process where the generation AI automatically refers to relevant market data while storing and analyzing data, and performs analysis according to the economic situation in real time. For example, it performs analysis based on market data while storing data, and obtains insights according to the economic situation. This makes it possible to refer to market data and perform analysis according to the economic situation.

[0054] The data extraction unit allows the generation AI to automatically update related contract data while saving and analyzing data, thereby improving the efficiency of contract management. For example, the data extraction unit allows the generation AI to automatically update related contract data while saving and analyzing data. For example, the data extraction unit automatically updates contract data based on saved data, improving the efficiency of contract management. The data extraction unit also builds a system that updates contract data in real time while the generation AI is saving and analyzing data. For example, the data extraction unit updates contract data based on a saved database, keeping the contract status always up to date. The data extraction unit also executes a process in real time where the generation AI automatically updates related contract data while saving and analyzing data, improving the efficiency of contract management. For example, the data extraction unit automatically updates contract data while saving data, reducing the effort required for contract management. This automatically updates contract data, improving the efficiency of contract management.

[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 automation system can further include a behavior analysis unit that analyzes user behavior history. The behavior analysis unit analyzes how users use the system and identifies usage patterns. For example, it analyzes what time of day users tend to upload invoices and which functions they frequently use. The behavior analysis unit can also make suggestions to improve system usage efficiency based on the user behavior history. For example, it can provide an interface that prioritizes the display of functions that users use frequently. The behavior analysis unit can also monitor system usage in real time based on the user behavior history and issue an alert if abnormal behavior is detected. This makes it possible to analyze user behavior and improve system usage efficiency.

[0057] The data extraction unit may further include an environmental analysis unit that acquires environmental data and analyzes factors that affect invoice processing. The environmental analysis unit acquires external environmental data, such as weather and traffic conditions, and analyzes how it will affect invoice processing. For example, if delivery delays due to bad weather affect invoice processing, the environmental analysis unit can predict the impact in advance and propose countermeasures. The environmental analysis unit can also optimize invoice processing schedules based on external environmental data. For example, it can schedule deliveries to avoid times when traffic congestion is expected. The environmental analysis unit can also monitor external environmental data in real time and issue an alert if an abnormality is detected. This makes it possible to improve invoice processing efficiency by utilizing external environmental data.

[0058] The data extraction unit can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes how the user uses the system and identifies usage patterns. For example, it analyzes what time of day the user usually uploads invoices and which functions the user frequently uses. The behavior analysis unit can also make suggestions to improve system usage efficiency based on the user's behavioral history. For example, it can provide an interface that prioritizes the display of functions the user uses frequently. The behavior analysis unit can also monitor system usage in real time based on the user's behavioral history and issue an alert if abnormal behavior is detected. This makes it possible to analyze user behavior and improve system usage efficiency.

[0059] The inspection automation unit may further include an environmental analysis unit that acquires environmental data and analyzes factors that affect the inspection process. The environmental analysis unit acquires external environmental data, such as weather and traffic conditions, and analyzes how it will affect the inspection process. For example, if a delivery delay due to bad weather affects the inspection process, the environmental analysis unit can predict the impact in advance and propose countermeasures. The environmental analysis unit can also optimize the inspection process schedule based on the external environmental data. For example, it can schedule inspections to avoid times when traffic congestion is expected. The environmental analysis unit can also monitor external environmental data in real time and issue an alert if an abnormality is detected. This makes it possible to improve the efficiency of the inspection process by utilizing external environmental data.

[0060] The payment automation unit can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes how the user uses the system and identifies usage patterns. For example, it analyzes what time of day the user most often performs payment procedures and which functions the user frequently uses. The behavior analysis unit can also make suggestions to improve system usage efficiency based on the user's behavioral history. For example, it can provide an interface that prioritizes the display of functions the user uses frequently. The behavior analysis unit can also monitor system usage in real time based on the user's behavioral history and issue an alert if abnormal behavior is detected. This allows for analysis of user behavior and improvement of system usage efficiency.

[0061] The data extraction unit can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes how the user uses the system and identifies usage patterns. For example, it analyzes what time of day the user usually uploads invoices and which functions the user frequently uses. The behavior analysis unit can also make suggestions to improve system usage efficiency based on the user's behavioral history. For example, it can provide an interface that prioritizes the display of functions the user uses frequently. The behavior analysis unit can also monitor system usage in real time based on the user's behavioral history and issue an alert if abnormal behavior is detected. This makes it possible to analyze user behavior and improve system usage efficiency.

[0062] The payment automation unit may further include an environmental analysis unit that acquires environmental data and analyzes factors that affect the payment procedure. The environmental analysis unit acquires external environmental data, such as weather and traffic conditions, and analyzes how it will affect the payment procedure. For example, if a delivery delay due to bad weather affects the payment procedure, the environmental analysis unit can predict the impact in advance and propose countermeasures. The environmental analysis unit can also optimize the payment procedure schedule based on the external environmental data. For example, it can schedule payments to avoid times when traffic congestion is expected. The environmental analysis unit can also monitor external environmental data in real time and issue an alert if an abnormality is detected. This makes it possible to utilize external environmental data to improve the efficiency of payment procedures.

[0063] The processing flow of the first embodiment will be briefly explained below.

