System

Abstract

A system is provided.SOLUTION: A system comprising: means for connecting to a law database and acquiring new law revision information; means for analyzing and extracting the acquired law revision information; means for automatically generating a rule draft based on the revision information extracted by a generation AI; means for comparing the generated new draft with a current rule and clarifying a changed portion; means for transmitting the new draft to concerned parties and collecting feedback; means for correcting the draft based on the feedback and disclosing the corrected draft in a company after approval; and means for storing and managing the new rule and its revision history in a database.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Corporate regulation management encompasses a wide range of tasks, and requires rapid response, particularly when legal revisions occur. However, the current manual revision process requires a great deal of time and effort, and is prone to human errors such as typos and failure to check for legal compliance. Efficiency in the exchange of feedback between stakeholders is also an issue. Furthermore, managing and tracking revision history is complicated, making it time-consuming to review past revisions. An efficient system is needed to comprehensively resolve these issues. [Means for solving the problem]

[0005] The present invention provides a system that includes: a means for connecting to a legal database and acquiring new legal revision information; a means for analyzing and extracting the acquired legal revision information; a means for automatically generating draft regulations based on the revision information extracted by a generation AI; a means for comparing the generated new draft regulations with current regulations and indicating changes; a means for sending the new draft regulations to relevant parties and collecting feedback; a means for revising the draft regulations based on the feedback and publishing them internally after approval; and a means for storing and managing new regulations and their revision history in a database. This system enables the rapid collection of legal revision information and the automatic generation of draft regulations, while also efficiently collecting and incorporating feedback from relevant parties. Furthermore, management of past revision history is automated, allowing for easy tracking and confirmation at any time. This improves the efficiency and accuracy of regulations management.

[0006] A "legal database" is an electronic database that stores laws, regulations, revision information, etc. and allows searches and information retrieval.

[0007] "Amendment Information" refers to the changes and amendments made to existing laws and regulations.

[0008] "Generative AI" is a system that uses artificial intelligence technology to automatically perform specific tasks, and in this invention is used to draft regulations.

[0009] A "draft regulation" is a document showing a draft of a company's regulations or rules, and includes new content that reflects revised information.

[0010] "Feedback" refers to input information such as opinions, comments, and suggested corrections from stakeholders.

[0011] "Revision history" refers to information that shows past changes to regulations and rules, allowing you to track what changes were made and when.

[0012] A "database" is a system that enables efficient management, retrieval, and updating of electronically stored information.

[0013] The "management screen" is an interface that allows users to operate the system and perform management tasks such as entering, checking, and correcting information. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, automatically creates draft regulations based on the amendment information using a generative AI, collects feedback from stakeholders, finalizes the draft, and automates the process of publishing it internally.

[0036] Specifically, the system is configured and operated as follows:

[0037] Legal information gathering

[0038] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it obtains information on revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's official website.

[0039] Draft generation

[0040] The server passes the acquired revision information to the generation AI, which then uses that information to generate a new draft of the regulations. For example, it generates a new draft of the "Working Hours Regulations" that takes into account the revisions to the Labor Standards Act.

[0041] Comparison and Review

[0042] The server compares the new draft text created by the generative AI with the current regulations and uses text comparison tools to highlight the changes, making the changes visible at a glance and improving review efficiency.

[0043] Collecting feedback

[0044] The server emails the new draft to stakeholders, who then receive the emails on their own devices, review them, and provide feedback, which is collected through web forms and reply emails.

[0045] Approval and publication

[0046] The user checks the feedback, makes any necessary corrections, and finally approves the policy. The server then publishes the final version of the policy on the company intranet and notifies all employees.

[0047] History Management

[0048] The server stores the new regulations and their revision history in a database and manages them so that they can be accessed at any time. This makes it easy to track and check past revisions and their history.

[0049] Specific examples

[0050] Example 1

[0051] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day. The acquired data is in JSON format, which the server parses and passes to the generation AI the content to be created. The generation AI creates a draft of the "Working Hours Regulations" incorporating the revised parts, compares it with the current version, and highlights the changes in red.

[0052] Example 2

[0053] After a new draft is created, the server retrieves the email list of the HR department and sends an email with the draft attached. HR personnel receive the email on their own devices, review it, and provide feedback through a web form. The HR manager reviews the feedback, makes any necessary corrections, and approves the final draft.

[0054] Once the final draft is approved, the server publishes the policy on the company intranet and notifies all employees. The new policy and revision history are all stored in a database, so users can check past revisions at any time.

[0055] This invention comprehensively realizes the rapid collection of legal information, automatic generation of draft texts, efficient communication with stakeholders, and management of revision history, thereby significantly improving the efficiency of corporate regulation management and contributing to strengthening compliance with laws and regulations and internal control.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server uses the Ministry of Health, Labor and Welfare's API to obtain revision information for the Labor Standards Act in JSON format.

[0059] Step 2:

[0060] The server analyzes the legal amendment information it has acquired and extracts the necessary amendments. Text mining technology is used for the analysis to extract the main points of the legal amendments.

[0061] Step 3:

[0062] The server sends the extracted revision information to the generation AI, which then automatically creates a new draft regulation based on the revision information. At this time, the generation AI generates a draft regulation that conforms to the company's existing regulation format.

[0063] Step 4:

[0064] The server compares the new draft text with the current version using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[0065] Step 5:

[0066] The server emails the new draft to interested parties, including an attachment of the draft and a review link that they can click to access a web form to provide their feedback.

[0067] Step 6:

[0068] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[0069] Step 7:

[0070] The server collects and aggregates feedback from stakeholders, automatically sorts it, and lists the necessary changes.

[0071] Step 8:

[0072] The user reviews the feedback and makes any necessary corrections. The user then makes a final check of the revised draft and decides whether to approve it.

[0073] Step 9:

[0074] The server publishes the final approved version of the regulations on the company intranet, which is then immediately notified to all employees.

[0075] Step 10:

[0076] The server stores the new regulations and their revision history in a database, which is recorded in detail and managed so that it can be accessed at any time.

[0077] Specific examples

[0078] Step 1 example

[0079] The server obtains information on revisions to the Labor Standards Act through the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format.

[0080] Step 2: Example

[0081] The server uses text mining technology to analyze the revised parts of the JSON data it receives and extracts the revised contents of the Labor Standards Act.

[0082] Step 3 example

[0083] The server sends the extracted revision information to the generation AI, which then generates a draft of the new "Work Hours Regulations." The draft text conforms to the company's existing format.

[0084] Step 4: Example

[0085] The server compares the new draft with the current version using a text comparison tool and highlights the revised parts in red.

[0086] Step 5: Example

[0087] The server sends an email to the HR representative with the new draft attached and a link for review.

[0088] Step 6: Example

[0089] The HR staff receives the email on the device, reviews the new draft text, and submits feedback via a web form.

[0090] Step 7 Example

[0091] The server collects all the feedback and organizes a list of necessary fixes.

[0092] Step 8 Example

[0093] The user then revises the draft based on the feedback, and then gives final approval.

[0094] Step 9 Example

[0095] The server publishes the approved regulations on the company intranet and notifies all employees by email.

[0096] Step 10: Example

[0097] The server stores new regulations and their revision history in a detailed database, allowing users to access past changes.

[0098] Example 1

[0099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] Corporate regulation management requires a great deal of time and effort to deal with legal revisions and update internal regulations. The process of collecting information on legal revisions, drafting regulations, gathering feedback from stakeholders, and finally approving and publishing the final draft is particularly complex and requires efficient and accurate execution. However, current manual processes and partial automation make it difficult to fully meet the demands for regulatory compliance and strengthened internal controls. This leaves companies exposed to reduced operational efficiency and the risk of legal violations.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0102] In this invention, the server includes: means for connecting to a legal database and acquiring new legal revision information; means for analyzing and extracting the acquired legal revision information; means for automatically generating draft regulations based on the revision information extracted by the generative AI model; means for comparing the generated new draft regulations with existing regulations and indicating changes; means for automatically periodically collecting legal revision information from the Internet; means for storing the collected legal revision information in JSON format; means for comparing the new draft regulations with existing regulations using a text comparison tool; means for visualizing the comparison results and generating a document indicating changes; means for sending the new draft regulations to relevant parties and collecting feedback; means for revising the draft regulations based on the feedback and publishing them internally after approval; means for saving and managing the new regulations and their revision history in a database; and means for publishing approved regulations on the company's intranet and notifying all employees. This significantly streamlines the entire corporate regulations management process, enabling enhanced compliance with laws and regulations and internal control.

[0103] A "legal database" is a database that stores laws, regulations, and amendments that can be accessed and searched as needed.

[0104] "Revision Information" means information that describes changes or updates to current laws and regulations.

[0105] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to automatically generate new documents based on provided information.

[0106] A "draft rule" is a document that documents the rules and policies that apply within a company and is used as a draft.

[0107] A "text comparison tool" is software that compares two documents and automatically identifies and highlights differences and changes.

[0108] "Feedback" refers to information including opinions, requests for amendments, and suggestions from stakeholders regarding the new draft regulations.

[0109] The "Internet" is a communications network that interconnects computer networks around the world, enabling the sending and receiving of information.

[0110] "JSON format" stands for JavaScript Object Notation, a lightweight data exchange format that represents data as key-value pairs and is easy to read for both humans and machines.

[0111] An "internal intranet" is a dedicated network used within a company, built for the purpose of sharing internal information and communication.

[0112] A "database" is an information system that organizes and stores large amounts of data, enabling fast searching and access.

[0113] A "notification email" is an email sent to convey specific information, with the aim of quickly conveying the information to the recipient.

[0114] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, uses a generative AI model to automatically create draft regulations based on that amendment information, collects feedback from stakeholders, and automates the process of finalizing and publishing the draft internally. Specifically, the system is configured and operated as follows:

[0115] Legal information gathering

[0116] The server connects to the internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server retrieves information on revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's official website. The server analyzes the data and stores it in JSON format before passing it to the AI ​​model to generate the new content.

[0117] Draft generation

[0118] The server sends the saved JSON data of the legal amendment information to the generative AI model, which generates a new draft regulation based on the following prompt:

[0119] Please draft new working hours regulations based on the latest revisions to the Labor Standards Act.

[0120] The changes are as follows:

[0121] [Revision information]

[0122] The server receives the generated draft regulations and stores them in a database.

[0123] Comparison and Review

[0124] The server compares the new draft text with the existing policy using a text comparison tool, such as a diff tool, and the server highlights the changes in red, generating a document showing the changes.

[0125] Collecting feedback

[0126] The server sends new drafts and comparison documents to the stakeholders via email. The stakeholders receive the emails on their own devices and review the drafts and comparison documents. The stakeholders submit feedback via a web form or reply email. For example, feedback is collected when stakeholders access a web form, enter their feedback, and click the submit button.

[0127] Approval and publication

[0128] The user checks the feedback on the terminal and modifies the draft text as necessary. After the final draft is confirmed, the user presses the approval button. The server then publishes the approved draft text on the company intranet and sends an email to all employees to notify them.

[0129] History Management

[0130] The server stores and manages new regulations and their revision history in a database. Users with appropriate access rights can check the history of past revisions.

[0131] Specific examples

[0132] Example 1

[0133] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day. The acquired data is stored in JSON format, and the server analyzes it and passes the content to be created to the generative AI model. The generative AI model creates a draft of the "Working Hours Regulations" incorporating the revised parts, compares it with the current version, and highlights the changes in red.

[0134] Example 2

[0135] After a new draft is created, the server retrieves the email list of the HR department and sends it via email with the draft attached. HR personnel receive the email on their own devices, review it, and provide feedback via a web form. The HR manager checks the feedback, makes any necessary corrections, and approves the final draft. Once approved, the server publishes the policy on the company intranet and notifies all employees. In addition, the new policy and revision history are all stored in a database, allowing users to check past revisions at any time.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1:

[0138] The server connects to the Internet at 3:00 AM every day and collects the latest legal revision information from legal databases and official websites. This collection is done using APIs. For example, information on revisions to the Labor Standards Act is obtained from the Ministry of Health, Labor and Welfare's API. The input is the API request, and the output is the obtained revision information in JSON format. The server analyzes this data and extracts the necessary revision information.

[0139] Step 2:

[0140] The server analyzes and formats the extracted revision information and converts it into a format that can be passed to the generative AI model. Specifically, it formats the revision information and generates a prompt text. The input is revision information in JSON format, and the output is the prompt text that is passed to the generative AI model. Example of a prompt text:

[0141] Please draft new working hours regulations based on the latest revisions to the Labor Standards Act.

[0142] The changes are as follows:

[0143] [Revision information]

[0144] The server sends this prompt to the generative AI model.

[0145] Step 3:

[0146] The generative AI model generates a new draft policy sentence based on the prompt sentence. The input is the generated prompt sentence, and the output is the new draft policy sentence. The generative AI model uses natural language processing techniques to do this. The server receives the generated draft sentence and stores it in a database.

[0147] Step 4:

[0148] The server compares the new draft text with the existing policy using a text comparison tool. The input is the new draft text and the existing policy, and the output is a comparison document with the changes highlighted. The server uses a text comparison tool (e.g., a diff tool) to identify the changes and generate a comparison document with the changes highlighted in red.

[0149] Step 5:

[0150] The server sends the new draft document and the comparison document to the participants by email. The input is the new draft document and the comparison document, and the output is an email to the participants. The participants receive the email on their own devices and review the draft document and the comparison document.

[0151] Step 6:

[0152] Stakeholders use their terminals to review the new draft and comparison documents and provide feedback. The input is the review and feedback of the stakeholders, and the output is the feedback received by the server. Stakeholders submit their feedback via a web form or reply email.

[0153] Step 7:

[0154] The user checks the feedback on the terminal and modifies the draft text as necessary. The input is feedback from the stakeholders, and the output is the modified final draft text. The user reflects the feedback and confirms the final draft text.

[0155] Step 8:

[0156] The user approves the final draft. When the user presses the approval button, the server publishes the approved draft on the company intranet and sends a notification email to all employees. The input is the approved final draft, and the output is publication on the company intranet and a notification email.

[0157] Step 9:

[0158] The server stores and manages new policies and their revision history in a database. The input is the new policy and its revision history, and the output is an entry stored in the database. Users with appropriate access rights can check the history of past revisions.

[0159] (Application example 1)

[0160] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0161] In large facilities such as factories, updating and managing regulations based on the latest legal revisions is extremely time-consuming. Manual updates are prone to errors and delays, resulting in uncertain compliance. Furthermore, a lack of efficient means of communication with stakeholders means gathering feedback and approving final proposals takes time. To solve these issues, there is a need for a system that automates the regulations management process and can quickly and accurately comply with the latest laws.

[0162] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0163] In this invention, the server includes means for connecting to a legal database and acquiring new legal revision information, means for analyzing and extracting the acquired legal revision information, means for automatically generating draft regulations based on the revision information extracted by the generation AI, means for comparing the generated new draft regulations with the current regulations and indicating changes, means for sending the new draft regulations to relevant parties using a screen device and collecting feedback from them, means for revising the draft regulations based on the feedback and publishing them on the network after approval, means for saving and managing the new regulations and their revision history in a storage device, and means for automatically adjusting machine operation based on the latest regulation information. This ensures that machines in the factory always operate in accordance with the latest safety regulations and ensures compliance with laws and regulations.

[0164] - "Legal Database" means an online system for storing and managing data including the latest laws and regulations.

[0165] "New Law Change Information" means the latest information on changes or additions to existing laws and regulations.

[0166] "Generative AI" is a technology that uses artificial intelligence to generate text and content based on specified conditions and data.

[0167] A "draft regulation" is a document that lists the rules and guidelines that a company or organization must follow.

[0168] "Stakeholders" are people or organizations that play a significant role in a particular project or task.

[0169] "Feedback" is an opinion or evaluation given in response to a specific content or action.

[0170] A "network" is a system in which multiple computers and devices are connected to each other and exchange and share data.

[0171] A "storage device" is an electronic device for storing data for long periods of time and retrieving it as needed.

[0172] "Machines" are devices or robots that perform work automatically.

[0173] To implement the present invention in a factory or the like, a design is first made based on the specific combination of hardware and software that constitutes the entire system. The main components of the present invention are a server, a terminal, a generative AI model, a storage device, a network, and machines.

[0174] First, the server connects to a legal database and periodically retrieves new legal revision information. To do this, the server collects data from official websites and APIs via the Internet. Legal revision information is often provided in JSON format, which the server parses and extracts the necessary revision information. This is done using Python's requests library and analysis processing library.

[0175] Next, the extracted revision information is passed to a generative AI model to automatically generate a new draft regulation text. The generative AI model uses OpenAI's GPT-3, among others. The generative AI model generates a new draft regulation text based on the following prompt:

[0176] Generate factory safety regulations based on the new Labor Standards Act:

[0177] New regulations...

[0178] The server compares the new draft text with the current version and highlights any changes. This process uses a text comparison tool, and changes are highlighted in red, allowing stakeholders to see the changes at a glance.

[0179] The new draft text is sent to the relevant parties using a display device. The relevant parties receive the draft text on their own devices (smartphones, tablets, etc.) and provide feedback. This feedback is collected via email and web forms. The server that collects the feedback then modifies the draft text based on that feedback and generates the final version of the draft regulations.

[0180] Once the final draft of the regulations has been approved by the relevant parties, it will be published on the network by the server. At this point, all users will be able to view the new regulations. The new regulations and their revision history will be saved in a storage device and managed so that they can be accessed at any time.

[0181] Furthermore, the system is equipped with a function that automatically adjusts machine operation based on the latest regulatory information, ensuring that factory machinery always operates in compliance with the latest safety regulations and ensuring compliance with laws and regulations.

[0182] As an example, let's consider the case of obtaining information about revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's API. In this case, the server periodically sends requests to the API, analyzes the obtained JSON data, and passes it to a generative AI model to generate a draft of new working hours regulations. The generated draft is then compared with the current version, and relevant parties are asked to review it via a screen device, and revisions and approvals are made based on the feedback. The final regulations are published on the network, and the machines in the factory automatically change their behavior in accordance with the regulations.

[0183] In this way, the present invention comprehensively realizes the rapid collection of legal information, the automatic generation of draft regulations, efficient communication with relevant parties, management of revision history, and the adjustment of machine operation based on that history, thereby greatly improving the efficiency of regulations management in factories and other facilities.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The server connects to the legal database via the Internet to obtain new legal revision information. Specifically, the server periodically sends requests to the legal database's API and receives JSON-formatted data containing legal revision information. The input is the API request, and the output is the obtained JSON data.

[0187] Step 2:

[0188] The server parses the acquired legal amendment information and extracts the necessary amendment information. In this process, a JSON parsing library is used to parse the data and extract the specific amendment content. The input is the acquired JSON data, and the output is text data containing the specific amendment information.

[0189] Step 3:

[0190] The server passes the revision information to the generative AI model and generates a new draft regulation text. The server provides the prompt text "Please generate factory safety regulations based on the new Labor Standards Act:- New regulation content..." and the generative AI model generates a new draft regulation text. The input is the revision information and the prompt text, and the output is the generated draft regulation text.

[0191] Step 4:

[0192] The server compares the generated new draft with the current regulations and highlights the changes. This is done using a text comparison tool, which highlights the changes in red. The input is the new draft and the current draft regulations, and the output is text data containing the comparison results.

[0193] Step 5:

[0194] The server sends the new draft to the relevant parties using a display device. Each party receives the new draft on their device (smartphone or tablet) and can review it. The input is the compared draft regulations, and the output is the state in which the review request has been sent.

[0195] Step 6:

[0196] Participants use their devices to return feedback. Feedback is sent via email or web forms and collected on a server. The input is the participant's feedback, and the output is the collected feedback data.

[0197] Step 7:

[0198] The server then modifies the draft policy text based on the collected feedback. If necessary, it re-uses the generative AI model to generate a revised draft policy text. The input is the collected feedback data, and the output is the final revised draft policy text.

[0199] Step 8:

[0200] Once the final draft is approved by the parties involved, the server publishes it on the network. The final draft is saved in a storage device and managed in a database. The input is the approved final draft, and the output is the published regulations and a saved revision history.

[0201] Step 9:

[0202] The server automatically adjusts machine operation based on the latest regulation information. The latest regulation information is provided as parameters to machines in the factory via the network, and machine settings and operation are automatically updated. The input is the latest regulation information, and the output is the adjusted machine operation.

[0203] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0204] This invention is a system that streamlines corporate regulations management, and in particular, by combining it with an emotion engine that recognizes user emotions, it enables more serious and precise feedback collection and processing. This system automatically obtains new legal amendment information from a legal database, automatically creates draft regulations based on that amendment information using a generative AI, collects and evaluates feedback from stakeholders via the emotion engine, and streamlines the process of finalizing and publishing the draft within the company.

