system

Abstract

An object of a system according to an embodiment is to detect an error in an accounting process and efficiently create a defense plan at the time of tax investigation.SOLUTION: A system according to an embodiment includes a document reading unit, an analyzing unit, a notifying unit, and a defense plan creating unit. The document reading unit reads documents such as a contract document and an approval document of a transaction, and mail and EDI exchange with a business partner. The analysis unit analyzes the document read by the document reading unit and analyzes a possibility that there is an error in the accounting processing. The notification unit notifies the person in charge based on the result analyzed by the analysis unit. A defense plan preparation part prepares a defense plan in tax investigation.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, detecting accounting errors and preparing defenses during tax audits required time and effort, placing a heavy burden on tax personnel.

[0005] The system according to the embodiment aims to detect accounting errors and efficiently prepare defense proposals during tax audits. [Means for solving the problem]

[0006] The system according to the embodiment includes a document reading unit, an analysis unit, a notification unit, and a counterargument preparation unit. The document reading unit reads documents such as transaction contracts and approval documents, as well as emails and EDI exchanges with business partners. The analysis unit analyzes the documents read by the document reading unit and analyzes the possibility of accounting errors. The notification unit notifies the responsible person based on the results of the analysis by the analysis unit. The counterargument preparation unit prepares counterarguments during tax audits. [Effects of the Invention]

[0007] The system according to the embodiment can detect accounting errors and efficiently prepare defenses during tax audits. [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 accounting optimization system according to the embodiment of the present invention is a system that automatically checks the accuracy of a company's accounting procedures, notifies the person in charge if an error is found, and encourages appropriate processing. As a result, the accounting optimization system can automatically detect errors in a company's accounting procedures and encourage appropriate processing.

[0029] The accounting processing optimization system according to the embodiment includes a document reading unit, an analysis unit, a notification unit, and a counterargument preparation unit. The document reading unit reads documents such as transaction contracts, approval documents, emails, and EDI exchanges with business partners. For example, the document reading unit converts handwritten documents into digital data using OCR technology. The document reading unit can also directly read emails and EDI data. The analysis unit analyzes the documents read by the document reading unit and analyzes the possibility of accounting processing errors. For example, the analysis unit analyzes the content of the document using generative AI to evaluate the appropriateness of the accounting processing. The analysis unit can also determine the appropriateness of transactions based on tax law and legal precedents. The notification unit notifies the responsible person based on the results of the analysis by the analysis unit. For example, the notification unit notifies the responsible person via chat to encourage appropriate processing. The notification unit can also notify using email or alerts. The counterargument preparation unit prepares a counterargument during a tax audit. For example, the defense proposal preparation unit uses generation AI to prepare a defense proposal based on the findings of a tax auditor. The defense proposal preparation unit can also prepare a defense proposal by referring to the results of past tax investigations. As a result, the accounting processing optimization system according to the embodiment can automatically detect errors in a company's accounting processing and encourage proper processing. For example, the system can notify the person in charge to encourage proper processing and provide a defense proposal during a tax investigation.

[0030] The analysis unit can determine appropriateness based on prompts containing information about tax laws and legal precedents. For example, when the generation AI learns tax laws and legal precedents, the analysis unit imports past tax investigation results into a database and makes appropriateness judgments based on these. For example, it learns from cases pointed out in past tax investigations and detects similar errors. The analysis unit also allows the generation AI to import a company's financial data and compare it with tax laws and legal precedents to determine appropriateness. For example, it analyzes a company's financial statements and transaction history to identify transactions that may violate tax laws. The analysis unit also allows the generation AI to integrate past tax investigation results with the company's financial data to make more accurate appropriateness judgments. For example, it evaluates the likelihood that a specific transaction pattern violates tax laws based on past investigation results. This allows appropriateness to be determined based on tax laws and legal precedents.

[0031] The analysis unit can evaluate the appropriateness of a transaction by analyzing the contents of contracts and email exchanges with business partners. For example, the generation AI in the analysis unit learns international tax laws and legal precedents and determines appropriateness from a global perspective. For example, it incorporates OECD tax law guidelines and legal precedents from each country to evaluate the appropriateness of international transactions. The generation AI also incorporates the tax laws and legal precedents of each country into a database and determines the appropriateness of international transactions. For example, it evaluates the appropriateness of cross-border transactions based on the tax laws of different countries. The generation AI in the analysis unit also learns international tax laws and legal precedents and determines the appropriateness of a company's global transactions. For example, it evaluates the appropriateness of transactions from a global perspective based on the results of international tax investigations. This makes it possible to analyze contracts and email exchanges with business partners and evaluate the appropriateness of transactions.

[0032] The notification unit can conduct chat-based interviews with the person in charge when there is a possibility of an error in accounting processing, and encourage proper processing. The notification unit, for example, uses an emotion estimation function to collect the user's emotional reactions to interpretations of tax laws and precedents in real time, and provide an interpretation that is easy for the user to understand. For example, if the user is confused, the notification unit provides a more detailed explanation. The notification unit also uses the emotion estimation function to analyze the user's emotional reactions to interpretations of tax laws and precedents, and provides an interpretation that elicits positive emotions. For example, the notification unit preferentially presents interpretations that give the user a sense of security. The notification unit also uses the emotion estimation function to collect the user's emotional reactions to interpretations of tax laws and precedents, and uses this to help improve the interpretation. For example, the content of the interpretation is adjusted based on user feedback. As a result, when there is an error in accounting processing, the notification unit can conduct chat-based interviews with the person in charge, and encourage proper processing.

[0033] The defense proposal preparation unit can prepare a defense proposal based on the points raised by the tax auditor. In the defense proposal preparation unit, for example, the generation AI learns not only tax law and precedents, but also related economic news and market trends to make a comprehensive judgment on appropriateness. For example, it evaluates the appropriateness of a transaction based on the latest economic news. In addition, the defense proposal preparation unit incorporates market trends and judges appropriateness in light of tax law and precedents. For example, it evaluates the impact of specific market trends on tax law and judges the appropriateness of a transaction. In addition, the defense proposal preparation unit learns economic news and market trends, and integrates them with tax law and precedents to judge appropriateness. For example, it evaluates the possibility that a specific transaction violates tax law based on economic news. This allows a defense proposal to be prepared based on the points raised by the tax auditor.

