system

Abstract

The system according to the embodiment aims to improve the efficiency of creating checklists for audit work. [Solution] A system according to an embodiment includes an analysis unit, an identification unit, a classification unit, and a creation unit. The analysis unit analyzes electronic documents to be audited and extracts standards, requirements, and risks. The identification unit identifies important audit items based on the information extracted by the analysis unit. The classification unit classifies the audit items identified by the identification unit. The creation unit automatically creates a checklist based on the audit items classified by the classification unit.

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] Conventional techniques have had the problem that creating checklists for audit work requires a significant amount of man-hours.

[0005] The system according to the embodiment aims to improve the efficiency of creating checklists for audit work. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an identification unit, a classification unit, and a creation unit. The analysis unit analyzes the electronic document to be audited and extracts standards, requirements, and risks. The identification unit identifies important audit items based on the information extracted by the analysis unit. The classification unit classifies the audit items identified by the identification unit. The creation unit automatically creates a checklist based on the audit items classified by the classification unit. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency of creating checklists for audit work. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An audit support system according to an embodiment of the present invention analyzes electronic documents to be audited, and a generation AI extracts standards, requirements, and risks. It then identifies, classifies, and organizes important audit items, and automatically creates a checklist. The audit support system analyzes electronic documents to be audited, and a generation AI extracts standards, requirements, and risks. The generation AI then identifies important audit items based on the extracted information. The generation AI then classifies and organizes the identified audit items, and finally automatically creates a checklist. For example, the audit support system inputs electronic documents to be audited. For example, the audit support system extracts audit items based on specific standards from documents to be audited, such as financial reports and internal control documents. The audit support system then uses a generation AI to identify important audit items based on the extracted information. The generation AI then prioritizes and lists high-risk and high-importance items. The audit support system then categorizes and organizes the audit items identified by the generation AI. The generation AI then prioritizes and lists high-risk and high-importance items. Next, the audit support system automatically creates a checklist based on the audit items categorized and organized by the generation AI. This allows the audit support system to improve the efficiency of audit work and reduce the burden on auditors. It also enables accurate audits without overlooking important audit items. This allows the audit support system to improve the efficiency of audit work and reduce the burden on auditors. For example, the audit support system can quickly and accurately analyze electronic documents to be audited and identify important audit items. It also enables accurate audits without overlooking important audit items.

[0029] An audit support system according to an embodiment includes an analysis unit, an identification unit, a classification unit, and a creation unit. The analysis unit analyzes electronic documents to be audited and extracts standards, requirements, and risks. Electronic documents to be audited include, but are not limited to, financial reports, internal control documents, and risk management documents. The analysis unit analyzes the content of the documents using, for example, text analysis technology. The analysis unit can also extract standards, requirements, and risks from the documents using data mining technology. The analysis unit can also analyze the content of the documents using a generation AI to extract standards, requirements, and risks. For example, the generation AI analyzes the content of the documents and extracts information based on specific standards. The identification unit identifies important audit items based on the information extracted by the analysis unit. For example, the identification unit can identify important audit items based on a risk assessment. The identification unit can also identify important audit items based on legal requirements. The identification unit can also identify important audit items based on the extracted information using the generation AI. For example, the generation AI prioritizes listing high-risk or high-importance items. The classification unit classifies the audit items identified by the identification unit. The classification unit, for example, classifies the audit items by category. The classification unit can also classify the audit items by risk level. The classification unit can also classify the identified audit items using a generation AI. For example, the generation AI prioritizes listing high-risk items or high-importance items. The creation unit automatically creates a checklist based on the audit items classified by the classification unit. The creation unit creates a checklist including, for example, details of the items and check methods. The creation unit can also automatically create a checklist based on the classified audit items using the generation AI. For example, the generation AI efficiently creates a checklist based on the classified audit items. As a result, the audit support system according to the embodiment can improve the efficiency of audit work and reduce the burden on auditors. For example, the audit support system can quickly and accurately analyze electronic documents to be audited and identify important audit items. The audit support system also enables accurate audits without overlooking important audit items.

[0030] The analysis unit can apply an appropriate analysis algorithm depending on the type of document during analysis. For example, in the case of a financial report, the analysis unit causes the generation AI to apply an algorithm specialized for financial data analysis. Furthermore, in the case of an internal control document, the analysis unit can also cause the generation AI to apply an algorithm specialized for internal control evaluation. Furthermore, in the case of a risk management document, the analysis unit can also cause the generation AI to apply an algorithm specialized for risk evaluation. In this way, by applying an analysis algorithm depending on the type of document, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the type of document to the generation AI and cause the generation AI to select an appropriate analysis algorithm.

[0031] During analysis, the analysis unit can improve the accuracy of the analysis based on past analysis results. For example, the analysis unit refers to the analysis results of past financial reports and prioritizes analysis of items with similar patterns. The analysis unit can also refer to the analysis results of past internal control documents and prioritize analysis of items with similar risks. The analysis unit can also refer to the analysis results of past risk management documents and prioritize analysis of items with similar risk assessments. In this way, by referring to past analysis results, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis results into the generation AI and have the generation AI improve the accuracy of the analysis.

[0032] During analysis, the analysis unit can determine the priority of analysis based on the submission date and time of the document. For example, the analysis unit can prioritize analyzing recently submitted documents and perform an audit based on the latest information. The analysis unit can also prioritize analyzing documents with an upcoming submission deadline and complete the audit within the deadline. The analysis unit can also postpone analyzing documents with older submission dates and prioritize analyzing the latest information. In this way, by determining the priority of analysis based on the submission date and time of the document, an audit can be performed based on the latest information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission date and time of the document to the generation AI and have the generation AI determine the analysis priority.

[0033] The analysis unit can perform analysis based on the geographical distribution of documents during analysis. For example, the analysis unit can analyze documents from different geographical regions and perform analysis taking into account the characteristics of each region. The analysis unit can also analyze documents from geographically close regions together to efficiently proceed with the analysis. The analysis unit can also prioritize analysis of documents from geographically important regions and evaluate the risk for each region. This makes it possible to perform analysis that reflects the characteristics of each region by taking the geographical distribution of documents into account. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input geographical distribution data of documents to a generation AI and have the generation AI perform the analysis.