[0205] Specifically, the system is configured and operated as follows:

[0206] Legal information gathering

[0207] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it obtains information on revisions to the Labor Standards Act from the official website of the Ministry of Health, Labor and Welfare.

[0208] Draft generation

[0209] The server passes the acquired revision information to the generation AI, which then uses that information to generate new draft regulations. For example, it creates "working hours regulations" based on the revisions to the Labor Standards Act.

[0210] Comparison and Review

[0211] The server compares the new draft text created by the AI ​​with the current regulations using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[0212] Collecting feedback

[0213] The server then emails the new draft to the interested parties, including an attachment of the draft and a link for review.

[0214] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[0215] The server collects feedback from participants and analyzes it with an emotion engine, which evaluates the emotional state of the user's feedback and determines its importance and reliability according to the emotional state.

[0216] Approval and publication

[0217] The user checks the feedback while referring to the evaluation results from the emotion engine and makes any necessary corrections. After the final draft is approved, the server publishes the regulations on the company intranet and notifies all employees.

[0218] History Management

[0219] The server stores new regulations and their revision history in a database and manages them so that they can be accessed at any time. Past revisions and their history can be easily tracked and confirmed.

[0220] Specific examples

[0221] Example 1

[0222] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format. The acquired data is analyzed and the revisions are sent to the generation AI. The generation AI generates a draft of the new "Working Hours Regulations," and the server compares the text with the current version. Changes are highlighted in red.

[0223] Example 2

[0224] After a new draft is created, the server emails it to the relevant parties, informing them that it requires review.

[0225] The users receive the emails on their devices, review the new draft text, and submit their feedback via a web form. The server then analyzes the feedback using an emotion engine to assess the importance and credibility of the feedback based on the user's emotional state.

[0226] Finally, users make revisions based on the feedback and evaluations and approve the regulations. The approved regulations are published on the company intranet via a server. All revision history is also stored in a database and can be accessed at any time.

[0227] This invention significantly improves the efficiency of corporate regulations management and contributes to strengthening compliance with laws and regulations and internal control by comprehensively achieving the rapid collection of legal information, automatic generation of draft texts, efficient communication with stakeholders and feedback evaluation, and revision history management. In addition, the combination of an emotion engine improves the quality of feedback and achieves more accurate regulations management.

[0228] The processing flow will be explained below.

[0229] Step 1:

[0230] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it uses the Ministry of Health, Labor and Welfare's API to obtain revision information for the Labor Standards Act in JSON format.

[0231] Step 2:

[0232] The server analyzes the legal amendment information it has acquired and extracts the necessary amendments. Text mining technology is used for the analysis to extract the main points of the amendment information.

[0233] Step 3:

[0234] The server sends the extracted revision information to the generation AI, which then automatically creates a new draft regulation based on the revision information. At this time, the generation AI generates a draft regulation that conforms to the company's existing regulation format.

[0235] Step 4:

[0236] The server compares the new draft text with the current version using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[0237] Step 5:

[0238] The server emails the new draft to interested parties, including an attachment of the draft and a review link that they can click to access a web form to provide their feedback.

[0239] Step 6:

[0240] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[0241] Step 7:

[0242] The server collects feedback from participants and sends it to the emotion engine, which analyzes the text of the feedback and evaluates the user's emotional state. For example, the emotion engine detects "dissatisfaction" or "question" from the feedback content.

[0243] Step 8:

[0244] The server receives the emotion evaluation results from the emotion engine and lists the importance and reliability of the feedback. At this time, it categorizes the feedback based on the evaluation of the emotional state and determines the processing order according to urgency and importance.

[0245] Step 9:

[0246] The user checks the feedback while referring to the evaluation results of the emotion engine and makes any necessary corrections. The user prioritizes checking feedback that the emotion engine indicates as "dissatisfied" and makes appropriate corrections.

[0247] Step 10:

[0248] The user reviews the final draft and gives their approval. Once approved, the server publishes the regulations on the company intranet and notifies all employees.

[0249] Step 11:

[0250] The server stores the new regulations and their revision history in a database, which is recorded in detail and managed so that it can be accessed at any time.

[0251] Specific examples

[0252] Step 1 example

[0253] The server obtains information on revisions to the Labor Standards Act through the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format.

[0254] Step 2: Example

[0255] The server uses text mining technology to analyze the revision details from the received JSON data and extract the necessary information.

[0256] Step 3 example

[0257] The server sends the extracted revision information to the generation AI, which then automatically generates a draft of the new "Work Hours Regulations." This draft is created according to the company's existing format.

[0258] Step 4: Example

[0259] The server compares the new draft with the current "Work Hours Regulations" using a text comparison tool and highlights the changes in red.

[0260] Step 5: Example

[0261] The server sends an email to the HR representative with the new draft attached and a link for review.

[0262] Step 6: Example

[0263] The human resources staff member who receives the email on the device reviews the draft text, enters the review results into a web form, and submits it.

[0264] Step 7 Example

[0265] The server sends the collected feedback to an emotion engine, which analyzes the text of the feedback to evaluate the user's emotional state.

[0266] Step 8 Example

[0267] The server lists the importance and reliability of the feedback based on the evaluation results of the emotion engine. For example, feedback rated as "unsatisfactory" is given priority.

[0268] Step 9 Example

[0269] The user checks the feedback and makes necessary corrections based on the evaluation results of the emotion engine. Feedback rated as "unsatisfactory" is addressed first.

[0270] Step 10: Example

[0271] The user checks the final draft and gives their approval. Once approved, the server publishes the regulations on the company intranet and notifies all employees.

[0272] Step 11 Example

[0273] The server stores new regulations and revision history in detail in a database and manages them so that users can access them at any time.

[0274] Example 2

[0275] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0276] For corporate regulations management, it is important to respond quickly to legal revisions. However, in many cases, collecting feedback from stakeholders and evaluating its content takes time, making efficient operation difficult. There is also a need for a method to improve the quality of feedback and make more appropriate revisions and approvals. To solve these issues, there is a need for a system that streamlines the entire process of automatically obtaining legal revision information, automatically generating draft regulations, and collecting and analyzing feedback, thereby enabling rapid and accurate regulation revisions.

[0277] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0278] In this invention, the server includes means for connecting to a legal database and acquiring new legal revision information, means for analyzing and extracting the acquired legal revision information, means for automatically generating draft regulations based on the revision information extracted by the generative AI model, means for comparing the generated new draft regulations with current regulations and indicating changes, means for sending the new draft regulations to stakeholders and collecting feedback, means for analyzing the feedback using an emotion engine and evaluating its importance and reliability, means for revising the draft regulations based on the feedback and publishing them internally after approval, and means for storing and managing the new regulations and their revision history in a database. This enables companies to respond quickly and accurately to legal revisions, improve the quality of feedback from stakeholders, and more appropriately revise and approve regulations.

[0279] A "legal database" is a database that stores the latest information on legal amendments and laws that will be enacted, and is accessible via the Internet.

[0280] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to automatically generate sentences and content based on input text data.

[0281] An "emotion engine" is software or an algorithm that analyzes the content of user feedback and evaluates its emotional state, importance, and reliability.

[0282] "Draft Regulations" means a draft of regulations prepared based on legal amendment information and other requirements.

[0283] A "text comparison tool" is software that compares different texts and highlights the changes.

[0284] A "database" is a computer system designed to store information systematically and allow rapid retrieval and access.

[0285] A "web form" is a form-filling feature built into a web page on the Internet, allowing users to enter and submit information.

[0286] "Email" is a means of communication for sending and receiving text messages and attachments over the Internet.

[0287] A "corporate intranet" is a private network used within an organization that uses Internet technology for the purpose of sharing and accessing internal information.

[0288] An "SMTP server" is a computer server that implements the Simple Mail Transfer Protocol, a protocol for sending email.

[0289] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, automatically creates draft regulations based on that amendment information using a generative AI model, collects and evaluates feedback from stakeholders using an emotion engine, and then finalizes and publishes the final draft, streamlining the process.

[0290] Legal information gathering

[0291] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server uses the Ministry of Health, Labor and Welfare's API to obtain revision information on the Labor Standards Act in JSON format. This obtained data is then analyzed within the system to extract the necessary information.

[0292] Draft generation

[0293] The server passes the acquired revision information to the generative AI model, which then generates a new draft of the regulations based on that information. An example of a prompt is, "Please generate a new draft of the working hours regulations based on the latest revision information of the Labor Standards Act." The generated draft is saved within the system and proceeds to the next step.

[0294] Comparison and Review

[0295] The server compares the generated new draft regulations with the current regulations using a text comparison tool. The changes are highlighted so that stakeholders can see them at a glance. The comparison results are saved as an HTML file and sent to stakeholders.

[0296] Collecting feedback

[0297] The server sends the new draft regulations to the relevant parties via email. The email contains an attachment of the draft regulations and a link for review. The relevant parties receive the email on their devices, check the attachment, and review it. They then enter the review results into a web form and submit it. The server collects feedback from the relevant parties and analyzes it using an emotion engine. The emotion engine evaluates the emotional state of the user's feedback and determines its importance and reliability based on that emotional state.

[0298] Approval and publication

[0299] The user checks the feedback based on the evaluation results from the emotion engine and makes any necessary revisions. After the final draft is approved, the server publishes the policy on the company intranet and notifies all employees. Notification is sent via email, and all employees can access the new policy.

[0300] History Management

[0301] The server stores the new regulations and their revision history in a database and manages them so that they can be accessed at any time, making it easy to track and check past revisions and their history.

[0302] Specific example explanation

[0303] For example, the server collects information on revisions to the Labor Standards Act through the Ministry of Health, Labor, and Welfare's API at 3:00 AM every day, analyzes the data, and sends a prompt to the generative AI model: "Please generate a new draft of the working hours regulations based on the latest revisions to the Labor Standards Act." The generative AI model generates a new draft, compares it with the current version using a text comparison tool, and highlights changes in red. The server then emails the new draft and the comparison results to relevant parties and accepts feedback. The relevant parties submit feedback on their devices, and the server analyzes it using an emotion engine. Finally, the user reviews the feedback, makes corrections and approvals, and the server publishes it on the company intranet. This process enables companies to manage regulations quickly and efficiently.

[0304] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0305] Step 1:

[0306] Legal information gathering

[0307] The server connects to the Internet at a set time every day (e.g., 3:00 AM) and accesses legal databases and official websites. Specifically, the server retrieves revision information for the Labor Standards Act in JSON format from the Ministry of Health, Labor and Welfare's API.

[0308] Input: Legal database access information, API endpoint, query parameters

[0309] Output: Legal change information in JSON format

[0310] What it does: Sends an HTTP request, parses the response from the API, and saves it as JSON data.

[0311] Step 2:

[0312] Legal Information Analysis and Extraction

[0313] The server analyzes the acquired JSON-formatted legal amendment information and extracts the necessary amendment details. Specifically, it extracts the relevant legal provisions and their amendment details from the JSON data.

[0314] Input: Legal amendment information in JSON format

[0315] Output: Extracted data of revision details (text and object format containing necessary information)

[0316] What it does: It uses a JSON parser to parse the data and extract the values ​​of specific fields.

[0317] Step 3:

[0318] Automatic generation of draft regulations

[0319] The server sends the extracted revision details to the generation AI model. It instructs the model to generate a draft regulation using a prompt. The specific prompt is, "Please generate a draft of the new working hours regulations based on the latest revision information of the Labor Standards Act."

[0320] Input: Extracted revision data, prompt text

[0321] Output: Generated draft regulations (text format)

[0322] How it works: Sends an API request to the generative AI model and retrieves the generated text.

[0323] Step 4:

[0324] Comparison of the text of the old and new draft regulations

[0325] The server compares the generated new draft regulations with the current regulations using a text comparison tool, highlighting the changes.

[0326] Input: New regulation draft text, current regulation text

[0327] Output: Comparison results with highlighted changes (HTML or PDF format)

[0328] How it works: It uses a text comparison algorithm to calculate the differences and identify the changes, which are then highlighted in red.

[0329] Step 5:

[0330] Submitting a new rule proposal

[0331] The server will then email the generated comparison results and the new rule proposal to the relevant parties, including a link for review.

[0332] Input: Email addresses of relevant parties, new rule draft, comparison results, review link

[0333] Output: Email sent

[0334] What it does: Sends an email through an SMTP server, containing a text message and an attachment.

[0335] Step 6:

[0336] Collecting feedback

[0337] The relevant parties receive the email on their terminal, check the attachments, review the file, and then enter the review results into a web form and submit it.

[0338] Input: Incoming emails, attachments, and web form entries

[0339] Output: Feedback data sent

[0340] What it does: Open the attachment in your email client, check the contents, then fill out the form in your web browser.

[0341] Step 7:

[0342] Feedback Analysis

[0343] The server sends the collected feedback to the emotion engine for analysis, which evaluates the emotional state of the feedback.

[0344] Input: Feedback data

[0345] Output: Sentiment analysis results (score, evaluation comments)

[0346] Behavior: Sends feedback data to the Emotion Engine API and receives analysis results.

[0347] Step 8:

[0348] Review and correct feedback

[0349] The user checks the emotion engine's analysis results and makes any necessary corrections based on the feedback.

[0350] Input: Sentiment analysis results, feedback content

[0351] Output: Revised draft regulations

[0352] How it works: View feedback and ratings through the admin panel and make corrections using the editing tools.

[0353] Step 9:

[0354] Approval and publication of the final draft

[0355] The user checks and approves the final draft of the regulations. The server then publishes the approved draft on the company intranet and notifies all employees.

[0356] Input: Confirm the final draft regulations and give approval instructions

[0357] Output: Published regulations, notification to all employees

[0358] Operation: Approval is performed on the management screen, and the data is uploaded to the intranet and notified to all employees by email.

[0359] Step 10:

[0360] Saving revision history

[0361] The server stores the new rule draft and its revision history in a database.

[0362] Input: Final draft regulations, previous revision history

[0363] Output: Saved revision history data

[0364] Behavior: Performs an INSERT operation on the database and records the revision history.

[0365] (Application example 2)

[0366] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0367] The process of corporate policy management involves complex tasks such as manually processing large amounts of legal information, collecting and evaluating feedback from stakeholders, and publishing new policies in a timely manner, making it difficult to carry out efficiently. Furthermore, to improve the quality of feedback, it is also important to accurately grasp and evaluate users' emotional states. This calls for a system that enables more accurate policy management.

[0368] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0369] In this invention, the server includes: means for connecting to a legal database and acquiring information on new legal revisions; means for analyzing and extracting the acquired legal revision information; means for automatically generating draft regulations based on the revision information extracted by the generation AI; means for comparing the generated new draft regulations with current regulations and indicating changes; means for sending the new draft regulations to relevant parties and collecting feedback; means for revising the draft regulations based on the feedback and publishing them internally after approval; means for storing and managing the new regulations and their revision history in a database; means for periodically collecting the latest regulatory information on industrial safety and quality control; means for automatically generating new work procedures and regulations using the generation AI; means for comparing the generated new work procedures and regulations with current ones and indicating changes; means for analyzing feedback using an emotion engine and evaluating the importance and reliability of the feedback based on the emotional state; and means for finalizing and introducing the final draft regulations into the production line. This enables rapid acquisition and analysis of legal revision information, and enables efficient automatic generation of new draft regulations and work procedures using the generation AI. In addition, using an emotion engine improves the quality of feedback, enabling more accurate regulation management.

[0370] A "legal database" is a data storage system that systematically collects, stores, and makes accessible legal information.

[0371] "Legal amendment information" refers to various detailed information about newly enacted laws and amendments to existing laws.

[0372] "Generative AI" is a type of artificial intelligence that is a technology that automatically generates sentences and procedures based on given data and conditions.

[0373] A "draft regulation" is a formal draft document that lists the rules and procedures that must be followed within a company or organization.

[0374] The "emotion engine" is an artificial intelligence technology that analyzes the user's emotional state and evaluates the quality and importance of feedback based on that information.

[0375] "Feedback" refers to opinions and evaluations from stakeholders that are used to refine and modify new draft texts and procedures.

[0376] "Revision History" means information that keeps a record of all past changes and modifications and allows them to be tracked.

[0377] "Industrial safety" refers to rules and standards to ensure the health and safety of workers, and measures to minimize dangers in factories and work sites.

[0378] "Quality control" refers to planned and controlled activities to maintain and improve the quality of products and services.

[0379] A "production line" is a system that divides the manufacturing process in a factory or other facility to carry out continuous and efficient production.

[0380] This invention aims to improve the efficiency of a quality control system using factory robots. This system automatically generates procedures and rules to quickly respond to changes in laws and regulations, and includes an emotion engine to effectively collect and analyze feedback. Specific embodiments are described below.

[0381] System Configuration

[0382] The system consists of the following main elements:

[0383] 1. Server: This is the central hardware that manages and controls the entire system. The server connects to the Internet, retrieves the latest regulatory information from the legal database, and generates new work procedures using generative AI models.

[0384] 2. Generative AI: This is an artificial intelligence technology that generates new work procedures and rules. For example, OpenAI's GPT-3 model can be used.

[0385] 3. Emotion Engine: This is an artificial intelligence technology that analyzes feedback from stakeholders and evaluates their emotional state, determining the importance and credibility of the feedback.

[0386] 4. Database: A data storage system for storing and managing new regulations and their revision history.

[0387] Processing procedures and data calculations

[0388] Legal information gathering

[0389] The server collects the latest legal revision information from legal databases and official websites via the Internet, for example, periodically obtaining the latest regulatory information related to industrial safety and quality control.

[0390] Draft generation

[0391] The acquired legal amendment information is passed to a generative AI, which automatically generates new draft regulations and work procedures. A generative AI model (e.g., GPT-3) is used to generate new procedures using the following prompt sentence as input:

[0392] "Please generate new factory work procedures based on the following legal changes: 'According to new industrial safety regulations, the working time limit has changed. This means that working time in hazardous areas will now be limited to 6 hours per day. Please provide new work procedures.'"

[0393] Comparison and Review

[0394] The server compares the new draft text created by the AI ​​with the current regulations using a text comparison tool, highlighting the changes so that they are clearly visible to stakeholders.

[0395] Collecting feedback

[0396] The server sends new work instructions to stakeholders via email or web forms and collects feedback, which is analyzed using an emotion engine and rated for importance and credibility based on the emotional state.

[0397] Approval and publication

[0398] The server checks the feedback based on the evaluation results from the emotion engine and makes any necessary corrections. After the final proposal is approved, it will be implemented on the production line and the work procedures will be finalized.

[0399] History Management

[0400] The server stores new work procedures and their revision history in a database and manages them so that they can be accessed at any time. Past revisions and their history can be easily tracked and checked.

[0401] This enables the rapid acquisition and analysis of legal amendment information, and new draft regulations and work procedures are efficiently created through automatic generation using generative AI. In addition, the use of an emotion engine improves the quality of feedback, resulting in more accurate regulation management.

[0402] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0403] Step 1:

[0404] The server connects to the legal database to retrieve new legal amendment information. It receives data from the legal database API as input and stores the legal amendment information in JSON format as output. This data includes newly enacted laws and amendments to existing laws.

[0405] Step 2:

[0406] The server analyzes the acquired legal amendment information and extracts the necessary information. The input is the JSON of the legal amendment information acquired in step 1, and the output is the analyzed and extracted amendment information. The server extracts the necessary information using a text analysis tool and passes it to the generative AI model.

[0407] Step 3:

[0408] The server inputs the revision information into the generative AI, which then automatically generates new draft regulations and work procedures. The input is the analyzed revision information, and the output is the generated new draft regulations and work procedures. For example, the generative AI model (e.g., GPT-3) is given the following prompt:

[0409] "Please generate new factory work procedures based on the following legal changes: 'According to new industrial safety regulations, the working time limit has changed. This means that working time in hazardous areas will now be limited to 6 hours per day. Please provide new work procedures.'"

[0410] The generation AI generates a corresponding new procedure.

[0411] Step 4:

[0412] The server compares the generated new draft with the current policy using a text comparison tool. The input is the new draft and the current policy, and the output is text with the changes clearly marked. The server uses the text comparison tool to compare the old and new procedures and highlight the changes.

[0413] Step 5:

[0414] The server sends the new draft to stakeholders via email or a web form and collects their feedback. The input is the new draft with the changes highlighted, and the output is feedback from stakeholders. Stakeholders use their devices to send their opinions via email or a web form.

[0415] Step 6:

[0416] The server analyzes the collected feedback using an emotion engine. The input is the feedback from the stakeholders, and the output is an evaluation of the importance and credibility of the feedback based on its emotional state. The emotion engine analyzes the feedback text and extracts its emotional features.

