System

Abstract

A system is provided.SOLUTION: A system comprising: means for accepting a rule generation request from a user; means for acquiring an existing rule from a database; means for generating a new rule using a generative AI model and analyzing a contradiction with the existing rule; means for feeding back the generated new rule and the contradiction to the user; and means for notifying and sharing a finally confirmed rule to all users in an organization.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] Existing work styles involve complex rules that are difficult to disseminate and enforce. Furthermore, when new team rules are introduced, they may conflict with existing rules. If this situation continues, it could have a negative impact on communication and efficiency within the organization. Therefore, there is a need for a system that can simply manage rules and share them widely within the organization. [Means for solving the problem]

[0005] The present invention is a system that includes a means for accepting rule generation requests from users, a means for retrieving existing rules from a database, a means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, a means for providing feedback on the generated new rules and inconsistencies to the user, and a means for notifying and sharing the final confirmed rules with all users within an organization. This system makes it possible to simply manage complex organizational rules and easily disseminate them widely. Furthermore, the generative AI model automatically analyzes inconsistencies between new rules and existing rules, thereby preventing conflicts from occurring in advance.

[0006] A "user" is an individual or organization that utilizes this system to make rule generation requests and receive feedback.

[0007] The "means for accepting rule generation requests" is an interface that receives input from users about ideas for new rules and changes, and transmits them to the system.

[0008] "Means for obtaining existing rules from a database" refers to a process for searching and obtaining rules and regulations that have already been established within an organization from a database.

[0009] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[0010] The "feedback means" is a mechanism for notifying the user of the generated new rules and their inconsistencies, and for urging them to check and correct them.

[0011] The "means for notifying and sharing the final confirmed rule" is a function for notifying all users in the organization of the rule that has been finally confirmed by the user, and for widely sharing the rule. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users within the organization. An embodiment of this system is described in detail below.

[0034] System Program Overview

[0035] 1. Acceptance of rule generation requests

[0036] User

[0037] The user enters the proposed new rules or changes into a dedicated form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00 to 18:00) is entered.

[0038] Terminal

[0039] The terminal receives the user's input data and sends it to the server as an HTTP request.

[0040] 2. Get existing rules

[0041] server

[0042] The server receives the HTTP request, checks the integrity of the data, and then retrieves existing rule information from the organization's database. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[0043] 3. Rule generation and analysis using generative AI models

[0044] server

[0045] The server compiles the acquired existing rules and user suggestions into a data packet and sends it to the generative AI model.

[0046] Generative AI Models

[0047] The generative AI model generates new rules based on the received data and analyzes any inconsistencies with existing rules. For example, it checks whether the new rule (9:00 AM to 6:00 PM) conflicts with the existing lunch break time (12:00 PM to 1:00 PM).

[0048] 4. Providing Feedback

[0049] server

[0050] The server receives the output of the generative AI model (the new rule and the inconsistencies) and provides feedback to the user. For example, it sends an email containing information that the inconsistency is not inconsistent with the lunch break time.

[0051] User

[0052] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[0053] 5. Finalize and share the rules

[0054] User

[0055] When final confirmation is received from the user, the final version is sent from the terminal to the server.

[0056] server

[0057] The server transfers the final rules to the shared system and sends notifications to all users within the organization.

[0058] Terminal

[0059] Your device will receive a notification and display a message to confirm the new rule.

[0060] Specific examples

[0061] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[0062] 1. User enters a suggestion

[0063] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[0064] 2. Get existing rules

[0065] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[0066] 3. Analysis using generative AI models

[0067] Server: Sends new proposals and existing rules to the generative AI model.

[0068] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[0069] 4. Conflict detection and feedback

[0070] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[0071] Server: Compiles feedback and notifies users.

[0072] 5. Sharing rules

[0073] User: Review feedback and submit final version from device.

[0074] Server: Notifies all users of the final rules and transfers them to the shared system.

[0075] The above process allows for simple management of complex organizational rules and makes it easy to disseminate them widely. This system efficiently handles everything from rule generation to final sharing, supporting communication within an organization and effective business operations.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] User

[0079] The user enters a proposal for a new rule or change into the form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00-18:00) is entered.

[0080] Step 2:

[0081] Terminal

[0082] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[0083] Step 3:

[0084] server

[0085] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[0086] Step 4:

[0087] server

[0088] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[0089] Step 5:

[0090] server

[0091] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[0092] Step 6:

[0093] Generative AI Models

[0094] The generative AI model analyzes the received data and generates new rules. For example, it generates a new working hours policy (9:00-18:00). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00-13:00) are consistent.

[0095] Step 7:

[0096] Generative AI Models

[0097] The generative AI model outputs the analysis results and creates a list of proposed new rules and contradictions.

[0098] Step 8:

[0099] server

[0100] The server receives the analysis results from the generative AI model, temporarily stores the proposed new rules and any inconsistencies in a database, and then formats the data for feedback to the user.

[0101] Step 9:

[0102] server

[0103] The server provides feedback to the user, for example, by sending an email or a notification to the terminal containing information that the discrepancy is "not in conflict with the lunch break time."

[0104] Step 10:

[0105] User

[0106] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[0107] Step 11:

[0108] User

[0109] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[0110] Step 12:

[0111] server

[0112] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[0113] Step 13:

[0114] Terminal

[0115] The device will display a notification of the new rules to all users in the organization, allowing them to check the new rules.

[0116] The above processing steps enable the simple management of complex organizational rules and their widespread dissemination. This system efficiently handles everything from rule generation to final sharing, thereby more effectively supporting communication and business operations within an organization.

[0117] Example 1

[0118] 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."

[0119] In the current system, rule generation and sharing within an organization are not carried out efficiently, and there is a high possibility that conflicts with existing rules will occur, especially when new rules are generated. In addition, suggestions and feedback from users are often not properly reflected, resulting in a lack of responsiveness across the organization. This results in issues such as the time it takes to apply rules and a decline in work efficiency across the organization.

[0120] 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.

[0121] In this invention, the server includes means for accepting rule generation requests from users, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for providing feedback to the user on the generated new rules and inconsistencies, and means for notifying and sharing the final confirmed rules received from the user with all users in the organization. This streamlines the rule generation process and enables automatic analysis of inconsistencies with existing rules, improving responsiveness throughout the organization and enabling improved business efficiency.

[0122] A "user" is a user who submits a rule generation request to the system and checks the feedback.

[0123] A "rule creation request" is a request that a user sends to the system to propose a new rule or a rule change.

[0124] A "database" is an information storage system that stores existing rule information within an organization and allows that information to be searched and retrieved as needed.

[0125] A "generative AI model" is an artificial intelligence system that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[0126] "Inconsistencies" refer to areas of inconsistency or conflict between new rules and existing rules.

[0127] "Feedback" is a response that notifies the user of new rules generated by the generative AI model and information about inconsistencies.

[0128] An "HTTP request" is a communication format for sending user input to a server.

[0129] A "terminal" is a device such as a computer or smartphone that a user uses to request rule generation or check feedback.

[0130] "Intra-organizational" refers to the interior of the particular company or organization to which the rules apply.

[0131] A "notification" is a message sent by the server to notify all users in an organization of new rules or updated information.

[0132] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users in the organization.

[0133] System Configuration

[0134] User

[0135] Users can input new rule suggestions or changes through a dedicated web interface. For example, they can enter a suggestion to change working hours to "9:00 AM - 6:00 PM" into a form and click the "Submit" button. This generates an HTTP request.

[0136] Terminal

[0137] The terminal receives input data from the user and sends it to the server as an HTTP request. The user then checks the terminal for a message indicating that the data has been sent.

[0138] server

[0139] The server receives the HTTP request and first checks the data format and content for consistency. It then accesses the organization's database to retrieve existing rule information. For example, if the existing working hours are "8:00 AM - 5:00 PM," that information is retrieved from the database.

[0140] The server obtains the existing rules and new proposals, converts this information into data packets, and sends them to the generative AI model. The generative AI model generates new rules based on the received data and analyzes any inconsistencies with the existing rules. For example, it checks whether the new working hours of "9:00 AM - 6:00 PM" are consistent with the lunch break time of "12:00 PM - 1:00 PM."

[0141] The analysis results of the generative AI model are returned to the server as new rules and inconsistencies, which the server uses to create feedback messages and send to the user via email or notification.

[0142] The user reviews the feedback and, if necessary, modifies the proposal or approves it for final review. The finalized rules are then sent back to the server, which transfers the final rules to the shared system and sends a notification to all users in the organization that the new rules have been finalized.

[0143] The device will receive a notification and display a message to the user saying "New rules have been shared with you," allowing the user to review and apply the new rules.

[0144] Specific examples

[0145] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[0146] 1. User enters a suggestion

[0147] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[0148] 2. Get existing rules

[0149] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[0150] 3. Analysis using generative AI models

[0151] Server: Sends new proposals and existing rules to the generative AI model.

[0152] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[0153] 4. Conflict detection and feedback

[0154] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[0155] Server: Compiles feedback and notifies users.

[0156] 5. Sharing rules

[0157] User: Review feedback and submit final version from device.

[0158] Server: Notifies all users of the final rules and transfers them to the shared system.

[0159] Device: Notify the user that a new rule has been shared with them.

[0160] This system streamlines the rule generation process and can automatically analyze inconsistencies with existing rules, improving responsiveness across the organization and enabling improved operational efficiency.

[0161] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0162] Step 1:

[0163] (User inputs and submits rule generation request)

[0164] The user enters a new rule proposal or changes into a dedicated web form and clicks the "Submit" button. For example, a proposal to change working hours to "9:00-18:00" is entered. This generates the user's input (proposed new rule) as input data.

[0165] Input: Propose a new rule (e.g., change working hours)

[0166] Output: User input data (in HTTP request format)

[0167] Step 2:

[0168] (The device sends the user's input data to the server)

[0169] The terminal receives the user's input data and sends it to the server as an HTTP request. After the request is sent, a "Send completed" message is displayed to notify the user.

[0170] Input: User input data (proposed new rules)

[0171] Output: "Sent" message

[0172] Step 3:

[0173] (Server retrieves existing rules)

[0174] The server receives the HTTP request and checks the data format and content for consistency. Next, it accesses the organization's database to retrieve existing rule information. For example, it searches for and retrieves rules that include the existing working hours of "8:00 AM - 5:00 PM."

[0175] Input: User input data (HTTP request), existing rule information

[0176] Output: Existing rules (e.g., working hours "8:00-17:00")

[0177] Step 4:

[0178] (The server sends the data to the generative AI model)

[0179] The server compiles the acquired existing rules and user suggestions, converts them into a data packet, and sends it to the generative AI model. Specifically, it structures the data in JSON format or similar and generates a data packet that includes the new rules and existing rules.

[0180] Input: User suggestions, existing rules

[0181] Output: Data packet (e.g., JSON format)

[0182] Step 5:

[0183] (The generative AI model generates rules and performs analysis)

[0184] The generative AI model analyzes the received data packets and generates new rules. It also checks whether the generated rules are consistent with existing rules. For example, it checks whether a new work schedule of "9:00 AM - 6:00 PM" is consistent with a lunch break of "12:00 PM - 1:00 PM."

[0185] Input: Data packet (new rule / existing rule)

[0186] Output: New rules, list of inconsistencies

[0187] Step 6:

[0188] (Server sends feedback to user)

[0189] The server receives the output data (new rules and inconsistencies) from the generative AI model and generates a feedback message for the user. For example, it creates a feedback message including the content "The new working hours (9:00-18:00) are not inconsistent with the lunch break time (12:00-13:00)" and sends it to the user via email or notification.

[0190] Input: New rules, list of discrepancies

[0191] Output: Feedback message

[0192] Step 7:

[0193] (User checks feedback)

[0194] The user receives the feedback, reviews it on their device, considers it, makes new suggestions or modifies existing ones as needed, and if there are no problems, approves it for final review.

[0195] Input: Feedback message

[0196] Output: Approved final rules or proposed amendments

[0197] Step 8:

[0198] (User submits finalized rule)

[0199] Once the user has reviewed the feedback and finalized the rules, the terminal sends the final rules to the server, including details of the final approved rules.

[0200] Input: Approved Final Rules

[0201] Output: Data sent to the server

[0202] Step 9:

[0203] (Server shares the final rules)

[0204] The server receives the final rules, transfers them to the shared system, and sends a notification to all users in the organization that the new rules have been finalized, for example via an intranet or internal chat tool.

[0205] Input: Final rules

[0206] Output: Notification to all users in the organization

[0207] Step 10:

[0208] (Device displays notification)

[0209] The device will receive a notification and display a message to the user saying "New rules have been shared with you," allowing the user to review and apply the new rules.

[0210] Input: Notification from the server

[0211] Output: Display of notification message

[0212] Through the above steps, the process from a user's rule generation request to the final sharing of the rules can be carried out efficiently.

[0213] (Application example 1)

[0214] 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."

[0215] In factories, work rules and work instructions are frequently changed, and the latest rules and instructions may not be communicated quickly and reliably to everyone on the shop floor. This problem is particularly pronounced in complex manufacturing and quality control processes, and can lead to reduced work efficiency and deterioration of product quality. Conventional manual methods of rule management and sharing cannot adequately solve these issues, creating a need for automated systems.

[0216] 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.

[0217] In this invention, the server includes means for accepting rule generation requests from users, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for providing feedback to the user on the generated new rules and inconsistencies, means for notifying and sharing the final confirmed rules with all users in the organization, and means for generating, managing, and sharing rules and work instructions within the factory via smart devices (smartphones, tablets, head-mounted displays, factory robots). This allows the latest work rules and instructions to be quickly and reliably communicated to everyone on site, improving work efficiency and ensuring product quality.

[0218] A "user" is an individual or member of an organization who accesses the system and makes a rule generation request.

[0219] The "means for accepting rule generation requests" is an interface that has the function of accepting proposals for new rules or rule changes from users.

[0220] The "means for obtaining existing rules from a database" is a program that has the function of searching for and obtaining existing rule information stored in a database within an organization.

[0221] A "generative AI model" is an artificial intelligence model used to generate new rules based on input data and analyze inconsistencies with existing rules.

[0222] The "feedback means" is a system that has the function of notifying the user of the new rules that have been generated and the results of the analysis of contradictions.

[0223] The "means for notifying and sharing the final confirmed rules" is a system that has the function of quickly notifying all users in the organization of the rules that have received final confirmation from the users and sharing them.

[0224] A "smart device" is a portable electronic terminal (e.g., smartphone, tablet, head-mounted display, factory robot) that a user uses to access the system, submit rule generation requests, and receive feedback.

[0225] This invention is a system for efficiently managing, generating, and sharing rules and work instructions within a factory. This system accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. It also provides feedback on the generated rules and inconsistencies to the user, and notifies and shares the final confirmed rules with all users within the organization.

[0226] 1. Hardware and Software Configuration

[0227] The system is implemented using the following hardware and software:

[0228] Server: Accepts rule generation requests, retrieves existing rules from the database, executes the generative AI model, generates feedback, and finalizes and shares the rules.

[0229] Devices: Smartphones, tablets, head-mounted displays, and factory robots for inputting rule generation requests

[0230] Database: PostgreSQL (management of existing rules)

[0231] Generative AI model: OpenAI API (new rule generation and inconsistency analysis)

[0232] Framework: Flask (Web interface implementation)

[0233] 2. Overview of the processing procedure

[0234] A user uses a smart device to send a rule generation request to the system. This request includes a new rule or a proposed change, such as "Change the frequency of machine maintenance inspections to once a week." The server receives this request and retrieves existing rules from the database.

[0235] The server sends the existing rules and the new proposal to the generative AI model, which generates new rules and analyzes the inconsistencies with the existing rules.The generative AI model generates the inconsistencies as prompt sentences based on the proposed rules and the existing rules, as follows:

[0236] plain

[0237] Proposed rule: Change machine maintenance inspection frequency to once a week.

[0238] Existing rules: Machine maintenance inspections twice a month.

[0239] Detect the inconsistencies.

[0240] Based on the analysis results returned by the generative AI model, the server creates feedback and notifies the user. The feedback includes the new rules generated and whether or not there are any inconsistencies. For example, if there are no inconsistencies, the server notifies the user that "a new rule can be introduced."

[0241] The user checks the feedback and, if final confirmation is obtained, submits the final rules to the system. The server then notifies and shares the final confirmed rules with all users within the organization. This ensures that the latest rules and instructions are quickly and reliably communicated to everyone on-site.

[0242] This system will streamline the management of work rules and instructions within the factory, making it possible to maintain work efficiency and product quality.

[0243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0244] Step 1:

[0245] A user uses a smart device (smartphone, tablet, head-mounted display, factory robot) to input a request to create a new rule. For example, the user might input "Change the machine maintenance inspection frequency to once a week" and click the send button. At this time, the input data is sent to the server as an HTTP request.

[0246] Step 2:

[0247] The server accepts the HTTP request data received from the user and verifies the integrity of the data. At this time, it checks whether the format and content of the request data are correct. Next, it sends a query to the database (PostgreSQL) to obtain existing related rule information. For example, it searches for and obtains a rule such as "Machine maintenance inspections should be performed twice a month." The obtained data is stored in internal memory.

[0248] Step 3:

[0249] The server compiles existing rules and user suggestions into a data packet and sends it to the generative AI model (OpenAI API). The generative AI model generates new rules based on the received data and analyzes any inconsistencies with existing rules. An example of a prompt sentence used in this process is as follows:

[0250] plain

[0251] Proposed rule: Change machine maintenance inspection frequency to once a week.

[0252] Existing rules: Machine maintenance inspections twice a month.

[0253] Detect the inconsistencies.

[0254] Based on this prompt, the generative AI model returns new rules and analysis results of inconsistencies.

[0255] Step 4:

[0256] The server receives the analysis results returned by the generative AI model and creates feedback based on them. The feedback includes information on new rules and inconsistencies. For example, a message such as "New rules can be introduced" is generated. This feedback is sent to the user as a notification.

[0257] Step 5:

[0258] The user reviews the feedback on their smart device and, if necessary, modifies and resubmits the proposal or finalizes new rules based on the feedback.

[0259] Step 6:

[0260] The user sends the finalized rules from the terminal to the server, which then forwards the finalized rules to the shared system, which then notifies all users in the organization of the new rules and makes them applicable.

[0261] Step 7:

[0262] Devices (smartphones, tablets, head-mounted displays) will receive notifications and display messages to confirm the new rules, allowing all users to quickly understand the latest rules.

[0263] 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.

[0264] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules, and further combines it with an emotion engine that recognizes the user's emotions. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users within the organization. An embodiment of this system is described in detail below.

[0265] System Program Overview

[0266] 1. Acceptance of rule generation requests

[0267] User

[0268] The user enters the proposed new rules or changes into a dedicated form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00 to 18:00) is entered.

[0269] Terminal

[0270] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[0271] 2. Get existing rules

[0272] server

[0273] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[0274] server

[0275] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[0276] 3. Rule generation and analysis using generative AI models

[0277] server

[0278] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[0279] Generative AI Models

[0280] The generative AI model generates new rules based on the received data. For example, it generates a new working hours policy (9:00 AM to 6:00 PM). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00 PM to 1:00 PM) are consistent.

[0281] 4. Emotional Analysis of Users by Emotion Engine

[0282] server

[0283] The server sends the data obtained from the user interface to the emotion engine.

[0284] Emotion Engine

[0285] The emotion engine analyzes emotions based on user input and interactions, for example, determining stress or satisfaction from user input and click frequency.

[0286] 5. Providing Feedback

[0287] server

[0288] The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides feedback to the user. For example, it sends an email containing information that the inconsistency is "not inconsistent with the lunch break time" and a message corresponding to the user's emotional state.