[0034] During analysis, the analysis unit can improve the accuracy of the analysis by referring to related literature of the document. The analysis unit, for example, refers to related financial reports and analyzes items with similar patterns. The analysis unit can also refer to related internal control documents and analyze items with similar risks. The analysis unit can also refer to related risk management documents and analyze items with similar risk assessments. In this way, by referring to related literature, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input related literature data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0035] The analysis unit can perform analysis based on the market value of the document during analysis. For example, the analysis unit can prioritize analyzing documents with high market value and extract important information. The analysis unit can also prioritize analyzing documents with high importance, leaving documents with low market value for later analysis. The analysis unit can also take fluctuations in market value into account and perform analysis based on the latest market value. This makes it possible to prioritize analysis of important information by taking the market value of the document into consideration. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input market value data of the document to the generation AI and have the generation AI perform the analysis.

[0036] During the identification process, the identification unit can apply an algorithm that prioritizes identifying high-risk items. For example, the identification unit prioritizes identifying high-risk financial items and listing them as important audit items. The identification unit can also prioritize identifying high-risk internal control items and listing them as important audit items. The identification unit can also prioritize identifying high-risk risk management items and listing them as important audit items. This allows for efficient identification of important audit items by prioritizing high-risk items. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input risk assessment data into a generation AI and have the generation AI identify high-risk items.

[0037] During identification, the identification unit can improve the accuracy of identification based on past identification results. For example, the identification unit refers to identification results from past financial reports and identifies items with similar patterns. The identification unit can also refer to identification results from past internal control documents and identify items with similar risks. The identification unit can also refer to identification results from past risk management documents and identify items with similar risk assessments. In this way, by referring to past identification results, the accuracy of identification is improved. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input past identification result data into the generation AI and have the generation AI improve the accuracy of identification.

[0038] During identification, the identification unit can perform identification based on attribute information of the document submitter. For example, if the submitter is a financial officer, the identification unit can prioritize identifying financial items. Furthermore, if the submitter is an internal control officer, the identification unit can also prioritize identifying internal control items. Furthermore, if the submitter is a risk management officer, the identification unit can also prioritize identifying risk management items. This makes it possible to identify more appropriate audit items by taking into account the attribute information of the document submitter. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input attribute information data of the submitter into the generation AI and have the generation AI perform identification.

[0039] During identification, the identification unit can perform identification based on the geographic distribution of documents. For example, the identification unit can identify documents from different geographical regions and perform identification taking into account the characteristics of each region. The identification unit can also identify documents from geographically close regions together to efficiently proceed with identification. The identification unit can also prioritize identifying documents from geographically important regions and evaluate the risk for each region. This makes it possible to perform identification that reflects the characteristics of each region by taking the geographic distribution of documents into consideration. Some or all of the above-mentioned processing in the identification unit can be performed using, for example, AI, or without AI. For example, the identification unit can input geographical distribution data of documents to a generation AI and have the generation AI perform identification.

[0040] During identification, the identification unit can improve the accuracy of identification by referring to related literature of the document. For example, the identification unit can refer to related financial reports to identify items with similar patterns. The identification unit can also refer to related internal control documents to identify items with similar risks. The identification unit can also refer to related risk management documents to identify items with similar risk assessments. In this way, the accuracy of identification is improved by referring to related literature. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input related literature data into the generation AI and have the generation AI perform improvement of the accuracy of identification.

[0041] The identification unit can perform identification based on the market value of the document during identification. For example, the identification unit can prioritize identifying documents with high market value and extract important information. The identification unit can also prioritize identifying documents with high importance, leaving documents with low market value for later. The identification unit can also take fluctuations in market value into account and perform identification based on the latest market value. This makes it possible to prioritize identifying important information by taking the market value of the document into consideration. Some or all of the above-mentioned processing in the identification unit can be performed using, for example, AI, or can be performed without using AI. For example, the identification unit can input market value data of the document to the generation AI and have the generation AI perform identification.

[0042] The classification unit can improve the accuracy of classification based on the interrelationships between audit items during classification. For example, the classification unit analyzes the interrelationships between audit items and classifies related items together. The classification unit can also take into account the interrelationships between audit items and prioritize classification of items with high importance. The classification unit can also efficiently proceed with classification based on the interrelationships between audit items. In this way, by taking into account the interrelationships between audit items, the accuracy of classification is improved. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input interrelationship data between audit items to the generation AI and cause the generation AI to improve the accuracy of classification.

[0043] The classification unit can perform classification taking into consideration attribute information of the person who submitted the audit items. For example, if the submitter is a financial officer, the classification unit can prioritize classifying financial items. Furthermore, if the submitter is an internal control officer, the classification unit can also prioritize classifying internal control items. Furthermore, if the submitter is a risk management officer, the classification unit can also prioritize classifying risk management items. This enables more appropriate classification by taking into consideration attribute information of the person who submitted the audit items. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input attribute information data of the submitter to the generation AI and have the generation AI perform the classification.

[0044] During classification, the classification unit can weight the classification based on the number of times the audit item is submitted. For example, the classification unit prioritizes classification of audit items that are submitted frequently and sets a high level of importance. The classification unit can also postpone audit items that are submitted less frequently and set a low level of importance. The classification unit can also weight the classification based on the latest submission frequency, taking into account fluctuations in submission frequency. In this way, by weighting the classification based on the submission frequency of the audit item, it is possible to prioritize classification of items with a high level of importance. Some or all of the above-described processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input submission frequency data to a generation AI and have the generation AI perform the weighting of the classification.

[0045] The classification unit can perform classification based on the geographical distribution of the audit items during classification. For example, the classification unit can classify audit items in different geographical regions and perform classification taking into account the characteristics of each region. The classification unit can also classify audit items in geographically close regions together to efficiently proceed with classification. The classification unit can also prioritize classification of audit items in geographically important regions and evaluate the risks of each region. This makes it possible to perform classification that reflects the characteristics of each region by taking the geographical distribution of the audit items into consideration. Some or all of the above-mentioned processing in the classification unit can be performed using, for example, AI, or without AI. For example, the classification unit can input geographical distribution data of the audit items to the generation AI and have the generation AI perform the classification.

[0046] During classification, the classification unit can improve the accuracy of the classification by referring to related literature of the audit items. For example, the classification unit refers to related financial reports and classifies items with similar patterns. The classification unit can also refer to related internal control documents and classify items with similar risks. The classification unit can also refer to related risk management documents and classify items with similar risk assessments. In this way, by referring to related literature, the accuracy of the classification is improved. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input related literature data into the generation AI and have the generation AI improve the accuracy of the classification.