[0417] Step 7:

[0418] The user refers to the feedback evaluation results from the emotion engine and modifies the new draft regulations and work procedures. The input is the emotion engine's evaluation results and feedback content, and the output is the final modified draft regulations and procedures. After making the necessary modifications, the user sends the finalized procedures to the server.

[0419] Step 8:

[0420] The server implements the approved new procedures on the production line. The input is the final revised draft or procedure, and the output is the procedure converted into a form that can be implemented on the production line. The server then uses an automated process to ensure that the new procedure is applied on the production line.

[0421] Step 9:

[0422] The server saves and manages new work procedures and their revision history in a database. The input is the final implemented work procedure and its history, and the output is the history saved in the database. The server periodically updates the database and manages it so that past revisions and history can be tracked and checked.

[0423] These are the specific processing steps of the system that realizes this application example. This process efficiently acquires information on legal changes, generates new procedures, collects and analyzes feedback, and implements the final procedures.

[0424] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0425] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0426] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0427] [Second embodiment]

[0428] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0429] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0430] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0431] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0432] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0433] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0434] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0435] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0436] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0437] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0438] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0439] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0440] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, automatically creates draft regulations based on the amendment information using a generative AI, collects feedback from stakeholders, finalizes the draft, and automates the process of publishing it internally.

[0441] Specifically, the system is configured and operated as follows:

[0442] Legal information gathering

[0443] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it obtains information on revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's official website.

[0444] Draft generation

[0445] The server passes the acquired revision information to the generation AI, which then uses that information to generate a new draft of the regulations. For example, it generates a new draft of the "Working Hours Regulations" that takes into account the revisions to the Labor Standards Act.

[0446] Comparison and Review

[0447] The server compares the new draft text created by the generative AI with the current regulations and uses text comparison tools to highlight the changes, making the changes visible at a glance and improving review efficiency.

[0448] Collecting feedback

[0449] The server emails the new draft to stakeholders, who then receive the emails on their own devices, review them, and provide feedback, which is collected through web forms and reply emails.

[0450] Approval and publication

[0451] The user checks the feedback, makes any necessary corrections, and finally approves the policy. The server then publishes the final version of the policy on the company intranet and notifies all employees.

[0452] History Management

[0453] The server stores the new regulations and their revision history in a database and manages them so that they can be accessed at any time. This makes it easy to track and check past revisions and their history.

[0454] Specific examples

[0455] Example 1

[0456] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day. The acquired data is in JSON format, which the server parses and passes to the generation AI the content to be created. The generation AI creates a draft of the "Working Hours Regulations" incorporating the revised parts, compares it with the current version, and highlights the changes in red.

[0457] Example 2

[0458] After a new draft is created, the server retrieves the email list of the HR department and sends an email with the draft attached. HR personnel receive the email on their own devices, review it, and provide feedback through a web form. The HR manager reviews the feedback, makes any necessary corrections, and approves the final draft.

[0459] Once the final draft is approved, the server publishes the policy on the company intranet and notifies all employees. The new policy and revision history are all stored in a database, so users can check past revisions at any time.

[0460] This invention comprehensively realizes the rapid collection of legal information, automatic generation of draft texts, efficient communication with stakeholders, and management of revision history, thereby significantly improving the efficiency of corporate regulation management and contributing to strengthening compliance with laws and regulations and internal control.

[0461] The processing flow will be explained below.

[0462] Step 1:

[0463] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server uses the Ministry of Health, Labor and Welfare's API to obtain revision information for the Labor Standards Act in JSON format.

[0464] Step 2:

[0465] The server analyzes the legal amendment information it has acquired and extracts the necessary amendments. Text mining technology is used for the analysis to extract the main points of the legal amendments.

[0466] Step 3:

[0467] The server sends the extracted revision information to the generation AI, which then automatically creates a new draft regulation based on the revision information. At this time, the generation AI generates a draft regulation that conforms to the company's existing regulation format.

[0468] Step 4:

[0469] The server compares the new draft text with the current version using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[0470] Step 5:

[0471] The server emails the new draft to interested parties, including an attachment of the draft and a review link that they can click to access a web form to provide their feedback.

[0472] Step 6:

[0473] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[0474] Step 7:

[0475] The server collects and aggregates feedback from stakeholders, automatically sorts it, and lists the necessary changes.

[0476] Step 8:

[0477] The user reviews the feedback and makes any necessary corrections. The user then makes a final check of the revised draft and decides whether to approve it.

[0478] Step 9:

[0479] The server publishes the final approved version of the regulations on the company intranet, which is then immediately notified to all employees.

[0480] Step 10:

[0481] The server stores the new regulations and their revision history in a database, which is recorded in detail and managed so that it can be accessed at any time.

[0482] Specific examples

[0483] Step 1 example

[0484] The server obtains information on revisions to the Labor Standards Act through the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format.

[0485] Step 2: Example

[0486] The server uses text mining technology to analyze the revised parts of the JSON data it receives and extracts the revised contents of the Labor Standards Act.

[0487] Step 3 example

[0488] The server sends the extracted revision information to the generation AI, which then generates a draft of the new "Work Hours Regulations." The draft text conforms to the company's existing format.

[0489] Step 4: Example

[0490] The server compares the new draft with the current version using a text comparison tool and highlights the revised parts in red.

[0491] Step 5: Example

[0492] The server sends an email to the HR representative with the new draft attached and a link for review.

[0493] Step 6: Example

[0494] The HR staff receives the email on the device, reviews the new draft text, and submits feedback via a web form.

[0495] Step 7 Example

[0496] The server collects all the feedback and organizes a list of necessary fixes.

[0497] Step 8 Example

[0498] The user then revises the draft based on the feedback, and then gives final approval.

[0499] Step 9 Example

[0500] The server publishes the approved regulations on the company intranet and notifies all employees by email.

[0501] Step 10: Example

[0502] The server stores new regulations and their revision history in a detailed database, allowing users to access past changes.

[0503] Example 1

[0504] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0505] Corporate regulation management requires a great deal of time and effort to deal with legal revisions and update internal regulations. The process of collecting information on legal revisions, drafting regulations, gathering feedback from stakeholders, and finally approving and publishing the final draft is particularly complex and requires efficient and accurate execution. However, current manual processes and partial automation make it difficult to fully meet the demands for regulatory compliance and strengthened internal controls. This leaves companies exposed to reduced operational efficiency and the risk of legal violations.

[0506] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0507] In this invention, the server includes: means for connecting to a legal database and acquiring new legal revision information; means for analyzing and extracting the acquired legal revision information; means for automatically generating draft regulations based on the revision information extracted by the generative AI model; means for comparing the generated new draft regulations with existing regulations and indicating changes; means for automatically periodically collecting legal revision information from the Internet; means for storing the collected legal revision information in JSON format; means for comparing the new draft regulations with existing regulations using a text comparison tool; means for visualizing the comparison results and generating a document indicating changes; means for sending the new draft regulations to relevant parties and collecting feedback; means for revising the draft regulations based on the feedback and publishing them internally after approval; means for saving and managing the new regulations and their revision history in a database; and means for publishing approved regulations on the company's intranet and notifying all employees. This significantly streamlines the entire corporate regulations management process, enabling enhanced compliance with laws and regulations and internal control.

[0508] A "legal database" is a database that stores laws, regulations, and amendments that can be accessed and searched as needed.

[0509] "Revision Information" means information that describes changes or updates to current laws and regulations.

[0510] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to automatically generate new documents based on provided information.

[0511] A "draft rule" is a document that documents the rules and policies that apply within a company and is used as a draft.

[0512] A "text comparison tool" is software that compares two documents and automatically identifies and highlights differences and changes.

[0513] "Feedback" refers to information including opinions, requests for amendments, and suggestions from stakeholders regarding the new draft regulations.

[0514] The "Internet" is a communications network that interconnects computer networks around the world, enabling the sending and receiving of information.

[0515] "JSON format" stands for JavaScript Object Notation, a lightweight data exchange format that represents data as key-value pairs and is easy to read for both humans and machines.

[0516] An "internal intranet" is a dedicated network used within a company, built for the purpose of sharing internal information and communication.

[0517] A "database" is an information system that organizes and stores large amounts of data, enabling fast searching and access.

[0518] A "notification email" is an email sent to convey specific information, with the aim of quickly conveying the information to the recipient.

[0519] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, uses a generative AI model to automatically create draft regulations based on that amendment information, collects feedback from stakeholders, and automates the process of finalizing and publishing the draft internally. Specifically, the system is configured and operated as follows:

[0520] Legal information gathering

[0521] The server connects to the internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server retrieves information on revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's official website. The server analyzes the data and stores it in JSON format before passing it to the AI ​​model to generate the new content.

[0522] Draft generation

[0523] The server sends the saved JSON data of the legal amendment information to the generative AI model, which generates a new draft regulation based on the following prompt:

[0524] Please draft new working hours regulations based on the latest revisions to the Labor Standards Act.

[0525] The changes are as follows:

[0526] [Revision information]

[0527] The server receives the generated draft regulations and stores them in a database.

[0528] Comparison and Review

[0529] The server compares the new draft text with the existing policy using a text comparison tool, such as a diff tool, and the server highlights the changes in red, generating a document showing the changes.

[0530] Collecting feedback

[0531] The server sends new drafts and comparison documents to the stakeholders via email. The stakeholders receive the emails on their own devices and review the drafts and comparison documents. The stakeholders submit feedback via a web form or reply email. For example, feedback is collected when stakeholders access a web form, enter their feedback, and click the submit button.

[0532] Approval and publication

[0533] The user checks the feedback on the terminal and modifies the draft text as necessary. After the final draft is confirmed, the user presses the approval button. The server then publishes the approved draft text on the company intranet and sends an email to all employees to notify them.

[0534] History Management

[0535] The server stores and manages new regulations and their revision history in a database. Users with appropriate access rights can check the history of past revisions.

[0536] Specific examples

[0537] Example 1

[0538] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day. The acquired data is stored in JSON format, and the server analyzes it and passes the content to be created to the generative AI model. The generative AI model creates a draft of the "Working Hours Regulations" incorporating the revised parts, compares it with the current version, and highlights the changes in red.

[0539] Example 2

[0540] After a new draft is created, the server retrieves the email list of the HR department and sends it via email with the draft attached. HR personnel receive the email on their own devices, review it, and provide feedback via a web form. The HR manager checks the feedback, makes any necessary corrections, and approves the final draft. Once approved, the server publishes the policy on the company intranet and notifies all employees. In addition, the new policy and revision history are all stored in a database, allowing users to check past revisions at any time.

[0541] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0542] Step 1:

[0543] The server connects to the Internet at 3:00 AM every day and collects the latest legal revision information from legal databases and official websites. This collection is done using APIs. For example, information on revisions to the Labor Standards Act is obtained from the Ministry of Health, Labor and Welfare's API. The input is the API request, and the output is the obtained revision information in JSON format. The server analyzes this data and extracts the necessary revision information.

[0544] Step 2:

[0545] The server analyzes and formats the extracted revision information and converts it into a format that can be passed to the generative AI model. Specifically, it formats the revision information and generates a prompt text. The input is revision information in JSON format, and the output is the prompt text that is passed to the generative AI model. Example of a prompt text:

[0546] Please draft new working hours regulations based on the latest revisions to the Labor Standards Act.

[0547] The changes are as follows:

[0548] [Revision information]

[0549] The server sends this prompt to the generative AI model.

[0550] Step 3:

[0551] The generative AI model generates a new draft policy sentence based on the prompt sentence. The input is the generated prompt sentence, and the output is the new draft policy sentence. The generative AI model uses natural language processing techniques to do this. The server receives the generated draft sentence and stores it in a database.

[0552] Step 4:

[0553] The server compares the new draft text with the existing policy using a text comparison tool. The input is the new draft text and the existing policy, and the output is a comparison document with the changes highlighted. The server uses a text comparison tool (e.g., a diff tool) to identify the changes and generate a comparison document with the changes highlighted in red.

[0554] Step 5:

[0555] The server sends the new draft document and the comparison document to the participants by email. The input is the new draft document and the comparison document, and the output is an email to the participants. The participants receive the email on their own devices and review the draft document and the comparison document.

[0556] Step 6:

[0557] Stakeholders use their terminals to review the new draft and comparison documents and provide feedback. The input is the review and feedback of the stakeholders, and the output is the feedback received by the server. Stakeholders submit their feedback via a web form or reply email.

[0558] Step 7:

[0559] The user checks the feedback on the terminal and modifies the draft text as necessary. The input is feedback from the stakeholders, and the output is the modified final draft text. The user reflects the feedback and confirms the final draft text.

[0560] Step 8:

[0561] The user approves the final draft. When the user presses the approval button, the server publishes the approved draft on the company intranet and sends a notification email to all employees. The input is the approved final draft, and the output is publication on the company intranet and a notification email.

[0562] Step 9:

[0563] The server stores and manages new policies and their revision history in a database. The input is the new policy and its revision history, and the output is an entry stored in the database. Users with appropriate access rights can check the history of past revisions.

[0564] (Application example 1)

[0565] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0566] In large facilities such as factories, updating and managing regulations based on the latest legal revisions is extremely time-consuming. Manual updates are prone to errors and delays, resulting in uncertain compliance. Furthermore, a lack of efficient means of communication with stakeholders means gathering feedback and approving final proposals takes time. To solve these issues, there is a need for a system that automates the regulations management process and can quickly and accurately comply with the latest laws.

[0567] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0568] In this invention, the server includes means for connecting to a legal database and acquiring new legal revision information, means for analyzing and extracting the acquired legal revision information, means for automatically generating draft regulations based on the revision information extracted by the generation AI, means for comparing the generated new draft regulations with the current regulations and indicating changes, means for sending the new draft regulations to relevant parties using a screen device and collecting feedback from them, means for revising the draft regulations based on the feedback and publishing them on the network after approval, means for saving and managing the new regulations and their revision history in a storage device, and means for automatically adjusting machine operation based on the latest regulation information. This ensures that machines in the factory always operate in accordance with the latest safety regulations and ensures compliance with laws and regulations.

[0569] - "Legal Database" means an online system for storing and managing data including the latest laws and regulations.

[0570] "New Law Change Information" means the latest information on changes or additions to existing laws and regulations.

[0571] "Generative AI" is a technology that uses artificial intelligence to generate text and content based on specified conditions and data.

[0572] A "draft regulation" is a document that lists the rules and guidelines that a company or organization must follow.

[0573] "Stakeholders" are people or organizations that play a significant role in a particular project or task.

[0574] "Feedback" is an opinion or evaluation given in response to a specific content or action.

[0575] A "network" is a system in which multiple computers and devices are connected to each other and exchange and share data.

[0576] A "storage device" is an electronic device for storing data for long periods of time and retrieving it as needed.

[0577] "Machines" are devices or robots that perform work automatically.

[0578] To implement the present invention in a factory or the like, a design is first made based on the specific combination of hardware and software that constitutes the entire system. The main components of the present invention are a server, a terminal, a generative AI model, a storage device, a network, and machines.

[0579] First, the server connects to a legal database and periodically retrieves new legal revision information. To do this, the server collects data from official websites and APIs via the Internet. Legal revision information is often provided in JSON format, which the server parses and extracts the necessary revision information. This is done using Python's requests library and analysis processing library.

[0580] Next, the extracted revision information is passed to a generative AI model to automatically generate a new draft regulation text. The generative AI model uses OpenAI's GPT-3, among others. The generative AI model generates a new draft regulation text based on the following prompt:

[0581] Generate factory safety regulations based on the new Labor Standards Act:

[0582] New regulations...

[0583] The server compares the new draft text with the current version and highlights any changes. This process uses a text comparison tool, and changes are highlighted in red, allowing stakeholders to see the changes at a glance.

[0584] The new draft text is sent to the relevant parties using a display device. The relevant parties receive the draft text on their own devices (smartphones, tablets, etc.) and provide feedback. This feedback is collected via email and web forms. The server that collects the feedback then modifies the draft text based on that feedback and generates the final version of the draft regulations.

[0585] Once the final draft of the regulations has been approved by the relevant parties, it will be published on the network by the server. At this point, all users will be able to view the new regulations. The new regulations and their revision history will be saved in a storage device and managed so that they can be accessed at any time.

[0586] Furthermore, the system is equipped with a function that automatically adjusts machine operation based on the latest regulatory information, ensuring that factory machinery always operates in compliance with the latest safety regulations and ensuring compliance with laws and regulations.

[0587] As an example, let's consider the case of obtaining information about revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's API. In this case, the server periodically sends requests to the API, analyzes the obtained JSON data, and passes it to a generative AI model to generate a draft of new working hours regulations. The generated draft is then compared with the current version, and relevant parties are asked to review it via a screen device, and revisions and approvals are made based on the feedback. The final regulations are published on the network, and the machines in the factory automatically change their behavior in accordance with the regulations.

[0588] In this way, the present invention comprehensively realizes the rapid collection of legal information, the automatic generation of draft regulations, efficient communication with relevant parties, management of revision history, and the adjustment of machine operation based on that history, thereby greatly improving the efficiency of regulations management in factories and other facilities.

[0589] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0590] Step 1:

[0591] The server connects to the legal database via the Internet to obtain new legal revision information. Specifically, the server periodically sends requests to the legal database's API and receives JSON-formatted data containing legal revision information. The input is the API request, and the output is the obtained JSON data.

[0592] Step 2:

[0593] The server parses the acquired legal amendment information and extracts the necessary amendment information. In this process, a JSON parsing library is used to parse the data and extract the specific amendment content. The input is the acquired JSON data, and the output is text data containing the specific amendment information.

[0594] Step 3:

[0595] The server passes the revision information to the generative AI model and generates a new draft regulation text. The server provides the prompt text "Please generate factory safety regulations based on the new Labor Standards Act:- New regulation content..." and the generative AI model generates a new draft regulation text. The input is the revision information and the prompt text, and the output is the generated draft regulation text.

[0596] Step 4:

[0597] The server compares the generated new draft with the current regulations and highlights the changes. This is done using a text comparison tool, which highlights the changes in red. The input is the new draft and the current draft regulations, and the output is text data containing the comparison results.

[0598] Step 5:

[0599] The server sends the new draft to the relevant parties using a display device. Each party receives the new draft on their device (smartphone or tablet) and can review it. The input is the compared draft regulations, and the output is the state in which the review request has been sent.

[0600] Step 6:

[0601] Participants use their devices to return feedback. Feedback is sent via email or web forms and collected on a server. The input is the participant's feedback, and the output is the collected feedback data.

[0602] Step 7:

[0603] The server then modifies the draft policy text based on the collected feedback. If necessary, it re-uses the generative AI model to generate a revised draft policy text. The input is the collected feedback data, and the output is the final revised draft policy text.

[0604] Step 8:

[0605] Once the final draft is approved by the parties involved, the server publishes it on the network. The final draft is saved in a storage device and managed in a database. The input is the approved final draft, and the output is the published regulations and a saved revision history.

[0606] Step 9:

[0607] The server automatically adjusts machine operation based on the latest regulation information. The latest regulation information is provided as parameters to machines in the factory via the network, and machine settings and operation are automatically updated. The input is the latest regulation information, and the output is the adjusted machine operation.

[0608] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0609] This invention is a system that streamlines corporate regulations management, and in particular, by combining it with an emotion engine that recognizes user emotions, it enables more serious and precise feedback collection and processing. This system automatically obtains new legal amendment information from a legal database, automatically creates draft regulations based on that amendment information using a generative AI, collects and evaluates feedback from stakeholders via the emotion engine, and streamlines the process of finalizing and publishing the draft within the company.

[0610] Specifically, the system is configured and operated as follows:

[0611] Legal information gathering

[0612] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it obtains information on revisions to the Labor Standards Act from the official website of the Ministry of Health, Labor and Welfare.

[0613] Draft generation

[0614] The server passes the acquired revision information to the generation AI, which then uses that information to generate new draft regulations. For example, it creates "working hours regulations" based on the revisions to the Labor Standards Act.

[0615] Comparison and Review

[0616] The server compares the new draft text created by the AI ​​with the current regulations using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[0617] Collecting feedback

[0618] The server then emails the new draft to the interested parties, including an attachment of the draft and a link for review.

[0619] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[0620] The server collects feedback from participants and analyzes it with an emotion engine, which evaluates the emotional state of the user's feedback and determines its importance and reliability according to the emotional state.

[0621] Approval and publication

[0622] The user checks the feedback while referring to the evaluation results from the emotion engine and makes any necessary corrections. After the final draft is approved, the server publishes the regulations on the company intranet and notifies all employees.

[0623] History Management

[0624] The server stores new regulations and their revision history in a database and manages them so that they can be accessed at any time. Past revisions and their history can be easily tracked and confirmed.