[0289] User

[0290] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[0291] 6. Finalize and share the rules

[0292] User

[0293] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[0294] server

[0295] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[0296] Terminal

[0297] Your device will receive a notification and display a message to confirm the new rule.

[0298] Specific examples

[0299] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[0300] 1. User enters a suggestion

[0301] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[0302] 2. Get existing rules

[0303] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[0304] 3. Analysis using generative AI models

[0305] Server: Sends new proposals and existing rules to the generative AI model.

[0306] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[0307] 4. Analysis by Emotion Engine

[0308] Server: Sends user input data to the emotion engine.

[0309] Emotion engine: Analyzes user emotions and determines stress and satisfaction.

[0310] 5. Conflict detection and feedback

[0311] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[0312] Server: Compiles the feedback and sends notifications with messages depending on the user's emotional state.

[0313] 6. Sharing rules

[0314] User: Review feedback and submit final version from device.

[0315] Server: Notifies all users of the final rules and transfers them to the shared system.

[0316] Through the above process, complex organizational rules can be managed simply and easily and widely disseminated.By using an emotion engine, this system provides more personalized feedback according to the user's emotional state, more effectively supporting communication and business operations within an organization.

[0317] The processing flow will be explained below.

[0318] Step 1:

[0319] User

[0320] The user enters a proposal for a new rule or change into the form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00-18:00) is entered.

[0321] Step 2:

[0322] Terminal

[0323] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[0324] Step 3:

[0325] server

[0326] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[0327] Step 4:

[0328] server

[0329] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[0330] Step 5:

[0331] server

[0332] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[0333] Step 6:

[0334] Generative AI Models

[0335] The generative AI model analyzes the received data and generates new rules. For example, it generates a new working hours policy (9:00-18:00). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00-13:00) are consistent.

[0336] Step 7:

[0337] Generative AI Models

[0338] The generative AI model outputs the analysis results and creates a list of proposed new rules and contradictions.

[0339] Step 8:

[0340] server

[0341] The server receives the analysis results from the generative AI model, temporarily stores the proposed new rules and any inconsistencies in a database, and then formats the data for feedback to the user.

[0342] Step 9:

[0343] server

[0344] The server sends the data obtained from the user interface to the emotion engine.

[0345] Step 10:

[0346] Emotion Engine

[0347] The emotion engine analyzes emotions based on user input and interactions, for example, determining stress or satisfaction from user input and click frequency.

[0348] Step 11:

[0349] server

[0350] The server receives the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user, for example, by sending an email containing information indicating that the discrepancy is not inconsistent with the lunch break time and a message corresponding to the user's emotional state.

[0351] Step 12:

[0352] User

[0353] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[0354] Step 13:

[0355] User

[0356] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[0357] Step 14:

[0358] server

[0359] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[0360] Step 15:

[0361] Terminal

[0362] Your device will receive a notification and display a message to confirm the new rule.

[0363] Through the above processing steps, complex organizational rules can be managed simply and easily and widely disseminated.By using an emotion engine, this system provides more personalized feedback according to the user's emotional state, more effectively supporting communication and business operations within an organization.

[0364] Example 2

[0365] 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."

[0366] In conventional rule management systems, the creation of new rules and the detection of inconsistencies with existing rules were not automated and had to be done manually. This meant that rule creation required a great deal of time and effort, and it was difficult to provide feedback that took into account the user's emotions. This resulted in problems such as reduced usability and disrupted communication within the organization.

[0367] 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.

[0368] In this invention, the server includes means for accepting a rule generation request from a user, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for using an emotion engine to analyze the user's emotional state, means for providing feedback to the user about the generated new rules and inconsistencies, means for reaccepting suggestions and changes based on the feedback, and means for notifying and sharing the final confirmed rules with all users in the organization. This makes rule generation more efficient and automated, and by providing feedback that takes the user's emotional state into consideration, it becomes possible to facilitate communication within the organization.

[0369] "User" refers to an entity that uses the system to request the creation or modification of rules.

[0370] "Means for accepting rule generation requests" refers to an interface or mechanism for accepting new rule suggestions or changes from users.

[0371] "Database" refers to a data storage system for storing existing rule information managed within the system.

[0372] A "generative AI model" refers to a model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[0373] "Means for conflict analysis" refers to a mechanism or algorithm that checks for conflicts between existing rules and new proposed rules.

[0374] "Emotion engine" refers to software or algorithms that analyze emotional states based on user input and interaction data.

[0375] "Means for providing feedback" refers to a mechanism that notifies the user of the generated new rules and the analysis results of inconsistencies, and provides evaluation and advice on the proposals.

[0376] "Means for resubmitting suggestions and changes" refers to an interface or mechanism that allows users to receive feedback and make further suggestions or changes.

[0377] "Means for notifying and sharing finalized rules" refers to a mechanism for notifying and sharing rules that have been finalized by users to all users within an organization.

[0378] The present invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. Furthermore, it incorporates an emotion engine that recognizes the user's emotions, provides feedback to the user about the generated rules and any inconsistencies, and notifies and shares the final confirmed rules with all users within the organization. The following describes in detail an embodiment of the present invention.

[0379] 1. A method for accepting rule generation requests from users

[0380] User

[0381] The user enters new rule proposals or changes into a dedicated form on the device and clicks the "Submit" button. For example, the user can enter a specific proposal such as "Change working hours to 9:00-18:00."

[0382] Terminal

[0383] The terminal receives user input, validates the input data, checking that all required fields are filled in and that the format is correct, and if validation is successful, sends the data to the server as an HTTP request.

[0384] 2. How to retrieve existing rules from a database

[0385] server

[0386] The server receives the HTTP request from the device and verifies that the data format is correct. It checks that the request is in JSON format.

[0387] server

[0388] The server accesses the database and retrieves existing rule information. For example, it retrieves information from the database that "the current working hours policy is 8:00 to 17:00." The retrieved information is saved for use in the next step.

[0389] 3. A means of generating new rules using generative AI models and analyzing inconsistencies with existing rules

[0390] server

[0391] The server collects the existing rules and the user's new proposals into a data packet and sends it to the generative AI model. For example, it formats the data in a format such as "existing rules: working hours 8:00-17:00, new proposal: 9:00-18:00."

[0392] Generative AI Models

[0393] The generative AI model generates new rules based on the received data. For example, it generates "new working hours: 9:00 AM to 6:00 PM." It also checks for inconsistencies with existing rules. For example, it checks whether the new rules conflict with the lunch break time (12:00 PM to 1:00 PM).

[0394] 4. Using an emotion engine to analyze the user's emotional state

[0395] server

[0396] The server sends data obtained from the user interface to the emotion engine, including user-entered text and interaction data.

[0397] Emotion Engine

[0398] The emotion engine analyzes emotions based on user input and interactions, for example, determining that a user is stressed if they are making a lot of edits.

[0399] 5. A means of providing feedback to the user about new rules and inconsistencies

[0400] server

[0401] The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides this as feedback to the user. For example, it sends an email containing information such as "The new working hours of 9:00 AM to 6:00 PM are consistent with the lunch break time" and a message saying "The feedback you provided has been completed."

[0402] 6. A way to re-open the project for suggestions and changes based on feedback

[0403] User

[0404] Users receive feedback, review it on their devices, and, if necessary, make further suggestions or modify existing suggestions.

[0405] Terminal

[0406] The device will then accept new suggestions and modifications from the user and send them to the server again.

[0407] 7. How to communicate and share the finalized rules with all users in the organization

[0408] User

[0409] The user makes a final confirmation and sends the final version of the rules to the server from the terminal. For example, the user may confirm, "I officially approve this new working hours policy (9:00-18:00)."

[0410] server

[0411] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, by email or through an internal notification system, informing everyone that the new working hours policy has been approved.

[0412] Terminal

[0413] The device receives the notification and displays a message to the user to confirm the new rules, for example, a notification saying "Please review the new working hours policy."

[0414] Specific examples

[0415] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[0416] 1. User enters a suggestion

[0417] User: Enter "Proposal to change working hours to 9:00-18:00" into the form on the device and submit it.

[0418] 2. Get existing rules

[0419] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[0420] 3. Analysis using generative AI models

[0421] Server: Sends new proposals and existing rules to the generative AI model.

[0422] Generative AI model: Checks whether "Working hours 9:00-18:00" conflicts with lunch break times (12:00-13:00).

[0423] 4. Analysis by Emotion Engine

[0424] Server: Sends user input data to the emotion engine.

[0425] Emotion engine: Analyzes user emotions and determines stress and satisfaction.

[0426] 5. Conflict detection and feedback

[0427] Generative AI model: Confirms that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are acceptable and sends them back to the server.

[0428] Server: Compiles the feedback and sends notifications with messages depending on the user's emotional state.

[0429] 6. Sharing rules

[0430] User: Review feedback and submit final version from device.

[0431] Server: Notifies all users of the final rules and transfers them to the shared system.

[0432] Prompt Sentence Examples

[0433] "I would like to propose a new working hours policy of 9am to 6pm. Please check for any inconsistencies with existing policies and provide feedback."

[0434] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0435] Step 1:

[0436] User: The user enters new rule suggestions or changes into a dedicated form on the terminal. The input includes a new working hours policy (e.g., "Change working hours to 9:00-18:00"). By clicking the "Submit" button, the suggestion is sent to the system.

[0437] Input: Propose a new rule (e.g., "Change working hours to 9:00-18:00")

[0438] Output: Data sent to the server as an HTTP request

[0439] Step 2:

[0440] Terminal: The terminal validates the received user input data, checking that the input data is correctly formatted and that all required fields are filled in. If validation is successful, the terminal sends the data to the server as an HTTP request.

[0441] Input: User-entered data

[0442] Output: Sent to the server as an HTTP request

[0443] Step 3:

[0444] Server: The server receives the HTTP request from the device, verifies that the data format is correct, and checks that the request is in JSON format, and then passes the data to the next step.

[0445] Input: HTTP request data

[0446] Output: Validated data

[0447] Step 4:

[0448] Server: The server accesses the database and retrieves existing rule information. For example, it retrieves information from the database that "the current working hours policy is 8:00 to 17:00." This retrieved information is saved for use in the next step.

[0449] Input: The request to be retrieved from the database

[0450] Output: Existing rule information

[0451] Step 5:

[0452] Server: The server compiles the existing rules and the user's new proposal into a data packet and sends it to the generative AI model. The data is formatted as "Existing rules: working hours 8:00-17:00, new proposal: 9:00-18:00."

[0453] Input: Existing rule information and new rule proposals

[0454] Output: Data packets

[0455] Step 6:

[0456] Generative AI model: The generative AI model generates new rules based on the data it receives. For example, it generates "new working hours will be from 9:00 to 18:00." It also checks for inconsistencies with existing rules. For example, it checks whether "working hours and lunch break times (12:00 to 13:00) are consistent."

[0457] Input: Data packet (existing rules and new proposals)

[0458] Output: New rules and conflict information

[0459] Step 7:

[0460] Server: The server receives output data from the generative AI model and sends data obtained from the user interface to the emotion engine.

[0461] Input: Output data of generative AI model, data from user interface

[0462] Output: Data sent to the emotion engine

[0463] Step 8:

[0464] Emotion Engine: The emotion engine analyzes emotions based on user input and interactions. For example, if a user makes a lot of edits, it determines that the user is stressed.

[0465] Input: User interface data

[0466] Output: User sentiment analysis results

[0467] Step 9:

[0468] Server: The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides feedback to the user. For example, it sends an email containing information such as "The new working hours of 9:00 AM to 6:00 PM are consistent with the lunch break time" and a message saying "The feedback you provided has been completed."

[0469] Input: Output of generative AI model, analysis results of emotion engine

[0470] Output: Feedback to the user

[0471] Step 10:

[0472] User: The user receives the feedback, reviews it on their device, and can resubmit or revise existing suggestions as needed.

[0473] Input: Feedback

[0474] Output: Re-proposal or revised proposal

[0475] Step 11:

[0476] User: The user performs the final confirmation and sends the final version of the rules to the server from the terminal. For example, the user confirms, "I officially approve this new working hours policy (9:00-18:00)."

[0477] Input: Finalized rules

[0478] Output: Final rules sent to the server

[0479] Step 12:

[0480] Server: The server transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, by email or through the internal notification system, informing everyone that the new working hours policy has been approved.

[0481] Input: Final rules

[0482] Output: Notify everyone in the organization

[0483] Step 13:

[0484] Terminal: The terminal receives the notification and displays a message to confirm the new rule. For example, a notification is displayed to the user saying "Please review the new working hours policy."

[0485] Input: Notification from the server

[0486] Output: Message displayed to the user

[0487] (Application example 2)

[0488] 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."

[0489] Managing rule changes and new proposals within an organization requires a lot of manual work, and it is extremely difficult to properly create and share new rules while maintaining consistency with existing rules. Furthermore, if feedback on employee proposals is not provided promptly, it can have a negative impact on employee morale and emotions. This calls for intuitive and efficient rule management and feedback that takes employee feelings into consideration.

[0490] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a rule generation request from a user, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for analyzing the user's emotional state using an emotion engine that recognizes the user's emotions, means for providing feedback based on the generated new rules, inconsistencies, and the user's emotional state, and means for notifying and sharing the final confirmed rules with all users in the organization. This makes it possible to efficiently manage rule changes within the organization and provide personalized feedback according to the user's emotional state.

[0491] A "user" is a person or organization that uses the system to make a rule generation request.

[0492] The "means for accepting rule generation requests" is an interface or function that accepts suggestions and changes regarding rule generation from the user.

[0493] The "means for obtaining existing rules from a database" is a function for searching and obtaining current rule information stored in a database.

[0494] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[0495] An "emotion engine" is an algorithm or system for analyzing and recognizing a user's emotional state from their input and behavior.

[0496] The "means for providing feedback" is a function that provides the user with appropriate information based on the new rules, discrepancies, and emotional state that have been generated.

[0497] The "means for notifying and sharing rules" refers to a function or system for notifying and sharing the finalized rules with all users within the organization.

[0498] A system for implementing this invention includes a series of processes required to accept rule generation requests from users, collect existing rules, generate new rules, detect inconsistencies, provide feedback, and notify all users in an organization of the final confirmed rules.

[0499] First, a user inputs a rule generation request using a smartphone application. The user enters suggestions or changes through a form in the app and clicks the "Submit" button. For example, a suggestion could be to change working hours. The device receives this input data and sends it to the server as an HTTP request. Basic validation is performed to ensure the data format and content are correct.

[0500] The server then receives the HTTP request and checks the data format for validity. If the input data is in the correct format, the server accesses a database to retrieve existing rules, such as the current working hours policy.

[0501] The server assembles this data into data packets and sends them to a generative AI model, which uses machine learning frameworks like TensorFlow to generate new rules and analyze existing rules for inconsistencies—for example, checking that a new work hour policy doesn't conflict with lunch break times.

[0502] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This emotion engine analyzes the user's input and interactions to determine stress and satisfaction. The server receives the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user. For example, a notification containing information indicating there are no inconsistencies or a message corresponding to the user's emotional state may be sent.

[0503] Finally, if the user reviews the feedback and modifies and confirms the rules to their satisfaction, the details are sent to the server. The server then notifies all users in the organization of the final confirmed rules and stores them in a shared system. Notifications are sent via email and the internal notification system to ensure that everyone is aware of the new rules.

[0504] Prompt Sentence Examples

[0505] The following is an example of a prompt sentence to be used when sending a rule generation request to the server.

[0506] api_url = 'http: / / example.com / submit-proposal'

[0507] headers = {'Content-Type': 'application / json'}

[0508] proposal_data = {

[0509] 'proposal': 'I would like to extend the afternoon break to 30 minutes'

[0510] }

[0511] response = requests.post(api_url, json=proposal_data, headers=headers)

[0512] print(response.json())

[0513] As described above, an embodiment of the present invention optimizes organizational rule management and employee feedback provision by combining an efficient and intuitive user interface with an advanced generative AI model and emotion engine. This system is expected to significantly simplify the process from proposal to final confirmation and improve employee satisfaction.

[0514] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0515] Step 1:

[0516] The user inputs a rule generation request. Using a smartphone app, the user inputs new rules or proposed changes into a dedicated form. This input data is sent to the system by clicking the "Submit" button. A specific input might be something like "I would like to extend the afternoon break to 30 minutes." The output is an HTTP request in which this proposal is sent to the server.

[0517] Step 2:

[0518] The terminal receives input data and sends it to the server as an HTTP request. The terminal checks the format and content of the input data and performs basic validation. Only data in the correct format is sent to the server. The input is the proposal entered by the user, and the output is an HTTP request containing data that has passed validation.

[0519] Step 3:

[0520] The server receives an HTTP request and checks the integrity of the data format. The server checks the request content and confirms that it is in the correct format before proceeding to the next step. The input is the data sent from the terminal, and the output is the correct data after the integrity check.

[0521] Step 4:

[0522] The server accesses the database to retrieve existing rule information. The server sends a query to the database to search for and retrieve relevant existing rules, for example, the current working hours policy. The input is the proposed data after consistency check, and the output is the existing rule information.

[0523] Step 5:

[0524] The server compiles the acquired data into a data packet and sends it to the generative AI model. The generative AI model generates new rules based on this data and analyzes any inconsistencies with existing rules. For example, it checks whether a new working hours policy conflicts with existing lunch break times. The input is the proposed data and existing rule information, and the output is the generated new rules and the analysis results of any inconsistencies.

[0525] Step 6:

[0526] The server receives the output of the generative AI model (new rules and inconsistencies) and sends the user's input data to the emotion engine. The emotion engine analyzes emotions based on the user's input and interactions. For example, it determines stress and satisfaction from the input text and frequency of clicks. The input is the user's suggested data, and the output is the emotion analysis results.

[0527] Step 7:

[0528] The server integrates the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user. Specifically, it creates a message based on the new rules, inconsistencies, and the user's emotional state, and provides feedback via email or app notification. The input is the new rules, inconsistencies, and emotion analysis results, and the output is the feedback information notified to the user.

[0529] Step 8:

[0530] The user receives and reviews the feedback, and if necessary makes new suggestions or modifies existing suggestions. This results in an iterative process of reviewing and modifying the final rule. The input is the feedback information, and the output is the modified suggestions.

[0531] Step 9:

[0532] When the user performs final confirmation, the terminal sends the final version of the rules to the server. This final rule is stored on the server. The input is the final confirmed rule, and the output is the final rule stored on the server.

[0533] Step 10:

[0534] The server transfers the final confirmed rules to the shared system and notifies all users in the organization. The server notifies all users of the new rules via email or the internal notification system. The input is the final confirmed rules, and the output is the notification to all users.

[0535] This effectively manages the rule change process within an organization and provides personalized feedback according to the user's emotional state.

[0536] 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.

[0537] 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.

[0538] 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.

[0539] [Second embodiment]

[0540] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0541] 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.

[0542] 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).

[0543] 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.

[0544] 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.

[0545] 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).

[0546] 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. 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.

[0547] 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.

[0548] 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.

[0549] 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.

[0550] In the smart glasses 214, 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.

[0551] 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."

[0552] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users within the organization. An embodiment of this system is described in detail below.

[0553] System Program Overview

[0554] 1. Acceptance of rule generation requests

[0555] User

[0556] The user enters the proposed new rules or changes into a dedicated form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00 to 18:00) is entered.

[0557] Terminal

[0558] The terminal receives the user's input data and sends it to the server as an HTTP request.