[0034] The analysis unit incorporates past tax investigation results and corporate financial data to make more accurate judgments on appropriateness. For example, when the generation AI learns tax laws and precedents, the analysis unit imports past tax investigation results into a database and makes judgments on appropriateness based on these. For example, it learns from cases pointed out in past tax investigations and detects similar errors. The analysis unit also allows the generation AI to import corporate financial data and judge appropriateness by comparing it with tax laws and precedents. For example, it analyzes corporate financial statements and transaction history to identify transactions that may violate tax laws. The analysis unit also allows the generation AI to integrate past tax investigation results with corporate financial data to make more accurate judgments on appropriateness. For example, it evaluates the likelihood that a specific transaction pattern violates tax laws based on past investigation results. This allows the generation AI to incorporate past tax investigation results and corporate financial data to make more accurate judgments on appropriateness.

[0035] The analysis unit learns international tax laws and legal precedents and can make judgments on appropriateness from a global perspective. In the analysis unit, for example, the generation AI learns international tax laws and legal precedents and judges appropriateness from a global perspective. For example, it incorporates OECD tax law guidelines and legal precedents from each country to evaluate the appropriateness of international transactions. In addition, the generation AI imports each country's tax laws and legal precedents into a database and makes judgments on appropriateness for international transactions. For example, it evaluates the appropriateness of cross-border transactions based on the tax laws of different countries. In addition, the analysis unit learns international tax laws and legal precedents and judges the appropriateness of a company's global transactions. For example, it evaluates the appropriateness of transactions from a global perspective based on the results of international tax investigations. This allows it to learn international tax laws and legal precedents and make judgments on appropriateness from a global perspective.

[0036] The analysis unit can study related economic news and market trends in addition to tax laws and legal precedents, and make comprehensive judgments on appropriateness. For example, the generation AI can study related economic news and market trends in addition to tax laws and legal precedents, and make comprehensive judgments on appropriateness. For example, the analysis unit evaluates the appropriateness of a transaction based on the latest economic news. The generation AI can also incorporate market trends and judge appropriateness in light of tax laws and legal precedents. For example, the analysis unit can evaluate the impact of specific market trends on tax laws and judge the appropriateness of a transaction. The generation AI can also learn economic news and market trends, and integrate them with tax laws and legal precedents to make judgments on appropriateness. For example, the analysis unit can evaluate the possibility that a specific transaction violates tax laws based on economic news. This allows the generation AI to study related economic news and market trends in addition to tax laws and legal precedents, and make comprehensive judgments on appropriateness.

[0037] The document reading unit also analyzes the intentions and background information of the document creator, enabling more accurate judgments of appropriateness. For example, when the generation AI reads a document, the document reading unit analyzes the intentions of the document creator and reflects this in the judgment of appropriateness. For example, it understands the intention behind the creation of a contract and evaluates the appropriateness of the transaction. The document reading unit also allows the generation AI to analyze the background information of the document and use this information to help with the judgment of appropriateness. For example, it evaluates the appropriateness of the current transaction based on past interactions with a business partner. The document reading unit also allows the generation AI to integrate the intentions and background information of the document creator and make more accurate judgments of appropriateness. For example, it analyzes the background information of a request form and evaluates the appropriateness of the transaction. This allows the intentions and background information of the document creator to be analyzed and more accurate judgments of appropriateness to be made.

[0038] The document reading unit adds a function to detect document tampering or unauthorized changes, thereby improving reliability. For example, the document reading unit adds a function to detect tampering or unauthorized changes when the generation AI analyzes a document. For example, it checks whether the contents of a contract have been tampered with. The document reading unit also introduces an algorithm to detect tampering or unauthorized changes so that the generation AI can improve the reliability of documents. For example, it checks whether the contents of emails with business partners have been unauthorizedly changed. The document reading unit also builds a system in which the generation AI detects document tampering or unauthorized changes, improving reliability. For example, it checks whether EDI exchanges have been unauthorizedly changed. This adds a function to detect document tampering or unauthorized changes, thereby improving reliability.

[0039] The document reading unit analyzes audio and video data in addition to documents, and can make appropriateness judgments based on multimodal information. In the document reading unit, for example, the generation AI analyzes audio data in addition to documents to evaluate the appropriateness of a transaction. For example, it analyzes audio data from a conference call with a business partner to determine the appropriateness of the transaction. In the document reading unit, the generation AI analyzes video data to evaluate the appropriateness of a transaction. For example, it analyzes the content of a video conference with a business partner to determine the appropriateness of the transaction. In the document reading unit, the generation AI integrates and analyzes document, audio, and video data to evaluate the appropriateness of a transaction based on multimodal information. For example, it integrates the content of a contract and the content of a conversation with a business partner to determine appropriateness. This allows it to analyze audio and video data in addition to documents, and make appropriateness judgments based on multimodal information.

[0040] The document reading unit automatically translates the contents of the analyzed document into different languages ​​and can judge the appropriateness from an international perspective. For example, the document reading unit automatically translates the contents of a document analyzed by the generation AI into different languages ​​and judges the appropriateness from an international perspective. For example, it translates a Japanese contract into English and evaluates the appropriateness for international transactions. The document reading unit also translates the contents of a document into multiple languages ​​and evaluates the appropriateness for transactions in different languages. For example, it translates an English email into French and judges the appropriateness of the transaction. The document reading unit also builds a system in which the generation AI automatically translates the contents of a document and judges the appropriateness from an international perspective. For example, it translates EDI exchanges into multiple languages ​​and evaluates the appropriateness of the transaction. This makes it possible to automatically translate the contents of an analyzed document into different languages ​​and judge the appropriateness from an international perspective.

[0041] The notification unit can ask more accurate questions by referring to the results of past interviews and the response history of the person in charge. In the notification unit, for example, the generation AI refers to the results of past interviews and asks more accurate questions to the person in charge. For example, it asks additional questions based on information obtained in past interviews. In addition, the notification unit allows the generation AI to analyze the response history of the person in charge and generate appropriate questions. For example, it asks questions about unresolved issues based on the content of past responses. In addition, the notification unit allows the generation AI to integrate the results of past interviews and the response history of the person in charge and ask more accurate questions. For example, it generates appropriate questions based on information obtained in past interviews and the content of current responses. This allows more accurate questions to be asked by referring to the results of past interviews and the response history of the person in charge.

