System

Abstract

To provide a system.SOLUTION: A system includes: means for designating a managerial position of an organization and a plurality of business contents included in the organization for each of a plurality of regenerative AI's, and allowing the plurality of regenerative AI's to manage the organization while talking to one another; means for confirming whether an organization can be managed on the basis of data that becomes a base for the system; analysis means for analyzing a result of simulated organization management by inputting a scenario of the simulated organization management inputted by a user to regenerative AI models; means for specifying a problematical point in the organization on the basis of a result of the simulated organization management by the analysis means and a feeling by inputting a feeling engine for recognizing a user's feeling and a specific prompt sentence to regenerative AI models, and proposing a solution for the specified problematical point; and means for reinforcing a successful strategy of the organization and correcting a failed strategy of the organization by feeding back the feeling to a simulation engine.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Currently, company management relies heavily on human experience and intuition, which can make it difficult to make appropriate management decisions. In addition, there is no way to conduct simulated company management that takes into account the size of the company, number of members, skills, etc., and provide consulting on future company management based on the results. [Means for solving the problem]

[0005] The system disclosed herein includes: a means for assigning an organizational position and multiple job duties within the organization to each of multiple generative AIs, and running the organization while having the multiple generative AIs converse with each other; a means for confirming whether organization management can be performed based on data that forms the basis of the system; an analysis means for analyzing the results of the simulated organizational management by inputting a simulated organizational management scenario entered by a user into a generative AI model; an emotion engine that recognizes the user's emotions; a means for identifying problems in the organization based on the results of the simulated organizational management by the analysis means and the emotions by inputting a specific prompt sentence into the generative AI model, and proposing solutions to the identified problems; and a means for strengthening a successful strategy of the organization and correcting an unsuccessful strategy of the organization by feeding back the emotions to a simulation engine. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. [Figure 19] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the embodiment 2 of the second embodiment in the case where an emotion engine is combined. [Figure 20] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when combined with an emotion engine. [Figure 21] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the embodiment 3 of the form example 3 in the case where an emotion engine is combined. [Figure 22] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Also, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices.

[0010] Examples of the computing device include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0011] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0012] 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.

[0013] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0014] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0015] [First embodiment]

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 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 wide area network (WAN) and / or a local area network (LAN).

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

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

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0026] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing 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.

[0027] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0028] "Example 1"

[0029] In one embodiment of the present invention, the generation AI is assigned job titles such as president, department manager, section manager, and member, and the work content of each section is set. For example, the AI ​​of the sales department is made to plan a strategy for acquiring new customers, and the AI ​​of the development department is made to plan the development of a new product. These AIs run the company while talking to each other.

[0030] "Example 2"

[0031] In another embodiment of the present invention, the size of the company, the number of members, skills, etc. are specified, and the AIs run a simulated company. For example, conditions are set such as a small- or medium-sized company with 50 members and a diverse skill set, and the AI ​​runs a simulated company.

[0032] "Example 3"

[0033] As a further embodiment of the present invention, consulting on future company management is provided based on the results of the simulated company management. For example, if the result of the company management simulated by the AI ​​shows that the strategy for acquiring new customers is not successful, the cause is analyzed and a remedy is proposed. The server may include a means for analyzing the cause and proposing a remedy when the result of the simulated organization management shows that the strategy for acquiring new customers is not successful.

[0034] The process flow of each embodiment will be described below.

[0035] "Example 1"

[0036] Step 1: Specify job titles such as president, department manager, section manager, and member to the generating AI.

[0037] Step 2: Set the work content for each department. For example, have the AI ​​in the sales department create a strategy to acquire new customers, and the AI ​​in the development department create a development plan for a new product.

[0038] Step 3: These AIs will talk to each other and run the company.

[0039] "Example 2"

[0040] Step 1: Specify the size of your company, number of members, skills, etc.

[0041] Step 2: Have the AIs run a simulated company. For example, set conditions such as a small- or medium-sized company with 50 members and diverse skill sets, and have the AI ​​run a simulated company.

[0042] "Example 3"

[0043] Step 1: Based on the results of the simulated company operations, provide consulting for future company operations.

[0044] Step 2: For example, if the strategy for acquiring new customers is not successful as a result of the company management simulated by the AI, analyze the cause and propose a remedy. The server may include a means for analyzing the cause and proposing a remedy when the strategy for acquiring new customers is not successful as a result of the simulated organization management.

[0045] Example 1

[0046] Next, a description will be given of Example 1 of the embodiment 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".

[0047] In traditional organizational management, the task content for each position and progress management were often done manually, making efficient management difficult. In addition, there was a lack of cooperation between departments, making it difficult to share information and unify strategies. Furthermore, it was difficult to find an appropriate management method based on the size of the organization and the skills of its members, and there was also the problem of being unable to provide sufficient consulting on future management.

[0048] 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.

[0049] In this invention, the server includes a means for assigning job titles and work content to multiple generation AIs and having the AIs talk to each other to operate the organization, a means for checking whether the organization can be operated appropriately based on a huge data backbone, a means for a user to access the system and set job titles and work content, a means for the server to generate AIs corresponding to each job title using a generation AI model, a means for the server to assign work content to each AI, a means for each AI to talk to each other and proceed with the work, a means for the server to monitor the conversation content and progress of each AI and make adjustments as necessary, and a means for a user to access the system and check the progress. This enables efficient organization management, strengthens cooperation between each department, and makes it easier to share information and unify strategies. It also makes it possible to explore appropriate management methods according to the size of the organization and the skills of its members, and provides consulting for future management.

[0050] "Generative AI" is a type of artificial intelligence that uses natural language processing to generate text.

[0051] A "position" indicates a job title or level of responsibility within an organization, and includes, for example, president, department manager, section manager, member, etc.

[0052] "Job content" refers to the specific duties and tasks each position is responsible for, such as developing strategies for acquiring new customers and planning new product development.

[0053] A "server" refers to a computer system that provides services to other computers over a network.

[0054] "User" refers to a person or organization that uses the system.

[0055] "Data backbone" refers to the large amount of data that forms the foundation of the system, on which appropriate decisions and operations are made.

[0056] A "prompt" is text that is used to input specific instructions or questions to the generative AI.

[0057] "Progress" refers to the state or condition that indicates how far a task or project has progressed.

[0058] "Simulated organizational management" refers to virtually trying out management methods by simulating actual organizational management.

[0059] "Consulting" refers to providing advice and support regarding organizational management based on specialized knowledge and experience.

[0060] The present invention relates to a system for improving the efficiency of organizational management by using a generative AI. A specific embodiment of this system will be described below.

[0061] First, the user accesses the system using a terminal. The user specifies the role of the person, such as president, department manager, section manager, or member, and sets the job content for each role. For example, the AI ​​for the sales department can be set to "draft a strategy to acquire new customers," and the AI ​​for the development department can be set to "draft a development plan for a new product."

[0062] Next, the server uses a generative AI model (e.g., GPT-4 (registered trademark) by OpenAI (registered trademark)) to generate an AI corresponding to each job title. The server inputs the job content set by the user as a prompt to the generated AI.

[0063] The server assigns each generated AI task set by the user. For example, the sales department's AI could be assigned the task of "creating a strategy to acquire new customers," while the development department's AI could be assigned the task of "creating a development plan for a new product."

[0064] Each AI will carry out its assigned tasks by talking to each other. For example, if the sales department's AI suggests that "we should strengthen social media advertising to acquire new customers," the development department's AI will respond by saying, "We will adjust the development schedule for new products to match the advertising strategy."

[0065] The server monitors the conversation content and work progress of each AI in real time. If necessary, the server adjusts the AI's tasks to support the smooth running of work. For example, if the strategy proposed by the sales department's AI is not feasible, the server will instruct it to revise the proposal.

[0066] The user can access the system again using a terminal to check the progress of each AI task. The user can issue new instructions to the AI ​​if necessary.

[0067] As a concrete example, if a user inputs "Sales AI, please plan a new customer acquisition strategy for the next quarter," the server will send this prompt to the Sales AI. The Sales AI will respond with, "We will propose a strategy to strengthen SNS advertising in the next quarter and expand the target demographic." If the user then inputs, "Development AI, please plan a new product development plan and adjust it to match the Sales strategy," the server will send this prompt to the Development AI. The Development AI will respond with, "We will bring forward the development schedule for the new product and conduct promotions in line with SNS advertising."

[0068] In this way, the server uses the generative AI model to assign tasks to the AIs in each role and run the organization by having them work together. This system enables efficient organizational management, strengthens collaboration between departments, and makes it easier to share information and unify strategies. It also makes it possible to explore appropriate management methods according to the size of the organization and the skills of its members, and provides consulting on future management.

[0069] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0070] Step 1:

[0071] A user accesses the system and sets their job title and job description.

[0072] Input: The user uses a terminal to input job titles such as president, department manager, section manager, and member, as well as the job description of each position.

[0073] Data processing: The server saves the job title and job description entered by the user in a database.

[0074] Output: Data with job title and job description is generated.

[0075] Specific operations: Through the terminal interface, the user inputs to the sales department's AI, "Draw up a strategy for acquiring new customers," and to the development department's AI, "Draw up a development plan for a new product."

[0076] Step 2:

[0077] The server uses the generative AI model to generate AI corresponding to each position.

[0078] Input: The server retrieves the job title and job description data stored in step 1.

[0079] Data processing: The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate AI corresponding to each role.

[0080] Output: A generation AI corresponding to each role is generated.

[0081] Specific operation: The server generates a GPT-4 as the AI ​​for the sales department and another GPT-4 instance as the AI ​​for the development department.

[0082] Step 3:

[0083] The server assigns tasks to each AI.

[0084] Input: The server obtains the data of each AI generated in step 2 and the task content set in step 1.

[0085] Data processing: The server inputs the corresponding task details as prompts for each AI.

[0086] Output: An AI with assigned task content is generated.

[0087] Specific operation: The server inputs a prompt to the sales department's AI, "Draw up a strategy for acquiring new customers," and a prompt to the development department's AI, "Draw up a development plan for a new product."

[0088] Step 4:

[0089] Each AI will converse with each other and carry out its work.

[0090] Input: Prompts for the tasks assigned to each AI.

[0091] Data processing: Each AI carries out its assigned tasks by conversing with each other.

[0092] Output: The business plans and strategies generated by each AI.

[0093] Specific operation: The sales department's AI suggests, "We should strengthen our social media advertising to acquire new customers," and the development department's AI responds, "We will adjust the development schedule for new products to match our advertising strategy."

[0094] Step 5:

[0095] The server monitors the conversations and progress of each AI and makes adjustments as necessary.

[0096] Input: Conversation content and work progress data of each AI.

[0097] Data processing: The server monitors the conversation content and progress of each AI in real time and adjusts tasks as necessary.

[0098] Output: Aligned business plans and strategies.

[0099] Specific operation: If the strategy proposed by the sales department's AI is not feasible, the server instructs the sales department to revise the proposal.

[0100] Step 6:

[0101] The user accesses the system and checks the progress.

[0102] Input: The user uses a terminal to access the system and check the progress of each AI.

[0103] Data processing: The server formats the data to display each AI's progress to the user.

[0104] Output: A user-visible display of progress.

[0105] Specific operations: Through the terminal, the user can check the progress of the strategies proposed by the sales department's AI and the development plans drawn up by the development department's AI, and issue new instructions as necessary.

[0106] (Application example 1)

[0107] Next, a description will be given of Application Example 1 of Form 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."

[0108] In traditional company and factory operations, human managers were required to oversee the work of each department and machine to ensure optimal operation. However, this required a great deal of effort and time, making efficient operation difficult. In addition, because each department and machine operated independently, there was a lack of overall coordination, and optimal operation was often not possible. Furthermore, there was a lack of systems for performing simulated operations, making it difficult to grasp problems in actual operations in advance. In order to solve these issues, an efficient operation system that utilizes AI is needed.

[0109] 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.

[0110] In this invention, the server includes a means for assigning job titles and work content for each section to multiple generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be properly managed based on a huge data backbone, and a means for assigning job titles to each machine in the factory, each machine taking charge of a specific task, and optimizing the operation of the entire factory while conversing with each other. This enables efficient company and factory operations using AI.

[0111] "Generative AI" is artificial intelligence that generates new information or content based on given data or prompts.

[0112] A "position" is a rank or position within an organization that has specific duties and responsibilities.

[0113] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[0114] A "conversation" is the process by which multiple AIs exchange information with each other and communicate with each other.

[0115] "Means of running the company" refers to methods and systems that use AI to manage the operations of the entire organization and operate it efficiently.

[0116] A "data backbone" is a data infrastructure that enables AI to make appropriate judgments and predictions based on massive amounts of data.

[0117] "Each machine in the factory" refers to the various devices and equipment in the factory used for manufacturing and production.

[0118] "Taking charge of specific tasks" means that each machine or AI carries out specific tasks or work according to its role.

[0119] "Means to optimize operations throughout the factory" refers to methods or systems in which each machine and AI within the factory works together to efficiently produce and manage, thereby improving overall performance.

[0120] The following system is constructed as an embodiment of the present invention. The server includes a means for assigning job titles and work content for each department to multiple generation AIs and running the company while having the AIs converse with each other, a means for confirming whether the company can be properly run based on a huge data backbone, and a means for assigning job titles to each machine in the factory, each machine taking charge of a specific task, and optimizing the operation of the entire factory while conversing with each other.

[0121] System Programming

[0122] The server uses Python and the OpenAI API to execute a program that assigns the job title and job content to each generated AI. Specifically, it performs the following process.

[0123] 1. The server generates a prompt for each generated AI, specifying the job title and job description.

[0124] 2. The server uses the OpenAI API to send a prompt to the generating AI and get a response.

[0125] 3. Based on the responses received, the server allows each generation AI to converse with each other and proceed with the work.

[0126] Hardware and Software Used

[0127] Hardware: Each machine in the factory (production line robots, quality control robots, logistics robots, maintenance robots, etc.)

[0128] Software: Python, OpenAI API

[0129] Data processing and calculation

[0130] The server generates and sends a prompt sentence like the following to each generated AI.

[0131] Examples of prompt statements

[0132] "Please act as a manufacturing line robot and create production plans."

[0133] "As a quality control robot, please create a quality check strategy."

[0134] "As a logistics robot, please manage inventory and plan delivery."

[0135] "As a maintenance robot, please create a maintenance plan for the equipment."

[0136] The server receives the generative AI's responses to these prompts, and each machine is responsible for a specific task, and as they converse with each other, they generate data to optimize the operation of the entire factory.

[0137] Examples

[0138] For example, if a manufacturing line robot is sent a prompt saying, "As a manufacturing line robot, please create a production plan," the generation AI will propose a specific production plan. A quality control robot can be sent a prompt saying, "As a quality control robot, please create a quality check strategy," which will have it propose a specific strategy for quality checks. This makes it possible for each machine in the factory to work together to efficiently carry out operations and optimize the operation of the entire factory.

[0139] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0140] Step 1:

[0141] The server generates a prompt statement specifying the job title and job description for each generated AI.

[0142] Input: List of job titles and job duties

[0143] Output: Prompt for each generated AI

[0144] Specific operation: The server creates an appropriate prompt for each AI based on the list of job titles and job content. For example, it generates a prompt such as, "As a manufacturing line robot, please create a production plan."

[0145] Step 2:

[0146] The server sends the generated prompt text to each generating AI using the OpenAI API.

[0147] Input: Generated prompt text

[0148] Output: Response from the generation AI

[0149] Specific operation: The server sends the generated prompt text to the OpenAI API and waits for a response from each generated AI. For example, it obtains a response to the prompt text, "As a manufacturing line robot, please create a production plan."

[0150] Step 3:

[0151] The server analyzes the responses it receives and confirms the tasks for which each generation AI is responsible.

[0152] Input: Response from the generation AI

[0153] Output: Analyzed business content

[0154] Specific operation: The server analyzes the response from the generation AI and checks the work content proposed by each generation AI. For example, it analyzes the specific production plan proposed by a manufacturing line robot.

[0155] Step 4:

[0156] The server creates an operation plan for the entire factory based on the suggestions of each generation AI.

[0157] Input: Parsed business content

[0158] Output: Factory-wide operation plan

[0159] Specific operation: The server integrates the work content proposed by each generation AI and creates an operation plan for the entire factory. For example, it integrates the production plan for the manufacturing line robot and the quality check strategy for the quality control robot.

[0160] Step 5:

[0161] The server distributes the created operation plan to each machine in the factory and has them execute it.

[0162] Input: Overall plant operation plan

[0163] Output: Instructions for each machine to execute

[0164] Specific operations: The server distributes the created operation plan to each machine in the factory and instructs each machine to carry out its work based on the plan. For example, it instructs a manufacturing line robot to carry out a specific production task.

[0165] Step 6:

[0166] The server monitors the performance of each machine and makes adjustments as necessary.

[0167] Input: Running status data for each machine

[0168] Output: Adjustment instructions

[0169] Specific operation: The server monitors the execution status of each machine in real time and issues adjustment instructions as necessary. For example, if there is a delay in the production plan, it instructs the manufacturing line robot to adjust the schedule.

[0170] Example 2

[0171] Next, a second embodiment of the second embodiment will be described. 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."

[0172] In conventional company management simulation systems, it was difficult to perform realistic simulations based on conditions specified by the user. In addition, there was a lack of means to provide users with the results of simulated company management simulations using generative AI models, so the information that users could obtain was limited. Furthermore, there was a lack of concrete means to provide consulting for future company management.

[0173] 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.

[0174] In this invention, the server includes a means for allowing a user to input conditions such as the size of the company, the number of members, and a skill set, a means for generating simulated company data based on the conditions, a means for executing a simulation based on the generated company data, and a means for providing the user with the simulation results. This makes it possible to perform a realistic simulation based on the conditions specified by the user, and to provide the user with the results of a simulated company management simulation using a generated AI model. In addition, a specific means for providing consulting on future company management is also provided.

[0175] A "user" is a person or organization that uses the system to input conditions for simulating company operations.

[0176] A "server" is a computer system that receives input from users, generates data, runs simulations, and provides results.

[0177] "Conditions" are information entered by the user, such as company size, number of members, skill set, etc.

[0178] "Simulated company data" refers to data such as the skill sets, job titles, and job descriptions of company members that is generated based on conditions entered by the user.

[0179] "Simulation" is the process of virtually recreating the operating conditions of a company using a generative AI model based on generated simulated company data.

[0180] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to generate simulated company data based on user input and run simulations.

[0181] "Simulation results" refers to information obtained by running a simulation, such as the company's performance, the performance of each member, problems, and areas for improvement.

[0182] "Consulting" is the process of providing advice and suggestions regarding the future management of a company based on the results of a simulation.

[0183] The present invention is a system for simulating a mock company operation based on conditions specified by a user and providing the results. A specific embodiment of this system will be described below.

[0184] Hardware and Software Used

[0185] Hardware: High-performance servers (e.g. virtual servers in cloud services)

[0186] Software: Generative AI models (e.g., AI models that perform natural language processing), database management systems (e.g., MySQL), web servers (e.g., Nginx)

[0187] System Overview

[0188] The system generates mock company data based on conditions entered by the user through a terminal, such as company size, number of members, and skill sets. Based on the generated data, it runs a simulation using a generative AI model and provides the results to the user.

[0189] Program Processing

[0190] The server receives input from the user and starts a simulation to run a mock company based on the specified conditions. Specifically, the process proceeds as follows:

[0191] 1. Receive user input:

[0192] A user accesses a web interface using a terminal and inputs conditions such as company size, number of members, skill set, etc. For example, the user inputs conditions such as "small to medium-sized business, 50 members, diverse skill sets."

[0193] 2. Conditional Data Generation:

[0194] The server generates data for a mock company based on the conditions entered by the user, including each member's skill set, job title, and job description, and uses a generative AI model to create and input prompts.

[0195] Example prompt:

[0196] "Please simulate the operation of a small to medium-sized company with 50 members and diverse skill sets. Please consider each member's job title, skills, and duties and simulate the overall operation of the company."

[0197] 3. Run the simulation:

[0198] The server starts a simulation based on the generated company data. The generative AI model simulates the behavior and work progress of each member and evaluates the overall operating status of the company.

[0199] 4. Result output:

[0200] The server provides the user with the results of the simulation, including the company's performance, the performance of each member, problems, and areas for improvement.

[0201] Examples

[0202] For example, if a user enters conditions such as "small to medium-sized business, 50 members, diverse skill sets," the server generates simulated company data based on these conditions. The generative AI model runs a simulation using prompt statements to evaluate the behavior of each member and the progress of work. The simulation results are provided to the user, displaying the company's performance, the performance of each member, problems, and areas for improvement.

[0203] This system allows users to perform realistic simulations based on specified conditions and obtain simulated company operations using generative AI models. It also provides specific means for consulting on future company operations.

[0204] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0205] Step 1:

[0206] Receiving user input

[0207] A user uses a terminal to access a web interface and inputs conditions such as company size, number of members, and skill sets. For example, the user may input conditions such as "small to medium-sized business, 50 members, diverse skill sets." The terminal sends the information entered by the user to the server. The server stores the received information in a database.

[0208] Input: Company size, number of members, skill set, and other criteria

[0209] Output: User input information stored in a database

[0210] Step 2:

[0211] Conditional Data Generation

[0212] The server retrieves the conditions entered by the user from the database. The server uses the generative AI model to generate data for a simulated company. This data includes each member's skill set, job title, and job description. The server creates and inputs a prompt sentence to the generative AI model.

[0213] Example prompt:

[0214] "Please simulate the operation of a small to medium-sized company with 50 members and diverse skill sets. Please consider each member's job title, skills, and duties and simulate the overall operation of the company."

[0215] Input: User criteria retrieved from the database

[0216] Output: Generated mock company data

[0217] Step 3:

[0218] Running the Simulation

[0219] The server starts a simulation based on the generated company data. The generative AI model simulates the actions and work progress of each member and evaluates the overall operational status of the company. The server creates and inputs a prompt for the simulation to the generative AI model.