[0559] 2. Get existing rules

[0560] server

[0561] The server receives the HTTP request, checks the integrity of the data, and then retrieves existing rule information from the organization's database. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[0562] 3. Rule generation and analysis using generative AI models

[0563] server

[0564] The server compiles the acquired existing rules and user suggestions into a data packet and sends it to the generative AI model.

[0565] Generative AI Models

[0566] The generative AI model generates new rules based on the received data and analyzes any inconsistencies with existing rules. For example, it checks whether the new rule (9:00 AM to 6:00 PM) conflicts with the existing lunch break time (12:00 PM to 1:00 PM).

[0567] 4. Providing Feedback

[0568] server

[0569] The server receives the output of the generative AI model (the new rule and the inconsistencies) and provides feedback to the user. For example, it sends an email containing information that the inconsistency is not inconsistent with the lunch break time.

[0570] User

[0571] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[0572] 5. Finalize and share the rules

[0573] User

[0574] When final confirmation is received from the user, the final version is sent from the terminal to the server.

[0575] server

[0576] The server transfers the final rules to the shared system and sends notifications to all users within the organization.

[0577] Terminal

[0578] Your device will receive a notification and display a message to confirm the new rule.

[0579] Specific examples

[0580] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[0581] 1. User enters a suggestion

[0582] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[0583] 2. Get existing rules

[0584] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[0585] 3. Analysis using generative AI models

[0586] Server: Sends new proposals and existing rules to the generative AI model.

[0587] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[0588] 4. Conflict detection and feedback

[0589] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[0590] Server: Compiles feedback and notifies users.

[0591] 5. Sharing rules

[0592] User: Review feedback and submit final version from device.

[0593] Server: Notifies all users of the final rules and transfers them to the shared system.

[0594] The above process allows for simple management of complex organizational rules and makes it easy to disseminate them widely. This system efficiently handles everything from rule generation to final sharing, supporting communication within an organization and effective business operations.

[0595] The processing flow will be explained below.

[0596] Step 1:

[0597] User

[0598] The user enters a proposal for a new rule or change into the form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00-18:00) is entered.

[0599] Step 2:

[0600] Terminal

[0601] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[0602] Step 3:

[0603] server

[0604] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[0605] Step 4:

[0606] server

[0607] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[0608] Step 5:

[0609] server

[0610] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[0611] Step 6:

[0612] Generative AI Models

[0613] The generative AI model analyzes the received data and generates new rules. For example, it generates a new working hours policy (9:00-18:00). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00-13:00) are consistent.

[0614] Step 7:

[0615] Generative AI Models

[0616] The generative AI model outputs the analysis results and creates a list of proposed new rules and contradictions.

[0617] Step 8:

[0618] server

[0619] The server receives the analysis results from the generative AI model, temporarily stores the proposed new rules and any inconsistencies in a database, and then formats the data for feedback to the user.

[0620] Step 9:

[0621] server

[0622] The server provides feedback to the user, for example, by sending an email or a notification to the terminal containing information that the discrepancy is "not in conflict with the lunch break time."

[0623] Step 10:

[0624] User

[0625] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[0626] Step 11:

[0627] User

[0628] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[0629] Step 12:

[0630] server

[0631] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[0632] Step 13:

[0633] Terminal

[0634] The device will display a notification of the new rules to all users in the organization, allowing them to check the new rules.

[0635] The above processing steps enable the simple management of complex organizational rules and their widespread dissemination. This system efficiently handles everything from rule generation to final sharing, thereby more effectively supporting communication and business operations within an organization.

[0636] Example 1

[0637] 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."

[0638] In the current system, rule generation and sharing within an organization are not carried out efficiently, and there is a high possibility that conflicts with existing rules will occur, especially when new rules are generated. In addition, suggestions and feedback from users are often not properly reflected, resulting in a lack of responsiveness across the organization. This results in issues such as the time it takes to apply rules and a decline in work efficiency across the organization.

[0639] 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.

[0640] In this invention, the server includes means for accepting rule generation requests from users, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for providing feedback to the user on the generated new rules and inconsistencies, and means for notifying and sharing the final confirmed rules received from the user with all users in the organization. This streamlines the rule generation process and enables automatic analysis of inconsistencies with existing rules, improving responsiveness throughout the organization and enabling improved business efficiency.

[0641] A "user" is a user who submits a rule generation request to the system and checks the feedback.

[0642] A "rule creation request" is a request that a user sends to the system to propose a new rule or a rule change.

[0643] A "database" is an information storage system that stores existing rule information within an organization and allows that information to be searched and retrieved as needed.

[0644] A "generative AI model" is an artificial intelligence system that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[0645] "Inconsistencies" refer to areas of inconsistency or conflict between new rules and existing rules.

[0646] "Feedback" is a response that notifies the user of new rules generated by the generative AI model and information about inconsistencies.

[0647] An "HTTP request" is a communication format for sending user input to a server.

[0648] A "terminal" is a device such as a computer or smartphone that a user uses to request rule generation or check feedback.

[0649] "Intra-organizational" refers to the interior of the particular company or organization to which the rules apply.

[0650] A "notification" is a message sent by the server to notify all users in an organization of new rules or updated information.

[0651] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users in the organization.

[0652] System Configuration

[0653] User

[0654] Users can input new rule suggestions or changes through a dedicated web interface. For example, they can enter a suggestion to change working hours to "9:00 AM - 6:00 PM" into a form and click the "Submit" button. This generates an HTTP request.

[0655] Terminal

[0656] The terminal receives input data from the user and sends it to the server as an HTTP request. The user then checks the terminal for a message indicating that the data has been sent.

[0657] server

[0658] The server receives the HTTP request and first checks the data format and content for consistency. It then accesses the organization's database to retrieve existing rule information. For example, if the existing working hours are "8:00 AM - 5:00 PM," that information is retrieved from the database.

[0659] The server obtains the existing rules and new proposals, converts this information into data packets, and sends them to the generative AI model. The generative AI model generates new rules based on the received data and analyzes any inconsistencies with the existing rules. For example, it checks whether the new working hours of "9:00 AM - 6:00 PM" are consistent with the lunch break time of "12:00 PM - 1:00 PM."

[0660] The analysis results of the generative AI model are returned to the server as new rules and inconsistencies, which the server uses to create feedback messages and send to the user via email or notification.

[0661] The user reviews the feedback and, if necessary, modifies the proposal or approves it for final review. The finalized rules are then sent back to the server, which transfers the final rules to the shared system and sends a notification to all users in the organization that the new rules have been finalized.

[0662] The device will receive a notification and display a message to the user saying "New rules have been shared with you," allowing the user to review and apply the new rules.

[0663] Specific examples

[0664] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[0665] 1. User enters a suggestion

[0666] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[0667] 2. Get existing rules

[0668] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[0669] 3. Analysis using generative AI models

[0670] Server: Sends new proposals and existing rules to the generative AI model.

[0671] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[0672] 4. Conflict detection and feedback

[0673] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[0674] Server: Compiles feedback and notifies users.

[0675] 5. Sharing rules

[0676] User: Review feedback and submit final version from device.

[0677] Server: Notifies all users of the final rules and transfers them to the shared system.

[0678] Device: Notify the user that a new rule has been shared with them.

[0679] This system streamlines the rule generation process and can automatically analyze inconsistencies with existing rules, improving responsiveness across the organization and enabling improved operational efficiency.

[0680] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0681] Step 1:

[0682] (User inputs and submits rule generation request)

[0683] The user enters a new rule proposal or changes into a dedicated web form and clicks the "Submit" button. For example, a proposal to change working hours to "9:00-18:00" is entered. This generates the user's input (proposed new rule) as input data.

[0684] Input: Propose a new rule (e.g., change working hours)

[0685] Output: User input data (in HTTP request format)

[0686] Step 2:

[0687] (The device sends the user's input data to the server)

[0688] The terminal receives the user's input data and sends it to the server as an HTTP request. After the request is sent, a "Send completed" message is displayed to notify the user.

[0689] Input: User input data (proposed new rules)

[0690] Output: "Sent" message

[0691] Step 3:

[0692] (Server retrieves existing rules)

[0693] The server receives the HTTP request and checks the data format and content for consistency. Next, it accesses the organization's database to retrieve existing rule information. For example, it searches for and retrieves rules that include the existing working hours of "8:00 AM - 5:00 PM."

[0694] Input: User input data (HTTP request), existing rule information

[0695] Output: Existing rules (e.g., working hours "8:00-17:00")

[0696] Step 4:

[0697] (The server sends the data to the generative AI model)

[0698] The server compiles the acquired existing rules and user suggestions, converts them into a data packet, and sends it to the generative AI model. Specifically, it structures the data in JSON format or similar and generates a data packet that includes the new rules and existing rules.

[0699] Input: User suggestions, existing rules

[0700] Output: Data packet (e.g., JSON format)

[0701] Step 5:

[0702] (The generative AI model generates rules and performs analysis)

[0703] The generative AI model analyzes the received data packets and generates new rules. It also checks whether the generated rules are consistent with existing rules. For example, it checks whether a new work schedule of "9:00 AM - 6:00 PM" is consistent with a lunch break of "12:00 PM - 1:00 PM."

[0704] Input: Data packet (new rule / existing rule)

[0705] Output: New rules, list of inconsistencies

[0706] Step 6:

[0707] (Server sends feedback to user)

[0708] The server receives the output data (new rules and inconsistencies) from the generative AI model and generates a feedback message for the user. For example, it creates a feedback message including the content "The new working hours (9:00-18:00) are not inconsistent with the lunch break time (12:00-13:00)" and sends it to the user via email or notification.

[0709] Input: New rules, list of discrepancies

[0710] Output: Feedback message

[0711] Step 7:

[0712] (User checks feedback)

[0713] The user receives the feedback, reviews it on their device, considers it, makes new suggestions or modifies existing ones as needed, and if there are no problems, approves it for final review.

[0714] Input: Feedback message

[0715] Output: Approved final rules or proposed amendments

[0716] Step 8:

[0717] (User submits finalized rule)

[0718] Once the user has reviewed the feedback and finalized the rules, the terminal sends the final rules to the server, including details of the final approved rules.

[0719] Input: Approved Final Rules

[0720] Output: Data sent to the server

[0721] Step 9:

[0722] (Server shares the final rules)

[0723] The server receives the final rules, transfers them to the shared system, and sends a notification to all users in the organization that the new rules have been finalized, for example via an intranet or internal chat tool.

[0724] Input: Final rules

[0725] Output: Notification to all users in the organization

[0726] Step 10:

[0727] (Device displays notification)

[0728] The device will receive a notification and display a message to the user saying "New rules have been shared with you," allowing the user to review and apply the new rules.

[0729] Input: Notification from the server

[0730] Output: Display of notification message

[0731] Through the above steps, the process from a user's rule generation request to the final sharing of the rules can be carried out efficiently.

[0732] (Application example 1)

[0733] 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."

[0734] In factories, work rules and work instructions are frequently changed, and the latest rules and instructions may not be communicated quickly and reliably to everyone on the shop floor. This problem is particularly pronounced in complex manufacturing and quality control processes, and can lead to reduced work efficiency and deterioration of product quality. Conventional manual methods of rule management and sharing cannot adequately solve these issues, creating a need for automated systems.

[0735] 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.

[0736] In this invention, the server includes means for accepting rule generation requests from users, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for providing feedback to the user on the generated new rules and inconsistencies, means for notifying and sharing the final confirmed rules with all users in the organization, and means for generating, managing, and sharing rules and work instructions within the factory via smart devices (smartphones, tablets, head-mounted displays, factory robots). This allows the latest work rules and instructions to be quickly and reliably communicated to everyone on site, improving work efficiency and ensuring product quality.

[0737] A "user" is an individual or member of an organization who accesses the system and makes a rule generation request.

[0738] The "means for accepting rule generation requests" is an interface that has the function of accepting proposals for new rules or rule changes from users.

[0739] The "means for obtaining existing rules from a database" is a program that has the function of searching for and obtaining existing rule information stored in a database within an organization.

[0740] A "generative AI model" is an artificial intelligence model used to generate new rules based on input data and analyze inconsistencies with existing rules.

[0741] The "feedback means" is a system that has the function of notifying the user of the new rules that have been generated and the results of the analysis of contradictions.

[0742] The "means for notifying and sharing the final confirmed rules" is a system that has the function of quickly notifying all users in the organization of the rules that have received final confirmation from the users and sharing them.

[0743] A "smart device" is a portable electronic terminal (e.g., smartphone, tablet, head-mounted display, factory robot) that a user uses to access the system, submit rule generation requests, and receive feedback.

[0744] This invention is a system for efficiently managing, generating, and sharing rules and work instructions within a factory. This system accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. It also provides feedback on the generated rules and inconsistencies to the user, and notifies and shares the final confirmed rules with all users within the organization.

[0745] 1. Hardware and Software Configuration

[0746] The system is implemented using the following hardware and software:

[0747] Server: Accepts rule generation requests, retrieves existing rules from the database, executes the generative AI model, generates feedback, and finalizes and shares the rules.

[0748] Devices: Smartphones, tablets, head-mounted displays, and factory robots for inputting rule generation requests

[0749] Database: PostgreSQL (management of existing rules)

[0750] Generative AI model: OpenAI API (new rule generation and inconsistency analysis)

[0751] Framework: Flask (Web interface implementation)

[0752] 2. Overview of the processing procedure

[0753] A user uses a smart device to send a rule generation request to the system. This request includes a new rule or a proposed change, such as "Change the frequency of machine maintenance inspections to once a week." The server receives this request and retrieves existing rules from the database.

[0754] The server sends the existing rules and the new proposal to the generative AI model, which generates new rules and analyzes the inconsistencies with the existing rules.The generative AI model generates the inconsistencies as prompt sentences based on the proposed rules and the existing rules, as follows:

[0755] plain

[0756] Proposed rule: Change machine maintenance inspection frequency to once a week.

[0757] Existing rules: Machine maintenance inspections twice a month.

[0758] Detect the inconsistencies.

[0759] Based on the analysis results returned by the generative AI model, the server creates feedback and notifies the user. The feedback includes the new rules generated and whether or not there are any inconsistencies. For example, if there are no inconsistencies, the server notifies the user that "a new rule can be introduced."

[0760] The user checks the feedback and, if final confirmation is obtained, submits the final rules to the system. The server then notifies and shares the final confirmed rules with all users within the organization. This ensures that the latest rules and instructions are quickly and reliably communicated to everyone on-site.

[0761] This system will streamline the management of work rules and instructions within the factory, making it possible to maintain work efficiency and product quality.

[0762] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0763] Step 1:

[0764] A user uses a smart device (smartphone, tablet, head-mounted display, factory robot) to input a request to create a new rule. For example, the user might input "Change the machine maintenance inspection frequency to once a week" and click the send button. At this time, the input data is sent to the server as an HTTP request.

[0765] Step 2:

[0766] The server accepts the HTTP request data received from the user and verifies the integrity of the data. At this time, it checks whether the format and content of the request data are correct. Next, it sends a query to the database (PostgreSQL) to obtain existing related rule information. For example, it searches for and obtains a rule such as "Machine maintenance inspections should be performed twice a month." The obtained data is stored in internal memory.

[0767] Step 3:

[0768] The server compiles existing rules and user suggestions into a data packet and sends it to the generative AI model (OpenAI API). The generative AI model generates new rules based on the received data and analyzes any inconsistencies with existing rules. An example of a prompt sentence used in this process is as follows:

[0769] plain

[0770] Proposed rule: Change machine maintenance inspection frequency to once a week.

[0771] Existing rules: Machine maintenance inspections twice a month.

[0772] Detect the inconsistencies.

[0773] Based on this prompt, the generative AI model returns new rules and analysis results of inconsistencies.

[0774] Step 4:

[0775] The server receives the analysis results returned by the generative AI model and creates feedback based on them. The feedback includes information on new rules and inconsistencies. For example, a message such as "New rules can be introduced" is generated. This feedback is sent to the user as a notification.

[0776] Step 5:

[0777] The user reviews the feedback on their smart device and, if necessary, modifies and resubmits the proposal or finalizes new rules based on the feedback.

[0778] Step 6:

[0779] The user sends the finalized rules from the terminal to the server, which then forwards the finalized rules to the shared system, which then notifies all users in the organization of the new rules and makes them applicable.

[0780] Step 7:

[0781] Devices (smartphones, tablets, head-mounted displays) will receive notifications and display messages to confirm the new rules, allowing all users to quickly understand the latest rules.

[0782] 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.

[0783] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules, and further combines it with an emotion engine that recognizes the user's emotions. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users within the organization. An embodiment of this system is described in detail below.

[0784] System Program Overview

[0785] 1. Acceptance of rule generation requests

[0786] User

[0787] The user enters the proposed new rules or changes into a dedicated form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00 to 18:00) is entered.

[0788] Terminal

[0789] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[0790] 2. Get existing rules

[0791] server

[0792] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[0793] server

[0794] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[0795] 3. Rule generation and analysis using generative AI models

[0796] server

[0797] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[0798] Generative AI Models

[0799] The generative AI model generates new rules based on the received data. For example, it generates a new working hours policy (9:00 AM to 6:00 PM). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00 PM to 1:00 PM) are consistent.

[0800] 4. Emotional Analysis of Users by Emotion Engine

[0801] server

[0802] The server sends the data obtained from the user interface to the emotion engine.

[0803] Emotion Engine

[0804] The emotion engine analyzes emotions based on user input and interactions, for example, determining stress or satisfaction from user input and click frequency.

[0805] 5. Providing Feedback

[0806] server

[0807] The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides feedback to the user. For example, it sends an email containing information that the inconsistency is "not inconsistent with the lunch break time" and a message corresponding to the user's emotional state.

[0808] User

[0809] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[0810] 6. Finalize and share the rules

[0811] User

[0812] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[0813] server

[0814] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[0815] Terminal

[0816] Your device will receive a notification and display a message to confirm the new rule.

[0817] Specific examples

[0818] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[0819] 1. User enters a suggestion

[0820] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[0821] 2. Get existing rules

[0822] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[0823] 3. Analysis using generative AI models

[0824] Server: Sends new proposals and existing rules to the generative AI model.

[0825] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[0826] 4. Analysis by Emotion Engine

[0827] Server: Sends user input data to the emotion engine.

[0828] Emotion engine: Analyzes user emotions and determines stress and satisfaction.

[0829] 5. Conflict detection and feedback

[0830] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[0831] Server: Compiles the feedback and sends notifications with messages depending on the user's emotional state.

[0832] 6. Sharing rules

[0833] User: Review feedback and submit final version from device.

[0834] Server: Notifies all users of the final rules and transfers them to the shared system.

[0835] Through the above process, complex organizational rules can be managed simply and easily and widely disseminated.By using an emotion engine, this system provides more personalized feedback according to the user's emotional state, more effectively supporting communication and business operations within an organization.

[0836] The processing flow will be explained below.

[0837] Step 1:

[0838] User

[0839] The user enters a proposal for a new rule or change into the form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00-18:00) is entered.

[0840] Step 2:

[0841] Terminal

[0842] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[0843] Step 3:

[0844] server

[0845] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[0846] Step 4:

[0847] server

[0848] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[0849] Step 5:

[0850] server

[0851] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[0852] Step 6:

[0853] Generative AI Models

[0854] The generative AI model analyzes the received data and generates new rules. For example, it generates a new working hours policy (9:00-18:00). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00-13:00) are consistent.

[0855] Step 7:

[0856] Generative AI Models

[0857] The generative AI model outputs the analysis results and creates a list of proposed new rules and contradictions.

[0858] Step 8:

[0859] server

[0860] The server receives the analysis results from the generative AI model, temporarily stores the proposed new rules and any inconsistencies in a database, and then formats the data for feedback to the user.