[0042] The notification unit is able to ask questions at the optimal timing, taking into consideration the workload and schedule of the person in charge. For example, the generation AI in the notification unit analyzes the workload of the person in charge and asks questions at the optimal timing. For example, questions are asked during times when there is less work based on the person in charge's schedule. The generation AI in the notification unit also takes into consideration the person in charge's schedule and interviews at the appropriate timing. For example, questions are asked by referencing the person in charge's calendar during times when there are no meetings or important work. The generation AI in the notification unit also integrates and analyzes the workload and schedule of the person in charge and asks questions at the optimal timing. For example, interviews are conducted during times when there is less work. This allows questions to be asked at the optimal timing, taking into consideration the workload and schedule of the person in charge.

[0043] The notification unit supports voice input and video calls in addition to chat-based hearings, thereby providing a wider variety of communication methods. For example, the notification unit allows the generation AI to support voice input in addition to chat-based hearings, thereby providing a wider variety of communication methods. For example, it allows the agent to respond by voice. The notification unit also allows the generation AI to support video calls, thereby complementing chat-based hearings. For example, it allows the agent to provide detailed explanations via video calls. The notification unit also allows the generation AI to integrate voice input and video calls, thereby providing a wider variety of communication methods. For example, it allows the agent to select either chat, voice, or video calls. This allows the generation AI to support voice input and video calls in addition to chat-based hearings, thereby providing a wider variety of communication methods.

[0044] The notification department can also collaborate with personnel from different departments and positions to collect comprehensive information. For example, the generation AI in the notification department collaborates with personnel from different departments to collect comprehensive information. For example, it collects information from personnel from the accounting department and sales department, and evaluates the appropriateness of the transaction. The generation AI in the notification department also collaborates with personnel from different positions to collect comprehensive information. For example, it collects information from personnel from different positions, such as department managers and section managers, and evaluates the appropriateness of the transaction. The generation AI in the notification department also collaborates with personnel from different departments and positions to build a system for comprehensive information collection. For example, it integrates information from multiple personnel and evaluates the appropriateness of the transaction. This makes it possible to collaborate with personnel from different departments and positions to collect comprehensive information.

[0045] The defense proposal creation unit can refer to past successful and unsuccessful cases to generate a more effective defense proposal. In the defense proposal creation unit, for example, the generation AI refers to past successful cases to generate an effective defense proposal. For example, a new defense proposal is created based on defense proposals that were successful in past tax audits. In addition, the defense proposal creation unit can refer to past unsuccessful cases to generate a defense proposal to avoid failure. For example, a defense proposal that reflects improvements based on cases that failed in past tax audits is created. In addition, the defense proposal creation unit can integrate past successful and unsuccessful cases to generate a more effective defense proposal. For example, a defense proposal that incorporates elements of successful cases and reflects improvements from unsuccessful cases is created. In this way, more effective defense proposals can be generated by referring to past successful and unsuccessful cases.

[0046] The counterargument preparation unit can analyze the tax auditor's past tendency and style of pointing out issues and provide a counterargument that is optimized accordingly. In the counterargument preparation unit, for example, a generation AI analyzes the tax auditor's past tendency of pointing out issues and provides a counterargument that is optimized accordingly. For example, a counterargument preparation unit creates a counterargument based on points that a particular auditor often points out. In addition, the counterargument preparation unit can analyze the tax auditor's style and provide a counterargument that is optimized accordingly. For example, a counterargument preparation unit creates a counterargument based on the auditor's questioning style and how the auditor points out issues. In addition, the counterargument preparation unit can integrate and analyze the tax auditor's past tendency and style of pointing out issues and provide a counterargument that is optimized accordingly. For example, an optimal counterargument is created based on the tax auditor's tendency and style of pointing out issues. In this way, it is possible to analyze the tax auditor's past tendency and style of pointing out issues and provide a counterargument that is optimized accordingly.

[0047] The defense proposal preparation unit can provide multilingual defense proposals that can be used for tax audits in different jurisdictions or countries. For example, the defense proposal preparation unit uses a generation AI to create defense proposals that can be used for tax audits in different jurisdictions. For example, defense proposals are provided that can be used for tax audits in Japan and the United States. The defense proposal preparation unit also uses a generation AI to create multilingual defense proposals that can be used for tax audits in different countries. For example, defense proposals are created in English and French to be used for international tax audits. The defense proposal preparation unit also builds a system that provides multilingual defense proposals that can be used for tax audits in different jurisdictions or countries. For example, defense proposals based on the tax laws of each country are provided in multiple languages. This makes it possible to provide multilingual defense proposals that can be used for tax audits in different jurisdictions or countries.

[0048] The counterargument preparation unit can evaluate the prepared counterargument plans in advance using a simulation tool and select the optimal counterargument plan. For example, the counterargument preparation unit evaluates the counterargument plans prepared by the generation AI using a simulation tool and selects the optimal counterargument plan. For example, it selects the most effective counterargument plan based on the simulation results. The counterargument preparation unit also evaluates the counterargument plans prepared by the generation AI in advance using a simulation tool and reflects areas for improvement. For example, it modifies the counterargument plan based on the simulation results. The counterargument preparation unit also builds a system that evaluates the counterargument plans prepared by the generation AI using a simulation tool and selects the optimal counterargument plan. For example, it reflects the simulation results in real time and provides the optimal counterargument plan. This makes it possible to evaluate the prepared counterargument plans in advance using a simulation tool and select the optimal counterargument plan.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The accounting optimization system can further include a data visualization unit. The data visualization unit visually displays accounting errors detected by the analysis unit and the results of the appropriateness assessment. For example, it can use graphs and charts to show the frequency and trends of errors. The data visualization unit can also display information using color coding and icons to make it easy for personnel to understand. Furthermore, the data visualization unit can also be equipped with a function to evaluate the current situation by comparing it with past data. This makes it easier for personnel to visually grasp the information, enabling quick and appropriate responses.

[0051] The accounting optimization system can further include a risk assessment unit. The risk assessment unit evaluates the risk level of accounting errors detected by the analysis unit. For example, if an error has the potential to pose a significant financial risk, it is evaluated as a high risk. The risk assessment unit can also determine the risk level by taking into account the scope of the error's impact and the cost required to correct it. Furthermore, the risk assessment unit can notify the person in charge of the risk assessment results and indicate errors that should be addressed as a priority. This allows the person in charge to respond quickly to high-risk errors and maintain the financial soundness of the company.

[0052] The accounting processing optimization system can further include an education support unit. The education support unit provides training content to the person in charge based on the accounting processing errors detected by the analysis unit. For example, it can provide videos or documents that explain the causes of the errors and the proper processing methods. The education support unit can also evaluate the person in charge's level of understanding and provide additional training content as needed. Furthermore, the education support unit can provide information on the latest tax laws and accounting standards, which are updated regularly, to keep the person in charge's knowledge up to date. This allows the person in charge to acquire the knowledge to prevent errors and perform proper accounting processing.