[0047] The classification unit can perform classification based on the market value of the audit items during classification. For example, the classification unit can prioritize classification of audit items with high market value and extract important information. The classification unit can also prioritize classification of audit items with high importance, leaving audit items with low market value for later. The classification unit can also perform classification based on the latest market value, taking into account fluctuations in market value. In this way, important information can be prioritized by taking into account the market value of the audit items. Some or all of the above-mentioned processing in the classification unit can be performed using, for example, AI, or without AI. For example, the classification unit can input market value data of the audit items to the generation AI and have the generation AI perform the classification.

[0048] The creation unit can adjust the level of detail of the checklist based on the importance of the audit items during creation. For example, the creation unit can describe audit items with high importance in detail and simplify items with low importance. The creation unit can also postpone audit items with low importance and prioritize items with high importance. The creation unit can also adjust the level of detail of the checklist based on the latest importance, taking into account changes in importance. In this way, important items can be described in detail by adjusting the level of detail of the checklist based on the importance of the audit items. Some or all of the above-mentioned processing in the creation unit can be performed using, for example, AI, or without AI. For example, the creation unit can input audit item importance data into the generation AI and have the generation AI adjust the level of detail of the checklist.

[0049] When creating a checklist, the creation unit can apply an appropriate creation algorithm depending on the category of the audit item. For example, in the case of financial items, the creation unit can create a checklist by applying an algorithm specialized for financial data analysis. In addition, in the case of internal control items, the creation unit can also create a checklist by applying an algorithm specialized for internal control evaluation. In addition, in the case of risk management items, the creation unit can also create a checklist by applying an algorithm specialized for risk evaluation. In this way, by applying a creation algorithm depending on the category of the audit item, the accuracy of the checklist is improved. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input category data of the audit items into a generation AI and have the generation AI select an appropriate creation algorithm.

[0050] During checklist creation, the creation unit can improve the accuracy of the checklist creation based on past checklist creation results. For example, the creation unit references checklist creation results for past financial reports to create a checklist that includes items with similar patterns. The creation unit can also reference checklist creation results for past internal control documents to create a checklist that includes items with similar risks. The creation unit can also reference checklist creation results for past risk management documents to create a checklist that includes items with similar risk assessments. This improves the accuracy of the creation by referring to past checklist creation results. Some or all of the above-described processing in the creation unit may be performed, for example, using AI, or may be performed without using AI. For example, the creation unit can input past checklist creation result data into the generation AI and have the generation AI improve the accuracy of the creation.

[0051] When creating the checklist, the creation unit can determine the priority of the checklist based on the submission date and time of the audit items. For example, the creation unit can prioritize the most recently submitted audit items in the checklist. The creation unit can also prioritize the audit items with an upcoming submission deadline in the checklist. The creation unit can also postpone audit items with older submission dates and prioritize the most recent information in the checklist. In this way, by determining the priority of the checklist based on the submission date and time of the audit items, audits can be performed based on the most recent information. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the submission date and time data of the audit items into the generation AI and have the generation AI determine the priority of the checklist.

[0052] The creation unit can adjust the order of the checklist based on the relationships between the audit items when creating the checklist. For example, the creation unit can include related audit items together in the checklist to efficiently proceed with the audit. The creation unit can also take into account the relevance of the audit items and prioritize items of high importance in the checklist. The creation unit can also efficiently adjust the order of the checklist based on the relevance of the audit items. This enables efficient audits by adjusting the order of the checklist based on the relevance of the audit items. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input relevance data of the audit items into the generation AI and have the generation AI adjust the order of the checklist.

[0053] During creation, the creation unit can adjust the use of technical terms in the checklist according to the knowledge level of the audit item. For example, the creation unit can create a checklist that uses a lot of technical terms for audit items requiring a high level of expertise. The creation unit can also create a simple checklist that avoids technical terms for audit items requiring a low level of expertise. The creation unit can also adjust the use of technical terms in the checklist based on the latest level of expertise, taking into account changes in the level of expertise. This allows for the creation of a checklist that is easy for users to understand by adjusting the use of technical terms in the checklist according to the level of expertise of the audit item. Some or all of the above-described processing in the creation unit can be performed using, for example, AI, or without AI. For example, the creation unit can input knowledge level data of the audit items into a generation AI and have the generation AI execute the use of technical terms in the checklist.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] During analysis, the analysis unit can apply an appropriate analysis algorithm based on the language of the document. For example, it can apply an English-specific analysis algorithm to an English document, and a Japanese-specific analysis algorithm to a Japanese document. Furthermore, the analysis unit can also apply a combination of analysis algorithms corresponding to each language to a document containing multiple languages. This improves the accuracy of analysis by applying an analysis algorithm appropriate for the language of the document. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the language data of the document into a generation AI and have the generation AI select an appropriate analysis algorithm.

[0056] The classification unit can improve the accuracy of classification based on the interrelationships between audit items during classification. For example, the classification unit can analyze the interrelationships between audit items and classify related items together. The classification unit can also take into account the interrelationships between audit items and prioritize classification of items with high importance. The classification unit can also efficiently proceed with classification based on the interrelationships between audit items. This improves the accuracy of classification by taking into account the interrelationships between audit items. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input interrelationship data between audit items to the generation AI and have the generation AI improve the accuracy of classification.

[0057] During analysis, the analysis unit can determine the priority of analysis based on the submission date and time of the document. For example, the analysis unit can prioritize analyzing recently submitted documents and perform an audit based on the latest information. The analysis unit can also prioritize analyzing documents with an upcoming submission deadline and complete the audit within the deadline. The analysis unit can also postpone analyzing documents with older submission dates and prioritize analyzing the latest information. In this way, by determining the priority of analysis based on the submission date and time of the document, an audit can be performed based on the latest information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission date and time of the document to the generation AI and have the generation AI determine the analysis priority.

[0058] During the identification process, the identification unit can apply an algorithm that prioritizes identifying high-risk items. For example, the identification unit prioritizes identifying high-risk financial items and listing them as important audit items. The identification unit can also prioritize identifying high-risk internal control items and listing them as important audit items. The identification unit can also prioritize identifying high-risk risk management items and listing them as important audit items. In this way, by prioritizing high-risk items, important audit items can be efficiently identified. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input risk assessment data into a generation AI and have the generation AI identify high-risk items.