[0861] Step 9:

[0862] server

[0863] The server sends the data obtained from the user interface to the emotion engine.

[0864] Step 10:

[0865] Emotion Engine

[0866] The emotion engine analyzes emotions based on user input and interactions, for example, determining stress or satisfaction from user input and click frequency.

[0867] Step 11:

[0868] server

[0869] The server receives the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user, for example, by sending an email containing information indicating that the discrepancy is not inconsistent with the lunch break time and a message corresponding to the user's emotional state.

[0870] Step 12:

[0871] User

[0872] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[0873] Step 13:

[0874] User

[0875] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[0876] Step 14:

[0877] server

[0878] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[0879] Step 15:

[0880] Terminal

[0881] Your device will receive a notification and display a message to confirm the new rule.

[0882] Through the above processing steps, complex organizational rules can be managed simply and easily and widely disseminated.By using an emotion engine, this system provides more personalized feedback according to the user's emotional state, more effectively supporting communication and business operations within an organization.

[0883] Example 2

[0884] 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."

[0885] In conventional rule management systems, the creation of new rules and the detection of inconsistencies with existing rules were not automated and had to be done manually. This meant that rule creation required a great deal of time and effort, and it was difficult to provide feedback that took into account the user's emotions. This resulted in problems such as reduced usability and disrupted communication within the organization.

[0886] 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.

[0887] In this invention, the server includes means for accepting a rule generation request from a user, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for using an emotion engine to analyze the user's emotional state, means for providing feedback to the user about the generated new rules and inconsistencies, means for reaccepting suggestions and changes based on the feedback, and means for notifying and sharing the final confirmed rules with all users in the organization. This makes rule generation more efficient and automated, and by providing feedback that takes the user's emotional state into consideration, it becomes possible to facilitate communication within the organization.

[0888] "User" refers to an entity that uses the system to request the creation or modification of rules.

[0889] "Means for accepting rule generation requests" refers to an interface or mechanism for accepting new rule suggestions or changes from users.

[0890] "Database" refers to a data storage system for storing existing rule information managed within the system.

[0891] A "generative AI model" refers to a model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[0892] "Means for conflict analysis" refers to a mechanism or algorithm that checks for conflicts between existing rules and new proposed rules.

[0893] "Emotion engine" refers to software or algorithms that analyze emotional states based on user input and interaction data.

[0894] "Means for providing feedback" refers to a mechanism that notifies the user of the generated new rules and the analysis results of inconsistencies, and provides evaluation and advice on the proposals.

[0895] "Means for resubmitting suggestions and changes" refers to an interface or mechanism that allows users to receive feedback and make further suggestions or changes.

[0896] "Means for notifying and sharing finalized rules" refers to a mechanism for notifying and sharing rules that have been finalized by users to all users within an organization.

[0897] The present invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. Furthermore, it incorporates an emotion engine that recognizes the user's emotions, provides feedback to the user about the generated rules and any inconsistencies, and notifies and shares the final confirmed rules with all users within the organization. The following describes in detail an embodiment of the present invention.

[0898] 1. A method for accepting rule generation requests from users

[0899] User

[0900] The user enters new rule proposals or changes into a dedicated form on the device and clicks the "Submit" button. For example, the user can enter a specific proposal such as "Change working hours to 9:00-18:00."

[0901] Terminal

[0902] The terminal receives user input, validates the input data, checking that all required fields are filled in and that the format is correct, and if validation is successful, sends the data to the server as an HTTP request.

[0903] 2. How to retrieve existing rules from a database

[0904] server

[0905] The server receives the HTTP request from the device and verifies that the data format is correct. It checks that the request is in JSON format.

[0906] server

[0907] The server accesses the database and retrieves existing rule information. For example, it retrieves information from the database that "the current working hours policy is 8:00 to 17:00." The retrieved information is saved for use in the next step.

[0908] 3. A means of generating new rules using generative AI models and analyzing inconsistencies with existing rules

[0909] server

[0910] The server collects the existing rules and the user's new proposals into a data packet and sends it to the generative AI model. For example, it formats the data in a format such as "existing rules: working hours 8:00-17:00, new proposal: 9:00-18:00."

[0911] Generative AI Models

[0912] The generative AI model generates new rules based on the received data. For example, it generates "new working hours: 9:00 AM to 6:00 PM." It also checks for inconsistencies with existing rules. For example, it checks whether the new rules conflict with the lunch break time (12:00 PM to 1:00 PM).

[0913] 4. Using an emotion engine to analyze the user's emotional state

[0914] server

[0915] The server sends data obtained from the user interface to the emotion engine, including user-entered text and interaction data.

[0916] Emotion Engine

[0917] The emotion engine analyzes emotions based on user input and interactions, for example, determining that a user is stressed if they are making a lot of edits.

[0918] 5. A means of providing feedback to the user about new rules and inconsistencies

[0919] server

[0920] The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides this as feedback to the user. For example, it sends an email containing information such as "The new working hours of 9:00 AM to 6:00 PM are consistent with the lunch break time" and a message saying "The feedback you provided has been completed."

[0921] 6. A way to re-open the project for suggestions and changes based on feedback

[0922] User

[0923] Users receive feedback, review it on their devices, and, if necessary, make further suggestions or modify existing suggestions.

[0924] Terminal

[0925] The device will then accept new suggestions and modifications from the user and send them to the server again.

[0926] 7. How to communicate and share the finalized rules with all users in the organization

[0927] User

[0928] The user makes a final confirmation and sends the final version of the rules to the server from the terminal. For example, the user may confirm, "I officially approve this new working hours policy (9:00-18:00)."

[0929] server

[0930] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, by email or through an internal notification system, informing everyone that the new working hours policy has been approved.

[0931] Terminal

[0932] The device receives the notification and displays a message to the user to confirm the new rules, for example, a notification saying "Please review the new working hours policy."

[0933] Specific examples

[0934] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[0935] 1. User enters a suggestion

[0936] User: Enter "Proposal to change working hours to 9:00-18:00" into the form on the device and submit it.

[0937] 2. Get existing rules

[0938] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[0939] 3. Analysis using generative AI models

[0940] Server: Sends new proposals and existing rules to the generative AI model.

[0941] Generative AI model: Checks whether "Working hours 9:00-18:00" conflicts with lunch break times (12:00-13:00).

[0942] 4. Analysis by Emotion Engine

[0943] Server: Sends user input data to the emotion engine.

[0944] Emotion engine: Analyzes user emotions and determines stress and satisfaction.

[0945] 5. Conflict detection and feedback

[0946] Generative AI model: Confirms that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are acceptable and sends them back to the server.

[0947] Server: Compiles the feedback and sends notifications with messages depending on the user's emotional state.

[0948] 6. Sharing rules

[0949] User: Review feedback and submit final version from device.

[0950] Server: Notifies all users of the final rules and transfers them to the shared system.

[0951] Prompt Sentence Examples

[0952] "I would like to propose a new working hours policy of 9am to 6pm. Please check for any inconsistencies with existing policies and provide feedback."

[0953] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0954] Step 1:

[0955] User: The user enters new rule suggestions or changes into a dedicated form on the terminal. The input includes a new working hours policy (e.g., "Change working hours to 9:00-18:00"). By clicking the "Submit" button, the suggestion is sent to the system.

[0956] Input: Propose a new rule (e.g., "Change working hours to 9:00-18:00")

[0957] Output: Data sent to the server as an HTTP request

[0958] Step 2:

[0959] Terminal: The terminal validates the received user input data, checking that the input data is correctly formatted and that all required fields are filled in. If validation is successful, the terminal sends the data to the server as an HTTP request.

[0960] Input: User-entered data

[0961] Output: Sent to the server as an HTTP request

[0962] Step 3:

[0963] Server: The server receives the HTTP request from the device, verifies that the data format is correct, and checks that the request is in JSON format, and then passes the data to the next step.

[0964] Input: HTTP request data

[0965] Output: Validated data

[0966] Step 4:

[0967] Server: The server accesses the database and retrieves existing rule information. For example, it retrieves information from the database that "the current working hours policy is 8:00 to 17:00." This retrieved information is saved for use in the next step.

[0968] Input: The request to be retrieved from the database

[0969] Output: Existing rule information

[0970] Step 5:

[0971] Server: The server compiles the existing rules and the user's new proposal into a data packet and sends it to the generative AI model. The data is formatted as "Existing rules: working hours 8:00-17:00, new proposal: 9:00-18:00."

[0972] Input: Existing rule information and new rule proposals

[0973] Output: Data packets

[0974] Step 6:

[0975] Generative AI model: The generative AI model generates new rules based on the data it receives. For example, it generates "new working hours will be from 9:00 to 18:00." It also checks for inconsistencies with existing rules. For example, it checks whether "working hours and lunch break times (12:00 to 13:00) are consistent."

[0976] Input: Data packet (existing rules and new proposals)

[0977] Output: New rules and conflict information

[0978] Step 7:

[0979] Server: The server receives output data from the generative AI model and sends data obtained from the user interface to the emotion engine.

[0980] Input: Output data of generative AI model, data from user interface

[0981] Output: Data sent to the emotion engine

[0982] Step 8:

[0983] Emotion Engine: The emotion engine analyzes emotions based on user input and interactions. For example, if a user makes a lot of edits, it determines that the user is stressed.

[0984] Input: User interface data

[0985] Output: User sentiment analysis results

[0986] Step 9:

[0987] Server: The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides feedback to the user. For example, it sends an email containing information such as "The new working hours of 9:00 AM to 6:00 PM are consistent with the lunch break time" and a message saying "The feedback you provided has been completed."

[0988] Input: Output of generative AI model, analysis results of emotion engine

[0989] Output: Feedback to the user

[0990] Step 10:

[0991] User: The user receives the feedback, reviews it on their device, and can resubmit or revise existing suggestions as needed.

[0992] Input: Feedback

[0993] Output: Re-proposal or revised proposal

[0994] Step 11:

[0995] User: The user performs the final confirmation and sends the final version of the rules to the server from the terminal. For example, the user confirms, "I officially approve this new working hours policy (9:00-18:00)."

[0996] Input: Finalized rules

[0997] Output: Final rules sent to the server

[0998] Step 12:

[0999] Server: The server transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, by email or through the internal notification system, informing everyone that the new working hours policy has been approved.

[1000] Input: Final rules

[1001] Output: Notify everyone in the organization

[1002] Step 13:

[1003] Terminal: The terminal receives the notification and displays a message to confirm the new rule. For example, a notification is displayed to the user saying "Please review the new working hours policy."

[1004] Input: Notification from the server

[1005] Output: Message displayed to the user

[1006] (Application example 2)

[1007] 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."

[1008] Managing rule changes and new proposals within an organization requires a lot of manual work, and it is extremely difficult to properly create and share new rules while maintaining consistency with existing rules. Furthermore, if feedback on employee proposals is not provided promptly, it can have a negative impact on employee morale and emotions. This calls for intuitive and efficient rule management and feedback that takes employee feelings into consideration.

[1009] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a rule generation request from a user, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for analyzing the user's emotional state using an emotion engine that recognizes the user's emotions, means for providing feedback based on the generated new rules, inconsistencies, and the user's emotional state, and means for notifying and sharing the final confirmed rules with all users in the organization. This makes it possible to efficiently manage rule changes within the organization and provide personalized feedback according to the user's emotional state.

[1010] A "user" is a person or organization that uses the system to make a rule generation request.

[1011] The "means for accepting rule generation requests" is an interface or function that accepts suggestions and changes regarding rule generation from the user.

[1012] The "means for obtaining existing rules from a database" is a function for searching and obtaining current rule information stored in a database.

[1013] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[1014] An "emotion engine" is an algorithm or system for analyzing and recognizing a user's emotional state from their input and behavior.

[1015] The "means for providing feedback" is a function that provides the user with appropriate information based on the new rules, discrepancies, and emotional state that have been generated.

[1016] The "means for notifying and sharing rules" refers to a function or system for notifying and sharing the finalized rules with all users within the organization.

[1017] A system for implementing this invention includes a series of processes required to accept rule generation requests from users, collect existing rules, generate new rules, detect inconsistencies, provide feedback, and notify all users in an organization of the final confirmed rules.

[1018] First, a user inputs a rule generation request using a smartphone application. The user enters suggestions or changes through a form in the app and clicks the "Submit" button. For example, a suggestion could be to change working hours. The device receives this input data and sends it to the server as an HTTP request. Basic validation is performed to ensure the data format and content are correct.

[1019] The server then receives the HTTP request and checks the data format for validity. If the input data is in the correct format, the server accesses a database to retrieve existing rules, such as the current working hours policy.

[1020] The server assembles this data into data packets and sends them to a generative AI model, which uses machine learning frameworks like TensorFlow to generate new rules and analyze existing rules for inconsistencies—for example, checking that a new work hour policy doesn't conflict with lunch break times.

[1021] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This emotion engine analyzes the user's input and interactions to determine stress and satisfaction. The server receives the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user. For example, a notification containing information indicating there are no inconsistencies or a message corresponding to the user's emotional state may be sent.

[1022] Finally, if the user reviews the feedback and modifies and confirms the rules to their satisfaction, the details are sent to the server. The server then notifies all users in the organization of the final confirmed rules and stores them in a shared system. Notifications are sent via email and the internal notification system to ensure that everyone is aware of the new rules.

[1023] Prompt Sentence Examples

[1024] The following is an example of a prompt sentence to be used when sending a rule generation request to the server.

[1025] api_url = 'http: / / example.com / submit-proposal'

[1026] headers = {'Content-Type': 'application / json'}

[1027] proposal_data = {

[1028] 'proposal': 'I would like to extend the afternoon break to 30 minutes'

[1029] }

[1030] response = requests.post(api_url, json=proposal_data, headers=headers)

[1031] print(response.json())

[1032] As described above, an embodiment of the present invention optimizes organizational rule management and employee feedback provision by combining an efficient and intuitive user interface with an advanced generative AI model and emotion engine. This system is expected to significantly simplify the process from proposal to final confirmation and improve employee satisfaction.

[1033] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1034] Step 1:

[1035] The user inputs a rule generation request. Using a smartphone app, the user inputs new rules or proposed changes into a dedicated form. This input data is sent to the system by clicking the "Submit" button. A specific input might be something like "I would like to extend the afternoon break to 30 minutes." The output is an HTTP request in which this proposal is sent to the server.

[1036] Step 2:

[1037] The terminal receives input data and sends it to the server as an HTTP request. The terminal checks the format and content of the input data and performs basic validation. Only data in the correct format is sent to the server. The input is the proposal entered by the user, and the output is an HTTP request containing data that has passed validation.

[1038] Step 3:

[1039] The server receives an HTTP request and checks the integrity of the data format. The server checks the request content and confirms that it is in the correct format before proceeding to the next step. The input is the data sent from the terminal, and the output is the correct data after the integrity check.

[1040] Step 4:

[1041] The server accesses the database to retrieve existing rule information. The server sends a query to the database to search for and retrieve relevant existing rules, for example, the current working hours policy. The input is the proposed data after consistency check, and the output is the existing rule information.

[1042] Step 5:

[1043] The server compiles the acquired data into a data packet and sends it to the generative AI model. The generative AI model generates new rules based on this data and analyzes any inconsistencies with existing rules. For example, it checks whether a new working hours policy conflicts with existing lunch break times. The input is the proposed data and existing rule information, and the output is the generated new rules and the analysis results of any inconsistencies.

[1044] Step 6:

[1045] The server receives the output of the generative AI model (new rules and inconsistencies) and sends the user's input data to the emotion engine. The emotion engine analyzes emotions based on the user's input and interactions. For example, it determines stress and satisfaction from the input text and frequency of clicks. The input is the user's suggested data, and the output is the emotion analysis results.

[1046] Step 7:

[1047] The server integrates the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user. Specifically, it creates a message based on the new rules, inconsistencies, and the user's emotional state, and provides feedback via email or app notification. The input is the new rules, inconsistencies, and emotion analysis results, and the output is the feedback information notified to the user.

[1048] Step 8:

[1049] The user receives and reviews the feedback, and if necessary makes new suggestions or modifies existing suggestions. This results in an iterative process of reviewing and modifying the final rule. The input is the feedback information, and the output is the modified suggestions.

[1050] Step 9:

[1051] When the user performs final confirmation, the terminal sends the final version of the rules to the server. This final rule is stored on the server. The input is the final confirmed rule, and the output is the final rule stored on the server.

[1052] Step 10:

[1053] The server transfers the final confirmed rules to the shared system and notifies all users in the organization. The server notifies all users of the new rules via email or the internal notification system. The input is the final confirmed rules, and the output is the notification to all users.

[1054] This effectively manages the rule change process within an organization and provides personalized feedback according to the user's emotional state.

[1055] 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.

[1056] 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.

[1057] 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.

[1058] [Third embodiment]

[1059] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1060] 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.

[1061] 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).

[1062] 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.

[1063] 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.

[1064] 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).

[1065] 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. 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.

[1066] 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.

[1067] 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.

[1068] 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.

[1069] 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.

[1070] 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."

[1071] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users within the organization. An embodiment of this system is described in detail below.

[1072] System Program Overview

[1073] 1. Acceptance of rule generation requests

[1074] User

[1075] The user enters the proposed new rules or changes into a dedicated form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00 to 18:00) is entered.

[1076] Terminal

[1077] The terminal receives the user's input data and sends it to the server as an HTTP request.

[1078] 2. Get existing rules

[1079] server

[1080] The server receives the HTTP request, checks the integrity of the data, and then retrieves existing rule information from the organization's database. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[1081] 3. Rule generation and analysis using generative AI models

[1082] server

[1083] The server compiles the acquired existing rules and user suggestions into a data packet and sends it to the generative AI model.

[1084] Generative AI Models

[1085] The generative AI model generates new rules based on the received data and analyzes any inconsistencies with existing rules. For example, it checks whether the new rule (9:00 AM to 6:00 PM) conflicts with the existing lunch break time (12:00 PM to 1:00 PM).

[1086] 4. Providing Feedback

[1087] server

[1088] The server receives the output of the generative AI model (the new rule and the inconsistencies) and provides feedback to the user. For example, it sends an email containing information that the inconsistency is not inconsistent with the lunch break time.

[1089] User

[1090] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[1091] 5. Finalize and share the rules

[1092] User

[1093] When final confirmation is received from the user, the final version is sent from the terminal to the server.

[1094] server

[1095] The server transfers the final rules to the shared system and sends notifications to all users within the organization.

[1096] Terminal

[1097] Your device will receive a notification and display a message to confirm the new rule.

[1098] Specific examples

[1099] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[1100] 1. User enters a suggestion

[1101] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[1102] 2. Get existing rules

[1103] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[1104] 3. Analysis using generative AI models

[1105] Server: Sends new proposals and existing rules to the generative AI model.

[1106] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[1107] 4. Conflict detection and feedback

[1108] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[1109] Server: Compiles feedback and notifies users.

[1110] 5. Sharing rules

[1111] User: Review feedback and submit final version from device.

[1112] Server: Notifies all users of the final rules and transfers them to the shared system.

[1113] The above process allows for simple management of complex organizational rules and makes it easy to disseminate them widely. This system efficiently handles everything from rule generation to final sharing, supporting communication within an organization and effective business operations.

[1114] The processing flow will be explained below.

[1115] Step 1:

[1116] User

[1117] The user enters a proposal for a new rule or change into the form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00-18:00) is entered.

