system

Abstract

The system according to this embodiment aims to quickly and efficiently verify internal regulations and respond to legal revisions. [Solution] The system according to the embodiment comprises an identification unit, a judgment unit, a proposal unit, and a documentation unit. The identification unit identifies the relevant section of the company regulations. The judgment unit determines the suitability of the section identified by the identification unit. The proposal unit makes a proposed solution based on the result determined by the judgment unit. The documentation unit verifies and documents related materials based on the content proposed by the proposal unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it takes time and effort to check internal regulations and respond to legal amendments, making it difficult to perform efficient work.

[0005] The system according to the embodiment aims to quickly and efficiently check internal regulations and respond to legal amendments.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an identification unit, a judgment unit, a proposal unit, and a documentation unit. The identification unit identifies the relevant section of the company regulations. The judgment unit determines the suitability of the section identified by the identification unit. The proposal unit makes a proposed solution based on the result determined by the judgment unit. The documentation unit verifies and documents related materials based on the content proposed by the proposal unit. [Effects of the Invention]

[0007] The system according to this embodiment can quickly and efficiently verify internal regulations and respond to legal revisions. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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), or Bluetooth (registered trademark).

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

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​agent system according to an embodiment of the present invention is a system that supports companies in reviewing internal regulations and responding to legal revisions. This AI agent system learns the impact of legal revisions on internal regulations, operational rules, and clause content. Next, the AI ​​agent system identifies areas of law that need to be understood and addressed in relation to internal procedures and operations, and groups and categorizes them. This enables it to make appropriate suggestions to employees. Furthermore, it proposes customized advice and improvement measures that take into account the legal compliance status of each department and company. For example, by automatically identifying tasks related to legal revisions and creating improvement measures and countermeasures, it is possible to reduce the workload and improve efficiency. This enables departments and the entire company to respond smoothly to legal revisions and minimizes risks and omissions in operational and regulation revisions. For example, the AI ​​agent system identifies the relevant parts of internal regulations and determines their compliance. Next, it reduces workload and burden by proposing countermeasures, reviewing related documents, and documenting them. It also predicts future changes, impacts, concerns, and risks while considering parliamentary deliberations, public opinion trends, scandals and incidents of other companies. Furthermore, the AI ​​agent system analyzes the content and scope of legal revisions and automatically identifies affected internal documents and operational rules. It automatically evaluates the company's compliance with legal revisions and proposes corrections and improvements. It also automatically detects changes in regulations due to legal revisions and automatically generates comparison tables and proposed updates. In this way, the AI ​​agent system enables efficient business operations and minimizes legal risks for companies. For example, it can quickly respond to frequently occurring legal revisions in a company's back-office operations. In addition, it allows employees to easily consult about laws and internal procedures, leading to increased operational efficiency. As a result, the AI ​​agent system can efficiently review internal regulations and respond to legal revisions.

[0029] The AI ​​agent system according to this embodiment comprises an identification unit, a judgment unit, a proposal unit, and a documentation unit. The identification unit identifies the relevant section of the company regulations. The identification unit, for example, uses AI to analyze the text data of the company regulations and extract the relevant section. The identification unit can, for example, use natural language processing technology to understand the content of the regulations and identify the relevant section. The identification unit can also, for example, refer to the change history of the regulations and identify the changes. The judgment unit determines the suitability of the section identified by the identification unit. The judgment unit, for example, uses AI to evaluate suitability based on laws and regulations and company standards. The judgment unit can, for example, create a database of legal standards and company standards and determine suitability by comparing them with the identified section. The judgment unit can also, for example, refer to past suitability evaluation results to improve the accuracy of its judgment. The proposal unit makes a proposal for action based on the results determined by the judgment unit. The proposal unit, for example, uses AI to propose an appropriate action. The proposal unit can, for example, propose changes and improvements to operations due to legal revisions. The proposal department can, for example, refer to past proposal history to make the most appropriate proposal. The documentation department verifies and documents relevant materials based on the content proposed by the proposal department. The documentation department can, for example, use AI to automatically collect and document relevant materials. The documentation department can, for example, create a database of legal documents and internal company documents and automatically generate the necessary materials. The documentation department can, for example, refer to past documentation history to select the most appropriate documentation method. As a result, the AI ​​agent system according to the embodiment can efficiently verify internal regulations and respond to legal revisions.

[0030] The designated department identifies the relevant sections of the company regulations. For example, the department uses AI to analyze the text data of the company regulations and extract the relevant sections. Specifically, it can use natural language processing technology to understand the content of the regulations and identify the relevant sections. Natural language processing technology includes morphological analysis, contextual analysis, and semantic analysis, and by combining these, it can accurately grasp the context and meaning of the regulations. For example, morphological analysis is used to divide the text into words, and contextual analysis is used to analyze the relationships between words. Furthermore, semantic analysis is used to understand the meaning of the entire sentence and identify the relevant sections. The designated department can also refer to the change history of the regulations and identify the changes. The change history is managed using a version control system, which records past changes and the date of change. The designated department analyzes this change history and identifies the changes by comparing the latest regulation content with past regulation content. This allows the designated department to quickly and accurately identify the relevant sections of the company regulations and understand the changes. Furthermore, the designated department can share the identified relevant sections in cooperation with other departments and systems. For example, the identified relevant sections can be saved in a database, making them accessible to other departments. Furthermore, the department can collect feedback on the identified sections to improve the accuracy of the identification process. This allows the department to streamline the management and operation of internal regulations and improve overall business processes.

[0031] The judgment unit determines the conformity of the areas identified by the identification unit. The judgment unit evaluates conformity based on laws and internal standards, for example, using AI. Specifically, it can determine conformity by creating a database of legal and internal standards and comparing them with the identified areas. The AI ​​uses machine learning algorithms to analyze the text data of laws and standards and evaluate the degree of agreement with the identified areas. For example, it uses natural language processing technology to understand the content of laws and standards and evaluate their relevance to the identified areas. Furthermore, the judgment unit can also improve the accuracy of its judgments by referring to past conformity evaluation results. Past evaluation results are stored in the database and used by the AI ​​as training data. This allows the judgment unit to perform more accurate conformity evaluations based on past evaluation results. The judgment unit can share the results of conformity evaluations in cooperation with other departments and systems. For example, evaluation results can be stored in a database and made accessible to other departments. The judgment unit can also collect feedback on the evaluation results and use it to improve evaluation accuracy. This allows the judgment unit to perform conformity evaluations based on laws and internal standards efficiently and accurately, improving the overall business process.

[0032] The Proposal Department makes countermeasure proposals based on the results determined by the Decision Department. The Proposal Department, for example, uses AI to propose appropriate countermeasures. Specifically, it can propose changes and improvements to operations in response to legal revisions. The AI ​​uses machine learning algorithms to learn from past countermeasure proposal history and make optimal proposals. For example, it can create a database of past changes and improvements to operations in response to legal revisions, and the AI ​​analyzes this data to propose the most suitable countermeasure for the current situation. The Proposal Department can share its proposals with other departments and systems. For example, it can save proposals in a database so that other departments can access them. The Proposal Department can also collect feedback on its proposals and use it to improve the accuracy of its proposals. This allows the Proposal Department to efficiently and accurately propose countermeasures in response to legal revisions and business improvements, thereby improving the overall business process. Furthermore, the Proposal Department hands over its proposals to the Documentation Department, providing basic information for the verification and documentation of related documents. This allows the Proposal Department to ensure consistency and accuracy in its countermeasure proposals and to smoothly advance the overall business process.

[0033] The Documentation Department verifies and documents relevant materials based on the proposals submitted by the Proposal Department. For example, the Documentation Department can automatically collect and document relevant materials using AI. Specifically, it can create a database of legal and internal documents and automatically generate necessary materials. The AI ​​analyzes the content of documents using natural language processing technology and extracts relevant information. For example, it can extract necessary articles and regulations from legal documents and relevant procedures and guidelines from internal documents. The Documentation Department can also refer to past documentation history to select the optimal documentation method. Past documentation history is stored in a database and used by the AI ​​as training data. This allows the Documentation Department to perform more efficient and accurate documentation based on past documentation history. The Documentation Department can share the documented content with other departments and systems. For example, it can store the documented content in a database so that other departments can access it. Furthermore, the Documentation Department can collect feedback on the documented content to improve the accuracy of documentation. This allows the Documentation Department to efficiently and accurately verify and document relevant materials, improving the overall business process. Furthermore, the documentation department can regularly update the documented content, ensuring that the information remains up-to-date. This allows the documentation department to consistently provide documents based on the latest information, thereby facilitating the smooth progress of the overall business process.

[0034] The analysis unit can analyze the content and scope of legal amendments and automatically identify affected areas. For example, the analysis unit can use AI to analyze the articles of the legal amendments and identify their scope. For example, the analysis unit can create a database of the content of legal amendments and automatically extract affected areas. For example, the analysis unit can refer to past legal amendment history to identify affected areas. This allows for the rapid identification of the impact of legal amendments.

[0035] The evaluation department can automatically assess a company's compliance with legal revisions and propose corrections and improvements. For example, the evaluation department can use AI to assess a company's compliance with legal revisions. For example, the evaluation department can create a database of legal and internal standards and evaluate a company's compliance. For example, the evaluation department can improve the accuracy of its evaluations by referring to past compliance assessment results. This allows the evaluation of a company's compliance with legal revisions and the proposal of improvement measures.

[0036] The generation unit can automatically detect changes in regulations due to legal revisions and automatically generate comparison tables of old and new versions, as well as draft updates. For example, the generation unit can use AI to analyze the articles of the legal revisions and identify the changes. For example, the generation unit can create a database of the legal revisions and automatically generate comparison tables of old and new versions, as well as draft updates. The generation unit can also, for example, refer to past legal revision history to identify changes. This allows for the automatic detection of changes in regulations and the generation of draft updates.

[0037] The forecasting function can predict future changes, impacts, concerns, and risks by considering parliamentary deliberations, public opinion trends, scandals and incidents involving other companies. For example, the forecasting function can use AI to analyze parliamentary deliberations and public opinion trends to predict future changes and impacts. For example, the forecasting function can collect data on scandals and incidents involving other companies to predict risks. For example, the forecasting function can improve the accuracy of its predictions by referring to past risk prediction results. This allows it to predict future changes, impacts, concerns, and risks.