[0059] The creation unit can adjust the order of the checklist based on the relationships between the audit items when creating the checklist. For example, related audit items can be included together in the checklist to efficiently conduct the audit. The creation unit can also take into account the relevance of the audit items and prioritize items of high importance in the checklist. The creation unit can also efficiently adjust the order of the checklist based on the relevance of the audit items. This enables efficient audits by adjusting the order of the checklist based on the relevance of the audit items. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input relevance data of the audit items into the generation AI and have the generation AI adjust the order of the checklist.

[0060] During analysis, the analysis unit can perform analysis based on the market value of the document. For example, documents with high market value are analyzed with priority to extract important information. The analysis unit can also postpone analyzing documents with low market value and prioritize analyzing documents with high importance. The analysis unit can also take fluctuations in market value into account and perform analysis based on the latest market value. This makes it possible to prioritize analysis of important information by taking the market value of the document into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input market value data of the document into the generation AI and have the generation AI perform the analysis.

[0061] During identification, the identification unit can improve the accuracy of identification based on past identification results. For example, the identification unit can refer to the identification results of past financial reports and identify items with similar patterns. The identification unit can also refer to the identification results of past internal control documents and identify items with similar risks. The identification unit can also refer to the identification results of past risk management documents and identify items with similar risk assessments. In this way, by referring to past identification results, the accuracy of identification is improved. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input past identification result data into the generation AI and have the generation AI improve the accuracy of identification.

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

[0063] Step 1: The analysis unit analyzes the electronic documents to be audited and extracts standards, requirements, and risks. Electronic documents to be audited include financial reports, internal control documents, and risk management documents. The analysis unit uses text analysis technology, data mining technology, and generative AI to analyze the contents of the documents and extract standards, requirements, and risks. Step 2: The Identification Department identifies important audit items based on the information extracted by the Analysis Department. The Identification Department identifies important audit items based on risk assessment and legal requirements, and uses Generative AI to prioritize and list high-risk and high-importance items. Step 3: The classification unit classifies the audit items identified by the identification unit. The classification unit classifies the audit items by category and risk level, and uses generation AI to prioritize and list high-risk and high-importance items. Step 4: The creation unit automatically creates a checklist based on the audit items classified by the classification unit. The creation unit creates a checklist including details of the items and how to check them, and uses generation AI to efficiently create the checklist.

[0064] (Example 2) An audit support system according to an embodiment of the present invention analyzes electronic documents to be audited, and a generation AI extracts standards, requirements, and risks. It then identifies, classifies, and organizes important audit items, and automatically creates a checklist. The audit support system analyzes electronic documents to be audited, and a generation AI extracts standards, requirements, and risks. The generation AI then identifies important audit items based on the extracted information. The generation AI then classifies and organizes the identified audit items, and finally automatically creates a checklist. For example, the audit support system inputs electronic documents to be audited. For example, the audit support system extracts audit items based on specific standards from documents to be audited, such as financial reports and internal control documents. The audit support system then uses a generation AI to identify important audit items based on the extracted information. The generation AI then prioritizes and lists high-risk and high-importance items. The audit support system then categorizes and organizes the audit items identified by the generation AI. The generation AI then prioritizes and lists high-risk and high-importance items. Next, the audit support system automatically creates a checklist based on the audit items categorized and organized by the generation AI. This allows the audit support system to improve the efficiency of audit work and reduce the burden on auditors. It also enables accurate audits without overlooking important audit items. This allows the audit support system to improve the efficiency of audit work and reduce the burden on auditors. For example, the audit support system can quickly and accurately analyze electronic documents to be audited and identify important audit items. It also enables accurate audits without overlooking important audit items.

[0065] An audit support system according to an embodiment includes an analysis unit, an identification unit, a classification unit, and a creation unit. The analysis unit analyzes electronic documents to be audited and extracts standards, requirements, and risks. Electronic documents to be audited include, but are not limited to, financial reports, internal control documents, and risk management documents. The analysis unit analyzes the content of the documents using, for example, text analysis technology. The analysis unit can also extract standards, requirements, and risks from the documents using data mining technology. The analysis unit can also analyze the content of the documents using a generation AI to extract standards, requirements, and risks. For example, the generation AI analyzes the content of the documents and extracts information based on specific standards. The identification unit identifies important audit items based on the information extracted by the analysis unit. For example, the identification unit can identify important audit items based on a risk assessment. The identification unit can also identify important audit items based on legal requirements. The identification unit can also identify important audit items based on the extracted information using the generation AI. For example, the generation AI prioritizes listing high-risk or high-importance items. The classification unit classifies the audit items identified by the identification unit. The classification unit, for example, classifies the audit items by category. The classification unit can also classify the audit items by risk level. The classification unit can also classify the identified audit items using a generation AI. For example, the generation AI prioritizes listing high-risk items or high-importance items. The creation unit automatically creates a checklist based on the audit items classified by the classification unit. The creation unit creates a checklist including, for example, details of the items and check methods. The creation unit can also automatically create a checklist based on the classified audit items using the generation AI. For example, the generation AI efficiently creates a checklist based on the classified audit items. As a result, the audit support system according to the embodiment can improve the efficiency of audit work and reduce the burden on auditors. For example, the audit support system can quickly and accurately analyze electronic documents to be audited and identify important audit items. The audit support system also enables accurate audits without overlooking important audit items.

[0066] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the user's emotions. For example, if the user is feeling stressed, the analysis unit can adjust the analysis priority so that the generation AI can relax and start analyzing items with lower importance. Furthermore, if the user is relaxed, the analysis unit can also have the generation AI start analyzing items with higher importance, thereby efficiently proceeding with the analysis. Furthermore, if the user is in a hurry, the analysis unit can have the generation AI prioritize analyzing the most important items and quickly provide results. This reduces the burden on the user by adjusting the analysis priority according to the user's emotions and enables efficient analysis. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0067] The analysis unit can apply an appropriate analysis algorithm depending on the type of document during analysis. For example, in the case of a financial report, the analysis unit causes the generation AI to apply an algorithm specialized for financial data analysis. Furthermore, in the case of an internal control document, the analysis unit can also cause the generation AI to apply an algorithm specialized for internal control evaluation. Furthermore, in the case of a risk management document, the analysis unit can also cause the generation AI to apply an algorithm specialized for risk evaluation. In this way, by applying an analysis algorithm depending on the type of document, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the type of document to the generation AI and cause the generation AI to select an appropriate analysis algorithm.