[1118] Step 2:

[1119] Terminal

[1120] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[1121] Step 3:

[1122] server

[1123] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[1124] Step 4:

[1125] server

[1126] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[1127] Step 5:

[1128] server

[1129] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[1130] Step 6:

[1131] Generative AI Models

[1132] The generative AI model analyzes the received data and generates new rules. For example, it generates a new working hours policy (9:00-18:00). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00-13:00) are consistent.

[1133] Step 7:

[1134] Generative AI Models

[1135] The generative AI model outputs the analysis results and creates a list of proposed new rules and contradictions.

[1136] Step 8:

[1137] server

[1138] The server receives the analysis results from the generative AI model, temporarily stores the proposed new rules and any inconsistencies in a database, and then formats the data for feedback to the user.

[1139] Step 9:

[1140] server

[1141] The server provides feedback to the user, for example, by sending an email or a notification to the terminal containing information that the discrepancy is "not in conflict with the lunch break time."

[1142] Step 10:

[1143] User

[1144] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[1145] Step 11:

[1146] User

[1147] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[1148] Step 12:

[1149] server

[1150] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[1151] Step 13:

[1152] Terminal

[1153] The device will display a notification of the new rules to all users in the organization, allowing them to check the new rules.

[1154] The above processing steps enable the simple management of complex organizational rules and their widespread dissemination. This system efficiently handles everything from rule generation to final sharing, thereby more effectively supporting communication and business operations within an organization.

[1155] Example 1

[1156] 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."

[1157] In the current system, rule generation and sharing within an organization are not carried out efficiently, and there is a high possibility that conflicts with existing rules will occur, especially when new rules are generated. In addition, suggestions and feedback from users are often not properly reflected, resulting in a lack of responsiveness across the organization. This results in issues such as the time it takes to apply rules and a decline in work efficiency across the organization.

[1158] 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.

[1159] In this invention, the server includes means for accepting rule generation requests from users, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for providing feedback to the user on the generated new rules and inconsistencies, and means for notifying and sharing the final confirmed rules received from the user with all users in the organization. This streamlines the rule generation process and enables automatic analysis of inconsistencies with existing rules, improving responsiveness throughout the organization and enabling improved business efficiency.

[1160] A "user" is a user who submits a rule generation request to the system and checks the feedback.

[1161] A "rule creation request" is a request that a user sends to the system to propose a new rule or a rule change.

[1162] A "database" is an information storage system that stores existing rule information within an organization and allows that information to be searched and retrieved as needed.

[1163] A "generative AI model" is an artificial intelligence system that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[1164] "Inconsistencies" refer to areas of inconsistency or conflict between new rules and existing rules.

[1165] "Feedback" is a response that notifies the user of new rules generated by the generative AI model and information about inconsistencies.

[1166] An "HTTP request" is a communication format for sending user input to a server.

[1167] A "terminal" is a device such as a computer or smartphone that a user uses to request rule generation or check feedback.

[1168] "Intra-organizational" refers to the interior of the particular company or organization to which the rules apply.

[1169] A "notification" is a message sent by the server to notify all users in an organization of new rules or updated information.

[1170] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users in the organization.

[1171] System Configuration

[1172] User

[1173] Users can input new rule suggestions or changes through a dedicated web interface. For example, they can enter a suggestion to change working hours to "9:00 AM - 6:00 PM" into a form and click the "Submit" button. This generates an HTTP request.

[1174] Terminal

[1175] The terminal receives input data from the user and sends it to the server as an HTTP request. The user then checks the terminal for a message indicating that the data has been sent.

[1176] server

[1177] The server receives the HTTP request and first checks the data format and content for consistency. It then accesses the organization's database to retrieve existing rule information. For example, if the existing working hours are "8:00 AM - 5:00 PM," that information is retrieved from the database.

[1178] The server obtains the existing rules and new proposals, converts this information into data packets, and sends them to the generative AI model. The generative AI model generates new rules based on the received data and analyzes any inconsistencies with the existing rules. For example, it checks whether the new working hours of "9:00 AM - 6:00 PM" are consistent with the lunch break time of "12:00 PM - 1:00 PM."

[1179] The analysis results of the generative AI model are returned to the server as new rules and inconsistencies, which the server uses to create feedback messages and send to the user via email or notification.

[1180] The user reviews the feedback and, if necessary, modifies the proposal or approves it for final review. The finalized rules are then sent back to the server, which transfers the final rules to the shared system and sends a notification to all users in the organization that the new rules have been finalized.

[1181] The device will receive a notification and display a message to the user saying "New rules have been shared with you," allowing the user to review and apply the new rules.

[1182] Specific examples

[1183] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[1184] 1. User enters a suggestion

[1185] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[1186] 2. Get existing rules

[1187] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[1188] 3. Analysis using generative AI models

[1189] Server: Sends new proposals and existing rules to the generative AI model.

[1190] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[1191] 4. Conflict detection and feedback

[1192] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[1193] Server: Compiles feedback and notifies users.

[1194] 5. Sharing rules

[1195] User: Review feedback and submit final version from device.

[1196] Server: Notifies all users of the final rules and transfers them to the shared system.

[1197] Device: Notify the user that a new rule has been shared with them.

[1198] This system streamlines the rule generation process and can automatically analyze inconsistencies with existing rules, improving responsiveness across the organization and enabling improved operational efficiency.

[1199] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1200] Step 1:

[1201] (User inputs and submits rule generation request)

[1202] The user enters a new rule proposal or changes into a dedicated web form and clicks the "Submit" button. For example, a proposal to change working hours to "9:00-18:00" is entered. This generates the user's input (proposed new rule) as input data.

[1203] Input: Propose a new rule (e.g., change working hours)

[1204] Output: User input data (in HTTP request format)

[1205] Step 2:

[1206] (The device sends the user's input data to the server)

[1207] The terminal receives the user's input data and sends it to the server as an HTTP request. After the request is sent, a "Send completed" message is displayed to notify the user.

[1208] Input: User input data (proposed new rules)

[1209] Output: "Sent" message

[1210] Step 3:

[1211] (Server retrieves existing rules)

[1212] The server receives the HTTP request and checks the data format and content for consistency. Next, it accesses the organization's database to retrieve existing rule information. For example, it searches for and retrieves rules that include the existing working hours of "8:00 AM - 5:00 PM."

[1213] Input: User input data (HTTP request), existing rule information

[1214] Output: Existing rules (e.g., working hours "8:00-17:00")

[1215] Step 4:

[1216] (The server sends the data to the generative AI model)

[1217] The server compiles the acquired existing rules and user suggestions, converts them into a data packet, and sends it to the generative AI model. Specifically, it structures the data in JSON format or similar and generates a data packet that includes the new rules and existing rules.

[1218] Input: User suggestions, existing rules

[1219] Output: Data packet (e.g., JSON format)

[1220] Step 5:

[1221] (The generative AI model generates rules and performs analysis)

[1222] The generative AI model analyzes the received data packets and generates new rules. It also checks whether the generated rules are consistent with existing rules. For example, it checks whether a new work schedule of "9:00 AM - 6:00 PM" is consistent with a lunch break of "12:00 PM - 1:00 PM."

[1223] Input: Data packet (new rule / existing rule)

[1224] Output: New rules, list of inconsistencies

[1225] Step 6:

[1226] (Server sends feedback to user)

[1227] The server receives the output data (new rules and inconsistencies) from the generative AI model and generates a feedback message for the user. For example, it creates a feedback message including the content "The new working hours (9:00-18:00) are not inconsistent with the lunch break time (12:00-13:00)" and sends it to the user via email or notification.

[1228] Input: New rules, list of discrepancies

[1229] Output: Feedback message

[1230] Step 7:

[1231] (User checks feedback)

[1232] The user receives the feedback, reviews it on their device, considers it, makes new suggestions or modifies existing ones as needed, and if there are no problems, approves it for final review.

[1233] Input: Feedback message

[1234] Output: Approved final rules or proposed amendments

[1235] Step 8:

[1236] (User submits finalized rule)

[1237] Once the user has reviewed the feedback and finalized the rules, the terminal sends the final rules to the server, including details of the final approved rules.

[1238] Input: Approved Final Rules

[1239] Output: Data sent to the server

[1240] Step 9:

[1241] (Server shares the final rules)

[1242] The server receives the final rules, transfers them to the shared system, and sends a notification to all users in the organization that the new rules have been finalized, for example via an intranet or internal chat tool.

[1243] Input: Final rules

[1244] Output: Notification to all users in the organization

[1245] Step 10:

[1246] (Device displays notification)

[1247] The device will receive a notification and display a message to the user saying "New rules have been shared with you," allowing the user to review and apply the new rules.

[1248] Input: Notification from the server

[1249] Output: Display of notification message

[1250] Through the above steps, the process from a user's rule generation request to the final sharing of the rules can be carried out efficiently.

[1251] (Application example 1)

[1252] 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."

[1253] In factories, work rules and work instructions are frequently changed, and the latest rules and instructions may not be communicated quickly and reliably to everyone on the shop floor. This problem is particularly pronounced in complex manufacturing and quality control processes, and can lead to reduced work efficiency and deterioration of product quality. Conventional manual methods of rule management and sharing cannot adequately solve these issues, creating a need for automated systems.

[1254] 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.

[1255] In this invention, the server includes means for accepting rule generation requests from users, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for providing feedback to the user on the generated new rules and inconsistencies, means for notifying and sharing the final confirmed rules with all users in the organization, and means for generating, managing, and sharing rules and work instructions within the factory via smart devices (smartphones, tablets, head-mounted displays, factory robots). This allows the latest work rules and instructions to be quickly and reliably communicated to everyone on site, improving work efficiency and ensuring product quality.

[1256] A "user" is an individual or member of an organization who accesses the system and makes a rule generation request.

[1257] The "means for accepting rule generation requests" is an interface that has the function of accepting proposals for new rules or rule changes from users.

[1258] The "means for obtaining existing rules from a database" is a program that has the function of searching for and obtaining existing rule information stored in a database within an organization.

[1259] A "generative AI model" is an artificial intelligence model used to generate new rules based on input data and analyze inconsistencies with existing rules.

[1260] The "feedback means" is a system that has the function of notifying the user of the new rules that have been generated and the results of the analysis of contradictions.

[1261] The "means for notifying and sharing the final confirmed rules" is a system that has the function of quickly notifying all users in the organization of the rules that have received final confirmation from the users and sharing them.

[1262] A "smart device" is a portable electronic terminal (e.g., smartphone, tablet, head-mounted display, factory robot) that a user uses to access the system, submit rule generation requests, and receive feedback.

[1263] This invention is a system for efficiently managing, generating, and sharing rules and work instructions within a factory. This system accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. It also provides feedback on the generated rules and inconsistencies to the user, and notifies and shares the final confirmed rules with all users within the organization.

[1264] 1. Hardware and Software Configuration

[1265] The system is implemented using the following hardware and software:

[1266] Server: Accepts rule generation requests, retrieves existing rules from the database, executes the generative AI model, generates feedback, and finalizes and shares the rules.

[1267] Devices: Smartphones, tablets, head-mounted displays, and factory robots for inputting rule generation requests

[1268] Database: PostgreSQL (management of existing rules)

[1269] Generative AI model: OpenAI API (new rule generation and inconsistency analysis)

[1270] Framework: Flask (Web interface implementation)

[1271] 2. Overview of the processing procedure

[1272] A user uses a smart device to send a rule generation request to the system. This request includes a new rule or a proposed change, such as "Change the frequency of machine maintenance inspections to once a week." The server receives this request and retrieves existing rules from the database.

[1273] The server sends the existing rules and the new proposal to the generative AI model, which generates new rules and analyzes the inconsistencies with the existing rules.The generative AI model generates the inconsistencies as prompt sentences based on the proposed rules and the existing rules, as follows:

[1274] plain

[1275] Proposed rule: Change machine maintenance inspection frequency to once a week.

[1276] Existing rules: Machine maintenance inspections twice a month.

[1277] Detect the inconsistencies.

[1278] Based on the analysis results returned by the generative AI model, the server creates feedback and notifies the user. The feedback includes the new rules generated and whether or not there are any inconsistencies. For example, if there are no inconsistencies, the server notifies the user that "a new rule can be introduced."

[1279] The user checks the feedback and, if final confirmation is obtained, submits the final rules to the system. The server then notifies and shares the final confirmed rules with all users within the organization. This ensures that the latest rules and instructions are quickly and reliably communicated to everyone on-site.

[1280] This system will streamline the management of work rules and instructions within the factory, making it possible to maintain work efficiency and product quality.

[1281] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1282] Step 1:

[1283] A user uses a smart device (smartphone, tablet, head-mounted display, factory robot) to input a request to create a new rule. For example, the user might input "Change the machine maintenance inspection frequency to once a week" and click the send button. At this time, the input data is sent to the server as an HTTP request.

[1284] Step 2:

[1285] The server accepts the HTTP request data received from the user and verifies the integrity of the data. At this time, it checks whether the format and content of the request data are correct. Next, it sends a query to the database (PostgreSQL) to obtain existing related rule information. For example, it searches for and obtains a rule such as "Machine maintenance inspections should be performed twice a month." The obtained data is stored in internal memory.

[1286] Step 3:

[1287] The server compiles existing rules and user suggestions into a data packet and sends it to the generative AI model (OpenAI API). The generative AI model generates new rules based on the received data and analyzes any inconsistencies with existing rules. An example of a prompt sentence used in this process is as follows:

[1288] plain

[1289] Proposed rule: Change machine maintenance inspection frequency to once a week.

[1290] Existing rules: Machine maintenance inspections twice a month.

[1291] Detect the inconsistencies.

[1292] Based on this prompt, the generative AI model returns new rules and analysis results of inconsistencies.

[1293] Step 4:

[1294] The server receives the analysis results returned by the generative AI model and creates feedback based on them. The feedback includes information on new rules and inconsistencies. For example, a message such as "New rules can be introduced" is generated. This feedback is sent to the user as a notification.

[1295] Step 5:

[1296] The user reviews the feedback on their smart device and, if necessary, modifies and resubmits the proposal or finalizes new rules based on the feedback.

[1297] Step 6:

[1298] The user sends the finalized rules from the terminal to the server, which then forwards the finalized rules to the shared system, which then notifies all users in the organization of the new rules and makes them applicable.

[1299] Step 7:

[1300] Devices (smartphones, tablets, head-mounted displays) will receive notifications and display messages to confirm the new rules, allowing all users to quickly understand the latest rules.

[1301] 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.

[1302] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules, and further combines it with an emotion engine that recognizes the user's emotions. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users within the organization. An embodiment of this system is described in detail below.

[1303] System Program Overview

[1304] 1. Acceptance of rule generation requests

[1305] User

[1306] The user enters the proposed new rules or changes into a dedicated form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00 to 18:00) is entered.

[1307] Terminal

[1308] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[1309] 2. Get existing rules

[1310] server

[1311] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[1312] server

[1313] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[1314] 3. Rule generation and analysis using generative AI models

[1315] server

[1316] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[1317] Generative AI Models

[1318] The generative AI model generates new rules based on the received data. For example, it generates a new working hours policy (9:00 AM to 6:00 PM). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00 PM to 1:00 PM) are consistent.

[1319] 4. Emotional Analysis of Users by Emotion Engine

[1320] server

[1321] The server sends the data obtained from the user interface to the emotion engine.

[1322] Emotion Engine

[1323] The emotion engine analyzes emotions based on user input and interactions, for example, determining stress or satisfaction from user input and click frequency.

[1324] 5. Providing Feedback

[1325] server

[1326] The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides feedback to the user. For example, it sends an email containing information that the inconsistency is "not inconsistent with the lunch break time" and a message corresponding to the user's emotional state.

[1327] User

[1328] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[1329] 6. Finalize and share the rules

[1330] User

[1331] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[1332] server

[1333] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[1334] Terminal

[1335] Your device will receive a notification and display a message to confirm the new rule.

[1336] Specific examples

[1337] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[1338] 1. User enters a suggestion

[1339] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[1340] 2. Get existing rules

[1341] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[1342] 3. Analysis using generative AI models

[1343] Server: Sends new proposals and existing rules to the generative AI model.

[1344] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[1345] 4. Analysis by Emotion Engine

[1346] Server: Sends user input data to the emotion engine.

[1347] Emotion engine: Analyzes user emotions and determines stress and satisfaction.

[1348] 5. Conflict detection and feedback

[1349] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[1350] Server: Compiles the feedback and sends notifications with messages depending on the user's emotional state.

[1351] 6. Sharing rules

[1352] User: Review feedback and submit final version from device.

[1353] Server: Notifies all users of the final rules and transfers them to the shared system.

[1354] Through the above process, complex organizational rules can be managed simply and easily and widely disseminated.By using an emotion engine, this system provides more personalized feedback according to the user's emotional state, more effectively supporting communication and business operations within an organization.

[1355] The processing flow will be explained below.

[1356] Step 1:

[1357] User

[1358] The user enters a proposal for a new rule or change into the form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00-18:00) is entered.

[1359] Step 2:

[1360] Terminal

[1361] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[1362] Step 3:

[1363] server

[1364] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[1365] Step 4:

[1366] server

[1367] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[1368] Step 5:

[1369] server

[1370] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[1371] Step 6:

[1372] Generative AI Models

[1373] The generative AI model analyzes the received data and generates new rules. For example, it generates a new working hours policy (9:00-18:00). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00-13:00) are consistent.

[1374] Step 7:

[1375] Generative AI Models

[1376] The generative AI model outputs the analysis results and creates a list of proposed new rules and contradictions.

[1377] Step 8:

[1378] server

[1379] The server receives the analysis results from the generative AI model, temporarily stores the proposed new rules and any inconsistencies in a database, and then formats the data for feedback to the user.

[1380] Step 9:

[1381] server

[1382] The server sends the data obtained from the user interface to the emotion engine.

[1383] Step 10:

[1384] Emotion Engine

[1385] The emotion engine analyzes emotions based on user input and interactions, for example, determining stress or satisfaction from user input and click frequency.

[1386] Step 11:

[1387] server

[1388] The server receives the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user, for example, by sending an email containing information indicating that the discrepancy is not inconsistent with the lunch break time and a message corresponding to the user's emotional state.

[1389] Step 12:

[1390] User

[1391] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[1392] Step 13:

[1393] User

[1394] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[1395] Step 14:

[1396] server

[1397] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[1398] Step 15:

[1399] Terminal

[1400] Your device will receive a notification and display a message to confirm the new rule.

[1401] Through the above processing steps, complex organizational rules can be managed simply and easily and widely disseminated.By using an emotion engine, this system provides more personalized feedback according to the user's emotional state, more effectively supporting communication and business operations within an organization.

[1402] Example 2

[1403] 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."

[1404] In conventional rule management systems, the creation of new rules and the detection of inconsistencies with existing rules were not automated and had to be done manually. This meant that rule creation required a great deal of time and effort, and it was difficult to provide feedback that took into account the user's emotions. This resulted in problems such as reduced usability and disrupted communication within the organization.

[1405] 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.

[1406] In this invention, the server includes means for accepting a rule generation request from a user, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for using an emotion engine to analyze the user's emotional state, means for providing feedback to the user about the generated new rules and inconsistencies, means for reaccepting suggestions and changes based on the feedback, and means for notifying and sharing the final confirmed rules with all users in the organization. This makes rule generation more efficient and automated, and by providing feedback that takes the user's emotional state into consideration, it becomes possible to facilitate communication within the organization.

[1407] "User" refers to an entity that uses the system to request the creation or modification of rules.

[1408] "Means for accepting rule generation requests" refers to an interface or mechanism for accepting new rule suggestions or changes from users.

[1409] "Database" refers to a data storage system for storing existing rule information managed within the system.

