system

Abstract

The system according to this embodiment aims to automate the collection of legal revision information and the updating of internal regulations, enabling a rapid response. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, and a selection unit. The collection unit collects legal amendment information. The analysis unit analyzes the legal amendment information collected by the collection unit. The generation unit generates a revised version based on the information analyzed by the analysis unit. The selection unit selects the revised version generated by the generation 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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the collection of legal amendment information and the update of internal regulations are performed manually, making it difficult to respond promptly.

[0005] The system according to the embodiment aims to automate the collection of legal amendment information and the update of internal regulations and respond promptly.

Means for Solving the Problems

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a selection unit. The collection unit collects legal amendment information. The analysis unit analyzes the legal amendment information collected by the collection unit. The generation unit generates a revision plan based on the information analyzed by the analysis unit. The selection unit selects the revision plan generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can automate the collection of legal amendment information and the updating of internal regulations, enabling rapid response. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 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 embodiment 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 solution for automating the rapid acquisition of legal amendment information and the updating of internal regulations according to the embodiment of the present invention is a system that collects, analyzes, generates, and selects legal amendment information. By collecting, analyzing, generating, and selecting legal amendment information, this system improves operational efficiency and reduces compliance risks. For example, this system crawls government websites and automatically collects legal amendment information. For example, the AI ​​periodically visits websites to obtain the latest legal amendment information. For example, it can collect information on newly enacted and amended laws. This reduces the risk of overlooking information or delays in response due to manual information collection. Next, the AI ​​analyzes the collected legal amendment information and the company's internal regulations. For example, the AI ​​analyzes the collected legal amendment information and determines what impact it will have on the internal regulations. For example, if there is an amendment to the Personal Information Protection Act, the AI ​​can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. Subsequently, the AI ​​generates three proposed revisions (minimal change, moderate change, and major revision). For example, the minimal change approach proposes only the minimum necessary modifications to existing regulations in response to legal changes. For example, the moderate change approach makes moderate adjustments to existing regulations in response to legal changes. For example, the major revision approach involves a complete review of existing regulations in response to legal changes, incorporating the latest business flows and technologies. In this way, those in charge can select the optimal revision plan according to their company's situation. Furthermore, this system has multilingual analysis capabilities that can handle global legal regulations, enabling rapid responses to legal changes in each country. For example, it can collect and analyze legal change information in the United States and Europe. This enables global companies to respond to legal changes quickly and accurately. In addition, this system can capture discussions regarding legal changes in government and prepare for future regulation revisions. For example, it can collect the content of discussions regarding legal changes and prepare for future regulation revisions. This enables regulation revisions that are in line with current trends. This mechanism automates the rapid acquisition of legal change information and the updating of internal regulations, resulting in reduced compliance risks and improved operational efficiency.Furthermore, a key feature is the ability to select the most suitable version from multiple revised options, making it an extremely useful solution for corporate legal and general affairs departments that manage regulations. This solution automates the rapid acquisition of legal revision information and the updating of internal regulations, thereby improving operational efficiency and reducing compliance risks.

[0029] The system for automating the rapid acquisition of legal amendment information and the updating of internal regulations according to the embodiment comprises a collection unit, an analysis unit, a generation unit, and a selection unit. The collection unit collects legal amendment information. The collection unit, for example, crawls government websites and automatically collects legal amendment information. The collection unit can, for example, periodically visit websites using AI to obtain the latest legal amendment information. The collection unit can, for example, collect information on newly enacted and amended laws. The collection unit can, for example, reduce the risk of oversights and delays in response due to manual information collection. The analysis unit analyzes the legal amendment information collected by the collection unit. The analysis unit, for example, analyzes the collected legal amendment information and determines what impact it will have on internal regulations. For example, if there is an amendment to the Personal Information Protection Act, the analysis unit can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. The generation unit generates revised drafts based on the information analyzed by the analysis unit. The generation unit generates three revised drafts, for example, minimal changes, moderate changes, and major revisions. The generation unit, for example, in the minimal change approach, proposes only the minimum necessary modifications to the current regulations for the legal amendment. The generation unit, for example, in the moderate change approach, makes moderate adjustments to the current regulations in response to the legal amendment requirements. The generation unit, for example, in the major revision approach, comprehensively reviews the current regulations in response to the legal amendment and introduces the latest business flows and technologies. The selection unit selects the proposed revisions generated by the generation unit. The selection unit allows, for example, a person in charge to select the most suitable proposed revision for their company's situation. As a result, the system that automates the rapid acquisition of legal amendment information and the updating of internal regulations according to the embodiment can achieve improved operational efficiency and reduced compliance risks. Some or all of the above-described processes in the collection unit may be performed using AI, for example, or not. For example, the collection unit can use AI to crawl websites and obtain the latest legal amendment information in order to collect legal amendment information. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or not.For example, the analysis unit can use AI to analyze the collected legal amendment information and determine what impact it will have on internal regulations. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can use AI to generate three revision proposals: minimal changes, moderate changes, and major revisions. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can use AI to select the optimal revision proposal from the generated proposals.

[0030] The data collection unit collects information on legal amendments. For example, the unit crawls government websites to automatically collect information on legal amendments. Specifically, the unit uses a web crawler to periodically visit the websites of various government agencies and obtain newly published information on legal amendments. The web crawler analyzes the HTML structure of each webpage based on a specified URL list and extracts information related to legal amendments. The data collection unit can also use AI to periodically visit websites and obtain the latest information on legal amendments. The AI ​​uses natural language processing technology to analyze the content of webpages and extract important information regarding legal amendments. For example, the AI ​​automatically extracts information such as the name of the law, the date of amendment, and the content of the amendment, and stores it in a database. The data collection unit can collect information on newly enacted and amended laws. The data collection unit can reduce the risk of oversights and delays in response due to manual information collection. This allows the data collection unit to collect legal amendment information quickly and accurately, providing the information necessary for updating internal regulations. Furthermore, the data collection unit can centrally manage the collected information and collaborate with other systems and departments as needed. For example, collected legal amendment information is stored on a cloud server, making it accessible to the analysis and generation units. Furthermore, the collection unit can flexibly configure the collection frequency and the websites to be collected, enabling rapid responses to specific legal amendment information. This allows the collection unit to efficiently and effectively collect legal amendment information, improving the overall system performance.

[0031] The analysis unit analyzes the legal amendment information collected by the collection unit. For example, the analysis unit analyzes the collected legal amendment information and determines what impact it will have on internal company regulations. Specifically, the analysis unit uses natural language processing technology to analyze the content of the legal amendment information and extract the key points of the amendments. For example, if there is an amendment to the Personal Information Protection Act, the analysis unit can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. The AI ​​analyzes the text of the legal amendment information, extracts the key points of the amendments, and identifies which parts of the internal regulations are affected. For example, the AI ​​extracts keywords related to the amendments, searches for the relevant parts of the internal regulations, and identifies the scope of the impact. For example, the analysis unit evaluates the importance and scope of the amendments and identifies the parts of the internal regulations that need to be updated. This allows the analysis unit to quickly and accurately analyze the collected legal amendment information and provide the information necessary to update internal regulations. Furthermore, the analysis unit can also utilize past legal amendment information and the history of changes to internal regulations to conduct long-term impact assessments and trend analyses. For example, based on past legal amendment data, the analysis unit can analyze the frequency and scope of amendments to specific laws and regulations, and formulate future countermeasures. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the analysis unit to not only grasp the situation in real time, but also to handle long-term risk management and anomaly detection, improving the overall reliability and security of the system.

[0032] The generation unit generates revised drafts based on the information analyzed by the analysis unit. The generation unit generates three types of revised drafts: minimal changes, moderate changes, and major revisions. Specifically, the generation unit automatically generates revised drafts using AI. The minimal change approach proposes only the minimum necessary modifications to the current regulations to comply with the legal amendment. For example, if the legal amendment can be addressed by simply modifying the wording of a specific clause, the minimal change approach is applied. The moderate change approach makes moderate adjustments to the current regulations in response to the legal amendment. For example, if modifications across multiple clauses or the addition of new clauses are required, the moderate change approach is applied. The major revision approach involves a complete review of the current regulations in response to the legal amendment, introducing the latest business flows and technologies. For example, if the legal amendment necessitates a review of the entire business process, the major revision approach is applied. The generation unit automatically generates these revised drafts and provides them to the responsible personnel. This allows the generation unit to provide revised drafts that enable quick and flexible responses to legal amendments, streamlining the updating of internal regulations. Furthermore, the generation unit can continuously improve the accuracy and effectiveness of proposed revisions by utilizing past revision history and business flow data. For example, it can analyze the results of past proposed revisions and optimize the revision generation algorithm. In addition, the generation unit can reduce the burden on personnel and improve operational efficiency by automating the proposal generation process. As a result, the generation unit can support the updating of internal regulations and contribute to reducing compliance risks by providing prompt and accurate proposed revisions.

[0033] The selection unit selects the proposed revisions generated by the generation unit. For example, the selection unit allows a person in charge to select the most suitable revision based on their company's specific circumstances. Specifically, the selection unit displays a list of generated revisions, allowing the person in charge to review the details of each revision. The person in charge compares the content and scope of impact of the revisions and selects the one best suited to their company's situation. The selection unit can, for example, use AI to select the optimal revision. Based on past selection history and workflow data, the AI ​​recommends the most suitable revision to the person in charge. For example, the AI ​​analyzes past revision history and learns selection patterns for similar legal amendments. This allows the AI ​​to recommend the most suitable revision to the person in charge and support the selection process. Furthermore, the selection unit collects the implementation results of the selected revisions as feedback, continuously improving the accuracy of the revision generation and selection algorithms. For example, it analyzes the implementation results of the revisions and evaluates their effectiveness and impact. This allows the selection unit to streamline the revision selection process and reduce the burden on the person in charge. Furthermore, the selection unit can provide tools and resources to support the implementation of the selected revisions. For example, it can automatically generate and provide the necessary documents and procedures for implementing the revisions to the person in charge. In this way, the selection unit can consistently support the process from the selection of revisions to their implementation, streamlining the updating of internal regulations.