[0068] During analysis, the analysis unit can improve the accuracy of the analysis based on past analysis results. For example, the analysis unit refers to the analysis results of past financial reports and prioritizes analysis of items with similar patterns. The analysis unit can also refer to the analysis results of past internal control documents and prioritize analysis of items with similar risks. The analysis unit can also refer to the analysis results of past risk management documents and prioritize analysis of items with similar risk assessments. In this way, by referring to past analysis results, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis results into the generation AI and have the generation AI improve the accuracy of the analysis.

[0069] During analysis, the analysis unit can determine the priority of analysis based on the submission date and time of the document. For example, the analysis unit can prioritize analyzing recently submitted documents and perform an audit based on the latest information. The analysis unit can also prioritize analyzing documents with an upcoming submission deadline and complete the audit within the deadline. The analysis unit can also postpone analyzing documents with older submission dates and prioritize analyzing the latest information. In this way, by determining the priority of analysis based on the submission date and time of the document, an audit can be performed based on the latest information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission date and time of the document to the generation AI and have the generation AI determine the analysis priority.

[0070] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the user's emotions. For example, if the user is nervous, the generation AI can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This allows the display method of the analysis results to be adjusted according to the user's emotions, enabling a display that is easy for the user to view. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0071] The analysis unit can perform analysis based on the geographical distribution of documents during analysis. For example, the analysis unit can analyze documents from different geographical regions and perform analysis taking into account the characteristics of each region. The analysis unit can also analyze documents from geographically close regions together to efficiently proceed with the analysis. The analysis unit can also prioritize analysis of documents from geographically important regions and evaluate the risk for each region. This makes it possible to perform analysis that reflects the characteristics of each region by taking the geographical distribution of documents into account. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input geographical distribution data of documents to a generation AI and have the generation AI perform the analysis.

[0072] During analysis, the analysis unit can improve the accuracy of the analysis by referring to related literature of the document. The analysis unit, for example, refers to related financial reports and analyzes items with similar patterns. The analysis unit can also refer to related internal control documents and analyze items with similar risks. The analysis unit can also refer to related risk management documents and analyze items with similar risk assessments. In this way, by referring to related literature, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input related literature data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0073] The analysis unit can perform analysis based on the market value of the document during analysis. For example, the analysis unit can prioritize analyzing documents with high market value and extract important information. The analysis unit can also prioritize analyzing documents with high importance, leaving documents with low market value for later analysis. The analysis unit can also take fluctuations in market value into account and perform analysis based on the latest market value. This makes it possible to prioritize analysis of important information by taking the market value of the document into consideration. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input market value data of the document to the generation AI and have the generation AI perform the analysis.

[0074] The identification unit can estimate the user's emotions and prioritize the audit items to be identified based on the user's emotions. For example, if the user is feeling stressed, the identification unit can start identifying items with a lower importance so that the generation AI can relax. Furthermore, if the user is relaxed, the identification unit can also have the generation AI start identifying items with a higher importance, thereby efficiently progressing the identification. Furthermore, if the user is in a hurry, the identification unit can have the generation AI prioritize the most important items and provide results quickly. This reduces the burden on the user by prioritizing audit items based on the user's emotions and enables efficient auditing. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the identification unit may be performed using, for example, an AI. For example, the identification unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0075] During the identification process, the identification unit can apply an algorithm that prioritizes identifying high-risk items. For example, the identification unit prioritizes identifying high-risk financial items and listing them as important audit items. The identification unit can also prioritize identifying high-risk internal control items and listing them as important audit items. The identification unit can also prioritize identifying high-risk risk management items and listing them as important audit items. This allows for efficient identification of important audit items by prioritizing high-risk items. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input risk assessment data into a generation AI and have the generation AI identify high-risk items.

[0076] During identification, the identification unit can improve the accuracy of identification based on past identification results. For example, the identification unit refers to identification results from past financial reports and identifies items with similar patterns. The identification unit can also refer to identification results from past internal control documents and identify items with similar risks. The identification unit can also refer to identification results from past risk management documents and identify items with similar risk assessments. In this way, by referring to past identification results, the accuracy of identification is improved. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input past identification result data into the generation AI and have the generation AI improve the accuracy of identification.

[0077] During identification, the identification unit can perform identification based on attribute information of the document submitter. For example, if the submitter is a financial officer, the identification unit can prioritize identifying financial items. Furthermore, if the submitter is an internal control officer, the identification unit can also prioritize identifying internal control items. Furthermore, if the submitter is a risk management officer, the identification unit can also prioritize identifying risk management items. This makes it possible to identify more appropriate audit items by taking into account the attribute information of the document submitter. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input attribute information data of the submitter into the generation AI and have the generation AI perform identification.

[0078] The identification unit can estimate the user's emotions and adjust the display method of the identified audit items based on the user's emotions. For example, if the user is nervous, the identification unit can cause the generation AI to provide a simple, highly visible display method. Furthermore, if the user is relaxed, the identification unit can cause the generation AI to provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the identification unit can cause the generation AI to provide a display method that focuses on the main points. This allows the display method of the audit items to be adjusted according to the user's emotions, resulting in a display that is easy for the user to view. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the identification unit can be performed using, for example, an AI, or without an AI. For example, the identification unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0079] During identification, the identification unit can perform identification based on the geographic distribution of documents. For example, the identification unit can identify documents from different geographical regions and perform identification taking into account the characteristics of each region. The identification unit can also identify documents from geographically close regions together to efficiently proceed with identification. The identification unit can also prioritize identifying documents from geographically important regions and evaluate the risk for each region. This makes it possible to perform identification that reflects the characteristics of each region by taking the geographic distribution of documents into consideration. Some or all of the above-mentioned processing in the identification unit can be performed using, for example, AI, or without AI. For example, the identification unit can input geographical distribution data of documents to a generation AI and have the generation AI perform identification.

[0080] During identification, the identification unit can improve the accuracy of identification by referring to related literature of the document. For example, the identification unit can refer to related financial reports to identify items with similar patterns. The identification unit can also refer to related internal control documents to identify items with similar risks. The identification unit can also refer to related risk management documents to identify items with similar risk assessments. In this way, the accuracy of identification is improved by referring to related literature. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input related literature data into the generation AI and have the generation AI perform improvement of the accuracy of identification.

[0081] The identification unit can perform identification based on the market value of the document during identification. For example, the identification unit can prioritize identifying documents with high market value and extract important information. The identification unit can also prioritize identifying documents with high importance, leaving documents with low market value for later. The identification unit can also take fluctuations in market value into account and perform identification based on the latest market value. This makes it possible to prioritize identifying important information by taking the market value of the document into consideration. Some or all of the above-mentioned processing in the identification unit can be performed using, for example, AI, or can be performed without using AI. For example, the identification unit can input market value data of the document to the generation AI and have the generation AI perform identification.