[0038] The creation unit can automatically identify tasks related to legal revisions and generate improvement measures and countermeasures. For example, the creation unit uses AI to identify tasks related to legal revisions. For example, the creation unit can create a database of legal revision content and automatically generate improvement measures and countermeasures. The creation unit can also refer to past improvement measures and countermeasures to create the most optimal solutions. This enables the automatic identification of tasks related to legal revisions and the generation of improvement measures and countermeasures.

[0039] The department can analyze the history of past changes to internal regulations and improve the accuracy of its identification. For example, the department can use AI to analyze the history of past changes to regulations. For example, the department can prioritize identifying regulations that are frequently changed. The department can also identify regulations that have a significant impact from changes. Furthermore, the department can improve accuracy by identifying patterns in changes. This allows for improved accuracy in identifying regulations by analyzing the history of past changes to regulations.

[0040] The identification unit can adjust the level of detail based on the importance of the regulations at the time of identification. The identification unit can, for example, use AI to evaluate the importance of the regulations. The identification unit can, for example, provide detailed information for regulations of high importance. The identification unit can also, for example, provide simplified information for regulations of low importance. The identification unit can also, for example, dynamically adjust the level of detail according to the importance of the regulations. This allows the level of detail to be adjusted based on the importance of the regulations.

[0041] The identification unit can adjust the order of the regulations based on their relevance at the time of identification. The identification unit can, for example, use AI to evaluate the relevance of the regulations. The identification unit can, for example, group related regulations together, taking into account their relevance. The identification unit can also, for example, dynamically adjust the order of the regulations based on their relevance. The identification unit can, for example, analyze the relevance of the regulations and identify them in the optimal order. This allows the order of the regulations to be adjusted based on their relevance.

[0042] The Identification Department can determine specific priorities based on the submission date of the regulations at the time of identification. The Identification Department can, for example, use AI to evaluate the submission date of the regulations. The Identification Department can, for example, prioritize the identification of regulations that have been submitted recently. The Identification Department can also, for example, adjust the specific priorities for regulations that have been submitted older as needed. The Identification Department can also, for example, dynamically determine specific priorities based on the submission date. This allows for the determination of specific priorities based on the submission date of the regulations.

[0043] The decision-making unit can improve the accuracy of its decisions by considering the interrelationships of the regulations. For example, the decision-making unit can use AI to evaluate the interrelationships of the regulations. For example, the decision-making unit can analyze the interrelationships of the regulations and make a decision considering the relevant regulations. For example, the decision-making unit can also improve the accuracy of its decisions based on the interrelationships of the regulations. For example, the decision-making unit can make the optimal decision by considering the interrelationships of the regulations. This allows for improved accuracy of decisions by considering the interrelationships of the regulations.

[0044] The decision-making unit can make decisions by considering the attribute information of the person submitting the regulations. For example, the decision-making unit can use AI to evaluate the attribute information of the person submitting the regulations. For example, the decision-making unit can make decisions by considering the position and department of the person submitting the regulations. For example, the decision-making unit can make decisions by referring to the past submission history of the person submitting the regulations. For example, the decision-making unit can make the optimal decision based on the attribute information of the person submitting the regulations. This allows the decision-making unit to consider the attribute information of the person submitting the regulations.

[0045] The decision-making unit can make decisions considering the geographical distribution of the regulations. For example, the decision-making unit can use AI to evaluate the geographical distribution of the regulations. For example, the decision-making unit can make decisions for each region where the scope of application of the regulations differs. For example, the decision-making unit can make the optimal decision based on the geographical distribution. For example, the decision-making unit can improve the accuracy of its decisions by considering the geographical distribution of the regulations. This allows the decision-making unit to take the geographical distribution of the regulations into consideration.

[0046] The decision-making unit can improve the accuracy of its decisions by referring to relevant documents related to the regulations during the decision-making process. For example, the decision-making unit may use AI to refer to relevant documents related to the regulations. The decision-making unit can improve the accuracy of its decisions by referring to relevant documents related to the regulations. The decision-making unit can also make the optimal decision based on relevant documents. The decision-making unit can also improve the accuracy of its decisions by considering relevant documents related to the regulations. This allows for improved decision-making accuracy by referring to relevant documents related to the regulations.

[0047] The proposal department can adjust the level of detail in its proposals based on the importance of the regulations. For example, the proposal department can use AI to evaluate the importance of the regulations. For example, the proposal department can provide detailed proposals for high-importance regulations. For example, the proposal department can provide simplified proposals for low-importance regulations. The proposal department can also dynamically adjust the level of detail in its proposals according to the importance of the regulations. This allows the level of detail in proposals to be adjusted based on the importance of the regulations.

[0048] The proposal team can apply different proposal algorithms depending on the category of the regulations when making a proposal. For example, the proposal team can use AI to evaluate the category of the regulations. For example, the proposal team can select the optimal proposal algorithm depending on the category of the regulations. The proposal team can also apply different proposal algorithms for each category of regulations. For example, the proposal team can improve the accuracy of the proposals based on the category of the regulations. This allows the application of the optimal proposal algorithm depending on the category of the regulations.

[0049] The proposal department can determine the priority of proposals based on the submission date of the regulations when submitting them. For example, the proposal department can use AI to evaluate the submission date of the regulations. For example, the proposal department can prioritize proposals for regulations that have been submitted recently. For example, the proposal department can adjust the priority of proposals for regulations that have been submitted older as needed. For example, the proposal department can dynamically determine the priority of proposals based on the submission date. This allows the priority of proposals to be determined based on the submission date of the regulations.

[0050] The proposal department can adjust the order of proposals based on the relevance of the regulations when making proposals. For example, the proposal department can use AI to evaluate the relevance of the regulations. For example, the proposal department can group related proposals together, taking into account the relevance of the regulations. The proposal department can also dynamically adjust the order of proposals based on the relevance of the regulations. For example, the proposal department can analyze the relevance of the regulations and make proposals in the optimal order. This allows the order of proposals to be adjusted based on the relevance of the regulations.

[0051] The documentation department can select the optimal documentation method by referring to past documentation of the regulations during the documentation process. For example, the documentation department can use AI to refer to past documentation. For example, the documentation department can refer to past documentation of the regulations and select the optimal documentation method. For example, the documentation department can select the optimal documentation method based on past documentation. For example, the documentation department can select the optimal documentation method by considering past documentation of the regulations. This allows for the selection of the optimal documentation method by referring to past documentation of the regulations.

[0052] The documentation unit can adjust the level of detail in the documentation based on the importance of the regulations during the documentation process. For example, the documentation unit can use AI to evaluate the importance of the regulations. For example, the documentation unit can create detailed documentation for regulations with high importance. For example, the documentation unit can also create simplified documentation for regulations with low importance. The documentation unit can also dynamically adjust the level of detail in the documentation according to the importance of the regulations. This allows the level of detail in the documentation to be adjusted based on the importance of the regulations.

[0053] The documentation unit can create documentation while considering the geographical distribution of the regulations. For example, the documentation unit can use AI to evaluate the geographical distribution of the regulations. For example, the documentation unit can create documentation for each region where the scope of application of the regulations differs. For example, the documentation unit can create optimal documentation based on geographical distribution. For example, the documentation unit can improve the accuracy of documentation by considering the geographical distribution of the regulations. This allows for documentation to be created while considering the geographical distribution of the regulations.

[0054] The documentation unit can improve the accuracy of documentation by referring to relevant documents related to the regulations during the documentation process. For example, the documentation unit can use AI to refer to relevant documents related to the regulations. The documentation unit can improve the accuracy of documentation by referring to relevant documents related to the regulations. The documentation unit can also perform optimal documentation based on relevant documents. The documentation unit can also improve the accuracy of documentation by considering relevant documents related to the regulations. This allows for improved accuracy of documentation by referring to relevant documents related to the regulations.

[0055] The analysis unit can improve the accuracy of the analysis by considering the interrelationships of the regulations during the analysis. For example, the analysis unit can use AI to evaluate the interrelationships of the regulations. For example, the analysis unit can analyze the interrelationships of the regulations and perform the analysis considering the relevant regulations. The analysis unit can also improve the accuracy of the analysis based on the interrelationships of the regulations. For example, the analysis unit can perform the optimal analysis by considering the interrelationships of the regulations. This allows for improved accuracy of the analysis by considering the interrelationships of the regulations.

[0056] The analysis unit can perform analysis while considering the attribute information of the person who submitted the regulations. For example, the analysis unit can use AI to evaluate the attribute information of the person who submitted the regulations. For example, the analysis unit can perform analysis while considering the position and department of the person who submitted the regulations. For example, the analysis unit can also perform analysis while referring to the past submission history of the person who submitted the regulations. For example, the analysis unit can perform optimal analysis based on the attribute information of the person who submitted the regulations. This allows the analysis to be performed while considering the attribute information of the person who submitted the regulations.

[0057] The analysis unit can perform analysis while considering the geographical distribution of regulations. For example, the analysis unit can use AI to evaluate the geographical distribution of regulations. For example, the analysis unit can perform analysis for each region where the scope of application of regulations differs. For example, the analysis unit can perform the optimal analysis based on geographical distribution. For example, the analysis unit can improve the accuracy of the analysis by considering the geographical distribution of regulations. This allows the analysis to be performed while considering the geographical distribution of regulations.

[0058] The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the regulations during the analysis. For example, the analysis unit can use AI to refer to relevant literature related to the regulations. The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the regulations. The analysis unit can also perform an optimal analysis based on relevant literature. The analysis unit can also improve the accuracy of its analysis by considering relevant literature related to the regulations. This allows for improved accuracy of the analysis by referring to relevant literature related to the regulations.

[0059] The evaluation unit can improve the accuracy of its evaluations by considering the interrelationships between regulations. For example, the evaluation unit can use AI to evaluate the interrelationships between regulations. For example, the evaluation unit can analyze the interrelationships between regulations and perform evaluations considering the relevant regulations. The evaluation unit can also improve the accuracy of its evaluations based on the interrelationships between regulations. For example, the evaluation unit can perform optimal evaluations by considering the interrelationships between regulations. This allows for improved evaluation accuracy by considering the interrelationships between regulations.

[0060] The evaluation department can consider the attribute information of the person submitting the regulations when conducting the evaluation. For example, the evaluation department can use AI to evaluate the attribute information of the person submitting the regulations. For example, the evaluation department can consider the position and department of the person submitting the regulations when conducting the evaluation. For example, the evaluation department can also refer to the person's past submission history when conducting the evaluation. For example, the evaluation department can make an optimal evaluation based on the attribute information of the person submitting the regulations. This allows the evaluation to be conducted while considering the attribute information of the person submitting the regulations.