[0034] The multilingual analysis unit is equipped with multilingual analysis capabilities. The multilingual analysis unit is equipped with multilingual analysis capabilities that can, for example, respond to global legal regulations. The multilingual analysis unit can, for example, respond quickly to legal changes in various countries. The multilingual analysis unit can, for example, collect and analyze information on legal changes in the United States and Europe. The multilingual analysis unit enables, for example, global companies to respond quickly and accurately to legal changes. This allows the multilingual analysis unit to respond quickly to global legal regulations. Some or all of the above-described processes in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, the multilingual analysis unit can use AI to perform multilingual analysis in order to collect and analyze information on legal changes.

[0035] The discussion catching unit captures discussions in preparation for future revisions of regulations. For example, the discussion catching unit captures discussions toward amendments to laws in administration. For example, the discussion catching unit can collect the content of discussions toward legal amendments and prepare for future revisions of regulations. For example, the discussion catching unit can revise regulations in line with current trends. This enables the discussion catching unit to prepare for future legal amendments. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, the discussion catching unit can use AI to collect the content of discussions in order to capture discussions toward legal amendments.

[0036] The analysis unit can analyze collected legal amendment information and determine what impact it will have on internal regulations. For example, if there is an amendment to the Personal Information Protection Act, the analysis unit can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. This allows the analysis unit to automatically determine the impact of legal amendment information on internal regulations. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use AI to analyze collected legal amendment information and determine what impact it will have on internal regulations.

[0037] The generation unit can generate three types of revision proposals: minimal changes, moderate changes, and major revisions. For example, the generation unit can generate three types of revision proposals: minimal changes, moderate changes, and major revisions. For example, in the minimal change approach, the generation unit proposes only the minimum necessary modifications to the current regulations required for the legal amendment. For example, in the moderate change approach, the generation unit makes moderate adjustments to the current regulations in response to the requirements of the legal amendment. For example, in the major revision approach, the generation unit comprehensively reviews the current regulations in response to the legal amendment and introduces the latest business flows and technologies. This allows the generation unit to select the best one from multiple revision proposals. Some or all of the above processing in the generation unit may be performed using AI, for example, or not. For example, the generation unit can use AI to generate three types of revision proposals: minimal changes, moderate changes, and major revisions in order to generate revision proposals.

[0038] The selection unit can select the best option from the generated revised drafts. For example, the selection unit can select the best option from the generated revised drafts. For example, the selection unit can allow a person in charge to select the best revised draft that suits their company's situation. This streamlines the updating of internal regulations by allowing the selection unit to select the best revised draft. Some or all of the above-described processes in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can use AI to select the best revised draft in order to select from the generated revised drafts.

[0039] The data collection unit can analyze past legal amendment information collection history and select the optimal collection method. For example, the data collection unit can select a method to efficiently obtain information by collecting it during specific time periods based on past collection history. For example, the data collection unit can analyze past collection history and prioritize information collection from specific websites. For example, the data collection unit can optimize collection frequency based on past collection history to ensure that all necessary information is collected without omission. This enables efficient information collection by allowing the data collection unit to select the optimal collection method based on past collection history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can use AI to analyze data in order to analyze past collection history and select the optimal collection method.

[0040] The data collection unit can filter information on legal amendments based on specific legal fields or regions. For example, the data collection unit can collect only information related to specific legal fields (e.g., labor law, tax law). For example, the data collection unit can prioritize the collection of information on legal amendments in specific regions (e.g., the United States, Europe). For example, the data collection unit can filter and collect the necessary information based on a combination of legal field and region. This allows the data collection unit to efficiently collect the necessary information by filtering it based on specific legal fields or regions. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when collecting information on legal amendments, the data collection unit can use AI to filter the information based on specific legal fields or regions.

[0041] The data collection unit can prioritize the collection of highly relevant information when gathering information on legal amendments, taking into account the user's industry characteristics. For example, if the user belongs to the financial industry, the data collection unit will prioritize the collection of financial-related legal amendments. For example, if the user belongs to the manufacturing industry, the data collection unit can prioritize the collection of manufacturing-related legal amendments. For example, if the user belongs to the IT industry, the data collection unit can prioritize the collection of IT-related legal amendments. In this way, the data collection unit can efficiently collect highly relevant information by collecting information while taking into account the user's industry characteristics. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, when collecting information on legal amendments, the data collection unit can use AI to collect information while taking into account the user's industry characteristics.

[0042] The data collection unit can analyze users' social media activity and collect relevant information when collecting information on legal amendments. For example, the data collection unit can prioritize collecting information on legal amendments that users have shown interest in on social media. For example, the data collection unit can collect relevant information on legal amendments from users' social media activity. For example, the data collection unit can analyze posts from experts and organizations that users follow and collect relevant information on legal amendments. This allows the data collection unit to efficiently collect relevant information by analyzing users' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, when collecting information on legal amendments, the data collection unit can use AI to analyze users' social media activity and collect relevant information.

[0043] The analysis unit can adjust the level of detail of its analysis based on the importance of the legal amendment information during the analysis. For example, the analysis unit can perform a detailed analysis of legal amendment information of high importance. For example, the analysis unit can perform a concise analysis of legal amendment information of low importance. The analysis unit can adjust the level of detail of its analysis in stages according to the importance of the information. This enables efficient analysis by allowing the analysis unit to adjust the level of detail of its analysis according to the importance of the legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit can use AI to adjust the level of detail of its analysis based on its importance.

[0044] The analysis unit can apply different analysis algorithms depending on the category of the legal amendment information during analysis. For example, the analysis unit can apply a labor law-specific analysis algorithm to legal amendment information related to labor law. For example, the analysis unit can apply a tax law-specific analysis algorithm to legal amendment information related to tax law. For example, the analysis unit can apply an environmental law-specific analysis algorithm to legal amendment information related to environmental law. This allows the analysis unit to perform highly accurate analysis by applying an analysis algorithm according to the category of the legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit can use AI to apply different analysis algorithms depending on the category.

[0045] The analysis unit can determine the priority of analysis based on the publication date of legal amendment information during the analysis process. For example, the analysis unit may prioritize the analysis of recently published legal amendment information. For example, the analysis unit may postpone the analysis of older legal amendment information. For example, the analysis unit may adjust the priority of analysis in stages according to the publication date. This enables efficient analysis by allowing the analysis unit to determine the priority of analysis based on the publication date of legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit may use AI to determine the priority of analysis based on the publication date.

[0046] The analysis unit can adjust the order of analysis based on the relevance of the legal amendment information during the analysis. For example, the analysis unit may prioritize the analysis of legal amendment information that has a significant impact on internal company regulations. For example, the analysis unit may postpone the analysis of less relevant legal amendment information. For example, the analysis unit may adjust the order of analysis in stages according to relevance. This enables efficient analysis by adjusting the order of analysis based on the relevance of the legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit may use AI to adjust the order of analysis based on relevance.

[0047] The generation unit can adjust the level of detail in the proposed revisions based on the importance of the legal amendment information when generating the revised revisions. For example, the generation unit can generate detailed revised revisions for legal amendment information of high importance. For example, the generation unit can generate concise revised revisions for legal amendment information of low importance. The generation unit can adjust the level of detail in the revised revisions in stages according to the importance. This enables efficient generation of revised revisions by adjusting the level of detail in the revised revisions according to the importance of the legal amendment information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, when generating revised revisions, the generation unit can use AI to adjust the level of detail in the revised revisions based on their importance.

[0048] The generation unit can apply different revision generation algorithms depending on the category of the legal amendment information when generating revision proposals. For example, the generation unit can apply a revision generation algorithm specifically for labor law to legal amendment information concerning labor law. For example, the generation unit can apply a revision generation algorithm specifically for tax law to legal amendment information concerning tax law. For example, the generation unit can apply a revision generation algorithm specifically for environmental law to legal amendment information concerning environmental law. This enables the generation unit to generate highly accurate revision proposals by applying a revision generation algorithm according to the category of the legal amendment information. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, when generating revision proposals, the generation unit can use AI to apply different revision generation algorithms depending on the category.

[0049] The generation unit can determine the priority of proposed revisions based on the timing of announcements of legal amendment information when generating revised drafts. For example, the generation unit can prioritize the inclusion of recently announced legal amendment information in the revised drafts. For example, the generation unit can postpone the generation of revised drafts for older legal amendment information. For example, the generation unit can adjust the priority of revised drafts in stages according to the timing of announcements. This enables efficient generation of revised drafts by determining the priority of revised drafts based on the timing of announcements of legal amendment information. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, when generating revised drafts, the generation unit can use AI to determine the priority of revised drafts based on the timing of announcements.

[0050] The generation unit can adjust the order of the revised drafts based on the relevance of the legal amendment information when generating the revised drafts. For example, the generation unit will prioritize reflecting legal amendment information that has a significant impact on internal regulations in the revised drafts. For example, the generation unit can postpone the generation of revised drafts for legal amendment information that is less relevant. For example, the generation unit can adjust the order of the revised drafts in stages according to their relevance. This enables efficient generation of revised drafts by adjusting the order of the revised drafts based on the relevance of the legal amendment information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, when generating revised drafts, the generation unit can use AI to adjust the order of the revised drafts based on their relevance.