[0082] The classification unit can estimate the user's emotions and adjust the classification criteria based on the user's emotions. For example, if the user is feeling stressed, the classification unit can start classification from items of low importance so that the generation AI can relax. Furthermore, if the user is relaxed, the classification unit can also cause the generation AI to start classification from items of high importance, thereby efficiently proceeding with classification. Furthermore, if the user is in a hurry, the classification unit can cause the generation AI to prioritize the most important items and quickly provide results. This reduces the burden on the user by adjusting the classification criteria according to the user's emotions and enables efficient classification. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the classification unit can be performed using, for example, an AI. For example, the classification unit can input the user's emotion data into the generation AI and cause the generation AI to perform emotion estimation.

[0083] The classification unit can improve the accuracy of classification based on the interrelationships between audit items during classification. For example, the classification unit analyzes the interrelationships between audit items and classifies related items together. The classification unit can also take into account the interrelationships between audit items and prioritize classification of items with high importance. The classification unit can also efficiently proceed with classification based on the interrelationships between audit items. In this way, by taking into account the interrelationships between audit items, the accuracy of classification is improved. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input interrelationship data between audit items to the generation AI and cause the generation AI to improve the accuracy of classification.

[0084] The classification unit can perform classification taking into consideration attribute information of the person who submitted the audit items. For example, if the submitter is a financial officer, the classification unit can prioritize classifying financial items. Furthermore, if the submitter is an internal control officer, the classification unit can also prioritize classifying internal control items. Furthermore, if the submitter is a risk management officer, the classification unit can also prioritize classifying risk management items. This enables more appropriate classification by taking into consideration attribute information of the person who submitted the audit items. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input attribute information data of the submitter to the generation AI and have the generation AI perform the classification.

[0085] During classification, the classification unit can weight the classification based on the number of times the audit item is submitted. For example, the classification unit prioritizes classification of audit items that are submitted frequently and sets a high level of importance. The classification unit can also postpone audit items that are submitted less frequently and set a low level of importance. The classification unit can also weight the classification based on the latest submission frequency, taking into account fluctuations in submission frequency. In this way, by weighting the classification based on the submission frequency of the audit item, it is possible to prioritize classification of items with a high level of importance. Some or all of the above-described processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input submission frequency data to a generation AI and have the generation AI perform the weighting of the classification.

[0086] The classification unit can estimate the user's emotions and adjust the display method of the classification results based on the user's emotions. For example, if the user is nervous, the generation AI can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the classification unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the classification unit can provide a display method that focuses on the main points. By adjusting the display method of the classification results according to the user's emotions, a display that is easy for the user to view is possible. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the classification unit can be performed using, for example, an AI. For example, the classification unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0087] The classification unit can perform classification based on the geographical distribution of the audit items during classification. For example, the classification unit can classify audit items in different geographical regions and perform classification taking into account the characteristics of each region. The classification unit can also classify audit items in geographically close regions together to efficiently proceed with classification. The classification unit can also prioritize classification of audit items in geographically important regions and evaluate the risks of each region. This makes it possible to perform classification that reflects the characteristics of each region by taking the geographical distribution of the audit items into consideration. Some or all of the above-mentioned processing in the classification unit can be performed using, for example, AI, or without AI. For example, the classification unit can input geographical distribution data of the audit items to the generation AI and have the generation AI perform the classification.

[0088] During classification, the classification unit can improve the accuracy of the classification by referring to related literature of the audit items. For example, the classification unit refers to related financial reports and classifies items with similar patterns. The classification unit can also refer to related internal control documents and classify items with similar risks. The classification unit can also refer to related risk management documents and classify items with similar risk assessments. In this way, by referring to related literature, the accuracy of the classification is improved. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input related literature data into the generation AI and have the generation AI improve the accuracy of the classification.

[0089] The classification unit can perform classification based on the market value of the audit items during classification. For example, the classification unit can prioritize classification of audit items with high market value and extract important information. The classification unit can also prioritize classification of audit items with high importance, leaving audit items with low market value for later. The classification unit can also perform classification based on the latest market value, taking into account fluctuations in market value. In this way, important information can be prioritized by taking into account the market value of the audit items. Some or all of the above-mentioned processing in the classification unit can be performed using, for example, AI, or without AI. For example, the classification unit can input market value data of the audit items to the generation AI and have the generation AI perform the classification.

[0090] The creation unit can estimate the user's emotions and adjust the checklist creation method based on the user's emotions. For example, if the user is feeling stressed, the creation unit can create a simple checklist to allow the generation AI to relax. Furthermore, if the user is relaxed, the creation unit can also allow the generation AI to create a detailed checklist to efficiently conduct the audit. Furthermore, if the user is in a hurry, the creation unit can also create a checklist that prioritizes the most important items. This reduces the burden on the user by adjusting the checklist creation method according to the user's emotions and enables efficient checklist creation. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the creation unit can be performed using, for example, AI, or without AI. For example, the creation unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0091] The creation unit can adjust the level of detail of the checklist based on the importance of the audit items during creation. For example, the creation unit can describe audit items with high importance in detail and simplify items with low importance. The creation unit can also postpone audit items with low importance and prioritize items with high importance. The creation unit can also adjust the level of detail of the checklist based on the latest importance, taking into account changes in importance. In this way, important items can be described in detail by adjusting the level of detail of the checklist based on the importance of the audit items. Some or all of the above-mentioned processing in the creation unit can be performed using, for example, AI, or without AI. For example, the creation unit can input audit item importance data into the generation AI and have the generation AI adjust the level of detail of the checklist.

[0092] When creating a checklist, the creation unit can apply an appropriate creation algorithm depending on the category of the audit item. For example, in the case of financial items, the creation unit can create a checklist by applying an algorithm specialized for financial data analysis. In addition, in the case of internal control items, the creation unit can also create a checklist by applying an algorithm specialized for internal control evaluation. In addition, in the case of risk management items, the creation unit can also create a checklist by applying an algorithm specialized for risk evaluation. In this way, by applying a creation algorithm depending on the category of the audit item, the accuracy of the checklist is improved. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input category data of the audit items into a generation AI and have the generation AI select an appropriate creation algorithm.