[0625] Specific examples

[0626] Example 1

[0627] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format. The acquired data is analyzed and the revisions are sent to the generation AI. The generation AI generates a draft of the new "Working Hours Regulations," and the server compares the text with the current version. Changes are highlighted in red.

[0628] Example 2

[0629] After a new draft is created, the server emails it to the relevant parties, informing them that it requires review.

[0630] The users receive the emails on their devices, review the new draft text, and submit their feedback via a web form. The server then analyzes the feedback using an emotion engine to assess the importance and credibility of the feedback based on the user's emotional state.

[0631] Finally, users make revisions based on the feedback and evaluations and approve the regulations. The approved regulations are published on the company intranet via a server. All revision history is also stored in a database and can be accessed at any time.

[0632] This invention significantly improves the efficiency of corporate regulations management and contributes to strengthening compliance with laws and regulations and internal control by comprehensively achieving the rapid collection of legal information, automatic generation of draft texts, efficient communication with stakeholders and feedback evaluation, and revision history management. In addition, the combination of an emotion engine improves the quality of feedback and achieves more accurate regulations management.

[0633] The processing flow will be explained below.

[0634] Step 1:

[0635] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it uses the Ministry of Health, Labor and Welfare's API to obtain revision information for the Labor Standards Act in JSON format.

[0636] Step 2:

[0637] The server analyzes the legal amendment information it has acquired and extracts the necessary amendments. Text mining technology is used for the analysis to extract the main points of the amendment information.

[0638] Step 3:

[0639] The server sends the extracted revision information to the generation AI, which then automatically creates a new draft regulation based on the revision information. At this time, the generation AI generates a draft regulation that conforms to the company's existing regulation format.

[0640] Step 4:

[0641] The server compares the new draft text with the current version using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[0642] Step 5:

[0643] The server emails the new draft to interested parties, including an attachment of the draft and a review link that they can click to access a web form to provide their feedback.

[0644] Step 6:

[0645] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[0646] Step 7:

[0647] The server collects feedback from participants and sends it to the emotion engine, which analyzes the text of the feedback and evaluates the user's emotional state. For example, the emotion engine detects "dissatisfaction" or "question" from the feedback content.

[0648] Step 8:

[0649] The server receives the emotion evaluation results from the emotion engine and lists the importance and reliability of the feedback. At this time, it categorizes the feedback based on the evaluation of the emotional state and determines the processing order according to urgency and importance.

[0650] Step 9:

[0651] The user checks the feedback while referring to the evaluation results of the emotion engine and makes any necessary corrections. The user prioritizes checking feedback that the emotion engine indicates as "dissatisfied" and makes appropriate corrections.

[0652] Step 10:

[0653] The user reviews the final draft and gives their approval. Once approved, the server publishes the regulations on the company intranet and notifies all employees.

[0654] Step 11:

[0655] The server stores the new regulations and their revision history in a database, which is recorded in detail and managed so that it can be accessed at any time.

[0656] Specific examples

[0657] Step 1 example

[0658] The server obtains information on revisions to the Labor Standards Act through the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format.

[0659] Step 2: Example

[0660] The server uses text mining technology to analyze the revision details from the received JSON data and extract the necessary information.

[0661] Step 3 example

[0662] The server sends the extracted revision information to the generation AI, which then automatically generates a draft of the new "Work Hours Regulations." This draft is created according to the company's existing format.

[0663] Step 4: Example

[0664] The server compares the new draft with the current "Work Hours Regulations" using a text comparison tool and highlights the changes in red.

[0665] Step 5: Example

[0666] The server sends an email to the HR representative with the new draft attached and a link for review.

[0667] Step 6: Example

[0668] The human resources staff member who receives the email on the device reviews the draft text, enters the review results into a web form, and submits it.

[0669] Step 7 Example

[0670] The server sends the collected feedback to an emotion engine, which analyzes the text of the feedback to evaluate the user's emotional state.

[0671] Step 8 Example

[0672] The server lists the importance and reliability of the feedback based on the evaluation results of the emotion engine. For example, feedback rated as "unsatisfactory" is given priority.

[0673] Step 9 Example

[0674] The user checks the feedback and makes necessary corrections based on the evaluation results of the emotion engine. Feedback rated as "unsatisfactory" is addressed first.

[0675] Step 10: Example

[0676] The user checks the final draft and gives their approval. Once approved, the server publishes the regulations on the company intranet and notifies all employees.

[0677] Step 11 Example

[0678] The server stores new regulations and revision history in detail in a database and manages them so that users can access them at any time.

[0679] Example 2

[0680] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0681] For corporate regulations management, it is important to respond quickly to legal revisions. However, in many cases, collecting feedback from stakeholders and evaluating its content takes time, making efficient operation difficult. There is also a need for a method to improve the quality of feedback and make more appropriate revisions and approvals. To solve these issues, there is a need for a system that streamlines the entire process of automatically obtaining legal revision information, automatically generating draft regulations, and collecting and analyzing feedback, thereby enabling rapid and accurate regulation revisions.

[0682] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0683] In this invention, the server includes means for connecting to a legal database and acquiring new legal revision information, means for analyzing and extracting the acquired legal revision information, means for automatically generating draft regulations based on the revision information extracted by the generative AI model, means for comparing the generated new draft regulations with current regulations and indicating changes, means for sending the new draft regulations to stakeholders and collecting feedback, means for analyzing the feedback using an emotion engine and evaluating its importance and reliability, means for revising the draft regulations based on the feedback and publishing them internally after approval, and means for storing and managing the new regulations and their revision history in a database. This enables companies to respond quickly and accurately to legal revisions, improve the quality of feedback from stakeholders, and more appropriately revise and approve regulations.

[0684] A "legal database" is a database that stores the latest information on legal amendments and laws that will be enacted, and is accessible via the Internet.

[0685] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to automatically generate sentences and content based on input text data.

[0686] An "emotion engine" is software or an algorithm that analyzes the content of user feedback and evaluates its emotional state, importance, and reliability.

[0687] "Draft Regulations" means a draft of regulations prepared based on legal amendment information and other requirements.

[0688] A "text comparison tool" is software that compares different texts and highlights the changes.

[0689] A "database" is a computer system designed to store information systematically and allow rapid retrieval and access.

[0690] A "web form" is a form-filling feature built into a web page on the Internet, allowing users to enter and submit information.

[0691] "Email" is a means of communication for sending and receiving text messages and attachments over the Internet.

[0692] A "corporate intranet" is a private network used within an organization that uses Internet technology for the purpose of sharing and accessing internal information.

[0693] An "SMTP server" is a computer server that implements the Simple Mail Transfer Protocol, a protocol for sending email.

[0694] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, automatically creates draft regulations based on that amendment information using a generative AI model, collects and evaluates feedback from stakeholders using an emotion engine, and then finalizes and publishes the final draft, streamlining the process.

[0695] Legal information gathering

[0696] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server uses the Ministry of Health, Labor and Welfare's API to obtain revision information on the Labor Standards Act in JSON format. This obtained data is then analyzed within the system to extract the necessary information.

[0697] Draft generation

[0698] The server passes the acquired revision information to the generative AI model, which then generates a new draft of the regulations based on that information. An example of a prompt is, "Please generate a new draft of the working hours regulations based on the latest revision information of the Labor Standards Act." The generated draft is saved within the system and proceeds to the next step.

[0699] Comparison and Review

[0700] The server compares the generated new draft regulations with the current regulations using a text comparison tool. The changes are highlighted so that stakeholders can see them at a glance. The comparison results are saved as an HTML file and sent to stakeholders.

[0701] Collecting feedback

[0702] The server sends the new draft regulations to the relevant parties via email. The email contains an attachment of the draft regulations and a link for review. The relevant parties receive the email on their devices, check the attachment, and review it. They then enter the review results into a web form and submit it. The server collects feedback from the relevant parties and analyzes it using an emotion engine. The emotion engine evaluates the emotional state of the user's feedback and determines its importance and reliability based on that emotional state.

[0703] Approval and publication

[0704] The user checks the feedback based on the evaluation results from the emotion engine and makes any necessary revisions. After the final draft is approved, the server publishes the policy on the company intranet and notifies all employees. Notification is sent via email, and all employees can access the new policy.

[0705] History Management

[0706] The server stores the new regulations and their revision history in a database and manages them so that they can be accessed at any time, making it easy to track and check past revisions and their history.

[0707] Specific example explanation

[0708] For example, the server collects information on revisions to the Labor Standards Act through the Ministry of Health, Labor, and Welfare's API at 3:00 AM every day, analyzes the data, and sends a prompt to the generative AI model: "Please generate a new draft of the working hours regulations based on the latest revisions to the Labor Standards Act." The generative AI model generates a new draft, compares it with the current version using a text comparison tool, and highlights changes in red. The server then emails the new draft and the comparison results to relevant parties and accepts feedback. The relevant parties submit feedback on their devices, and the server analyzes it using an emotion engine. Finally, the user reviews the feedback, makes corrections and approvals, and the server publishes it on the company intranet. This process enables companies to manage regulations quickly and efficiently.

[0709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0710] Step 1:

[0711] Legal information gathering

[0712] The server connects to the Internet at a set time every day (e.g., 3:00 AM) and accesses legal databases and official websites. Specifically, the server retrieves revision information for the Labor Standards Act in JSON format from the Ministry of Health, Labor and Welfare's API.

[0713] Input: Legal database access information, API endpoint, query parameters

[0714] Output: Legal change information in JSON format

[0715] What it does: Sends an HTTP request, parses the response from the API, and saves it as JSON data.

[0716] Step 2:

[0717] Legal Information Analysis and Extraction

[0718] The server analyzes the acquired JSON-formatted legal amendment information and extracts the necessary amendment details. Specifically, it extracts the relevant legal provisions and their amendment details from the JSON data.

[0719] Input: Legal amendment information in JSON format

[0720] Output: Extracted data of revision details (text and object format containing necessary information)

[0721] What it does: It uses a JSON parser to parse the data and extract the values ​​of specific fields.

[0722] Step 3:

[0723] Automatic generation of draft regulations

[0724] The server sends the extracted revision details to the generation AI model. It instructs the model to generate a draft regulation using a prompt. The specific prompt is, "Please generate a draft of the new working hours regulations based on the latest revision information of the Labor Standards Act."

[0725] Input: Extracted revision data, prompt text

[0726] Output: Generated draft regulations (text format)

[0727] How it works: Sends an API request to the generative AI model and retrieves the generated text.

[0728] Step 4:

[0729] Comparison of the text of the old and new draft regulations

[0730] The server compares the generated new draft regulations with the current regulations using a text comparison tool, highlighting the changes.

[0731] Input: New regulation draft text, current regulation text

[0732] Output: Comparison results with highlighted changes (HTML or PDF format)

[0733] How it works: It uses a text comparison algorithm to calculate the differences and identify the changes, which are then highlighted in red.

[0734] Step 5:

[0735] Submitting a new rule proposal

[0736] The server will then email the generated comparison results and the new rule proposal to the relevant parties, including a link for review.

[0737] Input: Email addresses of relevant parties, new rule draft, comparison results, review link

[0738] Output: Email sent

[0739] What it does: Sends an email through an SMTP server, containing a text message and an attachment.

[0740] Step 6:

[0741] Collecting feedback

[0742] The relevant parties receive the email on their terminal, check the attachments, review the file, and then enter the review results into a web form and submit it.

[0743] Input: Incoming emails, attachments, and web form entries

[0744] Output: Feedback data sent

[0745] What it does: Open the attachment in your email client, check the contents, then fill out the form in your web browser.

[0746] Step 7:

[0747] Feedback Analysis

[0748] The server sends the collected feedback to the emotion engine for analysis, which evaluates the emotional state of the feedback.

[0749] Input: Feedback data

[0750] Output: Sentiment analysis results (score, evaluation comments)

[0751] Behavior: Sends feedback data to the Emotion Engine API and receives analysis results.

[0752] Step 8:

[0753] Review and correct feedback

[0754] The user checks the emotion engine's analysis results and makes any necessary corrections based on the feedback.

[0755] Input: Sentiment analysis results, feedback content

[0756] Output: Revised draft regulations

[0757] How it works: View feedback and ratings through the admin panel and make corrections using the editing tools.

[0758] Step 9:

[0759] Approval and publication of the final draft

[0760] The user checks and approves the final draft of the regulations. The server then publishes the approved draft on the company intranet and notifies all employees.

[0761] Input: Confirm the final draft regulations and give approval instructions

[0762] Output: Published regulations, notification to all employees

[0763] Operation: Approval is performed on the management screen, and the data is uploaded to the intranet and notified to all employees by email.

[0764] Step 10:

[0765] Saving revision history

[0766] The server stores the new rule draft and its revision history in a database.

[0767] Input: Final draft regulations, previous revision history

[0768] Output: Saved revision history data

[0769] Behavior: Performs an INSERT operation on the database and records the revision history.

[0770] (Application example 2)

[0771] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0772] The process of corporate policy management involves complex tasks such as manually processing large amounts of legal information, collecting and evaluating feedback from stakeholders, and publishing new policies in a timely manner, making it difficult to carry out efficiently. Furthermore, to improve the quality of feedback, it is also important to accurately grasp and evaluate users' emotional states. This calls for a system that enables more accurate policy management.

[0773] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0774] In this invention, the server includes: means for connecting to a legal database and acquiring information on new legal revisions; means for analyzing and extracting the acquired legal revision information; means for automatically generating draft regulations based on the revision information extracted by the generation AI; means for comparing the generated new draft regulations with current regulations and indicating changes; means for sending the new draft regulations to relevant parties and collecting feedback; means for revising the draft regulations based on the feedback and publishing them internally after approval; means for storing and managing the new regulations and their revision history in a database; means for periodically collecting the latest regulatory information on industrial safety and quality control; means for automatically generating new work procedures and regulations using the generation AI; means for comparing the generated new work procedures and regulations with current ones and indicating changes; means for analyzing feedback using an emotion engine and evaluating the importance and reliability of the feedback based on the emotional state; and means for finalizing and introducing the final draft regulations into the production line. This enables rapid acquisition and analysis of legal revision information, and enables efficient automatic generation of new draft regulations and work procedures using the generation AI. In addition, using an emotion engine improves the quality of feedback, enabling more accurate regulation management.

[0775] A "legal database" is a data storage system that systematically collects, stores, and makes accessible legal information.

[0776] "Legal amendment information" refers to various detailed information about newly enacted laws and amendments to existing laws.

[0777] "Generative AI" is a type of artificial intelligence that is a technology that automatically generates sentences and procedures based on given data and conditions.

[0778] A "draft regulation" is a formal draft document that lists the rules and procedures that must be followed within a company or organization.

[0779] The "emotion engine" is an artificial intelligence technology that analyzes the user's emotional state and evaluates the quality and importance of feedback based on that information.

[0780] "Feedback" refers to opinions and evaluations from stakeholders that are used to refine and modify new draft texts and procedures.

[0781] "Revision History" means information that keeps a record of all past changes and modifications and allows them to be tracked.

[0782] "Industrial safety" refers to rules and standards to ensure the health and safety of workers, and measures to minimize dangers in factories and work sites.

[0783] "Quality control" refers to planned and controlled activities to maintain and improve the quality of products and services.

[0784] A "production line" is a system that divides the manufacturing process in a factory or other facility to carry out continuous and efficient production.

[0785] This invention aims to improve the efficiency of a quality control system using factory robots. This system automatically generates procedures and rules to quickly respond to changes in laws and regulations, and includes an emotion engine to effectively collect and analyze feedback. Specific embodiments are described below.

[0786] System Configuration

[0787] The system consists of the following main elements:

[0788] 1. Server: This is the central hardware that manages and controls the entire system. The server connects to the Internet, retrieves the latest regulatory information from the legal database, and generates new work procedures using generative AI models.

[0789] 2. Generative AI: This is an artificial intelligence technology that generates new work procedures and rules. For example, OpenAI's GPT-3 model can be used.

[0790] 3. Emotion Engine: This is an artificial intelligence technology that analyzes feedback from stakeholders and evaluates their emotional state, determining the importance and credibility of the feedback.

[0791] 4. Database: A data storage system for storing and managing new regulations and their revision history.

[0792] Processing procedures and data calculations

[0793] Legal information gathering

[0794] The server collects the latest legal revision information from legal databases and official websites via the Internet, for example, periodically obtaining the latest regulatory information related to industrial safety and quality control.

[0795] Draft generation

[0796] The acquired legal amendment information is passed to a generative AI, which automatically generates new draft regulations and work procedures. A generative AI model (e.g., GPT-3) is used to generate new procedures using the following prompt sentence as input:

[0797] "Please generate new factory work procedures based on the following legal changes: 'According to new industrial safety regulations, the working time limit has changed. This means that working time in hazardous areas will now be limited to 6 hours per day. Please provide new work procedures.'"

[0798] Comparison and Review

[0799] The server compares the new draft text created by the AI ​​with the current regulations using a text comparison tool, highlighting the changes so that they are clearly visible to stakeholders.

[0800] Collecting feedback

[0801] The server sends new work instructions to stakeholders via email or web forms and collects feedback, which is analyzed using an emotion engine and rated for importance and credibility based on the emotional state.

[0802] Approval and publication

[0803] The server checks the feedback based on the evaluation results from the emotion engine and makes any necessary corrections. After the final proposal is approved, it will be implemented on the production line and the work procedures will be finalized.

[0804] History Management

[0805] The server stores new work procedures and their revision history in a database and manages them so that they can be accessed at any time. Past revisions and their history can be easily tracked and checked.

[0806] This enables the rapid acquisition and analysis of legal amendment information, and new draft regulations and work procedures are efficiently created through automatic generation using generative AI. In addition, the use of an emotion engine improves the quality of feedback, resulting in more accurate regulation management.

[0807] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0808] Step 1:

[0809] The server connects to the legal database to retrieve new legal amendment information. It receives data from the legal database API as input and stores the legal amendment information in JSON format as output. This data includes newly enacted laws and amendments to existing laws.

[0810] Step 2:

[0811] The server analyzes the acquired legal amendment information and extracts the necessary information. The input is the JSON of the legal amendment information acquired in step 1, and the output is the analyzed and extracted amendment information. The server extracts the necessary information using a text analysis tool and passes it to the generative AI model.

[0812] Step 3:

[0813] The server inputs the revision information into the generative AI, which then automatically generates new draft regulations and work procedures. The input is the analyzed revision information, and the output is the generated new draft regulations and work procedures. For example, the generative AI model (e.g., GPT-3) is given the following prompt:

[0814] "Please generate new factory work procedures based on the following legal changes: 'According to new industrial safety regulations, the working time limit has changed. This means that working time in hazardous areas will now be limited to 6 hours per day. Please provide new work procedures.'"

[0815] The generation AI generates a corresponding new procedure.

[0816] Step 4:

[0817] The server compares the generated new draft with the current policy using a text comparison tool. The input is the new draft and the current policy, and the output is text with the changes clearly marked. The server uses the text comparison tool to compare the old and new procedures and highlight the changes.

[0818] Step 5:

[0819] The server sends the new draft to stakeholders via email or a web form and collects their feedback. The input is the new draft with the changes highlighted, and the output is feedback from stakeholders. Stakeholders use their devices to send their opinions via email or a web form.

[0820] Step 6:

[0821] The server analyzes the collected feedback using an emotion engine. The input is the feedback from the stakeholders, and the output is an evaluation of the importance and credibility of the feedback based on its emotional state. The emotion engine analyzes the feedback text and extracts its emotional features.

[0822] Step 7:

[0823] The user refers to the feedback evaluation results from the emotion engine and modifies the new draft regulations and work procedures. The input is the emotion engine's evaluation results and feedback content, and the output is the final modified draft regulations and procedures. After making the necessary modifications, the user sends the finalized procedures to the server.

[0824] Step 8:

[0825] The server implements the approved new procedures on the production line. The input is the final revised draft or procedure, and the output is the procedure converted into a form that can be implemented on the production line. The server then uses an automated process to ensure that the new procedure is applied on the production line.

[0826] Step 9:

[0827] The server saves and manages new work procedures and their revision history in a database. The input is the final implemented work procedure and its history, and the output is the history saved in the database. The server periodically updates the database and manages it so that past revisions and history can be tracked and checked.

[0828] These are the specific processing steps of the system that realizes this application example. This process efficiently acquires information on legal changes, generates new procedures, collects and analyzes feedback, and implements the final procedures.

[0829] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0830] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0831] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0832] [Third embodiment]

[0833] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0834] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0835] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0836] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0837] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0838] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0839] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0840] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0841] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0842] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0843] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0844] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0845] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, automatically creates draft regulations based on the amendment information using a generative AI, collects feedback from stakeholders, finalizes the draft, and automates the process of publishing it internally.