[0220] Example prompt:

[0221] "Simulate the actions and work progress of each member based on the generated company data."

[0222] Input: Generated mock company data

[0223] Output: Simulation results

[0224] Step 4:

[0225] Output of results

[0226] The server formats the simulation results to provide them to the user. The terminal displays the simulation results to the user, such as the company's performance, the performance of each member, problems and areas for improvement, etc. The server stores the simulation results in a database.

[0227] Input: Simulation results

[0228] Output: Formatted simulation results provided to the user.

[0229] In this way, users can perform realistic simulations based on specified conditions and obtain simulated results of company operations using generative AI models.

[0230] (Application example 2)

[0231] Next, a description will be given of Application Example 2 of Form 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."

[0232] Conventional company management simulation systems allow users to specify the size of a company, the number of members, and the skill set to perform simulated operations, but lack simulations specialized for factory operations. In addition, they lack the functionality to automatically simulate a factory's production efficiency, cost management, and quality management and propose optimal operation methods, making it difficult to optimize actual factory operations. This creates the issue that no specific proposals can be made to improve the efficiency of factory operations, making it difficult to optimize operations.

[0233] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0234] In this invention, the server includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be appropriately managed based on a huge data backbone, a means for specifying the size of the factory, the number of employees, and the skill set, and for the AI ​​to simulate the operation of the factory, and a means for the AI ​​to automatically simulate the production efficiency, cost management, and quality management of the factory and propose the optimal operation method. This makes it possible to optimize the production efficiency, cost management, and quality management in the operation of the factory.

[0235] "Generative AI" refers to artificial intelligence that generates new information and content based on data.

[0236] A "position" indicates a rank of job or responsibility within an organization.

[0237] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[0238] A "data backbone" refers to the large amount of data that forms the foundation of systems and networks.

[0239] "Corporate management" refers to all activities involved in running and managing a business.

[0240] "Factory size" refers to the physical size and production capacity of the factory.

[0241] "Number of employees" refers to the total number of people working in an organization or factory.

[0242] A "skill set" is a collection of skills and abilities possessed by an individual or group.

[0243] "Running a simulated factory" means simulating actual factory operations.

[0244] "Production efficiency" indicates the ratio of production volume obtained to the resources input.

[0245] "Cost management" is the activity of planning, monitoring and controlling expenses in a business or factory.

[0246] "Quality control" refers to activities for maintaining and improving the quality of products and services.

[0247] "Proposing the optimal management method" means presenting specific methods and strategies for maximizing management efficiency.

[0248] The system for implementing this invention has the function of assigning job titles and work content for each department to multiple generation AIs, and having the AIs converse with each other to operate the company. It also has a function to check whether the company can be managed appropriately based on a huge data backbone. Furthermore, it has a function to specify the size of the factory, the number of employees, and the skill set, and have the AI ​​simulate the operation of the factory, and includes a function to automatically simulate the production efficiency, cost management, and quality management of the factory and propose the optimal operation method.

[0249] Hardware and Software Used

[0250] Hardware: Factory robots (e.g. ABB's IRB series), servers (e.g. AWS EC2 instances)

[0251] Software: Python 3.x, machine learning libraries (e.g. TENSORFLOW(registered trademark), PyTorch), databases (e.g. MySQL)

[0252] Data processing and calculation

[0253] The server first randomly generates employee skill sets. To do this, it uses Python random functions to randomly assign skills such as "assembly," "quality control," "maintenance," and "logistics" to each employee. Next, it simulates the operating efficiency of the factory based on the generated skill sets. Specifically, it aggregates the skill sets of each employee and calculates the production efficiency of the entire factory.

[0254] Examples

[0255] For example, when simulating a factory with 100 employees and four skill sets - assembly, quality control, maintenance, and logistics - the server performs the following process.

[0256] 1. Data generation: Randomly generate employee skill sets using the generate_employees function.

[0257] 2. Simulation: The simulate_operation method calculates the operational efficiency of the factory. Based on the skill sets of the employees, the efficiency of the entire factory is evaluated.

[0258] 3. Result output: Output the simulation results to help optimize factory operations.

[0259] Examples of prompt statements

[0260] An example of a prompt to be input to the generative AI model is as follows:

[0261] "Simulate the operational efficiency of a factory with 100 employees and the skill sets of 'Assembly', 'Quality Control', 'Maintenance' and 'Logistics'."

[0262] In this way, the factory operation simulator can evaluate the factory's operating efficiency and propose optimal operating methods.

[0263] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0264] Step 1:

[0265] The server randomly generates employee skill sets. Specifically, it uses Python random functions to randomly assign skills such as "assembly," "quality control," "maintenance," and "logistics" to each employee. The input requires the number of employees and a list of skill sets, and the output is the generated skill set for each employee.

[0266] Step 2:

[0267] The server simulates the factory's operational efficiency based on the generated skill sets. Specifically, it aggregates the skill sets of each employee and calculates the production efficiency of the entire factory. The input is the skill set of each employee, and the output is the operational efficiency of the entire factory.

[0268] Step 3:

[0269] The server generates optimization proposals for factory operations based on the simulation results. Specifically, it uses a generative AI model to present specific methods and strategies for maximizing operational efficiency. Simulation results are required as input, and optimization proposals are obtained as output.

[0270] Step 4:

[0271] The server presents the optimization proposal to the user by sending the generated proposal to the user's terminal for the user to review. As input, an optimization proposal is required, and as output, a proposal is obtained that is displayed on the user's terminal.

[0272] Step 5:

[0273] The user implements improvements to factory operations based on the presented optimization proposals. Specifically, the user applies the proposed methods and strategies to actual factory operations and confirms their effectiveness. The input is the optimization proposals, and the output is the improved factory operations.

[0274] Example 3

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

[0276] Conventional organizational management simulation systems did not sufficiently simulate operations using generative artificial intelligence, making it difficult to evaluate the effectiveness of strategies in actual operations in advance. In addition, they lacked the functionality to effectively utilize past operational data and market data and propose specific improvement measures based on simulation results. As a result, organizational management efficiency and strategy optimization were not fully achieved.

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

[0278] In this invention, the server includes a means for assigning job titles and work contents of each department to a plurality of generative AIs and having the AIs converse with each other to operate the organization, a means for confirming whether appropriate organizational management can be performed based on a huge data backbone, a means for collecting past operational data and market data, a means for simulating simulated organizational management using a generative AI model based on the collected data, a means for analyzing the simulation results and identifying successful and unsuccessful strategies, and a means for proposing improvement measures based on the analysis results. This makes it possible to improve the efficiency of organizational management and optimize strategies. The server may include a means for confirming whether organizational management can be performed based on a data backbone, which is a large amount of data that forms the basis of the system.

[0279] "Generative artificial intelligence" is artificial intelligence that uses natural language processing and machine learning to generate data and perform specific tasks.

[0280] A "position" refers to a position within an organization that has specific duties and responsibilities.

[0281] "Job Description" refers to the specific work or tasks associated with a particular position or job function.

[0282] "Data backbone" refers to the vast data foundation that the system uses, including the infrastructure that supports data collection, storage, and analysis.

[0283] "Organizational management" refers to the processes of planning, executing, controlling, and evaluating necessary to achieve an organization's goals.

[0284] "Simulation" refers to a method for simulating real-world operating conditions and predicting the results.

[0285] "Strategy" refers to the plans and policies for achieving an organization's goals.

[0286] "Improvement measures" refer to specific methods or means for solving current problems and achieving better results.

[0287] "Data collection" refers to the process of gathering the necessary information or data.

[0288] "Analysis" refers to the process of evaluating collected data and extracting meaningful information.

[0289] This invention is a system that uses generative artificial intelligence to simulate organizational management and aims to improve the efficiency of organizational management and optimize strategies based on the results. A specific embodiment of this system is described below.

[0290] System program generation

[0291] The server generates a program for a system that provides consulting based on the results of the simulated organizational management. This program uses a generative AI model (e.g., GPT-4 by OpenAI) to simulate organizational management and analyzes the results. The server may include an analysis means that inputs a scenario of the simulated organizational management input by a user into the generative AI model, thereby analyzing the results of the simulated organizational management.

[0292] Program processing explanation

[0293] The server uses the generative AI model to simulate organizational operations. In this simulation, the following data processing and calculations are performed:

[0294] 1. Data collection: The server collects past organizational operation data and market data, including sales data, customer data, marketing data, etc. Specifically, the server obtains these data from a database (e.g., MySQL or PostgreSQL). It also collects marketing data through APIs and collects competitor data using web scraping technology.

[0295] 2. Simulation execution: Based on the collected data, the generative AI model performs simulated organizational operations. For example, it executes a marketing strategy to acquire new customers and simulates the results. The server preprocesses the collected data and converts it into a format to be input to the generative AI model. Next, a prompt sentence is input to the generative AI model and the simulation is executed. An example of a prompt sentence is "Simulate a marketing strategy to acquire new customers and predict the results." The simulation results obtained from the generative AI model are stored on the server.

[0296] 3. Result analysis: The server analyzes the results of the simulation. Specifically, it identifies successful and unsuccessful strategies and analyzes the causes. The server uses a generative AI model to perform a causal analysis of the simulation results. An example of a prompt is "Analyze the causes of the simulation results and identify successful and unsuccessful strategies." The results of the causal analysis are generated in the form of a report.

[0297] 4. Proposal of improvement measures: The server proposes improvement measures based on the analysis results. For example, if the strategy for acquiring new customers is not effective, the server identifies the cause and proposes improvement measures. The server generates improvement measures using a generative AI model based on the results of the causal analysis. An example of a prompt sentence is "Please propose improvement measures based on the cause why the strategy for acquiring new customers was not effective." The generated improvement measures are notified to the user, and a specific action plan for implementing the improvement measures is generated. The server may include a means for analyzing the cause and proposing improvement measures when the strategy for acquiring new customers is not effective as a result of the simulated organizational operation.

[0298] Examples

[0299] The user requests the server to simulate a marketing strategy for acquiring new customers. The server collects past marketing data and runs a simulation using a generative AI model. The simulation results show that the strategy for acquiring new customers did not produce the expected results. The server analyzes the cause and identifies reasons such as "the target market was selected inappropriately." The server then proposes improvement measures such as "reevaluating the target market and focusing on a more appropriate market."

[0300] In this way, the server provides a system for consulting on future organizational management based on the results of the simulated organizational management. The flow of the specific process in the third embodiment will be described with reference to Fig. 15. The server may include an analysis means for inputting the scenario of the simulated organizational management input by the user into the generative AI model, thereby analyzing the results of the simulated organizational management.

[0301] Step 1: Data collection

[0302] The server collects historical organizational operational data and market data. The inputs include sales data, customer data, marketing data, etc. The server retrieves these data from a database (e.g. MySQL or PostgreSQL). It also collects marketing data through APIs and competitor data using web scraping techniques. The output is the collected data.

[0303] Specific behavior:

[0304] The server retrieves historical sales data from a database using a SQL query.

[0305] The server collects marketing data through an API.

[0306] The server collects competitor data using web scraping technology.

[0307] Step 2: Data Preprocessing

[0308] The server preprocesses the collected data and converts it into a format that can be input to the generative AI model. The input includes the collected raw data. The server processes the data by cleaning, normalizing, extracting features, etc. The output is the preprocessed data.

[0309] Specific behavior:

[0310] The server imputes missing values ​​and removes outliers.

[0311] The server normalizes and scales the data.

[0312] The server extracts features and converts them into a format suitable for the generative AI model.

[0313] Step 3: Run the simulation

[0314] The server uses a generative AI model based on the preprocessed data to simulate a simulated organizational operation. The input includes the preprocessed data and a prompt sentence. The server inputs the prompt sentence to the generative AI model and executes the simulation. The output is the simulation result.

[0315] Specific behavior:

[0316] The server inputs a prompt sentence to the generative AI model.

[0317] Example prompt: "Simulate marketing strategies for acquiring new customers and predict the outcomes."

[0318] The server stores the simulation results obtained from the generative AI model.

[0319] Step 4: Analyze the results

[0320] The server analyzes the results of the simulation. As input, it contains the simulation results. Using a generative AI model, the server identifies successful and unsuccessful strategies and analyzes their causes. As output, it obtains the analysis results.

[0321] Specific behavior:

[0322] The server uses the generative AI model to perform factor analysis of the simulation results.

[0323] Example prompt: "Analyze the factors that contributed to the simulation results and identify successful and unsuccessful strategies."

[0324] The server generates the result of the factor analysis in the form of a report.

[0325] Step 5: Propose improvements

[0326] The server proposes improvement measures based on the analysis results. The input includes the results of the causal analysis. The server generates improvement measures using a generative AI model. The output is the improvement measures.

[0327] Specific behavior:

[0328] Based on the results of the factor analysis, the server uses a generative AI model to generate improvement measures.

[0329] Example prompt: "Based on why our customer acquisition strategy was unsuccessful, please suggest a solution."

[0330] The server notifies the user of the generated remedial action.

[0331] The server generates a specific action plan for implementing the remedial measures.

[0332] (Application example 3)

[0333] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0334] Conventional company management simulation systems lacked specific improvement measures based on the simulated management results, making it difficult to fully utilize them for strategy planning and decision-making in real company management. In addition, there was a lack of means to analyze the simulated management results and propose specific improvement measures, making it difficult for operators to create effective strategies.

[0335] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means. In this invention, the server includes a means for assigning job titles and work contents of each department to multiple generation AIs and running the company while having the AIs talk to each other, a means for confirming whether the company can be managed appropriately based on a huge data backbone, a means for providing consulting on future company management based on the results of the simulated company management, and a means for generating data of the simulated company management, analyzing the data, and proposing improvement measures. This makes it possible to propose specific improvement measures based on the results of the simulated management, which can be useful for strategy planning and decision-making in actual company management.

[0336] "Generative AI" refers to artificial intelligence that generates new information and results based on data.

[0337] A "position" is a position within an organization that has specific duties and responsibilities.

[0338] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[0339] "Having a conversation" refers to the process in which multiple AIs exchange information with each other.

[0340] "Running a company" means having an AI simulate the management activities of a company.

[0341] A "data backbone" refers to the vast data foundation used by the system.

[0342] "Good business management" refers to the methods and strategies for running a company efficiently and effectively.

[0343] "Simulated company operations" refers to the process of simulating actual company operations.

[0344] "Consulting" refers to the activity of providing advice and suggestions based on specialized knowledge and analysis.

[0345] "Generating data" refers to the process by which a system creates new data.

[0346] "Analyzing data" is the process of evaluating collected data and extracting meaningful information.

[0347] "Proposing improvements" means showing specific methods or strategies for solving current problems.

[0348] A system for implementing this invention includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to run a company, a means for confirming whether the company can be managed appropriately based on a huge data backbone, a means for providing consulting on future company management based on the results of the simulated company management, and a means for generating data on the simulated company management, analyzing the data, and proposing improvement measures.

[0349] Hardware and Software Used

[0350] Hardware: Servers, smartphones

[0351] Software: Python, NumPy, scikit-learn

[0352] Data processing and calculation

[0353] The server first generates data for a simulated company's operations, such as marketing budgets, website traffic, conversion rates, and sales, randomly generated data, and then uses a linear regression model to analyze the data and evaluate the impact of each factor on sales.

[0354] The server then uses the analysis to recommend specific improvements to boost sales, such as increasing the marketing budget or strengthening SEO measures to increase website traffic.

[0355] Examples

[0356] For example, if you set a marketing budget of 5,000 yen, your website traffic will be 2,000 people, and your conversion rate will be 0.05 (5%), your sales will be 100. Based on this data, the server can suggest that "increasing your marketing budget may improve your sales."

[0357] Examples of prompt statements

[0358] "If the marketing budget is set at 5,000 yen, the website traffic is 2,000 people, and the conversion rate is 0.05, then the sales will be 100. Please suggest improvement measures to increase sales based on this data."

[0359] In this way, the server can propose specific improvement measures based on the results of the simulated company operations, which the user can use to help with strategy planning and decision-making in the actual operation of the company.

[0360] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0361] Step 1:

[0362] The server generates data for a simulated company operation, i.e., randomly generating data such as marketing budget, website traffic, conversion rate, sales, etc. As input, it takes parameters such as marketing budget range and conversion rate range, and as output, it gets the generated dataset.

[0363] Step 2:

[0364] The server uses a linear regression model to analyze the generated data. As input, it receives the dataset generated in step 1, and as output, it obtains a model that evaluates the impact of each factor on sales. Specifically, it trains the model with marketing budget, website traffic, and conversion rate as features and sales as the target variable.

[0365] Step 3:

[0366] Based on the analysis results, the server proposes specific improvement measures to increase sales. As input, it receives the model obtained in step 2 and the dataset generated in step 1, and as output, it obtains a list of improvement measures. Specifically, it uses the model to predict sales for each data point, compares them with the actual sales, and if the predicted sales exceed the actual sales, it proposes improvement measures such as increasing the marketing budget or strengthening SEO measures.

[0367] Step 4:

[0368] The user receives the improvement measures proposed by the server and uses them to formulate strategies and make decisions in the actual operation of the company. As input, the user receives a list of improvement measures from the server, and as output, formulates a specific operation strategy. Specifically, based on the proposed improvement measures, the user adjusts the marketing budget and implements SEO measures.

[0369] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0370] "Example 1"

[0371] As an embodiment of the invention described in claim 4, a system in which a job title and the work content of each department are assigned to a generating AI and the AIs converse with each other to run a company is combined with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions from the user's tone of voice, facial expressions, and choice of words, and feeds the results back to the AI. For example, if the user expresses anger, the AI ​​receives that information and considers a countermeasure. This allows the AI ​​to respond appropriately according to the user's emotions.

[0372] "Example 2"

[0373] As an embodiment of the invention described in claim 5, there is a form in which an emotion engine that recognizes the emotions of a user is combined with a system in which AIs run a simulated company after specifying the size of the company, the number of members, skills, etc. This emotion engine analyzes the user's emotions and feeds the results back to the AI. For example, if the user expresses an emotion of joy, the AI ​​receives that information and considers a response such as re-implementing a successful strategy or action. This allows the AI ​​to respond appropriately according to the user's emotions.

[0374] "Example 3"

[0375] As an embodiment of the invention described in claim 6, there is a form in which an emotion engine that recognizes the emotions of a user is combined with a system that enables consulting for future company management.

[0376] The emotion engine analyzes the user's emotions and feeds the results back to the AI. For example, if the user expresses anxiety, the AI ​​receives that information, identifies the problem, and considers how to respond, such as proposing a solution. This allows the AI ​​to respond appropriately according to the user's emotions.

[0377] The process flow of each embodiment will be described below.

[0378] "Example 1"

[0379] Step 1: Specify the job titles and work content of each department to the generation AI.

[0380] Step 2: Have the AIs talk to each other and run the company.

[0381] Step 3: Combine an emotion engine to recognize user emotions.

[0382] Step 4: The emotion engine analyzes the user's emotions from their tone of voice, facial expressions, and choice of words.

[0383] Step 5: Feed back the analysis results to the AI.

[0384] Step 6: The AI ​​receives the feedback and considers a response.

[0385] "Example 2"

[0386] Step 1: Specify the size of your company, number of members, skills, etc.

[0387] Step 2: Have the AIs run a simulated company.

[0388] Step 3: Combine an emotion engine to recognize user emotions.

[0389] Step 4: The emotion engine analyzes the user's emotions.

[0390] Step 5: Feed back the analysis results to the AI.

[0391] Step 6: The AI ​​receives the feedback and considers a response.

[0392] "Example 3"

[0393] Step 1: Set up a system that will enable consulting on future company operations.

[0394] Step 2: Assemble an emotion engine to recognize the user's emotions.

[0395] Step 3: The emotion engine analyzes the user's emotion.

[0396] Step 4: Feed back the analysis results to the AI.

[0397] Step 5: The AI ​​receives the feedback and considers a response.

[0398] Example 1

[0399] Next, a description will be given of Example 1 of the embodiment 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".

[0400] Conventional organizational management systems did not adequately use AI to set job content for each position or to manage the system through conversation between AIs. In addition, they lacked the functionality to analyze user emotions and respond accordingly, making it difficult to increase user satisfaction. Furthermore, there was a lack of means to conduct simulated organizational management or future consulting. To solve these issues, a system that combines more advanced AI technology and emotion analysis technology is needed.

[0401] 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.

[0402] In this invention, the server includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to operate the organization, a means for confirming whether the organization can be operated appropriately based on a huge data backbone, a means for receiving user input and sending a prompt to the generation AI model, a means for the generation AI model to generate AI for each job title, a means for analyzing the user's emotions using an emotion engine and feeding back the results to the AI, and a means for making the AI ​​respond according to the user's emotions. This enables advanced organization management using AI and realizes flexible responses according to the user's emotions.

[0403] "Generative AI" is an artificial intelligence technology that generates AI with specific job titles and job duties based on user input.

[0404] A "prompt sentence" is an input sentence that instructs the generation AI on a specific job title or job content.

[0405] A "position" refers to a position within an organization that has specific responsibilities or duties.

[0406] "Job description" refers to the specific tasks and responsibilities assigned to a particular position.

[0407] The "emotion engine" is a technology that analyzes emotions from a user's tone of voice, facial expressions, choice of words, etc.

[0408] "Feedback" is the process of communicating analysis results and user responses to AI.

[0409] A "data backbone" is a fundamental system that supports the vast amounts of data necessary for organizational management.

[0410] "Simulated organizational management" is the process of simulating the management of an actual organization.

[0411] "Consulting" refers to the service of providing advice and guidance regarding organizational management.

[0412] This invention uses a system that combines a generative AI model and an emotion engine to realize advanced organizational management. A specific embodiment of this system is described below.