[0061] The evaluation unit can perform evaluations while considering the geographical distribution of the regulations. For example, the evaluation unit can use AI to evaluate the geographical distribution of the regulations. For example, the evaluation unit can perform evaluations for each region where the scope of application of the regulations differs. For example, the evaluation unit can perform optimal evaluations based on geographical distribution. For example, the evaluation unit can improve the accuracy of evaluations by considering the geographical distribution of the regulations. This allows evaluations to be performed while considering the geographical distribution of the regulations.

[0062] The evaluation unit can improve the accuracy of its evaluation by referring to relevant literature on the regulations during the evaluation process. For example, the evaluation unit can use AI to refer to relevant literature on the regulations. For example, the evaluation unit can improve the accuracy of its evaluation by referring to relevant literature on the regulations. The evaluation unit can also perform an optimal evaluation based on relevant literature. For example, the evaluation unit can improve the accuracy of its evaluation by considering relevant literature on the regulations. This allows for improved evaluation accuracy by referring to relevant literature on the regulations.

[0063] The generation unit can improve the accuracy of generation by considering the interrelationships of the regulations during generation. For example, the generation unit can use AI to evaluate the interrelationships of the regulations. For example, the generation unit can analyze the interrelationships of the regulations and perform generation while considering the relevant regulations. For example, the generation unit can also improve the accuracy of generation based on the interrelationships of the regulations. For example, the generation unit can perform optimal generation by considering the interrelationships of the regulations. This makes it possible to improve the accuracy of generation by considering the interrelationships of the regulations.

[0064] The generation unit can perform generation while considering the attribute information of the person submitting the regulations. For example, the generation unit can use AI to evaluate the attribute information of the person submitting the regulations. For example, the generation unit can perform generation while considering the position and department of the person submitting the regulations. For example, the generation unit can perform generation by referring to the past submission history of the person submitting the regulations. For example, the generation unit can perform optimal generation based on the attribute information of the person submitting the regulations. This allows the generation to be performed while considering the attribute information of the person submitting the regulations.

[0065] The generation unit can perform generation while considering the geographical distribution of the regulations. For example, the generation unit can use AI to evaluate the geographical distribution of the regulations. For example, the generation unit can perform generation for each region where the scope of application of the regulations differs. For example, the generation unit can perform optimal generation based on geographical distribution. For example, the generation unit can improve the accuracy of generation by considering the geographical distribution of the regulations. This allows generation to be performed while considering the geographical distribution of the regulations.

[0066] The generation unit can improve the accuracy of its generation by referring to relevant literature in the regulations during the generation process. For example, the generation unit uses AI to refer to relevant literature in the regulations. The generation unit improves the accuracy of its generation by referring to relevant literature in the regulations. The generation unit can also perform optimal generation based on relevant literature. The generation unit can also improve the accuracy of its generation by considering relevant literature in the regulations. This allows for improved generation accuracy by referring to relevant literature in the regulations.

[0067] The prediction unit can improve the accuracy of its predictions by considering the interrelationships of the regulations during the prediction process. For example, the prediction unit can use AI to evaluate the interrelationships of the regulations. For example, the prediction unit can analyze the interrelationships of the regulations and make predictions considering the relevant regulations. The prediction unit can also improve the accuracy of its predictions based on the interrelationships of the regulations. For example, the prediction unit can make optimal predictions by considering the interrelationships of the regulations. This allows for improved prediction accuracy by considering the interrelationships of the regulations.

[0068] The prediction unit can make predictions while considering the attribute information of the person submitting the regulations. For example, the prediction unit can use AI to evaluate the attribute information of the person submitting the regulations. For example, the prediction unit can make predictions while considering the position and department of the person submitting the regulations. For example, the prediction unit can also make predictions by referring to the past submission history of the person submitting the regulations. For example, the prediction unit can make the optimal prediction based on the attribute information of the person submitting the regulations. This allows the prediction to be made while considering the attribute information of the person submitting the regulations.

[0069] The forecasting unit can make predictions while considering the geographical distribution of the regulations. For example, the forecasting unit can use AI to evaluate the geographical distribution of the regulations. For example, the forecasting unit can make predictions for each region where the scope of application of the regulations differs. For example, the forecasting unit can make optimal predictions based on geographical distribution. For example, the forecasting unit can improve the accuracy of predictions by considering the geographical distribution of the regulations. This allows the forecasting unit to make predictions while considering the geographical distribution of the regulations.

[0070] The prediction unit can improve the accuracy of its predictions by referring to relevant literature on the regulations during the prediction process. For example, the prediction unit can use AI to refer to relevant literature on the regulations. The prediction unit can improve the accuracy of its predictions by referring to relevant literature on the regulations. The prediction unit can also make optimal predictions based on relevant literature. The prediction unit can also improve the accuracy of its predictions by considering relevant literature on the regulations. This allows for improved prediction accuracy by referring to relevant literature on the regulations.

[0071] The creation unit can improve the accuracy of its creation process by considering the interrelationships between regulations. For example, the creation unit can use AI to evaluate the interrelationships between regulations. For example, the creation unit can analyze the interrelationships between regulations and create the regulations while considering the relevant regulations. The creation unit can also improve the accuracy of its creation process based on the interrelationships between regulations. For example, the creation unit can perform optimal creation by considering the interrelationships between regulations. This allows for improved accuracy in creation by considering the interrelationships between regulations.

[0072] The creation department can create the regulations while considering the attribute information of the person submitting the regulations. For example, the creation department can use AI to evaluate the attribute information of the person submitting the regulations. For example, the creation department can create the regulations while considering the position and department of the person submitting the regulations. For example, the creation department can also create the regulations while referring to the person's past submission history. For example, the creation department can create the regulations optimally based on the attribute information of the person submitting the regulations. This allows the creation to take into account the attribute information of the person submitting the regulations.

[0073] The creation unit can create regulations while considering their geographical distribution. For example, the creation unit can use AI to evaluate the geographical distribution of the regulations. For example, the creation unit can create regulations for each region with different application scopes. The creation unit can also, for example, perform optimal creation based on geographical distribution. For example, the creation unit can improve the accuracy of creation by considering the geographical distribution of the regulations. This allows for the creation of regulations while considering their geographical distribution.

[0074] The creation unit can improve the accuracy of its creation by referring to relevant documents related to the regulations during the creation process. For example, the creation unit can use AI to refer to relevant documents related to the regulations. For example, the creation unit can improve the accuracy of its creation by referring to relevant documents related to the regulations. The creation unit can also, for example, perform optimal creation based on relevant documents. For example, the creation unit can improve the accuracy of its creation by considering relevant documents related to the regulations. This allows for improved accuracy of creation by referring to relevant documents related to the regulations.

[0075] The creation department can determine the priority of creation based on the submission date of the regulations during the creation process. For example, the creation department can use AI to evaluate the submission date of the regulations. For example, the creation department can prioritize the creation of regulations with a newer submission date. For example, the creation department can adjust the priority of creation for regulations with an older submission date as needed. For example, the creation department can dynamically determine the priority of creation based on the submission date. This allows the creation priority to be determined based on the submission date of the regulations.

[0076] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0077] The AI ​​agent system can also be equipped with a notification function. This notification function can quickly inform employees of important information regarding legal revisions and changes to regulations. For example, when a legal revision occurs, the notification function can immediately send notifications to relevant departments and personnel. It can also send reminders to relevant employees when changes to regulations are necessary. Furthermore, the notification function can manage important deadlines related to legal revisions and changes to regulations, and send notifications as those deadlines approach. This ensures that employees do not miss important information and can respond quickly.

[0078] The AI ​​agent system can also be equipped with a feedback unit. This unit can collect feedback from employees and use it to improve the system. For example, the feedback unit can provide an interface where employees can submit suggestions and opinions regarding legal revisions or changes to regulations. Furthermore, the feedback unit can analyze the collected feedback to identify areas for improvement in the system's functionality and usability. In addition, the feedback unit can update the system or add new features based on employee feedback. This allows for system improvements tailored to employee needs.

[0079] The AI ​​agent system can also include a training department. This department can provide employees with training on legal revisions and changes to regulations. For example, it can offer online courses on the content and impact of legal revisions. It can also create training materials explaining changes to work procedures resulting from regulation changes. Furthermore, the training department can administer tests to check employees' understanding after training. This allows employees to deepen their understanding of legal revisions and regulation changes and respond appropriately.

[0080] The AI ​​agent system can also be equipped with a monitoring unit. This unit can continuously monitor a company's response to legal revisions and regulatory changes. For example, it can check whether each department within the company is appropriately responding to legal revisions. Furthermore, the monitoring unit can provide audit functions to verify that regulatory changes are being implemented correctly. In addition, the monitoring unit can automatically generate periodic reports detailing the status of responses to legal revisions and regulatory changes. This allows the company to understand its overall compliance with legal revisions and take necessary corrective actions.

[0081] The AI ​​agent system can also be equipped with a simulation unit. This unit can simulate the impact of legal revisions and regulatory changes on a company. For example, it can predict how legal revisions will affect a company's business processes. It can also evaluate how regulatory changes will affect a company's compliance status. Furthermore, the simulation unit can simulate the effectiveness of countermeasures against legal revisions and regulatory changes and propose the optimal countermeasures. This allows companies to understand the risks associated with legal revisions and regulatory changes in advance and take appropriate action.

[0082] The following briefly describes the processing flow for example form 1.

[0083] Step 1: The relevant department identifies the relevant section of the company regulations. The department can, for example, use AI to analyze the text data of the company regulations and extract the relevant section. The department can use natural language processing technology to understand the content of the regulations and identify the relevant section. It can also refer to the revision history of the regulations and identify the changes. Step 2: The judgment unit determines the conformity of the parts identified by the identification unit. The judgment unit uses AI to evaluate conformity based on laws and internal standards. By creating a database of legal and internal standards and comparing them with the identified parts, conformity can be determined. The accuracy of the judgment can also be improved by referring to past conformity evaluation results. Step 3: The proposal department makes a proposed course of action based on the results determined by the decision-making department. The proposal department uses AI to propose appropriate countermeasures. It can propose changes and improvements to operations due to legal revisions. It can also refer to past countermeasure proposal history to make the most optimal proposal. Step 4: The Documentation Department verifies and documents relevant materials based on the proposal submitted by the Proposal Department. The Documentation Department uses AI to automatically collect and document relevant materials. It can create a database of legal and internal documents and automatically generate the necessary materials. It can also refer to past documentation history to select the most suitable documentation method.