[0064] Step 1: The invoice uploading section uploads the invoice. For example, an image or PDF file of the invoice can be uploaded to the system. Handwritten invoices can also be scanned and converted into digital data. Step 2: The data extraction unit analyzes the uploaded invoice content and extracts the necessary data. For example, OCR technology can be used to automatically read the invoice issue date, invoice amount, payee information, etc. Text mining technology can also be used to analyze the invoice content and extract the necessary data. Step 3: The Inspection Automation Department automates the inspection process based on the extracted data. For example, it can compare the contents of the invoice with the contents of the purchase order to ensure they match. It can also compare them with delivery notes and receipts to ensure that the goods and services actually delivered match those listed on the invoice. Step 4: After inspection is complete, the payment automation unit automates the payment process. For example, it generates payment instructions based on the recipient's bank account information and sends them to the bank system. It can also manage payment schedules to ensure payments are made on time.

[0065] (Example 2) The automation system according to an embodiment of the present invention automates the acceptance inspection and payment procedures based on invoices. This system automates the acceptance inspection and payment procedures simply by uploading an invoice. As a result, the automation system automates everything from uploading an invoice to the payment procedures, thereby improving work efficiency and saving time.

[0066] The automated system according to the embodiment includes an invoice upload unit, a data extraction unit, an inspection automation unit, and a payment automation unit. The invoice upload unit uploads invoices. For example, it can upload images or PDF files of invoices to the system. The invoice upload unit can also scan handwritten invoices and convert them into digital data. The data extraction unit analyzes the uploaded invoice content and extracts necessary data. For example, the generation AI can automatically read the invoice issue date, invoice amount, payee information, etc. using OCR technology. The generation AI can also analyze the invoice content and extract necessary data using text mining technology. The inspection automation unit automates the inspection process based on the extracted data. For example, the generation AI can compare the invoice content with the purchase order content to confirm that they match. The generation AI can also compare the invoice content with delivery notes and receipts to confirm that the actually delivered goods or services match the details listed on the invoice. The payment automation unit automates the payment procedure after inspection is complete. For example, the generation AI can generate a payment instruction based on the payee's bank account information and send it to the bank system. The generation AI can also manage payment schedules to ensure payments are made on time. As a result, the automated system according to the embodiment automates everything from uploading invoices to payment procedures, thereby improving work efficiency and saving time.

[0067] The data extraction unit can automatically read the invoice issue date, invoice amount, and payee information. For example, when an image or PDF file of an invoice is uploaded, the data extraction unit allows the generation AI to analyze its contents and extract data such as the issue date, invoice amount, and payee information. The extracted data is then automatically translated into different languages ​​to accommodate international transactions. For example, a Japanese invoice can be translated into English or Chinese. The data extraction unit also automatically translates the invoice into different languages ​​and provides an interface for checking the translation results. For example, the content of the invoice translated into English can be checked and corrected as necessary. The data extraction unit also automatically translates the invoice into different languages ​​in real time. For example, when an invoice is uploaded, the translation results are displayed within seconds, enabling quick response to international transactions. This automatically extracts important invoice information, eliminating the need for manual work.

[0068] The automated inspection department can compare the contents of an invoice with the contents of a purchase order to confirm that they match. For example, when an invoice is uploaded, the generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. The extracted data is compared with past transaction data to automatically detect fraudulent invoices. For example, invoice amounts and payee information that do not match past transaction data are detected. The automated inspection department also performs a real-time process in which the generation AI compares the data with past transaction data to automatically detect fraudulent invoices. For example, when an invoice is uploaded, a fraudulent invoice is detected within a few seconds and an alert is issued. The automated inspection department also builds a system in which the generation AI compares the data with past transaction data to automatically detect fraudulent invoices. For example, it references a past transaction database and sends a notification if a fraudulent invoice is detected. This automatically compares the contents of invoices and purchase orders, improving the accuracy of inspection work.

[0069] The payment automation unit can generate payment instructions based on the payee's bank account information and send them to the bank system. For example, when an invoice is uploaded, the payment automation unit's generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. At the same time, it uses an emotion estimation function to analyze employees' emotions regarding the invoice contents. For example, it detects stress or dissatisfaction regarding the invoice contents. After extracting the invoice data, the payment automation unit also uses the emotion estimation function to analyze employees' emotions in real time. For example, it calculates an emotion score regarding the invoice contents and identifies stressful tasks. The payment automation unit also uses the emotion estimation function to build a system that analyzes employees' emotions regarding the invoice contents and identifies stressful tasks. For example, it makes improvement suggestions for tasks with high emotion scores, reducing workloads. This automates payment procedures, thereby improving the efficiency and accuracy of payments.

[0070] The payment automation unit can notify users when payments are late or when payments are completed. For example, when an invoice is uploaded, the generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. Based on the extracted data, the generation AI automatically displays a message prompting users to simultaneously upload related contracts and purchase orders. For example, the system instructs users to select the contract or purchase order files related to the invoice. The payment automation unit also builds a system in which, when uploading an invoice, the generation AI automatically searches for and prompts users to upload related contracts and purchase orders. For example, the system automatically suggests related files based on the invoice contents. The payment automation unit also provides an interface that prompts the generation AI to simultaneously upload related contracts and purchase orders when uploading an invoice. For example, the system adds an upload button for related files to the invoice upload screen. This allows users to monitor payment status in real time and respond quickly if an abnormality occurs.