[0053] The accounting processing optimization system can further include a feedback collection unit. The feedback collection unit collects feedback from the person in charge regarding the accounting processing errors detected by the analysis unit. For example, it collects the person in charge's opinions and suggestions regarding the cause of the error and how to correct it. The feedback collection unit can also analyze the collected feedback and use it to improve the system. Furthermore, the feedback collection unit can adjust the analysis algorithm and notification method based on the person in charge's feedback. This allows the system to respond flexibly to the needs of the person in charge, further improving the accuracy of accounting processing.

[0054] The accounting optimization system can further include a predictive analysis unit. The predictive analysis unit predicts the likelihood of future errors based on past accounting data and error patterns. For example, it analyzes trends in which errors are likely to occur during specific periods or transactions, and notifies the person in charge of the prediction results. The predictive analysis unit can also provide advice for taking measures in advance based on the prediction results. Furthermore, the predictive analysis unit can visually display the prediction results so that the person in charge can easily understand them. This allows the person in charge to take measures to prevent future errors and maintain the accuracy of accounting procedures.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The document reader reads documents such as transaction contracts, approval documents, emails with business partners, and EDI exchanges. For example, the document reader uses OCR technology to convert handwritten documents into digital data. The document reader can also directly read emails and EDI data. Step 2: The analysis unit analyzes the document read by the document reading unit and analyzes the possibility of errors in the accounting process. For example, the analysis unit may use a generative AI to analyze the content of the document and evaluate the appropriateness of the accounting process. The analysis unit may also determine the appropriateness of the transaction based on tax laws and legal precedents. Step 3: The notification unit notifies the person in charge based on the results of the analysis by the analysis unit. For example, the notification unit may notify the person in charge via chat and prompt them to take appropriate action. The notification unit may also notify them using email or an alert. Step 4: The defense preparation department prepares a defense during a tax audit. For example, the defense preparation department uses generation AI to prepare a defense based on the findings of the tax auditor. The defense preparation department can also create a defense by referencing the results of past tax audits.

[0057] (Example 2) The accounting optimization system according to the embodiment of the present invention is a system that automatically checks the accuracy of a company's accounting procedures, notifies the person in charge if an error is found, and encourages appropriate processing. As a result, the accounting optimization system can automatically detect errors in a company's accounting procedures and encourage appropriate processing.

[0058] The accounting processing optimization system according to the embodiment includes a document reading unit, an analysis unit, a notification unit, and a counterargument preparation unit. The document reading unit reads documents such as transaction contracts, approval documents, emails, and EDI exchanges with business partners. For example, the document reading unit converts handwritten documents into digital data using OCR technology. The document reading unit can also directly read emails and EDI data. The analysis unit analyzes the documents read by the document reading unit and analyzes the possibility of accounting processing errors. For example, the analysis unit analyzes the content of the document using generative AI to evaluate the appropriateness of the accounting processing. The analysis unit can also determine the appropriateness of transactions based on tax law and legal precedents. The notification unit notifies the responsible person based on the results of the analysis by the analysis unit. For example, the notification unit notifies the responsible person via chat to encourage appropriate processing. The notification unit can also notify using email or alerts. The counterargument preparation unit prepares a counterargument during a tax audit. For example, the defense proposal preparation unit uses generation AI to prepare a defense proposal based on the findings of a tax auditor. The defense proposal preparation unit can also prepare a defense proposal by referring to the results of past tax investigations. As a result, the accounting processing optimization system according to the embodiment can automatically detect errors in a company's accounting processing and encourage proper processing. For example, the system can notify the person in charge to encourage proper processing and provide a defense proposal during a tax investigation.

[0059] The analysis unit can determine appropriateness based on prompts containing information about tax laws and legal precedents. For example, when the generation AI learns tax laws and legal precedents, the analysis unit imports past tax investigation results into a database and makes appropriateness judgments based on these. For example, it learns from cases pointed out in past tax investigations and detects similar errors. The analysis unit also allows the generation AI to import a company's financial data and compare it with tax laws and legal precedents to determine appropriateness. For example, it analyzes a company's financial statements and transaction history to identify transactions that may violate tax laws. The analysis unit also allows the generation AI to integrate past tax investigation results with the company's financial data to make more accurate appropriateness judgments. For example, it evaluates the likelihood that a specific transaction pattern violates tax laws based on past investigation results. This allows appropriateness to be determined based on tax laws and legal precedents.

[0060] The analysis unit can evaluate the appropriateness of a transaction by analyzing the contents of contracts and email exchanges with business partners. For example, the generation AI in the analysis unit learns international tax laws and legal precedents and determines appropriateness from a global perspective. For example, it incorporates OECD tax law guidelines and legal precedents from each country to evaluate the appropriateness of international transactions. The generation AI also incorporates the tax laws and legal precedents of each country into a database and determines the appropriateness of international transactions. For example, it evaluates the appropriateness of cross-border transactions based on the tax laws of different countries. The generation AI in the analysis unit also learns international tax laws and legal precedents and determines the appropriateness of a company's global transactions. For example, it evaluates the appropriateness of transactions from a global perspective based on the results of international tax investigations. This makes it possible to analyze contracts and email exchanges with business partners and evaluate the appropriateness of transactions.

[0061] The notification unit can conduct chat-based interviews with the person in charge when there is a possibility of an error in accounting processing, and encourage proper processing. The notification unit, for example, uses an emotion estimation function to collect the user's emotional reactions to interpretations of tax laws and precedents in real time, and provide an interpretation that is easy for the user to understand. For example, if the user is confused, the notification unit provides a more detailed explanation. The notification unit also uses the emotion estimation function to analyze the user's emotional reactions to interpretations of tax laws and precedents, and provides an interpretation that elicits positive emotions. For example, the notification unit preferentially presents interpretations that give the user a sense of security. The notification unit also uses the emotion estimation function to collect the user's emotional reactions to interpretations of tax laws and precedents, and uses this to help improve the interpretation. For example, the content of the interpretation is adjusted based on user feedback. As a result, when there is an error in accounting processing, the notification unit can conduct chat-based interviews with the person in charge, and encourage proper processing.