[0084] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system that supports companies in reviewing internal regulations and responding to legal revisions. This AI agent system learns the impact of legal revisions on internal regulations, operational rules, and clause content. Next, the AI ​​agent system identifies areas of law that need to be understood and addressed in relation to internal procedures and operations, and groups and categorizes them. This enables it to make appropriate suggestions to employees. Furthermore, it proposes customized advice and improvement measures that take into account the legal compliance status of each department and company. For example, by automatically identifying tasks related to legal revisions and creating improvement measures and countermeasures, it is possible to reduce the workload and improve efficiency. This enables departments and the entire company to respond smoothly to legal revisions and minimizes risks and omissions in operational and regulation revisions. For example, the AI ​​agent system identifies the relevant parts of internal regulations and determines their compliance. Next, it reduces workload and burden by proposing countermeasures, reviewing related documents, and documenting them. It also predicts future changes, impacts, concerns, and risks while considering parliamentary deliberations, public opinion trends, scandals and incidents of other companies. Furthermore, the AI ​​agent system analyzes the content and scope of legal revisions and automatically identifies affected internal documents and operational rules. It automatically evaluates the company's compliance with legal revisions and proposes corrections and improvements. It also automatically detects changes in regulations due to legal revisions and automatically generates comparison tables and proposed updates. In this way, the AI ​​agent system enables efficient business operations and minimizes legal risks for companies. For example, it can quickly respond to frequently occurring legal revisions in a company's back-office operations. In addition, it allows employees to easily consult about laws and internal procedures, leading to increased operational efficiency. As a result, the AI ​​agent system can efficiently review internal regulations and respond to legal revisions.

[0085] The AI ​​agent system according to this embodiment comprises an identification unit, a judgment unit, a proposal unit, and a documentation unit. The identification unit identifies the relevant section of the company regulations. The identification unit, for example, uses AI to analyze the text data of the company regulations and extract the relevant section. The identification unit can, for example, use natural language processing technology to understand the content of the regulations and identify the relevant section. The identification unit can also, for example, refer to the change history of the regulations and identify the changes. The judgment unit determines the suitability of the section identified by the identification unit. The judgment unit, for example, uses AI to evaluate suitability based on laws and regulations and company standards. The judgment unit can, for example, create a database of legal standards and company standards and determine suitability by comparing them with the identified section. The judgment unit can also, for example, refer to past suitability evaluation results to improve the accuracy of its judgment. The proposal unit makes a proposal for action based on the results determined by the judgment unit. The proposal unit, for example, uses AI to propose an appropriate action. The proposal unit can, for example, propose changes and improvements to operations due to legal revisions. The proposal department can, for example, refer to past proposal history to make the most appropriate proposal. The documentation department verifies and documents relevant materials based on the content proposed by the proposal department. The documentation department can, for example, use AI to automatically collect and document relevant materials. The documentation department can, for example, create a database of legal documents and internal company documents and automatically generate the necessary materials. The documentation department can, for example, refer to past documentation history to select the most appropriate documentation method. As a result, the AI ​​agent system according to the embodiment can efficiently verify internal regulations and respond to legal revisions.

[0086] The designated department identifies the relevant sections of the company regulations. For example, the department uses AI to analyze the text data of the company regulations and extract the relevant sections. Specifically, it can use natural language processing technology to understand the content of the regulations and identify the relevant sections. Natural language processing technology includes morphological analysis, contextual analysis, and semantic analysis, and by combining these, it can accurately grasp the context and meaning of the regulations. For example, morphological analysis is used to divide the text into words, and contextual analysis is used to analyze the relationships between words. Furthermore, semantic analysis is used to understand the meaning of the entire sentence and identify the relevant sections. The designated department can also refer to the change history of the regulations and identify the changes. The change history is managed using a version control system, which records past changes and the date of change. The designated department analyzes this change history and identifies the changes by comparing the latest regulation content with past regulation content. This allows the designated department to quickly and accurately identify the relevant sections of the company regulations and understand the changes. Furthermore, the designated department can share the identified relevant sections in cooperation with other departments and systems. For example, the identified relevant sections can be saved in a database, making them accessible to other departments. Furthermore, the department can collect feedback on the identified sections to improve the accuracy of the identification process. This allows the department to streamline the management and operation of internal regulations and improve overall business processes.

[0087] The judgment unit determines the conformity of the areas identified by the identification unit. The judgment unit evaluates conformity based on laws and internal standards, for example, using AI. Specifically, it can determine conformity by creating a database of legal and internal standards and comparing them with the identified areas. The AI ​​uses machine learning algorithms to analyze the text data of laws and standards and evaluate the degree of agreement with the identified areas. For example, it uses natural language processing technology to understand the content of laws and standards and evaluate their relevance to the identified areas. Furthermore, the judgment unit can also improve the accuracy of its judgments by referring to past conformity evaluation results. Past evaluation results are stored in the database and used by the AI ​​as training data. This allows the judgment unit to perform more accurate conformity evaluations based on past evaluation results. The judgment unit can share the results of conformity evaluations in cooperation with other departments and systems. For example, evaluation results can be stored in a database and made accessible to other departments. The judgment unit can also collect feedback on the evaluation results and use it to improve evaluation accuracy. This allows the judgment unit to perform conformity evaluations based on laws and internal standards efficiently and accurately, improving the overall business process.

[0088] The Proposal Department makes countermeasure proposals based on the results determined by the Decision Department. The Proposal Department, for example, uses AI to propose appropriate countermeasures. Specifically, it can propose changes and improvements to operations in response to legal revisions. The AI ​​uses machine learning algorithms to learn from past countermeasure proposal history and make optimal proposals. For example, it can create a database of past changes and improvements to operations in response to legal revisions, and the AI ​​analyzes this data to propose the most suitable countermeasure for the current situation. The Proposal Department can share its proposals with other departments and systems. For example, it can save proposals in a database so that other departments can access them. The Proposal Department can also collect feedback on its proposals and use it to improve the accuracy of its proposals. This allows the Proposal Department to efficiently and accurately propose countermeasures in response to legal revisions and business improvements, thereby improving the overall business process. Furthermore, the Proposal Department hands over its proposals to the Documentation Department, providing basic information for the verification and documentation of related documents. This allows the Proposal Department to ensure consistency and accuracy in its countermeasure proposals and to smoothly advance the overall business process.

[0089] The Documentation Department verifies and documents relevant materials based on the proposals submitted by the Proposal Department. For example, the Documentation Department can automatically collect and document relevant materials using AI. Specifically, it can create a database of legal and internal documents and automatically generate necessary materials. The AI ​​analyzes the content of documents using natural language processing technology and extracts relevant information. For example, it can extract necessary articles and regulations from legal documents and relevant procedures and guidelines from internal documents. The Documentation Department can also refer to past documentation history to select the optimal documentation method. Past documentation history is stored in a database and used by the AI ​​as training data. This allows the Documentation Department to perform more efficient and accurate documentation based on past documentation history. The Documentation Department can share the documented content with other departments and systems. For example, it can store the documented content in a database so that other departments can access it. Furthermore, the Documentation Department can collect feedback on the documented content to improve the accuracy of documentation. This allows the Documentation Department to efficiently and accurately verify and document relevant materials, improving the overall business process. Furthermore, the documentation department can regularly update the documented content, ensuring that the information remains up-to-date. This allows the documentation department to consistently provide documents based on the latest information, thereby facilitating the smooth progress of the overall business process.

[0090] The analysis unit can analyze the content and scope of legal amendments and automatically identify affected areas. For example, the analysis unit can use AI to analyze the articles of the legal amendments and identify their scope. For example, the analysis unit can create a database of the content of legal amendments and automatically extract affected areas. For example, the analysis unit can refer to past legal amendment history to identify affected areas. This allows for the rapid identification of the impact of legal amendments.

[0091] The evaluation department can automatically assess a company's compliance with legal revisions and propose corrections and improvements. For example, the evaluation department can use AI to assess a company's compliance with legal revisions. For example, the evaluation department can create a database of legal and internal standards and evaluate a company's compliance. For example, the evaluation department can improve the accuracy of its evaluations by referring to past compliance assessment results. This allows the evaluation of a company's compliance with legal revisions and the proposal of improvement measures.

[0092] The generation unit can automatically detect changes in regulations due to legal revisions and automatically generate comparison tables of old and new versions, as well as draft updates. For example, the generation unit can use AI to analyze the articles of the legal revisions and identify the changes. For example, the generation unit can create a database of the legal revisions and automatically generate comparison tables of old and new versions, as well as draft updates. The generation unit can also, for example, refer to past legal revision history to identify changes. This allows for the automatic detection of changes in regulations and the generation of draft updates.

[0093] The forecasting function can predict future changes, impacts, concerns, and risks by considering parliamentary deliberations, public opinion trends, scandals and incidents involving other companies. For example, the forecasting function can use AI to analyze parliamentary deliberations and public opinion trends to predict future changes and impacts. For example, the forecasting function can collect data on scandals and incidents involving other companies to predict risks. For example, the forecasting function can improve the accuracy of its predictions by referring to past risk prediction results. This allows it to predict future changes, impacts, concerns, and risks.

[0094] The creation unit can automatically identify tasks related to legal revisions and generate improvement measures and countermeasures. For example, the creation unit uses AI to identify tasks related to legal revisions. For example, the creation unit can create a database of legal revision content and automatically generate improvement measures and countermeasures. The creation unit can also refer to past improvement measures and countermeasures to create the most optimal solutions. This enables the automatic identification of tasks related to legal revisions and the generation of improvement measures and countermeasures.

[0095] The identification unit can estimate the user's emotions and determine the priority of the rules to be identified based on the estimated user emotions. The identification unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the identification unit will prioritize identifying high-priority rules. For example, if the user is relaxed, the identification unit can also determine priorities that include detailed rules. For example, if the user is in a hurry, the identification unit can also prioritize identifying rules that require immediate attention. This allows for the prioritization of rules based on the user's emotions.

[0096] The department can analyze the history of past changes to internal regulations and improve the accuracy of its identification. For example, the department can use AI to analyze the history of past changes to regulations. For example, the department can prioritize identifying regulations that are frequently changed. The department can also identify regulations that have a significant impact from changes. Furthermore, the department can improve accuracy by identifying patterns in changes. This allows for improved accuracy in identifying regulations by analyzing the history of past changes to regulations.