[0051] The selection unit can select the optimal selection method by referring to past selection history when selecting a revised proposal. For example, the selection unit can propose the optimal selection method based on the history of previously selected revised proposals. For example, the selection unit can prioritize presenting revised proposals based on user preferences from past selection history. For example, the selection unit can analyze past selection history and propose the most efficient selection method. As a result, the selection unit can efficiently select revised proposals by selecting the optimal selection method based on past selection history. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised proposal, the selection unit can use AI to refer to past selection history and select the optimal selection method.

[0052] The selection unit can customize the selection method based on the user's work situation when selecting a revised proposal. For example, if the user is busy, the selection unit will prioritize presenting a concise and to-the-point revised proposal. For example, if the user has ample time, the selection unit can present a detailed revised proposal. For example, the selection unit can customize the selection method according to the user's work situation and present the optimal revised proposal. In this way, the selection unit can select the optimal revised proposal by customizing the selection method according to the user's work situation. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised proposal, the selection unit can use AI to analyze the user's work situation and customize the selection method.

[0053] The selection unit can choose the optimal selection method when selecting a revised proposal, taking into account the user's industry characteristics. For example, if the user belongs to the financial industry, the selection unit can prioritize presenting financial-related revised proposals. For example, if the user belongs to the manufacturing industry, the selection unit can prioritize presenting manufacturing-related revised proposals. For example, if the user belongs to the IT industry, the selection unit can prioritize presenting IT-related revised proposals. In this way, the selection unit can select a highly relevant revised proposal by choosing a selection method that takes into account the user's industry characteristics. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised proposal, the selection unit can use AI to analyze the user's industry characteristics and select the optimal selection method.

[0054] The selection unit can analyze the user's social media activity and suggest methods for selection when selecting a revised version. For example, the selection unit can prioritize presenting revised versions that the user has shown interest in on social media. For example, the selection unit can present relevant revised versions based on the user's social media activity. For example, the selection unit can analyze posts from experts and organizations that the user follows and present relevant revised versions. In this way, the selection unit can efficiently select relevant revised versions by analyzing the user's social media activity. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised version, the selection unit can use AI to analyze the user's social media activity and suggest methods for selection.

[0055] The multilingual analysis unit can optimize its analysis algorithm by referring to past analysis data during multilingual analysis. For example, the multilingual analysis unit can select the optimal analysis algorithm based on past analysis data. For example, the multilingual analysis unit can analyze past analysis data and apply an algorithm to improve analysis accuracy. For example, the multilingual analysis unit can refer to past analysis data and apply an algorithm to improve analysis efficiency. As a result, the multilingual analysis unit improves analysis accuracy by optimizing its analysis algorithm based on past analysis data. Some or all of the above processes in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, when the multilingual analysis unit refers to past analysis data, it can use AI to analyze the data and select the optimal analysis algorithm.

[0056] The multilingual analysis unit can customize its analysis methods based on specific languages ​​and regions during multilingual analysis. For example, the multilingual analysis unit can apply analysis methods corresponding to specific languages ​​(e.g., English, French). For example, the multilingual analysis unit can apply analysis methods corresponding to legal amendment information in specific regions (e.g., America, Europe). For example, the multilingual analysis unit can customize the optimal analysis method based on a combination of language and region. This enables the multilingual analysis unit to perform highly accurate analysis by customizing its analysis methods based on specific languages ​​and regions. Some or all of the above-described processes in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the multilingual analysis unit can use AI to customize its analysis methods based on specific languages ​​and regions.

[0057] The multilingual analysis unit can select the optimal analysis method by considering the user's industry characteristics during multilingual analysis. For example, if the user belongs to the financial industry, the multilingual analysis unit can apply a financial-related multilingual analysis method. For example, if the user belongs to the manufacturing industry, the multilingual analysis unit can apply a manufacturing-related multilingual analysis method. For example, if the user belongs to the IT industry, the multilingual analysis unit can apply an IT-related multilingual analysis method. In this way, the multilingual analysis unit can provide highly relevant analysis results by selecting an analysis method that considers the user's industry characteristics. Some or all of the above processing in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the multilingual analysis unit can use AI to analyze the user's industry characteristics and select the optimal analysis method.

[0058] The multilingual analysis unit can analyze the user's social media activity and propose analysis methods during multilingual analysis. For example, the multilingual analysis unit can prioritize providing multilingual analysis results that the user has shown interest in on social media. For example, the multilingual analysis unit can provide relevant multilingual analysis results from the user's social media activity. For example, the multilingual analysis unit can analyze posts from experts and organizations that the user follows and provide relevant multilingual analysis results. In this way, the multilingual analysis unit can efficiently provide relevant analysis results by analyzing the user's social media activity. Some or all of the above processing in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the multilingual analysis unit can use AI to analyze the user's social media activity and propose analysis methods.

[0059] The discussion catching unit can optimize its catching algorithm by referring to past discussion data when catching a discussion. For example, the discussion catching unit can select the optimal catching algorithm based on past discussion data. For example, the discussion catching unit can analyze past discussion data and apply an algorithm to improve catching accuracy. For example, the discussion catching unit can refer to past discussion data and apply an algorithm to improve catching efficiency. As a result, the discussion catching unit improves catching accuracy by optimizing its catching algorithm based on past discussion data. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without using AI. For example, when the discussion catching unit refers to past discussion data, it can use AI to analyze the data and select the optimal catching algorithm.

[0060] The discussion catching unit can customize its catching methods based on specific legal fields or regions when catching discussions. For example, the discussion catching unit can prioritize catching discussions related to specific legal fields (e.g., labor law, tax law). For example, the discussion catching unit can prioritize catching discussions in specific regions (e.g., the United States, Europe). For example, the discussion catching unit can customize the optimal catching method based on a combination of legal field and region. This enables the discussion catching unit to capture discussions with high accuracy by customizing its catching methods based on specific legal fields and regions. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, when capturing discussions, the discussion catching unit can use AI to customize its catching methods based on specific legal fields or regions.

[0061] The discussion catching unit can select the optimal catching method when catching discussions, taking into account the user's industry characteristics. For example, if the user belongs to the financial industry, the discussion catching unit will prioritize catching financial-related discussions. For example, if the user belongs to the manufacturing industry, the discussion catching unit can prioritize catching manufacturing-related discussions. For example, if the user belongs to the IT industry, the discussion catching unit can prioritize catching IT-related discussions. In this way, the discussion catching unit can efficiently catch highly relevant discussions by selecting a catching method that takes into account the user's industry characteristics. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, when catching discussions, the discussion catching unit can use AI to analyze the user's industry characteristics and select the optimal catching method.

[0062] The discussion catching unit can analyze the user's social media activity and suggest methods for catching discussions when catching them. For example, the discussion catching unit can prioritize catching discussions that the user has shown interest in on social media. For example, the discussion catching unit can catch relevant discussions from the user's social media activity. For example, the discussion catching unit can analyze posts from experts and organizations that the user follows and catch relevant discussions. In this way, the discussion catching unit can efficiently catch relevant discussions by analyzing the user's social media activity. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, when catching discussions, the discussion catching unit can use AI to analyze the user's social media activity and suggest methods for catching discussions.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The data collection unit can analyze past legal amendment information collection history and select the optimal collection method. For example, it can select a method to efficiently obtain information by collecting it during specific time periods based on past collection history. For example, it can analyze past collection history and prioritize information collection from specific websites. For example, it can optimize collection frequency based on past collection history to ensure that all necessary information is collected without omission. In this way, the data collection unit can efficiently collect information by selecting the optimal collection method based on past collection history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can use AI to analyze data in order to analyze past collection history and select the optimal collection method.

[0065] The data collection unit can filter information on legal amendments based on specific legal fields or regions. For example, it can collect only information related to specific legal fields (e.g., labor law, tax law). For example, it can prioritize the collection of legal amendment information for specific regions (e.g., the United States, Europe). For example, it can filter and collect necessary information based on a combination of legal field and region. This allows the data collection unit to efficiently collect necessary information by filtering it based on specific legal fields or regions. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when collecting legal amendment information, the data collection unit can use AI to filter information based on specific legal fields or regions.

[0066] The analysis unit can adjust the level of detail of its analysis based on the importance of the legal amendment information during the analysis. For example, it can perform a detailed analysis on legal amendment information of high importance, and a simplified analysis on legal amendment information of low importance. For example, it can adjust the level of detail of the analysis in stages according to the importance. This allows the analysis unit to perform efficient analysis by adjusting the level of detail of the analysis according to the importance of the legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit can use AI to adjust the level of detail of the analysis based on importance.

[0067] The generation unit can apply different revision generation algorithms depending on the category of the legal amendment information when generating revision proposals. For example, a revision generation algorithm specifically for labor law can be applied to legal amendment information concerning labor law. For example, a revision generation algorithm specifically for tax law can be applied to legal amendment information concerning tax law. For example, a revision generation algorithm specifically for environmental law can be applied to legal amendment information concerning environmental law. This allows the generation unit to generate highly accurate revision proposals by applying a revision generation algorithm according to the category of the legal amendment information. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, when generating revision proposals, the generation unit can use AI to apply different revision generation algorithms depending on the category.