[0062] The defense proposal preparation unit can prepare a defense proposal based on the points raised by the tax auditor. In the defense proposal preparation unit, for example, the generation AI learns not only tax law and precedents, but also related economic news and market trends to make a comprehensive judgment on appropriateness. For example, it evaluates the appropriateness of a transaction based on the latest economic news. In addition, the defense proposal preparation unit incorporates market trends and judges appropriateness in light of tax law and precedents. For example, it evaluates the impact of specific market trends on tax law and judges the appropriateness of a transaction. In addition, the defense proposal preparation unit learns economic news and market trends, and integrates them with tax law and precedents to judge appropriateness. For example, it evaluates the possibility that a specific transaction violates tax law based on economic news. This allows a defense proposal to be prepared based on the points raised by the tax auditor.

[0063] The analysis unit incorporates past tax investigation results and corporate financial data to make more accurate judgments on appropriateness. For example, when the generation AI learns tax laws and precedents, the analysis unit imports past tax investigation results into a database and makes judgments on appropriateness based on these. For example, it learns from cases pointed out in past tax investigations and detects similar errors. The analysis unit also allows the generation AI to import corporate financial data and judge appropriateness by comparing it with tax laws and precedents. For example, it analyzes corporate financial statements and transaction history to identify transactions that may violate tax laws. The analysis unit also allows the generation AI to integrate past tax investigation results with corporate financial data to make more accurate judgments on appropriateness. For example, it evaluates the likelihood that a specific transaction pattern violates tax laws based on past investigation results. This allows the generation AI to incorporate past tax investigation results and corporate financial data to make more accurate judgments on appropriateness.

[0064] The analysis unit learns international tax laws and legal precedents and can make judgments on appropriateness from a global perspective. In the analysis unit, for example, the generation AI learns international tax laws and legal precedents and judges appropriateness from a global perspective. For example, it incorporates OECD tax law guidelines and legal precedents from each country to evaluate the appropriateness of international transactions. In addition, the generation AI imports each country's tax laws and legal precedents into a database and makes judgments on appropriateness for international transactions. For example, it evaluates the appropriateness of cross-border transactions based on the tax laws of different countries. In addition, the analysis unit learns international tax laws and legal precedents and judges the appropriateness of a company's global transactions. For example, it evaluates the appropriateness of transactions from a global perspective based on the results of international tax investigations. This allows it to learn international tax laws and legal precedents and make judgments on appropriateness from a global perspective.

[0065] The analysis unit can analyze the user's emotional reactions to the interpretations of tax laws and legal precedents and provide an interpretation that is easy for the user to understand. For example, the analysis unit uses an emotion estimation function to collect the user's emotional reactions to the interpretations of tax laws and legal precedents in real time and provide an interpretation that is easy for the user to understand. For example, if the user is confused, the analysis unit provides a more detailed explanation. The analysis unit also uses the emotion estimation function to analyze the user's emotional reactions to the interpretations of tax laws and legal precedents and provide an interpretation that elicits positive emotions. For example, the analysis unit preferentially presents interpretations that give the user a sense of security. The analysis unit also uses the emotion estimation function to collect the user's emotional reactions to the interpretations of tax laws and legal precedents and use this to improve the interpretations. For example, the analysis unit adjusts the content of the interpretation based on user feedback. In this way, the analysis unit can analyze the user's emotional reactions to the interpretations of tax laws and legal precedents and provide an interpretation that is easy for the user to understand.

[0066] The analysis unit can study related economic news and market trends in addition to tax laws and legal precedents, and make comprehensive judgments on appropriateness. For example, the generation AI can study related economic news and market trends in addition to tax laws and legal precedents, and make comprehensive judgments on appropriateness. For example, the analysis unit evaluates the appropriateness of a transaction based on the latest economic news. The generation AI can also incorporate market trends and judge appropriateness in light of tax laws and legal precedents. For example, the analysis unit can evaluate the impact of specific market trends on tax laws and judge the appropriateness of a transaction. The generation AI can also learn economic news and market trends, and integrate them with tax laws and legal precedents to make judgments on appropriateness. For example, the analysis unit can evaluate the possibility that a specific transaction violates tax laws based on economic news. This allows the generation AI to study related economic news and market trends in addition to tax laws and legal precedents, and make comprehensive judgments on appropriateness.

[0067] The analysis unit collects the user's emotional reactions to the tax law and legal precedent learning content, and can use the collected information to improve the learning content. For example, the analysis unit uses an emotion estimation function to collect the user's emotional reactions to the tax law and legal precedent learning content in real time, and can use the collected information to improve the learning content. For example, the analysis unit adjusts the learning content to make it easier for the user to understand. The analysis unit also uses the emotion estimation function to analyze the user's emotional reactions to the tax law and legal precedent learning content, and provides learning content that elicits positive emotions. For example, the analysis unit preferentially presents learning content that gives the user a sense of security. The analysis unit also uses the emotion estimation function to collect the user's emotional reactions to the tax law and legal precedent learning content, and can use the collected information to improve the learning content. For example, the analysis unit adjusts the learning content based on user feedback. In this way, the analysis unit can collect the user's emotional reactions to the tax law and legal precedent learning content, and can use the collected information to improve the learning content.

[0068] The document reading unit also analyzes the intentions and background information of the document creator, enabling more accurate judgments of appropriateness. For example, when the generation AI reads a document, the document reading unit analyzes the intentions of the document creator and reflects this in the judgment of appropriateness. For example, it understands the intention behind the creation of a contract and evaluates the appropriateness of the transaction. The document reading unit also allows the generation AI to analyze the background information of the document and use this information to help with the judgment of appropriateness. For example, it evaluates the appropriateness of the current transaction based on past interactions with a business partner. The document reading unit also allows the generation AI to integrate the intentions and background information of the document creator and make more accurate judgments of appropriateness. For example, it analyzes the background information of a request form and evaluates the appropriateness of the transaction. This allows the intentions and background information of the document creator to be analyzed and more accurate judgments of appropriateness to be made.

[0069] The document reading unit adds a function to detect document tampering or unauthorized changes, thereby improving reliability. For example, the document reading unit adds a function to detect tampering or unauthorized changes when the generation AI analyzes a document. For example, it checks whether the contents of a contract have been tampered with. The document reading unit also introduces an algorithm to detect tampering or unauthorized changes so that the generation AI can improve the reliability of documents. For example, it checks whether the contents of emails with business partners have been unauthorizedly changed. The document reading unit also builds a system in which the generation AI detects document tampering or unauthorized changes, improving reliability. For example, it checks whether EDI exchanges have been unauthorizedly changed. This adds a function to detect document tampering or unauthorized changes, thereby improving reliability.