[0846] Specifically, the system is configured and operated as follows:

[0847] Legal information gathering

[0848] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it obtains information on revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's official website.

[0849] Draft generation

[0850] The server passes the acquired revision information to the generation AI, which then uses that information to generate a new draft of the regulations. For example, it generates a new draft of the "Working Hours Regulations" that takes into account the revisions to the Labor Standards Act.

[0851] Comparison and Review

[0852] The server compares the new draft text created by the generative AI with the current regulations and uses text comparison tools to highlight the changes, making the changes visible at a glance and improving review efficiency.

[0853] Collecting feedback

[0854] The server emails the new draft to stakeholders, who then receive the emails on their own devices, review them, and provide feedback, which is collected through web forms and reply emails.

[0855] Approval and publication

[0856] The user checks the feedback, makes any necessary corrections, and finally approves the policy. The server then publishes the final version of the policy on the company intranet and notifies all employees.

[0857] History Management

[0858] The server stores the new regulations and their revision history in a database and manages them so that they can be accessed at any time. This makes it easy to track and check past revisions and their history.

[0859] Specific examples

[0860] Example 1

[0861] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day. The acquired data is in JSON format, which the server parses and passes to the generation AI the content to be created. The generation AI creates a draft of the "Working Hours Regulations" incorporating the revised parts, compares it with the current version, and highlights the changes in red.

[0862] Example 2

[0863] After a new draft is created, the server retrieves the email list of the HR department and sends an email with the draft attached. HR personnel receive the email on their own devices, review it, and provide feedback through a web form. The HR manager reviews the feedback, makes any necessary corrections, and approves the final draft.

[0864] Once the final draft is approved, the server publishes the policy on the company intranet and notifies all employees. The new policy and revision history are all stored in a database, so users can check past revisions at any time.

[0865] This invention comprehensively realizes the rapid collection of legal information, automatic generation of draft texts, efficient communication with stakeholders, and management of revision history, thereby significantly improving the efficiency of corporate regulation management and contributing to strengthening compliance with laws and regulations and internal control.

[0866] The processing flow will be explained below.

[0867] Step 1:

[0868] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server uses the Ministry of Health, Labor and Welfare's API to obtain revision information for the Labor Standards Act in JSON format.

[0869] Step 2:

[0870] The server analyzes the legal amendment information it has acquired and extracts the necessary amendments. Text mining technology is used for the analysis to extract the main points of the legal amendments.

[0871] Step 3:

[0872] The server sends the extracted revision information to the generation AI, which then automatically creates a new draft regulation based on the revision information. At this time, the generation AI generates a draft regulation that conforms to the company's existing regulation format.

[0873] Step 4:

[0874] The server compares the new draft text with the current version using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[0875] Step 5:

[0876] The server emails the new draft to interested parties, including an attachment of the draft and a review link that they can click to access a web form to provide their feedback.

[0877] Step 6:

[0878] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[0879] Step 7:

[0880] The server collects and aggregates feedback from stakeholders, automatically sorts it, and lists the necessary changes.

[0881] Step 8:

[0882] The user reviews the feedback and makes any necessary corrections. The user then makes a final check of the revised draft and decides whether to approve it.

[0883] Step 9:

[0884] The server publishes the final approved version of the regulations on the company intranet, which is then immediately notified to all employees.

[0885] Step 10:

[0886] The server stores the new regulations and their revision history in a database, which is recorded in detail and managed so that it can be accessed at any time.

[0887] Specific examples

[0888] Step 1 example

[0889] The server obtains information on revisions to the Labor Standards Act through the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format.

[0890] Step 2: Example

[0891] The server uses text mining technology to analyze the revised parts of the JSON data it receives and extracts the revised contents of the Labor Standards Act.

[0892] Step 3 example

[0893] The server sends the extracted revision information to the generation AI, which then generates a draft of the new "Work Hours Regulations." The draft text conforms to the company's existing format.

[0894] Step 4: Example

[0895] The server compares the new draft with the current version using a text comparison tool and highlights the revised parts in red.

[0896] Step 5: Example

[0897] The server sends an email to the HR representative with the new draft attached and a link for review.

[0898] Step 6: Example

[0899] The HR staff receives the email on the device, reviews the new draft text, and submits feedback via a web form.

[0900] Step 7 Example

[0901] The server collects all the feedback and organizes a list of necessary fixes.

[0902] Step 8 Example

[0903] The user then revises the draft based on the feedback, and then gives final approval.

[0904] Step 9 Example

[0905] The server publishes the approved regulations on the company intranet and notifies all employees by email.

[0906] Step 10: Example

[0907] The server stores new regulations and their revision history in a detailed database, allowing users to access past changes.

[0908] Example 1

[0909] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0910] Corporate regulation management requires a great deal of time and effort to deal with legal revisions and update internal regulations. The process of collecting information on legal revisions, drafting regulations, gathering feedback from stakeholders, and finally approving and publishing the final draft is particularly complex and requires efficient and accurate execution. However, current manual processes and partial automation make it difficult to fully meet the demands for regulatory compliance and strengthened internal controls. This leaves companies exposed to reduced operational efficiency and the risk of legal violations.

[0911] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0912] In this invention, the server includes: means for connecting to a legal database and acquiring new legal revision information; means for analyzing and extracting the acquired legal revision information; means for automatically generating draft regulations based on the revision information extracted by the generative AI model; means for comparing the generated new draft regulations with existing regulations and indicating changes; means for automatically periodically collecting legal revision information from the Internet; means for storing the collected legal revision information in JSON format; means for comparing the new draft regulations with existing regulations using a text comparison tool; means for visualizing the comparison results and generating a document indicating changes; means for sending the new draft regulations to relevant parties and collecting feedback; means for revising the draft regulations based on the feedback and publishing them internally after approval; means for saving and managing the new regulations and their revision history in a database; and means for publishing approved regulations on the company's intranet and notifying all employees. This significantly streamlines the entire corporate regulations management process, enabling enhanced compliance with laws and regulations and internal control.

[0913] A "legal database" is a database that stores laws, regulations, and amendments that can be accessed and searched as needed.

[0914] "Revision Information" means information that describes changes or updates to current laws and regulations.

[0915] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to automatically generate new documents based on provided information.

[0916] A "draft rule" is a document that documents the rules and policies that apply within a company and is used as a draft.

[0917] A "text comparison tool" is software that compares two documents and automatically identifies and highlights differences and changes.

[0918] "Feedback" refers to information including opinions, requests for amendments, and suggestions from stakeholders regarding the new draft regulations.

[0919] The "Internet" is a communications network that interconnects computer networks around the world, enabling the sending and receiving of information.

[0920] "JSON format" stands for JavaScript Object Notation, a lightweight data exchange format that represents data as key-value pairs and is easy to read for both humans and machines.

[0921] An "internal intranet" is a dedicated network used within a company, built for the purpose of sharing internal information and communication.

[0922] A "database" is an information system that organizes and stores large amounts of data, enabling fast searching and access.

[0923] A "notification email" is an email sent to convey specific information, with the aim of quickly conveying the information to the recipient.

[0924] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, uses a generative AI model to automatically create draft regulations based on that amendment information, collects feedback from stakeholders, and automates the process of finalizing and publishing the draft internally. Specifically, the system is configured and operated as follows:

[0925] Legal information gathering

[0926] The server connects to the internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server retrieves information on revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's official website. The server analyzes the data and stores it in JSON format before passing it to the AI ​​model to generate the new content.

[0927] Draft generation

[0928] The server sends the saved JSON data of the legal amendment information to the generative AI model, which generates a new draft regulation based on the following prompt:

[0929] Please draft new working hours regulations based on the latest revisions to the Labor Standards Act.

[0930] The changes are as follows:

[0931] [Revision information]

[0932] The server receives the generated draft regulations and stores them in a database.

[0933] Comparison and Review

[0934] The server compares the new draft text with the existing policy using a text comparison tool, such as a diff tool, and the server highlights the changes in red, generating a document showing the changes.

[0935] Collecting feedback

[0936] The server sends new drafts and comparison documents to the stakeholders via email. The stakeholders receive the emails on their own devices and review the drafts and comparison documents. The stakeholders submit feedback via a web form or reply email. For example, feedback is collected when stakeholders access a web form, enter their feedback, and click the submit button.

[0937] Approval and publication

[0938] The user checks the feedback on the terminal and modifies the draft text as necessary. After the final draft is confirmed, the user presses the approval button. The server then publishes the approved draft text on the company intranet and sends an email to all employees to notify them.

[0939] History Management

[0940] The server stores and manages new regulations and their revision history in a database. Users with appropriate access rights can check the history of past revisions.

[0941] Specific examples

[0942] Example 1

[0943] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day. The acquired data is stored in JSON format, and the server analyzes it and passes the content to be created to the generative AI model. The generative AI model creates a draft of the "Working Hours Regulations" incorporating the revised parts, compares it with the current version, and highlights the changes in red.

[0944] Example 2

[0945] After a new draft is created, the server retrieves the email list of the HR department and sends it via email with the draft attached. HR personnel receive the email on their own devices, review it, and provide feedback via a web form. The HR manager checks the feedback, makes any necessary corrections, and approves the final draft. Once approved, the server publishes the policy on the company intranet and notifies all employees. In addition, the new policy and revision history are all stored in a database, allowing users to check past revisions at any time.

[0946] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0947] Step 1:

[0948] The server connects to the Internet at 3:00 AM every day and collects the latest legal revision information from legal databases and official websites. This collection is done using APIs. For example, information on revisions to the Labor Standards Act is obtained from the Ministry of Health, Labor and Welfare's API. The input is the API request, and the output is the obtained revision information in JSON format. The server analyzes this data and extracts the necessary revision information.

[0949] Step 2:

[0950] The server analyzes and formats the extracted revision information and converts it into a format that can be passed to the generative AI model. Specifically, it formats the revision information and generates a prompt text. The input is revision information in JSON format, and the output is the prompt text that is passed to the generative AI model. Example of a prompt text:

[0951] Please draft new working hours regulations based on the latest revisions to the Labor Standards Act.

[0952] The changes are as follows:

[0953] [Revision information]

[0954] The server sends this prompt to the generative AI model.

[0955] Step 3:

[0956] The generative AI model generates a new draft policy sentence based on the prompt sentence. The input is the generated prompt sentence, and the output is the new draft policy sentence. The generative AI model uses natural language processing techniques to do this. The server receives the generated draft sentence and stores it in a database.

[0957] Step 4:

[0958] The server compares the new draft text with the existing policy using a text comparison tool. The input is the new draft text and the existing policy, and the output is a comparison document with the changes highlighted. The server uses a text comparison tool (e.g., a diff tool) to identify the changes and generate a comparison document with the changes highlighted in red.

[0959] Step 5:

[0960] The server sends the new draft document and the comparison document to the participants by email. The input is the new draft document and the comparison document, and the output is an email to the participants. The participants receive the email on their own devices and review the draft document and the comparison document.

[0961] Step 6:

[0962] Stakeholders use their terminals to review the new draft and comparison documents and provide feedback. The input is the review and feedback of the stakeholders, and the output is the feedback received by the server. Stakeholders submit their feedback via a web form or reply email.

[0963] Step 7:

[0964] The user checks the feedback on the terminal and modifies the draft text as necessary. The input is feedback from the stakeholders, and the output is the modified final draft text. The user reflects the feedback and confirms the final draft text.

[0965] Step 8:

[0966] The user approves the final draft. When the user presses the approval button, the server publishes the approved draft on the company intranet and sends a notification email to all employees. The input is the approved final draft, and the output is publication on the company intranet and a notification email.

[0967] Step 9:

[0968] The server stores and manages new policies and their revision history in a database. The input is the new policy and its revision history, and the output is an entry stored in the database. Users with appropriate access rights can check the history of past revisions.

[0969] (Application example 1)

[0970] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0971] In large facilities such as factories, updating and managing regulations based on the latest legal revisions is extremely time-consuming. Manual updates are prone to errors and delays, resulting in uncertain compliance. Furthermore, a lack of efficient means of communication with stakeholders means gathering feedback and approving final proposals takes time. To solve these issues, there is a need for a system that automates the regulations management process and can quickly and accurately comply with the latest laws.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0973] In this invention, the server includes means for connecting to a legal database and acquiring new legal revision information, means for analyzing and extracting the acquired legal revision information, means for automatically generating draft regulations based on the revision information extracted by the generation AI, means for comparing the generated new draft regulations with the current regulations and indicating changes, means for sending the new draft regulations to relevant parties using a screen device and collecting feedback from them, means for revising the draft regulations based on the feedback and publishing them on the network after approval, means for saving and managing the new regulations and their revision history in a storage device, and means for automatically adjusting machine operation based on the latest regulation information. This ensures that machines in the factory always operate in accordance with the latest safety regulations and ensures compliance with laws and regulations.

[0974] - "Legal Database" means an online system for storing and managing data including the latest laws and regulations.

[0975] "New Law Change Information" means the latest information on changes or additions to existing laws and regulations.

[0976] "Generative AI" is a technology that uses artificial intelligence to generate text and content based on specified conditions and data.

[0977] A "draft regulation" is a document that lists the rules and guidelines that a company or organization must follow.

[0978] "Stakeholders" are people or organizations that play a significant role in a particular project or task.

[0979] "Feedback" is an opinion or evaluation given in response to a specific content or action.

[0980] A "network" is a system in which multiple computers and devices are connected to each other and exchange and share data.

[0981] A "storage device" is an electronic device for storing data for long periods of time and retrieving it as needed.

[0982] "Machines" are devices or robots that perform work automatically.

[0983] To implement the present invention in a factory or the like, a design is first made based on the specific combination of hardware and software that constitutes the entire system. The main components of the present invention are a server, a terminal, a generative AI model, a storage device, a network, and machines.

[0984] First, the server connects to a legal database and periodically retrieves new legal revision information. To do this, the server collects data from official websites and APIs via the Internet. Legal revision information is often provided in JSON format, which the server parses and extracts the necessary revision information. This is done using Python's requests library and analysis processing library.

[0985] Next, the extracted revision information is passed to a generative AI model to automatically generate a new draft regulation text. The generative AI model uses OpenAI's GPT-3, among others. The generative AI model generates a new draft regulation text based on the following prompt:

[0986] Generate factory safety regulations based on the new Labor Standards Act:

[0987] New regulations...

[0988] The server compares the new draft text with the current version and highlights any changes. This process uses a text comparison tool, and changes are highlighted in red, allowing stakeholders to see the changes at a glance.

[0989] The new draft text is sent to the relevant parties using a display device. The relevant parties receive the draft text on their own devices (smartphones, tablets, etc.) and provide feedback. This feedback is collected via email and web forms. The server that collects the feedback then modifies the draft text based on that feedback and generates the final version of the draft regulations.

[0990] Once the final draft of the regulations has been approved by the relevant parties, it will be published on the network by the server. At this point, all users will be able to view the new regulations. The new regulations and their revision history will be saved in a storage device and managed so that they can be accessed at any time.

[0991] Furthermore, the system is equipped with a function that automatically adjusts machine operation based on the latest regulatory information, ensuring that factory machinery always operates in compliance with the latest safety regulations and ensuring compliance with laws and regulations.

[0992] As an example, let's consider the case of obtaining information about revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's API. In this case, the server periodically sends requests to the API, analyzes the obtained JSON data, and passes it to a generative AI model to generate a draft of new working hours regulations. The generated draft is then compared with the current version, and relevant parties are asked to review it via a screen device, and revisions and approvals are made based on the feedback. The final regulations are published on the network, and the machines in the factory automatically change their behavior in accordance with the regulations.

[0993] In this way, the present invention comprehensively realizes the rapid collection of legal information, the automatic generation of draft regulations, efficient communication with relevant parties, management of revision history, and the adjustment of machine operation based on that history, thereby greatly improving the efficiency of regulations management in factories and other facilities.

[0994] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0995] Step 1:

[0996] The server connects to the legal database via the Internet to obtain new legal revision information. Specifically, the server periodically sends requests to the legal database's API and receives JSON-formatted data containing legal revision information. The input is the API request, and the output is the obtained JSON data.

[0997] Step 2:

[0998] The server parses the acquired legal amendment information and extracts the necessary amendment information. In this process, a JSON parsing library is used to parse the data and extract the specific amendment content. The input is the acquired JSON data, and the output is text data containing the specific amendment information.

[0999] Step 3:

[1000] The server passes the revision information to the generative AI model and generates a new draft regulation text. The server provides the prompt text "Please generate factory safety regulations based on the new Labor Standards Act:- New regulation content..." and the generative AI model generates a new draft regulation text. The input is the revision information and the prompt text, and the output is the generated draft regulation text.

[1001] Step 4:

[1002] The server compares the generated new draft with the current regulations and highlights the changes. This is done using a text comparison tool, which highlights the changes in red. The input is the new draft and the current draft regulations, and the output is text data containing the comparison results.

[1003] Step 5:

[1004] The server sends the new draft to the relevant parties using a display device. Each party receives the new draft on their device (smartphone or tablet) and can review it. The input is the compared draft regulations, and the output is the state in which the review request has been sent.

[1005] Step 6:

[1006] Participants use their devices to return feedback. Feedback is sent via email or web forms and collected on a server. The input is the participant's feedback, and the output is the collected feedback data.

[1007] Step 7:

[1008] The server then modifies the draft policy text based on the collected feedback. If necessary, it re-uses the generative AI model to generate a revised draft policy text. The input is the collected feedback data, and the output is the final revised draft policy text.

[1009] Step 8:

[1010] Once the final draft is approved by the parties involved, the server publishes it on the network. The final draft is saved in a storage device and managed in a database. The input is the approved final draft, and the output is the published regulations and a saved revision history.

[1011] Step 9:

[1012] The server automatically adjusts machine operation based on the latest regulation information. The latest regulation information is provided as parameters to machines in the factory via the network, and machine settings and operation are automatically updated. The input is the latest regulation information, and the output is the adjusted machine operation.

[1013] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1014] This invention is a system that streamlines corporate regulations management, and in particular, by combining it with an emotion engine that recognizes user emotions, it enables more serious and precise feedback collection and processing. This system automatically obtains new legal amendment information from a legal database, automatically creates draft regulations based on that amendment information using a generative AI, collects and evaluates feedback from stakeholders via the emotion engine, and streamlines the process of finalizing and publishing the draft within the company.

[1015] Specifically, the system is configured and operated as follows:

[1016] Legal information gathering

[1017] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it obtains information on revisions to the Labor Standards Act from the official website of the Ministry of Health, Labor and Welfare.

[1018] Draft generation

[1019] The server passes the acquired revision information to the generation AI, which then uses that information to generate new draft regulations. For example, it creates "working hours regulations" based on the revisions to the Labor Standards Act.

[1020] Comparison and Review

[1021] The server compares the new draft text created by the AI ​​with the current regulations using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[1022] Collecting feedback

[1023] The server then emails the new draft to the interested parties, including an attachment of the draft and a link for review.

[1024] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[1025] The server collects feedback from participants and analyzes it with an emotion engine, which evaluates the emotional state of the user's feedback and determines its importance and reliability according to the emotional state.

[1026] Approval and publication

[1027] The user checks the feedback while referring to the evaluation results from the emotion engine and makes any necessary corrections. After the final draft is approved, the server publishes the regulations on the company intranet and notifies all employees.

[1028] History Management

[1029] The server stores new regulations and their revision history in a database and manages them so that they can be accessed at any time. Past revisions and their history can be easily tracked and confirmed.

[1030] Specific examples

[1031] Example 1

[1032] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format. The acquired data is analyzed and the revisions are sent to the generation AI. The generation AI generates a draft of the new "Working Hours Regulations," and the server compares the text with the current version. Changes are highlighted in red.

[1033] Example 2

[1034] After a new draft is created, the server emails it to the relevant parties, informing them that it requires review.

[1035] The users receive the emails on their devices, review the new draft text, and submit their feedback via a web form. The server then analyzes the feedback using an emotion engine to assess the importance and credibility of the feedback based on the user's emotional state.

[1036] Finally, users make revisions based on the feedback and evaluations and approve the regulations. The approved regulations are published on the company intranet via a server. All revision history is also stored in a database and can be accessed at any time.

[1037] This invention significantly improves the efficiency of corporate regulations management and contributes to strengthening compliance with laws and regulations and internal control by comprehensively achieving the rapid collection of legal information, automatic generation of draft texts, efficient communication with stakeholders and feedback evaluation, and revision history management. In addition, the combination of an emotion engine improves the quality of feedback and achieves more accurate regulations management.

[1038] The processing flow will be explained below.

[1039] Step 1:

[1040] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it uses the Ministry of Health, Labor and Welfare's API to obtain revision information for the Labor Standards Act in JSON format.