[0093] During checklist creation, the creation unit can improve the accuracy of the checklist creation based on past checklist creation results. For example, the creation unit references checklist creation results for past financial reports to create a checklist that includes items with similar patterns. The creation unit can also reference checklist creation results for past internal control documents to create a checklist that includes items with similar risks. The creation unit can also reference checklist creation results for past risk management documents to create a checklist that includes items with similar risk assessments. This improves the accuracy of the creation by referring to past checklist creation results. Some or all of the above-described processing in the creation unit may be performed, for example, using AI, or may be performed without using AI. For example, the creation unit can input past checklist creation result data into the generation AI and have the generation AI improve the accuracy of the creation.

[0094] The creation unit can estimate the user's emotions and adjust the checklist display method based on the user's emotions. For example, if the user is nervous, the creation unit can cause the generation AI to provide a simple, highly visible display method. Furthermore, if the user is relaxed, the creation unit can cause the generation AI to provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the creation unit can cause the generation AI to provide a display method that focuses on the main points. This allows the checklist display method to be adjusted according to the user's emotions, resulting in a display that is easy for the user to view. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the creation unit can be performed using, for example, an AI, or without an AI. For example, the creation unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0095] When creating the checklist, the creation unit can determine the priority of the checklist based on the submission date and time of the audit items. For example, the creation unit can prioritize the most recently submitted audit items in the checklist. The creation unit can also prioritize the audit items with an upcoming submission deadline in the checklist. The creation unit can also postpone audit items with older submission dates and prioritize the most recent information in the checklist. In this way, by determining the priority of the checklist based on the submission date and time of the audit items, audits can be performed based on the most recent information. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the submission date and time data of the audit items into the generation AI and have the generation AI determine the priority of the checklist.

[0096] The creation unit can adjust the order of the checklist based on the relationships between the audit items when creating the checklist. For example, the creation unit can include related audit items together in the checklist to efficiently proceed with the audit. The creation unit can also take into account the relevance of the audit items and prioritize items of high importance in the checklist. The creation unit can also efficiently adjust the order of the checklist based on the relevance of the audit items. This enables efficient audits by adjusting the order of the checklist based on the relevance of the audit items. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input relevance data of the audit items into the generation AI and have the generation AI adjust the order of the checklist.

[0097] During creation, the creation unit can adjust the use of technical terms in the checklist according to the knowledge level of the audit item. For example, the creation unit can create a checklist that uses a lot of technical terms for audit items requiring a high level of expertise. The creation unit can also create a simple checklist that avoids technical terms for audit items requiring a low level of expertise. The creation unit can also adjust the use of technical terms in the checklist based on the latest level of expertise, taking into account changes in the level of expertise. This allows for the creation of a checklist that is easy for users to understand by adjusting the use of technical terms in the checklist according to the level of expertise of the audit item. Some or all of the above-described processing in the creation unit can be performed using, for example, AI, or without AI. For example, the creation unit can input knowledge level data of the audit items into a generation AI and have the generation AI execute the use of technical terms in the checklist. === Hard Collateral 1-1 === Each of the multiple elements, including the analysis unit, identification unit, classification unit, and creation unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the computer 36 of the smart device 14 or the processor 28 of the data processing device 12, and analyzes the electronic document to be audited to extract standards, requirements, and risks. The identification unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and identifies important audit items based on the extracted information. The classification unit is implemented, for example, by the control unit 46A of the smart device 14 or the identification processing unit 290 of the data processing device 12, and classifies the identified audit items. The creation unit is implemented, for example, by the control unit 46A of the smart device 14 or the identification processing unit 290 of the data processing device 12, and automatically creates a checklist based on the classified audit items. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, identification unit, classification unit, and creation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the computer 36 of the smart glasses 214 or the processor 28 of the data processing device 12, and analyzes the electronic document to be audited and extracts standards, requirements, and risks. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies important audit items based on the extracted information. The classification unit is realized, for example, by the control unit 46A of the smart glasses 214 or the identification processing unit 290 of the data processing device 12, and classifies the identified audit items. The creation unit is realized, for example, by the control unit 46A of the smart glasses 214 or the identification processing unit 290 of the data processing device 12, and automatically creates a checklist based on the classified audit items. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned analysis unit, identification unit, classification unit, and creation unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the analysis unit is realized by the computer 36 of the headset terminal 314 or the processor 28 of the data processing device 12, and analyzes the electronic document to be audited to extract standards, requirements, and risks. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies important audit items based on the extracted information. The classification unit is realized, for example, by the control unit 46A of the headset terminal 314 or the identification processing unit 290 of the data processing device 12, and classifies the identified audit items. The creation unit is realized, for example, by the control unit 46A of the headset terminal 314 or the identification processing unit 290 of the data processing device 12, and automatically creates a checklist based on the classified audit items. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned analysis unit, identification unit, classification unit, and creation unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the computer 36 of the robot 414 or the processor 28 of the data processing device 12, and analyzes the electronic document to be audited to extract standards, requirements, and risks. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies important audit items based on the extracted information. The classification unit is realized, for example, by the control unit 46A of the robot 414 or the identification processing unit 290 of the data processing device 12, and classifies the identified audit items. The creation unit is realized, for example, by the control unit 46A of the robot 414 or the identification processing unit 290 of the data processing device 12, and automatically creates a checklist based on the classified audit items.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] During analysis, the analysis unit can apply an appropriate analysis algorithm based on the language of the document. For example, it can apply an English-specific analysis algorithm to an English document, and a Japanese-specific analysis algorithm to a Japanese document. Furthermore, the analysis unit can also apply a combination of analysis algorithms corresponding to each language to a document containing multiple languages. This improves the accuracy of analysis by applying an analysis algorithm appropriate for the language of the document. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the language data of the document into a generation AI and have the generation AI select an appropriate analysis algorithm.

[0100] The identification unit can estimate the user's emotions and prioritize the audit items to be identified based on the user's emotions. For example, if the user is feeling stressed, the generation AI can start identifying items with lower importance so that the user can relax. Furthermore, if the user is relaxed, the identification unit can also have the generation AI start identifying items with higher importance, thereby efficiently progressing the identification. Furthermore, if the user is in a hurry, the identification unit can have the generation AI prioritize the most important items and provide results quickly. This reduces the burden on the user by prioritizing audit items based on the user's emotions and enables efficient auditing. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the identification unit may be performed using AI, or without AI. For example, the identification unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0101] The classification unit can improve the accuracy of classification based on the interrelationships between audit items during classification. For example, the classification unit can analyze the interrelationships between audit items and classify related items together. The classification unit can also take into account the interrelationships between audit items and prioritize classification of items with high importance. The classification unit can also efficiently proceed with classification based on the interrelationships between audit items. This improves the accuracy of classification by taking into account the interrelationships between audit items. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can input interrelationship data between audit items to the generation AI and have the generation AI improve the accuracy of classification.