[0070] The document reading unit analyzes the emotional reactions of the parties to the content of the document and can make an appropriateness judgment that takes emotional factors into consideration. The document reading unit, for example, uses an emotion estimation function to collect the emotional reactions of the parties to the content of the document in real time and use this information to make an appropriateness judgment. For example, the appropriateness of a transaction is evaluated based on the emotional reactions to a business partner's email. The document reading unit also uses the emotion estimation function to analyze the emotional reactions of the parties to the content of the document and make an appropriateness judgment that takes emotional factors into consideration. For example, the appropriateness of a transaction is evaluated based on the emotional reactions of the parties to a request for approval. The document reading unit also uses the emotion estimation function to collect the emotional reactions of the parties to the content of the document and make an appropriateness judgment that takes emotional factors into consideration. For example, the appropriateness of a transaction is evaluated based on the emotional reactions of the parties to a contract. This makes it possible to analyze the emotional reactions of the parties to the content of the document and make an appropriateness judgment that takes emotional factors into consideration.

[0071] The document reading unit analyzes audio and video data in addition to documents, and can make appropriateness judgments based on multimodal information. In the document reading unit, for example, the generation AI analyzes audio data in addition to documents to evaluate the appropriateness of a transaction. For example, it analyzes audio data from a conference call with a business partner to determine the appropriateness of the transaction. In the document reading unit, the generation AI analyzes video data to evaluate the appropriateness of a transaction. For example, it analyzes the content of a video conference with a business partner to determine the appropriateness of the transaction. In the document reading unit, the generation AI integrates and analyzes document, audio, and video data to evaluate the appropriateness of a transaction based on multimodal information. For example, it integrates the content of a contract and the content of a conversation with a business partner to determine appropriateness. This allows it to analyze audio and video data in addition to documents, and make appropriateness judgments based on multimodal information.

[0072] The document reading unit automatically translates the contents of the analyzed document into different languages ​​and can judge the appropriateness from an international perspective. For example, the document reading unit automatically translates the contents of a document analyzed by the generation AI into different languages ​​and judges the appropriateness from an international perspective. For example, it translates a Japanese contract into English and evaluates the appropriateness for international transactions. The document reading unit also translates the contents of a document into multiple languages ​​and evaluates the appropriateness for transactions in different languages. For example, it translates an English email into French and judges the appropriateness of the transaction. The document reading unit also builds a system in which the generation AI automatically translates the contents of a document and judges the appropriateness from an international perspective. For example, it translates EDI exchanges into multiple languages ​​and evaluates the appropriateness of the transaction. This makes it possible to automatically translate the contents of an analyzed document into different languages ​​and judge the appropriateness from an international perspective.

[0073] The document reading unit collects the user's emotional reactions to the content of the document in real time, thereby improving the accuracy of the analysis results. The document reading unit, for example, uses an emotion estimation function to collect the user's emotional reactions to the content of the document in real time, thereby improving the accuracy of the analysis results. For example, the appropriateness of a transaction is evaluated based on the user's emotional reactions to the content of a contract. The document reading unit also uses the emotion estimation function to analyze the user's emotional reactions to the content of the document, thereby improving the accuracy of the analysis results. For example, the appropriateness of a transaction is evaluated based on the user's emotional reactions to the content of an email with a business partner. The document reading unit also uses the emotion estimation function to collect the user's emotional reactions to the content of the document, thereby improving the accuracy of the analysis results. For example, the appropriateness of a transaction is evaluated based on the user's emotional reactions to the content of a request for approval. In this way, the user's emotional reactions to the content of the document are collected in real time, thereby improving the accuracy of the analysis results.

[0074] The notification unit can ask more accurate questions by referring to the results of past interviews and the response history of the person in charge. In the notification unit, for example, the generation AI refers to the results of past interviews and asks more accurate questions to the person in charge. For example, it asks additional questions based on information obtained in past interviews. In addition, the notification unit allows the generation AI to analyze the response history of the person in charge and generate appropriate questions. For example, it asks questions about unresolved issues based on the content of past responses. In addition, the notification unit allows the generation AI to integrate the results of past interviews and the response history of the person in charge and ask more accurate questions. For example, it generates appropriate questions based on information obtained in past interviews and the content of current responses. This allows more accurate questions to be asked by referring to the results of past interviews and the response history of the person in charge.

[0075] The notification unit is able to ask questions at the optimal timing, taking into consideration the workload and schedule of the person in charge. For example, the generation AI in the notification unit analyzes the workload of the person in charge and asks questions at the optimal timing. For example, questions are asked during times when there is less work based on the person in charge's schedule. The generation AI in the notification unit also takes into consideration the person in charge's schedule and interviews at the appropriate timing. For example, questions are asked by referencing the person in charge's calendar during times when there are no meetings or important work. The generation AI in the notification unit also integrates and analyzes the workload and schedule of the person in charge and asks questions at the optimal timing. For example, interviews are conducted during times when there is less work. This allows questions to be asked at the optimal timing, taking into consideration the workload and schedule of the person in charge.

[0076] The notification unit supports voice input and video calls in addition to chat-based hearings, thereby providing a wider variety of communication methods. For example, the notification unit allows the generation AI to support voice input in addition to chat-based hearings, thereby providing a wider variety of communication methods. For example, it allows the agent to respond by voice. The notification unit also allows the generation AI to support video calls, thereby complementing chat-based hearings. For example, it allows the agent to provide detailed explanations via video calls. The notification unit also allows the generation AI to integrate voice input and video calls, thereby providing a wider variety of communication methods. For example, it allows the agent to select either chat, voice, or video calls. This allows the generation AI to support voice input and video calls in addition to chat-based hearings, thereby providing a wider variety of communication methods.

[0077] The notification department can also collaborate with personnel from different departments and positions to collect comprehensive information. For example, the generation AI in the notification department collaborates with personnel from different departments to collect comprehensive information. For example, it collects information from personnel from the accounting department and sales department, and evaluates the appropriateness of the transaction. The generation AI in the notification department also collaborates with personnel from different positions to collect comprehensive information. For example, it collects information from personnel from different positions, such as department managers and section managers, and evaluates the appropriateness of the transaction. The generation AI in the notification department also collaborates with personnel from different departments and positions to build a system for comprehensive information collection. For example, it integrates information from multiple personnel and evaluates the appropriateness of the transaction. This makes it possible to collaborate with personnel from different departments and positions to collect comprehensive information.