[1041] Step 2:

[1042] The server analyzes the legal amendment information it has acquired and extracts the necessary amendments. Text mining technology is used for the analysis to extract the main points of the amendment information.

[1043] Step 3:

[1044] The server sends the extracted revision information to the generation AI, which then automatically creates a new draft regulation based on the revision information. At this time, the generation AI generates a draft regulation that conforms to the company's existing regulation format.

[1045] Step 4:

[1046] The server compares the new draft text with the current version using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[1047] Step 5:

[1048] The server emails the new draft to interested parties, including an attachment of the draft and a review link that they can click to access a web form to provide their feedback.

[1049] Step 6:

[1050] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[1051] Step 7:

[1052] The server collects feedback from participants and sends it to the emotion engine, which analyzes the text of the feedback and evaluates the user's emotional state. For example, the emotion engine detects "dissatisfaction" or "question" from the feedback content.

[1053] Step 8:

[1054] The server receives the emotion evaluation results from the emotion engine and lists the importance and reliability of the feedback. At this time, it categorizes the feedback based on the evaluation of the emotional state and determines the processing order according to urgency and importance.

[1055] Step 9:

[1056] The user checks the feedback while referring to the evaluation results of the emotion engine and makes any necessary corrections. The user prioritizes checking feedback that the emotion engine indicates as "dissatisfied" and makes appropriate corrections.

[1057] Step 10:

[1058] The user reviews the final draft and gives their approval. Once approved, the server publishes the regulations on the company intranet and notifies all employees.

[1059] Step 11:

[1060] The server stores the new regulations and their revision history in a database, which is recorded in detail and managed so that it can be accessed at any time.

[1061] Specific examples

[1062] Step 1 example

[1063] The server obtains information on revisions to the Labor Standards Act through the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format.

[1064] Step 2: Example

[1065] The server uses text mining technology to analyze the revision details from the received JSON data and extract the necessary information.

[1066] Step 3 example

[1067] The server sends the extracted revision information to the generation AI, which then automatically generates a draft of the new "Work Hours Regulations." This draft is created according to the company's existing format.

[1068] Step 4: Example

[1069] The server compares the new draft with the current "Work Hours Regulations" using a text comparison tool and highlights the changes in red.

[1070] Step 5: Example

[1071] The server sends an email to the HR representative with the new draft attached and a link for review.

[1072] Step 6: Example

[1073] The human resources staff member who receives the email on the device reviews the draft text, enters the review results into a web form, and submits it.

[1074] Step 7 Example

[1075] The server sends the collected feedback to an emotion engine, which analyzes the text of the feedback to evaluate the user's emotional state.

[1076] Step 8 Example

[1077] The server lists the importance and reliability of the feedback based on the evaluation results of the emotion engine. For example, feedback rated as "unsatisfactory" is given priority.

[1078] Step 9 Example

[1079] The user checks the feedback and makes necessary corrections based on the evaluation results of the emotion engine. Feedback rated as "unsatisfactory" is addressed first.

[1080] Step 10: Example

[1081] The user checks the final draft and gives their approval. Once approved, the server publishes the regulations on the company intranet and notifies all employees.

[1082] Step 11 Example

[1083] The server stores new regulations and revision history in detail in a database and manages them so that users can access them at any time.

[1084] Example 2

[1085] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1086] For corporate regulations management, it is important to respond quickly to legal revisions. However, in many cases, collecting feedback from stakeholders and evaluating its content takes time, making efficient operation difficult. There is also a need for a method to improve the quality of feedback and make more appropriate revisions and approvals. To solve these issues, there is a need for a system that streamlines the entire process of automatically obtaining legal revision information, automatically generating draft regulations, and collecting and analyzing feedback, thereby enabling rapid and accurate regulation revisions.

[1087] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1088] In this invention, the server includes means for connecting to a legal database and acquiring new legal revision information, means for analyzing and extracting the acquired legal revision information, means for automatically generating draft regulations based on the revision information extracted by the generative AI model, means for comparing the generated new draft regulations with current regulations and indicating changes, means for sending the new draft regulations to stakeholders and collecting feedback, means for analyzing the feedback using an emotion engine and evaluating its importance and reliability, means for revising the draft regulations based on the feedback and publishing them internally after approval, and means for storing and managing the new regulations and their revision history in a database. This enables companies to respond quickly and accurately to legal revisions, improve the quality of feedback from stakeholders, and more appropriately revise and approve regulations.

[1089] A "legal database" is a database that stores the latest information on legal amendments and laws that will be enacted, and is accessible via the Internet.

[1090] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to automatically generate sentences and content based on input text data.

[1091] An "emotion engine" is software or an algorithm that analyzes the content of user feedback and evaluates its emotional state, importance, and reliability.

[1092] "Draft Regulations" means a draft of regulations prepared based on legal amendment information and other requirements.

[1093] A "text comparison tool" is software that compares different texts and highlights the changes.

[1094] A "database" is a computer system designed to store information systematically and allow rapid retrieval and access.

[1095] A "web form" is a form-filling feature built into a web page on the Internet, allowing users to enter and submit information.

[1096] "Email" is a means of communication for sending and receiving text messages and attachments over the Internet.

[1097] A "corporate intranet" is a private network used within an organization that uses Internet technology for the purpose of sharing and accessing internal information.

[1098] An "SMTP server" is a computer server that implements the Simple Mail Transfer Protocol, a protocol for sending email.

[1099] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, automatically creates draft regulations based on that amendment information using a generative AI model, collects and evaluates feedback from stakeholders using an emotion engine, and then finalizes and publishes the final draft, streamlining the process.

[1100] Legal information gathering

[1101] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server uses the Ministry of Health, Labor and Welfare's API to obtain revision information on the Labor Standards Act in JSON format. This obtained data is then analyzed within the system to extract the necessary information.

[1102] Draft generation

[1103] The server passes the acquired revision information to the generative AI model, which then generates a new draft of the regulations based on that information. An example of a prompt is, "Please generate a new draft of the working hours regulations based on the latest revision information of the Labor Standards Act." The generated draft is saved within the system and proceeds to the next step.

[1104] Comparison and Review

[1105] The server compares the generated new draft regulations with the current regulations using a text comparison tool. The changes are highlighted so that stakeholders can see them at a glance. The comparison results are saved as an HTML file and sent to stakeholders.

[1106] Collecting feedback

[1107] The server sends the new draft regulations to the relevant parties via email. The email contains an attachment of the draft regulations and a link for review. The relevant parties receive the email on their devices, check the attachment, and review it. They then enter the review results into a web form and submit it. The server collects feedback from the relevant parties and analyzes it using an emotion engine. The emotion engine evaluates the emotional state of the user's feedback and determines its importance and reliability based on that emotional state.

[1108] Approval and publication

[1109] The user checks the feedback based on the evaluation results from the emotion engine and makes any necessary revisions. After the final draft is approved, the server publishes the policy on the company intranet and notifies all employees. Notification is sent via email, and all employees can access the new policy.

[1110] History Management

[1111] The server stores the new regulations and their revision history in a database and manages them so that they can be accessed at any time, making it easy to track and check past revisions and their history.

[1112] Specific example explanation

[1113] For example, the server collects information on revisions to the Labor Standards Act through the Ministry of Health, Labor, and Welfare's API at 3:00 AM every day, analyzes the data, and sends a prompt to the generative AI model: "Please generate a new draft of the working hours regulations based on the latest revisions to the Labor Standards Act." The generative AI model generates a new draft, compares it with the current version using a text comparison tool, and highlights changes in red. The server then emails the new draft and the comparison results to relevant parties and accepts feedback. The relevant parties submit feedback on their devices, and the server analyzes it using an emotion engine. Finally, the user reviews the feedback, makes corrections and approvals, and the server publishes it on the company intranet. This process enables companies to manage regulations quickly and efficiently.

[1114] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1115] Step 1:

[1116] Legal information gathering

[1117] The server connects to the Internet at a set time every day (e.g., 3:00 AM) and accesses legal databases and official websites. Specifically, the server retrieves revision information for the Labor Standards Act in JSON format from the Ministry of Health, Labor and Welfare's API.

[1118] Input: Legal database access information, API endpoint, query parameters

[1119] Output: Legal change information in JSON format

[1120] What it does: Sends an HTTP request, parses the response from the API, and saves it as JSON data.

[1121] Step 2:

[1122] Legal Information Analysis and Extraction

[1123] The server analyzes the acquired JSON-formatted legal amendment information and extracts the necessary amendment details. Specifically, it extracts the relevant legal provisions and their amendment details from the JSON data.

[1124] Input: Legal amendment information in JSON format

[1125] Output: Extracted data of revision details (text and object format containing necessary information)

[1126] What it does: It uses a JSON parser to parse the data and extract the values ​​of specific fields.

[1127] Step 3:

[1128] Automatic generation of draft regulations

[1129] The server sends the extracted revision details to the generation AI model. It instructs the model to generate a draft regulation using a prompt. The specific prompt is, "Please generate a draft of the new working hours regulations based on the latest revision information of the Labor Standards Act."

[1130] Input: Extracted revision data, prompt text

[1131] Output: Generated draft regulations (text format)

[1132] How it works: Sends an API request to the generative AI model and retrieves the generated text.

[1133] Step 4:

[1134] Comparison of the text of the old and new draft regulations

[1135] The server compares the generated new draft regulations with the current regulations using a text comparison tool, highlighting the changes.

[1136] Input: New regulation draft text, current regulation text

[1137] Output: Comparison results with highlighted changes (HTML or PDF format)

[1138] How it works: It uses a text comparison algorithm to calculate the differences and identify the changes, which are then highlighted in red.

[1139] Step 5:

[1140] Submitting a new rule proposal

[1141] The server will then email the generated comparison results and the new rule proposal to the relevant parties, including a link for review.

[1142] Input: Email addresses of relevant parties, new rule draft, comparison results, review link

[1143] Output: Email sent

[1144] What it does: Sends an email through an SMTP server, containing a text message and an attachment.

[1145] Step 6:

[1146] Collecting feedback

[1147] The relevant parties receive the email on their terminal, check the attachments, review the file, and then enter the review results into a web form and submit it.

[1148] Input: Incoming emails, attachments, and web form entries

[1149] Output: Feedback data sent

[1150] What it does: Open the attachment in your email client, check the contents, then fill out the form in your web browser.

[1151] Step 7:

[1152] Feedback Analysis

[1153] The server sends the collected feedback to the emotion engine for analysis, which evaluates the emotional state of the feedback.

[1154] Input: Feedback data

[1155] Output: Sentiment analysis results (score, evaluation comments)

[1156] Behavior: Sends feedback data to the Emotion Engine API and receives analysis results.

[1157] Step 8:

[1158] Review and correct feedback

[1159] The user checks the emotion engine's analysis results and makes any necessary corrections based on the feedback.

[1160] Input: Sentiment analysis results, feedback content

[1161] Output: Revised draft regulations

[1162] How it works: View feedback and ratings through the admin panel and make corrections using the editing tools.

[1163] Step 9:

[1164] Approval and publication of the final draft

[1165] The user checks and approves the final draft of the regulations. The server then publishes the approved draft on the company intranet and notifies all employees.

[1166] Input: Confirm the final draft regulations and give approval instructions

[1167] Output: Published regulations, notification to all employees

[1168] Operation: Approval is performed on the management screen, and the data is uploaded to the intranet and notified to all employees by email.

[1169] Step 10:

[1170] Saving revision history

[1171] The server stores the new rule draft and its revision history in a database.

[1172] Input: Final draft regulations, previous revision history

[1173] Output: Saved revision history data

[1174] Behavior: Performs an INSERT operation on the database and records the revision history.

[1175] (Application example 2)

[1176] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1177] The process of corporate policy management involves complex tasks such as manually processing large amounts of legal information, collecting and evaluating feedback from stakeholders, and publishing new policies in a timely manner, making it difficult to carry out efficiently. Furthermore, to improve the quality of feedback, it is also important to accurately grasp and evaluate users' emotional states. This calls for a system that enables more accurate policy management.

[1178] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1179] In this invention, the server includes: means for connecting to a legal database and acquiring information on new legal revisions; means for analyzing and extracting the acquired legal revision information; means for automatically generating draft regulations based on the revision information extracted by the generation AI; means for comparing the generated new draft regulations with current regulations and indicating changes; means for sending the new draft regulations to relevant parties and collecting feedback; means for revising the draft regulations based on the feedback and publishing them internally after approval; means for storing and managing the new regulations and their revision history in a database; means for periodically collecting the latest regulatory information on industrial safety and quality control; means for automatically generating new work procedures and regulations using the generation AI; means for comparing the generated new work procedures and regulations with current ones and indicating changes; means for analyzing feedback using an emotion engine and evaluating the importance and reliability of the feedback based on the emotional state; and means for finalizing and introducing the final draft regulations into the production line. This enables rapid acquisition and analysis of legal revision information, and enables efficient automatic generation of new draft regulations and work procedures using the generation AI. In addition, using an emotion engine improves the quality of feedback, enabling more accurate regulation management.

[1180] A "legal database" is a data storage system that systematically collects, stores, and makes accessible legal information.

[1181] "Legal amendment information" refers to various detailed information about newly enacted laws and amendments to existing laws.

[1182] "Generative AI" is a type of artificial intelligence that is a technology that automatically generates sentences and procedures based on given data and conditions.

[1183] A "draft regulation" is a formal draft document that lists the rules and procedures that must be followed within a company or organization.

[1184] The "emotion engine" is an artificial intelligence technology that analyzes the user's emotional state and evaluates the quality and importance of feedback based on that information.

[1185] "Feedback" refers to opinions and evaluations from stakeholders that are used to refine and modify new draft texts and procedures.

[1186] "Revision History" means information that keeps a record of all past changes and modifications and allows them to be tracked.

[1187] "Industrial safety" refers to rules and standards to ensure the health and safety of workers, and measures to minimize dangers in factories and work sites.

[1188] "Quality control" refers to planned and controlled activities to maintain and improve the quality of products and services.

[1189] A "production line" is a system that divides the manufacturing process in a factory or other facility to carry out continuous and efficient production.

[1190] This invention aims to improve the efficiency of a quality control system using factory robots. This system automatically generates procedures and rules to quickly respond to changes in laws and regulations, and includes an emotion engine to effectively collect and analyze feedback. Specific embodiments are described below.

[1191] System Configuration

[1192] The system consists of the following main elements:

[1193] 1. Server: This is the central hardware that manages and controls the entire system. The server connects to the Internet, retrieves the latest regulatory information from the legal database, and generates new work procedures using generative AI models.

[1194] 2. Generative AI: This is an artificial intelligence technology that generates new work procedures and rules. For example, OpenAI's GPT-3 model can be used.

[1195] 3. Emotion Engine: This is an artificial intelligence technology that analyzes feedback from stakeholders and evaluates their emotional state, determining the importance and credibility of the feedback.

[1196] 4. Database: A data storage system for storing and managing new regulations and their revision history.

[1197] Processing procedures and data calculations

[1198] Legal information gathering

[1199] The server collects the latest legal revision information from legal databases and official websites via the Internet, for example, periodically obtaining the latest regulatory information related to industrial safety and quality control.

[1200] Draft generation

[1201] The acquired legal amendment information is passed to a generative AI, which automatically generates new draft regulations and work procedures. A generative AI model (e.g., GPT-3) is used to generate new procedures using the following prompt sentence as input:

[1202] "Please generate new factory work procedures based on the following legal changes: 'According to new industrial safety regulations, the working time limit has changed. This means that working time in hazardous areas will now be limited to 6 hours per day. Please provide new work procedures.'"

[1203] Comparison and Review

[1204] The server compares the new draft text created by the AI ​​with the current regulations using a text comparison tool, highlighting the changes so that they are clearly visible to stakeholders.

[1205] Collecting feedback

[1206] The server sends new work instructions to stakeholders via email or web forms and collects feedback, which is analyzed using an emotion engine and rated for importance and credibility based on the emotional state.

[1207] Approval and publication

[1208] The server checks the feedback based on the evaluation results from the emotion engine and makes any necessary corrections. After the final proposal is approved, it will be implemented on the production line and the work procedures will be finalized.

[1209] History Management

[1210] The server stores new work procedures and their revision history in a database and manages them so that they can be accessed at any time. Past revisions and their history can be easily tracked and checked.

[1211] This enables the rapid acquisition and analysis of legal amendment information, and new draft regulations and work procedures are efficiently created through automatic generation using generative AI. In addition, the use of an emotion engine improves the quality of feedback, resulting in more accurate regulation management.

[1212] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1213] Step 1:

[1214] The server connects to the legal database to retrieve new legal amendment information. It receives data from the legal database API as input and stores the legal amendment information in JSON format as output. This data includes newly enacted laws and amendments to existing laws.

[1215] Step 2:

[1216] The server analyzes the acquired legal amendment information and extracts the necessary information. The input is the JSON of the legal amendment information acquired in step 1, and the output is the analyzed and extracted amendment information. The server extracts the necessary information using a text analysis tool and passes it to the generative AI model.

[1217] Step 3:

[1218] The server inputs the revision information into the generative AI, which then automatically generates new draft regulations and work procedures. The input is the analyzed revision information, and the output is the generated new draft regulations and work procedures. For example, the generative AI model (e.g., GPT-3) is given the following prompt:

[1219] "Please generate new factory work procedures based on the following legal changes: 'According to new industrial safety regulations, the working time limit has changed. This means that working time in hazardous areas will now be limited to 6 hours per day. Please provide new work procedures.'"

[1220] The generation AI generates a corresponding new procedure.

[1221] Step 4:

[1222] The server compares the generated new draft with the current policy using a text comparison tool. The input is the new draft and the current policy, and the output is text with the changes clearly marked. The server uses the text comparison tool to compare the old and new procedures and highlight the changes.

[1223] Step 5:

[1224] The server sends the new draft to stakeholders via email or a web form and collects their feedback. The input is the new draft with the changes highlighted, and the output is feedback from stakeholders. Stakeholders use their devices to send their opinions via email or a web form.

[1225] Step 6:

[1226] The server analyzes the collected feedback using an emotion engine. The input is the feedback from the stakeholders, and the output is an evaluation of the importance and credibility of the feedback based on its emotional state. The emotion engine analyzes the feedback text and extracts its emotional features.

[1227] Step 7:

[1228] The user refers to the feedback evaluation results from the emotion engine and modifies the new draft regulations and work procedures. The input is the emotion engine's evaluation results and feedback content, and the output is the final modified draft regulations and procedures. After making the necessary modifications, the user sends the finalized procedures to the server.

[1229] Step 8:

[1230] The server implements the approved new procedures on the production line. The input is the final revised draft or procedure, and the output is the procedure converted into a form that can be implemented on the production line. The server then uses an automated process to ensure that the new procedure is applied on the production line.

[1231] Step 9:

[1232] The server saves and manages new work procedures and their revision history in a database. The input is the final implemented work procedure and its history, and the output is the history saved in the database. The server periodically updates the database and manages it so that past revisions and history can be tracked and checked.

[1233] These are the specific processing steps of the system that realizes this application example. This process efficiently acquires information on legal changes, generates new procedures, collects and analyzes feedback, and implements the final procedures.

[1234] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1235] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1236] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1237] [Fourth embodiment]

[1238] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1239] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1240] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1241] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1242] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1243] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1244] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1245] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1246] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1247] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1248] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1249] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1250] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1251] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, automatically creates draft regulations based on the amendment information using a generative AI, collects feedback from stakeholders, finalizes the draft, and automates the process of publishing it internally.

[1252] Specifically, the system is configured and operated as follows:

[1253] Legal information gathering

[1254] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it obtains information on revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's official website.

[1255] Draft generation

[1256] The server passes the acquired revision information to the generation AI, which then uses that information to generate a new draft of the regulations. For example, it generates a new draft of the "Working Hours Regulations" that takes into account the revisions to the Labor Standards Act.

[1257] Comparison and Review

[1258] The server compares the new draft text created by the generative AI with the current regulations and uses text comparison tools to highlight the changes, making the changes visible at a glance and improving review efficiency.

[1259] Collecting feedback

[1260] The server emails the new draft to stakeholders, who then receive the emails on their own devices, review them, and provide feedback, which is collected through web forms and reply emails.

[1261] Approval and publication

[1262] The user checks the feedback, makes any necessary corrections, and finally approves the policy. The server then publishes the final version of the policy on the company intranet and notifies all employees.

[1263] History Management

[1264] The server stores the new regulations and their revision history in a database and manages them so that they can be accessed at any time. This makes it easy to track and check past revisions and their history.

[1265] Specific examples

[1266] Example 1

[1267] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day. The acquired data is in JSON format, which the server parses and passes to the generation AI the content to be created. The generation AI creates a draft of the "Working Hours Regulations" incorporating the revised parts, compares it with the current version, and highlights the changes in red.