[0068] The selection unit can select the optimal selection method by referring to past selection history when selecting a revised proposal. For example, it can propose the optimal selection method based on the history of previously selected revised proposals. For example, it can prioritize presenting revised proposals based on user preferences from past selection history. For example, it can analyze past selection history and propose the most efficient selection method. As a result, the selection unit can efficiently select revised proposals by selecting the optimal selection method based on past selection history. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised proposal, the selection unit can use AI to refer to past selection history and select the optimal selection method.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The collection unit collects information on legal amendments. The collection unit can, for example, crawl government websites and automatically collect information on legal amendments. The collection unit can, for example, use AI to periodically visit websites and obtain the latest information on legal amendments. The collection unit can, for example, collect information on newly enacted and amended laws. The collection unit can, for example, reduce the risk of oversights and delays in response due to manual information collection. Step 2: The analysis unit analyzes the legal amendment information collected by the collection unit. For example, the analysis unit analyzes the collected legal amendment information and determines what impact it will have on internal regulations. For example, if there is an amendment to the Personal Information Protection Act, the analysis unit can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. Step 3: The generation unit generates revised proposals based on the information analyzed by the analysis unit. The generation unit generates three types of revised proposals, for example: minimal changes, moderate changes, and major revisions. For example, in the minimal change approach, the generation unit proposes only the minimum necessary modifications to the current regulations to comply with the legal amendment. For example, in the moderate change approach, the generation unit makes moderate adjustments to the current regulations in response to the requirements of the legal amendment. For example, in the major revision approach, the generation unit comprehensively reviews the current regulations in response to the legal amendment and introduces the latest business flows and technologies. Step 4: The selection unit selects the revised draft generated by the generation unit. The selection unit allows, for example, a person in charge to select the most suitable revised draft according to their company's circumstances. As a result, the system that automates the rapid acquisition of legal revision information and the updating of internal regulations according to the embodiment can achieve improved operational efficiency and reduced compliance risks.

[0071] (Example of form 2) The solution for automating the rapid acquisition of legal amendment information and the updating of internal regulations according to the embodiment of the present invention is a system that collects, analyzes, generates, and selects legal amendment information. By collecting, analyzing, generating, and selecting legal amendment information, this system improves operational efficiency and reduces compliance risks. For example, this system crawls government websites and automatically collects legal amendment information. For example, the AI ​​periodically visits websites to obtain the latest legal amendment information. For example, it can collect information on newly enacted and amended laws. This reduces the risk of overlooking information or delays in response due to manual information collection. Next, the AI ​​analyzes the collected legal amendment information and the company's internal regulations. For example, the AI ​​analyzes the collected legal amendment information and determines what impact it will have on the internal regulations. For example, if there is an amendment to the Personal Information Protection Act, the AI ​​can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. Subsequently, the AI ​​generates three proposed revisions (minimal change, moderate change, and major revision). For example, the minimal change approach proposes only the minimum necessary modifications to existing regulations in response to legal changes. For example, the moderate change approach makes moderate adjustments to existing regulations in response to legal changes. For example, the major revision approach involves a complete review of existing regulations in response to legal changes, incorporating the latest business flows and technologies. In this way, those in charge can select the optimal revision plan according to their company's situation. Furthermore, this system has multilingual analysis capabilities that can handle global legal regulations, enabling rapid responses to legal changes in each country. For example, it can collect and analyze legal change information in the United States and Europe. This enables global companies to respond to legal changes quickly and accurately. In addition, this system can capture discussions regarding legal changes in government and prepare for future regulation revisions. For example, it can collect the content of discussions regarding legal changes and prepare for future regulation revisions. This enables regulation revisions that are in line with current trends. This mechanism automates the rapid acquisition of legal change information and the updating of internal regulations, resulting in reduced compliance risks and improved operational efficiency.Furthermore, a key feature is the ability to select the most suitable version from multiple revised options, making it an extremely useful solution for corporate legal and general affairs departments that manage regulations. This solution automates the rapid acquisition of legal revision information and the updating of internal regulations, thereby improving operational efficiency and reducing compliance risks.

[0072] The system for automating the rapid acquisition of legal amendment information and the updating of internal regulations according to the embodiment comprises a collection unit, an analysis unit, a generation unit, and a selection unit. The collection unit collects legal amendment information. The collection unit, for example, crawls government websites and automatically collects legal amendment information. The collection unit can, for example, periodically visit websites using AI to obtain the latest legal amendment information. The collection unit can, for example, collect information on newly enacted and amended laws. The collection unit can, for example, reduce the risk of oversights and delays in response due to manual information collection. The analysis unit analyzes the legal amendment information collected by the collection unit. The analysis unit, for example, analyzes the collected legal amendment information and determines what impact it will have on internal regulations. For example, if there is an amendment to the Personal Information Protection Act, the analysis unit can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. The generation unit generates revised drafts based on the information analyzed by the analysis unit. The generation unit generates three revised drafts, for example, minimal changes, moderate changes, and major revisions. The generation unit, for example, in the minimal change approach, proposes only the minimum necessary modifications to the current regulations for the legal amendment. The generation unit, for example, in the moderate change approach, makes moderate adjustments to the current regulations in response to the legal amendment requirements. The generation unit, for example, in the major revision approach, comprehensively reviews the current regulations in response to the legal amendment and introduces the latest business flows and technologies. The selection unit selects the proposed revisions generated by the generation unit. The selection unit allows, for example, a person in charge to select the most suitable proposed revision for their company's situation. As a result, the system that automates the rapid acquisition of legal amendment information and the updating of internal regulations according to the embodiment can achieve improved operational efficiency and reduced compliance risks. Some or all of the above-described processes in the collection unit may be performed using AI, for example, or not. For example, the collection unit can use AI to crawl websites and obtain the latest legal amendment information in order to collect legal amendment information. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or not.For example, the analysis unit can use AI to analyze the collected legal amendment information and determine what impact it will have on internal regulations. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can use AI to generate three revision proposals: minimal changes, moderate changes, and major revisions. Some or all of the above-described processes in the selection unit may be performed using AI or not. For example, the selection unit can use AI to select the optimal revision proposal from the generated proposals.

[0073] The data collection unit collects information on legal amendments. For example, the unit crawls government websites to automatically collect information on legal amendments. Specifically, the unit uses a web crawler to periodically visit the websites of various government agencies and obtain newly published information on legal amendments. The web crawler analyzes the HTML structure of each webpage based on a specified URL list and extracts information related to legal amendments. The data collection unit can also use AI to periodically visit websites and obtain the latest information on legal amendments. The AI ​​uses natural language processing technology to analyze the content of webpages and extract important information regarding legal amendments. For example, the AI ​​automatically extracts information such as the name of the law, the date of amendment, and the content of the amendment, and stores it in a database. The data collection unit can collect information on newly enacted and amended laws. The data collection unit can reduce the risk of oversights and delays in response due to manual information collection. This allows the data collection unit to collect legal amendment information quickly and accurately, providing the information necessary for updating internal regulations. Furthermore, the data collection unit can centrally manage the collected information and collaborate with other systems and departments as needed. For example, collected legal amendment information is stored on a cloud server, making it accessible to the analysis and generation units. Furthermore, the collection unit can flexibly configure the collection frequency and the websites to be collected, enabling rapid responses to specific legal amendment information. This allows the collection unit to efficiently and effectively collect legal amendment information, improving the overall system performance.

[0074] The analysis unit analyzes the legal amendment information collected by the collection unit. For example, the analysis unit analyzes the collected legal amendment information and determines what impact it will have on internal company regulations. Specifically, the analysis unit uses natural language processing technology to analyze the content of the legal amendment information and extract the key points of the amendments. For example, if there is an amendment to the Personal Information Protection Act, the analysis unit can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. The AI ​​analyzes the text of the legal amendment information, extracts the key points of the amendments, and identifies which parts of the internal regulations are affected. For example, the AI ​​extracts keywords related to the amendments, searches for the relevant parts of the internal regulations, and identifies the scope of the impact. For example, the analysis unit evaluates the importance and scope of the amendments and identifies the parts of the internal regulations that need to be updated. This allows the analysis unit to quickly and accurately analyze the collected legal amendment information and provide the information necessary to update internal regulations. Furthermore, the analysis unit can also utilize past legal amendment information and the history of changes to internal regulations to conduct long-term impact assessments and trend analyses. For example, based on past legal amendment data, the analysis unit can analyze the frequency and scope of amendments to specific laws and regulations, and formulate future countermeasures. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the analysis unit to not only grasp the situation in real time, but also to handle long-term risk management and anomaly detection, improving the overall reliability and security of the system.

[0075] The generation unit generates revised drafts based on the information analyzed by the analysis unit. The generation unit generates three types of revised drafts: minimal changes, moderate changes, and major revisions. Specifically, the generation unit automatically generates revised drafts using AI. The minimal change approach proposes only the minimum necessary modifications to the current regulations to comply with the legal amendment. For example, if the legal amendment can be addressed by simply modifying the wording of a specific clause, the minimal change approach is applied. The moderate change approach makes moderate adjustments to the current regulations in response to the legal amendment. For example, if modifications across multiple clauses or the addition of new clauses are required, the moderate change approach is applied. The major revision approach involves a complete review of the current regulations in response to the legal amendment, introducing the latest business flows and technologies. For example, if the legal amendment necessitates a review of the entire business process, the major revision approach is applied. The generation unit automatically generates these revised drafts and provides them to the responsible personnel. This allows the generation unit to provide revised drafts that enable quick and flexible responses to legal amendments, streamlining the updating of internal regulations. Furthermore, the generation unit can continuously improve the accuracy and effectiveness of proposed revisions by utilizing past revision history and business flow data. For example, it can analyze the results of past proposed revisions and optimize the revision generation algorithm. In addition, the generation unit can reduce the burden on personnel and improve operational efficiency by automating the proposal generation process. As a result, the generation unit can support the updating of internal regulations and contribute to reducing compliance risks by providing prompt and accurate proposed revisions.