[0071] The data extraction unit can predict future payment schedules based on past payment history. For example, when an invoice is uploaded, the generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. Based on the extracted data, the generation AI automatically performs related tax processing. For example, it automates the calculation of consumption tax and the preparation of tax returns. The data extraction unit also builds a system in which, after extracting invoice data, the generation AI automatically performs related tax processing. For example, it automatically generates a tax return based on the invoice content and submits it to the tax office. Furthermore, when an invoice is uploaded, the data extraction unit allows the generation AI to automatically execute the process of related tax processing in real time. For example, it analyzes the invoice content and generates a tax return within seconds. This allows for the prediction of future payment schedules, thereby improving the efficiency of cash management.

[0072] The data extraction unit extracts invoice data, which the generation AI can automatically translate into different languages. For example, when an image or PDF file of an invoice is uploaded, the data extraction unit allows the generation AI to analyze its contents and extract data such as the issue date, invoice amount, and payee information. The extracted data is automatically translated into different languages ​​to accommodate international transactions. For example, a Japanese invoice can be translated into English or Chinese. The data extraction unit also allows the generation AI to automatically translate into different languages ​​and provides an interface for checking the translation results. For example, the content of the invoice translated into English can be checked and corrected as necessary. The data extraction unit also allows the generation AI to automatically translate into different languages ​​in real time. For example, when an invoice is uploaded, the translation results are displayed within a few seconds, allowing for quick response to international transactions. This allows invoice data to be automatically translated to accommodate international transactions.

[0073] The data extraction unit compares invoice data with past transaction data when extracting it, enabling the automatic detection of fraudulent invoices. For example, when an invoice is uploaded, the generation AI analyzes its contents and extracts data such as the issue date, invoice amount, and payee information. The extracted data is compared with past transaction data to automatically detect fraudulent invoices. For example, invoice amounts and payee information that do not match past transaction data are detected. The data extraction unit also performs a real-time process in which the generation AI compares the data with past transaction data to automatically detect fraudulent invoices. For example, when an invoice is uploaded, a fraudulent invoice is detected within seconds, and an alert is issued. The data extraction unit also builds a system in which the generation AI compares the data with past transaction data to automatically detect fraudulent invoices. For example, it references a past transaction database and notifies users if a fraudulent invoice is detected. This automatic detection of fraudulent invoices helps prevent fraud and errors.

[0074] The data extraction unit uses the emotion estimation function to analyze employees' emotions regarding the contents of an invoice, identify stressful tasks, and make improvement suggestions. For example, when the data extraction unit uploads an invoice, the generation AI analyzes the content and extracts data such as the issue date, invoice amount, and payee information. At the same time, the emotion estimation function is used to analyze employees' emotions regarding the invoice contents. For example, stress and dissatisfaction regarding the invoice contents are detected. After extracting the invoice data, the data extraction unit also uses the emotion estimation function to analyze employees' emotions in real time. For example, the emotion estimation function calculates an emotion score regarding the invoice contents and identifies stressful tasks. The data extraction unit also uses the emotion estimation function to build a system that analyzes employees' emotions regarding the invoice contents and identifies stressful tasks. For example, improvement suggestions can be made for tasks with high emotion scores to reduce workload. This makes it possible to analyze employees' emotions and make improvement suggestions to reduce workload.

[0075] The data extraction unit can prompt the generation AI to automatically upload related contracts or purchase orders at the same time when uploading an invoice. For example, when an invoice is uploaded, the data extraction unit analyzes the contents of the invoice and displays a message prompting the generation AI to also upload related contracts and purchase orders at the same time. For example, the data extraction unit instructs the user to select files of contracts or purchase orders related to the invoice. The data extraction unit also builds a system in which, when an invoice is uploaded, the generation AI automatically searches for related contracts and purchase orders and prompts the user to upload them. For example, the data extraction unit automatically suggests related files based on the content of the invoice. The data extraction unit also provides an interface that prompts the generation AI to also upload related contracts and purchase orders at the same time when uploading an invoice. For example, the data extraction unit adds an upload button for related files to the invoice upload screen. This allows the simultaneous upload of related contracts and purchase orders, thereby streamlining the inspection process.

[0076] After the data extraction unit extracts invoice data, the generation AI automatically performs the relevant tax processing, reducing the effort required for tax returns. For example, when an invoice is uploaded, the data extraction unit allows the generation AI to analyze its contents and extract data such as the issue date, invoice amount, and payee information. Based on the extracted data, the generation AI automatically performs the relevant tax processing. For example, it automates the calculation of consumption tax and the preparation of tax returns. The data extraction unit also builds a system in which the generation AI automatically performs the relevant tax processing after extracting invoice data. For example, it automatically generates a tax return based on the invoice content and submits it to the tax office. Furthermore, when an invoice is uploaded, the data extraction unit allows the generation AI to automatically execute the process of performing the relevant tax processing in real time. For example, it analyzes the content of the invoice and generates a tax return within seconds. This automates tax processing, reducing the effort required for tax returns.

[0077] The data extraction unit uses the emotion estimation function to analyze the customer's emotions regarding the invoice contents, which can be used to improve business relationships. For example, when the data extraction unit uploads an invoice, the generation AI analyzes the contents and extracts data such as the issue date, invoice amount, and payee information. At the same time, the emotion estimation function is used to analyze the customer's emotions regarding the invoice contents. For example, the customer's satisfaction or dissatisfaction with the invoice contents is detected. After extracting the invoice data, the data extraction unit also uses the emotion estimation function to analyze the customer's emotions in real time. For example, the data extraction unit calculates the customer's emotion score regarding the invoice contents, which can be used to improve business relationships. The data extraction unit also uses the emotion estimation function to analyze the customer's emotions regarding the invoice contents and build a system that can be used to improve business relationships. For example, improvement suggestions can be made to customers with low emotion scores to strengthen business relationships. This makes it possible to analyze the customer's emotions and use the results to improve business relationships.