[0097] The identification unit can adjust the level of detail based on the importance of the regulations at the time of identification. The identification unit can, for example, use AI to evaluate the importance of the regulations. The identification unit can, for example, provide detailed information for regulations of high importance. The identification unit can also, for example, provide simplified information for regulations of low importance. The identification unit can also, for example, dynamically adjust the level of detail according to the importance of the regulations. This allows the level of detail to be adjusted based on the importance of the regulations.

[0098] The identification unit can estimate the user's emotions and adjust the display method of the specified regulations based on the estimated user emotions. The identification unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is tense, the identification unit provides a simple and highly visible display method. For example, if the user is relaxed, the identification unit may also provide a display method that includes detailed information. For example, if the user is in a hurry, the identification unit may also provide a display method that gets straight to the point. This allows the display method of the regulations to be adjusted based on the user's emotions.

[0099] The identification unit can adjust the order of the regulations based on their relevance at the time of identification. The identification unit can, for example, use AI to evaluate the relevance of the regulations. The identification unit can, for example, group related regulations together, taking into account their relevance. The identification unit can also, for example, dynamically adjust the order of the regulations based on their relevance. The identification unit can, for example, analyze the relevance of the regulations and identify them in the optimal order. This allows the order of the regulations to be adjusted based on their relevance.

[0100] The Identification Department can determine specific priorities based on the submission date of the regulations at the time of identification. The Identification Department can, for example, use AI to evaluate the submission date of the regulations. The Identification Department can, for example, prioritize the identification of regulations that have been submitted recently. The Identification Department can also, for example, adjust the specific priorities for regulations that have been submitted older as needed. The Identification Department can also, for example, dynamically determine specific priorities based on the submission date. This allows for the determination of specific priorities based on the submission date of the regulations.

[0101] The decision-making unit can estimate the user's emotions and adjust its decision criteria based on those emotions. The unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the unit provides concise criteria. If the user is relaxed, the unit can also provide detailed criteria. If the user is in a hurry, the unit can provide criteria that allow for quick decision-making. This allows the decision criteria to be adjusted based on the user's emotions.

[0102] The decision-making unit can improve the accuracy of its decisions by considering the interrelationships of the regulations. For example, the decision-making unit can use AI to evaluate the interrelationships of the regulations. For example, the decision-making unit can analyze the interrelationships of the regulations and make a decision considering the relevant regulations. For example, the decision-making unit can also improve the accuracy of its decisions based on the interrelationships of the regulations. For example, the decision-making unit can make the optimal decision by considering the interrelationships of the regulations. This allows for improved accuracy of decisions by considering the interrelationships of the regulations.

[0103] The decision-making unit can make decisions by considering the attribute information of the person submitting the regulations. For example, the decision-making unit can use AI to evaluate the attribute information of the person submitting the regulations. For example, the decision-making unit can make decisions by considering the position and department of the person submitting the regulations. For example, the decision-making unit can make decisions by referring to the past submission history of the person submitting the regulations. For example, the decision-making unit can make the optimal decision based on the attribute information of the person submitting the regulations. This allows the decision-making unit to consider the attribute information of the person submitting the regulations.

[0104] The decision-making unit can estimate the user's emotions and adjust the order in which the decision results are displayed based on the estimated emotions. The decision-making unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is tense, the decision-making unit can prioritize displaying important results. For example, if the user is relaxed, the decision-making unit can also display detailed results in a sequential manner. For example, if the user is in a hurry, the decision-making unit can prioritize displaying results that summarize the key points. This allows the order in which the decision results are displayed to be adjusted based on the user's emotions.

[0105] The decision-making unit can make decisions considering the geographical distribution of the regulations. For example, the decision-making unit can use AI to evaluate the geographical distribution of the regulations. For example, the decision-making unit can make decisions for each region where the scope of application of the regulations differs. For example, the decision-making unit can make the optimal decision based on the geographical distribution. For example, the decision-making unit can improve the accuracy of its decisions by considering the geographical distribution of the regulations. This allows the decision-making unit to take the geographical distribution of the regulations into consideration.

[0106] The decision-making unit can improve the accuracy of its decisions by referring to relevant documents related to the regulations during the decision-making process. For example, the decision-making unit may use AI to refer to relevant documents related to the regulations. The decision-making unit can improve the accuracy of its decisions by referring to relevant documents related to the regulations. The decision-making unit can also make the optimal decision based on relevant documents. The decision-making unit can also improve the accuracy of its decisions by considering relevant documents related to the regulations. This allows for improved decision-making accuracy by referring to relevant documents related to the regulations.

[0107] The suggestion function can estimate the user's emotions and adjust the way it presents its suggestions based on those emotions. For example, the suggestion function might use an emotion engine or generative AI to estimate the user's emotions. For instance, if the user is stressed, the suggestion function might offer concise and easy-to-understand suggestions. If the user is relaxed, for example, the suggestion function might offer more detailed suggestions. If the user is in a hurry, for example, the suggestion function might offer suggestions that allow for quick action. This allows the suggestion function to adjust its presentation based on the user's emotions.

[0108] The proposal department can adjust the level of detail in its proposals based on the importance of the regulations. For example, the proposal department can use AI to evaluate the importance of the regulations. For example, the proposal department can provide detailed proposals for high-importance regulations. For example, the proposal department can provide simplified proposals for low-importance regulations. The proposal department can also dynamically adjust the level of detail in its proposals according to the importance of the regulations. This allows the level of detail in proposals to be adjusted based on the importance of the regulations.

[0109] The proposal team can apply different proposal algorithms depending on the category of the regulations when making a proposal. For example, the proposal team can use AI to evaluate the category of the regulations. For example, the proposal team can select the optimal proposal algorithm depending on the category of the regulations. The proposal team can also apply different proposal algorithms for each category of regulations. For example, the proposal team can improve the accuracy of the proposals based on the category of the regulations. This allows the application of the optimal proposal algorithm depending on the category of the regulations.

[0110] The suggestion unit can estimate the user's emotions and adjust the length of the suggestion based on those emotions. The suggestion unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the suggestion unit will provide short, concise suggestions. If the user is relaxed, the suggestion unit can provide more detailed suggestions. If the user is in a hurry, the suggestion unit can provide suggestions that allow for quick action. This allows the length of suggestions to be adjusted based on the user's emotions.

[0111] The proposal department can determine the priority of proposals based on the submission date of the regulations when submitting them. For example, the proposal department can use AI to evaluate the submission date of the regulations. For example, the proposal department can prioritize proposals for regulations that have been submitted recently. For example, the proposal department can adjust the priority of proposals for regulations that have been submitted older as needed. For example, the proposal department can dynamically determine the priority of proposals based on the submission date. This allows the priority of proposals to be determined based on the submission date of the regulations.

[0112] The proposal department can adjust the order of proposals based on the relevance of the regulations when making proposals. For example, the proposal department can use AI to evaluate the relevance of the regulations. For example, the proposal department can group related proposals together, taking into account the relevance of the regulations. The proposal department can also dynamically adjust the order of proposals based on the relevance of the regulations. For example, the proposal department can analyze the relevance of the regulations and make proposals in the optimal order. This allows the order of proposals to be adjusted based on the relevance of the regulations.

[0113] The documentation unit can estimate the user's emotions and adjust the documentation method based on the estimated emotions. The documentation unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the documentation unit can create concise and easy-to-understand documentation. For example, if the user is relaxed, the documentation unit can also create detailed documentation. For example, if the user is in a hurry, the documentation unit can create documentation that allows for quick responses. This allows the documentation method to be adjusted based on the user's emotions.

[0114] The documentation department can select the optimal documentation method by referring to past documentation of the regulations during the documentation process. For example, the documentation department can use AI to refer to past documentation. For example, the documentation department can refer to past documentation of the regulations and select the optimal documentation method. For example, the documentation department can select the optimal documentation method based on past documentation. For example, the documentation department can select the optimal documentation method by considering past documentation of the regulations. This allows for the selection of the optimal documentation method by referring to past documentation of the regulations.

[0115] The documentation unit can adjust the level of detail in the documentation based on the importance of the regulations during the documentation process. For example, the documentation unit can use AI to evaluate the importance of the regulations. For example, the documentation unit can create detailed documentation for regulations with high importance. For example, the documentation unit can also create simplified documentation for regulations with low importance. The documentation unit can also dynamically adjust the level of detail in the documentation according to the importance of the regulations. This allows the level of detail in the documentation to be adjusted based on the importance of the regulations.

[0116] The documentation unit can estimate the user's emotions and determine the priority of documentation based on those estimated emotions. The documentation unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the documentation unit will prioritize creating important documents. For example, if the user is relaxed, the documentation unit may also prioritize creating detailed documents. For example, if the user is in a hurry, the documentation unit may also prioritize creating documents that require immediate attention. This allows the documentation unit to determine the priority of documentation based on the user's emotions.

[0117] The documentation unit can create documentation while considering the geographical distribution of the regulations. For example, the documentation unit can use AI to evaluate the geographical distribution of the regulations. For example, the documentation unit can create documentation for each region where the scope of application of the regulations differs. For example, the documentation unit can create optimal documentation based on geographical distribution. For example, the documentation unit can improve the accuracy of documentation by considering the geographical distribution of the regulations. This allows for documentation to be created while considering the geographical distribution of the regulations.

[0118] The documentation unit can improve the accuracy of documentation by referring to relevant documents related to the regulations during the documentation process. For example, the documentation unit can use AI to refer to relevant documents related to the regulations. The documentation unit can improve the accuracy of documentation by referring to relevant documents related to the regulations. The documentation unit can also perform optimal documentation based on relevant documents. The documentation unit can also improve the accuracy of documentation by considering relevant documents related to the regulations. This allows for improved accuracy of documentation by referring to relevant documents related to the regulations.

[0119] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated emotions. The analysis unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the analysis unit provides concise criteria. For example, if the user is relaxed, the analysis unit can also provide detailed criteria. For example, if the user is in a hurry, the analysis unit can provide criteria that allow for quick analysis. This allows the analysis criteria to be adjusted based on the user's emotions.

[0120] The analysis unit can improve the accuracy of the analysis by considering the interrelationships of the regulations during the analysis. For example, the analysis unit can use AI to evaluate the interrelationships of the regulations. For example, the analysis unit can analyze the interrelationships of the regulations and perform the analysis considering the relevant regulations. The analysis unit can also improve the accuracy of the analysis based on the interrelationships of the regulations. For example, the analysis unit can perform the optimal analysis by considering the interrelationships of the regulations. This allows for improved accuracy of the analysis by considering the interrelationships of the regulations.