[1410] A "generative AI model" refers to a model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[1411] "Means for conflict analysis" refers to a mechanism or algorithm that checks for conflicts between existing rules and new proposed rules.

[1412] "Emotion engine" refers to software or algorithms that analyze emotional states based on user input and interaction data.

[1413] "Means for providing feedback" refers to a mechanism that notifies the user of the generated new rules and the analysis results of inconsistencies, and provides evaluation and advice on the proposals.

[1414] "Means for resubmitting suggestions and changes" refers to an interface or mechanism that allows users to receive feedback and make further suggestions or changes.

[1415] "Means for notifying and sharing finalized rules" refers to a mechanism for notifying and sharing rules that have been finalized by users to all users within an organization.

[1416] The present invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. Furthermore, it incorporates an emotion engine that recognizes the user's emotions, provides feedback to the user about the generated rules and any inconsistencies, and notifies and shares the final confirmed rules with all users within the organization. The following describes in detail an embodiment of the present invention.

[1417] 1. A method for accepting rule generation requests from users

[1418] User

[1419] The user enters new rule proposals or changes into a dedicated form on the device and clicks the "Submit" button. For example, the user can enter a specific proposal such as "Change working hours to 9:00-18:00."

[1420] Terminal

[1421] The terminal receives user input, validates the input data, checking that all required fields are filled in and that the format is correct, and if validation is successful, sends the data to the server as an HTTP request.

[1422] 2. How to retrieve existing rules from a database

[1423] server

[1424] The server receives the HTTP request from the device and verifies that the data format is correct. It checks that the request is in JSON format.

[1425] server

[1426] The server accesses the database and retrieves existing rule information. For example, it retrieves information from the database that "the current working hours policy is 8:00 to 17:00." The retrieved information is saved for use in the next step.

[1427] 3. A means of generating new rules using generative AI models and analyzing inconsistencies with existing rules

[1428] server

[1429] The server collects the existing rules and the user's new proposals into a data packet and sends it to the generative AI model. For example, it formats the data in a format such as "existing rules: working hours 8:00-17:00, new proposal: 9:00-18:00."

[1430] Generative AI Models

[1431] The generative AI model generates new rules based on the received data. For example, it generates "new working hours: 9:00 AM to 6:00 PM." It also checks for inconsistencies with existing rules. For example, it checks whether the new rules conflict with the lunch break time (12:00 PM to 1:00 PM).

[1432] 4. Using an emotion engine to analyze the user's emotional state

[1433] server

[1434] The server sends data obtained from the user interface to the emotion engine, including user-entered text and interaction data.

[1435] Emotion Engine

[1436] The emotion engine analyzes emotions based on user input and interactions, for example, determining that a user is stressed if they are making a lot of edits.

[1437] 5. A means of providing feedback to the user about new rules and inconsistencies

[1438] server

[1439] The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides this as feedback to the user. For example, it sends an email containing information such as "The new working hours of 9:00 AM to 6:00 PM are consistent with the lunch break time" and a message saying "The feedback you provided has been completed."

[1440] 6. A way to re-open the project for suggestions and changes based on feedback

[1441] User

[1442] Users receive feedback, review it on their devices, and, if necessary, make further suggestions or modify existing suggestions.

[1443] Terminal

[1444] The device will then accept new suggestions and modifications from the user and send them to the server again.

[1445] 7. How to communicate and share the finalized rules with all users in the organization

[1446] User

[1447] The user makes a final confirmation and sends the final version of the rules to the server from the terminal. For example, the user may confirm, "I officially approve this new working hours policy (9:00-18:00)."

[1448] server

[1449] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, by email or through an internal notification system, informing everyone that the new working hours policy has been approved.

[1450] Terminal

[1451] The device receives the notification and displays a message to the user to confirm the new rules, for example, a notification saying "Please review the new working hours policy."

[1452] Specific examples

[1453] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[1454] 1. User enters a suggestion

[1455] User: Enter "Proposal to change working hours to 9:00-18:00" into the form on the device and submit it.

[1456] 2. Get existing rules

[1457] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[1458] 3. Analysis using generative AI models

[1459] Server: Sends new proposals and existing rules to the generative AI model.

[1460] Generative AI model: Checks whether "Working hours 9:00-18:00" conflicts with lunch break times (12:00-13:00).

[1461] 4. Analysis by Emotion Engine

[1462] Server: Sends user input data to the emotion engine.

[1463] Emotion engine: Analyzes user emotions and determines stress and satisfaction.

[1464] 5. Conflict detection and feedback

[1465] Generative AI model: Confirms that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are acceptable and sends them back to the server.

[1466] Server: Compiles the feedback and sends notifications with messages depending on the user's emotional state.

[1467] 6. Sharing rules

[1468] User: Review feedback and submit final version from device.

[1469] Server: Notifies all users of the final rules and transfers them to the shared system.

[1470] Prompt Sentence Examples

[1471] "I would like to propose a new working hours policy of 9am to 6pm. Please check for any inconsistencies with existing policies and provide feedback."

[1472] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1473] Step 1:

[1474] User: The user enters new rule suggestions or changes into a dedicated form on the terminal. The input includes a new working hours policy (e.g., "Change working hours to 9:00-18:00"). By clicking the "Submit" button, the suggestion is sent to the system.

[1475] Input: Propose a new rule (e.g., "Change working hours to 9:00-18:00")

[1476] Output: Data sent to the server as an HTTP request

[1477] Step 2:

[1478] Terminal: The terminal validates the received user input data, checking that the input data is correctly formatted and that all required fields are filled in. If validation is successful, the terminal sends the data to the server as an HTTP request.

[1479] Input: User-entered data

[1480] Output: Sent to the server as an HTTP request

[1481] Step 3:

[1482] Server: The server receives the HTTP request from the device, verifies that the data format is correct, and checks that the request is in JSON format, and then passes the data to the next step.

[1483] Input: HTTP request data

[1484] Output: Validated data

[1485] Step 4:

[1486] Server: The server accesses the database and retrieves existing rule information. For example, it retrieves information from the database that "the current working hours policy is 8:00 to 17:00." This retrieved information is saved for use in the next step.

[1487] Input: The request to be retrieved from the database

[1488] Output: Existing rule information

[1489] Step 5:

[1490] Server: The server compiles the existing rules and the user's new proposal into a data packet and sends it to the generative AI model. The data is formatted as "Existing rules: working hours 8:00-17:00, new proposal: 9:00-18:00."

[1491] Input: Existing rule information and new rule proposals

[1492] Output: Data packets

[1493] Step 6:

[1494] Generative AI model: The generative AI model generates new rules based on the data it receives. For example, it generates "new working hours will be from 9:00 to 18:00." It also checks for inconsistencies with existing rules. For example, it checks whether "working hours and lunch break times (12:00 to 13:00) are consistent."

[1495] Input: Data packet (existing rules and new proposals)

[1496] Output: New rules and conflict information

[1497] Step 7:

[1498] Server: The server receives output data from the generative AI model and sends data obtained from the user interface to the emotion engine.

[1499] Input: Output data of generative AI model, data from user interface

[1500] Output: Data sent to the emotion engine

[1501] Step 8:

[1502] Emotion Engine: The emotion engine analyzes emotions based on user input and interactions. For example, if a user makes a lot of edits, it determines that the user is stressed.

[1503] Input: User interface data

[1504] Output: User sentiment analysis results

[1505] Step 9:

[1506] Server: The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides feedback to the user. For example, it sends an email containing information such as "The new working hours of 9:00 AM to 6:00 PM are consistent with the lunch break time" and a message saying "The feedback you provided has been completed."

[1507] Input: Output of generative AI model, analysis results of emotion engine

[1508] Output: Feedback to the user

[1509] Step 10:

[1510] User: The user receives the feedback, reviews it on their device, and can resubmit or revise existing suggestions as needed.

[1511] Input: Feedback

[1512] Output: Re-proposal or revised proposal

[1513] Step 11:

[1514] User: The user performs the final confirmation and sends the final version of the rules to the server from the terminal. For example, the user confirms, "I officially approve this new working hours policy (9:00-18:00)."

[1515] Input: Finalized rules

[1516] Output: Final rules sent to the server

[1517] Step 12:

[1518] Server: The server transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, by email or through the internal notification system, informing everyone that the new working hours policy has been approved.

[1519] Input: Final rules

[1520] Output: Notify everyone in the organization

[1521] Step 13:

[1522] Terminal: The terminal receives the notification and displays a message to confirm the new rule. For example, a notification is displayed to the user saying "Please review the new working hours policy."

[1523] Input: Notification from the server

[1524] Output: Message displayed to the user

[1525] (Application example 2)

[1526] 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."

[1527] Managing rule changes and new proposals within an organization requires a lot of manual work, and it is extremely difficult to properly create and share new rules while maintaining consistency with existing rules. Furthermore, if feedback on employee proposals is not provided promptly, it can have a negative impact on employee morale and emotions. This calls for intuitive and efficient rule management and feedback that takes employee feelings into consideration.

[1528] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a rule generation request from a user, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for analyzing the user's emotional state using an emotion engine that recognizes the user's emotions, means for providing feedback based on the generated new rules, inconsistencies, and the user's emotional state, and means for notifying and sharing the final confirmed rules with all users in the organization. This makes it possible to efficiently manage rule changes within the organization and provide personalized feedback according to the user's emotional state.

[1529] A "user" is a person or organization that uses the system to make a rule generation request.

[1530] The "means for accepting rule generation requests" is an interface or function that accepts suggestions and changes regarding rule generation from the user.

[1531] The "means for obtaining existing rules from a database" is a function for searching and obtaining current rule information stored in a database.

[1532] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[1533] An "emotion engine" is an algorithm or system for analyzing and recognizing a user's emotional state from their input and behavior.

[1534] The "means for providing feedback" is a function that provides the user with appropriate information based on the new rules, discrepancies, and emotional state that have been generated.

[1535] The "means for notifying and sharing rules" refers to a function or system for notifying and sharing the finalized rules with all users within the organization.

[1536] A system for implementing this invention includes a series of processes required to accept rule generation requests from users, collect existing rules, generate new rules, detect inconsistencies, provide feedback, and notify all users in an organization of the final confirmed rules.

[1537] First, a user inputs a rule generation request using a smartphone application. The user enters suggestions or changes through a form in the app and clicks the "Submit" button. For example, a suggestion could be to change working hours. The device receives this input data and sends it to the server as an HTTP request. Basic validation is performed to ensure the data format and content are correct.

[1538] The server then receives the HTTP request and checks the data format for validity. If the input data is in the correct format, the server accesses a database to retrieve existing rules, such as the current working hours policy.

[1539] The server assembles this data into data packets and sends them to a generative AI model, which uses machine learning frameworks like TensorFlow to generate new rules and analyze existing rules for inconsistencies—for example, checking that a new work hour policy doesn't conflict with lunch break times.

[1540] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This emotion engine analyzes the user's input and interactions to determine stress and satisfaction. The server receives the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user. For example, a notification containing information indicating there are no inconsistencies or a message corresponding to the user's emotional state may be sent.

[1541] Finally, if the user reviews the feedback and modifies and confirms the rules to their satisfaction, the details are sent to the server. The server then notifies all users in the organization of the final confirmed rules and stores them in a shared system. Notifications are sent via email and the internal notification system to ensure that everyone is aware of the new rules.

[1542] Prompt Sentence Examples

[1543] The following is an example of a prompt sentence to be used when sending a rule generation request to the server.

[1544] api_url = 'http: / / example.com / submit-proposal'

[1545] headers = {'Content-Type': 'application / json'}

[1546] proposal_data = {

[1547] 'proposal': 'I would like to extend the afternoon break to 30 minutes'

[1548] }

[1549] response = requests.post(api_url, json=proposal_data, headers=headers)

[1550] print(response.json())

[1551] As described above, an embodiment of the present invention optimizes organizational rule management and employee feedback provision by combining an efficient and intuitive user interface with an advanced generative AI model and emotion engine. This system is expected to significantly simplify the process from proposal to final confirmation and improve employee satisfaction.

[1552] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1553] Step 1:

[1554] The user inputs a rule generation request. Using a smartphone app, the user inputs new rules or proposed changes into a dedicated form. This input data is sent to the system by clicking the "Submit" button. A specific input might be something like "I would like to extend the afternoon break to 30 minutes." The output is an HTTP request in which this proposal is sent to the server.

[1555] Step 2:

[1556] The terminal receives input data and sends it to the server as an HTTP request. The terminal checks the format and content of the input data and performs basic validation. Only data in the correct format is sent to the server. The input is the proposal entered by the user, and the output is an HTTP request containing data that has passed validation.

[1557] Step 3:

[1558] The server receives an HTTP request and checks the integrity of the data format. The server checks the request content and confirms that it is in the correct format before proceeding to the next step. The input is the data sent from the terminal, and the output is the correct data after the integrity check.

[1559] Step 4:

[1560] The server accesses the database to retrieve existing rule information. The server sends a query to the database to search for and retrieve relevant existing rules, for example, the current working hours policy. The input is the proposed data after consistency check, and the output is the existing rule information.

[1561] Step 5:

[1562] The server compiles the acquired data into a data packet and sends it to the generative AI model. The generative AI model generates new rules based on this data and analyzes any inconsistencies with existing rules. For example, it checks whether a new working hours policy conflicts with existing lunch break times. The input is the proposed data and existing rule information, and the output is the generated new rules and the analysis results of any inconsistencies.

[1563] Step 6:

[1564] The server receives the output of the generative AI model (new rules and inconsistencies) and sends the user's input data to the emotion engine. The emotion engine analyzes emotions based on the user's input and interactions. For example, it determines stress and satisfaction from the input text and frequency of clicks. The input is the user's suggested data, and the output is the emotion analysis results.

[1565] Step 7:

[1566] The server integrates the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user. Specifically, it creates a message based on the new rules, inconsistencies, and the user's emotional state, and provides feedback via email or app notification. The input is the new rules, inconsistencies, and emotion analysis results, and the output is the feedback information notified to the user.

[1567] Step 8:

[1568] The user receives and reviews the feedback, and if necessary makes new suggestions or modifies existing suggestions. This results in an iterative process of reviewing and modifying the final rule. The input is the feedback information, and the output is the modified suggestions.

[1569] Step 9:

[1570] When the user performs final confirmation, the terminal sends the final version of the rules to the server. This final rule is stored on the server. The input is the final confirmed rule, and the output is the final rule stored on the server.

[1571] Step 10:

[1572] The server transfers the final confirmed rules to the shared system and notifies all users in the organization. The server notifies all users of the new rules via email or the internal notification system. The input is the final confirmed rules, and the output is the notification to all users.

[1573] This effectively manages the rule change process within an organization and provides personalized feedback according to the user's emotional state.

[1574] 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.

[1575] 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.

[1576] 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.

[1577] [Fourth embodiment]

[1578] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1579] 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.

[1580] 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).

[1581] 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.

[1582] 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.

[1583] 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).

[1584] 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. 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.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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."

[1591] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users within the organization. An embodiment of this system is described in detail below.

[1592] System Program Overview

[1593] 1. Acceptance of rule generation requests

[1594] User

[1595] The user enters the proposed new rules or changes into a dedicated form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00 to 18:00) is entered.

[1596] Terminal

[1597] The terminal receives the user's input data and sends it to the server as an HTTP request.

[1598] 2. Get existing rules

[1599] server

[1600] The server receives the HTTP request, checks the integrity of the data, and then retrieves existing rule information from the organization's database. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[1601] 3. Rule generation and analysis using generative AI models

[1602] server

[1603] The server compiles the acquired existing rules and user suggestions into a data packet and sends it to the generative AI model.

[1604] Generative AI Models

[1605] The generative AI model generates new rules based on the received data and analyzes any inconsistencies with existing rules. For example, it checks whether the new rule (9:00 AM to 6:00 PM) conflicts with the existing lunch break time (12:00 PM to 1:00 PM).

[1606] 4. Providing Feedback

[1607] server

[1608] The server receives the output of the generative AI model (the new rule and the inconsistencies) and provides feedback to the user. For example, it sends an email containing information that the inconsistency is not inconsistent with the lunch break time.

[1609] User

[1610] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[1611] 5. Finalize and share the rules

[1612] User

[1613] When final confirmation is received from the user, the final version is sent from the terminal to the server.

[1614] server

[1615] The server transfers the final rules to the shared system and sends notifications to all users within the organization.

[1616] Terminal

[1617] Your device will receive a notification and display a message to confirm the new rule.

[1618] Specific examples

[1619] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[1620] 1. User enters a suggestion

[1621] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[1622] 2. Get existing rules

[1623] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[1624] 3. Analysis using generative AI models

[1625] Server: Sends new proposals and existing rules to the generative AI model.

[1626] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[1627] 4. Conflict detection and feedback

[1628] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[1629] Server: Compiles feedback and notifies users.

[1630] 5. Sharing rules

[1631] User: Review feedback and submit final version from device.

[1632] Server: Notifies all users of the final rules and transfers them to the shared system.

[1633] The above process allows for simple management of complex organizational rules and makes it easy to disseminate them widely. This system efficiently handles everything from rule generation to final sharing, supporting communication within an organization and effective business operations.

[1634] The processing flow will be explained below.

[1635] Step 1:

[1636] User

[1637] The user enters a proposal for a new rule or change into the form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00-18:00) is entered.

[1638] Step 2:

[1639] Terminal

[1640] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[1641] Step 3:

[1642] server

[1643] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[1644] Step 4:

[1645] server

[1646] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[1647] Step 5:

[1648] server

[1649] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[1650] Step 6:

[1651] Generative AI Models

[1652] The generative AI model analyzes the received data and generates new rules. For example, it generates a new working hours policy (9:00-18:00). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00-13:00) are consistent.

[1653] Step 7:

[1654] Generative AI Models

[1655] The generative AI model outputs the analysis results and creates a list of proposed new rules and contradictions.

[1656] Step 8:

[1657] server

[1658] The server receives the analysis results from the generative AI model, temporarily stores the proposed new rules and any inconsistencies in a database, and then formats the data for feedback to the user.

[1659] Step 9:

[1660] server

[1661] The server provides feedback to the user, for example, by sending an email or a notification to the terminal containing information that the discrepancy is "not in conflict with the lunch break time."

[1662] Step 10:

[1663] User

[1664] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[1665] Step 11:

[1666] User

[1667] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[1668] Step 12:

[1669] server

[1670] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[1671] Step 13:

[1672] Terminal

[1673] The device will display a notification of the new rules to all users in the organization, allowing them to check the new rules.

[1674] The above processing steps enable the simple management of complex organizational rules and their widespread dissemination. This system efficiently handles everything from rule generation to final sharing, thereby more effectively supporting communication and business operations within an organization.

[1675] Example 1

[1676] 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."

[1677] In the current system, rule generation and sharing within an organization are not carried out efficiently, and there is a high possibility that conflicts with existing rules will occur, especially when new rules are generated. In addition, suggestions and feedback from users are often not properly reflected, resulting in a lack of responsiveness across the organization. This results in issues such as the time it takes to apply rules and a decline in work efficiency across the organization.

[1678] 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.

[1679] In this invention, the server includes means for accepting rule generation requests from users, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for providing feedback to the user on the generated new rules and inconsistencies, and means for notifying and sharing the final confirmed rules received from the user with all users in the organization. This streamlines the rule generation process and enables automatic analysis of inconsistencies with existing rules, improving responsiveness throughout the organization and enabling improved business efficiency.

[1680] A "user" is a user who submits a rule generation request to the system and checks the feedback.

[1681] A "rule creation request" is a request that a user sends to the system to propose a new rule or a rule change.