[0413] First, the server generates a program using a generative AI model. For this generative AI model, a high-performance AI model (e.g., OpenAI's GPT-4) that runs on a general cloud service is used. The server receives the user's input and sends a prompt sentence based on it to the generative AI model.

[0414] For example, if a user types, "What is your strategy for entering new markets?", the server will take this input and send a prompt to the generative AI model like this:

[0415] "You are an AI in the sales department. Please create a strategy to acquire new customers."

[0416] The generative AI model generates an AI for each job title based on this prompt. The generated AI is assigned to each department, such as the sales department or development department, and begins working according to the job content of each department. The server sets specific job content for these AI, and the AIs run the organization by conversing with each other.

[0417] Furthermore, the server uses an emotion engine to analyze the user's emotions. This emotion engine uses a general API capable of analyzing voice and facial expressions (e.g., Microsoft® Azure® Emotion API). It analyzes emotions from the user's tone of voice, facial expressions, and choice of words, and feeds the results back to the AI.

[0418] For example, if a user provides feedback such as "This strategy is specific and easy to understand," the server uses an emotion engine to sense tension from the user's tone of voice. This information is fed back to the sales department's AI, which then tells the user, "Don't worry, I'll explain the specific steps one by one."

[0419] The system also includes a method to check whether appropriate organizational management can be performed based on a huge data backbone. This enables advanced organizational management using AI and realizes flexible responses according to the user's emotions.

[0420] As a concrete example, there is a scenario in which a user inputs "Please tell me your strategy for entering a new market," the generative AI model generates the sales AI, and the sales AI asks the development AI, "Please tell me the features of the new product." The development AI responds, "The new product uses environmentally friendly materials," and the user provides feedback, "This strategy is specific and easy to understand." The server uses an emotion engine to sense tension from the tone of the user's voice, and the sales AI tells the user, "Don't worry, I'll explain the specific steps one by one."

[0421] In this way, a system is realized in which servers, terminals, and users work together to run an organization using generative AI models and emotion engines.

[0422] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0423] Step 1:

[0424] A user accesses the system.

[0425] A user accesses the system using a terminal (PC or smartphone). For example, the user opens a web browser and enters the system's URL. The system's URL is required as input, and the system's home screen is displayed as output.

[0426] Step 2:

[0427] The server receives the user's input.

[0428] The user types a specific question into the system's interface, such as "What is your strategy for entering new markets?" The server takes this input and generates a prompt. As input, it expects the user's question, and as output, it gets the generated prompt.

[0429] Step 3:

[0430] The server sends a prompt to the generative AI model.

[0431] The server sends the generated prompt sentence to the generative AI model. For example, it sends the prompt sentence, "You are an AI in the sales department. Please create a strategy for acquiring new customers." The generated prompt sentence is required as input, and the output is that it has been sent to the generative AI model.

[0432] Step 4:

[0433] The generative AI model generates AI for each job position.

[0434] The generative AI model generates AI for each job position based on the received prompt text. For example, it generates AI for the sales department and AI for the development department. The input requires a prompt text, and the output is the generated AI for each job position.

[0435] Step 5:

[0436] The server assigns the tasks to each AI.

[0437] The server sets specific tasks for each generated AI. For example, the task of "creating a strategy for acquiring new customers" is set for the AI ​​of the sales department. The generated AI and the task are required as inputs, and the output is an AI that reflects the set task.

[0438] Step 6:

[0439] Each AI initiates a conversation and runs the organization.

[0440] Each AI starts a conversation based on the set business content and runs the organization. For example, the AI ​​of the sales department asks the AI ​​of the development department, "Please tell me the features of the new product." The set business content is required as input, and the output is the progress of a conversation between the AIs.

[0441] Step 7:

[0442] The user provides feedback to the system.

[0443] The user provides feedback on the system's operation. For example, the user comments, "This strategy is specific and easy to understand." The user's feedback is required as an input, and the feedback is reflected in the system as an output.

[0444] Step 8:

[0445] The server uses an emotion engine to analyze the user's emotions.

[0446] The server uses an emotion engine to analyze emotions from the user's tone of voice, facial expressions, and choice of words. For example, it can sense tension from the user's tone of voice. The input is the user's voice and facial expressions, and the output is the analyzed emotion data.

[0447] Step 9:

[0448] The server feeds back the analysis results to the AI.

[0449] The server feeds back the emotion engine's analysis results to the AI. For example, information that "the user is nervous" is conveyed to the sales department's AI. The input is the analyzed emotion data, and the output is the feedback reflected in the AI.

[0450] Step 10:

[0451] Each AI responds according to the user's emotions.

[0452] Each AI responds according to the user's emotions based on the feedback. For example, the sales department's AI tells the user, "Don't worry, I'll explain each specific step one by one." The input requires the feedback emotion data, and the output is an appropriate response to the user.

[0453] (Application example 1)

[0454] Next, a description will be given of Application Example 1 of Form 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."

[0455] Conventional company management systems make it difficult to efficiently manage the work of each department and take appropriate action. In addition, they are unable to analyze users' emotions in real time and provide prompt responses based on the analysis, making it difficult to improve customer satisfaction. Furthermore, in brick-and-mortar stores, it is necessary to appropriately grasp and respond to the emotions of customers, but current systems lack such functionality.

[0456] 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.

[0457] In this invention, the server includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be managed appropriately based on a huge data backbone, a means for combining an emotion analysis engine that recognizes the user's emotions, analyzing the user's emotions from the user's tone of voice, facial expressions, and language, and feeding back the results to the AI, and a means for generating appropriate countermeasures based on the emotion analysis results. This makes it possible to efficiently manage the work of each department and quickly provide appropriate responses according to the user's emotions.

[0458] "Generative AI" is artificial intelligence that automatically conducts conversations and makes decisions based on specified job titles and job descriptions.

[0459] A "position" indicates a position or job within an organization, and examples include president, department manager, section manager, member, etc.

[0460] "Work content of each department" refers to the specific work and tasks that each department within an organization is responsible for.

[0461] "Having them converse" refers to the process in which multiple generative AIs exchange information with each other and make decisions.

[0462] "Running a company" refers to the generation AI running the entire organization based on designated job titles and job duties.

[0463] A "huge data backbone" refers to the massive data base that generative AI uses to make appropriate decisions.

[0464] "Verifying whether the company can be run appropriately" refers to the process of evaluating whether the decisions and strategies provided by the generative AI are effective in actual company operations.

[0465] An "emotion analysis engine" refers to software or hardware for analyzing emotions from a user's tone of voice, facial expressions, choice of words, etc.

[0466] "The tone of a user's voice" refers to characteristics such as the pitch and strength of the voice uttered by the user.

[0467] "Facial expressions" refer to the movements and expressions of a user's face, and are clues as to emotions.

[0468] "Language" refers to the choice of words and phrases a user uses, which provide clues as to their emotions.

[0469] "Emotion analysis" refers to the process of identifying a user's emotions from their tone of voice, facial expressions, and choice of words.

[0470] "Feedback" refers to the process of providing analyzed emotional information to the generative AI and having it reflected in decision-making.

[0471] "Generating an appropriate response" refers to the AI ​​devising the optimal way to respond to the user based on the analyzed emotional information.

[0472] The system for implementing this invention assigns job titles and the work content of each department to multiple generation AIs, and has the AIs converse with each other to run a company. In addition, it combines an emotion analysis engine that recognizes the user's emotions, analyzes the user's emotions from the tone of voice, facial expressions, and wording, and feeds the results back to the AI ​​to generate appropriate countermeasures.

[0473] Hardware and Software Used

[0474] 1. Hardware:

[0475] Smartphone (iOS / ANDROID (registered trademark))

[0476] Smart glasses (Google® Glass®, Microsoft HoloLens®, etc.)

[0477] 2. Software:

[0478] Generative AI models (e.g. GPT-4)

[0479] Sentiment analysis engine (Microsoft Azure Emotion API, IBM Watson(R) Tone Analyzer, etc.)

[0480] Mobile app development framework (React Native, Flutter (registered trademark), etc.)

[0481] Data processing and calculation

[0482] The server uses an emotion analysis engine to analyze the user's tone of voice, facial expressions, and choice of words, and feeds the results back to the generation AI, which then generates appropriate countermeasures based on the analysis results and provides them to the user via a smartphone or smart glasses.

[0483] Examples

[0484] For example, if a customer in a brick-and-mortar store expresses dissatisfaction with a staff member wearing smart glasses, the emotion analysis engine will detect "anger" and send that information to the generation AI, which will then instruct the staff on "specific measures to resolve the customer's dissatisfaction."

[0485] Examples of prompt statements

[0486] Analyze the user's tone of voice, facial expressions, and language to identify their emotions. If the user shows signs of anger, consider appropriate countermeasures.

[0487] This system makes it possible to efficiently manage the work of each department and quickly provide appropriate responses according to the user's emotions, which will improve the efficiency of brick-and-mortar store operations and customer satisfaction.

[0488] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0489] Step 1:

[0490] A user puts on the smart glasses and starts interacting with customers.

[0491] Input: Customers' voices, facial expressions, and language

[0492] Output: Audio data, video data

[0493] How it works: The microphone and camera in the smart glasses capture audio and video of customers.

[0494] Step 2:

[0495] The terminal transmits the captured audio and video data to the server.

[0496] Input: Audio data, video data

[0497] Output: Data sent to the server

[0498] How it works: The smart glasses upload data to the server via Wi-Fi or Bluetooth.

[0499] Step 3:

[0500] The server inputs the audio and video data into an emotion analysis engine to analyze emotions.

[0501] Input: Audio data, video data

[0502] Output: Sentiment analysis results (e.g. anger, joy, sadness)

[0503] How it works: An emotion analysis engine (such as Microsoft Azure Emotion API) analyzes voice tone and facial expressions to identify emotions.

[0504] Step 4:

[0505] The server feeds back the emotion analysis results to the generation AI.

[0506] Input: Sentiment analysis results

[0507] Output: Feedback data for the generative AI

[0508] What it does: Send the output of the sentiment analysis engine to a generative AI model (such as GPT-4).

[0509] Step 5:

[0510] The generative AI generates appropriate countermeasures based on the results of sentiment analysis.

[0511] Input: Sentiment analysis results

[0512] Output: Action to be taken (e.g., apology, reward, proposal to resolve the issue)

[0513] Specific operation: The generative AI generates a response based on the prompt text.

[0514] Step 6:

[0515] The server transmits the generated countermeasure to the terminal.

[0516] Input: Workaround

[0517] Output: Actions sent to the terminal

[0518] Specific operation: Send the output of the generative AI to smart glasses.

[0519] Step 7:

[0520] The terminal displays countermeasures to the user, and the user takes appropriate action to the customer.

[0521] Input: Workaround

[0522] Output: User action (e.g. apology, reward offer)

[0523] Specific operation: Countermeasures are displayed on the smart glasses display and the user acts accordingly.

[0524] Example 2

[0525] Next, a second embodiment of the second embodiment will be described. 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."

[0526] Conventional organizational management simulation systems were unable to take into account the user's feelings, resulting in low user satisfaction and low simulation realism. In addition, it was difficult to simulate specific conditions such as the size of the organization, the number of members, and skill sets, making it difficult to provide information that is useful for actual organizational management.

[0527] 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.

[0528] In this invention, the server includes a means for assigning job titles and the work content of each department to a plurality of generative AIs and having the AIs converse with each other to operate the organization, a means for confirming whether appropriate organizational management can be performed based on a huge data backbone, a means for a user to input the size of the organization, the number of members, and a skill set, a means for the generative AI to start a simulated organizational management, a means for analyzing the user's emotions using an emotion analysis engine, and a means for the generative AI to respond according to the user's emotions. This enables a realistic organizational management simulation that takes the user's emotions into account. The server may include a means for confirming whether organizational management can be performed based on a data backbone, which is a large amount of data that forms the basis of the system.

[0529] "Generative artificial intelligence" is artificial intelligence that has the ability to generate text and data using natural language processing and machine learning.

[0530] A "position" refers to a position within an organization that has specific duties and responsibilities.

[0531] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[0532] A "data backbone" is a collection of vast amounts of data used by a system, and refers to the basic data necessary for operating and analyzing the system.

[0533] "Organizational size" is an indicator of the size and scope of an organization, and is usually expressed in terms of the number of employees, sales, etc.

[0534] "Number of Members" refers to the total number of individual employees working within an organization.

[0535] A "skill set" refers to the collection of knowledge and techniques required to perform a specific task or job.

[0536] An "sentiment analysis engine" is software or a system that analyzes emotions from a user's text or behavior and provides the results.

[0537] "Simulated organizational management" refers to virtually operating an organization in a realistic environment by simulating actual organizational management.

[0538] "Responding according to the user's emotions" refers to the system taking appropriate reactions or actions based on the user's emotional state.

[0539] This invention is a system that simulates organizational management, and uses multiple generative artificial intelligences to simulate organizational management based on conditions specified by a user. Furthermore, by analyzing the user's emotions and responding according to the results, a more realistic simulation with high user satisfaction is realized.

[0540] Hardware and Software Used

[0541] Hardware: High-performance server (e.g. GPU-equipped server)

[0542] software:

[0543] Generative AI models (e.g. GPT-4)

[0544] Sentiment analysis engines (e.g. emotion analysis software)

[0545] Database management systems (e.g. database software)

[0546] Explanation of program processing

[0547] 1. A user accesses the system

[0548] Users access the system's web interface using a terminal (PC or smartphone).

[0549] The device launches a web browser and connects to the specified URL.

[0550] The server receives the user's access and displays a login screen.

[0551] 2. The user enters the company's requirements

[0552] Users input conditions such as the size of their organization (e.g., small or medium-sized enterprise), number of members (e.g., 50 people), and skill set (e.g., diverse) through their terminal.

[0553] The terminal transmits the input data to the server.

[0554] The server stores the received data in a database and proceeds to the next process.

[0555] 3. The server starts running a simulated organization.

[0556] Based on the stored conditions, the server starts a simulated organizational operation using a generative AI model (e.g., GPT-4).

[0557] The server sends a prompt to the generative AI model and starts the simulation.

[0558] The generative AI model generates various scenarios and simulates organizational management strategies and actions.

[0559] The server displays the generated scenario to the user.

[0560] 4. The server analyzes the user's emotions

[0561] While the user is using the system, the terminal collects the user's inputs and responses.

[0562] The terminal transmits the collected data to the server.

[0563] The server uses an emotion analysis engine (e.g., emotion analysis software) to analyze the user's emotions in real time.

[0564] The server feeds back the analysis results to the generative AI model.

[0565] 5. The server responds according to the user's emotions

[0566] The server receives feedback from the sentiment analysis engine and provides that information to the generative AI model.

[0567] The generative AI model considers responses based on the user's emotions, such as re-implementing successful strategies or actions.

[0568] The server displays new scenarios from the generative AI model to the user.

[0569] Examples and prompts

[0570] Examples:

[0571] The user enters the criteria: "Small to mid-size company with 50 members and diverse skill sets."

[0572] The sentiment analysis engine detects the user's emotions of joy.

[0573] Re-implement strategies where generative AI models have been successful (e.g., launching a new product).

[0574] Example prompt:

[0575] "Run a simulated small-to-medium-sized company with 50 members and diverse skill sets. Analyze user sentiment and re-implement successful strategies if you detect a positive sentiment."

[0576] In this way, the system performs simulated organizational management based on the conditions input by the user, and takes appropriate action according to the user's emotions.

[0577] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0578] Step 1:

[0579] A user accesses the system

[0580] Specific operation: A user uses a terminal (PC or smartphone) to access the system's web interface. The terminal starts a web browser and connects to the specified URL. The server receives the user's access and displays the login screen.

[0581] Input: User access request

[0582] Output: Login screen displayed

[0583] Step 2:

[0584] User enters company requirements

[0585] Specific operation: The user inputs conditions such as the size of the organization (e.g., small and medium-sized enterprises), the number of members (e.g., 50 people), and the skill set (e.g., diverse) through the terminal. The terminal sends the input data to the server. The server stores the received data in a database and proceeds to the next process.

[0586] Input: Criteria such as organization size, number of members, skill sets, etc.

[0587] Output: Condition data stored in a database

[0588] Step 3:

[0589] The server starts running a simulated organization.

[0590] Specific operation: Based on the saved conditions, the server starts a simulated organizational operation using a generative AI model (e.g. GPT-4). The server sends a prompt to the generative AI model and starts the simulation. The generative AI model generates various scenarios and simulates the strategies and actions of organizational operation. The server displays the generated scenarios to the user.

[0591] Input: Condition data stored in the database, prompt text

[0592] Output: Generated scenario, displayed to the user

[0593] Step 4:

[0594] The server analyzes the user's emotions

[0595] How it works: While the user is using the system, the device collects the user's inputs and reactions. The device sends the collected data to the server. The server uses an emotion analysis engine (e.g. emotion analysis software) to analyze the user's emotions in real time. The server feeds the analysis results back to the generative AI model.

[0596] Input: User input and response data

[0597] Output: Sentiment analysis results, feedback to generative AI model

[0598] Step 5:

[0599] The server responds according to the user's emotions.

[0600] Specific operation: The server receives feedback from the sentiment analysis engine and provides that information to the generative AI model. The generative AI model considers how to respond to the user's emotions, such as re-executing successful strategies or actions. The server displays the new scenario from the generative AI model to the user.

[0601] Input: Sentiment analysis results, feedback to generative AI model

[0602] Output: New scenario, displayed to the user

[0603] (Application example 2)

[0604] Next, a description will be given of Application Example 2 of Form 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."

[0605] Conventional company management systems use AI to perform simulated operations, but because they are unable to respond to user emotions, there is a problem that appropriate feedback cannot be obtained in actual operations. In addition, in the operation of production lines, strategies are not adjusted using emotion data, making efficient production management difficult.

[0606] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0607] In this invention, the server includes a means for assigning job titles and work contents of each department to a plurality of generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be appropriately managed based on a huge data backbone, a means for combining an emotion engine that recognizes the user's emotions and responding according to the user's emotions, a means for operating a simulated production line and proposing an optimal production strategy, a means for analyzing the user's emotion data in real time and feeding back the results to the simulation engine, and a means for strengthening a successful strategy and correcting an unsuccessful strategy based on the emotion data. This makes it possible to obtain appropriate feedback based on the user's emotions, and to enable efficient production management. The server may include a means for strengthening a successful strategy of the organization and correcting an unsuccessful strategy of the organization by feeding back the emotions to the simulation engine.

[0608] "Generative AI" refers to artificial intelligence that generates new information and content based on data.

[0609] A "position" is a position within an organization that has specific duties and responsibilities.

[0610] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[0611] A "data backbone" refers to the large amount of data that forms the foundation that supports the data for the entire system.

[0612] An "emotion engine" is an engine that analyzes the user's emotions and feeds the results back to the system.

[0613] "Simulated production line operation" refers to an operation method in which a simulation is performed by imitating an actual production line.

[0614] A "production strategy" refers to plans and policies for carrying out production activities efficiently.

[0615] "Emotion data" refers to data that indicates the user's emotional state.

[0616] A "simulation engine" is an engine for performing simulated operations or simulations.

[0617] "Feedback" refers to the process of making input or adjustments based on the system's output.

[0618] A system for carrying out the present invention is designed to improve the efficiency of production management in a factory. The system includes a means for assigning job titles and work contents of each department to a plurality of generating AIs and having the AIs converse with each other to operate a company. The system further includes a means for confirming whether the company can be appropriately managed based on a huge data backbone, a means for combining an emotion engine that recognizes the user's emotions and responding according to the user's emotions, a means for operating a simulated production line and proposing an optimal production strategy, a means for analyzing the user's emotion data in real time and feeding back the results to a simulation engine, and a means for strengthening a successful strategy and correcting an unsuccessful strategy based on the emotion data. The server may include a means for strengthening a successful strategy of the organization and correcting an unsuccessful strategy of the organization by feeding back the emotions to the simulation engine.

[0619] The server uses the generation AI to simulate company operations. Specifically, it specifies job titles and the work content of each department, and simulates operations while having the AI ​​converse with each other. This allows the server to recreate an environment close to the actual operation and explore appropriate management strategies.

[0620] The device uses an emotion engine to recognize the user's emotions in real time. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice to generate emotion data. This emotion data is sent to a server and fed back to the simulation engine.

[0621] The server adjusts the production strategy based on the emotion data. Specifically, if the user expresses an emotion of happiness, the server reinforces successful strategies and provides suggestions to further increase efficiency. Conversely, if the user expresses dissatisfaction, the server modifies strategies and provides new suggestions to resolve issues. The server may include means for feeding back the emotion to a simulation engine to reinforce successful strategies of the organization and modify unsuccessful strategies of the organization.

[0622] As a concrete example, consider a scenario in which a factory manager uses the system to improve the efficiency of a production line. If the manager expresses joy, the system will strengthen the strategy and provide suggestions to further improve efficiency. Conversely, if the manager expresses dissatisfaction, the system will modify the strategy and provide new suggestions to solve the problem.

[0623] An example of a prompt sentence might be:

[0624] A factory manager is using an AI system installed on a robot to increase the efficiency of the production line. If the manager expresses happiness, the system strengthens the strategy and makes suggestions to further increase efficiency. Conversely, if the manager expresses dissatisfaction, the system modifies the strategy and makes new suggestions to solve the problem.

[0625] The flow of the identification process in the application example 2 will be described with reference to FIG.

[0626] Step 1:

[0627] The server assigns the job titles and work content of each department to the generation AI and starts a simulated company operation. As input, it receives data such as the size of the company, number of members, and skill sets, and simulates operations by having the AIs converse with each other based on this data. As output, it obtains the simulated operation results and business strategy proposals.

[0628] Step 2:

[0629] The device uses an emotion engine to recognize the user's emotions in real time. As input, it receives the user's facial expressions and tone of voice captured by the camera and microphone, analyzes them, and generates emotion data. As output, it obtains data that indicates the user's emotional state.