[0121] The analysis unit can perform analysis while considering the attribute information of the person who submitted the regulations. For example, the analysis unit can use AI to evaluate the attribute information of the person who submitted the regulations. For example, the analysis unit can perform analysis while considering the position and department of the person who submitted the regulations. For example, the analysis unit can also perform analysis while referring to the past submission history of the person who submitted the regulations. For example, the analysis unit can perform optimal analysis based on the attribute information of the person who submitted the regulations. This allows the analysis to be performed while considering the attribute information of the person who submitted the regulations.

[0122] The analysis unit can estimate the user's emotions and adjust the order in which the analysis results are displayed based on the estimated emotions. The analysis unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is tense, the analysis unit can prioritize displaying important results. If the user is relaxed, the analysis unit can also display detailed results in a sequential manner. If the user is in a hurry, the analysis unit can also prioritize displaying results that summarize the key points. This allows the order in which the analysis results are displayed to be adjusted based on the user's emotions.

[0123] The analysis unit can perform analysis while considering the geographical distribution of regulations. For example, the analysis unit can use AI to evaluate the geographical distribution of regulations. For example, the analysis unit can perform analysis for each region where the scope of application of regulations differs. For example, the analysis unit can perform the optimal analysis based on geographical distribution. For example, the analysis unit can improve the accuracy of the analysis by considering the geographical distribution of regulations. This allows the analysis to be performed while considering the geographical distribution of regulations.

[0124] The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the regulations during the analysis. For example, the analysis unit can use AI to refer to relevant literature related to the regulations. The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the regulations. The analysis unit can also perform an optimal analysis based on relevant literature. The analysis unit can also improve the accuracy of its analysis by considering relevant literature related to the regulations. This allows for improved accuracy of the analysis by referring to relevant literature related to the regulations.

[0125] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on those emotions. The evaluation unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the evaluation unit provides concise criteria. For example, if the user is relaxed, the evaluation unit can also provide detailed criteria. For example, if the user is in a hurry, the evaluation unit can provide criteria that allow for quick evaluation. This allows the evaluation criteria to be adjusted based on the user's emotions.

[0126] The evaluation unit can improve the accuracy of its evaluations by considering the interrelationships between regulations. For example, the evaluation unit can use AI to evaluate the interrelationships between regulations. For example, the evaluation unit can analyze the interrelationships between regulations and perform evaluations considering the relevant regulations. The evaluation unit can also improve the accuracy of its evaluations based on the interrelationships between regulations. For example, the evaluation unit can perform optimal evaluations by considering the interrelationships between regulations. This allows for improved evaluation accuracy by considering the interrelationships between regulations.

[0127] The evaluation department can consider the attribute information of the person submitting the regulations when conducting the evaluation. For example, the evaluation department can use AI to evaluate the attribute information of the person submitting the regulations. For example, the evaluation department can consider the position and department of the person submitting the regulations when conducting the evaluation. For example, the evaluation department can also refer to the person's past submission history when conducting the evaluation. For example, the evaluation department can make an optimal evaluation based on the attribute information of the person submitting the regulations. This allows the evaluation to be conducted while considering the attribute information of the person submitting the regulations.

[0128] The evaluation unit can estimate the user's emotions and adjust the order in which the evaluation results are displayed based on the estimated emotions. The evaluation unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is tense, the evaluation unit can prioritize displaying important results. For example, if the user is relaxed, the evaluation unit can also prioritize displaying detailed results. For example, if the user is in a hurry, the evaluation unit can also prioritize displaying concise results. This allows the order in which evaluation results are displayed to be adjusted based on the user's emotions.

[0129] The evaluation unit can perform evaluations while considering the geographical distribution of the regulations. For example, the evaluation unit can use AI to evaluate the geographical distribution of the regulations. For example, the evaluation unit can perform evaluations for each region where the scope of application of the regulations differs. For example, the evaluation unit can perform optimal evaluations based on geographical distribution. For example, the evaluation unit can improve the accuracy of evaluations by considering the geographical distribution of the regulations. This allows evaluations to be performed while considering the geographical distribution of the regulations.

[0130] The evaluation unit can improve the accuracy of its evaluation by referring to relevant literature on the regulations during the evaluation process. For example, the evaluation unit can use AI to refer to relevant literature on the regulations. For example, the evaluation unit can improve the accuracy of its evaluation by referring to relevant literature on the regulations. The evaluation unit can also perform an optimal evaluation based on relevant literature. For example, the evaluation unit can improve the accuracy of its evaluation by considering relevant literature on the regulations. This allows for improved evaluation accuracy by referring to relevant literature on the regulations.

[0131] The generation unit can estimate the user's emotions and determine the priority of the content to generate based on the estimated emotions. The generation unit estimates the user's emotions using, for example, an emotion engine or a generation AI. For example, if the user is stressed, the generation unit will prioritize generating important content. For example, if the user is relaxed, the generation unit can also prioritize generating detailed content. For example, if the user is in a hurry, the generation unit can also prioritize generating content that requires immediate attention. This allows the generation unit to determine the priority of the content to generate based on the user's emotions.

[0132] The generation unit can improve the accuracy of generation by considering the interrelationships of the regulations during generation. For example, the generation unit can use AI to evaluate the interrelationships of the regulations. For example, the generation unit can analyze the interrelationships of the regulations and perform generation while considering the relevant regulations. For example, the generation unit can also improve the accuracy of generation based on the interrelationships of the regulations. For example, the generation unit can perform optimal generation by considering the interrelationships of the regulations. This makes it possible to improve the accuracy of generation by considering the interrelationships of the regulations.

[0133] The generation unit can perform generation while considering the attribute information of the person submitting the regulations. For example, the generation unit can use AI to evaluate the attribute information of the person submitting the regulations. For example, the generation unit can perform generation while considering the position and department of the person submitting the regulations. For example, the generation unit can perform generation by referring to the past submission history of the person submitting the regulations. For example, the generation unit can perform optimal generation based on the attribute information of the person submitting the regulations. This allows the generation to be performed while considering the attribute information of the person submitting the regulations.

[0134] The generation unit can estimate the user's emotions and adjust the display method of the generated content based on the estimated user emotions. The generation unit estimates the user's emotions using, for example, an emotion engine or a generation AI. For example, if the user is tense, the generation unit provides a simple and highly visible display method. For example, if the user is relaxed, the generation unit can also provide a display method that includes detailed information. For example, if the user is in a hurry, the generation unit can also provide a concise display method. This allows the display method of the generated content to be adjusted based on the user's emotions.

[0135] The generation unit can perform generation while considering the geographical distribution of the regulations. For example, the generation unit can use AI to evaluate the geographical distribution of the regulations. For example, the generation unit can perform generation for each region where the scope of application of the regulations differs. For example, the generation unit can perform optimal generation based on geographical distribution. For example, the generation unit can improve the accuracy of generation by considering the geographical distribution of the regulations. This allows generation to be performed while considering the geographical distribution of the regulations.

[0136] The generation unit can improve the accuracy of its generation by referring to relevant literature in the regulations during the generation process. For example, the generation unit uses AI to refer to relevant literature in the regulations. The generation unit improves the accuracy of its generation by referring to relevant literature in the regulations. The generation unit can also perform optimal generation based on relevant literature. The generation unit can also improve the accuracy of its generation by considering relevant literature in the regulations. This allows for improved generation accuracy by referring to relevant literature in the regulations.

[0137] The prediction unit can estimate the user's emotions and adjust the prediction criteria based on the estimated emotions. The prediction unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the prediction unit provides a concise criterion. For example, if the user is relaxed, the prediction unit can also provide a more detailed criterion. For example, if the user is in a hurry, the prediction unit can provide a quickly predictable criterion. This allows the prediction criteria to be adjusted based on the user's emotions.

[0138] The prediction unit can improve the accuracy of its predictions by considering the interrelationships of the regulations during the prediction process. For example, the prediction unit can use AI to evaluate the interrelationships of the regulations. For example, the prediction unit can analyze the interrelationships of the regulations and make predictions considering the relevant regulations. The prediction unit can also improve the accuracy of its predictions based on the interrelationships of the regulations. For example, the prediction unit can make optimal predictions by considering the interrelationships of the regulations. This allows for improved prediction accuracy by considering the interrelationships of the regulations.

[0139] The prediction unit can make predictions while considering the attribute information of the person submitting the regulations. For example, the prediction unit can use AI to evaluate the attribute information of the person submitting the regulations. For example, the prediction unit can make predictions while considering the position and department of the person submitting the regulations. For example, the prediction unit can also make predictions by referring to the past submission history of the person submitting the regulations. For example, the prediction unit can make the optimal prediction based on the attribute information of the person submitting the regulations. This allows the prediction to be made while considering the attribute information of the person submitting the regulations.

[0140] The prediction unit can estimate the user's emotions and adjust the order in which prediction results are displayed based on the estimated emotions. The prediction unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is nervous, the prediction unit can prioritize displaying important results. If the user is relaxed, the prediction unit can also display detailed results in a sequential manner. If the user is in a hurry, the prediction unit can also prioritize displaying results that summarize the key points. This allows the order in which prediction results are displayed to be adjusted based on the user's emotions.

[0141] The forecasting unit can make predictions while considering the geographical distribution of the regulations. For example, the forecasting unit can use AI to evaluate the geographical distribution of the regulations. For example, the forecasting unit can make predictions for each region where the scope of application of the regulations differs. For example, the forecasting unit can make optimal predictions based on geographical distribution. For example, the forecasting unit can improve the accuracy of predictions by considering the geographical distribution of the regulations. This allows the forecasting unit to make predictions while considering the geographical distribution of the regulations.

[0142] The prediction unit can improve the accuracy of its predictions by referring to relevant literature on the regulations during the prediction process. For example, the prediction unit can use AI to refer to relevant literature on the regulations. The prediction unit can improve the accuracy of its predictions by referring to relevant literature on the regulations. The prediction unit can also make optimal predictions based on relevant literature. The prediction unit can also improve the accuracy of its predictions by considering relevant literature on the regulations. This allows for improved prediction accuracy by referring to relevant literature on the regulations.