[0076] The selection unit selects the proposed revisions generated by the generation unit. For example, the selection unit allows a person in charge to select the most suitable revision based on their company's specific circumstances. Specifically, the selection unit displays a list of generated revisions, allowing the person in charge to review the details of each revision. The person in charge compares the content and scope of impact of the revisions and selects the one best suited to their company's situation. The selection unit can, for example, use AI to select the optimal revision. Based on past selection history and workflow data, the AI ​​recommends the most suitable revision to the person in charge. For example, the AI ​​analyzes past revision history and learns selection patterns for similar legal amendments. This allows the AI ​​to recommend the most suitable revision to the person in charge and support the selection process. Furthermore, the selection unit collects the implementation results of the selected revisions as feedback, continuously improving the accuracy of the revision generation and selection algorithms. For example, it analyzes the implementation results of the revisions and evaluates their effectiveness and impact. This allows the selection unit to streamline the revision selection process and reduce the burden on the person in charge. Furthermore, the selection unit can provide tools and resources to support the implementation of the selected revisions. For example, it can automatically generate and provide the necessary documents and procedures for implementing the revisions to the person in charge. In this way, the selection unit can consistently support the process from the selection of revisions to their implementation, streamlining the updating of internal regulations.

[0077] The multilingual analysis unit is equipped with multilingual analysis capabilities. The multilingual analysis unit is equipped with multilingual analysis capabilities that can, for example, respond to global legal regulations. The multilingual analysis unit can, for example, respond quickly to legal changes in various countries. The multilingual analysis unit can, for example, collect and analyze information on legal changes in the United States and Europe. The multilingual analysis unit enables, for example, global companies to respond quickly and accurately to legal changes. This allows the multilingual analysis unit to respond quickly to global legal regulations. Some or all of the above-described processes in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, the multilingual analysis unit can use AI to perform multilingual analysis in order to collect and analyze information on legal changes.

[0078] The discussion catching unit captures discussions in preparation for future revisions of regulations. For example, the discussion catching unit captures discussions toward amendments to laws in administration. For example, the discussion catching unit can collect the content of discussions toward legal amendments and prepare for future revisions of regulations. For example, the discussion catching unit can revise regulations in line with current trends. This enables the discussion catching unit to prepare for future legal amendments. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, the discussion catching unit can use AI to collect the content of discussions in order to capture discussions toward legal amendments.

[0079] The analysis unit can analyze collected legal amendment information and determine what impact it will have on internal regulations. For example, if there is an amendment to the Personal Information Protection Act, the analysis unit can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. This allows the analysis unit to automatically determine the impact of legal amendment information on internal regulations. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use AI to analyze collected legal amendment information and determine what impact it will have on internal regulations.

[0080] The generation unit can generate three types of revision proposals: minimal changes, moderate changes, and major revisions. For example, the generation unit can generate three types of revision proposals: minimal changes, moderate changes, and major revisions. For example, in the minimal change approach, the generation unit proposes only the minimum necessary modifications to the current regulations required for the legal amendment. For example, in the moderate change approach, the generation unit makes moderate adjustments to the current regulations in response to the requirements of the legal amendment. For example, in the major revision approach, the generation unit comprehensively reviews the current regulations in response to the legal amendment and introduces the latest business flows and technologies. This allows the generation unit to select the best one from multiple revision proposals. Some or all of the above processing in the generation unit may be performed using AI, for example, or not. For example, the generation unit can use AI to generate three types of revision proposals: minimal changes, moderate changes, and major revisions in order to generate revision proposals.

[0081] The selection unit can select the best option from the generated revised drafts. For example, the selection unit can select the best option from the generated revised drafts. For example, the selection unit can allow a person in charge to select the best revised draft that suits their company's situation. This streamlines the updating of internal regulations by allowing the selection unit to select the best revised draft. Some or all of the above-described processes in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can use AI to select the best revised draft in order to select from the generated revised drafts.

[0082] The data collection unit can estimate the user's emotions and adjust the timing of collecting legal amendment information based on the estimated user emotions. For example, if the user is stressed, the data collection unit can reduce the collection frequency and collect only important legal amendment information. For example, if the user is relaxed, the data collection unit can increase the collection frequency and collect detailed legal amendment information. For example, if the user is in a hurry, the data collection unit can speed up the collection timing and provide legal amendment information quickly. In this way, the data collection unit can efficiently collect information by adjusting the collection timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can use AI to analyze emotions in order to estimate the user's emotions and adjust the collection timing accordingly.

[0083] The data collection unit can analyze past legal amendment information collection history and select the optimal collection method. For example, the data collection unit can select a method to efficiently obtain information by collecting it during specific time periods based on past collection history. For example, the data collection unit can analyze past collection history and prioritize information collection from specific websites. For example, the data collection unit can optimize collection frequency based on past collection history to ensure that all necessary information is collected without omission. This enables efficient information collection by allowing the data collection unit to select the optimal collection method based on past collection history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can use AI to analyze data in order to analyze past collection history and select the optimal collection method.

[0084] The data collection unit can filter information on legal amendments based on specific legal fields or regions. For example, the data collection unit can collect only information related to specific legal fields (e.g., labor law, tax law). For example, the data collection unit can prioritize the collection of information on legal amendments in specific regions (e.g., the United States, Europe). For example, the data collection unit can filter and collect the necessary information based on a combination of legal field and region. This allows the data collection unit to efficiently collect the necessary information by filtering it based on specific legal fields or regions. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when collecting information on legal amendments, the data collection unit can use AI to filter the information based on specific legal fields or regions.

[0085] The data collection unit can estimate the user's emotions and determine the priority of legal amendment information to collect based on the estimated user emotions. For example, if the user is stressed, the data collection unit will prioritize collecting high-priority legal amendment information. For example, if the user is relaxed, the data collection unit can prioritize collecting detailed legal amendment information. For example, if the user is in a hurry, the data collection unit can prioritize collecting legal amendment information that requires immediate attention. In this way, the data collection unit can prioritize the collection of important information by prioritizing information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can use AI to analyze emotions in order to estimate the user's emotions and determine the priority of legal amendment information to collect.

[0086] The data collection unit can prioritize the collection of highly relevant information when gathering information on legal amendments, taking into account the user's industry characteristics. For example, if the user belongs to the financial industry, the data collection unit will prioritize the collection of financial-related legal amendments. For example, if the user belongs to the manufacturing industry, the data collection unit can prioritize the collection of manufacturing-related legal amendments. For example, if the user belongs to the IT industry, the data collection unit can prioritize the collection of IT-related legal amendments. In this way, the data collection unit can efficiently collect highly relevant information by collecting information while taking into account the user's industry characteristics. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, when collecting information on legal amendments, the data collection unit can use AI to collect information while taking into account the user's industry characteristics.

[0087] The data collection unit can analyze users' social media activity and collect relevant information when collecting information on legal amendments. For example, the data collection unit can prioritize collecting information on legal amendments that users have shown interest in on social media. For example, the data collection unit can collect relevant information on legal amendments from users' social media activity. For example, the data collection unit can analyze posts from experts and organizations that users follow and collect relevant information on legal amendments. This allows the data collection unit to efficiently collect relevant information by analyzing users' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, when collecting information on legal amendments, the data collection unit can use AI to analyze users' social media activity and collect relevant information.

[0088] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit can provide a concise and to-the-point analysis result. For example, if the user is relaxed, the analysis unit can provide a detailed analysis result. For example, if the user is in a hurry, the analysis unit can provide a summarized analysis result that can be quickly understood. In this way, the analysis unit can provide easy-to-understand analysis results by adjusting the presentation of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use AI to analyze emotions and adjust the presentation of the analysis in order to estimate the user's emotions.

[0089] The analysis unit can adjust the level of detail of its analysis based on the importance of the legal amendment information during the analysis. For example, the analysis unit can perform a detailed analysis of legal amendment information of high importance. For example, the analysis unit can perform a concise analysis of legal amendment information of low importance. The analysis unit can adjust the level of detail of its analysis in stages according to the importance of the information. This enables efficient analysis by allowing the analysis unit to adjust the level of detail of its analysis according to the importance of the legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit can use AI to adjust the level of detail of its analysis based on its importance.

[0090] The analysis unit can apply different analysis algorithms depending on the category of the legal amendment information during analysis. For example, the analysis unit can apply a labor law-specific analysis algorithm to legal amendment information related to labor law. For example, the analysis unit can apply a tax law-specific analysis algorithm to legal amendment information related to tax law. For example, the analysis unit can apply an environmental law-specific analysis algorithm to legal amendment information related to environmental law. This allows the analysis unit to perform highly accurate analysis by applying an analysis algorithm according to the category of the legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit can use AI to apply different analysis algorithms depending on the category.

[0091] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit can provide a short, concise analysis result. For example, if the user is relaxed, the analysis unit can provide a detailed analysis result. For example, if the user is in a hurry, the analysis unit can provide a summarized analysis result that can be quickly understood. In this way, the analysis unit can provide an easy-to-understand analysis result by adjusting the length of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use AI to analyze emotions and adjust the length of the analysis in order to estimate the user's emotions.

[0092] The analysis unit can determine the priority of analysis based on the publication date of legal amendment information during the analysis process. For example, the analysis unit may prioritize the analysis of recently published legal amendment information. For example, the analysis unit may postpone the analysis of older legal amendment information. For example, the analysis unit may adjust the priority of analysis in stages according to the publication date. This enables efficient analysis by allowing the analysis unit to determine the priority of analysis based on the publication date of legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit may use AI to determine the priority of analysis based on the publication date.