[0630] Step 3:

[0631] The server receives the emotion data sent from the terminal and feeds it back to the simulation engine. It receives the user's emotion data as input and adjusts the parameters of the simulation engine based on this. The adjusted simulation results are obtained as output.

[0632] Step 4:

[0633] The server adjusts the production strategy based on the emotion data. As input, it receives the adjusted simulation results and enhances successful strategies and modifies unsuccessful strategies based on the emotion data. As output, it obtains a proposal for an optimized production strategy.

[0634] Step 5:

[0635] The user receives the production strategy proposal provided by the server and applies it to the actual production line. As input, the user receives the optimized production strategy proposal and operates the production line based on this. As output, the actual production efficiency and results are obtained.

[0636] Step 6:

[0637] The server monitors the actual production efficiency and results and feeds them back to the simulation engine. As input, it receives the actual production data and readjusts the parameters of the simulation engine based on this. As output, it provides a proposal for a more optimized production strategy.

[0638] Step 7:

[0639] The device again recognizes the user's emotions and transmits them to the server. As input, it receives the user's new facial expressions and tone of voice captured by the camera and microphone, analyzes them, and generates emotion data. As output, it obtains data showing the updated emotional state of the user.

[0640] Step 8:

[0641] The server then adjusts the production strategy again based on the updated emotion data and makes an optimal proposal.As input, it receives the updated emotion data and the actual production data, and readjusts the strategy based on this.As output, it obtains a proposal for a further optimized production strategy.

[0642] Example 3

[0643] Next, a third embodiment of the third embodiment will be described. 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."

[0644] In conventional organizational management simulation systems, the analysis of simulated management results and feedback based on user emotions were insufficient, making it difficult to identify problems in actual management and propose solutions. In addition, because consulting that takes into account the user's emotions is not performed, it is not possible to respond appropriately to the user's concerns and questions. This has led to issues such as delayed improvements in organizational management.

[0645] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0646] In this invention, the server includes a means for assigning job titles and the work contents of each section to a plurality of generative AIs and having the AIs converse with each other to operate the organization, a means for confirming whether appropriate organizational management can be performed based on a huge data backbone, a means for a user to input a scenario of simulated organizational management, a means for executing simulated organizational management using an AI model, a means for analyzing the results of the simulated organizational management, a means for analyzing the user's emotions, and a means for identifying problems and proposing solutions based on the emotion analysis results. This makes it possible to analyze the results of the simulated organizational management in detail and provide appropriate feedback and solutions based on the user's emotions. The server may include a means for confirming whether organizational management can be performed based on a data backbone, which is a large amount of data that is the basis of the system. The server may include an analysis means for analyzing the results of the simulated organizational management by inputting the scenario of the simulated organizational management input by the user into the generative AI model.

[0647] "Generative AI" is AI that autonomously converses and makes decisions based on a designated job title or job description.

[0648] A "position" refers to a position within an organization that has specific duties and responsibilities.

[0649] "Job Description" refers to the specific tasks and responsibilities associated with a particular position.

[0650] A "data backbone" refers to a foundation for accumulating the vast amounts of data necessary for organizational management and using it for analysis and decision-making.

[0651] A "scenario" refers to a series of plans or strategies that are executed in a simulated organizational operation.

[0652] An "artificial intelligence model" refers to an algorithm or program built using machine learning or deep learning to perform a specific task.

[0653] "Simulated organizational management" refers to virtual management carried out using generative artificial intelligence to simulate actual organizational management.

[0654] "Analyzing the results" refers to a process of evaluating the results of the simulated organizational management in detail and identifying success factors and problems. The server may include an analysis means for analyzing the results of the simulated organizational management by inputting a scenario of the simulated organizational management input by a user into a generative AI model. The server may include an emotion engine for recognizing the emotion of a user, and a means for inputting a specific prompt sentence into a generative AI model, identifying problems in the organization based on the results of the simulated organizational management by the analysis means and the emotion, and proposing solutions to the identified problems by inputting the specific prompt sentence into a generative AI model.

[0655] "Analyzing emotions" refers to the process of identifying emotions from a user's input and behavior and assessing their emotional state.

[0656] "Feedback" refers to information or advice provided based on analysis results and evaluation.

[0657] "Proposing a solution" means showing specific methods or strategies for improving or resolving an identified problem.

[0658] The present invention is a system for performing a simulated organizational operation and providing consulting based on the results. A specific embodiment of the system will be described below. The server may include a means for performing a simulated production line operation and providing consulting for improving production efficiency based on the results of the production line operation.

[0659] System Configuration

[0660] This system consists of three main components: a server, a terminal, and a user. The server uses a generative AI model to run a simulated organizational management scenario and analyze the results. The terminal receives input from the user and performs sentiment analysis. The user inputs a simulated organizational management scenario into the system and checks the results.

[0661] Hardware and Software Used

[0662] Server: Use a server with high-performance computing power to run generative artificial intelligence models, specifically using machine learning frameworks such as TensorFlow and PyTorch.

[0663] Terminal: A computer or smartphone operated by the user is used. Sentiment analysis is performed using emotion analysis engines such as IBM Watson and Microsoft Azure Cognitive Services.

[0664] Data backbone: Use a database (e.g., MySQL, PostgreSQL) to store data necessary for organizational operations.

[0665] Program Processing

[0666] The server receives the simulated organizational management scenario input by the user and executes the simulation using a generative artificial intelligence model. The results of the simulation are analyzed in detail using data analysis tools (e.g., Pandas, NumPy). For example, the effectiveness of an advertising campaign is simulated and the results are evaluated.

[0667] The terminal receives input from the user and analyzes the user's emotions using a sentiment analysis engine. The analysis result is sent to a server, and the server identifies problems based on the information and proposes solutions. For example, if a user inputs "I feel like our strategy for acquiring new customers is not working," the terminal sends this text to the sentiment analysis engine and obtains the analysis result. The server may include an emotion engine that recognizes the user's emotions, and a means for inputting a specific prompt sentence into a generative AI model to identify problems in the organization based on the results of the simulated organization management by the analysis means and the emotions, and for proposing solutions to the identified problems.

[0668] Examples

[0669] Consider a case where a user is anxious about a strategy to acquire new customers. If the user types, "I feel like our strategy to acquire new customers is not working," the device will use a sentiment analysis engine to analyze the user's anxiety. The analysis results are sent to a server, which uses the information to identify the problem and propose a solution, such as, "You need to reevaluate the target demographic of your advertising campaign."

[0670] Examples of prompt statements

[0671] I feel like my strategy for acquiring new customers isn't working. Can you tell me what's wrong?

[0672] In this way, a system is realized in which the server, the terminal, and the user work together to provide consulting based on the results of a simulated organization operation. The flow of the specific process in the third embodiment will be described with reference to Fig. 21. The server may include a means for performing a simulated production line operation and providing consulting for improving production efficiency based on the results of the production line operation.

[0673] Step 1:

[0674] A user logs into the system.

[0675] The user enters a username and password on the login screen of the terminal. The terminal sends the entered information to the server, which then refers to the database to perform authentication. If authentication is successful, the user can access the dashboard.

[0676] Input: Username, Password

[0677] Output: Authentication result (success / failure)

[0678] Step 2:

[0679] The user inputs a scenario of a simulated organization operation.

[0680] The user enters "I want to run an advertising campaign to acquire new customers" into the input form on the dashboard. The terminal sends this information in JSON format to the server.

[0681] Input: A simulated organizational scenario

[0682] Output: Scenario data (JSON format)

[0683] Step 3:

[0684] The server uses the AI ​​model to run a simulated organizational operation.

[0685] The server runs a Python script based on the received scenario and loads the TensorFlow model, which then runs a simulation of the ad campaign and saves the results as a CSV file.

[0686] Input: Scenario data

[0687] Output: Simulation results (CSV file)

[0688] Step 4:

[0689] The server analyzes the results of the simulated organizational management. The server may include an analysis means for analyzing the results of the simulated organizational management by inputting the scenario of the simulated organizational management input by the user into the generative AI model.

[0690] The server reads the generated CSV file with Pandas and analyzes the effectiveness of the ad campaign, for example, calculating click-through rates and conversion rates and graphing the results.

[0691] Input: Simulation results (CSV file)

[0692] Output: Analysis results (graphs, statistical data)

[0693] Step 5:

[0694] The device analyzes the user's emotions.

[0695] The user reviews the results and types, "The results of my ad campaign are not good." The device sends this text to the sentiment analysis engine and gets the analysis results.

[0696] Input: User feedback (text)

[0697] Output: Emotion analysis results

[0698] Step 6:

[0699] The server identifies problems based on the emotion analysis results and proposes solutions. The server may include an emotion engine that recognizes the emotions of a user, and a means for inputting a specific prompt sentence into a generative AI model to identify problems in the organization based on the results of the simulated organization management by the analysis means and the emotions, and for proposing solutions to the identified problems.

[0700] The server receives the emotion analysis results, and the AI ​​determines that the user is feeling anxious. The AI ​​identifies the need to reevaluate the target audience of the advertising campaign and suggests specific improvement measures.

[0701] Input: Sentiment analysis results

[0702] Output: A proposed solution

[0703] Step 7:

[0704] The user reviews the proposed solution.

[0705] The user sees suggested solutions on the device dashboard, such as "reevaluate your target audience and change your ad content," and decides on the next action to take.

[0706] Input: Solution proposal

[0707] Output: User's next action

[0708] (Application example 3)

[0709] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0710] In the conventional organizational management system, there was insufficient consulting based on the results of simulated operations, and measures to improve the efficiency of production lines and manage the emotions of workers were particularly insufficient. In addition, specific measures to reduce the stress and anxiety of workers were not proposed, so improvements to the work environment were often delayed. This led to problems such as a decline in the productivity of the entire organization and a decline in worker satisfaction.

[0711] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0712] In this invention, the server includes a means for assigning job titles and the work content of each department to a plurality of generation AIs and having the AIs converse with each other to operate the organization, a means for confirming whether appropriate organizational management can be performed based on a huge data backbone, a means for performing simulated production line operation and providing consulting for improving production efficiency based on the results, and a means for recognizing the emotions of workers using an emotion engine and proposing measures to reduce stress and anxiety. This makes it possible to improve the production efficiency of the organization and to propose appropriate measures according to the emotions of the workers. The server may include a means for confirming whether organizational management can be performed based on a data backbone, which is a large amount of data that is the basis of the system. The server may include a means for performing simulated production line operation and providing consulting for improving production efficiency based on the results of the production line operation.

[0713] "Generative AI" is an artificial intelligence that performs simulated operations based on specified job titles and job content.

[0714] A "data backbone" is a data set that serves as the foundation for verifying appropriate organizational management based on vast amounts of data.

[0715] "Simulated production line operation" is the process of operating an actual production line in imitation of the actual production line and analyzing the results.

[0716] "Production efficiency" is an indicator that shows the efficiency of production activities within a certain period of time.

[0717] "Consulting" refers to the task of proposing improvement measures based on the results of a mock operation.

[0718] The "emotion engine" is a system that recognizes the emotions of workers and suggests countermeasures based on the results.

[0719] "Workers" refers to people who work in factories or on production lines.

[0720] "Stress" refers to the mental or physical strain or tension felt by workers.

[0721] "Anxiety" refers to the feelings of worry and fear that workers have about the future.

[0722] "Measures" refer to specific means or methods taken to solve a particular problem.

[0723] In order to implement the present invention, the following system configuration and program are required.

[0724] System Configuration

[0725] 1. Hardware:

[0726] Factory Robots

[0727] Heart rate monitor

[0728] camera

[0729] 2. Software:

[0730] Python

[0731] EmotionEngine Library

[0732] AISimulation Library

[0733] Program processing explanation

[0734] The server first assigns job titles and work content for each department to multiple generation AIs, and has the AIs converse with each other while operating the organization. This results in a simulated production line operation. Next, it is confirmed whether appropriate organizational management can be performed based on the huge data backbone. Consulting is provided to improve production efficiency based on the results of the simulated operation. The server may include a means for confirming whether organizational management can be performed based on the data backbone, which is a large amount of data that forms the foundation of the system. The server may include a means for performing a simulated production line operation, and providing consulting to improve production efficiency based on the results of the production line operation.

[0735] Furthermore, the system uses an emotion engine to recognize the emotions of workers and proposes measures to reduce stress and anxiety. Specifically, the system analyzes the worker's heart rate and facial expression data to recognize stress and anxiety. Based on the recognized emotions, the system proposes measures to reduce the worker's stress and anxiety.

[0736] Examples

[0737] For example, when a new product is being produced on a factory production line, if the AI ​​runs a simulation and finds that efficiency is declining, it will suggest reviewing the work process or introducing new machinery. Also, if a worker's heart rate is high and they look anxious, it will suggest increasing break times or improving the work environment.

[0738] Examples of prompt statements

[0739] Run a mock factory production line and analyze its efficiency. Based on the results, suggest improvements. Also, recognize the emotions of workers and suggest measures to reduce stress and anxiety.

[0740] In this way, the server can support efficient production and worker health through simulated production line operations and worker emotion recognition.

[0741] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0742] Step 1:

[0743] The server assigns job titles and the work content of each department to multiple generation AIs.

[0744] Input: Job title information, job description information

[0745] Data processing: Assigning job titles and job descriptions to generative AI

[0746] Output: Job title and job description set in the generated AI

[0747] Specific operation: The server retrieves job title information and job content information from the database and assigns it to the generation AI.

[0748] Step 2:

[0749] The server runs the organization by having the generated AIs talk to each other.

[0750] Input: Generated AI with job title and job description set

[0751] Data processing: Conversation simulation between generative AIs

[0752] Output: Results of a simulated organizational operation

[0753] Specific operation: The server simulates conversations between the generation AIs and generates scenarios for running an organization.

[0754] Step 3:

[0755] The server checks whether appropriate organizational management can be performed based on the huge data backbone. The server may include a means for checking whether appropriate organizational management can be performed based on the data backbone, which is a large amount of data that is the basis of the system.

[0756] Input: Results of simulated organizational operations, data backbone

[0757] Data processing: Analysis of organizational management results

[0758] Output: Evaluation results of organizational management

[0759] Specific operation: The server compares the results of the simulated operation with the data backbone and evaluates the organization's management.

[0760] Step 4:

[0761] The server performs a simulated production line operation and provides consulting for improving production efficiency based on the results of the operation. The server may include a means for performing a simulated production line operation and providing consulting for improving production efficiency based on the results of the production line operation.

[0762] Input: Production line operation scenario

[0763] Data processing: Simulation and analysis of production efficiency

[0764] Output: Proposals for improving production efficiency

[0765] Specific operation: The server performs a mock operation of a production line, simulates efficiency, and suggests improvement measures.

[0766] Step 5:

[0767] The server uses an emotion engine to recognize the emotions of workers and suggest measures to reduce stress and anxiety.

[0768] Input: Worker's heart rate data, facial expression data

[0769] Data processing: Emotion recognition and analysis

[0770] Output: Suggested measures to reduce stress and anxiety

[0771] How it works: The server analyzes data obtained from the heart rate monitor and camera, recognizes the worker's emotions, and suggests appropriate measures.

[0772] Step 6:

[0773] The server reports the overall results to the user and implements any necessary remedial measures.

[0774] Input: Evaluation results of organizational management, proposals for improving productivity, emotion recognition results

[0775] Data processing: synthesis of results and preparation of reports

[0776] Output: Report with remedial measures

[0777] What it does: The server consolidates the results of each step and creates a report for the user, suggesting any necessary remedial measures.

[0778] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0779] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0780] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0781] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0782] [Second embodiment]

[0783] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0784] 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.

[0785] 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 wide area network (WAN) and / or a local area network (LAN).

[0786] 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.

[0787] 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 the voice according to instructions from the processor 46.

[0788] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0789] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0790] Fig. 4 shows an example of 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.

[0791] 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.

[0792] 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.

[0793] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0794] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0795] "Example 1"

[0796] In one embodiment of the present invention, the generation AI is assigned job titles such as president, department manager, section manager, and member, and the work content of each section is set. For example, the AI ​​of the sales department is made to plan a strategy for acquiring new customers, and the AI ​​of the development department is made to plan the development of a new product. These AIs run the company while talking to each other.

[0797] "Example 2"

[0798] In another embodiment of the present invention, the size of the company, the number of members, skills, etc. are specified, and the AIs run a simulated company. For example, conditions are set such as a small- or medium-sized company with 50 members and a diverse skill set, and the AI ​​runs a simulated company.

[0799] "Example 3"

[0800] As a further embodiment of the present invention, consulting on future company management is provided based on the results of the simulated company management. For example, if the result of the company management simulated by the AI ​​shows that the strategy for acquiring new customers is not successful, the cause is analyzed and a remedy is proposed. The server may include a means for analyzing the cause and proposing a remedy when the result of the simulated organization management shows that the strategy for acquiring new customers is not successful.

[0801] The process flow of each embodiment will be described below.

[0802] "Example 1"

[0803] Step 1: Specify job titles such as president, department manager, section manager, and member to the generating AI.

[0804] Step 2: Set the work content for each department. For example, have the AI ​​in the sales department create a strategy to acquire new customers, and the AI ​​in the development department create a development plan for a new product.

[0805] Step 3: These AIs will talk to each other and run the company.

[0806] "Example 2"

[0807] Step 1: Specify the size of your company, number of members, skills, etc.

[0808] Step 2: Have the AIs run a simulated company. For example, set conditions such as a small- or medium-sized company with 50 members and diverse skill sets, and have the AI ​​run a simulated company.

[0809] "Example 3"

[0810] Step 1: Based on the results of the simulated company operations, provide consulting for future company operations.

[0811] Step 2: For example, if the strategy for acquiring new customers is not successful as a result of the company management simulated by the AI, analyze the cause and propose a remedy. The server may include a means for analyzing the cause and proposing a remedy when the strategy for acquiring new customers is not successful as a result of the simulated organization management.

[0812] Example 1

[0813] Next, a description will be given of Example 1 of Form 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".

[0814] In traditional organizational management, the task content for each position and progress management were often done manually, making efficient management difficult. In addition, there was a lack of cooperation between departments, making it difficult to share information and unify strategies. Furthermore, it was difficult to find an appropriate management method based on the size of the organization and the skills of its members, and there was also the problem of being unable to provide sufficient consulting on future management.

[0815] 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.

[0816] In this invention, the server includes a means for assigning job titles and work content to multiple generation AIs and having the AIs talk to each other to operate the organization, a means for checking whether the organization can be operated appropriately based on a huge data backbone, a means for a user to access the system and set job titles and work content, a means for the server to generate AIs corresponding to each job title using a generation AI model, a means for the server to assign work content to each AI, a means for each AI to talk to each other and proceed with the work, a means for the server to monitor the conversation content and progress of each AI and make adjustments as necessary, and a means for a user to access the system and check the progress. This enables efficient organization management, strengthens cooperation between each department, and makes it easier to share information and unify strategies. It also makes it possible to explore appropriate management methods according to the size of the organization and the skills of its members, and provides consulting for future management.

[0817] "Generative AI" is a type of artificial intelligence that uses natural language processing to generate text.

[0818] A "position" indicates a job title or level of responsibility within an organization, and includes, for example, president, department manager, section manager, member, etc.

[0819] "Job content" refers to the specific duties and tasks each position is responsible for, such as developing strategies for acquiring new customers and planning new product development.

[0820] A "server" refers to a computer system that provides services to other computers over a network.

[0821] "User" refers to a person or organization that uses the system.

[0822] "Data backbone" refers to the large amount of data that forms the foundation of the system, on which appropriate decisions and operations are made.

[0823] A "prompt" is text that is used to input specific instructions or questions to the generative AI.

[0824] "Progress" refers to the state or condition that indicates how far a task or project has progressed.

[0825] "Simulated organizational management" refers to virtually trying out management methods by simulating actual organizational management.

[0826] "Consulting" refers to providing advice and support regarding organizational management based on specialized knowledge and experience.

[0827] The present invention relates to a system for improving the efficiency of organizational management by using a generative AI. A specific embodiment of this system will be described below.

[0828] First, the user accesses the system using a terminal. The user specifies the role of the person, such as president, department manager, section manager, or member, and sets the job content for each role. For example, the AI ​​for the sales department can be set to "draft a strategy to acquire new customers," and the AI ​​for the development department can be set to "draft a development plan for a new product."

[0829] Next, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate an AI for each job title. The server inputs the job content set by the user as a prompt to the generated AI.

[0830] The server assigns each generated AI task set by the user. For example, the sales department's AI could be assigned the task of "creating a strategy to acquire new customers," while the development department's AI could be assigned the task of "creating a development plan for a new product."

[0831] Each AI will carry out its assigned tasks by talking to each other. For example, if the sales department's AI suggests that "we should strengthen social media advertising to acquire new customers," the development department's AI will respond by saying, "We will adjust the development schedule for new products to match the advertising strategy."

[0832] The server monitors the conversation content and work progress of each AI in real time. If necessary, the server adjusts the AI's tasks to support the smooth running of work. For example, if the strategy proposed by the sales department's AI is not feasible, the server will instruct it to revise the proposal.

[0833] The user can access the system again using a terminal to check the progress of each AI task. The user can issue new instructions to the AI ​​if necessary.

[0834] As a concrete example, if a user inputs "Sales AI, please plan a new customer acquisition strategy for the next quarter," the server will send this prompt to the Sales AI. The Sales AI will respond with, "We will propose a strategy to strengthen SNS advertising in the next quarter and expand the target demographic." If the user then inputs, "Development AI, please plan a new product development plan and adjust it to match the Sales strategy," the server will send this prompt to the Development AI. The Development AI will respond with, "We will bring forward the development schedule for the new product and conduct promotions in line with SNS advertising."