[0102] The creation unit can estimate the user's emotions and adjust the checklist creation method based on the user's emotions. For example, if the user is feeling stressed, the generation AI can create a simple checklist to help the user relax. Furthermore, if the user is relaxed, the creation unit can also have the generation AI create a detailed checklist to efficiently conduct the audit. Furthermore, if the user is in a hurry, the creation unit can have the generation AI create a checklist that prioritizes the most important items. This reduces the user's burden and enables efficient checklist creation by adjusting the checklist creation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the creation unit may be performed using, for example, an AI. For example, the creation unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0103] During analysis, the analysis unit can determine the priority of analysis based on the submission date and time of the document. For example, the analysis unit can prioritize analyzing recently submitted documents and perform an audit based on the latest information. The analysis unit can also prioritize analyzing documents with an upcoming submission deadline and complete the audit within the deadline. The analysis unit can also postpone analyzing documents with older submission dates and prioritize analyzing the latest information. In this way, by determining the priority of analysis based on the submission date and time of the document, an audit can be performed based on the latest information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission date and time of the document to the generation AI and have the generation AI determine the analysis priority.

[0104] During the identification process, the identification unit can apply an algorithm that prioritizes identifying high-risk items. For example, the identification unit prioritizes identifying high-risk financial items and listing them as important audit items. The identification unit can also prioritize identifying high-risk internal control items and listing them as important audit items. The identification unit can also prioritize identifying high-risk risk management items and listing them as important audit items. In this way, by prioritizing high-risk items, important audit items can be efficiently identified. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input risk assessment data into a generation AI and have the generation AI identify high-risk items.

[0105] The classification unit can estimate the user's emotions and adjust the classification criteria based on the user's emotions. For example, if the user is feeling stressed, the generation AI can start classifying items with lower importance so that the user can relax. Furthermore, if the user is relaxed, the classification unit can also have the generation AI start classifying items with higher importance, thereby efficiently proceeding with classification. Furthermore, if the user is in a hurry, the classification unit can have the generation AI prioritize classifying the most important items and quickly provide results. This reduces the burden on the user and enables efficient classification by adjusting the classification criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the classification unit can be performed using, for example, an AI. For example, the classification unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0106] The creation unit can adjust the order of the checklist based on the relationships between the audit items when creating the checklist. For example, related audit items can be included together in the checklist to efficiently conduct the audit. The creation unit can also take into account the relevance of the audit items and prioritize items of high importance in the checklist. The creation unit can also efficiently adjust the order of the checklist based on the relevance of the audit items. This enables efficient audits by adjusting the order of the checklist based on the relevance of the audit items. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input relevance data of the audit items into the generation AI and have the generation AI adjust the order of the checklist.

[0107] During analysis, the analysis unit can perform analysis based on the market value of the document. For example, documents with high market value are analyzed with priority to extract important information. The analysis unit can also postpone analyzing documents with low market value and prioritize analyzing documents with high importance. The analysis unit can also take fluctuations in market value into account and perform analysis based on the latest market value. This makes it possible to prioritize analysis of important information by taking the market value of the document into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input market value data of the document into the generation AI and have the generation AI perform the analysis.

[0108] During identification, the identification unit can improve the accuracy of identification based on past identification results. For example, the identification unit can refer to the identification results of past financial reports and identify items with similar patterns. The identification unit can also refer to the identification results of past internal control documents and identify items with similar risks. The identification unit can also refer to the identification results of past risk management documents and identify items with similar risk assessments. In this way, by referring to past identification results, the accuracy of identification is improved. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input past identification result data into the generation AI and have the generation AI improve the accuracy of identification.

[0109] The processing flow of the second embodiment will be briefly explained below.

[0110] Step 1: The analysis unit analyzes the electronic documents to be audited and extracts standards, requirements, and risks. Electronic documents to be audited include financial reports, internal control documents, and risk management documents. The analysis unit uses text analysis technology, data mining technology, and generative AI to analyze the contents of the documents and extract standards, requirements, and risks. Step 2: The Identification Department identifies important audit items based on the information extracted by the Analysis Department. The Identification Department identifies important audit items based on risk assessment and legal requirements, and uses Generative AI to prioritize and list high-risk and high-importance items. Step 3: The classification unit classifies the audit items identified by the identification unit. The classification unit classifies the audit items by category and risk level, and uses generation AI to prioritize and list high-risk and high-importance items. Step 4: The creation unit automatically creates a checklist based on the audit items classified by the classification unit. The creation unit creates a checklist including details of the items and how to check them, and uses generation AI to efficiently create the checklist.

[0111] 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.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0113] 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.

[0114] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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 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.

[0129] 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.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 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.

[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 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.

[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 (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).

[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] 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.

[0139] 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.

[0140] 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.

[0141] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0142] 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.

[0143] 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.

[0144] 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 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.

[0145] 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.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0159] 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.

[0160] 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.

[0161] 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 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.

[0162] 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.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the 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.

[0169] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0174] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0175] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0176] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

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

[0181] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0182] [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes electronic documents to be audited and extracts standards, requirements, and risks; an identification unit that identifies important audit items based on the information extracted by the analysis unit; a classification unit that classifies the inspection items identified by the identification unit; a creation unit that automatically creates a checklist based on the inspection items classified by the classification unit. A system characterized by:

2. The analysis unit Estimate user sentiment and adjust analysis priorities based on user sentiment 2. The system of claim 1.

3. The analysis unit During analysis, the appropriate analysis algorithm is applied depending on the document type.

2. The system of claim 1.

4. The analysis unit During analysis, improve the accuracy of the analysis based on past analysis results 2. The system of claim 1.

5. The analysis unit During analysis, prioritize analysis based on the document submission date and time 2. The system of claim 1.

6. The analysis unit Inferring user emotions and adjusting the way analysis results are displayed based on the user's emotions 2. The system of claim 1.

7. The analysis unit During analysis, the analysis is based on the geographic distribution of documents.

2. The system of claim 1.

8. The analysis unit During analysis, improve the accuracy of the analysis based on the document's related literature 2. The system of claim 1.

Images