[0143] The creation unit can estimate the user's emotions and determine the priority of the content to be created based on those estimated emotions. The creation unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is stressed, the creation unit will prioritize creating important content. If the user is relaxed, the creation unit may also prioritize creating detailed content. If the user is in a hurry, the creation unit may also prioritize creating content that requires immediate attention. This allows the creation unit to determine the priority of content based on the user's emotions.

[0144] The creation unit can improve the accuracy of its creation process by considering the interrelationships between regulations. For example, the creation unit can use AI to evaluate the interrelationships between regulations. For example, the creation unit can analyze the interrelationships between regulations and create the regulations while considering the relevant regulations. The creation unit can also improve the accuracy of its creation process based on the interrelationships between regulations. For example, the creation unit can perform optimal creation by considering the interrelationships between regulations. This allows for improved accuracy in creation by considering the interrelationships between regulations.

[0145] The creation department can create the regulations while considering the attribute information of the person submitting the regulations. For example, the creation department can use AI to evaluate the attribute information of the person submitting the regulations. For example, the creation department can create the regulations while considering the position and department of the person submitting the regulations. For example, the creation department can also create the regulations while referring to the person's past submission history. For example, the creation department can create the regulations optimally based on the attribute information of the person submitting the regulations. This allows the creation to take into account the attribute information of the person submitting the regulations.

[0146] The creation unit can estimate the user's emotions and adjust how the content is displayed based on those emotions. The creation unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, if the user is tense, the creation unit provides a simple and highly visible display. If the user is relaxed, the creation unit can also provide a display that includes detailed information. If the user is in a hurry, the creation unit can also provide a concise display. This allows the display method of the content to be adjusted based on the user's emotions.

[0147] The creation unit can create regulations while considering their geographical distribution. For example, the creation unit can use AI to evaluate the geographical distribution of the regulations. For example, the creation unit can create regulations for each region with different application scopes. The creation unit can also, for example, perform optimal creation based on geographical distribution. For example, the creation unit can improve the accuracy of creation by considering the geographical distribution of the regulations. This allows for the creation of regulations while considering their geographical distribution.

[0148] The creation unit can improve the accuracy of its creation by referring to relevant documents related to the regulations during the creation process. For example, the creation unit can use AI to refer to relevant documents related to the regulations. For example, the creation unit can improve the accuracy of its creation by referring to relevant documents related to the regulations. The creation unit can also, for example, perform optimal creation based on relevant documents. For example, the creation unit can improve the accuracy of its creation by considering relevant documents related to the regulations. This allows for improved accuracy of creation by referring to relevant documents related to the regulations.

[0149] The creation department can determine the priority of creation based on the submission date of the regulations during the creation process. For example, the creation department can use AI to evaluate the submission date of the regulations. For example, the creation department can prioritize the creation of regulations with a newer submission date. For example, the creation department can adjust the priority of creation for regulations with an older submission date as needed. For example, the creation department can dynamically determine the priority of creation based on the submission date. This allows the creation priority to be determined based on the submission date of the regulations.

[0150] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0151] The AI ​​agent system can also be equipped with a notification function. This notification function can quickly inform employees of important information regarding legal revisions and changes to regulations. For example, when a legal revision occurs, the notification function can immediately send notifications to relevant departments and personnel. It can also send reminders to relevant employees when changes to regulations are necessary. Furthermore, the notification function can manage important deadlines related to legal revisions and changes to regulations, and send notifications as those deadlines approach. This ensures that employees do not miss important information and can respond quickly.

[0152] The AI ​​agent system can also be equipped with a feedback unit. This unit can collect feedback from employees and use it to improve the system. For example, the feedback unit can provide an interface where employees can submit suggestions and opinions regarding legal revisions or changes to regulations. Furthermore, the feedback unit can analyze the collected feedback to identify areas for improvement in the system's functionality and usability. In addition, the feedback unit can update the system or add new features based on employee feedback. This allows for system improvements tailored to employee needs.

[0153] The AI ​​agent system can also include a training department. This department can provide employees with training on legal revisions and changes to regulations. For example, it can offer online courses on the content and impact of legal revisions. It can also create training materials explaining changes to work procedures resulting from regulation changes. Furthermore, the training department can administer tests to check employees' understanding after training. This allows employees to deepen their understanding of legal revisions and regulation changes and respond appropriately.

[0154] The AI ​​agent system can also be equipped with a monitoring unit. This unit can continuously monitor a company's response to legal revisions and regulatory changes. For example, it can check whether each department within the company is appropriately responding to legal revisions. Furthermore, the monitoring unit can provide audit functions to verify that regulatory changes are being implemented correctly. In addition, the monitoring unit can automatically generate periodic reports detailing the status of responses to legal revisions and regulatory changes. This allows the company to understand its overall compliance with legal revisions and take necessary corrective actions.

[0155] The AI ​​agent system can also be equipped with a simulation unit. This unit can simulate the impact of legal revisions and regulatory changes on a company. For example, it can predict how legal revisions will affect a company's business processes. It can also evaluate how regulatory changes will affect a company's compliance status. Furthermore, the simulation unit can simulate the effectiveness of countermeasures against legal revisions and regulatory changes and propose the optimal countermeasures. This allows companies to understand the risks associated with legal revisions and regulatory changes in advance and take appropriate action.

[0156] The AI ​​agent system can further utilize emotion estimation capabilities to adjust the timing of information provision regarding legal and regulatory changes based on employees' emotions. For example, if an employee is stressed, the timing of providing important information can be delayed. Conversely, if an employee is relaxed, detailed information can be provided earlier. Furthermore, if an employee is in a hurry, concise and to-the-point information can be provided quickly. This enables information provision that takes employees' emotions into consideration, improving the ease with which information is received.

[0157] The AI ​​agent system can further utilize emotion estimation capabilities to tailor training content regarding legal and regulatory changes based on employees' emotions. For example, if an employee is stressed, it can provide concise and easy-to-understand training. If an employee is relaxed, it can provide detailed training. Furthermore, if an employee is in a hurry, it can provide training that focuses on the essentials. This enables training tailored to employees' emotions, improving the effectiveness of the training.

[0158] The AI ​​agent system can further utilize emotion estimation capabilities to adjust how feedback is collected regarding legal and regulatory changes based on employees' emotions. For example, if an employee is stressed, a concise feedback form can be provided. If the employee is relaxed, a more detailed feedback form can be provided. Furthermore, if the employee is in a hurry, a to-the-point feedback form can be provided. This enables the collection of feedback tailored to employees' emotions, improving the quality of the feedback.

[0159] The AI ​​agent system can further utilize emotion estimation capabilities to tailor notifications regarding legal and regulatory changes based on employees' emotions. For example, if an employee is stressed, a concise and easy-to-understand notification can be sent. Conversely, if an employee is relaxed, a detailed notification can be sent. Furthermore, if an employee is in a hurry, a to-the-point notification can be sent. This enables notifications tailored to employees' emotions, improving their likelihood of being received.

[0160] The AI ​​agent system can further utilize emotion estimation capabilities to adjust how simulation results regarding legal and regulatory changes are displayed based on employees' emotions. For example, if an employee is stressed, a simple and highly visible display can be provided. If an employee is relaxed, a display with more detailed information can be provided. Furthermore, if an employee is in a hurry, a concise display can be provided. This enables the display of simulation results tailored to employees' emotions, improving their understanding of the results.

[0161] The following briefly describes the processing flow for example form 2.

[0162] Step 1: The relevant department identifies the relevant section of the company regulations. The department can, for example, use AI to analyze the text data of the company regulations and extract the relevant section. The department can use natural language processing technology to understand the content of the regulations and identify the relevant section. It can also refer to the revision history of the regulations and identify the changes. Step 2: The judgment unit determines the conformity of the parts identified by the identification unit. The judgment unit uses AI to evaluate conformity based on laws and internal standards. By creating a database of legal and internal standards and comparing them with the identified parts, conformity can be determined. The accuracy of the judgment can also be improved by referring to past conformity evaluation results. Step 3: The proposal department makes a proposed course of action based on the results determined by the decision-making department. The proposal department uses AI to propose appropriate countermeasures. It can propose changes and improvements to operations due to legal revisions. It can also refer to past countermeasure proposal history to make the most optimal proposal. Step 4: The Documentation Department verifies and documents relevant materials based on the proposal submitted by the Proposal Department. The Documentation Department uses AI to automatically collect and document relevant materials. It can create a database of legal and internal documents and automatically generate the necessary materials. It can also refer to past documentation history to select the most suitable documentation method.

[0163] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0164] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0165] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0166] Each of the multiple elements described above, including the identification unit, judgment unit, proposal unit, documentation unit, analysis unit, evaluation unit, generation unit, prediction unit, and creation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the identification unit is implemented by the control unit 46A of the smart device 14 and identifies the relevant section of the company regulations. The judgment unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the suitability of the identified section. The proposal unit is implemented by the identification processing unit 290 of the data processing unit 12 and makes a proposal for action. The documentation unit is implemented by the control unit 46A of the smart device 14 and verifies and documents related documents. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the content and scope of application of legal revisions. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and evaluates the suitability of the company. The generation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and detects changes in the regulations and generates a comparison table of old and new versions and proposed updates. The prediction unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and predicts future changes, impacts, concerns, and risks. The creation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and identifies tasks related to legal revisions and creates improvement measures and countermeasures. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0167] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0168] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0169] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0170] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0171] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0173] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0174] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0175] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0176] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0177] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0178] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0179] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0180] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0181] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0182] Each of the multiple elements described above, including the identification unit, judgment unit, proposal unit, documentation unit, analysis unit, evaluation unit, generation unit, prediction unit, and creation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the identification unit is implemented by the control unit 46A of the smart glasses 214 and identifies the relevant section of the company regulations. The judgment unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and determines the suitability of the identified section. The proposal unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and makes a proposal for action. The documentation unit is implemented, for example, by the control unit 46A of the smart glasses 214 and verifies and documents related materials. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and analyzes the content and scope of application of legal revisions. The evaluation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and evaluates the suitability of the company. The generation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and detects changes in the regulations and generates a comparison table of old and new versions and proposed updates. The prediction unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and predicts future changes, impacts, concerns, and risks. The creation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and identifies tasks related to legal revisions and creates improvement measures and countermeasures. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0183] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0184] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0185] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0186] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0187] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0188] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0189] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0190] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0191] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0192] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0193] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0194] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0195] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0196] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0197] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0198] Each of the multiple elements described above, including the identification unit, judgment unit, proposal unit, documentation unit, analysis unit, evaluation unit, generation unit, prediction unit, and creation unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the identification unit is implemented by the control unit 46A of the headset terminal 314 and identifies the relevant section of the company regulations. The judgment unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and determines the suitability of the identified section. The proposal unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and makes a proposal for countermeasures. The documentation unit is implemented by, for example, the control unit 46A of the headset terminal 314 and verifies and documents related materials. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes the content and scope of application of legal revisions. The evaluation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and evaluates the suitability of the company. The generation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and detects changes in the regulations and generates a comparison table of old and new versions and proposed updates. The prediction unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and predicts future changes, impacts, concerns, and risks. The creation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and identifies tasks related to legal revisions and creates improvement measures and countermeasures. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0199] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0200] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0201] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0202] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0203] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0204] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0205] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0206] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0207] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0208] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0209] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0210] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0211] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0212] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0213] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0214] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0215] Each of the multiple elements described above, including the identification unit, judgment unit, proposal unit, documentation unit, analysis unit, evaluation unit, generation unit, prediction unit, and creation unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the identification unit is implemented by the control unit 46A of the robot 414 and identifies the relevant section of the company regulations. The judgment unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and determines the suitability of the identified section. The proposal unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and makes a proposal for action. The documentation unit is implemented by, for example, the control unit 46A of the robot 414 and verifies and documents related documents. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes the content and scope of application of legal revisions. The evaluation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and evaluates the suitability of the company. The generation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and detects changes in the regulations and generates a comparison table of old and new versions and proposed updates. The prediction unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and predicts future changes, impacts, concerns, and risks. The creation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, and identifies tasks related to legal revisions and creates improvement measures and countermeasures. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0216] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0217] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0218] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0219] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0220] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0221] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0222] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0223] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0224] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0225] 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.