[0835] In this way, the server uses the generative AI model to assign tasks to the AIs in each role and run the organization by having them work together. This system enables efficient organizational management, strengthens collaboration between departments, and makes it easier to share information and unify strategies. It also makes it possible to explore appropriate management methods according to the size of the organization and the skills of its members, and provides consulting on future management.

[0836] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0837] Step 1:

[0838] A user accesses the system and sets their job title and job description.

[0839] Input: The user uses a terminal to input job titles such as president, department manager, section manager, and member, as well as the job description of each position.

[0840] Data processing: The server saves the job title and job description entered by the user in a database.

[0841] Output: Data with job title and job description is generated.

[0842] Specific operations: Through the terminal interface, the user inputs to the sales department's AI, "Draw up a strategy for acquiring new customers," and to the development department's AI, "Draw up a development plan for a new product."

[0843] Step 2:

[0844] The server uses the generative AI model to generate AI corresponding to each position.

[0845] Input: The server retrieves the job title and job description data stored in step 1.

[0846] Data processing: The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate AI corresponding to each role.

[0847] Output: A generation AI corresponding to each role is generated.

[0848] Specific operation: The server generates a GPT-4 as the AI ​​for the sales department and another GPT-4 instance as the AI ​​for the development department.

[0849] Step 3:

[0850] The server assigns tasks to each AI.

[0851] Input: The server obtains the data of each AI generated in step 2 and the task content set in step 1.

[0852] Data processing: The server inputs the corresponding task details as prompts for each AI.

[0853] Output: An AI with assigned task content is generated.

[0854] Specific operation: The server inputs a prompt to the sales department's AI, "Draw up a strategy for acquiring new customers," and a prompt to the development department's AI, "Draw up a development plan for a new product."

[0855] Step 4:

[0856] Each AI will converse with each other and carry out its work.

[0857] Input: Prompts for the tasks assigned to each AI.

[0858] Data processing: Each AI carries out its assigned tasks by conversing with each other.

[0859] Output: The business plans and strategies generated by each AI.

[0860] Specific operation: The sales department's AI suggests, "We should strengthen our social media advertising to acquire new customers," and the development department's AI responds, "We will adjust the development schedule for new products to match our advertising strategy."

[0861] Step 5:

[0862] The server monitors the conversations and progress of each AI and makes adjustments as necessary.

[0863] Input: Conversation content and work progress data of each AI.

[0864] Data processing: The server monitors the conversation content and progress of each AI in real time and adjusts tasks as necessary.

[0865] Output: Aligned business plans and strategies.

[0866] Specific operation: If the strategy proposed by the sales department's AI is not feasible, the server instructs the sales department to revise the proposal.

[0867] Step 6:

[0868] The user accesses the system and checks the progress.

[0869] Input: The user uses a terminal to access the system and check the progress of each AI.

[0870] Data processing: The server formats the data to display each AI's progress to the user.

[0871] Output: A user-visible display of progress.

[0872] Specific operations: Through the terminal, the user can check the progress of the strategies proposed by the sales department's AI and the development plans drawn up by the development department's AI, and issue new instructions as necessary.

[0873] (Application example 1)

[0874] Next, a description will be given of Application Example 1 of Form 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".

[0875] In traditional company and factory operations, human managers were required to oversee the work of each department and machine to ensure optimal operation. However, this required a great deal of effort and time, making efficient operation difficult. In addition, because each department and machine operated independently, there was a lack of overall coordination, and optimal operation was often not possible. Furthermore, there was a lack of systems for performing simulated operations, making it difficult to grasp problems in actual operations in advance. In order to solve these issues, an efficient operation system that utilizes AI is needed.

[0876] 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.

[0877] In this invention, the server includes a means for assigning job titles and work content for each section to multiple generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be properly managed based on a huge data backbone, and a means for assigning job titles to each machine in the factory, each machine taking charge of a specific task, and optimizing the operation of the entire factory while conversing with each other. This enables efficient company and factory operations using AI.

[0878] "Generative AI" is artificial intelligence that generates new information or content based on given data or prompts.

[0879] A "position" is a rank or position within an organization that has specific duties and responsibilities.

[0880] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[0881] A "conversation" is the process by which multiple AIs exchange information with each other and communicate with each other.

[0882] "Means of running the company" refers to methods and systems that use AI to manage the operations of the entire organization and operate it efficiently.

[0883] A "data backbone" is a data infrastructure that enables AI to make appropriate judgments and predictions based on massive amounts of data.

[0884] "Each machine in the factory" refers to the various devices and equipment in the factory used for manufacturing and production.

[0885] "Taking charge of specific tasks" means that each machine or AI carries out specific tasks or work according to its role.

[0886] "Means to optimize operations throughout the factory" refers to methods or systems in which each machine and AI within the factory works together to efficiently produce and manage, thereby improving overall performance.

[0887] The following system is constructed as an embodiment of the present invention. The server includes a means for assigning job titles and work content for each department to multiple generation AIs and running the company while having the AIs converse with each other, a means for confirming whether the company can be properly run based on a huge data backbone, and a means for assigning job titles to each machine in the factory, each machine taking charge of a specific task, and optimizing the operation of the entire factory while conversing with each other.

[0888] System Programming

[0889] The server uses Python and the OpenAI API to execute a program that assigns the job title and job content to each generated AI. Specifically, it performs the following process.

[0890] 1. The server generates a prompt for each generated AI, specifying the job title and job description.

[0891] 2. The server uses the OpenAI API to send a prompt to the generating AI and get a response.

[0892] 3. Based on the responses received, the server allows each generation AI to converse with each other and proceed with the work.

[0893] Hardware and Software Used

[0894] Hardware: Each machine in the factory (production line robots, quality control robots, logistics robots, maintenance robots, etc.)

[0895] Software: Python, OpenAI API

[0896] Data processing and calculation

[0897] The server generates and sends a prompt sentence like the following to each generated AI.

[0898] Examples of prompt statements

[0899] "Please act as a manufacturing line robot and create production plans."

[0900] "As a quality control robot, please create a quality check strategy."

[0901] "As a logistics robot, please manage inventory and plan delivery."

[0902] "As a maintenance robot, please create a maintenance plan for the equipment."

[0903] The server receives the generative AI's responses to these prompts, and each machine is responsible for a specific task, and as they converse with each other, they generate data to optimize the operation of the entire factory.

[0904] Examples

[0905] For example, if a manufacturing line robot is sent a prompt saying, "As a manufacturing line robot, please create a production plan," the generation AI will propose a specific production plan. A quality control robot can be sent a prompt saying, "As a quality control robot, please create a quality check strategy," which will have it propose a specific strategy for quality checks. This makes it possible for each machine in the factory to work together to efficiently carry out operations and optimize the operation of the entire factory.

[0906] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0907] Step 1:

[0908] The server generates a prompt statement specifying the job title and job description for each generated AI.

[0909] Input: List of job titles and job duties

[0910] Output: Prompt for each generated AI

[0911] Specific operation: The server creates an appropriate prompt for each AI based on the list of job titles and job content. For example, it generates a prompt such as, "As a manufacturing line robot, please create a production plan."

[0912] Step 2:

[0913] The server sends the generated prompt text to each generating AI using the OpenAI API.

[0914] Input: Generated prompt text

[0915] Output: Response from the generation AI

[0916] Specific operation: The server sends the generated prompt text to the OpenAI API and waits for a response from each generated AI. For example, it obtains a response to the prompt text, "As a manufacturing line robot, please create a production plan."

[0917] Step 3:

[0918] The server analyzes the responses it receives and confirms the tasks for which each generation AI is responsible.

[0919] Input: Response from the generation AI

[0920] Output: Analyzed business content

[0921] Specific operation: The server analyzes the response from the generation AI and checks the work content proposed by each generation AI. For example, it analyzes the specific production plan proposed by a manufacturing line robot.

[0922] Step 4:

[0923] The server creates an operation plan for the entire factory based on the suggestions of each generation AI.

[0924] Input: Parsed business content

[0925] Output: Factory-wide operation plan

[0926] Specific operation: The server integrates the work content proposed by each generation AI and creates an operation plan for the entire factory. For example, it integrates the production plan for the manufacturing line robot and the quality check strategy for the quality control robot.

[0927] Step 5:

[0928] The server distributes the created operation plan to each machine in the factory and has them execute it.

[0929] Input: Overall plant operation plan

[0930] Output: Instructions for each machine to execute

[0931] Specific operations: The server distributes the created operation plan to each machine in the factory and instructs each machine to carry out its work based on the plan. For example, it instructs a manufacturing line robot to carry out a specific production task.

[0932] Step 6:

[0933] The server monitors the performance of each machine and makes adjustments as necessary.

[0934] Input: Running status data for each machine

[0935] Output: Adjustment instructions

[0936] Specific operation: The server monitors the execution status of each machine in real time and issues adjustment instructions as necessary. For example, if there is a delay in the production plan, it instructs the manufacturing line robot to adjust the schedule.

[0937] Example 2

[0938] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0939] In conventional company management simulation systems, it was difficult to perform realistic simulations based on conditions specified by the user. In addition, there was a lack of means to provide users with the results of simulated company management simulations using generative AI models, so the information that users could obtain was limited. Furthermore, there was a lack of concrete means to provide consulting for future company management.

[0940] 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.

[0941] In this invention, the server includes a means for allowing a user to input conditions such as the size of the company, the number of members, and a skill set, a means for generating simulated company data based on the conditions, a means for executing a simulation based on the generated company data, and a means for providing the user with the simulation results. This makes it possible to perform a realistic simulation based on the conditions specified by the user, and to provide the user with the results of a simulated company management simulation using a generated AI model. In addition, a specific means for providing consulting on future company management is also provided.

[0942] A "user" is a person or organization that uses the system to input conditions for simulating company operations.

[0943] A "server" is a computer system that receives input from users, generates data, runs simulations, and provides results.

[0944] "Conditions" are information entered by the user, such as company size, number of members, skill set, etc.

[0945] "Simulated company data" refers to data such as the skill sets, job titles, and job descriptions of company members that is generated based on conditions entered by the user.

[0946] "Simulation" is the process of virtually recreating the operating conditions of a company using a generative AI model based on generated simulated company data.

[0947] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to generate simulated company data based on user input and run simulations.

[0948] "Simulation results" refers to information obtained by running a simulation, such as the company's performance, the performance of each member, problems, and areas for improvement.

[0949] "Consulting" is the process of providing advice and suggestions regarding the future management of a company based on the results of a simulation.

[0950] The present invention is a system for simulating a mock company operation based on conditions specified by a user and providing the results. A specific embodiment of this system will be described below.

[0951] Hardware and Software Used

[0952] Hardware: High-performance servers (e.g. virtual servers in cloud services)

[0953] Software: generative AI models (e.g., AI models for natural language processing), database management systems (e.g., MySQL), web servers (e.g., Nginx)

[0954] System Overview

[0955] The system generates mock company data based on conditions entered by the user through a terminal, such as company size, number of members, and skill sets. Based on the generated data, it runs a simulation using a generative AI model and provides the results to the user.

[0956] Program Processing

[0957] The server receives input from the user and starts a simulation to run a mock company based on the specified conditions. Specifically, the process proceeds as follows:

[0958] 1. Receive user input:

[0959] A user accesses a web interface using a terminal and inputs conditions such as company size, number of members, skill set, etc. For example, the user inputs conditions such as "small and medium-sized business, 50 members, diverse skill sets."

[0960] 2. Conditional Data Generation:

[0961] The server generates data for a mock company based on the conditions entered by the user, including each member's skill set, job title, and job description, and uses a generative AI model to create and input prompts.

[0962] Example prompt:

[0963] "Please simulate the operation of a small or medium-sized company with 50 members and diverse skill sets. Please consider each member's job title, skills, and duties and simulate the overall operation of the company."

[0964] 3. Run the simulation:

[0965] The server starts a simulation based on the generated company data. The generative AI model simulates the behavior and work progress of each member and evaluates the overall operating status of the company.

[0966] 4. Result output:

[0967] The server provides the user with the results of the simulation, including the company's performance, the performance of each member, problems, and areas for improvement.

[0968] Examples

[0969] For example, if a user enters conditions such as "small to medium-sized business, 50 members, diverse skill sets," the server generates simulated company data based on these conditions. The generative AI model runs a simulation using prompt statements to evaluate the behavior of each member and the progress of work. The simulation results are provided to the user, displaying the company's performance, the performance of each member, problems, and areas for improvement.

[0970] This system allows users to perform realistic simulations based on specified conditions and obtain simulated company operations using generative AI models. It also provides specific means for consulting on future company operations.

[0971] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0972] Step 1:

[0973] Receiving user input

[0974] A user uses a terminal to access a web interface and inputs conditions such as company size, number of members, and skill sets. For example, the user may input conditions such as "small to medium-sized business, 50 members, diverse skill sets." The terminal sends the information entered by the user to the server. The server stores the received information in a database.

[0975] Input: Company size, number of members, skill set, and other criteria

[0976] Output: User input information stored in a database

[0977] Step 2:

[0978] Conditional Data Generation

[0979] The server retrieves the conditions entered by the user from the database. The server uses the generative AI model to generate data for a simulated company. This data includes each member's skill set, job title, and job description. The server creates and inputs a prompt sentence to the generative AI model.

[0980] Example prompt:

[0981] "Please simulate the operation of a small to medium-sized company with 50 members and diverse skill sets. Please consider each member's job title, skills, and duties and simulate the overall operation of the company."

[0982] Input: User criteria retrieved from the database

[0983] Output: Generated mock company data

[0984] Step 3:

[0985] Running the Simulation

[0986] The server starts a simulation based on the generated company data. The generative AI model simulates the actions and work progress of each member and evaluates the overall operational status of the company. The server creates and inputs a prompt for the simulation to the generative AI model.

[0987] Example prompt:

[0988] "Simulate the actions and work progress of each member based on the generated company data."

[0989] Input: Generated mock company data

[0990] Output: Simulation results

[0991] Step 4:

[0992] Output of results

[0993] The server formats the simulation results to provide them to the user. The terminal displays the simulation results to the user, such as the company's performance, the performance of each member, problems and areas for improvement, etc. The server stores the simulation results in a database.

[0994] Input: Simulation results

[0995] Output: Formatted simulation results provided to the user.

[0996] In this way, users can perform realistic simulations based on specified conditions and obtain simulated results of company operations using generative AI models.

[0997] (Application example 2)

[0998] Next, a description will be given of Application Example 2 of Form 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".

[0999] Conventional company management simulation systems allow users to specify the size of a company, the number of members, and the skill set to perform simulated operations, but lack simulations specialized for factory operations. In addition, they lack the functionality to automatically simulate a factory's production efficiency, cost management, and quality management and propose optimal operation methods, making it difficult to optimize actual factory operations. This creates the issue that no specific proposals can be made to improve the efficiency of factory operations, making it difficult to optimize operations.

[1000] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1001] In this invention, the server includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be appropriately managed based on a huge data backbone, a means for specifying the size of the factory, the number of employees, and the skill set, and for the AI ​​to simulate the operation of the factory, and a means for the AI ​​to automatically simulate the production efficiency, cost management, and quality management of the factory and propose the optimal operation method. This makes it possible to optimize the production efficiency, cost management, and quality management in the operation of the factory.

[1002] "Generative AI" refers to artificial intelligence that generates new information and content based on data.

[1003] A "position" indicates a rank of job or responsibility within an organization.

[1004] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[1005] A "data backbone" refers to the large amount of data that forms the foundation of systems and networks.

[1006] "Corporate management" refers to all activities involved in running and managing a business.

[1007] "Factory size" refers to the physical size and production capacity of the factory.

[1008] "Number of employees" refers to the total number of people working in an organization or factory.

[1009] A "skill set" is a collection of skills and abilities possessed by an individual or group.

[1010] "Running a simulated factory" means simulating actual factory operations.

[1011] "Production efficiency" indicates the ratio of production volume obtained to the resources input.

[1012] "Cost management" is the activity of planning, monitoring and controlling expenses in a business or factory.

[1013] "Quality control" refers to activities for maintaining and improving the quality of products and services.

[1014] "Proposing the optimal management method" means presenting specific methods and strategies for maximizing management efficiency.

[1015] The system for implementing this invention has the function of assigning job titles and work content for each department to multiple generation AIs, and having the AIs converse with each other to operate the company. It also has a function to check whether the company can be properly managed based on a huge data backbone. Furthermore, it has a function to specify the size of the factory, the number of employees, and the skill set, and have the AI ​​simulate the operation of the factory, and includes a function to automatically simulate the production efficiency, cost management, and quality management of the factory and propose the optimal operation method.

[1016] Hardware and Software Used

[1017] Hardware: Factory robots (e.g. ABB's IRB series), servers (e.g. AWS EC2 instances)

[1018] Software: Python 3.x, machine learning libraries (e.g. TensorFlow, PyTorch), databases (e.g. MySQL)

[1019] Data processing and calculation

[1020] The server first randomly generates employee skill sets. To do this, it uses Python random functions to randomly assign skills such as "assembly," "quality control," "maintenance," and "logistics" to each employee. Next, it simulates the operating efficiency of the factory based on the generated skill sets. Specifically, it aggregates the skill sets of each employee and calculates the production efficiency of the entire factory.

[1021] Examples

[1022] For example, when simulating a factory with 100 employees and four skill sets - assembly, quality control, maintenance, and logistics - the server will perform the following process.

[1023] 1. Data generation: Randomly generate employee skill sets using the generate_employees function.

[1024] 2. Simulation: The simulate_operation method calculates the operational efficiency of the factory. Based on the skill sets of the employees, the efficiency of the entire factory is evaluated.

[1025] 3. Result output: Output the simulation results to help optimize factory operations.

[1026] Examples of prompt statements

[1027] An example of a prompt to be input to the generative AI model is as follows:

[1028] "Simulate the operational efficiency of a factory with 100 employees and the skill sets of 'Assembly', 'Quality Control', 'Maintenance' and 'Logistics'."

[1029] In this way, the factory operation simulator can evaluate the factory's operating efficiency and propose optimal operating methods.

[1030] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1031] Step 1:

[1032] The server randomly generates employee skill sets. Specifically, it uses Python random functions to randomly assign skills such as "assembly," "quality control," "maintenance," and "logistics" to each employee. The input requires the number of employees and a list of skill sets, and the output is the generated skill set for each employee.

[1033] Step 2:

[1034] The server simulates the factory's operational efficiency based on the generated skill sets. Specifically, it aggregates the skill sets of each employee and calculates the production efficiency of the entire factory. The input is the skill set of each employee, and the output is the operational efficiency of the entire factory.

[1035] Step 3:

[1036] The server generates optimization proposals for factory operations based on the simulation results. Specifically, it uses a generative AI model to present specific methods and strategies for maximizing operational efficiency. Simulation results are required as input, and optimization proposals are obtained as output.

[1037] Step 4:

[1038] The server presents the optimization proposal to the user by sending the generated proposal to the user's terminal for the user to review. As input, an optimization proposal is required, and as output, a proposal is obtained that is displayed on the user's terminal.

[1039] Step 5:

[1040] The user implements improvements to factory operations based on the presented optimization proposals. Specifically, the user applies the proposed methods and strategies to actual factory operations and confirms their effectiveness. The input is the optimization proposals, and the output is the improved factory operations.

[1041] Example 3

[1042] Next, a third embodiment of the third embodiment will be described. 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".

[1043] Conventional organizational management simulation systems did not sufficiently simulate operations using generative artificial intelligence, making it difficult to evaluate the effectiveness of strategies in actual operations in advance. In addition, they lacked the functionality to effectively utilize past operational data and market data and propose specific improvement measures based on simulation results. As a result, organizational management efficiency and strategy optimization were not fully achieved.

[1044] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1045] In this invention, the server includes a means for assigning a job title and a task content of each department to a plurality of generative AIs and having the AIs converse with each other to operate the organization, a means for confirming whether the organization can be appropriately managed based on a huge data backbone, a means for collecting past operational data and market data, a means for simulating an organizational operation using a generative AI model based on the collected data, a means for analyzing the simulation results and identifying successful and unsuccessful strategies, and a means for proposing improvement measures based on the analysis results. This makes it possible to improve the efficiency of organizational operation and optimize strategies. The server may include a means for assigning a job title and a task content of each department to each of the plurality of generative AIs and having the plurality of generative AIs converse with each other to operate the organization.

[1046] "Generative artificial intelligence" is artificial intelligence that uses natural language processing and machine learning to generate data and perform specific tasks.

[1047] A "position" refers to a position within an organization that has specific duties and responsibilities.

[1048] "Job Description" refers to the specific work or tasks associated with a particular position or job function.

[1049] "Data backbone" refers to the vast data foundation that the system uses, including the infrastructure that supports data collection, storage, and analysis.

[1050] "Organizational management" refers to the processes of planning, executing, controlling, and evaluating necessary to achieve an organization's goals.

[1051] "Simulation" refers to a method for simulating real-world operating conditions and predicting the results.

[1052] "Strategy" refers to the plans and policies for achieving an organization's goals.

[1053] "Improvement measures" refer to specific methods or means for solving current problems and achieving better results.

[1054] "Data collection" refers to the process of gathering the necessary information or data.

[1055] "Analysis" refers to the process of evaluating collected data and extracting meaningful information.

[1056] This invention is a system that uses generative artificial intelligence to simulate organizational management and aims to improve the efficiency of organizational management and optimize strategies based on the results. A specific embodiment of this system is described below.

[1057] System program generation

[1058] The server generates a program for the system to provide consulting services based on the results of the simulated organizational management. This program uses a generative AI model (e.g., OpenAI's GPT-4) to simulate organizational management and analyze the results.

[1059] Program processing explanation

[1060] The server uses the generative AI model to simulate organizational operations. In this simulation, the following data processing and calculations are performed:

[1061] 1. Data collection: The server collects past organizational operation data and market data, including sales data, customer data, marketing data, etc. Specifically, the server obtains these data from a database (e.g., MySQL or PostgreSQL). It also collects marketing data through APIs and collects competitor data using web scraping technology.