[1268] Example 2

[1269] After a new draft is created, the server retrieves the email list of the HR department and sends an email with the draft attached. HR personnel receive the email on their own devices, review it, and provide feedback through a web form. The HR manager reviews the feedback, makes any necessary corrections, and approves the final draft.

[1270] Once the final draft is approved, the server publishes the policy on the company intranet and notifies all employees. The new policy and revision history are all stored in a database, so users can check past revisions at any time.

[1271] This invention comprehensively realizes the rapid collection of legal information, automatic generation of draft texts, efficient communication with stakeholders, and management of revision history, thereby significantly improving the efficiency of corporate regulation management and contributing to strengthening compliance with laws and regulations and internal control.

[1272] The processing flow will be explained below.

[1273] Step 1:

[1274] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server uses the Ministry of Health, Labor and Welfare's API to obtain revision information for the Labor Standards Act in JSON format.

[1275] Step 2:

[1276] The server analyzes the legal amendment information it has acquired and extracts the necessary amendments. Text mining technology is used for the analysis to extract the main points of the legal amendments.

[1277] Step 3:

[1278] The server sends the extracted revision information to the generation AI, which then automatically creates a new draft regulation based on the revision information. At this time, the generation AI generates a draft regulation that conforms to the company's existing regulation format.

[1279] Step 4:

[1280] The server compares the new draft text with the current version using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[1281] Step 5:

[1282] The server emails the new draft to interested parties, including an attachment of the draft and a review link that they can click to access a web form to provide their feedback.

[1283] Step 6:

[1284] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[1285] Step 7:

[1286] The server collects and aggregates feedback from stakeholders, automatically sorts it, and lists the necessary changes.

[1287] Step 8:

[1288] The user reviews the feedback and makes any necessary corrections. The user then makes a final check of the revised draft and decides whether to approve it.

[1289] Step 9:

[1290] The server publishes the final approved version of the regulations on the company intranet, which is then immediately notified to all employees.

[1291] Step 10:

[1292] The server stores the new regulations and their revision history in a database, which is recorded in detail and managed so that it can be accessed at any time.

[1293] Specific examples

[1294] Step 1 example

[1295] The server obtains information on revisions to the Labor Standards Act through the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format.

[1296] Step 2: Example

[1297] The server uses text mining technology to analyze the revised parts of the JSON data it receives and extracts the revised contents of the Labor Standards Act.

[1298] Step 3 example

[1299] The server sends the extracted revision information to the generation AI, which then generates a draft of the new "Work Hours Regulations." The draft text conforms to the company's existing format.

[1300] Step 4: Example

[1301] The server compares the new draft with the current version using a text comparison tool and highlights the revised parts in red.

[1302] Step 5: Example

[1303] The server sends an email to the HR representative with the new draft attached and a link for review.

[1304] Step 6: Example

[1305] The HR staff receives the email on the device, reviews the new draft text, and submits feedback via a web form.

[1306] Step 7 Example

[1307] The server collects all the feedback and organizes a list of necessary fixes.

[1308] Step 8 Example

[1309] The user then revises the draft based on the feedback, and then gives final approval.

[1310] Step 9 Example

[1311] The server publishes the approved regulations on the company intranet and notifies all employees by email.

[1312] Step 10: Example

[1313] The server stores new regulations and their revision history in a detailed database, allowing users to access past changes.

[1314] Example 1

[1315] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1316] Corporate regulation management requires a great deal of time and effort to deal with legal revisions and update internal regulations. The process of collecting information on legal revisions, drafting regulations, gathering feedback from stakeholders, and finally approving and publishing the final draft is particularly complex and requires efficient and accurate execution. However, current manual processes and partial automation make it difficult to fully meet the demands for regulatory compliance and strengthened internal controls. This leaves companies exposed to reduced operational efficiency and the risk of legal violations.

[1317] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1318] In this invention, the server includes: means for connecting to a legal database and acquiring new legal revision information; means for analyzing and extracting the acquired legal revision information; means for automatically generating draft regulations based on the revision information extracted by the generative AI model; means for comparing the generated new draft regulations with existing regulations and indicating changes; means for automatically periodically collecting legal revision information from the Internet; means for storing the collected legal revision information in JSON format; means for comparing the new draft regulations with existing regulations using a text comparison tool; means for visualizing the comparison results and generating a document indicating changes; means for sending the new draft regulations to relevant parties and collecting feedback; means for revising the draft regulations based on the feedback and publishing them internally after approval; means for saving and managing the new regulations and their revision history in a database; and means for publishing approved regulations on the company's intranet and notifying all employees. This significantly streamlines the entire corporate regulations management process, enabling enhanced compliance with laws and regulations and internal control.

[1319] A "legal database" is a database that stores laws, regulations, and amendments that can be accessed and searched as needed.

[1320] "Revision Information" means information that describes changes or updates to current laws and regulations.

[1321] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to automatically generate new documents based on provided information.

[1322] A "draft rule" is a document that documents the rules and policies that apply within a company and is used as a draft.

[1323] A "text comparison tool" is software that compares two documents and automatically identifies and highlights differences and changes.

[1324] "Feedback" refers to information including opinions, requests for amendments, and suggestions from stakeholders regarding the new draft regulations.

[1325] The "Internet" is a communications network that interconnects computer networks around the world, enabling the sending and receiving of information.

[1326] "JSON format" stands for JavaScript Object Notation, a lightweight data exchange format that represents data as key-value pairs and is easy to read for both humans and machines.

[1327] An "internal intranet" is a dedicated network used within a company, built for the purpose of sharing internal information and communication.

[1328] A "database" is an information system that organizes and stores large amounts of data, enabling fast searching and access.

[1329] A "notification email" is an email sent to convey specific information, with the aim of quickly conveying the information to the recipient.

[1330] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, uses a generative AI model to automatically create draft regulations based on that amendment information, collects feedback from stakeholders, and automates the process of finalizing and publishing the draft internally. Specifically, the system is configured and operated as follows:

[1331] Legal information gathering

[1332] The server connects to the internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server retrieves information on revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's official website. The server analyzes the data and stores it in JSON format before passing it to the AI ​​model to generate the new content.

[1333] Draft generation

[1334] The server sends the saved JSON data of the legal amendment information to the generative AI model, which generates a new draft regulation based on the following prompt:

[1335] Please draft new working hours regulations based on the latest revisions to the Labor Standards Act.

[1336] The changes are as follows:

[1337] [Revision information]

[1338] The server receives the generated draft regulations and stores them in a database.

[1339] Comparison and Review

[1340] The server compares the new draft text with the existing policy using a text comparison tool, such as a diff tool, and the server highlights the changes in red, generating a document showing the changes.

[1341] Collecting feedback

[1342] The server sends new drafts and comparison documents to the stakeholders via email. The stakeholders receive the emails on their own devices and review the drafts and comparison documents. The stakeholders submit feedback via a web form or reply email. For example, feedback is collected when stakeholders access a web form, enter their feedback, and click the submit button.

[1343] Approval and publication

[1344] The user checks the feedback on the terminal and modifies the draft text as necessary. After the final draft is confirmed, the user presses the approval button. The server then publishes the approved draft text on the company intranet and sends an email to all employees to notify them.

[1345] History Management

[1346] The server stores and manages new regulations and their revision history in a database. Users with appropriate access rights can check the history of past revisions.

[1347] Specific examples

[1348] Example 1

[1349] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day. The acquired data is stored in JSON format, and the server analyzes it and passes the content to be created to the generative AI model. The generative AI model creates a draft of the "Working Hours Regulations" incorporating the revised parts, compares it with the current version, and highlights the changes in red.

[1350] Example 2

[1351] After a new draft is created, the server retrieves the email list of the HR department and sends it via email with the draft attached. HR personnel receive the email on their own devices, review it, and provide feedback via a web form. The HR manager checks the feedback, makes any necessary corrections, and approves the final draft. Once approved, the server publishes the policy on the company intranet and notifies all employees. In addition, the new policy and revision history are all stored in a database, allowing users to check past revisions at any time.

[1352] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1353] Step 1:

[1354] The server connects to the Internet at 3:00 AM every day and collects the latest legal revision information from legal databases and official websites. This collection is done using APIs. For example, information on revisions to the Labor Standards Act is obtained from the Ministry of Health, Labor and Welfare's API. The input is the API request, and the output is the obtained revision information in JSON format. The server analyzes this data and extracts the necessary revision information.

[1355] Step 2:

[1356] The server analyzes and formats the extracted revision information and converts it into a format that can be passed to the generative AI model. Specifically, it formats the revision information and generates a prompt text. The input is revision information in JSON format, and the output is the prompt text that is passed to the generative AI model. Example of a prompt text:

[1357] Please draft new working hours regulations based on the latest revisions to the Labor Standards Act.

[1358] The changes are as follows:

[1359] [Revision information]

[1360] The server sends this prompt to the generative AI model.

[1361] Step 3:

[1362] The generative AI model generates a new draft policy sentence based on the prompt sentence. The input is the generated prompt sentence, and the output is the new draft policy sentence. The generative AI model uses natural language processing techniques to do this. The server receives the generated draft sentence and stores it in a database.

[1363] Step 4:

[1364] The server compares the new draft text with the existing policy using a text comparison tool. The input is the new draft text and the existing policy, and the output is a comparison document with the changes highlighted. The server uses a text comparison tool (e.g., a diff tool) to identify the changes and generate a comparison document with the changes highlighted in red.

[1365] Step 5:

[1366] The server sends the new draft document and the comparison document to the participants by email. The input is the new draft document and the comparison document, and the output is an email to the participants. The participants receive the email on their own devices and review the draft document and the comparison document.

[1367] Step 6:

[1368] Stakeholders use their terminals to review the new draft and comparison documents and provide feedback. The input is the review and feedback of the stakeholders, and the output is the feedback received by the server. Stakeholders submit their feedback via a web form or reply email.

[1369] Step 7:

[1370] The user checks the feedback on the terminal and modifies the draft text as necessary. The input is feedback from the stakeholders, and the output is the modified final draft text. The user reflects the feedback and confirms the final draft text.

[1371] Step 8:

[1372] The user approves the final draft. When the user presses the approval button, the server publishes the approved draft on the company intranet and sends a notification email to all employees. The input is the approved final draft, and the output is publication on the company intranet and a notification email.

[1373] Step 9:

[1374] The server stores and manages new policies and their revision history in a database. The input is the new policy and its revision history, and the output is an entry stored in the database. Users with appropriate access rights can check the history of past revisions.

[1375] (Application example 1)

[1376] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1377] In large facilities such as factories, updating and managing regulations based on the latest legal revisions is extremely time-consuming. Manual updates are prone to errors and delays, resulting in uncertain compliance. Furthermore, a lack of efficient means of communication with stakeholders means gathering feedback and approving final proposals takes time. To solve these issues, there is a need for a system that automates the regulations management process and can quickly and accurately comply with the latest laws.

[1378] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1379] In this invention, the server includes means for connecting to a legal database and acquiring new legal revision information, means for analyzing and extracting the acquired legal revision information, means for automatically generating draft regulations based on the revision information extracted by the generation AI, means for comparing the generated new draft regulations with the current regulations and indicating changes, means for sending the new draft regulations to relevant parties using a screen device and collecting feedback from them, means for revising the draft regulations based on the feedback and publishing them on the network after approval, means for saving and managing the new regulations and their revision history in a storage device, and means for automatically adjusting machine operation based on the latest regulation information. This ensures that machines in the factory always operate in accordance with the latest safety regulations and ensures compliance with laws and regulations.

[1380] - "Legal Database" means an online system for storing and managing data including the latest laws and regulations.

[1381] "New Law Change Information" means the latest information on changes or additions to existing laws and regulations.

[1382] "Generative AI" is a technology that uses artificial intelligence to generate text and content based on specified conditions and data.

[1383] A "draft regulation" is a document that lists the rules and guidelines that a company or organization must follow.

[1384] "Stakeholders" are people or organizations that play a significant role in a particular project or task.

[1385] "Feedback" is an opinion or evaluation given in response to a specific content or action.

[1386] A "network" is a system in which multiple computers and devices are connected to each other and exchange and share data.

[1387] A "storage device" is an electronic device for storing data for long periods of time and retrieving it as needed.

[1388] "Machines" are devices or robots that perform work automatically.

[1389] To implement the present invention in a factory or the like, a design is first made based on the specific combination of hardware and software that constitutes the entire system. The main components of the present invention are a server, a terminal, a generative AI model, a storage device, a network, and machines.

[1390] First, the server connects to a legal database and periodically retrieves new legal revision information. To do this, the server collects data from official websites and APIs via the Internet. Legal revision information is often provided in JSON format, which the server parses and extracts the necessary revision information. This is done using Python's requests library and analysis processing library.

[1391] Next, the extracted revision information is passed to a generative AI model to automatically generate a new draft regulation text. The generative AI model uses OpenAI's GPT-3, among others. The generative AI model generates a new draft regulation text based on the following prompt:

[1392] Generate factory safety regulations based on the new Labor Standards Act:

[1393] New regulations...

[1394] The server compares the new draft text with the current version and highlights any changes. This process uses a text comparison tool, and changes are highlighted in red, allowing stakeholders to see the changes at a glance.

[1395] The new draft text is sent to the relevant parties using a display device. The relevant parties receive the draft text on their own devices (smartphones, tablets, etc.) and provide feedback. This feedback is collected via email and web forms. The server that collects the feedback then modifies the draft text based on that feedback and generates the final version of the draft regulations.

[1396] Once the final draft of the regulations has been approved by the relevant parties, it will be published on the network by the server. At this point, all users will be able to view the new regulations. The new regulations and their revision history will be saved in a storage device and managed so that they can be accessed at any time.

[1397] Furthermore, the system is equipped with a function that automatically adjusts machine operation based on the latest regulatory information, ensuring that factory machinery always operates in compliance with the latest safety regulations and ensuring compliance with laws and regulations.

[1398] As an example, let's consider the case of obtaining information about revisions to the Labor Standards Act from the Ministry of Health, Labor and Welfare's API. In this case, the server periodically sends requests to the API, analyzes the obtained JSON data, and passes it to a generative AI model to generate a draft of new working hours regulations. The generated draft is then compared with the current version, and relevant parties are asked to review it via a screen device, and revisions and approvals are made based on the feedback. The final regulations are published on the network, and the machines in the factory automatically change their behavior in accordance with the regulations.

[1399] In this way, the present invention comprehensively realizes the rapid collection of legal information, the automatic generation of draft regulations, efficient communication with relevant parties, management of revision history, and the adjustment of machine operation based on that history, thereby greatly improving the efficiency of regulations management in factories and other facilities.

[1400] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1401] Step 1:

[1402] The server connects to the legal database via the Internet to obtain new legal revision information. Specifically, the server periodically sends requests to the legal database's API and receives JSON-formatted data containing legal revision information. The input is the API request, and the output is the obtained JSON data.

[1403] Step 2:

[1404] The server parses the acquired legal amendment information and extracts the necessary amendment information. In this process, a JSON parsing library is used to parse the data and extract the specific amendment content. The input is the acquired JSON data, and the output is text data containing the specific amendment information.

[1405] Step 3:

[1406] The server passes the revision information to the generative AI model and generates a new draft regulation text. The server provides the prompt text "Please generate factory safety regulations based on the new Labor Standards Act:- New regulation content..." and the generative AI model generates a new draft regulation text. The input is the revision information and the prompt text, and the output is the generated draft regulation text.

[1407] Step 4:

[1408] The server compares the generated new draft with the current regulations and highlights the changes. This is done using a text comparison tool, which highlights the changes in red. The input is the new draft and the current draft regulations, and the output is text data containing the comparison results.

[1409] Step 5:

[1410] The server sends the new draft to the relevant parties using a display device. Each party receives the new draft on their device (smartphone or tablet) and can review it. The input is the compared draft regulations, and the output is the state in which the review request has been sent.

[1411] Step 6:

[1412] Participants use their devices to return feedback. Feedback is sent via email or web forms and collected on a server. The input is the participant's feedback, and the output is the collected feedback data.

[1413] Step 7:

[1414] The server then modifies the draft policy text based on the collected feedback. If necessary, it re-uses the generative AI model to generate a revised draft policy text. The input is the collected feedback data, and the output is the final revised draft policy text.

[1415] Step 8:

[1416] Once the final draft is approved by the parties involved, the server publishes it on the network. The final draft is saved in a storage device and managed in a database. The input is the approved final draft, and the output is the published regulations and a saved revision history.

[1417] Step 9:

[1418] The server automatically adjusts machine operation based on the latest regulation information. The latest regulation information is provided as parameters to machines in the factory via the network, and machine settings and operation are automatically updated. The input is the latest regulation information, and the output is the adjusted machine operation.

[1419] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1420] This invention is a system that streamlines corporate regulations management, and in particular, by combining it with an emotion engine that recognizes user emotions, it enables more serious and precise feedback collection and processing. This system automatically obtains new legal amendment information from a legal database, automatically creates draft regulations based on that amendment information using a generative AI, collects and evaluates feedback from stakeholders via the emotion engine, and streamlines the process of finalizing and publishing the draft within the company.

[1421] Specifically, the system is configured and operated as follows:

[1422] Legal information gathering

[1423] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it obtains information on revisions to the Labor Standards Act from the official website of the Ministry of Health, Labor and Welfare.

[1424] Draft generation

[1425] The server passes the acquired revision information to the generation AI, which then uses that information to generate new draft regulations. For example, it creates "working hours regulations" based on the revisions to the Labor Standards Act.

[1426] Comparison and Review

[1427] The server compares the new draft text created by the AI ​​with the current regulations using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[1428] Collecting feedback

[1429] The server then emails the new draft to the interested parties, including an attachment of the draft and a link for review.

[1430] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[1431] The server collects feedback from participants and analyzes it with an emotion engine, which evaluates the emotional state of the user's feedback and determines its importance and reliability according to the emotional state.

[1432] Approval and publication

[1433] The user checks the feedback while referring to the evaluation results from the emotion engine and makes any necessary corrections. After the final draft is approved, the server publishes the regulations on the company intranet and notifies all employees.

[1434] History Management

[1435] The server stores new regulations and their revision history in a database and manages them so that they can be accessed at any time. Past revisions and their history can be easily tracked and confirmed.

[1436] Specific examples

[1437] Example 1

[1438] The server collects information on revisions to the Labor Standards Act via the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format. The acquired data is analyzed and the revisions are sent to the generation AI. The generation AI generates a draft of the new "Working Hours Regulations," and the server compares the text with the current version. Changes are highlighted in red.

[1439] Example 2

[1440] After a new draft is created, the server emails it to the relevant parties, informing them that it requires review.

[1441] The users receive the emails on their devices, review the new draft text, and submit their feedback via a web form. The server then analyzes the feedback using an emotion engine to assess the importance and credibility of the feedback based on the user's emotional state.

[1442] Finally, users make revisions based on the feedback and evaluations and approve the regulations. The approved regulations are published on the company intranet via a server. All revision history is also stored in a database and can be accessed at any time.

[1443] This invention significantly improves the efficiency of corporate regulations management and contributes to strengthening compliance with laws and regulations and internal control by comprehensively achieving the rapid collection of legal information, automatic generation of draft texts, efficient communication with stakeholders and feedback evaluation, and revision history management. In addition, the combination of an emotion engine improves the quality of feedback and achieves more accurate regulations management.

[1444] The processing flow will be explained below.

[1445] Step 1:

[1446] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, it uses the Ministry of Health, Labor and Welfare's API to obtain revision information for the Labor Standards Act in JSON format.

[1447] Step 2:

[1448] The server analyzes the legal amendment information it has acquired and extracts the necessary amendments. Text mining technology is used for the analysis to extract the main points of the amendment information.

[1449] Step 3:

[1450] The server sends the extracted revision information to the generation AI, which then automatically creates a new draft regulation based on the revision information. At this time, the generation AI generates a draft regulation that conforms to the company's existing regulation format.

[1451] Step 4:

[1452] The server compares the new draft text with the current version using a text comparison tool, highlighting the changes so that stakeholders can see them at a glance.

[1453] Step 5:

[1454] The server emails the new draft to interested parties, including an attachment of the draft and a review link that they can click to access a web form to provide their feedback.

[1455] Step 6:

[1456] The relevant parties receive the email on the terminal, check the attachments, review the email, enter the review results into a web form, and submit the form.

[1457] Step 7:

[1458] The server collects feedback from participants and sends it to the emotion engine, which analyzes the text of the feedback and evaluates the user's emotional state. For example, the emotion engine detects "dissatisfaction" or "question" from the feedback content.