[1682] A "database" is an information storage system that stores existing rule information within an organization and allows that information to be searched and retrieved as needed.

[1683] A "generative AI model" is an artificial intelligence system that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[1684] "Inconsistencies" refer to areas of inconsistency or conflict between new rules and existing rules.

[1685] "Feedback" is a response that notifies the user of new rules generated by the generative AI model and information about inconsistencies.

[1686] An "HTTP request" is a communication format for sending user input to a server.

[1687] A "terminal" is a device such as a computer or smartphone that a user uses to request rule generation or check feedback.

[1688] "Intra-organizational" refers to the interior of the particular company or organization to which the rules apply.

[1689] A "notification" is a message sent by the server to notify all users in an organization of new rules or updated information.

[1690] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users in the organization.

[1691] System Configuration

[1692] User

[1693] Users can input new rule suggestions or changes through a dedicated web interface. For example, they can enter a suggestion to change working hours to "9:00 AM - 6:00 PM" into a form and click the "Submit" button. This generates an HTTP request.

[1694] Terminal

[1695] The terminal receives input data from the user and sends it to the server as an HTTP request. The user then checks the terminal for a message indicating that the data has been sent.

[1696] server

[1697] The server receives the HTTP request and first checks the data format and content for consistency. It then accesses the organization's database to retrieve existing rule information. For example, if the existing working hours are "8:00 AM - 5:00 PM," that information is retrieved from the database.

[1698] The server obtains the existing rules and new proposals, converts this information into data packets, and sends them to the generative AI model. The generative AI model generates new rules based on the received data and analyzes any inconsistencies with the existing rules. For example, it checks whether the new working hours of "9:00 AM - 6:00 PM" are consistent with the lunch break time of "12:00 PM - 1:00 PM."

[1699] The analysis results of the generative AI model are returned to the server as new rules and inconsistencies, which the server uses to create feedback messages and send to the user via email or notification.

[1700] The user reviews the feedback and, if necessary, modifies the proposal or approves it for final review. The finalized rules are then sent back to the server, which transfers the final rules to the shared system and sends a notification to all users in the organization that the new rules have been finalized.

[1701] The device will receive a notification and display a message to the user saying "New rules have been shared with you," allowing the user to review and apply the new rules.

[1702] Specific examples

[1703] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[1704] 1. User enters a suggestion

[1705] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[1706] 2. Get existing rules

[1707] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[1708] 3. Analysis using generative AI models

[1709] Server: Sends new proposals and existing rules to the generative AI model.

[1710] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[1711] 4. Conflict detection and feedback

[1712] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[1713] Server: Compiles feedback and notifies users.

[1714] 5. Sharing rules

[1715] User: Review feedback and submit final version from device.

[1716] Server: Notifies all users of the final rules and transfers them to the shared system.

[1717] Device: Notify the user that a new rule has been shared with them.

[1718] This system streamlines the rule generation process and can automatically analyze inconsistencies with existing rules, improving responsiveness across the organization and enabling improved operational efficiency.

[1719] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1720] Step 1:

[1721] (User inputs and submits rule generation request)

[1722] The user enters a new rule proposal or changes into a dedicated web form and clicks the "Submit" button. For example, a proposal to change working hours to "9:00-18:00" is entered. This generates the user's input (proposed new rule) as input data.

[1723] Input: Propose a new rule (e.g., change working hours)

[1724] Output: User input data (in HTTP request format)

[1725] Step 2:

[1726] (The device sends the user's input data to the server)

[1727] The terminal receives the user's input data and sends it to the server as an HTTP request. After the request is sent, a "Send completed" message is displayed to notify the user.

[1728] Input: User input data (proposed new rules)

[1729] Output: "Sent" message

[1730] Step 3:

[1731] (Server retrieves existing rules)

[1732] The server receives the HTTP request and checks the data format and content for consistency. Next, it accesses the organization's database to retrieve existing rule information. For example, it searches for and retrieves rules that include the existing working hours of "8:00 AM - 5:00 PM."

[1733] Input: User input data (HTTP request), existing rule information

[1734] Output: Existing rules (e.g., working hours "8:00-17:00")

[1735] Step 4:

[1736] (The server sends the data to the generative AI model)

[1737] The server compiles the acquired existing rules and user suggestions, converts them into a data packet, and sends it to the generative AI model. Specifically, it structures the data in JSON format or similar and generates a data packet that includes the new rules and existing rules.

[1738] Input: User suggestions, existing rules

[1739] Output: Data packet (e.g., JSON format)

[1740] Step 5:

[1741] (The generative AI model generates rules and performs analysis)

[1742] The generative AI model analyzes the received data packets and generates new rules. It also checks whether the generated rules are consistent with existing rules. For example, it checks whether a new work schedule of "9:00 AM - 6:00 PM" is consistent with a lunch break of "12:00 PM - 1:00 PM."

[1743] Input: Data packet (new rule / existing rule)

[1744] Output: New rules, list of inconsistencies

[1745] Step 6:

[1746] (Server sends feedback to user)

[1747] The server receives the output data (new rules and inconsistencies) from the generative AI model and generates a feedback message for the user. For example, it creates a feedback message including the content "The new working hours (9:00-18:00) are not inconsistent with the lunch break time (12:00-13:00)" and sends it to the user via email or notification.

[1748] Input: New rules, list of discrepancies

[1749] Output: Feedback message

[1750] Step 7:

[1751] (User checks feedback)

[1752] The user receives the feedback, reviews it on their device, considers it, makes new suggestions or modifies existing ones as needed, and if there are no problems, approves it for final review.

[1753] Input: Feedback message

[1754] Output: Approved final rules or proposed amendments

[1755] Step 8:

[1756] (User submits finalized rule)

[1757] Once the user has reviewed the feedback and finalized the rules, the terminal sends the final rules to the server, including details of the final approved rules.

[1758] Input: Approved Final Rules

[1759] Output: Data sent to the server

[1760] Step 9:

[1761] (Server shares the final rules)

[1762] The server receives the final rules, transfers them to the shared system, and sends a notification to all users in the organization that the new rules have been finalized, for example via an intranet or internal chat tool.

[1763] Input: Final rules

[1764] Output: Notification to all users in the organization

[1765] Step 10:

[1766] (Device displays notification)

[1767] The device will receive a notification and display a message to the user saying "New rules have been shared with you," allowing the user to review and apply the new rules.

[1768] Input: Notification from the server

[1769] Output: Display of notification message

[1770] Through the above steps, the process from a user's rule generation request to the final sharing of the rules can be carried out efficiently.

[1771] (Application example 1)

[1772] 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."

[1773] In factories, work rules and work instructions are frequently changed, and the latest rules and instructions may not be communicated quickly and reliably to everyone on the shop floor. This problem is particularly pronounced in complex manufacturing and quality control processes, and can lead to reduced work efficiency and deterioration of product quality. Conventional manual methods of rule management and sharing cannot adequately solve these issues, creating a need for automated systems.

[1774] 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.

[1775] In this invention, the server includes means for accepting rule generation requests from users, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for providing feedback to the user on the generated new rules and inconsistencies, means for notifying and sharing the final confirmed rules with all users in the organization, and means for generating, managing, and sharing rules and work instructions within the factory via smart devices (smartphones, tablets, head-mounted displays, factory robots). This allows the latest work rules and instructions to be quickly and reliably communicated to everyone on site, improving work efficiency and ensuring product quality.

[1776] A "user" is an individual or member of an organization who accesses the system and makes a rule generation request.

[1777] The "means for accepting rule generation requests" is an interface that has the function of accepting proposals for new rules or rule changes from users.

[1778] The "means for obtaining existing rules from a database" is a program that has the function of searching for and obtaining existing rule information stored in a database within an organization.

[1779] A "generative AI model" is an artificial intelligence model used to generate new rules based on input data and analyze inconsistencies with existing rules.

[1780] The "feedback means" is a system that has the function of notifying the user of the new rules that have been generated and the results of the analysis of contradictions.

[1781] The "means for notifying and sharing the final confirmed rules" is a system that has the function of quickly notifying all users in the organization of the rules that have received final confirmation from the users and sharing them.

[1782] A "smart device" is a portable electronic terminal (e.g., smartphone, tablet, head-mounted display, factory robot) that a user uses to access the system, submit rule generation requests, and receive feedback.

[1783] This invention is a system for efficiently managing, generating, and sharing rules and work instructions within a factory. This system accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. It also provides feedback on the generated rules and inconsistencies to the user, and notifies and shares the final confirmed rules with all users within the organization.

[1784] 1. Hardware and Software Configuration

[1785] The system is implemented using the following hardware and software:

[1786] Server: Accepts rule generation requests, retrieves existing rules from the database, executes the generative AI model, generates feedback, and finalizes and shares the rules.

[1787] Devices: Smartphones, tablets, head-mounted displays, and factory robots for inputting rule generation requests

[1788] Database: PostgreSQL (management of existing rules)

[1789] Generative AI model: OpenAI API (new rule generation and inconsistency analysis)

[1790] Framework: Flask (Web interface implementation)

[1791] 2. Overview of the processing procedure

[1792] A user uses a smart device to send a rule generation request to the system. This request includes a new rule or a proposed change, such as "Change the frequency of machine maintenance inspections to once a week." The server receives this request and retrieves existing rules from the database.

[1793] The server sends the existing rules and the new proposal to the generative AI model, which generates new rules and analyzes the inconsistencies with the existing rules.The generative AI model generates the inconsistencies as prompt sentences based on the proposed rules and the existing rules, as follows:

[1794] plain

[1795] Proposed rule: Change machine maintenance inspection frequency to once a week.

[1796] Existing rules: Machine maintenance inspections twice a month.

[1797] Detect the inconsistencies.

[1798] Based on the analysis results returned by the generative AI model, the server creates feedback and notifies the user. The feedback includes the new rules generated and whether or not there are any inconsistencies. For example, if there are no inconsistencies, the server notifies the user that "a new rule can be introduced."

[1799] The user checks the feedback and, if final confirmation is obtained, submits the final rules to the system. The server then notifies and shares the final confirmed rules with all users within the organization. This ensures that the latest rules and instructions are quickly and reliably communicated to everyone on-site.

[1800] This system will streamline the management of work rules and instructions within the factory, making it possible to maintain work efficiency and product quality.

[1801] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1802] Step 1:

[1803] A user uses a smart device (smartphone, tablet, head-mounted display, factory robot) to input a request to create a new rule. For example, the user might input "Change the machine maintenance inspection frequency to once a week" and click the send button. At this time, the input data is sent to the server as an HTTP request.

[1804] Step 2:

[1805] The server accepts the HTTP request data received from the user and verifies the integrity of the data. At this time, it checks whether the format and content of the request data are correct. Next, it sends a query to the database (PostgreSQL) to obtain existing related rule information. For example, it searches for and obtains a rule such as "Machine maintenance inspections should be performed twice a month." The obtained data is stored in internal memory.

[1806] Step 3:

[1807] The server compiles existing rules and user suggestions into a data packet and sends it to the generative AI model (OpenAI API). The generative AI model generates new rules based on the received data and analyzes any inconsistencies with existing rules. An example of a prompt sentence used in this process is as follows:

[1808] plain

[1809] Proposed rule: Change machine maintenance inspection frequency to once a week.

[1810] Existing rules: Machine maintenance inspections twice a month.

[1811] Detect the inconsistencies.

[1812] Based on this prompt, the generative AI model returns new rules and analysis results of inconsistencies.

[1813] Step 4:

[1814] The server receives the analysis results returned by the generative AI model and creates feedback based on them. The feedback includes information on new rules and inconsistencies. For example, a message such as "New rules can be introduced" is generated. This feedback is sent to the user as a notification.

[1815] Step 5:

[1816] The user reviews the feedback on their smart device and, if necessary, modifies and resubmits the proposal or finalizes new rules based on the feedback.

[1817] Step 6:

[1818] The user sends the finalized rules from the terminal to the server, which then forwards the finalized rules to the shared system, which then notifies all users in the organization of the new rules and makes them applicable.

[1819] Step 7:

[1820] Devices (smartphones, tablets, head-mounted displays) will receive notifications and display messages to confirm the new rules, allowing all users to quickly understand the latest rules.

[1821] 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.

[1822] This invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules, and further combines it with an emotion engine that recognizes the user's emotions. The generated rules and inconsistencies are fed back to the user, and the final confirmed rules are notified and shared with all users within the organization. An embodiment of this system is described in detail below.

[1823] System Program Overview

[1824] 1. Acceptance of rule generation requests

[1825] User

[1826] The user enters the proposed new rules or changes into a dedicated form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00 to 18:00) is entered.

[1827] Terminal

[1828] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[1829] 2. Get existing rules

[1830] server

[1831] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[1832] server

[1833] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[1834] 3. Rule generation and analysis using generative AI models

[1835] server

[1836] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[1837] Generative AI Models

[1838] The generative AI model generates new rules based on the received data. For example, it generates a new working hours policy (9:00 AM to 6:00 PM). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00 PM to 1:00 PM) are consistent.

[1839] 4. Emotional Analysis of Users by Emotion Engine

[1840] server

[1841] The server sends the data obtained from the user interface to the emotion engine.

[1842] Emotion Engine

[1843] The emotion engine analyzes emotions based on user input and interactions, for example, determining stress or satisfaction from user input and click frequency.

[1844] 5. Providing Feedback

[1845] server

[1846] The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides feedback to the user. For example, it sends an email containing information that the inconsistency is "not inconsistent with the lunch break time" and a message corresponding to the user's emotional state.

[1847] User

[1848] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[1849] 6. Finalize and share the rules

[1850] User

[1851] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[1852] server

[1853] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[1854] Terminal

[1855] Your device will receive a notification and display a message to confirm the new rule.

[1856] Specific examples

[1857] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[1858] 1. User enters a suggestion

[1859] User: Enter a proposal to change working hours to "9:00-18:00" into the terminal form and submit it.

[1860] 2. Get existing rules

[1861] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[1862] 3. Analysis using generative AI models

[1863] Server: Sends new proposals and existing rules to the generative AI model.

[1864] Generative AI model: Analyzes the proposal and checks whether the working hours of "9:00 AM - 6:00 PM" conflict with the lunch break time (12:00 PM - 1:00 PM).

[1865] 4. Analysis by Emotion Engine

[1866] Server: Sends user input data to the emotion engine.

[1867] Emotion engine: Analyzes user emotions and determines stress and satisfaction.

[1868] 5. Conflict detection and feedback

[1869] Generative AI model: Checks that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are correct and sends them back to the server.

[1870] Server: Compiles the feedback and sends notifications with messages depending on the user's emotional state.

[1871] 6. Sharing rules

[1872] User: Review feedback and submit final version from device.

[1873] Server: Notifies all users of the final rules and transfers them to the shared system.

[1874] Through the above process, complex organizational rules can be managed simply and easily and widely disseminated.By using an emotion engine, this system provides more personalized feedback according to the user's emotional state, more effectively supporting communication and business operations within an organization.

[1875] The processing flow will be explained below.

[1876] Step 1:

[1877] User

[1878] The user enters a proposal for a new rule or change into the form on the terminal and clicks the "Submit" button. For example, a proposal for a new working hours policy (9:00-18:00) is entered.

[1879] Step 2:

[1880] Terminal

[1881] The terminal receives input data and sends it to the server as an HTTP request, performing basic validation to ensure that the data format and content are correct.

[1882] Step 3:

[1883] server

[1884] The server receives the HTTP request and checks the data format for consistency. If the input data is confirmed to be in the correct format, it proceeds to the next step.

[1885] Step 4:

[1886] server

[1887] The server accesses the database and retrieves information about rules that already exist within the organization. For example, it searches for and retrieves information about existing working hours policies (8:00 to 17:00).

[1888] Step 5:

[1889] server

[1890] The server collects the existing rules and user suggestions into a data packet and sends it to the generative AI model, ensuring that the data packet contains the necessary information in the appropriate format.

[1891] Step 6:

[1892] Generative AI Models

[1893] The generative AI model analyzes the received data and generates new rules. For example, it generates a new working hours policy (9:00-18:00). It also checks for inconsistencies with existing rules. For example, it checks whether working hours and lunch break times (12:00-13:00) are consistent.

[1894] Step 7:

[1895] Generative AI Models

[1896] The generative AI model outputs the analysis results and creates a list of proposed new rules and contradictions.

[1897] Step 8:

[1898] server

[1899] The server receives the analysis results from the generative AI model, temporarily stores the proposed new rules and any inconsistencies in a database, and then formats the data for feedback to the user.

[1900] Step 9:

[1901] server

[1902] The server sends the data obtained from the user interface to the emotion engine.

[1903] Step 10:

[1904] Emotion Engine

[1905] The emotion engine analyzes emotions based on user input and interactions, for example, determining stress or satisfaction from user input and click frequency.

[1906] Step 11:

[1907] server

[1908] The server receives the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user, for example, by sending an email containing information indicating that the discrepancy is not inconsistent with the lunch break time and a message corresponding to the user's emotional state.

[1909] Step 12:

[1910] User

[1911] The user receives feedback, reviews it on their device, and, if necessary, makes new suggestions or modifies existing ones.

[1912] Step 13:

[1913] User

[1914] When the user has performed final confirmation, the terminal transmits the final version of the rules to the server.

[1915] Step 14:

[1916] server

[1917] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, via email or an internal notification system to let everyone know about the new rule.

[1918] Step 15:

[1919] Terminal

[1920] Your device will receive a notification and display a message to confirm the new rule.

[1921] Through the above processing steps, complex organizational rules can be managed simply and easily and widely disseminated.By using an emotion engine, this system provides more personalized feedback according to the user's emotional state, more effectively supporting communication and business operations within an organization.

[1922] Example 2

[1923] 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."

[1924] In conventional rule management systems, the creation of new rules and the detection of inconsistencies with existing rules were not automated and had to be done manually. This meant that rule creation required a great deal of time and effort, and it was difficult to provide feedback that took into account the user's emotions. This resulted in problems such as reduced usability and disrupted communication within the organization.

[1925] 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.

[1926] In this invention, the server includes means for accepting a rule generation request from a user, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for using an emotion engine to analyze the user's emotional state, means for providing feedback to the user about the generated new rules and inconsistencies, means for reaccepting suggestions and changes based on the feedback, and means for notifying and sharing the final confirmed rules with all users in the organization. This makes rule generation more efficient and automated, and by providing feedback that takes the user's emotional state into consideration, it becomes possible to facilitate communication within the organization.

[1927] "User" refers to an entity that uses the system to request the creation or modification of rules.

[1928] "Means for accepting rule generation requests" refers to an interface or mechanism for accepting new rule suggestions or changes from users.

[1929] "Database" refers to a data storage system for storing existing rule information managed within the system.

[1930] A "generative AI model" refers to a model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[1931] "Means for conflict analysis" refers to a mechanism or algorithm that checks for conflicts between existing rules and new proposed rules.

[1932] "Emotion engine" refers to software or algorithms that analyze emotional states based on user input and interaction data.

[1933] "Means for providing feedback" refers to a mechanism that notifies the user of the generated new rules and the analysis results of inconsistencies, and provides evaluation and advice on the proposals.

[1934] "Means for resubmitting suggestions and changes" refers to an interface or mechanism that allows users to receive feedback and make further suggestions or changes.

[1935] "Means for notifying and sharing finalized rules" refers to a mechanism for notifying and sharing rules that have been finalized by users to all users within an organization.

[1936] The present invention is a system that accepts rule generation requests from users, generates new rules based on those requests using a generative AI model, and analyzes inconsistencies with existing rules. Furthermore, it incorporates an emotion engine that recognizes the user's emotions, provides feedback to the user about the generated rules and any inconsistencies, and notifies and shares the final confirmed rules with all users within the organization. The following describes in detail an embodiment of the present invention.