[1062] 2. Simulation execution: Based on the collected data, the generative AI model performs simulated organizational operations. For example, it executes a marketing strategy to acquire new customers and simulates the results. The server preprocesses the collected data and converts it into a format to be input to the generative AI model. Next, a prompt sentence is input to the generative AI model and the simulation is executed. An example of a prompt sentence is "Simulate a marketing strategy to acquire new customers and predict the results." The simulation results obtained from the generative AI model are stored on the server.

[1063] 3. Result analysis: The server analyzes the results of the simulation. Specifically, it identifies successful and unsuccessful strategies and analyzes the causes. The server uses a generative AI model to perform a causal analysis of the simulation results. An example of a prompt is "Analyze the causes of the simulation results and identify successful and unsuccessful strategies." The results of the causal analysis are generated in the form of a report.

[1064] 4. Proposal of improvement measures: The server proposes improvement measures based on the analysis results. For example, if the strategy for acquiring new customers is not effective, the server identifies the cause and proposes improvement measures. The server generates improvement measures using a generative AI model based on the results of the causal analysis. An example of a prompt sentence is "Please propose improvement measures based on the cause why the strategy for acquiring new customers was not effective." The generated improvement measures are notified to the user, and a specific action plan for implementing the improvement measures is generated. The server may include a means for analyzing the cause and proposing improvement measures when the strategy for acquiring new customers is not effective as a result of the simulated organizational operation.

[1065] Examples

[1066] The user requests the server to simulate a marketing strategy for acquiring new customers. The server collects past marketing data and runs a simulation using a generative AI model. The simulation results show that the strategy for acquiring new customers did not produce the expected results. The server analyzes the cause and identifies reasons such as "the target market was selected inappropriately." The server then proposes improvement measures such as "reevaluating the target market and focusing on a more appropriate market."

[1067] In this way, the server provides a system for consulting on future organization management based on the results of the simulated organization management. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1068] Step 1: Data collection

[1069] The server collects historical organizational operational data and market data. The inputs include sales data, customer data, marketing data, etc. The server retrieves these data from a database (e.g. MySQL or PostgreSQL). It also collects marketing data through APIs and competitor data using web scraping techniques. The output is the collected data.

[1070] Specific behavior:

[1071] The server retrieves historical sales data from a database using a SQL query.

[1072] The server collects marketing data through an API.

[1073] The server collects competitor data using web scraping technology.

[1074] Step 2: Data Preprocessing

[1075] The server preprocesses the collected data and converts it into a format that can be input to the generative AI model. The input includes the collected raw data. The server processes the data by cleaning, normalizing, extracting features, etc. The output is the preprocessed data.

[1076] Specific behavior:

[1077] The server imputes missing values ​​and removes outliers.

[1078] The server normalizes and scales the data.

[1079] The server extracts features and converts them into a format suitable for the generative AI model.

[1080] Step 3: Run the simulation

[1081] The server uses a generative AI model based on the preprocessed data to simulate a simulated organizational operation. The input includes the preprocessed data and a prompt sentence. The server inputs the prompt sentence to the generative AI model and executes the simulation. The output is the simulation result.

[1082] Specific behavior:

[1083] The server inputs a prompt sentence to the generative AI model.

[1084] Example prompt: "Simulate marketing strategies for acquiring new customers and predict the outcomes."

[1085] The server stores the simulation results obtained from the generative AI model.

[1086] Step 4: Analyze the results

[1087] The server analyzes the results of the simulation. As input, it contains the simulation results. Using a generative AI model, the server identifies successful and unsuccessful strategies and analyzes their causes. As output, it obtains the analysis results.

[1088] Specific behavior:

[1089] The server uses the generative AI model to perform factor analysis of the simulation results.

[1090] Example prompt: "Analyze the factors that contributed to the simulation results and identify successful and unsuccessful strategies."

[1091] The server generates the result of the factor analysis in the form of a report.

[1092] Step 5: Propose improvements

[1093] The server proposes improvement measures based on the analysis results. The input includes the results of the causal analysis. The server generates improvement measures using a generative AI model. The output is the improvement measures.

[1094] Specific behavior:

[1095] Based on the results of the factor analysis, the server uses a generative AI model to generate improvement measures.

[1096] Example prompt: "Based on why our customer acquisition strategy was unsuccessful, please suggest a solution."

[1097] The server notifies the user of the generated remedial action.

[1098] The server generates a specific action plan for implementing the remedial measures.

[1099] (Application example 3)

[1100] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1101] Conventional company management simulation systems lacked specific improvement measures based on the simulated management results, making it difficult to fully utilize them for strategy planning and decision-making in real company management. In addition, there was a lack of means to analyze the simulated management results and propose specific improvement measures, making it difficult for operators to create effective strategies.

[1102] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means. In this invention, the server includes a means for assigning job titles and work contents of each department to multiple generation AIs and running the company while having the AIs talk to each other, a means for confirming whether the company can be managed appropriately based on a huge data backbone, a means for providing consulting on future company management based on the results of the simulated company management, and a means for generating data of the simulated company management, analyzing the data, and proposing improvement measures. This makes it possible to propose specific improvement measures based on the results of the simulated management, which can be useful for strategy planning and decision-making in actual company management.

[1103] "Generative AI" refers to artificial intelligence that generates new information and results based on data.

[1104] A "position" is a position within an organization that has specific duties and responsibilities.

[1105] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[1106] "Having a conversation" refers to the process in which multiple AIs exchange information with each other.

[1107] "Running a company" means having an AI simulate the management activities of a company.

[1108] A "data backbone" refers to the vast data foundation used by the system.

[1109] "Good business management" refers to the methods and strategies for running a company efficiently and effectively.

[1110] "Simulated company operations" refers to the process of simulating actual company operations.

[1111] "Consulting" refers to the activity of providing advice and suggestions based on specialized knowledge and analysis.

[1112] "Generating data" refers to the process by which a system creates new data.

[1113] "Analyzing data" is the process of evaluating collected data and extracting meaningful information.

[1114] "Proposing improvements" means showing specific methods or strategies for solving current problems.

[1115] A system for implementing this invention includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to run a company, a means for confirming whether the company can be managed appropriately based on a huge data backbone, a means for providing consulting on future company management based on the results of the simulated company management, and a means for generating data on the simulated company management, analyzing the data, and proposing improvement measures.

[1116] Hardware and Software Used

[1117] Hardware: Servers, smartphones

[1118] Software: Python, NumPy, scikit-learn

[1119] Data processing and calculation

[1120] The server first generates data for a simulated company's operations, such as marketing budgets, website traffic, conversion rates, and sales, randomly generated data, and then uses a linear regression model to analyze the data and evaluate the impact of each factor on sales.

[1121] The server then uses the analysis to recommend specific improvements to boost sales, such as increasing the marketing budget or strengthening SEO measures to increase website traffic.

[1122] Examples

[1123] For example, if you set a marketing budget of 5,000 yen, your website traffic will be 2,000 people, and your conversion rate will be 0.05 (5%), your sales will be 100. Based on this data, the server can suggest that "increasing your marketing budget may improve your sales."

[1124] Examples of prompt statements

[1125] "If the marketing budget is set at 5,000 yen, the website traffic is 2,000 people, and the conversion rate is 0.05, then the sales will be 100. Please suggest improvement measures to increase sales based on this data."

[1126] In this way, the server can propose specific improvement measures based on the results of the simulated company operations, which the user can use to help with strategy planning and decision-making in the actual operation of the company.

[1127] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1128] Step 1:

[1129] The server generates data for a simulated company operation, i.e., randomly generating data such as marketing budget, website traffic, conversion rate, sales, etc. As input, it takes parameters such as marketing budget range and conversion rate range, and as output, it gets the generated dataset.

[1130] Step 2:

[1131] The server uses a linear regression model to analyze the generated data. As input, it receives the dataset generated in step 1, and as output, it obtains a model that evaluates the impact of each factor on sales. Specifically, it trains the model with marketing budget, website traffic, and conversion rate as features and sales as the target variable.

[1132] Step 3:

[1133] Based on the analysis results, the server proposes specific improvement measures to increase sales. As input, it receives the model obtained in step 2 and the dataset generated in step 1, and as output, it obtains a list of improvement measures. Specifically, it uses the model to predict sales for each data point, compares them with the actual sales, and if the predicted sales exceed the actual sales, it proposes improvement measures such as increasing the marketing budget or strengthening SEO measures.

[1134] Step 4:

[1135] The user receives the improvement measures proposed by the server and uses them to formulate strategies and make decisions in the actual operation of the company. As input, the user receives a list of improvement measures from the server, and as output, formulates a specific operation strategy. Specifically, based on the proposed improvement measures, the user adjusts the marketing budget and implements SEO measures.

[1136] In addition, 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.

[1137] "Example 1"

[1138] As an embodiment of the invention described in claim 4, a system in which a job title and the work content of each department are assigned to a generating AI and the AIs converse with each other to run a company is combined with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions from the user's tone of voice, facial expressions, and choice of words, and feeds the results back to the AI. For example, if the user expresses anger, the AI ​​receives that information and considers a countermeasure. This allows the AI ​​to respond appropriately according to the user's emotions.

[1139] "Example 2"

[1140] As an embodiment of the invention described in claim 5, there is a form in which an emotion engine that recognizes the emotions of a user is combined with a system in which AIs run a simulated company after specifying the size of the company, the number of members, skills, etc. This emotion engine analyzes the user's emotions and feeds the results back to the AI. For example, if the user expresses an emotion of joy, the AI ​​receives that information and considers a response such as re-implementing a successful strategy or action. This allows the AI ​​to respond appropriately according to the user's emotions.

[1141] "Example 3"

[1142] As an embodiment of the invention described in claim 6, there is a form in which an emotion engine that recognizes the user's emotions is combined with a system that enables consulting on future company management. This emotion engine analyzes the user's emotions and feeds back the results to the AI. For example, if the user expresses anxiety, the AI ​​receives that information, identifies the problem, and considers a response such as proposing a solution. This allows the AI ​​to take an appropriate response according to the user's emotions.

[1143] The process flow of each embodiment will be described below.

[1144] "Example 1"

[1145] Step 1: Specify the job titles and work content of each department to the generation AI.

[1146] Step 2: Have the AIs talk to each other and run the company.

[1147] Step 3: Combine an emotion engine to recognize user emotions.

[1148] Step 4: The emotion engine analyzes the user's emotions from their tone of voice, facial expressions, and choice of words.

[1149] Step 5: Feed back the analysis results to the AI.

[1150] Step 6: The AI ​​receives the feedback and considers a response.

[1151] "Example 2"

[1152] Step 1: Specify the size of your company, number of members, skills, etc.

[1153] Step 2: Have the AIs run a simulated company.

[1154] Step 3: Combine an emotion engine to recognize user emotions.

[1155] Step 4: The emotion engine analyzes the user's emotions.

[1156] Step 5: Feed back the analysis results to the AI.

[1157] Step 6: The AI ​​receives the feedback and considers a response.

[1158] "Example 3"

[1159] Step 1: Set up a system that will enable consulting on future company operations.

[1160] Step 2: Assemble an emotion engine to recognize the user's emotions.

[1161] Step 3: The emotion engine analyzes the user's emotion.

[1162] Step 4: Feed back the analysis results to the AI.

[1163] Step 5: The AI ​​receives the feedback and considers a response.

[1164] Example 1

[1165] Next, a description will be given of Example 1 of Form 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".

[1166] Conventional organizational management systems did not adequately use AI to set job content for each position or to manage the system through conversation between AIs. In addition, they lacked the functionality to analyze user emotions and respond accordingly, making it difficult to increase user satisfaction. Furthermore, there was a lack of means to conduct simulated organizational management or future consulting. To solve these issues, a system that combines more advanced AI technology and emotion analysis technology is needed.

[1167] 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.

[1168] In this invention, the server includes a means for assigning a job title and a task content of each section to a plurality of generating AIs and having the AIs converse with each other to operate the organization, a means for confirming whether the organization can be appropriately operated based on a huge data backbone, a means for receiving a user's input and sending a prompt to the generating AI model, a means for the generating AI model to generate an AI for each job title, a means for analyzing the user's emotions using an emotion engine and feeding back the results to the AI, and a means for making the AI ​​respond according to the user's emotions. This enables advanced organizational management using AI, and realizes flexible responses according to the user's emotions. The server may include a means for assigning a job title and a task content of each section to each of a plurality of generating AIs and having the plurality of generating AIs converse with each other to operate the organization.

[1169] "Generative AI" is an artificial intelligence technology that generates AI with specific job titles and job duties based on user input.

[1170] A "prompt sentence" is an input sentence that instructs the generation AI on a specific job title or job content.

[1171] A "position" refers to a position within an organization that has specific responsibilities or duties.

[1172] "Job description" refers to the specific tasks and responsibilities assigned to a particular position.

[1173] The "emotion engine" is a technology that analyzes emotions from a user's tone of voice, facial expressions, choice of words, etc.

[1174] "Feedback" is the process of communicating analysis results and user responses to AI.

[1175] A "data backbone" is a fundamental system that supports the vast amounts of data necessary for organizational management.

[1176] "Simulated organizational management" is the process of simulating the management of an actual organization.

[1177] "Consulting" refers to the service of providing advice and guidance regarding organizational management.

[1178] This invention uses a system that combines a generative AI model and an emotion engine to realize advanced organizational management. A specific embodiment of this system is described below.

[1179] First, the server generates a program using a generative AI model. For this generative AI model, a high-performance AI model (e.g., OpenAI's GPT-4) that runs on a general cloud service is used. The server receives the user's input and sends a prompt sentence based on it to the generative AI model.

[1180] For example, if a user types, "What is your strategy for entering new markets?", the server will take this input and send a prompt to the generative AI model like this:

[1181] "You are an AI in the sales department. Please create a strategy to acquire new customers."

[1182] The generative AI model generates an AI for each job title based on this prompt. The generated AI is assigned to each department, such as the sales department or development department, and begins working according to the job content of each department. The server sets specific job content for these AI, and the AIs run the organization by conversing with each other.

[1183] In addition, the server uses an emotion engine to analyze the user's emotions. This emotion engine uses a general API capable of analyzing voice and facial expressions (e.g. Microsoft Azure's Emotion API). It analyzes emotions from the user's tone of voice, facial expressions, and choice of words, and feeds the results back to the AI.

[1184] For example, if a user provides feedback such as "This strategy is specific and easy to understand," the server uses an emotion engine to sense tension from the user's tone of voice. This information is fed back to the sales department's AI, which then tells the user, "Don't worry, I'll explain the specific steps one by one."

[1185] The system also includes a method to check whether appropriate organizational management can be performed based on a huge data backbone. This enables advanced organizational management using AI and realizes flexible responses according to the user's emotions.

[1186] As a concrete example, there is a scenario in which a user inputs "Please tell me your strategy for entering a new market," the generative AI model generates the sales AI, and the sales AI asks the development AI, "Please tell me the features of the new product." The development AI responds, "The new product uses environmentally friendly materials," and the user provides feedback, "This strategy is specific and easy to understand." The server uses an emotion engine to sense tension from the tone of the user's voice, and the sales AI tells the user, "Don't worry, I'll explain the specific steps one by one."

[1187] In this way, a system is realized in which servers, terminals, and users work together to run an organization using generative AI models and emotion engines.

[1188] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1189] Step 1:

[1190] A user accesses the system.

[1191] A user accesses the system using a terminal (PC or smartphone). For example, the user opens a web browser and enters the system's URL. The system's URL is required as input, and the system's home screen is displayed as output.

[1192] Step 2:

[1193] The server receives the user's input.

[1194] The user types a specific question into the system's interface, such as "What is your strategy for entering new markets?" The server takes this input and generates a prompt. As input, it expects the user's question, and as output, it gets the generated prompt.

[1195] Step 3:

[1196] The server sends a prompt to the generative AI model.

[1197] The server sends the generated prompt sentence to the generative AI model. For example, it sends the prompt sentence, "You are an AI in the sales department. Please create a strategy for acquiring new customers." The generated prompt sentence is required as input, and the output is that it has been sent to the generative AI model.

[1198] Step 4:

[1199] The generative AI model generates AI for each job position.

[1200] The generative AI model generates AI for each job position based on the received prompt text. For example, it generates AI for the sales department and AI for the development department. The input requires a prompt text, and the output is the generated AI for each job position.

[1201] Step 5:

[1202] The server assigns the tasks to each AI.

[1203] The server sets specific tasks for each generated AI. For example, the task of "creating a strategy for acquiring new customers" is set for the AI ​​of the sales department. The generated AI and the task are required as inputs, and the output is an AI that reflects the set task.

[1204] Step 6:

[1205] Each AI initiates a conversation and runs the organization.

[1206] Each AI starts a conversation based on the set business content and runs the organization. For example, the AI ​​of the sales department asks the AI ​​of the development department, "Please tell me the features of the new product." The set business content is required as input, and the output is the progress of a conversation between the AIs.

[1207] Step 7:

[1208] The user provides feedback to the system.

[1209] The user provides feedback on the system's operation. For example, the user comments, "This strategy is specific and easy to understand." The user's feedback is required as an input, and the feedback is reflected in the system as an output.

[1210] Step 8:

[1211] The server uses an emotion engine to analyze the user's emotions.

[1212] The server uses an emotion engine to analyze emotions from the user's tone of voice, facial expressions, and choice of words. For example, it can sense tension from the user's tone of voice. The input is the user's voice and facial expressions, and the output is the analyzed emotion data.

[1213] Step 9:

[1214] The server feeds back the analysis results to the AI.

[1215] The server feeds back the emotion engine's analysis results to the AI. For example, information that "the user is nervous" is conveyed to the sales department's AI. The input is the analyzed emotion data, and the output is the feedback reflected in the AI.

[1216] Step 10:

[1217] Each AI responds according to the user's emotions.

[1218] Each AI responds according to the user's emotions based on the feedback. For example, the sales department's AI tells the user, "Don't worry, I'll explain each specific step one by one." The input requires the feedback emotion data, and the output is an appropriate response to the user.

[1219] (Application example 1)

[1220] Next, a description will be given of Application Example 1 of Form 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".

[1221] Conventional company management systems make it difficult to efficiently manage the work of each department and take appropriate action. In addition, they are unable to analyze users' emotions in real time and provide prompt responses based on the analysis, making it difficult to improve customer satisfaction. Furthermore, in brick-and-mortar stores, it is necessary to appropriately grasp and respond to the emotions of customers, but current systems lack such functionality.

[1222] 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.

[1223] In this invention, the server includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be managed appropriately based on a huge data backbone, a means for combining an emotion analysis engine that recognizes the user's emotions, analyzing the user's emotions from the user's tone of voice, facial expressions, and language, and feeding back the results to the AI, and a means for generating appropriate countermeasures based on the emotion analysis results. This makes it possible to efficiently manage the work of each department and quickly provide appropriate responses according to the user's emotions.

[1224] "Generative AI" is artificial intelligence that automatically conducts conversations and makes decisions based on specified job titles and job descriptions.

[1225] A "position" indicates a position or job within an organization, and examples include president, department manager, section manager, member, etc.

[1226] "Work content of each department" refers to the specific work and tasks that each department within an organization is responsible for.

[1227] "Having them converse" refers to the process in which multiple generative AIs exchange information with each other and make decisions.

[1228] "Running a company" refers to the generation AI running the entire organization based on designated job titles and job duties.

[1229] A "huge data backbone" refers to the massive data base that generative AI uses to make appropriate decisions.

[1230] "Verifying whether the company can be run appropriately" refers to the process of evaluating whether the decisions and strategies provided by the generative AI are effective in actual company operations.

[1231] An "emotion analysis engine" refers to software or hardware for analyzing emotions from a user's tone of voice, facial expressions, choice of words, etc.

[1232] "The tone of a user's voice" refers to characteristics such as the pitch and strength of the voice uttered by the user.

[1233] "Facial expressions" refer to the movements and expressions of a user's face, and are clues as to emotions.

[1234] "Language" refers to the choice of words and phrases a user uses, which provide clues as to their emotions.

[1235] "Emotion analysis" refers to the process of identifying a user's emotions from their tone of voice, facial expressions, and choice of words.

[1236] "Feedback" refers to the process of providing analyzed emotional information to the generative AI and having it reflected in decision-making.

[1237] "Generating an appropriate response" refers to the AI ​​devising the optimal way to respond to the user based on the analyzed emotional information.

[1238] The system for implementing this invention assigns job titles and the work content of each department to multiple generation AIs, and has the AIs converse with each other to run a company. In addition, it combines an emotion analysis engine that recognizes the user's emotions, analyzes the user's emotions from the tone of voice, facial expressions, and wording, and feeds the results back to the AI ​​to generate appropriate countermeasures.

[1239] Hardware and Software Used

[1240] 1. Hardware:

[1241] Smartphone (iOS / Android)

[1242] Smart glasses (Google Glass, Microsoft HoloLens, etc.)

[1243] 2. Software:

[1244] Generative AI models (e.g. GPT-4)

[1245] Sentiment analysis engine (Microsoft Azure Emotion API, IBM Watson Tone Analyzer, etc.)

[1246] Mobile app development frameworks (React Native, Flutter, etc.)

[1247] Data processing and calculation

[1248] The server uses an emotion analysis engine to analyze the user's tone of voice, facial expressions, and choice of words, and feeds the results back to the generation AI, which then generates appropriate countermeasures based on the analysis results and provides them to the user via a smartphone or smart glasses.

[1249] Examples

[1250] For example, if a customer in a brick-and-mortar store expresses dissatisfaction with a staff member wearing smart glasses, the emotion analysis engine will detect "anger" and send that information to the generation AI, which will then instruct the staff on "specific measures to resolve the customer's dissatisfaction."

[1251] Examples of prompt statements

[1252] Analyze the user's tone of voice, facial expressions, and language to identify their emotions. If the user shows signs of anger, consider appropriate countermeasures.