[0078] The inspection automation unit can detect anomalies during the inspection process by comparing it with past inspection data and automatically issue an alert. For example, during the inspection process, the generation AI compares it with past inspection data to detect anomalies. For example, it compares the contents of the delivery note with past inspection data and automatically issues an alert if there is a discrepancy. The inspection automation unit also builds a system in which the generation AI references past inspection data in real time during the inspection process to detect anomalies. For example, it detects anomalies based on the inspection database and immediately notifies the user. The inspection automation unit also executes a process in real time during the inspection process in which the generation AI compares it with past inspection data to detect anomalies and automatically issue an alert. For example, if an anomaly is detected during the inspection process, an alert is issued within a few seconds. This allows anomalies to be detected during the inspection process and a prompt response can be made.

[0079] The inspection automation unit allows the generation AI to automatically check relevant laws and regulations during the inspection process, preventing compliance violations. For example, the inspection automation unit allows the generation AI to automatically check relevant laws and regulations during the inspection process. For example, it checks whether the contents of the delivery note comply with laws and regulations and automatically issues an alert if there is a violation. The inspection automation unit also builds a system in which the generation AI references relevant laws and regulations in real time during the inspection process to prevent compliance violations. For example, it checks inspection data based on a legal regulations database and issues a notification if a violation is detected. The inspection automation unit also allows the generation AI to automatically check relevant laws and regulations during the inspection process and executes a process in real time to prevent compliance violations. For example, if a legal violation is detected during the inspection process, an alert is issued within a few seconds. This makes it possible to automatically check laws and regulations and prevent compliance violations.

[0080] The inspection automation unit uses the emotion estimation function to analyze the emotions of employees during the inspection process and make improvement suggestions to reduce their workload. The inspection automation unit, for example, uses the emotion estimation function to analyze employees' emotions during the inspection process. For example, it detects stress or dissatisfaction during inspection work and makes improvement suggestions to reduce their workload. The inspection automation unit also builds a system that uses the emotion estimation function to analyze employees' emotions in real time during the inspection process. For example, it calculates an emotion score during inspection work and makes improvement suggestions for stressful work. The inspection automation unit also uses the emotion estimation function to analyze employees' emotions during the inspection process and executes a process in real time to make improvement suggestions to reduce their workload. For example, it immediately makes improvement suggestions for work with a high emotion score during inspection work. This makes it possible to analyze employees' emotions and make improvement suggestions to reduce their workload.

[0081] The inspection automation department can support quality assurance by having the generation AI automatically refer to relevant quality control data during the inspection process. For example, the inspection automation department has the generation AI automatically refer to relevant quality control data during the inspection process. For example, it compares the contents of the delivery note with the quality control data to confirm whether quality is being ensured. The inspection automation department also builds a system in which the generation AI refers to quality control data in real time during the inspection process to support quality assurance. For example, it checks the inspection data based on a quality control database to confirm whether quality is being ensured. The inspection automation department also executes a process in real time in which the generation AI automatically refers to relevant quality control data during the inspection process to support quality assurance. For example, it refers to quality control data during inspection work to confirm whether quality is being ensured. This makes it possible to refer to quality control data and support quality assurance.

[0082] The inspection automation unit allows the generation AI to automatically update related inventory data during the inspection process, thereby improving the efficiency of inventory management. For example, the inspection automation unit allows the generation AI to automatically update related inventory data during the inspection process. For example, it automatically updates inventory data based on the contents of a delivery note, improving the efficiency of inventory management. The inspection automation unit also builds a system where the generation AI updates inventory data in real time during the inspection process. For example, it updates an inventory database based on the contents of a delivery note, keeping the inventory status up to date at all times. The inspection automation unit also runs a process in real time where the generation AI automatically updates related inventory data during the inspection process, improving the efficiency of inventory management. For example, it automatically updates inventory data during inspection work, reducing the effort required for inventory management. This automatically updates inventory data, improving the efficiency of inventory management.

[0083] The inspection automation unit uses the emotion estimation function to analyze the emotions of a business partner during the inspection process and can use the results to improve business relationships. The inspection automation unit, for example, uses the emotion estimation function to analyze the emotions of a business partner during the inspection process. For example, it detects the business partner's satisfaction or dissatisfaction with the contents of a delivery note and uses this to help improve business relationships. The inspection automation unit also builds a system that uses the emotion estimation function to analyze the emotions of a business partner in real time during the inspection process. For example, it calculates the business partner's emotion score for the contents of the delivery note and uses this to help improve business relationships. The inspection automation unit also uses the emotion estimation function to analyze the business partner's emotions during the inspection process and executes a process in real time that helps improve business relationships. For example, if a business partner's emotion score is low during inspection work, it makes improvement suggestions. This makes it possible to analyze the business partner's emotions and use this to help improve business relationships.