[0093] The analysis unit can adjust the order of analysis based on the relevance of the legal amendment information during the analysis. For example, the analysis unit may prioritize the analysis of legal amendment information that has a significant impact on internal company regulations. For example, the analysis unit may postpone the analysis of less relevant legal amendment information. For example, the analysis unit may adjust the order of analysis in stages according to relevance. This enables efficient analysis by adjusting the order of analysis based on the relevance of the legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit may use AI to adjust the order of analysis based on relevance.

[0094] The generation unit can estimate the user's emotions and adjust the way the revised draft is presented based on the estimated emotions. For example, if the user is stressed, the generation unit can generate a concise and to-the-point revised draft. For example, if the user is relaxed, the generation unit can generate a detailed revised draft. For example, if the user is in a hurry, the generation unit can generate a summarized revised draft that can be quickly understood. In this way, the generation unit can provide an easy-to-understand revised draft by adjusting the way the revised draft is presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not using AI. For example, the generation unit can use AI to analyze emotions in order to estimate the user's emotions and adjust the way the revised draft is presented.

[0095] The generation unit can adjust the level of detail in the proposed revisions based on the importance of the legal amendment information when generating the revised revisions. For example, the generation unit can generate detailed revised revisions for legal amendment information of high importance. For example, the generation unit can generate concise revised revisions for legal amendment information of low importance. The generation unit can adjust the level of detail in the revised revisions in stages according to the importance. This enables efficient generation of revised revisions by adjusting the level of detail in the revised revisions according to the importance of the legal amendment information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, when generating revised revisions, the generation unit can use AI to adjust the level of detail in the revised revisions based on their importance.

[0096] The generation unit can apply different revision generation algorithms depending on the category of the legal amendment information when generating revision proposals. For example, the generation unit can apply a revision generation algorithm specifically for labor law to legal amendment information concerning labor law. For example, the generation unit can apply a revision generation algorithm specifically for tax law to legal amendment information concerning tax law. For example, the generation unit can apply a revision generation algorithm specifically for environmental law to legal amendment information concerning environmental law. This enables the generation unit to generate highly accurate revision proposals by applying a revision generation algorithm according to the category of the legal amendment information. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, when generating revision proposals, the generation unit can use AI to apply different revision generation algorithms depending on the category.

[0097] The generation unit can estimate the user's emotions and adjust the length of the revised draft based on the estimated emotions. For example, if the user is stressed, the generation unit can generate a short, concise revised draft. For example, if the user is relaxed, the generation unit can generate a detailed revised draft. For example, if the user is in a hurry, the generation unit can generate a summarized revised draft that can be quickly understood. In this way, the generation unit can provide an easy-to-understand revised draft by adjusting its length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not using AI. For example, the generation unit can use AI to analyze emotions in order to estimate the user's emotions and adjust the length of the revised draft.

[0098] The generation unit can determine the priority of proposed revisions based on the timing of announcements of legal amendment information when generating revised drafts. For example, the generation unit can prioritize the inclusion of recently announced legal amendment information in the revised drafts. For example, the generation unit can postpone the generation of revised drafts for older legal amendment information. For example, the generation unit can adjust the priority of revised drafts in stages according to the timing of announcements. This enables efficient generation of revised drafts by determining the priority of revised drafts based on the timing of announcements of legal amendment information. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, when generating revised drafts, the generation unit can use AI to determine the priority of revised drafts based on the timing of announcements.

[0099] The generation unit can adjust the order of the revised drafts based on the relevance of the legal amendment information when generating the revised drafts. For example, the generation unit will prioritize reflecting legal amendment information that has a significant impact on internal regulations in the revised drafts. For example, the generation unit can postpone the generation of revised drafts for legal amendment information that is less relevant. For example, the generation unit can adjust the order of the revised drafts in stages according to their relevance. This enables efficient generation of revised drafts by adjusting the order of the revised drafts based on the relevance of the legal amendment information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, when generating revised drafts, the generation unit can use AI to adjust the order of the revised drafts based on their relevance.

[0100] The selection unit can estimate the user's emotions and adjust its selection method for revised versions based on the estimated emotions. For example, if the user is stressed, the selection unit may prioritize presenting concise and to-the-point revised versions. If the user is relaxed, for example, the selection unit may present detailed revised versions. If the user is in a hurry, for example, the selection unit may present summarized revised versions that can be quickly understood. In this way, the selection unit can select the optimal revised version by adjusting its selection method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI, for example, or not using AI. For example, the selection unit may use AI to analyze emotions in order to estimate the user's emotions and adjust its selection method for revised versions.

[0101] The selection unit can select the optimal selection method by referring to past selection history when selecting a revised proposal. For example, the selection unit can propose the optimal selection method based on the history of previously selected revised proposals. For example, the selection unit can prioritize presenting revised proposals based on user preferences from past selection history. For example, the selection unit can analyze past selection history and propose the most efficient selection method. As a result, the selection unit can efficiently select revised proposals by selecting the optimal selection method based on past selection history. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised proposal, the selection unit can use AI to refer to past selection history and select the optimal selection method.

[0102] The selection unit can customize the selection method based on the user's work situation when selecting a revised proposal. For example, if the user is busy, the selection unit will prioritize presenting a concise and to-the-point revised proposal. For example, if the user has ample time, the selection unit can present a detailed revised proposal. For example, the selection unit can customize the selection method according to the user's work situation and present the optimal revised proposal. In this way, the selection unit can select the optimal revised proposal by customizing the selection method according to the user's work situation. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised proposal, the selection unit can use AI to analyze the user's work situation and customize the selection method.

[0103] The selection unit can estimate the user's emotions and determine the priority of proposed revisions based on the estimated emotions. For example, if the user is stressed, the selection unit will prioritize presenting high-priority proposed revisions. For example, if the user is relaxed, the selection unit may prioritize presenting detailed proposed revisions. For example, if the user is in a hurry, the selection unit may prioritize presenting proposed revisions that require immediate attention. In this way, the selection unit can prioritize important proposed revisions by determining the priority of revisions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI, for example, or not using AI. For example, when selecting proposed revisions, the selection unit may use AI to analyze the user's emotions and determine the priority of the proposed revisions.

[0104] The selection unit can choose the optimal selection method when selecting a revised proposal, taking into account the user's industry characteristics. For example, if the user belongs to the financial industry, the selection unit can prioritize presenting financial-related revised proposals. For example, if the user belongs to the manufacturing industry, the selection unit can prioritize presenting manufacturing-related revised proposals. For example, if the user belongs to the IT industry, the selection unit can prioritize presenting IT-related revised proposals. In this way, the selection unit can select a highly relevant revised proposal by choosing a selection method that takes into account the user's industry characteristics. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised proposal, the selection unit can use AI to analyze the user's industry characteristics and select the optimal selection method.

[0105] The selection unit can analyze the user's social media activity and suggest methods for selection when selecting a revised version. For example, the selection unit can prioritize presenting revised versions that the user has shown interest in on social media. For example, the selection unit can present relevant revised versions based on the user's social media activity. For example, the selection unit can analyze posts from experts and organizations that the user follows and present relevant revised versions. In this way, the selection unit can efficiently select relevant revised versions by analyzing the user's social media activity. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised version, the selection unit can use AI to analyze the user's social media activity and suggest methods for selection.

[0106] The multilingual analysis unit can estimate the user's emotions and adjust the multilingual analysis method based on the estimated user emotions. For example, if the user is stressed, the multilingual analysis unit can provide a concise and to-the-point multilingual analysis result. For example, if the user is relaxed, the multilingual analysis unit can provide a detailed multilingual analysis result. For example, if the user is in a hurry, the multilingual analysis unit can provide a summarized multilingual analysis result that can be quickly understood. In this way, the multilingual analysis unit can provide easy-to-understand analysis results by adjusting the multilingual analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, the multilingual analysis unit can use AI to analyze emotions and adjust the multilingual analysis method in order to estimate the user's emotions.

[0107] The multilingual analysis unit can optimize its analysis algorithm by referring to past analysis data during multilingual analysis. For example, the multilingual analysis unit can select the optimal analysis algorithm based on past analysis data. For example, the multilingual analysis unit can analyze past analysis data and apply an algorithm to improve analysis accuracy. For example, the multilingual analysis unit can refer to past analysis data and apply an algorithm to improve analysis efficiency. As a result, the multilingual analysis unit improves analysis accuracy by optimizing its analysis algorithm based on past analysis data. Some or all of the above processes in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, when the multilingual analysis unit refers to past analysis data, it can use AI to analyze the data and select the optimal analysis algorithm.

[0108] The multilingual analysis unit can customize its analysis methods based on specific languages ​​and regions during multilingual analysis. For example, the multilingual analysis unit can apply analysis methods corresponding to specific languages ​​(e.g., English, French). For example, the multilingual analysis unit can apply analysis methods corresponding to legal amendment information in specific regions (e.g., America, Europe). For example, the multilingual analysis unit can customize the optimal analysis method based on a combination of language and region. This enables the multilingual analysis unit to perform highly accurate analysis by customizing its analysis methods based on specific languages ​​and regions. Some or all of the above-described processes in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the multilingual analysis unit can use AI to customize its analysis methods based on specific languages ​​and regions.

[0109] The multilingual analysis unit can estimate the user's emotions and determine the priority of multilingual analysis based on the estimated user emotions. For example, if the user is stressed, the multilingual analysis unit can prioritize providing high-priority multilingual analysis results. For example, if the user is relaxed, the multilingual analysis unit can prioritize providing detailed multilingual analysis results. For example, if the user is in a hurry, the multilingual analysis unit can prioritize providing multilingual analysis results that require immediate attention. In this way, the multilingual analysis unit can prioritize providing important analysis results by determining the priority of multilingual analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, the multilingual analysis unit can use AI to analyze emotions and determine the priority of multilingual analysis in order to estimate the user's emotions.