[1253] This system makes it possible to efficiently manage the work of each department and quickly provide appropriate responses according to the user's emotions, which will improve the efficiency of brick-and-mortar store operations and customer satisfaction.

[1254] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1255] Step 1:

[1256] A user puts on the smart glasses and starts interacting with customers.

[1257] Input: Customers' voices, facial expressions, and language

[1258] Output: Audio data, video data

[1259] How it works: The microphone and camera in the smart glasses capture audio and video of customers.

[1260] Step 2:

[1261] The terminal transmits the captured audio and video data to the server.

[1262] Input: Audio data, video data

[1263] Output: Data sent to the server

[1264] How it works: The smart glasses upload data to the server via Wi-Fi or Bluetooth.

[1265] Step 3:

[1266] The server inputs the audio and video data into an emotion analysis engine to analyze emotions.

[1267] Input: Audio data, video data

[1268] Output: Sentiment analysis results (e.g. anger, joy, sadness)

[1269] How it works: An emotion analysis engine (such as Microsoft Azure Emotion API) analyzes voice tone and facial expressions to identify emotions.

[1270] Step 4:

[1271] The server feeds back the emotion analysis results to the generation AI.

[1272] Input: Sentiment analysis results

[1273] Output: Feedback data for the generative AI

[1274] What it does: Send the output of the sentiment analysis engine to a generative AI model (such as GPT-4).

[1275] Step 5:

[1276] The generative AI generates appropriate countermeasures based on the results of sentiment analysis.

[1277] Input: Sentiment analysis results

[1278] Output: Action to be taken (e.g., apology, reward, proposal to resolve the issue)

[1279] Specific operation: The generative AI generates a response based on the prompt text.

[1280] Step 6:

[1281] The server transmits the generated countermeasure to the terminal.

[1282] Input: Workaround

[1283] Output: Actions sent to the terminal

[1284] Specific operation: Send the output of the generative AI to smart glasses.

[1285] Step 7:

[1286] The terminal displays countermeasures to the user, and the user takes appropriate action to the customer.

[1287] Input: Workaround

[1288] Output: User action (e.g. apology, reward offer)

[1289] Specific operation: Countermeasures are displayed on the smart glasses display and the user acts accordingly.

[1290] Example 2

[1291] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1292] Conventional organizational management simulation systems were unable to take into account the user's feelings, resulting in low user satisfaction and low simulation realism. In addition, it was difficult to simulate specific conditions such as the size of the organization, the number of members, and skill sets, making it difficult to provide information that is useful for actual organizational management.

[1293] 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.

[1294] In this invention, the server includes a means for assigning a job title and a task content of each section to a plurality of generative AIs and having the AIs converse with each other to operate the organization, a means for confirming whether the organization can be appropriately managed based on a huge data backbone, a means for a user to input the size of the organization, the number of members, and a skill set, a means for the generative AI to start a simulated organization operation, a means for analyzing the user's emotions using an emotion analysis engine, and a means for the generative AI to respond according to the user's emotions. This enables a realistic organization operation simulation that takes the user's emotions into account. The server may include a means for assigning a job title and a task content of each section to each of a plurality of generative AIs and having the plurality of generative AIs converse with each other to operate the organization.

[1295] "Generative artificial intelligence" is artificial intelligence that has the ability to generate text and data using natural language processing and machine learning.

[1296] A "position" refers to a position within an organization that has specific duties and responsibilities.

[1297] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[1298] A "data backbone" is a collection of vast amounts of data used by a system, and refers to the basic data necessary for operating and analyzing the system.

[1299] "Organizational size" is an indicator of the size and scope of an organization, and is usually expressed in terms of the number of employees, sales, etc.

[1300] "Number of Members" refers to the total number of individual employees working within an organization.

[1301] A "skill set" refers to the collection of knowledge and techniques required to perform a specific task or job.

[1302] An "sentiment analysis engine" is software or a system that analyzes emotions from a user's text or behavior and provides the results.

[1303] "Simulated organizational management" refers to virtually operating an organization in a realistic environment by simulating actual organizational management.

[1304] "Responding according to the user's emotions" refers to the system taking appropriate reactions or actions based on the user's emotional state.

[1305] This invention is a system that simulates organizational management, and uses multiple generative artificial intelligences to simulate organizational management based on conditions specified by a user. Furthermore, by analyzing the user's emotions and responding according to the results, a more realistic simulation with high user satisfaction is realized.

[1306] Hardware and Software Used

[1307] Hardware: High-performance server (e.g. GPU-equipped server)

[1308] software:

[1309] Generative AI models (e.g. GPT-4)

[1310] Sentiment analysis engines (e.g. emotion analysis software)

[1311] Database management systems (e.g. database software)

[1312] Explanation of program processing

[1313] 1. A user accesses the system

[1314] Users access the system's web interface using a terminal (PC or smartphone).

[1315] The device launches a web browser and connects to the specified URL.

[1316] The server receives the user's access and displays a login screen.

[1317] 2. The user enters the company's requirements

[1318] Users input conditions such as the size of their organization (e.g., small or medium-sized enterprise), number of members (e.g., 50 people), and skill set (e.g., diverse) through their terminal.

[1319] The terminal transmits the input data to the server.

[1320] The server stores the received data in a database and proceeds to the next process.

[1321] 3. The server starts running a simulated organization.

[1322] Based on the stored conditions, the server starts a simulated organizational operation using a generative AI model (e.g., GPT-4).

[1323] The server sends a prompt to the generative AI model and starts the simulation.

[1324] The generative AI model generates various scenarios and simulates organizational management strategies and actions.

[1325] The server displays the generated scenario to the user.

[1326] 4. The server analyzes the user's emotions

[1327] While the user is using the system, the terminal collects the user's inputs and responses.

[1328] The terminal transmits the collected data to the server.

[1329] The server uses an emotion analysis engine (e.g., emotion analysis software) to analyze the user's emotions in real time.

[1330] The server feeds back the analysis results to the generative AI model.

[1331] 5. The server responds according to the user's emotions

[1332] The server receives feedback from the sentiment analysis engine and provides that information to the generative AI model.

[1333] The generative AI model considers responses based on the user's emotions, such as re-implementing successful strategies or actions.

[1334] The server displays new scenarios from the generative AI model to the user.

[1335] Examples and prompts

[1336] Examples:

[1337] The user enters the criteria: "Small to mid-size company with 50 members and diverse skill sets."

[1338] The sentiment analysis engine detects the user's emotions of joy.

[1339] Re-implement strategies where generative AI models have been successful (e.g., launching a new product).

[1340] Example prompt:

[1341] "Run a simulated small-to-medium-sized company with 50 members and diverse skill sets. Analyze user sentiment and re-implement successful strategies if you detect a positive sentiment."

[1342] In this way, the system performs simulated organizational management based on the conditions input by the user, and takes appropriate action according to the user's emotions.

[1343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1344] Step 1:

[1345] A user accesses the system

[1346] Specific operation: A user uses a terminal (PC or smartphone) to access the system's web interface. The terminal starts a web browser and connects to the specified URL. The server receives the user's access and displays the login screen.

[1347] Input: User access request

[1348] Output: Login screen displayed

[1349] Step 2:

[1350] User enters company requirements

[1351] Specific operation: The user inputs conditions such as the size of the organization (e.g., small and medium-sized enterprises), the number of members (e.g., 50 people), and the skill set (e.g., diverse) through the terminal. The terminal sends the input data to the server. The server stores the received data in a database and proceeds to the next process.

[1352] Input: Criteria such as organization size, number of members, skill sets, etc.

[1353] Output: Condition data stored in a database

[1354] Step 3:

[1355] The server starts running a simulated organization.

[1356] Specific operation: Based on the saved conditions, the server starts a simulated organizational operation using a generative AI model (e.g. GPT-4). The server sends a prompt to the generative AI model and starts the simulation. The generative AI model generates various scenarios and simulates the strategies and actions of organizational operation. The server displays the generated scenarios to the user.

[1357] Input: Condition data stored in the database, prompt text

[1358] Output: Generated scenario, displayed to the user

[1359] Step 4:

[1360] The server analyzes the user's emotions

[1361] How it works: While the user is using the system, the device collects the user's inputs and reactions. The device sends the collected data to the server. The server uses an emotion analysis engine (e.g. emotion analysis software) to analyze the user's emotions in real time. The server feeds the analysis results back to the generative AI model.

[1362] Input: User input and response data

[1363] Output: Sentiment analysis results, feedback to generative AI model

[1364] Step 5:

[1365] The server responds according to the user's emotions.

[1366] Specific operation: The server receives feedback from the sentiment analysis engine and provides that information to the generative AI model. The generative AI model considers how to respond to the user's emotions, such as re-executing successful strategies or actions. The server displays the new scenario from the generative AI model to the user.

[1367] Input: Sentiment analysis results, feedback to generative AI model

[1368] Output: New scenario, displayed to the user

[1369] (Application example 2)

[1370] Next, a description will be given of Application Example 2 of Form 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".

[1371] Conventional company management systems use AI to perform simulated operations, but because they are unable to respond to user emotions, there is a problem that appropriate feedback cannot be obtained in actual operations. In addition, in the operation of production lines, strategies are not adjusted using emotion data, making efficient production management difficult.

[1372] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1373] In this invention, the server includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to operate the company, a means for checking whether the company can be managed appropriately based on a huge data backbone, a means for combining an emotion engine that recognizes the user's emotions and responding according to the user's emotions, a means for running a simulated production line and proposing an optimal production strategy, a means for analyzing the user's emotion data in real time and feeding back the results to the simulation engine, and a means for strengthening successful strategies and correcting unsuccessful strategies based on the emotion data. This allows for appropriate feedback based on the user's emotions, enabling efficient production management.

[1374] "Generative AI" refers to artificial intelligence that generates new information and content based on data.

[1375] A "position" is a position within an organization that has specific duties and responsibilities.

[1376] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[1377] A "data backbone" refers to the large amount of data that forms the foundation that supports the data for the entire system.

[1378] An "emotion engine" is an engine that analyzes the user's emotions and feeds the results back to the system.

[1379] "Simulated production line operation" refers to an operation method in which a simulation is performed by imitating an actual production line.

[1380] A "production strategy" refers to plans and policies for carrying out production activities efficiently.

[1381] "Emotion data" refers to data that indicates the user's emotional state.

[1382] A "simulation engine" is an engine for performing simulated operations or simulations.

[1383] "Feedback" refers to the process of making input or adjustments based on the system's output.

[1384] A system for carrying out this invention is designed to improve the efficiency of production management in a factory. The system includes a means for assigning job titles and the work content of each department to multiple generation AIs and running a company while having the AIs converse with each other. The system further includes a means for confirming whether the company can be managed appropriately based on a huge data backbone, a means for combining an emotion engine that recognizes the user's emotions and responding according to the user's emotions, a means for operating a simulated production line and proposing an optimal production strategy, a means for analyzing the user's emotion data in real time and feeding back the results to the simulation engine, and a means for strengthening successful strategies and correcting unsuccessful strategies based on the emotion data.

[1385] The server uses the generation AI to simulate company operations. Specifically, it specifies job titles and the work content of each department, and simulates operations while having the AI ​​converse with each other. This allows the server to recreate an environment close to the actual operation and explore appropriate management strategies.

[1386] The device uses an emotion engine to recognize the user's emotions in real time. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice to generate emotion data. This emotion data is sent to a server and fed back to the simulation engine.

[1387] The server adjusts production strategies based on the emotion data: if the user expresses joy, it strengthens successful strategies and makes suggestions to further improve efficiency; if the user expresses dissatisfaction, it modifies strategies and makes new suggestions to solve problems.

[1388] As a concrete example, consider a scenario in which a factory manager uses the system to improve the efficiency of a production line. If the manager expresses joy, the system will strengthen the strategy and provide suggestions to further improve efficiency. Conversely, if the manager expresses dissatisfaction, the system will modify the strategy and provide new suggestions to solve the problem.

[1389] An example of a prompt sentence might be:

[1390] A factory manager is using an AI system installed on a robot to increase the efficiency of the production line. If the manager expresses happiness, the system strengthens the strategy and makes suggestions to further increase efficiency. Conversely, if the manager expresses dissatisfaction, the system modifies the strategy and makes new suggestions to solve the problem.

[1391] The flow of the identification process in the application example 2 will be described with reference to FIG.

[1392] Step 1:

[1393] The server assigns the job titles and work content of each department to the generation AI and starts a simulated company operation. As input, it receives data such as the size of the company, number of members, and skill sets, and simulates operations by having the AIs converse with each other based on this data. As output, it obtains the simulated operation results and business strategy proposals.

[1394] Step 2:

[1395] The device uses an emotion engine to recognize the user's emotions in real time. As input, it receives the user's facial expressions and tone of voice captured by the camera and microphone, analyzes them, and generates emotion data. As output, it obtains data that indicates the user's emotional state.

[1396] Step 3:

[1397] The server receives the emotion data sent from the terminal and feeds it back to the simulation engine. It receives the user's emotion data as input and adjusts the parameters of the simulation engine based on this. The adjusted simulation results are obtained as output.

[1398] Step 4:

[1399] The server adjusts the production strategy based on the emotion data. As input, it receives the adjusted simulation results and enhances successful strategies and modifies unsuccessful strategies based on the emotion data. As output, it obtains a proposal for an optimized production strategy.

[1400] Step 5:

[1401] The user receives the production strategy proposal provided by the server and applies it to the actual production line. As input, the user receives the optimized production strategy proposal and operates the production line based on this. As output, the actual production efficiency and results are obtained.

[1402] Step 6:

[1403] The server monitors the actual production efficiency and results and feeds them back to the simulation engine. As input, it receives the actual production data and readjusts the parameters of the simulation engine based on this. As output, it provides a proposal for a more optimized production strategy.

[1404] Step 7:

[1405] The device again recognizes the user's emotions and transmits them to the server. As input, it receives the user's new facial expressions and tone of voice captured by the camera and microphone, analyzes them, and generates emotion data. As output, it obtains data showing the updated emotional state of the user.

[1406] Step 8:

[1407] The server then adjusts the production strategy again based on the updated emotion data and makes an optimal proposal.As input, it receives the updated emotion data and the actual production data, and readjusts the strategy based on this.As output, it obtains a proposal for a further optimized production strategy.

[1408] Example 3

[1409] Next, a third embodiment of the third embodiment will be described. 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".

[1410] In conventional organizational management simulation systems, the analysis of simulated management results and feedback based on user emotions were insufficient, making it difficult to identify problems in actual management and propose solutions. In addition, because consulting that takes into account the user's emotions is not performed, it is not possible to respond appropriately to the user's concerns and questions. This has led to issues such as delayed improvements in organizational management.

[1411] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1412] In this invention, the server includes a means for assigning a job title and a task content of each section to a plurality of generative AIs and having the AIs converse with each other to operate the organization, a means for confirming whether appropriate organizational management can be performed based on a huge data backbone, a means for a user to input a scenario of simulated organizational management, a means for executing simulated organizational management using an AI model, a means for analyzing the results of the simulated organizational management, a means for analyzing the user's emotions, and a means for identifying problems and proposing solutions based on the emotion analysis results. This makes it possible to analyze the results of the simulated organizational management in detail and provide appropriate feedback and solutions based on the user's emotions. The server may include a means for assigning a job title and a task content of each section to each of a plurality of generative AIs and having the plurality of generative AIs converse with each other to operate the organization.

[1413] "Generative AI" is AI that autonomously converses and makes decisions based on a designated job title or job description.

[1414] A "position" refers to a position within an organization that has specific duties and responsibilities.

[1415] "Job Description" refers to the specific tasks and responsibilities associated with a particular position.

[1416] A "data backbone" refers to a foundation for accumulating the vast amounts of data necessary for organizational management and using it for analysis and decision-making.

[1417] A "scenario" refers to a series of plans or strategies that are executed in a simulated organizational operation.

[1418] An "artificial intelligence model" refers to an algorithm or program built using machine learning or deep learning to perform a specific task.

[1419] "Simulated organizational management" refers to virtual management carried out using generative artificial intelligence to simulate actual organizational management.

[1420] "Analyzing the results" refers to the process of evaluating the results of the simulated organizational operations in detail and identifying success factors and problems.

[1421] "Analyzing emotions" refers to the process of identifying emotions from a user's input and behavior and assessing their emotional state.

[1422] "Feedback" refers to information or advice provided based on analysis results and evaluation.

[1423] "Proposing a solution" means showing specific methods or strategies for improving or resolving an identified problem.

[1424] The present invention is a system for performing a simulated organizational operation and providing consulting based on the results. A specific embodiment of this system will be described below.

[1425] System Configuration

[1426] This system consists of three main components: a server, a terminal, and a user. The server uses a generative AI model to run a simulated organizational management scenario and analyze the results. The terminal receives input from the user and performs sentiment analysis. The user inputs a simulated organizational management scenario into the system and checks the results.

[1427] Hardware and Software Used

[1428] Server: Use a server with high-performance computing power to run generative artificial intelligence models, specifically using machine learning frameworks such as TensorFlow and PyTorch.

[1429] Terminal: A computer or smartphone operated by the user is used. Sentiment analysis is performed using emotion analysis engines such as IBM Watson and Microsoft Azure Cognitive Services.

[1430] Data backbone: Use a database (e.g., MySQL, PostgreSQL) to store data necessary for organizational operations.

[1431] Program Processing

[1432] The server receives the simulated organizational management scenario input by the user and executes the simulation using a generative artificial intelligence model. The results of the simulation are analyzed in detail using data analysis tools (e.g., Pandas, NumPy). For example, the effectiveness of an advertising campaign is simulated and the results are evaluated.

[1433] The device receives input from the user and analyzes the user's emotions using a sentiment analysis engine. The analysis results are sent to a server, which uses the information to identify problems and propose solutions. For example, if a user enters "I feel like our strategy for acquiring new customers is not working," the device sends this text to the sentiment analysis engine and obtains the analysis results.

[1434] Examples

[1435] Consider a case where a user is anxious about a strategy to acquire new customers. If the user types, "I feel like our strategy to acquire new customers is not working," the device will use a sentiment analysis engine to analyze the user's anxiety. The analysis results are sent to a server, which uses the information to identify the problem and propose a solution, such as, "You need to reevaluate the target demographic of your advertising campaign."

[1436] Examples of prompt statements

[1437] I feel like my strategy for acquiring new customers isn't working. Can you tell me what's wrong?

[1438] In this way, a system is realized in which the server, the terminal, and the user work together to provide consulting based on the results of the simulated organization management. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1439] Step 1:

[1440] A user logs into the system.

[1441] The user enters a username and password on the login screen of the terminal. The terminal sends the entered information to the server, which then refers to the database to perform authentication. If authentication is successful, the user can access the dashboard.

[1442] Input: Username, Password

[1443] Output: Authentication result (success / failure)

[1444] Step 2:

[1445] The user inputs a scenario of a simulated organization operation.

[1446] The user enters "I want to run an advertising campaign to acquire new customers" into the input form on the dashboard. The terminal sends this information in JSON format to the server.

[1447] Input: A simulated organizational scenario

[1448] Output: Scenario data (JSON format)

[1449] Step 3:

[1450] The server uses the AI ​​model to run a simulated organizational operation.

[1451] The server runs a Python script based on the received scenario and loads the TensorFlow model, which then runs a simulation of the ad campaign and saves the results as a CSV file.

[1452] Input: Scenario data

[1453] Output: Simulation results (CSV file)

[1454] Step 4:

[1455] The server analyzes the results of the simulated organizational management.

[1456] The server reads the generated CSV file with Pandas and analyzes the effectiveness of the ad campaign, for example, calculating click-through rates and conversion rates and graphing the results.

[1457] Input: Simulation results (CSV file)

[1458] Output: Analysis results (graphs, statistical data)

[1459] Step 5:

[1460] The device analyzes the user's emotions.

[1461] The user reviews the results and types, "The results of my ad campaign are not good." The device sends this text to the sentiment analysis engine and gets the analysis results.

[1462] Input: User feedback (text)

[1463] Output: Emotion analysis results

[1464] Step 6:

[1465] The server identifies problems based on the results of sentiment analysis and proposes solutions.

[1466] The server receives the emotion analysis results, and the AI ​​determines that the user is feeling anxious. The AI ​​identifies the need to reevaluate the target audience of the advertising campaign and suggests specific improvement measures.

[1467] Input: Sentiment analysis results

[1468] Output: A proposed solution

[1469] Step 7:

[1470] The user reviews the proposed solution.

[1471] The user sees suggested solutions on the device dashboard, such as "reevaluate your target audience and change your ad content," and decides on the next action to take.

[1472] Input: Solution proposal

[1473] Output: User's next action

[1474] (Application example 3)

[1475] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1476] In the conventional organizational management system, there was insufficient consulting based on the results of simulated operations, and measures to improve the efficiency of production lines and manage the emotions of workers were particularly insufficient. In addition, specific measures to reduce the stress and anxiety of workers were not proposed, so improvements to the work environment were often delayed. This led to problems such as a decline in the productivity of the entire organization and a decline in worker satisfaction.

[1477] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1478] In this invention, the server includes a means for assigning a job title and a task content of each section to a plurality of generation AIs and having the AIs converse with each other to operate the organization, a means for confirming whether the organization can be appropriately managed based on a huge data backbone, a means for performing a simulated production line operation and providing consulting to improve production efficiency based on the results, and a means for recognizing the emotions of workers using an emotion engine and proposing measures to reduce stress and anxiety. This makes it possible to improve the production efficiency of the organization and to propose appropriate measures according to the emotions of the workers. The server may include a means for assigning a job title and a plurality of task content of each section to each of the plurality of generation AIs and having the plurality of generation AIs converse with each other to operate the organization.

[1479] "Generative AI" is an artificial intelligence that performs simulated operations based on specified job titles and job content.