[1459] Step 8:

[1460] The server receives the emotion evaluation results from the emotion engine and lists the importance and reliability of the feedback. At this time, it categorizes the feedback based on the evaluation of the emotional state and determines the processing order according to urgency and importance.

[1461] Step 9:

[1462] The user checks the feedback while referring to the evaluation results of the emotion engine and makes any necessary corrections. The user prioritizes checking feedback that the emotion engine indicates as "dissatisfied" and makes appropriate corrections.

[1463] Step 10:

[1464] The user reviews the final draft and gives their approval. Once approved, the server publishes the regulations on the company intranet and notifies all employees.

[1465] Step 11:

[1466] The server stores the new regulations and their revision history in a database, which is recorded in detail and managed so that it can be accessed at any time.

[1467] Specific examples

[1468] Step 1 example

[1469] The server obtains information on revisions to the Labor Standards Act through the Ministry of Health, Labor and Welfare's API at 3:00 AM every day and receives it in JSON format.

[1470] Step 2: Example

[1471] The server uses text mining technology to analyze the revision details from the received JSON data and extract the necessary information.

[1472] Step 3 example

[1473] The server sends the extracted revision information to the generation AI, which then automatically generates a draft of the new "Work Hours Regulations." This draft is created according to the company's existing format.

[1474] Step 4: Example

[1475] The server compares the new draft with the current "Work Hours Regulations" using a text comparison tool and highlights the changes in red.

[1476] Step 5: Example

[1477] The server sends an email to the HR representative with the new draft attached and a link for review.

[1478] Step 6: Example

[1479] The human resources staff member who receives the email on the device reviews the draft text, enters the review results into a web form, and submits it.

[1480] Step 7 Example

[1481] The server sends the collected feedback to an emotion engine, which analyzes the text of the feedback to evaluate the user's emotional state.

[1482] Step 8 Example

[1483] The server lists the importance and reliability of the feedback based on the evaluation results of the emotion engine. For example, feedback rated as "unsatisfactory" is given priority.

[1484] Step 9 Example

[1485] The user checks the feedback and makes necessary corrections based on the evaluation results of the emotion engine. Feedback rated as "unsatisfactory" is addressed first.

[1486] Step 10: Example

[1487] The user checks the final draft and gives their approval. Once approved, the server publishes the regulations on the company intranet and notifies all employees.

[1488] Step 11 Example

[1489] The server stores new regulations and revision history in detail in a database and manages them so that users can access them at any time.

[1490] Example 2

[1491] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1492] For corporate regulations management, it is important to respond quickly to legal revisions. However, in many cases, collecting feedback from stakeholders and evaluating its content takes time, making efficient operation difficult. There is also a need for a method to improve the quality of feedback and make more appropriate revisions and approvals. To solve these issues, there is a need for a system that streamlines the entire process of automatically obtaining legal revision information, automatically generating draft regulations, and collecting and analyzing feedback, thereby enabling rapid and accurate regulation revisions.

[1493] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1494] In this invention, the server includes means for connecting to a legal database and acquiring new legal revision information, means for analyzing and extracting the acquired legal revision information, means for automatically generating draft regulations based on the revision information extracted by the generative AI model, means for comparing the generated new draft regulations with current regulations and indicating changes, means for sending the new draft regulations to stakeholders and collecting feedback, means for analyzing the feedback using an emotion engine and evaluating its importance and reliability, means for revising the draft regulations based on the feedback and publishing them internally after approval, and means for storing and managing the new regulations and their revision history in a database. This enables companies to respond quickly and accurately to legal revisions, improve the quality of feedback from stakeholders, and more appropriately revise and approve regulations.

[1495] A "legal database" is a database that stores the latest information on legal amendments and laws that will be enacted, and is accessible via the Internet.

[1496] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to automatically generate sentences and content based on input text data.

[1497] An "emotion engine" is software or an algorithm that analyzes the content of user feedback and evaluates its emotional state, importance, and reliability.

[1498] "Draft Regulations" means a draft of regulations prepared based on legal amendment information and other requirements.

[1499] A "text comparison tool" is software that compares different texts and highlights the changes.

[1500] A "database" is a computer system designed to store information systematically and allow rapid retrieval and access.

[1501] A "web form" is a form-filling feature built into a web page on the Internet, allowing users to enter and submit information.

[1502] "Email" is a means of communication for sending and receiving text messages and attachments over the Internet.

[1503] A "corporate intranet" is a private network used within an organization that uses Internet technology for the purpose of sharing and accessing internal information.

[1504] An "SMTP server" is a computer server that implements the Simple Mail Transfer Protocol, a protocol for sending email.

[1505] This invention is a system that streamlines corporate regulations management. This system automatically retrieves new legal amendment information from a legal database, automatically creates draft regulations based on that amendment information using a generative AI model, collects and evaluates feedback from stakeholders using an emotion engine, and then finalizes and publishes the final draft, streamlining the process.

[1506] Legal information gathering

[1507] The server connects to the Internet and periodically collects the latest legal revision information from legal databases and official websites. For example, the server uses the Ministry of Health, Labor and Welfare's API to obtain revision information on the Labor Standards Act in JSON format. This obtained data is then analyzed within the system to extract the necessary information.

[1508] Draft generation

[1509] The server passes the acquired revision information to the generative AI model, which then generates a new draft of the regulations based on that information. An example of a prompt is, "Please generate a new draft of the working hours regulations based on the latest revision information of the Labor Standards Act." The generated draft is saved within the system and proceeds to the next step.

[1510] Comparison and Review

[1511] The server compares the generated new draft regulations with the current regulations using a text comparison tool. The changes are highlighted so that stakeholders can see them at a glance. The comparison results are saved as an HTML file and sent to stakeholders.

[1512] Collecting feedback

[1513] The server sends the new draft regulations to the relevant parties via email. The email contains an attachment of the draft regulations and a link for review. The relevant parties receive the email on their devices, check the attachment, and review it. They then enter the review results into a web form and submit it. The server collects feedback from the relevant parties and analyzes it using an emotion engine. The emotion engine evaluates the emotional state of the user's feedback and determines its importance and reliability based on that emotional state.

[1514] Approval and publication

[1515] The user checks the feedback based on the evaluation results from the emotion engine and makes any necessary revisions. After the final draft is approved, the server publishes the policy on the company intranet and notifies all employees. Notification is sent via email, and all employees can access the new policy.

[1516] History Management

[1517] The server stores the new regulations and their revision history in a database and manages them so that they can be accessed at any time, making it easy to track and check past revisions and their history.

[1518] Specific example explanation

[1519] For example, the server collects information on revisions to the Labor Standards Act through the Ministry of Health, Labor, and Welfare's API at 3:00 AM every day, analyzes the data, and sends a prompt to the generative AI model: "Please generate a new draft of the working hours regulations based on the latest revisions to the Labor Standards Act." The generative AI model generates a new draft, compares it with the current version using a text comparison tool, and highlights changes in red. The server then emails the new draft and the comparison results to relevant parties and accepts feedback. The relevant parties submit feedback on their devices, and the server analyzes it using an emotion engine. Finally, the user reviews the feedback, makes corrections and approvals, and the server publishes it on the company intranet. This process enables companies to manage regulations quickly and efficiently.

[1520] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1521] Step 1:

[1522] Legal information gathering

[1523] The server connects to the Internet at a set time every day (e.g., 3:00 AM) and accesses legal databases and official websites. Specifically, the server retrieves revision information for the Labor Standards Act in JSON format from the Ministry of Health, Labor and Welfare's API.

[1524] Input: Legal database access information, API endpoint, query parameters

[1525] Output: Legal change information in JSON format

[1526] What it does: Sends an HTTP request, parses the response from the API, and saves it as JSON data.

[1527] Step 2:

[1528] Legal Information Analysis and Extraction

[1529] The server analyzes the acquired JSON-formatted legal amendment information and extracts the necessary amendment details. Specifically, it extracts the relevant legal provisions and their amendment details from the JSON data.

[1530] Input: Legal amendment information in JSON format

[1531] Output: Extracted data of revision details (text and object format containing necessary information)

[1532] What it does: It uses a JSON parser to parse the data and extract the values ​​of specific fields.

[1533] Step 3:

[1534] Automatic generation of draft regulations

[1535] The server sends the extracted revision details to the generation AI model. It instructs the model to generate a draft regulation using a prompt. The specific prompt is, "Please generate a draft of the new working hours regulations based on the latest revision information of the Labor Standards Act."

[1536] Input: Extracted revision data, prompt text

[1537] Output: Generated draft regulations (text format)

[1538] How it works: Sends an API request to the generative AI model and retrieves the generated text.

[1539] Step 4:

[1540] Comparison of the text of the old and new draft regulations

[1541] The server compares the generated new draft regulations with the current regulations using a text comparison tool, highlighting the changes.

[1542] Input: New regulation draft text, current regulation text

[1543] Output: Comparison results with highlighted changes (HTML or PDF format)

[1544] How it works: It uses a text comparison algorithm to calculate the differences and identify the changes, which are then highlighted in red.

[1545] Step 5:

[1546] Submitting a new rule proposal

[1547] The server will then email the generated comparison results and the new rule proposal to the relevant parties, including a link for review.

[1548] Input: Email addresses of relevant parties, new rule draft, comparison results, review link

[1549] Output: Email sent

[1550] What it does: Sends an email through an SMTP server, containing a text message and an attachment.

[1551] Step 6:

[1552] Collecting feedback

[1553] The relevant parties receive the email on their terminal, check the attachments, review the file, and then enter the review results into a web form and submit it.

[1554] Input: Incoming emails, attachments, and web form entries

[1555] Output: Feedback data sent

[1556] What it does: Open the attachment in your email client, check the contents, then fill out the form in your web browser.

[1557] Step 7:

[1558] Feedback Analysis

[1559] The server sends the collected feedback to the emotion engine for analysis, which evaluates the emotional state of the feedback.

[1560] Input: Feedback data

[1561] Output: Sentiment analysis results (score, evaluation comments)

[1562] Behavior: Sends feedback data to the Emotion Engine API and receives analysis results.

[1563] Step 8:

[1564] Review and correct feedback

[1565] The user checks the emotion engine's analysis results and makes any necessary corrections based on the feedback.

[1566] Input: Sentiment analysis results, feedback content

[1567] Output: Revised draft regulations

[1568] How it works: View feedback and ratings through the admin panel and make corrections using the editing tools.

[1569] Step 9:

[1570] Approval and publication of the final draft

[1571] The user checks and approves the final draft of the regulations. The server then publishes the approved draft on the company intranet and notifies all employees.

[1572] Input: Confirm the final draft regulations and give approval instructions

[1573] Output: Published regulations, notification to all employees

[1574] Operation: Approval is performed on the management screen, and the data is uploaded to the intranet and notified to all employees by email.

[1575] Step 10:

[1576] Saving revision history

[1577] The server stores the new rule draft and its revision history in a database.

[1578] Input: Final draft regulations, previous revision history

[1579] Output: Saved revision history data

[1580] Behavior: Performs an INSERT operation on the database and records the revision history.

[1581] (Application example 2)

[1582] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1583] The process of corporate policy management involves complex tasks such as manually processing large amounts of legal information, collecting and evaluating feedback from stakeholders, and publishing new policies in a timely manner, making it difficult to carry out efficiently. Furthermore, to improve the quality of feedback, it is also important to accurately grasp and evaluate users' emotional states. This calls for a system that enables more accurate policy management.

[1584] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1585] In this invention, the server includes: means for connecting to a legal database and acquiring information on new legal revisions; means for analyzing and extracting the acquired legal revision information; means for automatically generating draft regulations based on the revision information extracted by the generation AI; means for comparing the generated new draft regulations with current regulations and indicating changes; means for sending the new draft regulations to relevant parties and collecting feedback; means for revising the draft regulations based on the feedback and publishing them internally after approval; means for storing and managing the new regulations and their revision history in a database; means for periodically collecting the latest regulatory information on industrial safety and quality control; means for automatically generating new work procedures and regulations using the generation AI; means for comparing the generated new work procedures and regulations with current ones and indicating changes; means for analyzing feedback using an emotion engine and evaluating the importance and reliability of the feedback based on the emotional state; and means for finalizing and introducing the final draft regulations into the production line. This enables rapid acquisition and analysis of legal revision information, and enables efficient automatic generation of new draft regulations and work procedures using the generation AI. In addition, using an emotion engine improves the quality of feedback, enabling more accurate regulation management.

[1586] A "legal database" is a data storage system that systematically collects, stores, and makes accessible legal information.

[1587] "Legal amendment information" refers to various detailed information about newly enacted laws and amendments to existing laws.

[1588] "Generative AI" is a type of artificial intelligence that is a technology that automatically generates sentences and procedures based on given data and conditions.

[1589] A "draft regulation" is a formal draft document that lists the rules and procedures that must be followed within a company or organization.

[1590] The "emotion engine" is an artificial intelligence technology that analyzes the user's emotional state and evaluates the quality and importance of feedback based on that information.

[1591] "Feedback" refers to opinions and evaluations from stakeholders that are used to refine and modify new draft texts and procedures.

[1592] "Revision History" means information that keeps a record of all past changes and modifications and allows them to be tracked.

[1593] "Industrial safety" refers to rules and standards to ensure the health and safety of workers, and measures to minimize dangers in factories and work sites.

[1594] "Quality control" refers to planned and controlled activities to maintain and improve the quality of products and services.

[1595] A "production line" is a system that divides the manufacturing process in a factory or other facility to carry out continuous and efficient production.

[1596] This invention aims to improve the efficiency of a quality control system using factory robots. This system automatically generates procedures and rules to quickly respond to changes in laws and regulations, and includes an emotion engine to effectively collect and analyze feedback. Specific embodiments are described below.

[1597] System Configuration

[1598] The system consists of the following main elements:

[1599] 1. Server: This is the central hardware that manages and controls the entire system. The server connects to the Internet, retrieves the latest regulatory information from the legal database, and generates new work procedures using generative AI models.

[1600] 2. Generative AI: This is an artificial intelligence technology that generates new work procedures and rules. For example, OpenAI's GPT-3 model can be used.

[1601] 3. Emotion Engine: This is an artificial intelligence technology that analyzes feedback from stakeholders and evaluates their emotional state, determining the importance and credibility of the feedback.

[1602] 4. Database: A data storage system for storing and managing new regulations and their revision history.

[1603] Processing procedures and data calculations

[1604] Legal information gathering

[1605] The server collects the latest legal revision information from legal databases and official websites via the Internet, for example, periodically obtaining the latest regulatory information related to industrial safety and quality control.

[1606] Draft generation

[1607] The acquired legal amendment information is passed to a generative AI, which automatically generates new draft regulations and work procedures. A generative AI model (e.g., GPT-3) is used to generate new procedures using the following prompt sentence as input:

[1608] "Please generate new factory work procedures based on the following legal changes: 'According to new industrial safety regulations, the working time limit has changed. This means that working time in hazardous areas will now be limited to 6 hours per day. Please provide new work procedures.'"

[1609] Comparison and Review

[1610] The server compares the new draft text created by the AI ​​with the current regulations using a text comparison tool, highlighting the changes so that they are clearly visible to stakeholders.

[1611] Collecting feedback

[1612] The server sends new work instructions to stakeholders via email or web forms and collects feedback, which is analyzed using an emotion engine and rated for importance and credibility based on the emotional state.

[1613] Approval and publication

[1614] The server checks the feedback based on the evaluation results from the emotion engine and makes any necessary corrections. After the final proposal is approved, it will be implemented on the production line and the work procedures will be finalized.

[1615] History Management

[1616] The server stores new work procedures and their revision history in a database and manages them so that they can be accessed at any time. Past revisions and their history can be easily tracked and checked.

[1617] This enables the rapid acquisition and analysis of legal amendment information, and new draft regulations and work procedures are efficiently created through automatic generation using generative AI. In addition, the use of an emotion engine improves the quality of feedback, resulting in more accurate regulation management.

[1618] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1619] Step 1:

[1620] The server connects to the legal database to retrieve new legal amendment information. It receives data from the legal database API as input and stores the legal amendment information in JSON format as output. This data includes newly enacted laws and amendments to existing laws.

[1621] Step 2:

[1622] The server analyzes the acquired legal amendment information and extracts the necessary information. The input is the JSON of the legal amendment information acquired in step 1, and the output is the analyzed and extracted amendment information. The server extracts the necessary information using a text analysis tool and passes it to the generative AI model.

[1623] Step 3:

[1624] The server inputs the revision information into the generative AI, which then automatically generates new draft regulations and work procedures. The input is the analyzed revision information, and the output is the generated new draft regulations and work procedures. For example, the generative AI model (e.g., GPT-3) is given the following prompt:

[1625] "Please generate new factory work procedures based on the following legal changes: 'According to new industrial safety regulations, the working time limit has changed. This means that working time in hazardous areas will now be limited to 6 hours per day. Please provide new work procedures.'"

[1626] The generation AI generates a corresponding new procedure.

[1627] Step 4:

[1628] The server compares the generated new draft with the current policy using a text comparison tool. The input is the new draft and the current policy, and the output is text with the changes clearly marked. The server uses the text comparison tool to compare the old and new procedures and highlight the changes.

[1629] Step 5:

[1630] The server sends the new draft to stakeholders via email or a web form and collects their feedback. The input is the new draft with the changes highlighted, and the output is feedback from stakeholders. Stakeholders use their devices to send their opinions via email or a web form.

[1631] Step 6:

[1632] The server analyzes the collected feedback using an emotion engine. The input is the feedback from the stakeholders, and the output is an evaluation of the importance and credibility of the feedback based on its emotional state. The emotion engine analyzes the feedback text and extracts its emotional features.

[1633] Step 7:

[1634] The user refers to the feedback evaluation results from the emotion engine and modifies the new draft regulations and work procedures. The input is the emotion engine's evaluation results and feedback content, and the output is the final modified draft regulations and procedures. After making the necessary modifications, the user sends the finalized procedures to the server.

[1635] Step 8:

[1636] The server implements the approved new procedures on the production line. The input is the final revised draft or procedure, and the output is the procedure converted into a form that can be implemented on the production line. The server then uses an automated process to ensure that the new procedure is applied on the production line.

[1637] Step 9:

[1638] The server saves and manages new work procedures and their revision history in a database. The input is the final implemented work procedure and its history, and the output is the history saved in the database. The server periodically updates the database and manages it so that past revisions and history can be tracked and checked.

[1639] These are the specific processing steps of the system that realizes this application example. This process efficiently acquires information on legal changes, generates new procedures, collects and analyzes feedback, and implements the final procedures.

[1640] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1641] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1642] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1643] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1644] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1645] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1646] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1647] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1648] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1649] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1650] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1651] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1652] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1653] 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.

[1654] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1655] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1656] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1657] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1658] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1659] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1660] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1661] The following is further disclosed regarding the above embodiment.

[1662] (Claim 1)

[1663] means for connecting to a legal database and obtaining information on new legal amendments;

[1664] A means for analyzing and extracting the acquired legal amendment information;

[1665] A means for automatically generating draft regulations based on the revision information extracted by the generation AI;

[1666] A means to compare the new draft text generated with the current regulations and highlight any changes;

[1667] A means to send new draft text to stakeholders and gather feedback;

[1668] The draft text will be revised based on the feedback and published internally after approval.

[1669] A means of storing and managing new regulations and their revision history in a database;

[1670] A system including:

[1671] (Claim 2)

[1672] 2. The system according to claim 1, wherein the means for collecting feedback from stakeholders is via email or a web form.

[1673] (Claim 3)

[1674] 2. The system according to claim 1, wherein the means for analyzing the legal amendment information collected from the legal database uses artificial intelligence.

[1675] "Example 1"

[1676] (Claim 1)

[1677] means for connecting to a legal database and obtaining information on new legal amendments;

[1678] A means for analyzing and extracting the acquired legal amendment information;

[1679] A means for automatically generating a draft plan based on the revision information extracted by the generative AI model;

[1680] A means to compare the new draft text generated with the current regulations and highlight any changes;

[1681] A means to send new draft text to stakeholders and gather feedback;

[1682] ...

Claims

1. means for connecting to a legal database and obtaining information on new legal amendments; A means for analyzing and extracting the acquired legal amendment information; A means for automatically generating draft regulations based on the revision information extracted by the generation AI; A means to compare the new draft text generated with the current regulations and highlight any changes; A means to send new draft text to stakeholders and gather feedback; The draft text will be revised based on the feedback and published internally after approval. A means of storing and managing new regulations and their revision history in a database; A system including:

2. 2. The system of claim 1, wherein the means for collecting feedback from participants is via email or a web form.

3. 2. The system according to claim 1, wherein the means for analyzing the legal change information collected from the legal database uses artificial intelligence.

Images