[0110] The multilingual analysis unit can select the optimal analysis method by considering the user's industry characteristics during multilingual analysis. For example, if the user belongs to the financial industry, the multilingual analysis unit can apply a financial-related multilingual analysis method. For example, if the user belongs to the manufacturing industry, the multilingual analysis unit can apply a manufacturing-related multilingual analysis method. For example, if the user belongs to the IT industry, the multilingual analysis unit can apply an IT-related multilingual analysis method. In this way, the multilingual analysis unit can provide highly relevant analysis results by selecting an analysis method that considers the user's industry characteristics. Some or all of the above processing in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the multilingual analysis unit can use AI to analyze the user's industry characteristics and select the optimal analysis method.

[0111] The multilingual analysis unit can analyze the user's social media activity and propose analysis methods during multilingual analysis. For example, the multilingual analysis unit can prioritize providing multilingual analysis results that the user has shown interest in on social media. For example, the multilingual analysis unit can provide relevant multilingual analysis results from the user's social media activity. For example, the multilingual analysis unit can analyze posts from experts and organizations that the user follows and provide relevant multilingual analysis results. In this way, the multilingual analysis unit can efficiently provide relevant analysis results by analyzing the user's social media activity. Some or all of the above processing in the multilingual analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the multilingual analysis unit can use AI to analyze the user's social media activity and propose analysis methods.

[0112] The discussion catching unit can estimate the user's emotions and adjust its discussion catching method based on the estimated emotions. For example, if the user is stressed, the discussion catching unit will only catch important discussions. For example, if the user is relaxed, the discussion catching unit can catch detailed discussions. For example, if the user is in a hurry, the discussion catching unit can catch discussions that require a quick response. In this way, the discussion catching unit can efficiently catch important discussions by adjusting its discussion catching method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, the discussion catching unit can use AI to analyze emotions in order to estimate the user's emotions and adjust its discussion catching method accordingly.

[0113] The discussion catching unit can optimize its catching algorithm by referring to past discussion data when catching a discussion. For example, the discussion catching unit can select the optimal catching algorithm based on past discussion data. For example, the discussion catching unit can analyze past discussion data and apply an algorithm to improve catching accuracy. For example, the discussion catching unit can refer to past discussion data and apply an algorithm to improve catching efficiency. As a result, the discussion catching unit improves catching accuracy by optimizing its catching algorithm based on past discussion data. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without using AI. For example, when the discussion catching unit refers to past discussion data, it can use AI to analyze the data and select the optimal catching algorithm.

[0114] The discussion catching unit can customize its catching methods based on specific legal fields or regions when catching discussions. For example, the discussion catching unit can prioritize catching discussions related to specific legal fields (e.g., labor law, tax law). For example, the discussion catching unit can prioritize catching discussions in specific regions (e.g., the United States, Europe). For example, the discussion catching unit can customize the optimal catching method based on a combination of legal field and region. This enables the discussion catching unit to capture discussions with high accuracy by customizing its catching methods based on specific legal fields and regions. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, when capturing discussions, the discussion catching unit can use AI to customize its catching methods based on specific legal fields or regions.

[0115] The discussion catching unit can estimate the user's emotions and determine the priority of discussions to catch based on the estimated emotions. For example, if the user is stressed, the discussion catching unit will prioritize catching discussions of high importance. For example, if the user is relaxed, the discussion catching unit can prioritize catching detailed discussions. For example, if the user is in a hurry, the discussion catching unit can prioritize catching discussions that require a quick response. In this way, the discussion catching unit can prioritize catching important discussions by determining the priority of discussions to catch according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, when catching discussions, the discussion catching unit can use AI to analyze the user's emotions and determine the priority of discussions to catch.

[0116] The discussion catching unit can select the optimal catching method when catching discussions, taking into account the user's industry characteristics. For example, if the user belongs to the financial industry, the discussion catching unit will prioritize catching financial-related discussions. For example, if the user belongs to the manufacturing industry, the discussion catching unit can prioritize catching manufacturing-related discussions. For example, if the user belongs to the IT industry, the discussion catching unit can prioritize catching IT-related discussions. In this way, the discussion catching unit can efficiently catch highly relevant discussions by selecting a catching method that takes into account the user's industry characteristics. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, when catching discussions, the discussion catching unit can use AI to analyze the user's industry characteristics and select the optimal catching method.

[0117] The discussion catching unit can analyze the user's social media activity and suggest methods for catching discussions when catching them. For example, the discussion catching unit can prioritize catching discussions that the user has shown interest in on social media. For example, the discussion catching unit can catch relevant discussions from the user's social media activity. For example, the discussion catching unit can analyze posts from experts and organizations that the user follows and catch relevant discussions. In this way, the discussion catching unit can efficiently catch relevant discussions by analyzing the user's social media activity. Some or all of the above processing in the discussion catching unit may be performed using AI, for example, or without AI. For example, when catching discussions, the discussion catching unit can use AI to analyze the user's social media activity and suggest methods for catching discussions.

[0118] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0119] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is stressed, it can prioritize the analysis of high-priority legal amendment information. For example, if the user is relaxed, it can perform a detailed analysis. For example, if the user is in a hurry, it can prioritize the analysis of legal amendment information that requires immediate attention. In this way, the analysis unit can perform efficient analysis by determining the priority of analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can use AI to analyze emotions in order to estimate the user's emotions and determine the priority of analysis.

[0120] The generation unit can estimate the user's emotions and adjust the method of generating the revised draft based on the estimated emotions. For example, if the user is stressed, it can generate a concise and to-the-point revised draft. For example, if the user is relaxed, it can generate a detailed revised draft. For example, if the user is in a hurry, it can generate a summarized revised draft that can be quickly understood. In this way, the generation unit can provide easily understandable revised drafts by adjusting the method of generating the revised draft according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can use AI to analyze emotions in order to estimate the user's emotions and adjust the method of generating the revised draft.

[0121] The selection unit can estimate the user's emotions and adjust its method of selecting revisions based on the estimated emotions. For example, if the user is stressed, it can prioritize presenting concise and to-the-point revisions. For example, if the user is relaxed, it can present detailed revisions. For example, if the user is in a hurry, it can present summarized revisions that can be quickly understood. In this way, the selection unit can select the optimal revision by adjusting its method of selecting revisions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI, for example, or not using AI. For example, the selection unit can use AI to analyze emotions in order to estimate the user's emotions and adjust its method of selecting revisions.

[0122] The data collection unit can estimate the user's emotions and adjust the timing of collecting legal amendment information based on the estimated emotions. For example, if the user is stressed, the collection frequency can be reduced, and only important legal amendment information can be collected. For example, if the user is relaxed, the collection frequency can be increased, and detailed legal amendment information can be collected. For example, if the user is in a hurry, the collection timing can be accelerated, and legal amendment information can be provided quickly. In this way, the data collection unit can efficiently collect information by adjusting the collection timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can use AI to analyze emotions in order to estimate the user's emotions and adjust the collection timing.

[0123] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is stressed, it can provide a concise and to-the-point analysis result. For example, if the user is relaxed, it can provide a detailed analysis result. For example, if the user is in a hurry, it can provide a summarized analysis result that can be quickly understood. In this way, the analysis unit can provide easy-to-understand analysis results by adjusting the presentation of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use AI to analyze emotions and adjust the presentation of the analysis in order to estimate the user's emotions.

[0124] The data collection unit can analyze past legal amendment information collection history and select the optimal collection method. For example, it can select a method to efficiently obtain information by collecting it during specific time periods based on past collection history. For example, it can analyze past collection history and prioritize information collection from specific websites. For example, it can optimize collection frequency based on past collection history to ensure that all necessary information is collected without omission. In this way, the data collection unit can efficiently collect information by selecting the optimal collection method based on past collection history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can use AI to analyze data in order to analyze past collection history and select the optimal collection method.

[0125] The data collection unit can filter information on legal amendments based on specific legal fields or regions. For example, it can collect only information related to specific legal fields (e.g., labor law, tax law). For example, it can prioritize the collection of legal amendment information for specific regions (e.g., the United States, Europe). For example, it can filter and collect necessary information based on a combination of legal field and region. This allows the data collection unit to efficiently collect necessary information by filtering it based on specific legal fields or regions. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when collecting legal amendment information, the data collection unit can use AI to filter information based on specific legal fields or regions.

[0126] The analysis unit can adjust the level of detail of its analysis based on the importance of the legal amendment information during the analysis. For example, it can perform a detailed analysis on legal amendment information of high importance, and a simplified analysis on legal amendment information of low importance. For example, it can adjust the level of detail of the analysis in stages according to the importance. This allows the analysis unit to perform efficient analysis by adjusting the level of detail of the analysis according to the importance of the legal amendment information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, when analyzing legal amendment information, the analysis unit can use AI to adjust the level of detail of the analysis based on importance.

[0127] The generation unit can apply different revision generation algorithms depending on the category of the legal amendment information when generating revision proposals. For example, a revision generation algorithm specifically for labor law can be applied to legal amendment information concerning labor law. For example, a revision generation algorithm specifically for tax law can be applied to legal amendment information concerning tax law. For example, a revision generation algorithm specifically for environmental law can be applied to legal amendment information concerning environmental law. This allows the generation unit to generate highly accurate revision proposals by applying a revision generation algorithm according to the category of the legal amendment information. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, when generating revision proposals, the generation unit can use AI to apply different revision generation algorithms depending on the category.