[0084] The payment automation unit allows the generation AI to automatically check exchange rates during payment procedures and make payments at the optimal time. For example, the generation AI automatically checks exchange rates during payment procedures. For example, to optimize the timing of payments, it monitors exchange rates in real time and makes payments at the most favorable rate. The payment automation unit also builds a system in which the generation AI checks exchange rates in real time during payment procedures and makes payments at the optimal time. For example, it automatically makes payments when the exchange rate is favorable. The payment automation unit also executes a process in real time in which the generation AI automatically checks exchange rates during payment procedures and makes payments at the optimal time. For example, it adjusts the timing of payments based on the exchange rate to reduce costs. This makes it possible to check exchange rates and make payments at the optimal time.

[0085] The payment automation unit allows the generation AI to automatically check the credit information of the payee during the payment procedure, thereby minimizing risk. For example, the payment automation unit allows the generation AI to automatically check the credit information of the payee during the payment procedure. For example, it checks the payee's credit score and withholds payment if the risk is high. The payment automation unit also builds a system in which the generation AI checks the payee's credit information in real time during the payment procedure, thereby minimizing risk. For example, it references a credit information database and issues an alert for payees who are high risk. The payment automation unit also allows the generation AI to automatically check the payee's credit information during the payment procedure, thereby executing a process in real time to minimize risk. For example, it withholds payment if the payee's credit score is low, thereby avoiding risk. This makes it possible to check the payee's credit information and minimize risk.

[0086] The payment automation unit uses the emotion estimation function to analyze the emotions of employees during payment procedures and make improvement suggestions to reduce their workload. The payment automation unit, for example, uses the emotion estimation function to analyze employees' emotions during payment procedures. For example, it detects stress and dissatisfaction during payment operations and makes improvement suggestions to reduce their workload. The payment automation unit also builds a system that uses the emotion estimation function to analyze employees' emotions in real time during payment procedures. For example, it calculates an emotion score during payment operations and makes improvement suggestions for stressful tasks. The payment automation unit also uses the emotion estimation function to analyze employees' emotions during payment procedures and executes a process in real time to make improvement suggestions to reduce their workload. For example, it immediately makes improvement suggestions for tasks with high emotion scores during payment operations. This makes it possible to analyze employees' emotions and make improvement suggestions to reduce their workload.

[0087] The payment automation unit allows the generation AI to automatically check related insurance policies during payment procedures, thereby supporting risk management. For example, the payment automation unit allows the generation AI to automatically check related insurance policies during payment procedures. For example, it checks whether the payee is covered under the insurance policies and supports risk management. The payment automation unit also builds a system in which the generation AI checks insurance policies in real time during payment procedures and supports risk management. For example, it references an insurance policy database and checks whether the payee is covered by insurance. The payment automation unit also allows the generation AI to automatically check related insurance policies during payment procedures and executes a process in real time to support risk management. For example, it issues an alert if the payee is not covered by insurance. This makes it possible to check insurance policies and support risk management.

[0088] The payment automation unit allows the generation AI to automatically update relevant financial data during payment procedures, thereby improving the efficiency of financial management. For example, the payment automation unit allows the generation AI to automatically update relevant financial data during payment procedures. For example, it automatically updates financial data based on the payment amount and payee information, improving the efficiency of financial management. The payment automation unit also builds a system in which the generation AI updates financial data in real time during payment procedures. For example, it updates financial data based on a payment database, keeping the financial situation always up to date. The payment automation unit also runs a process in real time in which the generation AI automatically updates relevant financial data during payment procedures, improving the efficiency of financial management. For example, it automatically updates financial data during payment operations, reducing the effort required for financial management. This automatically updates financial data and improves the efficiency of financial management.

[0089] The payment automation unit uses the emotion estimation function to analyze the emotions of a business partner during payment procedures, and can use this information to improve business relationships. The payment automation unit uses the emotion estimation function to analyze the emotions of a business partner during payment procedures, for example. For example, it detects the business partner's satisfaction or dissatisfaction with the payment details, and uses this information to improve business relationships. The payment automation unit also builds a system that uses the emotion estimation function to analyze the emotions of a business partner in real time during payment procedures. For example, it calculates the business partner's emotion score for the payment details, and uses this information to improve business relationships. The payment automation unit also uses the emotion estimation function to analyze the business partner's emotions during payment procedures, and executes a process in real time that helps improve business relationships. For example, if the business partner's emotion score is low during payment operations, it makes suggestions for improvement. This makes it possible to analyze the business partner's emotions and use this information to improve business relationships.

[0090] The payment automation unit allows the generation AI to automatically detect anomalies while monitoring the payment status and issue alerts in real time. For example, the payment automation unit allows the generation AI to automatically detect anomalies while monitoring the payment status. For example, it issues an alert if a payment is late or if the payment amount is abnormally high. The payment automation unit also builds a system that detects anomalies in real time while the generation AI is monitoring the payment status and issues an alert. For example, it detects anomalies based on a payment database and immediately notifies the user. The payment automation unit also executes a process in real time where the generation AI automatically detects anomalies while monitoring the payment status and issues an alert in real time. For example, if an anomaly is detected during payment processing, an alert will be issued within a few seconds. This allows anomalies to be detected while monitoring the payment status and a prompt response can be made.

[0091] The payment automation unit allows the generation AI to automatically check relevant laws and regulations while monitoring the payment status, preventing compliance violations. For example, the payment automation unit allows the generation AI to automatically check relevant laws and regulations while monitoring the payment status. For example, it checks whether the payment details comply with laws and regulations and automatically issues an alert if there is a violation. The payment automation unit also builds a system that references relevant laws and regulations in real time while the generation AI is monitoring the payment status and prevents compliance violations. For example, it checks payment data based on a legal regulations database and issues a notification if a violation is detected. The payment automation unit also allows the generation AI to automatically check relevant laws and regulations while monitoring the payment status and executes a process to prevent compliance violations in real time. For example, if a legal violation is detected during payment operations, an alert is issued within a few seconds. This allows laws and regulations to be automatically checked and compliance violations to be prevented.