[0226] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0227] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0228] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0229] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0230] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0231] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0232] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0233] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0234] (Note 1) A specific department identifies the relevant section of the company regulations, A determination unit that determines the suitability of the part identified by the aforementioned identification unit, A proposal unit makes a suggestion for action based on the result determined by the aforementioned determination unit, The system includes a documentation unit that verifies and documents related materials based on the content proposed by the aforementioned proposal unit. A system characterized by the following features. (Note 2) It includes an analysis unit that analyzes the content and scope of legal revisions and automatically identifies the affected areas. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an evaluation unit that automatically assesses a company's compliance with legal revisions and proposes corrections and improvements. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a generation unit that automatically detects changes in regulations due to legal revisions and automatically generates comparison tables of old and new versions, as well as proposed updates. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a forecasting section that predicts future changes, impacts, concerns, and risks, taking into account parliamentary deliberations, public opinion trends, scandals and incidents at other companies, and other events. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a creation unit that automatically identifies tasks related to legal revisions and generates improvement measures and countermeasures. The system described in Appendix 1, characterized by the features described herein. (Note 7) The specified part is, Estimate user sentiment and determine the priority of specific policies based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The specified part is, Analyze the history of past changes to internal regulations to improve specific accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 9) The specified part is, At specific times, adjust the level of detail based on the importance of the regulations. The system described in Appendix 1, characterized by the features described herein. (Note 10) The specified part is, We will estimate the user's sentiment and adjust how the policy is displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The specified part is, At specific times, adjust the order based on the relevant criteria. The system described in Appendix 1, characterized by the features described herein. (Note 12) The specified part is, At specific times, a specific priority is determined based on the submission date of the regulations. The system described in Appendix 1, characterized by the features described herein. (Note 13) The unit that makes the determination said, It estimates the user's emotions and adjusts the criteria for decision-making based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The unit that makes the determination said, When making a decision, consider the interrelationships between regulations to improve the accuracy of the decision. The system described in Appendix 1, characterized by the features described herein. (Note 15) The unit that makes the determination said, When making a decision, the attribute information of the person who submitted the regulations will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 16) The unit that makes the determination said, It estimates the user's emotions and adjusts the order in which decisions are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The unit that makes the determination said, When making a decision, the geographical distribution of the regulations will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 18) The unit that makes the determination said, When making a decision, refer to relevant literature in the regulations to improve the accuracy of the decision. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, When making a proposal, adjust the level of detail in the proposal based on the importance of the regulations. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, When submitting a proposal, different proposal algorithms are applied depending on the specified category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, When submitting a proposal, the priority of the proposal will be determined based on the submission deadline stipulated in the regulations. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, When making proposals, adjust the order of proposals based on the relevance of the regulations. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned data preparation unit, We estimate the user's emotions and adjust the documentation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned data preparation unit, When creating documentation, refer to past documentation of the regulations to select the most suitable documentation method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned data preparation unit, When creating documentation, adjust the level of detail based on the importance of the regulations. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned data preparation unit, We estimate user emotions and determine the priority of documentation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned data preparation unit, When creating documentation, the geographical distribution of the regulations should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned data preparation unit, When creating documentation, we refer to relevant literature related to the regulations to improve the accuracy of the documentation. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned analysis unit, During analysis, consider the interrelationships between the regulations to improve the accuracy of the analysis. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned analysis unit, During the analysis, the attribute information of the person who submitted the regulations will be taken into consideration. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned analysis unit, It estimates the user's emotions and adjusts the order in which the analysis results are displayed based on the estimated user emotions. The system according to appended note 2, characterized in that... (Appended note 35) The analysis unit Performs analysis considering the geographical distribution of the regulations during analysis The system according to appended note 2, characterized in that... (Appended note 36) The analysis unit Improves the accuracy of analysis by referring to the related literature of the regulations during analysis The system according to appended note 2, characterized in that... (Appended note 37) The evaluation unit Estimates the user's sentiment and adjusts the evaluation criteria based on the estimated user's sentiment The system according to appended note 3, characterized in that... (Appended note 38) The evaluation unit Improves the accuracy of evaluation by considering the interrelationships of the regulations during evaluation The system according to appended note 3, characterized in that... (Appended note 39) The evaluation unit Performs evaluation considering the attribute information of the submitter of the regulations during evaluation The system according to appended note 3, characterized in that... (Appended note 40) The evaluation unit Estimates the user's sentiment and adjusts the order of displaying the evaluation results based on the estimated user's sentiment The system according to appended note 3, characterized in that... (Appended note 41) The evaluation unit Performs evaluation considering the geographical distribution of the regulations during evaluation The system according to appended note 3, characterized in that... (Appended note 42) The evaluation unit Improves the accuracy of evaluation by referring to the related literature of the regulations during evaluation The system according to appended note 3, characterized in that... (Appended note 43) The generation unit It estimates the user's emotions and determines the priority of the content to generate based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The generating unit is During generation, the accuracy of the generation is improved by considering the interrelationships of the regulations. The system described in Appendix 4, characterized by the features described herein. (Note 45) The generating unit is During generation, the system takes into account the attribute information of the person submitting the regulations. The system described in Appendix 4, characterized by the features described herein. (Note 46) The generating unit is It estimates the user's emotions and adjusts how the generated content is displayed based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 47) The generating unit is During generation, the system takes into account the specified geographical distribution. The system described in Appendix 4, characterized by the features described herein. (Note 48) The generating unit is During generation, the accuracy of the generation is improved by referring to relevant literature specified in the regulations. The system described in Appendix 4, characterized by the features described herein. (Note 49) The aforementioned prediction unit, It estimates the user's emotions and adjusts the forecast criteria based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 50) The aforementioned prediction unit, When making predictions, we improve the accuracy of the predictions by considering the interrelationships between the regulations. The system described in Appendix 5, characterized by the features described herein. (Note 51) The aforementioned prediction unit, When making predictions, the attribute information of the person submitting the regulations will be taken into consideration. The system described in Appendix 5, characterized by the features described herein. (Appendix 52) The prediction unit estimates the user's emotion and adjusts the order of displaying the prediction result based on the estimated user's emotion The system according to Appendix 5, characterized in that (Appendix 53) The prediction unit makes a prediction considering the geographical distribution of regulations during prediction The system according to Appendix 5, characterized in that (Appendix 54) The prediction unit refers to the relevant literature of regulations to improve the accuracy of prediction during prediction The system according to Appendix 5, characterized in that (Appendix 55) The creation unit estimates the user's emotion and determines the priority of the content to be created based on the estimated user's emotion The system according to Appendix 6, characterized in that (Appendix 56) The creation unit considers the interrelationship of regulations to improve the accuracy of creation during creation The system according to Appendix 6, characterized in that (Appendix 57) The creation unit performs creation considering the attribute information of the submitter of the regulations during creation The system according to Appendix 6, characterized in that (Appendix 58) The creation unit estimates the user's emotion and adjusts the display method of the content to be created based on the estimated user's emotion The system according to Appendix 6, characterized in that (Appendix 59) The creation unit performs creation considering the geographical distribution of regulations during creation The system according to Appendix 6, characterized in that (Appendix 60) The creation unit When creating the document, refer to the relevant literature in the regulations to improve its accuracy. The system described in Appendix 6, characterized by the features described herein. (Note 61) The aforementioned creation unit, When creating the documents, prioritize their creation based on the submission deadlines for each regulation. The system described in Appendix 6, characterized by the features described herein. [Explanation of Symbols]

[0235] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A specific department identifies the relevant section of the company regulations, A determination unit that determines the suitability of the part identified by the aforementioned identification unit, A proposal unit makes a suggestion for action based on the result determined by the aforementioned determination unit, The system includes a documentation unit that verifies and documents related materials based on the content proposed by the aforementioned proposal unit. A system characterized by the following features.

2. It includes an analysis unit that analyzes the content and scope of legal revisions and automatically identifies the affected areas. The system according to feature 1.

3. It includes an evaluation unit that automatically assesses a company's compliance with legal revisions and proposes corrections and improvements. The system according to feature 1.

4. It includes a generation unit that automatically detects changes in regulations due to legal revisions and automatically generates comparison tables of old and new versions, as well as proposed updates. The system according to feature 1.

5. It includes a forecasting section that predicts future changes, impacts, concerns, and risks, taking into account parliamentary deliberations, public opinion trends, scandals and incidents at other companies, and other events. The system according to feature 1.

6. It includes a creation unit that automatically identifies tasks related to legal revisions and generates improvement measures and countermeasures. The system according to feature 1.

7. The specified part is, Estimate user sentiment and determine the priority of specific policies based on that estimated sentiment. The system according to feature 1.

8. The specified part is, Analyze the history of past changes to internal regulations to improve specific accuracy. The system according to feature 1.

Images