[0078] The notification unit can analyze the emotional response of the person in charge to the hearing content and ask questions that elicit positive emotions. The notification unit, for example, uses an emotion estimation function to collect the emotional response of the person in charge to the hearing content in real time and ask questions that elicit positive emotions. For example, it asks questions that make the person in charge feel relaxed. The notification unit also uses the emotion estimation function to analyze the emotional response of the person in charge to the hearing content and ask questions that elicit positive emotions. For example, it prioritizes asking questions that make the person in charge feel at ease. The notification unit also uses the emotion estimation function to collect the emotional response of the person in charge to the hearing content and ask questions that elicit positive emotions. For example, it asks questions that allow the person in charge to answer with a positive attitude. In this way, it is possible to analyze the emotional response of the person in charge to the hearing content and ask questions that elicit positive emotions.

[0079] The defense proposal creation unit can refer to past successful and unsuccessful cases to generate a more effective defense proposal. In the defense proposal creation unit, for example, the generation AI refers to past successful cases to generate an effective defense proposal. For example, a new defense proposal is created based on defense proposals that were successful in past tax audits. In addition, the defense proposal creation unit can refer to past unsuccessful cases to generate a defense proposal to avoid failure. For example, a defense proposal that reflects improvements based on cases that failed in past tax audits is created. In addition, the defense proposal creation unit can integrate past successful and unsuccessful cases to generate a more effective defense proposal. For example, a defense proposal that incorporates elements of successful cases and reflects improvements from unsuccessful cases is created. In this way, more effective defense proposals can be generated by referring to past successful and unsuccessful cases.

[0080] The counterargument preparation unit can analyze the tax auditor's past tendency and style of pointing out issues and provide a counterargument that is optimized accordingly. In the counterargument preparation unit, for example, a generation AI analyzes the tax auditor's past tendency of pointing out issues and provides a counterargument that is optimized accordingly. For example, a counterargument preparation unit creates a counterargument based on points that a particular auditor often points out. In addition, the counterargument preparation unit can analyze the tax auditor's style and provide a counterargument that is optimized accordingly. For example, a counterargument preparation unit creates a counterargument based on the auditor's questioning style and how the auditor points out issues. In addition, the counterargument preparation unit can integrate and analyze the tax auditor's past tendency and style of pointing out issues and provide a counterargument that is optimized accordingly. For example, an optimal counterargument is created based on the tax auditor's tendency and style of pointing out issues. In this way, it is possible to analyze the tax auditor's past tendency and style of pointing out issues and provide a counterargument that is optimized accordingly.

[0081] The counterargument preparation unit can analyze the emotional reaction of the person in charge to the counterargument, and create a counterargument that the person in charge can submit with confidence. The counterargument preparation unit, for example, uses an emotion estimation function to collect the emotional reaction of the person in charge to the counterargument in real time, and create a counterargument that the person in charge can submit with confidence. For example, a counterargument that makes the person in charge feel at ease is provided. Further, the counterargument preparation unit uses the emotion estimation function to analyze the emotional reaction of the person in charge to the counterargument, and create a counterargument that the person in charge can submit with confidence. For example, a counterargument that the person in charge can submit with a positive feeling is provided. Further, the counterargument preparation unit uses the emotion estimation function to collect the emotional reaction of the person in charge to the counterargument, and create a counterargument that the person in charge can submit with confidence. For example, a counterargument that the person in charge can agree with is provided. In this way, the emotional reaction of the person in charge to the counterargument can be analyzed, and a counterargument that the person in charge can submit with confidence can be created.

[0082] The defense proposal preparation unit can provide multilingual defense proposals that can be used for tax audits in different jurisdictions or countries. For example, the defense proposal preparation unit uses a generation AI to create defense proposals that can be used for tax audits in different jurisdictions. For example, defense proposals are provided that can be used for tax audits in Japan and the United States. The defense proposal preparation unit also uses a generation AI to create multilingual defense proposals that can be used for tax audits in different countries. For example, defense proposals are created in English and French to be used for international tax audits. The defense proposal preparation unit also builds a system that provides multilingual defense proposals that can be used for tax audits in different jurisdictions or countries. For example, defense proposals based on the tax laws of each country are provided in multiple languages. This makes it possible to provide multilingual defense proposals that can be used for tax audits in different jurisdictions or countries.

[0083] The counterargument preparation unit can evaluate the prepared counterargument plans in advance using a simulation tool and select the optimal counterargument plan. For example, the counterargument preparation unit evaluates the counterargument plans prepared by the generation AI using a simulation tool and selects the optimal counterargument plan. For example, it selects the most effective counterargument plan based on the simulation results. The counterargument preparation unit also evaluates the counterargument plans prepared by the generation AI in advance using a simulation tool and reflects areas for improvement. For example, it modifies the counterargument plan based on the simulation results. The counterargument preparation unit also builds a system that evaluates the counterargument plans prepared by the generation AI using a simulation tool and selects the optimal counterargument plan. For example, it reflects the simulation results in real time and provides the optimal counterargument plan. This makes it possible to evaluate the prepared counterargument plans in advance using a simulation tool and select the optimal counterargument plan.

[0084] The counterargument preparation unit can predict the emotional reaction of the tax auditor to the counterargument proposal and prepare the most acceptable counterargument. The counterargument preparation unit, for example, uses an emotion estimation function to predict the emotional reaction of the tax auditor to the counterargument proposal and prepare the most acceptable counterargument. For example, it uses expressions that are easy for the auditor to understand. The counterargument preparation unit also uses the emotion estimation function to analyze the emotional reaction of the tax auditor and prepare an acceptable counterargument. For example, it provides a counterargument that makes the auditor feel positive. The counterargument preparation unit also uses the emotion estimation function to predict the emotional reaction of the tax auditor to the counterargument proposal and builds a system that prepares the most acceptable counterargument. For example, it adjusts the counterargument based on the emotional reaction of the auditor. In this way, it is possible to predict the emotional reaction of the tax auditor to the counterargument proposal and prepare the most acceptable counterargument.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The accounting optimization system can further include a data visualization unit. The data visualization unit visually displays accounting errors detected by the analysis unit and the results of the appropriateness assessment. For example, it can use graphs and charts to show the frequency and trends of errors. The data visualization unit can also display information using color coding and icons to make it easy for personnel to understand. Furthermore, the data visualization unit can also be equipped with a function to evaluate the current situation by comparing it with past data. This makes it easier for personnel to visually grasp the information, enabling quick and appropriate responses.