[1937] 1. A method for accepting rule generation requests from users

[1938] User

[1939] The user enters new rule proposals or changes into a dedicated form on the device and clicks the "Submit" button. For example, the user can enter a specific proposal such as "Change working hours to 9:00-18:00."

[1940] Terminal

[1941] The terminal receives user input, validates the input data, checking that all required fields are filled in and that the format is correct, and if validation is successful, sends the data to the server as an HTTP request.

[1942] 2. How to retrieve existing rules from a database

[1943] server

[1944] The server receives the HTTP request from the device and verifies that the data format is correct. It checks that the request is in JSON format.

[1945] server

[1946] The server accesses the database and retrieves existing rule information. For example, it retrieves information from the database that "the current working hours policy is 8:00 to 17:00." The retrieved information is saved for use in the next step.

[1947] 3. A means of generating new rules using generative AI models and analyzing inconsistencies with existing rules

[1948] server

[1949] The server collects the existing rules and the user's new proposals into a data packet and sends it to the generative AI model. For example, it formats the data in a format such as "existing rules: working hours 8:00-17:00, new proposal: 9:00-18:00."

[1950] Generative AI Models

[1951] The generative AI model generates new rules based on the received data. For example, it generates "new working hours: 9:00 AM to 6:00 PM." It also checks for inconsistencies with existing rules. For example, it checks whether the new rules conflict with the lunch break time (12:00 PM to 1:00 PM).

[1952] 4. Using an emotion engine to analyze the user's emotional state

[1953] server

[1954] The server sends data obtained from the user interface to the emotion engine, including user-entered text and interaction data.

[1955] Emotion Engine

[1956] The emotion engine analyzes emotions based on user input and interactions, for example, determining that a user is stressed if they are making a lot of edits.

[1957] 5. A means of providing feedback to the user about new rules and inconsistencies

[1958] server

[1959] The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides this as feedback to the user. For example, it sends an email containing information such as "The new working hours of 9:00 AM to 6:00 PM are consistent with the lunch break time" and a message saying "The feedback you provided has been completed."

[1960] 6. A way to re-open the project for suggestions and changes based on feedback

[1961] User

[1962] Users receive feedback, review it on their devices, and, if necessary, make further suggestions or modify existing suggestions.

[1963] Terminal

[1964] The device will then accept new suggestions and modifications from the user and send them to the server again.

[1965] 7. How to communicate and share the finalized rules with all users in the organization

[1966] User

[1967] The user makes a final confirmation and sends the final version of the rules to the server from the terminal. For example, the user may confirm, "I officially approve this new working hours policy (9:00-18:00)."

[1968] server

[1969] The server then transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, by email or through an internal notification system, informing everyone that the new working hours policy has been approved.

[1970] Terminal

[1971] The device receives the notification and displays a message to the user to confirm the new rules, for example, a notification saying "Please review the new working hours policy."

[1972] Specific examples

[1973] For example, when proposing a new working hours policy (9:00 AM - 6:00 PM), the specific steps are as follows:

[1974] 1. User enters a suggestion

[1975] User: Enter "Proposal to change working hours to 9:00-18:00" into the form on the device and submit it.

[1976] 2. Get existing rules

[1977] Server: Obtain information about existing working hours (e.g., "8:00-17:00") from the database.

[1978] 3. Analysis using generative AI models

[1979] Server: Sends new proposals and existing rules to the generative AI model.

[1980] Generative AI model: Checks whether "Working hours 9:00-18:00" conflicts with lunch break times (12:00-13:00).

[1981] 4. Analysis by Emotion Engine

[1982] Server: Sends user input data to the emotion engine.

[1983] Emotion engine: Analyzes user emotions and determines stress and satisfaction.

[1984] 5. Conflict detection and feedback

[1985] Generative AI model: Confirms that the new rules (9:00-18:00) and the inconsistencies (lunch break 12:00-13:00) are acceptable and sends them back to the server.

[1986] Server: Compiles the feedback and sends notifications with messages depending on the user's emotional state.

[1987] 6. Sharing rules

[1988] User: Review feedback and submit final version from device.

[1989] Server: Notifies all users of the final rules and transfers them to the shared system.

[1990] Prompt Sentence Examples

[1991] "I would like to propose a new working hours policy of 9am to 6pm. Please check for any inconsistencies with existing policies and provide feedback."

[1992] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1993] Step 1:

[1994] User: The user enters new rule suggestions or changes into a dedicated form on the terminal. The input includes a new working hours policy (e.g., "Change working hours to 9:00-18:00"). By clicking the "Submit" button, the suggestion is sent to the system.

[1995] Input: Propose a new rule (e.g., "Change working hours to 9:00-18:00")

[1996] Output: Data sent to the server as an HTTP request

[1997] Step 2:

[1998] Terminal: The terminal validates the received user input data, checking that the input data is correctly formatted and that all required fields are filled in. If validation is successful, the terminal sends the data to the server as an HTTP request.

[1999] Input: User-entered data

[2000] Output: Sent to the server as an HTTP request

[2001] Step 3:

[2002] Server: The server receives the HTTP request from the device, verifies that the data format is correct, and checks that the request is in JSON format, and then passes the data to the next step.

[2003] Input: HTTP request data

[2004] Output: Validated data

[2005] Step 4:

[2006] Server: The server accesses the database and retrieves existing rule information. For example, it retrieves information from the database that "the current working hours policy is 8:00 to 17:00." This retrieved information is saved for use in the next step.

[2007] Input: The request to be retrieved from the database

[2008] Output: Existing rule information

[2009] Step 5:

[2010] Server: The server compiles the existing rules and the user's new proposal into a data packet and sends it to the generative AI model. The data is formatted as "Existing rules: working hours 8:00-17:00, new proposal: 9:00-18:00."

[2011] Input: Existing rule information and new rule proposals

[2012] Output: Data packets

[2013] Step 6:

[2014] Generative AI model: The generative AI model generates new rules based on the data it receives. For example, it generates "new working hours will be from 9:00 to 18:00." It also checks for inconsistencies with existing rules. For example, it checks whether "working hours and lunch break times (12:00 to 13:00) are consistent."

[2015] Input: Data packet (existing rules and new proposals)

[2016] Output: New rules and conflict information

[2017] Step 7:

[2018] Server: The server receives output data from the generative AI model and sends data obtained from the user interface to the emotion engine.

[2019] Input: Output data of generative AI model, data from user interface

[2020] Output: Data sent to the emotion engine

[2021] Step 8:

[2022] Emotion Engine: The emotion engine analyzes emotions based on user input and interactions. For example, if a user makes a lot of edits, it determines that the user is stressed.

[2023] Input: User interface data

[2024] Output: User sentiment analysis results

[2025] Step 9:

[2026] Server: The server receives the output of the generative AI model (new rules and inconsistencies) and the analysis results of the emotion engine, and provides feedback to the user. For example, it sends an email containing information such as "The new working hours of 9:00 AM to 6:00 PM are consistent with the lunch break time" and a message saying "The feedback you provided has been completed."

[2027] Input: Output of generative AI model, analysis results of emotion engine

[2028] Output: Feedback to the user

[2029] Step 10:

[2030] User: The user receives the feedback, reviews it on their device, and can resubmit or revise existing suggestions as needed.

[2031] Input: Feedback

[2032] Output: Re-proposal or revised proposal

[2033] Step 11:

[2034] User: The user performs the final confirmation and sends the final version of the rules to the server from the terminal. For example, the user confirms, "I officially approve this new working hours policy (9:00-18:00)."

[2035] Input: Finalized rules

[2036] Output: Final rules sent to the server

[2037] Step 12:

[2038] Server: The server transfers the final confirmed rule to a shared system and sends a notification to all users in the organization, for example, by email or through the internal notification system, informing everyone that the new working hours policy has been approved.

[2039] Input: Final rules

[2040] Output: Notify everyone in the organization

[2041] Step 13:

[2042] Terminal: The terminal receives the notification and displays a message to confirm the new rule. For example, a notification is displayed to the user saying "Please review the new working hours policy."

[2043] Input: Notification from the server

[2044] Output: Message displayed to the user

[2045] (Application example 2)

[2046] 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."

[2047] Managing rule changes and new proposals within an organization requires a lot of manual work, and it is extremely difficult to properly create and share new rules while maintaining consistency with existing rules. Furthermore, if feedback on employee proposals is not provided promptly, it can have a negative impact on employee morale and emotions. This calls for intuitive and efficient rule management and feedback that takes employee feelings into consideration.

[2048] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a rule generation request from a user, means for retrieving existing rules from a database, means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules, means for analyzing the user's emotional state using an emotion engine that recognizes the user's emotions, means for providing feedback based on the generated new rules, inconsistencies, and the user's emotional state, and means for notifying and sharing the final confirmed rules with all users in the organization. This makes it possible to efficiently manage rule changes within the organization and provide personalized feedback according to the user's emotional state.

[2049] A "user" is a person or organization that uses the system to make a rule generation request.

[2050] The "means for accepting rule generation requests" is an interface or function that accepts suggestions and changes regarding rule generation from the user.

[2051] The "means for obtaining existing rules from a database" is a function for searching and obtaining current rule information stored in a database.

[2052] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate new rules and analyze inconsistencies with existing rules.

[2053] An "emotion engine" is an algorithm or system for analyzing and recognizing a user's emotional state from their input and behavior.

[2054] The "means for providing feedback" is a function that provides the user with appropriate information based on the new rules, discrepancies, and emotional state that have been generated.

[2055] The "means for notifying and sharing rules" refers to a function or system for notifying and sharing the finalized rules with all users within the organization.

[2056] A system for implementing this invention includes a series of processes required to accept rule generation requests from users, collect existing rules, generate new rules, detect inconsistencies, provide feedback, and notify all users in an organization of the final confirmed rules.

[2057] First, a user inputs a rule generation request using a smartphone application. The user enters suggestions or changes through a form in the app and clicks the "Submit" button. For example, a suggestion could be to change working hours. The device receives this input data and sends it to the server as an HTTP request. Basic validation is performed to ensure the data format and content are correct.

[2058] The server then receives the HTTP request and checks the data format for validity. If the input data is in the correct format, the server accesses a database to retrieve existing rules, such as the current working hours policy.

[2059] The server assembles this data into data packets and sends them to a generative AI model, which uses machine learning frameworks like TensorFlow to generate new rules and analyze existing rules for inconsistencies—for example, checking that a new work hour policy doesn't conflict with lunch break times.

[2060] Furthermore, the server uses an emotion engine to analyze the user's emotional state. This emotion engine analyzes the user's input and interactions to determine stress and satisfaction. The server receives the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user. For example, a notification containing information indicating there are no inconsistencies or a message corresponding to the user's emotional state may be sent.

[2061] Finally, if the user reviews the feedback and modifies and confirms the rules to their satisfaction, the details are sent to the server. The server then notifies all users in the organization of the final confirmed rules and stores them in a shared system. Notifications are sent via email and the internal notification system to ensure that everyone is aware of the new rules.

[2062] Prompt Sentence Examples

[2063] The following is an example of a prompt sentence to be used when sending a rule generation request to the server.

[2064] api_url = 'http: / / example.com / submit-proposal'

[2065] headers = {'Content-Type': 'application / json'}

[2066] proposal_data = {

[2067] 'proposal': 'I would like to extend the afternoon break to 30 minutes'

[2068] }

[2069] response = requests.post(api_url, json=proposal_data, headers=headers)

[2070] print(response.json())

[2071] As described above, an embodiment of the present invention optimizes organizational rule management and employee feedback provision by combining an efficient and intuitive user interface with an advanced generative AI model and emotion engine. This system is expected to significantly simplify the process from proposal to final confirmation and improve employee satisfaction.

[2072] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2073] Step 1:

[2074] The user inputs a rule generation request. Using a smartphone app, the user inputs new rules or proposed changes into a dedicated form. This input data is sent to the system by clicking the "Submit" button. A specific input might be something like "I would like to extend the afternoon break to 30 minutes." The output is an HTTP request in which this proposal is sent to the server.

[2075] Step 2:

[2076] The terminal receives input data and sends it to the server as an HTTP request. The terminal checks the format and content of the input data and performs basic validation. Only data in the correct format is sent to the server. The input is the proposal entered by the user, and the output is an HTTP request containing data that has passed validation.

[2077] Step 3:

[2078] The server receives an HTTP request and checks the integrity of the data format. The server checks the request content and confirms that it is in the correct format before proceeding to the next step. The input is the data sent from the terminal, and the output is the correct data after the integrity check.

[2079] Step 4:

[2080] The server accesses the database to retrieve existing rule information. The server sends a query to the database to search for and retrieve relevant existing rules, for example, the current working hours policy. The input is the proposed data after consistency check, and the output is the existing rule information.

[2081] Step 5:

[2082] The server compiles the acquired data into a data packet and sends it to the generative AI model. The generative AI model generates new rules based on this data and analyzes any inconsistencies with existing rules. For example, it checks whether a new working hours policy conflicts with existing lunch break times. The input is the proposed data and existing rule information, and the output is the generated new rules and the analysis results of any inconsistencies.

[2083] Step 6:

[2084] The server receives the output of the generative AI model (new rules and inconsistencies) and sends the user's input data to the emotion engine. The emotion engine analyzes emotions based on the user's input and interactions. For example, it determines stress and satisfaction from the input text and frequency of clicks. The input is the user's suggested data, and the output is the emotion analysis results.

[2085] Step 7:

[2086] The server integrates the output of the generative AI model and the analysis results of the emotion engine and provides feedback to the user. Specifically, it creates a message based on the new rules, inconsistencies, and the user's emotional state, and provides feedback via email or app notification. The input is the new rules, inconsistencies, and emotion analysis results, and the output is the feedback information notified to the user.

[2087] Step 8:

[2088] The user receives and reviews the feedback, and if necessary makes new suggestions or modifies existing suggestions. This results in an iterative process of reviewing and modifying the final rule. The input is the feedback information, and the output is the modified suggestions.

[2089] Step 9:

[2090] When the user performs final confirmation, the terminal sends the final version of the rules to the server. This final rule is stored on the server. The input is the final confirmed rule, and the output is the final rule stored on the server.

[2091] Step 10:

[2092] The server transfers the final confirmed rules to the shared system and notifies all users in the organization. The server notifies all users of the new rules via email or the internal notification system. The input is the final confirmed rules, and the output is the notification to all users.

[2093] This effectively manages the rule change process within an organization and provides personalized feedback according to the user's emotional state.

[2094] 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.

[2095] 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.

[2096] 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 robot 414.

[2097] 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.

[2098] 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.

[2099] 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.

[2100] 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).

[2101] 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.

[2102] 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."

[2103] 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.

[2104] 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).

[2105] 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.

[2106] 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.

[2107] 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.

[2108] 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.

[2109] 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.

[2110] 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.

[2111] 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.

[2112] 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.

[2113] 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.

[2114] 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.

[2115] The following is further disclosed regarding the above embodiment.

[2116] (Claim 1)

[2117] means for receiving a rule generation request from a user;

[2118] A means of retrieving existing rules from a database;

[2119] A means of generating new rules using a generative AI model and analyzing inconsistencies with existing rules;

[2120] a means for providing feedback to the user about the generated new rules and inconsistencies;

[2121] A means to communicate and share the finalized rules with all users within the organization;

[2122] A system including:

[2123] (Claim 2)

[2124] The system of claim 1, wherein the means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules uses a machine learning algorithm.

[2125] (Claim 3)

[2126] 2. The system according to claim 1, wherein the means for accepting a rule generation request from a user is implemented through a web interface.

[2127] (Claim 4)

[2128] 2. The system according to claim 1, wherein the means for notifying and sharing the finalized rules with all users within the organization uses both email and an internal notification system.

[2129] "Example 1"

[2130] (Claim 1)

[2131] means for receiving a rule generation request from a user;

[2132] A means of retrieving existing rules from a database;

[2133] A means of generating new rules using a generative AI model and analyzing inconsistencies with existing rules;

[2134] a means for providing feedback to the user about the generated new rules and inconsistencies;

[2135] A means of notifying and sharing the final confirmed rules received from users to all users within the organization;

[2136] A system including a terminal that transmits a rule generation request to a server as an HTTP request.

[2137] (Claim 2)

[2138] The system of claim 1, wherein the means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules uses a machine learning algorithm.

[2139] (Claim 3)

[2140] 2. The system according to claim 1, wherein the means for accepting a rule generation request from a user is implemented through a web interface.

[2141] "Application Example 1"

[2142] (Claim 1)

[2143] means for receiving a rule generation request from a user;

[2144] A means of retrieving existing rules from a database;

[2145] A means of generating new rules using a generative AI model and analyzing inconsistencies with existing rules;

[2146] a means for providing feedback to the user about the generated new rules and inconsistencies;

[2147] A means to communicate and share the finalized rules with all users within the organization;

[2148] A means to create, manage, and share rules and work instructions within the factory through smart devices (smartphones, tablets, head-mounted displays, factory robots),

[2149] A system including:

[2150] (Claim 2)

[2151] The system of claim 1, wherein the means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules uses a machine learning algorithm.

[2152] (Claim 3)

[2153] 2. The system according to claim 1, wherein the means for accepting a rule generation request from a user is implemented through a web interface.

[2154] "Example 2: Combining Emotion Engines"

[2155] (Claim 1)

[2156] means for receiving a rule generation request from a user;

[2157] A means of retrieving existing rules from a database;

[2158] A means of generating new rules using a generative AI model and analyzing inconsistencies with existing rules;

[2159] a means using an emotion engine to analyze the user's emotional state;

[2160] a means for providing feedback to the user about the generated new rules and inconsistencies;

[2161] A means to re-open for suggestions and changes based on feedback, and

[2162] A means to communicate and share the finalized rules with all users within the organization;

[2163] A system including:

[2164] (Claim 2)

[2165] The system of claim 1, wherein the means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules uses a machine learning algorithm.

[2166] (Claim 3)

[2167] 2. The system according to claim 1, wherein the means for accepting a rule generation request from a user is implemented through a web interface.

[2168] "Application example 2 when combining emotion engines"

[2169] (Claim 1)

[2170] means for receiving a rule generation request from a user;

[2171] A means of retrieving existing rules from a database;

[2172] A means of generating new rules using a generative AI model and analyzing inconsistencies with existing rules;

[2173] means for analyzing the emotional state of a user using an emotion engine that recognizes the user's emotions;

[2174] means for providing feedback based on the generated new rules and discrepancies, as well as the user's emotional state;

[2175] A means to communicate and share the finalized rules with all users within the organization;

[2176] A system including:

[2177] (Claim 2)

[2178] The system of claim 1, wherein the means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules uses a machine learning algorithm.

[2179] (Claim 3)

[2180] 2. The system according to claim 1, wherein the means for accepting a rule generation request from a user is implemented through a web interface. [Explanation of symbols]

[2181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a rule generation request from a user; A means of retrieving existing rules from a database; A means of generating new rules using a generative AI model and analyzing inconsistencies with existing rules; a means for providing feedback to the user about the generated new rules and inconsistencies; A means to communicate and share the finalized rules with all users within the organization; A system including:

2. 2. The system of claim 1, wherein the means for generating new rules using a generative AI model and analyzing inconsistencies with existing rules uses a machine learning algorithm.

3. 2. The system according to claim 1, wherein the means for accepting a rule generation request from a user is implemented through a Web interface.

4. 2. The system according to claim 1, wherein the means for notifying and sharing the finalized rules with all users within the organization uses both email and an internal notification system.

Images