[0128] The selection unit can select the optimal selection method by referring to past selection history when selecting a revised proposal. For example, it can propose the optimal selection method based on the history of previously selected revised proposals. For example, it can prioritize presenting revised proposals based on user preferences from past selection history. For example, it can analyze past selection history and propose the most efficient selection method. As a result, the selection unit can efficiently select revised proposals by selecting the optimal selection method based on past selection history. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, when selecting a revised proposal, the selection unit can use AI to refer to past selection history and select the optimal selection method.

[0129] The following briefly describes the processing flow for example form 2.

[0130] Step 1: The collection unit collects information on legal amendments. The collection unit can, for example, crawl government websites and automatically collect information on legal amendments. The collection unit can, for example, use AI to periodically visit websites and obtain the latest information on legal amendments. The collection unit can, for example, collect information on newly enacted and amended laws. The collection unit can, for example, reduce the risk of oversights and delays in response due to manual information collection. Step 2: The analysis unit analyzes the legal amendment information collected by the collection unit. For example, the analysis unit analyzes the collected legal amendment information and determines what impact it will have on internal regulations. For example, if there is an amendment to the Personal Information Protection Act, the analysis unit can analyze the content of the amendment and determine what changes are necessary to the company's personal information protection regulations. Step 3: The generation unit generates revised proposals based on the information analyzed by the analysis unit. The generation unit generates three types of revised proposals, for example: minimal changes, moderate changes, and major revisions. For example, in the minimal change approach, the generation unit proposes only the minimum necessary modifications to the current regulations to comply with the legal amendment. For example, in the moderate change approach, the generation unit makes moderate adjustments to the current regulations in response to the requirements of the legal amendment. For example, in the major revision approach, the generation unit comprehensively reviews the current regulations in response to the legal amendment and introduces the latest business flows and technologies. Step 4: The selection unit selects the revised draft generated by the generation unit. The selection unit allows, for example, a person in charge to select the most suitable revised draft according to their company's circumstances. As a result, the system that automates the rapid acquisition of legal revision information and the updating of internal regulations according to the embodiment can achieve improved operational efficiency and reduced compliance risks.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, selection unit, multilingual analysis unit, argument capture unit, and sentiment estimation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and automatically collects legal amendment information by crawling government websites. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected legal amendment information to determine what impact it will have on company regulations. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates three proposed revisions: minimal change, moderate change, and major revision. The selection unit is implemented by the control unit 46A of the smart device 14 and selects one of the generated proposed revisions. The multilingual analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and collects and analyzes legal amendment information from various countries. The discussion capture unit is implemented, for example, by the control unit 46A of the smart device 14, and collects the content of discussions toward legal revision. The emotion estimation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the collection timing. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0135] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, selection unit, multilingual analysis unit, argument capture unit, and sentiment estimation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and automatically collects legal amendment information by crawling government websites. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected legal amendment information to determine what impact it will have on company regulations. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates three proposed revisions: minimal change, moderate change, and major revision. The selection unit is implemented by the control unit 46A of the smart glasses 214 and selects one of the generated proposed revisions. The multilingual analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and collects and analyzes legal amendment information from various countries. The discussion capture unit is implemented, for example, by the control unit 46A of the smart glasses 214, and collects the content of discussions toward legal revision. The emotion estimation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the collection timing. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0151] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, selection unit, multilingual analysis unit, argument capture unit, and sentiment estimation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and automatically collects legal amendment information by crawling government websites. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected legal amendment information to determine what impact it will have on company regulations. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates three proposed revisions: minimal change, moderate change, and major revision. The selection unit is implemented by the control unit 46A of the headset terminal 314 and selects one of the generated proposed revisions. The multilingual analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and collects and analyzes legal amendment information from various countries. The discussion capture unit is implemented, for example, by the control unit 46A of the headset terminal 314, and collects the content of discussions toward legal revision. The emotion estimation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and estimates the user's emotions and adjusts the collection timing. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0167] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0168] 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.

[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 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.

[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 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).

[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] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.).

[0180] 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.

[0181] 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.

[0182] 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.

[0183] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, selection unit, multilingual analysis unit, argument capture unit, and sentiment estimation unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and automatically collects legal amendment information by crawling government websites. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the collected legal amendment information to determine what impact it will have on company regulations. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates three proposed revisions: minimal change, moderate change, and major revision. The selection unit is implemented by, for example, the control unit 46A of the robot 414 and selects one of the generated proposed revisions. The multilingual analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and collects and analyzes legal amendment information from various countries. The discussion catching unit is implemented, for example, by the control unit 46A of the robot 414, and collects the content of discussions toward legal revision. The emotion estimation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and estimates the user's emotions and adjusts the collection timing. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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."

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] (Note 1) A collection department that collects information on legal amendments, An analysis unit analyzes the legal amendment information collected by the aforementioned collection unit, A generation unit generates a revised proposal based on the information analyzed by the aforementioned analysis unit, The system includes a selection unit that selects the revised draft generated by the generation unit. A system characterized by the following features. (Note 2) It is further equipped with a multilingual analysis unit that has multilingual analysis capabilities. The system described in Appendix 1, characterized by the features described herein. (Note 3) Further additions include a discussion-catching section to capture discussions in preparation for future revisions of regulations. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit, We analyze the collected information on legal changes and determine what impact they will have on internal company regulations. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generate three proposed revisions: minimal changes, moderate changes, and major revisions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned selection unit is Select the best option from the generated revised proposals. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate user sentiment and adjust the timing of collecting information on legal changes based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is We will analyze the history of collecting information on past legal amendments and select the most suitable collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting information on legal amendments, filter it based on specific legal fields or regions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is We estimate user sentiment and determine the priority of legal change information to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting information on legal revisions, we prioritize collecting highly relevant information, taking into account the user's industry characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting information on legal changes, we analyze users' social media activity and collect relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, the level of detail of the analysis is adjusted based on the importance of the legal amendment information. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of legal amendment information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During the analysis, the priority of the analysis is determined based on the timing of the announcement of legal amendment information. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the legal amendment information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is We estimate user sentiment and adjust the wording of the revised proposal based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating the revised draft, the level of detail in the draft is adjusted based on the importance of the legal amendment information. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating revised drafts, different revision generation algorithms are applied depending on the category of legal amendment information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is The system estimates user sentiment and adjusts the length of the revised proposal based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is When generating revised proposals, the priority of the proposed revisions is determined based on the timing of the announcement of information regarding the legal amendments. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating the revised draft, the order of the revised draft is adjusted based on the relevance of the legal amendment information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned selection unit is We estimate user sentiment and adjust the selection process for revised proposals based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned selection unit is When selecting a revised proposal, the system will refer to past selection history to determine the most suitable selection method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned selection unit is When selecting a revised version, customize the selection method based on the user's work situation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned selection unit is The system estimates user sentiment and prioritizes proposed revisions based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned selection unit is When selecting a revised proposal, the optimal selection method will be chosen considering the user's industry characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned selection unit is When selecting a revised proposal, we analyze users' social media activity to suggest methods for making that choice. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned multilingual analysis unit, The system estimates the user's emotions and adjusts the multilingual analysis method based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned multilingual analysis unit, During multilingual analysis, the analysis algorithm is optimized by referring to past analysis data. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned multilingual analysis unit, When performing multilingual analysis, customize the analysis methods based on specific languages ​​or regions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned multilingual analysis unit, It estimates the user's emotions and determines the priority of multilingual analysis based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned multilingual analysis unit, When performing multilingual analysis, the optimal analysis method is selected considering the user's industry characteristics. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned multilingual analysis unit, During multilingual analysis, we analyze users' social media activity and propose analysis methods. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned discussion catch section is, It estimates the user's emotions and adjusts the discussion-catching method based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned discussion catch section is, When capturing a discussion, the capture algorithm is optimized by referring to past discussion data. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned discussion catch section is, When catching a discussion, customize the means of catching based on specific legal fields or regions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned discussion catch section is, It estimates the user's emotions and determines the priority of discussion catches based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned discussion catch section is, When capturing discussion points, select the optimal capture method considering the user's industry characteristics. The system described in Appendix 3, characterized by the features described herein. (Note 42) The aforementioned discussion catch section is, When capturing discussions, we analyze users' social media activity and suggest methods for capturing them. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0203] 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 collection department that collects information on legal amendments, An analysis unit analyzes the legal amendment information collected by the aforementioned collection unit, A generation unit generates a revised proposal based on the information analyzed by the aforementioned analysis unit, The system includes a selection unit that selects the revised draft generated by the generation unit. A system characterized by the following features.

2. It is further equipped with a multilingual analysis unit that has multilingual analysis capabilities. The system according to feature 1.

3. Further additions include a discussion-catching section to capture discussions in preparation for future revisions of regulations. The system according to feature 1.

4. The aforementioned analysis unit, We analyze the collected information on legal changes and determine what impact they will have on internal company regulations. The system according to feature 1.

5. The generating unit is Generate three proposed revisions: minimal changes, moderate changes, and major revisions. The system according to feature 1.

6. The aforementioned selection unit is Select the best option from the generated revised proposals. The system according to feature 1.

7. The aforementioned collection unit is We estimate user sentiment and adjust the timing of collecting information on legal changes based on the estimated user sentiment. The system according to feature 1.

8. The aforementioned collection unit is We will analyze the history of collecting information on past legal amendments and select the most suitable collection method. The system according to feature 1.

9. The aforementioned collection unit is When collecting information on legal amendments, filter it based on specific legal fields or regions. The system according to feature 1.

Images