[0092] The payment automation unit uses the emotion estimation function to analyze the emotions of employees while monitoring the payment status and can make improvement suggestions to reduce the workload. The payment automation unit, for example, uses the emotion estimation function to analyze the emotions of employees while monitoring the payment status. For example, it detects stress or dissatisfaction during payment operations and makes improvement suggestions to reduce the workload. The payment automation unit also builds a system that uses the emotion estimation function to analyze the emotions of employees in real time while monitoring the payment status. For example, it calculates an emotion score during payment operations and makes improvement suggestions for stressful tasks. The payment automation unit also uses the emotion estimation function to analyze the emotions of employees while monitoring the payment status and executes a process in real time to make improvement suggestions to reduce the workload. For example, it immediately makes improvement suggestions for tasks with high emotion scores during payment operations. This makes it possible to analyze the emotions of employees and make improvement suggestions to reduce the workload.

[0093] The payment automation unit allows the generation AI to automatically refer to relevant market data while monitoring the payment status and propose a payment plan according to the economic situation. For example, the payment automation unit allows the generation AI to automatically refer to relevant market data while monitoring the payment status. For example, it proposes an optimal payment plan based on the current economic situation and market trends. The payment automation unit also builds a system in which the generation AI refers to market data in real time while monitoring the payment status and proposes a payment plan according to the economic situation. For example, it adjusts the payment schedule based on economic indicators and market trends. The payment automation unit also executes a process in real time in which the generation AI automatically refers to relevant market data while monitoring the payment status and proposes a payment plan according to the economic situation. For example, it adjusts the payment plan based on market data during payment operations to optimize costs. This makes it possible to refer to market data and propose a payment plan according to the economic situation.

[0094] The payment automation unit allows the generation AI to automatically update related contract data while monitoring the payment status, thereby improving the efficiency of contract management. For example, the payment automation unit allows the generation AI to automatically update related contract data while monitoring the payment status. For example, it automatically updates contract data based on payment details, improving the efficiency of contract management. The payment automation unit also builds a system that updates contract data in real time while the generation AI is monitoring the payment status. For example, it updates contract data based on a payment database, keeping the contract status always up to date. The payment automation unit also runs a process in real time where the generation AI automatically updates related contract data while monitoring the payment status, improving the efficiency of contract management. For example, it automatically updates contract data during payment operations, reducing the effort required for contract management. This automatically updates contract data, improving the efficiency of contract management.

[0095] The payment automation unit uses the emotion estimation function to analyze the emotions of the customer while monitoring the payment status, and can use the results to improve the business relationship. The payment automation unit, for example, uses the emotion estimation function to analyze the customer's emotions while monitoring the payment status. For example, it detects the customer's satisfaction or dissatisfaction with the payment details, and uses this to improve the business relationship. The payment automation unit also uses the emotion estimation function to build a system that analyzes the customer's emotions in real time while monitoring the payment status. For example, it calculates the customer's emotion score for the payment details, and uses this to improve the business relationship. The payment automation unit also uses the emotion estimation function to analyze the customer's emotions while monitoring the payment status, and executes a process in real time that helps improve the business relationship. For example, if the customer's emotion score is low during the payment process, it makes an improvement suggestion. This allows the customer's emotions to be analyzed and used to improve the business relationship.

[0096] The data extraction unit allows the generation AI to automatically detect anomalies while data is being saved and analyzed, and issue alerts in real time. For example, the data extraction unit allows the generation AI to automatically detect anomalies while data is being saved and analyzed. For example, it issues an alert if there is an inconsistency in the saved data or if an abnormal pattern is detected. The data extraction unit also builds a system that detects anomalies in real time while the generation AI is saving and analyzing data, and issues an alert. For example, it detects anomalies based on a database and immediately notifies the user. The data extraction unit also executes a process in real time where the generation AI automatically detects anomalies while data is being saved and analyzed, and issues an alert in real time. For example, if an anomaly is detected during data saving, an alert is issued within a few seconds. This allows anomalies to be detected while data is being saved and analyzed, and a rapid response can be made.

[0097] The data extraction unit allows the generation AI to automatically check relevant laws and regulations while saving and analyzing data, preventing compliance violations. For example, the data extraction unit checks whether the saved data complies with laws and regulations and automatically issues an alert if a violation is found. The data extraction unit also builds a system in which the generation AI references relevant laws and regulations in real time while saving and analyzing data, preventing compliance violations. For example, it checks saved data against a legal regulations database and issues a notification if a violation is detected. The data extraction unit also allows the generation AI to automatically check relevant laws and regulations while saving and analyzing data, executing a process to prevent compliance violations in real time. For example, if a legal violation is detected during data saving operations, an alert is issued within a few seconds. This allows the generation AI to automatically check laws and regulations and prevent compliance violations.