[0087] The accounting optimization system can further include a risk assessment unit. The risk assessment unit evaluates the risk level of accounting errors detected by the analysis unit. For example, if an error has the potential to pose a significant financial risk, it is evaluated as a high risk. The risk assessment unit can also determine the risk level by taking into account the scope of the error's impact and the cost required to correct it. Furthermore, the risk assessment unit can notify the person in charge of the risk assessment results and indicate errors that should be addressed as a priority. This allows the person in charge to respond quickly to high-risk errors and maintain the financial soundness of the company.

[0088] The accounting processing optimization system can further include an education support unit. The education support unit provides training content to the person in charge based on the accounting processing errors detected by the analysis unit. For example, it can provide videos or documents that explain the causes of the errors and the proper processing methods. The education support unit can also evaluate the person in charge's level of understanding and provide additional training content as needed. Furthermore, the education support unit can provide information on the latest tax laws and accounting standards, which are updated regularly, to keep the person in charge's knowledge up to date. This allows the person in charge to acquire the knowledge to prevent errors and perform proper accounting processing.

[0089] The accounting processing optimization system can further include a feedback collection unit. The feedback collection unit collects feedback from the person in charge regarding the accounting processing errors detected by the analysis unit. For example, it collects the person in charge's opinions and suggestions regarding the cause of the error and how to correct it. The feedback collection unit can also analyze the collected feedback and use it to improve the system. Furthermore, the feedback collection unit can adjust the analysis algorithm and notification method based on the person in charge's feedback. This allows the system to respond flexibly to the needs of the person in charge, further improving the accuracy of accounting processing.

[0090] The accounting optimization system can further include a predictive analysis unit. The predictive analysis unit predicts the likelihood of future errors based on past accounting data and error patterns. For example, it analyzes trends in which errors are likely to occur during specific periods or transactions, and notifies the person in charge of the prediction results. The predictive analysis unit can also provide advice for taking measures in advance based on the prediction results. Furthermore, the predictive analysis unit can visually display the prediction results so that the person in charge can easily understand them. This allows the person in charge to take measures to prevent future errors and maintain the accuracy of accounting procedures.

[0091] The analysis unit can estimate the user's emotions and evaluate the appropriateness of accounting procedures based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit will determine that there is a high possibility of an error and will perform a detailed check. Also, if the user feels relieved, the analysis unit can quickly notify the results of the appropriateness evaluation. Furthermore, the analysis unit can adjust the appropriateness evaluation algorithm based on the user's emotional response. This makes it possible to evaluate the appropriateness of accounting procedures by taking the user's emotions into consideration, resulting in more accurate evaluations of the appropriateness of accounting procedures.

[0092] The notification unit can estimate the user's emotions and select an appropriate notification method based on the estimated user emotions. For example, if the user is feeling stressed, the notification unit can provide a notification using gentle language. If the user is relaxed, the notification unit can provide a concise notification. Furthermore, the notification unit can adjust the content of the notification based on the user's emotional response. This enables notifications that take the user's emotions into consideration, making it easier for the user to perform appropriate accounting procedures.

[0093] The defense proposal creation unit can estimate the user's emotions and create an optimal defense proposal based on the estimated user's emotions. For example, if the user feels anxious, the defense proposal creation unit can provide a defense proposal that gives the user a sense of security. On the other hand, if the user feels confident, the defense proposal creation unit can provide a defense proposal that includes detailed information. Furthermore, the defense proposal creation unit can adjust the content of the defense proposal based on the user's emotional response. This allows the provision of a defense proposal that takes the user's emotions into consideration, enabling an effective response to a tax audit.

[0094] The analysis unit can estimate the user's emotions and evaluate the appropriateness of accounting procedures based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit will determine that there is a high possibility of an error and perform a detailed check. Also, if the user feels relieved, the analysis unit can quickly notify the user of the results of the appropriateness evaluation. Furthermore, the analysis unit can adjust the appropriateness evaluation algorithm based on the user's emotional response. This makes it possible to evaluate the appropriateness of accounting procedures by taking the user's emotions into consideration, resulting in more accurate evaluations of the appropriateness of accounting procedures.

[0095] The notification unit can estimate the user's emotions and select an appropriate notification method based on the estimated user emotions. For example, if the user is feeling stressed, the notification unit can provide a notification using gentle language. If the user is relaxed, the notification unit can provide a concise notification. Furthermore, the notification unit can adjust the content of the notification based on the user's emotional response. This enables notifications that take the user's emotions into consideration, making it easier for the user to perform appropriate accounting procedures.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The document reader reads documents such as transaction contracts, approval documents, emails with business partners, and EDI exchanges. For example, the document reader uses OCR technology to convert handwritten documents into digital data. The document reader can also directly read emails and EDI data. Step 2: The analysis unit analyzes the document read by the document reading unit and analyzes the possibility of errors in the accounting process. For example, the analysis unit may use a generative AI to analyze the content of the document and evaluate the appropriateness of the accounting process. The analysis unit may also determine the appropriateness of the transaction based on tax laws and legal precedents. Step 3: The notification unit notifies the person in charge based on the results of the analysis by the analysis unit. For example, the notification unit may notify the person in charge via chat and prompt them to take appropriate action. The notification unit may also notify them using email or an alert. Step 4: The defense preparation department prepares a defense during a tax audit. For example, the defense preparation department uses generation AI to prepare a defense based on the findings of the tax auditor. The defense preparation department can also create a defense by referencing the results of past tax audits.

[0098] 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.

[0099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> 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.

[0100] 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.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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 area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0152] 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."

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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]

[0165] 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. The document reading section reads documents such as transaction contracts, approval documents, emails with business partners, and EDI exchanges. an analysis unit that analyzes the document read by the document reading unit and analyzes the possibility of an error in the accounting process; a notification unit that notifies a person in charge based on the results of the analysis by the analysis unit; A defense drafting unit that prepares a defense draft during a tax audit. A system characterized by:

2. The analysis unit Determine suitability based on prompts containing information about tax law and case law 2. The system of claim 1.

3. The analysis unit Analyzing the contents of the contract and the email exchanges with the business partner to evaluate the appropriateness of the transaction 2. The system of claim 1.

4. The notification unit If there is a possibility that there is an error in the accounting process, we will conduct a chat-based interview with the person in charge and encourage them to process it properly.

2. The system of claim 1.

5. The defense drafting department Prepare the above-mentioned defense proposal based on the findings of the tax inspector 2. The system of claim 1.

6. The analysis unit Incorporating past tax investigation results and corporate financial data to make more accurate assessments 2. The system of claim 1.

Images