[0098] The data extraction unit uses the emotion estimation function to analyze the emotions of employees during data storage and analysis, and can make improvement suggestions to reduce their workload. The data extraction unit, for example, uses the emotion estimation function to analyze employees' emotions during data storage and analysis. For example, it detects stress or dissatisfaction during data storage work and makes improvement suggestions to reduce their workload. The data extraction unit also builds a system that uses the emotion estimation function to analyze employees' emotions in real time during data storage and analysis. For example, it calculates an emotion score during data storage work and makes improvement suggestions for stressful work. The data extraction unit also uses the emotion estimation function to analyze employees' emotions during data storage and analysis, and executes a process in real time to make improvement suggestions to reduce their workload. For example, it immediately makes improvement suggestions for work with a high emotion score during data storage work. This makes it possible to analyze employees' emotions and make improvement suggestions to reduce their workload.

[0099] The data extraction unit allows the generation AI to automatically refer to relevant market data while storing and analyzing data, and perform analysis according to the economic situation. For example, the data extraction unit allows the generation AI to automatically refer to relevant market data while storing and analyzing data. For example, it analyzes the stored data based on the current economic situation and market trends. The data extraction unit also builds a system where the generation AI refers to market data in real time while storing and analyzing data, and performs analysis according to the economic situation. For example, it analyzes data based on economic indicators and market trends. The data extraction unit also executes a process where the generation AI automatically refers to relevant market data while storing and analyzing data, and performs analysis according to the economic situation in real time. For example, it performs analysis based on market data while storing data, and obtains insights according to the economic situation. This makes it possible to refer to market data and perform analysis according to the economic situation.

[0100] The data extraction unit allows the generation AI to automatically update related contract data while saving and analyzing data, thereby improving the efficiency of contract management. For example, the data extraction unit allows the generation AI to automatically update related contract data while saving and analyzing data. For example, the data extraction unit automatically updates contract data based on saved data, improving the efficiency of contract management. The data extraction unit also builds a system that updates contract data in real time while the generation AI is saving and analyzing data. For example, the data extraction unit updates contract data based on a saved database, keeping the contract status always up to date. The data extraction unit also executes a process in real time where the generation AI automatically updates related contract data while saving and analyzing data, improving the efficiency of contract management. For example, the data extraction unit automatically updates contract data while saving data, reducing the effort required for contract management. This automatically updates contract data, improving the efficiency of contract management.

[0101] The data extraction unit uses the emotion estimation function to analyze the emotions of the business partner while data is being saved and analyzed, and can use the results to improve business relationships. The data extraction unit, for example, uses the emotion estimation function to analyze the emotions of the business partner while data is being saved and analyzed. For example, the data extraction unit detects the business partner's satisfaction or dissatisfaction with the saved data and uses the results to improve business relationships. The data extraction unit also builds a system that uses the emotion estimation function to analyze the business partner's emotions in real time while data is being saved and analyzed. For example, the data extraction unit calculates the business partner's emotion score for the saved data and uses the results to improve business relationships. The data extraction unit also uses the emotion estimation function to analyze the business partner's emotions while data is being saved and analyzed, and executes a process in real time that helps improve business relationships. For example, if the business partner's emotion score is low during data saving, the data extraction unit makes improvement suggestions. This makes it possible to analyze the business partner's emotions and use the results to improve business relationships.

[0102] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0103] The automation system can further include a behavior analysis unit that analyzes user behavior history. The behavior analysis unit analyzes how users use the system and identifies usage patterns. For example, it analyzes what time of day users tend to upload invoices and which functions they frequently use. The behavior analysis unit can also make suggestions to improve system usage efficiency based on the user behavior history. For example, it can provide an interface that prioritizes the display of functions that users use frequently. The behavior analysis unit can also monitor system usage in real time based on the user behavior history and issue an alert if abnormal behavior is detected. This makes it possible to analyze user behavior and improve system usage efficiency.

[0104] The data extraction unit may further include an environmental analysis unit that acquires environmental data and analyzes factors that affect invoice processing. The environmental analysis unit acquires external environmental data, such as weather and traffic conditions, and analyzes how it will affect invoice processing. For example, if delivery delays due to bad weather affect invoice processing, the environmental analysis unit can predict the impact in advance and propose countermeasures. The environmental analysis unit can also optimize invoice processing schedules based on external environmental data. For example, it can schedule deliveries to avoid times when traffic congestion is expected. The environmental analysis unit can also monitor external environmental data in real time and issue an alert if an abnormality is detected. This makes it possible to improve invoice processing efficiency by utilizing external environmental data.

[0105] The inspection automation unit can further estimate the user's emotions and adjust the inspection process based on the estimated user emotions. For example, if the user is feeling stressed, it can make suggestions to simplify the inspection process. The inspection automation unit can also monitor the user's emotions in real time and issue an alert if the emotion score is high. For example, if the user is feeling dissatisfied, it can identify the cause and suggest improvements. The inspection automation unit can also identify areas for improvement in the inspection process based on the user's emotion data and make suggestions to reduce the workload. This allows for an inspection process that takes user emotions into consideration, improving work efficiency.

[0106] The payment automation unit can further estimate the user's emotions and adjust the payment procedure based on the estimated user emotions. For example, if the user is feeling stressed, it can make suggestions to simplify the payment procedure. The payment automation unit can also monitor the user's emotions in real time and issue an alert if the emotion score is high. For example, if the user is feeling dissatisfied, it can identify the cause and suggest improvements. The payment automation unit can also identify areas for improvement in the payment procedure based on the user's emotion data and make suggestions to reduce the workload. This allows for payment procedures that take the user's emotions into consideration, improving work efficiency.

[0107] The payment automation unit can further estimate the user's emotions and monitor the payment status based on the estimated user emotions. For example, if the user is feeling stressed, it can make suggestions to simplify the payment status monitoring. The payment automation unit can also monitor the user's emotions in real time and issue an alert if the emotion score is high. For example, if the user is feeling dissatisfied, it can identify the cause and suggest improvements. The payment automation unit can also identify areas for improvement in payment status monitoring based on the user's emotion data and make suggestions to reduce the workload. This enables payment status monitoring that takes the user's emotions into consideration, improving work efficiency.

[0108] The data extraction unit can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes how the user uses the system and identifies usage patterns. For example, it analyzes what time of day the user usually uploads invoices and which functions the user frequently uses. The behavior analysis unit can also make suggestions to improve system usage efficiency based on the user's behavioral history. For example, it can provide an interface that prioritizes the display of functions the user uses frequently. The behavior analysis unit can also monitor system usage in real time based on the user's behavioral history and issue an alert if abnormal behavior is detected. This makes it possible to analyze user behavior and improve system usage efficiency.

[0109] The inspection automation unit may further include an environmental analysis unit that acquires environmental data and analyzes factors that affect the inspection process. The environmental analysis unit acquires external environmental data, such as weather and traffic conditions, and analyzes how it will affect the inspection process. For example, if a delivery delay due to bad weather affects the inspection process, the environmental analysis unit can predict the impact in advance and propose countermeasures. The environmental analysis unit can also optimize the inspection process schedule based on the external environmental data. For example, it can schedule inspections to avoid times when traffic congestion is expected. The environmental analysis unit can also monitor external environmental data in real time and issue an alert if an abnormality is detected. This makes it possible to improve the efficiency of the inspection process by utilizing external environmental data.

[0110] The payment automation unit can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes how the user uses the system and identifies usage patterns. For example, it analyzes what time of day the user most often performs payment procedures and which functions the user frequently uses. The behavior analysis unit can also make suggestions to improve system usage efficiency based on the user's behavioral history. For example, it can provide an interface that prioritizes the display of functions the user uses frequently. The behavior analysis unit can also monitor system usage in real time based on the user's behavioral history and issue an alert if abnormal behavior is detected. This allows for analysis of user behavior and improvement of system usage efficiency.

[0111] The data extraction unit can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes how the user uses the system and identifies usage patterns. For example, it analyzes what time of day the user usually uploads invoices and which functions the user frequently uses. The behavior analysis unit can also make suggestions to improve system usage efficiency based on the user's behavioral history. For example, it can provide an interface that prioritizes the display of functions the user uses frequently. The behavior analysis unit can also monitor system usage in real time based on the user's behavioral history and issue an alert if abnormal behavior is detected. This makes it possible to analyze user behavior and improve system usage efficiency.

[0112] The payment automation unit may further include an environmental analysis unit that acquires environmental data and analyzes factors that affect the payment procedure. The environmental analysis unit acquires external environmental data, such as weather and traffic conditions, and analyzes how it will affect the payment procedure. For example, if a delivery delay due to bad weather affects the payment procedure, the environmental analysis unit can predict the impact in advance and propose countermeasures. The environmental analysis unit can also optimize the payment procedure schedule based on the external environmental data. For example, it can schedule payments to avoid times when traffic congestion is expected. The environmental analysis unit can also monitor external environmental data in real time and issue an alert if an abnormality is detected. This makes it possible to utilize external environmental data to improve the efficiency of payment procedures.

[0113] The processing flow of the second embodiment will be briefly explained below.

[0114] Step 1: The invoice uploading section uploads the invoice. For example, an image or PDF file of the invoice can be uploaded to the system. Handwritten invoices can also be scanned and converted into digital data. Step 2: The data extraction unit analyzes the uploaded invoice content and extracts the necessary data. For example, OCR technology can be used to automatically read the invoice issue date, invoice amount, payee information, etc. Text mining technology can also be used to analyze the invoice content and extract the necessary data. Step 3: The Inspection Automation Department automates the inspection process based on the extracted data. For example, it can compare the contents of the invoice with the contents of the purchase order to ensure they match. It can also compare them with delivery notes and receipts to ensure that the goods and services actually delivered match those listed on the invoice. Step 4: After inspection is complete, the payment automation unit automates the payment process. For example, it generates payment instructions based on the recipient's bank account information and sends them to the bank system. It can also manage payment schedules to ensure payments are made on time.

[0115] 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.

[0116] 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 generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] 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.

[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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

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

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0144] 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.

[0145] 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.

[0146] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] 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.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0160] 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.

[0161] 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.

[0162] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0181] 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. [Explanation of symbols]

[0182] 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 invoice upload section for uploading invoices; a data extraction unit that analyzes the contents of the invoice uploaded by the invoice upload unit and extracts necessary data; an inspection automation unit that automates an inspection process based on the data extracted by the data extraction unit; and a payment automation unit that automates payment procedures after the inspection automation unit completes the inspection. A system characterized by:

2. The data extraction unit Automatically read the invoice issue date, invoice amount, and payment destination information 2. The system of claim 1.

3. The inspection automation unit includes: Compare the contents of the invoice with the contents of the purchase order to confirm that they match 2. The system of claim 1.

4. The payment automation unit The payment instruction is generated based on the bank account information of the payee and sent to the bank system.

2. The system of claim 1.

5. The payment automation unit Notify you if the payment is late or if the payment is complete 2. The system of claim 1.

Images