[1480] A "data backbone" is a data set that serves as the foundation for verifying appropriate organizational management based on vast amounts of data.

[1481] "Simulated production line operation" is the process of operating an actual production line in imitation of the actual production line and analyzing the results.

[1482] "Production efficiency" is an indicator that shows the efficiency of production activities within a certain period of time.

[1483] "Consulting" refers to the task of proposing improvement measures based on the results of a mock operation.

[1484] The "emotion engine" is a system that recognizes the emotions of workers and suggests countermeasures based on the results.

[1485] "Workers" refers to people who work in factories or on production lines.

[1486] "Stress" refers to the mental or physical strain or tension felt by workers.

[1487] "Anxiety" refers to the feelings of worry and fear that workers have about the future.

[1488] "Measures" refer to specific means or methods taken to solve a particular problem.

[1489] In order to implement the present invention, the following system configuration and program are required.

[1490] System Configuration

[1491] 1. Hardware:

[1492] Factory Robots

[1493] Heart rate monitor

[1494] camera

[1495] 2. Software:

[1496] Python

[1497] EmotionEngine Library

[1498] AISimulation Library

[1499] Program processing explanation

[1500] The server first assigns job titles and the work content of each department to multiple generation AIs, and has the AIs converse with each other while managing the organization. The server may include a means for assigning job titles in the organization and the work content of multiple departments included in the organization to each of multiple generation AIs, and having the multiple generation AIs converse with each other while managing the organization. This allows a simulated production line to be operated. Next, it is confirmed whether appropriate organizational management can be performed based on the huge data backbone. Consulting is provided to improve production efficiency based on the results of the simulated operation.

[1501] Furthermore, the system uses an emotion engine to recognize the emotions of workers and proposes measures to reduce stress and anxiety. Specifically, the system analyzes the worker's heart rate and facial expression data to recognize stress and anxiety. Based on the recognized emotions, the system proposes measures to reduce the worker's stress and anxiety.

[1502] Examples

[1503] For example, when a new product is being produced on a factory production line, if the AI ​​runs a simulation and finds that efficiency is declining, it will suggest reviewing the work process or introducing new machinery. Also, if a worker's heart rate is high and they look anxious, it will suggest increasing break times or improving the work environment.

[1504] Examples of prompt statements

[1505] Run a mock factory production line and analyze its efficiency. Based on the results, suggest improvements. Also, recognize the emotions of workers and suggest measures to reduce stress and anxiety.

[1506] In this way, the server can support efficient production and worker health through simulated production line operations and worker emotion recognition.

[1507] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1508] Step 1:

[1509] The server assigns job titles and the work content of each department to multiple generation AIs.

[1510] Input: Job title information, job description information

[1511] Data processing: Assigning job titles and job descriptions to generative AI

[1512] Output: Job title and job description set in the generated AI

[1513] Specific operation: The server retrieves job title information and job content information from the database and assigns it to the generation AI.

[1514] Step 2:

[1515] The server operates the organization while having the generation AIs converse with each other. The server may include a means for assigning to each of the plurality of generation AIs a position in the organization and a plurality of job contents included in the organization, and for operating the organization while having the plurality of generation AIs converse with each other.

[1516] Input: Generated AI with job title and job description set

[1517] Data processing: Conversation simulation between generative AIs

[1518] Output: Results of a simulated organizational operation

[1519] Specific operation: The server simulates conversations between the generation AIs and generates scenarios for running an organization.

[1520] Step 3:

[1521] The server checks whether appropriate organizational management can be performed based on the huge data backbone. The server may include a means for checking whether appropriate organizational management can be performed based on the data backbone, which is a large amount of data that is the basis of the system.

[1522] Input: Results of simulated organizational operations, data backbone

[1523] Data processing: Analysis of organizational management results

[1524] Output: Evaluation results of organizational management

[1525] Specific operation: The server compares the results of the simulated operation with the data backbone and evaluates the organization's management.

[1526] Step 4:

[1527] The server runs a simulated production line and provides consulting services to improve production efficiency based on the results.

[1528] Input: Production line operation scenario

[1529] Data processing: Simulation and analysis of production efficiency

[1530] Output: Proposals for improving production efficiency

[1531] Specific operation: The server performs a mock operation of a production line, simulates efficiency, and suggests improvement measures.

[1532] Step 5:

[1533] The server uses an emotion engine to recognize the emotions of workers and suggest measures to reduce stress and anxiety.

[1534] Input: Worker's heart rate data, facial expression data

[1535] Data processing: Emotion recognition and analysis

[1536] Output: Suggested measures to reduce stress and anxiety

[1537] How it works: The server analyzes data obtained from the heart rate monitor and camera, recognizes the worker's emotions, and suggests appropriate measures.

[1538] Step 6:

[1539] The server reports the overall results to the user and implements any necessary remedial measures.

[1540] Input: Evaluation results of organizational management, proposals for improving productivity, emotion recognition results

[1541] Data processing: synthesis of results and preparation of reports

[1542] Output: Report with remedial measures

[1543] What it does: The server consolidates the results of each step and creates a report for the user, suggesting any necessary remedial measures.

[1544] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1545] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1546] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1547] 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 smart glasses 214.

[1548] [Third embodiment]

[1549] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1550] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1551] 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 wide area network (WAN) and / or a local area network (LAN).

[1552] 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.

[1553] 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 the voice according to instructions from the processor 46.

[1554] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1555] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the transmission and reception of various information between the processor 46 and the processor 28 via the network 54.

[1556] The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1557] Fig. 6 shows an example of 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.

[1558] 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.

[1559] 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.

[1560] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1561] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1562] "Example 1"

[1563] In one embodiment of the present invention, the generation AI is assigned job titles such as president, department manager, section manager, and member, and the work content of each section is set. For example, the AI ​​of the sales department is made to plan a strategy for acquiring new customers, and the AI ​​of the development department is made to plan the development of a new product. These AIs run the company while talking to each other.

[1564] "Example 2"

[1565] In another embodiment of the present invention, the size of the company, the number of members, skills, etc. are specified, and the AIs run a simulated company. For example, conditions are set such as a small- or medium-sized company with 50 members and a diverse skill set, and the AI ​​runs a simulated company.

[1566] "Example 3"

[1567] As a further embodiment of the present invention, consulting on future company management is provided based on the results of the simulated company management. For example, if the results of the company management simulated by AI show that a strategy for acquiring new customers is not effective, the cause will be analyzed and improvement measures will be proposed.

[1568] The process flow of each embodiment will be described below.

[1569] "Example 1"

[1570] Step 1: Specify job titles such as president, department manager, section manager, and member to the generating AI.

[1571] Step 2: Set the work content for each department. For example, have the AI ​​in the sales department create a strategy to acquire new customers, and the AI ​​in the development department create a development plan for a new product.

[1572] Step 3: These AIs will talk to each other and run the company.

[1573] "Example 2"

[1574] Step 1: Specify the size of your company, number of members, skills, etc.

[1575] Step 2: Have the AIs run a simulated company. For example, set conditions such as a small- or medium-sized company with 50 members and diverse skill sets, and have the AI ​​run a simulated company.

[1576] "Example 3"

[1577] Step 1: Based on the results of the simulated company operations, provide consulting for future company operations.

[1578] Step 2: For example, if the AI's simulated company operations show that a strategy for acquiring new customers is not effective, it will analyze the reasons and propose improvements.

[1579] Example 1

[1580] Next, a description will be given of Example 1 of the embodiment 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".

[1581] In traditional organizational management, the task content for each position and progress management were often done manually, making efficient management difficult. In addition, there was a lack of cooperation between departments, making it difficult to share information and unify strategies. Furthermore, it was difficult to find an appropriate management method based on the size of the organization and the skills of its members, and there was also the problem of being unable to provide sufficient consulting on future management.

[1582] 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.

[1583] In this invention, the server includes a means for assigning job titles and work content to multiple generation AIs and having the AIs talk to each other to operate the organization, a means for checking whether the organization can be operated appropriately based on a huge data backbone, a means for a user to access the system and set job titles and work content, a means for the server to generate AIs corresponding to each job title using a generation AI model, a means for the server to assign work content to each AI, a means for each AI to talk to each other and proceed with the work, a means for the server to monitor the conversation content and progress of each AI and make adjustments as necessary, and a means for a user to access the system and check the progress. This enables efficient organization management, strengthens cooperation between each department, and makes it easier to share information and unify strategies. It also makes it possible to explore appropriate management methods according to the size of the organization and the skills of its members, and provides consulting for future management.

[1584] "Generative AI" is a type of artificial intelligence that uses natural language processing to generate text.

[1585] A "position" indicates a job title or level of responsibility within an organization, and includes, for example, president, department manager, section manager, member, etc.

[1586] "Job content" refers to the specific duties and tasks each position is responsible for, such as developing strategies for acquiring new customers and planning new product development.

[1587] A "server" refers to a computer system that provides services to other computers over a network.

[1588] "User" refers to a person or organization that uses the system.

[1589] "Data backbone" refers to the large amount of data that forms the foundation of the system, on which appropriate decisions and operations are made.

[1590] A "prompt" is text that is used to input specific instructions or questions to the generative AI.

[1591] "Progress" refers to the state or condition that indicates how far a task or project has progressed.

[1592] "Simulated organizational management" refers to virtually trying out management methods by simulating actual organizational management.

[1593] "Consulting" refers to providing advice and support regarding organizational management based on specialized knowledge and experience.

[1594] The present invention relates to a system for improving the efficiency of organizational management by using a generative AI. A specific embodiment of this system will be described below.

[1595] First, the user accesses the system using a terminal. The user specifies the role of the person, such as president, department manager, section manager, or member, and sets the job content for each role. For example, the AI ​​for the sales department can be set to "draft a strategy to acquire new customers," and the AI ​​for the development department can be set to "draft a development plan for a new product."

[1596] Next, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate an AI for each job title. The server inputs the job content set by the user as a prompt to the generated AI.

[1597] The server assigns each generated AI task set by the user. For example, the sales department's AI could be assigned the task of "creating a strategy to acquire new customers," while the development department's AI could be assigned the task of "creating a development plan for a new product."

[1598] Each AI will carry out its assigned tasks by talking to each other. For example, if the sales department's AI suggests that "we should strengthen social media advertising to acquire new customers," the development department's AI will respond by saying, "We will adjust the development schedule for new products to match the advertising strategy."

[1599] The server monitors the conversation content and work progress of each AI in real time. If necessary, the server adjusts the AI's tasks to support the smooth running of work. For example, if the strategy proposed by the sales department's AI is not feasible, the server will instruct it to revise the proposal.

[1600] The user can access the system again using a terminal to check the progress of each AI task. The user can issue new instructions to the AI ​​if necessary.

[1601] As a concrete example, if a user inputs "Sales AI, please plan a new customer acquisition strategy for the next quarter," the server will send this prompt to the Sales AI. The Sales AI will respond with, "We will propose a strategy to strengthen SNS advertising in the next quarter and expand the target demographic." If the user then inputs, "Development AI, please plan a new product development plan and adjust it to match the Sales strategy," the server will send this prompt to the Development AI. The Development AI will respond with, "We will bring forward the development schedule for the new product and conduct promotions in line with SNS advertising."

[1602] In this way, the server uses the generative AI model to assign tasks to the AIs in each role and run the organization by having them work together. This system enables efficient organizational management, strengthens collaboration between departments, and makes it easier to share information and unify strategies. It also makes it possible to explore appropriate management methods according to the size of the organization and the skills of its members, and provides consulting on future management.

[1603] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1604] Step 1:

[1605] A user accesses the system and sets their job title and job description.

[1606] Input: The user uses a terminal to input job titles such as president, department manager, section manager, and member, as well as the job description of each position.

[1607] Data processing: The server saves the job title and job description entered by the user in a database.

[1608] Output: Data with job title and job description is generated.

[1609] Specific operations: Through the terminal interface, the user inputs to the sales department's AI, "Draw up a strategy for acquiring new customers," and to the development department's AI, "Draw up a development plan for a new product."

[1610] Step 2:

[1611] The server uses the generative AI model to generate AI corresponding to each position.

[1612] Input: The server retrieves the job title and job description data stored in step 1.

[1613] Data processing: The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate AI corresponding to each role.

[1614] Output: A generation AI corresponding to each role is generated.

[1615] Specific operation: The server generates a GPT-4 as the AI ​​for the sales department and another GPT-4 instance as the AI ​​for the development department.

[1616] Step 3:

[1617] The server assigns tasks to each AI.

[1618] Input: The server obtains the data of each AI generated in step 2 and the task content set in step 1.

[1619] Data processing: The server inputs the corresponding task details as prompts for each AI.

[1620] Output: An AI with assigned task content is generated.

[1621] Specific operation: The server inputs a prompt to the sales department's AI, "Draw up a strategy for acquiring new customers," and a prompt to the development department's AI, "Draw up a development plan for a new product."

[1622] Step 4:

[1623] Each AI will converse with each other and carry out its work.

[1624] Input: Prompts for the tasks assigned to each AI.

[1625] Data processing: Each AI carries out its assigned tasks by conversing with each other.

[1626] Output: The business plans and strategies generated by each AI.

[1627] Specific operation: The sales department's AI suggests, "We should strengthen our social media advertising to acquire new customers," and the development department's AI responds, "We will adjust the development schedule for new products to match our advertising strategy."

[1628] Step 5:

[1629] The server monitors the conversations and progress of each AI and makes adjustments as necessary.

[1630] Input: Conversation content and work progress data of each AI.

[1631] Data processing: The server monitors the conversation content and progress of each AI in real time and adjusts tasks as necessary.

[1632] Output: Aligned business plans and strategies.

[1633] Specific operation: If the strategy proposed by the sales department's AI is not feasible, the server instructs the sales department to revise the proposal.

[1634] Step 6:

[1635] The user accesses the system and checks the progress.

[1636] Input: The user uses a terminal to access the system and check the progress of each AI.

[1637] Data processing: The server formats the data to display each AI's progress to the user.

[1638] Output: A user-visible display of progress.

[1639] Specific operations: Through the terminal, the user can check the progress of the strategies proposed by the sales department's AI and the development plans drawn up by the development department's AI, and issue new instructions as necessary.

[1640] (Application example 1)

[1641] Next, a description will be given of Application Example 1 of Form 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".

[1642] In traditional company and factory operations, human managers were required to oversee the work of each department and machine to ensure optimal operation. However, this required a great deal of effort and time, making efficient operation difficult. In addition, because each department and machine operated independently, there was a lack of overall coordination, and optimal operation was often not possible. Furthermore, there was a lack of systems for performing simulated operations, making it difficult to grasp problems in actual operations in advance. In order to solve these issues, an efficient operation system that utilizes AI is needed.

[1643] 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.

[1644] In this invention, the server includes a means for assigning job titles and work content for each section to multiple generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be properly managed based on a huge data backbone, and a means for assigning job titles to each machine in the factory, each machine taking charge of a specific task, and optimizing the operation of the entire factory while conversing with each other. This enables efficient company and factory operations using AI.

[1645] "Generative AI" is artificial intelligence that generates new information or content based on given data or prompts.

[1646] A "position" is a rank or position within an organization that has specific duties and responsibilities.

[1647] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[1648] A "conversation" is the process by which multiple AIs exchange information with each other and communicate with each other.

[1649] "Means of running the company" refers to methods and systems that use AI to manage the operations of the entire organization and operate it efficiently.

[1650] A "data backbone" is a data infrastructure that enables AI to make appropriate judgments and predictions based on massive amounts of data.

[1651] "Each machine in the factory" refers to the various devices and equipment in the factory used for manufacturing and production.

[1652] "Taking charge of specific tasks" means that each machine or AI carries out specific tasks or work according to its role.

[1653] "Means to optimize operations throughout the factory" refers to methods or systems in which each machine and AI within the factory works together to efficiently produce and manage, thereby improving overall performance.

[1654] The following system is constructed as an embodiment of the present invention. The server includes a means for assigning job titles and work content for each department to multiple generation AIs and running the company while having the AIs converse with each other, a means for confirming whether the company can be properly run based on a huge data backbone, and a means for assigning job titles to each machine in the factory, each machine taking charge of a specific task, and optimizing the operation of the entire factory while conversing with each other.

[1655] System Programming

[1656] The server uses Python and the OpenAI API to execute a program that assigns the job title and job content to each generated AI. Specifically, it performs the following process.

[1657] 1. The server generates a prompt for each generated AI, specifying the job title and job description.

[1658] 2. The server uses the OpenAI API to send a prompt to the generating AI and get a response.

[1659] 3. Based on the responses received, the server allows each generation AI to converse with each other and proceed with the work.

[1660] Hardware and Software Used

[1661] Hardware: Each machine in the factory (production line robots, quality control robots, logistics robots, maintenance robots, etc.)

[1662] Software: Python, OpenAI API

[1663] Data processing and calculation

[1664] The server generates and sends a prompt sentence like the following to each generated AI.

[1665] Examples of prompt statements

[1666] "Please act as a manufacturing line robot and create production plans."

[1667] "As a quality control robot, please create a quality check strategy."

[1668] "As a logistics robot, please manage inventory and plan delivery."

[1669] "As a maintenance robot, please create a maintenance plan for the equipment."

[1670] The server receives the generative AI's responses to these prompts, and each machine is responsible for a specific task, and as they converse with each other, they generate data to optimize the operation of the entire factory.

[1671] Examples

[1672] For example, if a manufacturing line robot is sent a prompt saying, "As a manufacturing line robot, please create a production plan," the generation AI will propose a specific production plan. A quality control robot can be sent a prompt saying, "As a quality control robot, please create a quality check strategy," which will have it propose a specific strategy for quality checks. This makes it possible for each machine in the factory to work together to efficiently carry out operations and optimize the operation of the entire factory.

[1673] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1674] Step 1:

[1675] The server generates a prompt statement specifying the job title and job description for each generated AI.

[1676] Input: List of job titles and job duties

[1677] Output: Prompt for each generated AI

[1678] Specific operation: The server creates an appropriate prompt for each AI based on the list of job titles and job content. For example, it generates a prompt such as, "As a manufacturing line robot, please create a production plan."

[1679] Step 2:

[1680] The server sends the generated prompt text to each generating AI using the OpenAI API.

[1681] Input: Generated prompt text

[1682] Output: Response from the generation AI

[1683] Specific operation: The server sends the generated prompt text to the OpenAI API and waits for a response from each generated AI. For example, it obtains a response to the prompt text, "As a manufacturing line robot, please create a production plan."

[1684] Step 3:

[1685] The server analyzes the responses it receives and confirms the tasks for which each generation AI is responsible.

[1686] Input: Response from the generation AI

[1687] Output: Analyzed business content

[1688] Specific operation: The server analyzes the response from the generation AI and checks the work content proposed by each generation AI. For example, it analyzes the specific production plan proposed by a manufacturing line robot.

[1689] Step 4:

[1690] The server creates an operation plan for the entire factory based on the suggestions of each generation AI.

[1691] Input: Parsed business content

[1692] Output: Factory-wide operation plan

[1693] Specific operation: The server integrates the work content proposed by each generation AI and creates an operation plan for the entire factory. For example, it integrates the production plan for the manufacturing line robot and the quality check strategy for the quality control robot.

[1694] Step 5:

[1695] The server distributes the created operation plan to each machine in the factory and has them execute it.

[1696] Input: Overall plant operation plan

[1697] Output: Instructions for each machine to execute

[1698] Specific operations: The server distributes the created operation plan to each machine in the factory and instructs each machine to carry out its work based on the plan. For example, it instructs a manufacturing line robot to carry out a specific production task.

[1699] Step 6:

[1700] The server monitors the performance of each machine and makes adjustments as necessary.

[1701] Input: Running status data for each machine

[1702] Output: Adjustment instructions

[1703] Specific operation: The server monitors the execution status of each machine in real time and issues adjustment instructions as necessary. For example, if there is a delay in the production plan, it instructs the manufacturing line robot to adjust the schedule.

[1704] Example 2

[1705] Next, a second embodiment of the second form will be described. 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".

[1706] In conventional company management simulation systems, it was difficult to perform realistic simulations based on conditions specified by the user. In addition, there was a lack of means to provide users with the results of simulated company management simulations using generative AI models, so the information that users could obtain was limited. Furthermore, there was a lack of concrete means to provide consulting for future company management.

[1707] 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.

[1708] In this invention, the server includes a means for allowing a user to input conditions such as the size of the company, the number of members, and a skill set, a means for generating simulated company data based on the conditions, a means for executing a simulation based on the generated company data, and a means for providing the user with the simulation results. This makes it possible to perform a realistic simulation based on the conditions specified by the user, and to provide the user with the results of a simulated company management simulation using a generated AI model. In addition, a specific means for providing consulting on future company management is also provided.

[1709] A "user" is a person or organization that uses the system to input conditions for simulating company operations.

[1710] A "server" is a computer system that receives input from users, generates data, runs simulations, and provides results.

[1711] "Conditions" are information entered by the user, such as company size, number of members, skill set, etc.

[1712] "Simulated company data" refers to data such as the skill sets, job titles, and job descriptions of company members that is generated based on conditions entered by the user.

[1713] "Simulation" is the process of virtually recreating the operating conditions of a company using a generative AI model based on generated simulated company data.

[1714] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to generate simulated company data based on user input and run simulations.

[1715] "Simulation results" refers to information obtained by running a simulation, such as the company's performance, the performance of each member, problems, and areas for improvement.

[1716] "Consulting" is the process of providing advice and suggestions regarding the future management of a company based on the results of a simulation.

[1717] The present invention is a system for simulating a mock company operation based on conditions specified by a user and providing the results. A specific embodiment of this system will be described below.

[1718] Hardware and Software Used

[1719] Hardware: High-performance servers (e.g. virtual servers in cloud services)

[1720] Software: generative AI models (e.g., AI models for natural language processing), database management systems (e.g., MySQL), web servers (e.g., Nginx)

[1721] System Overview

[1722] The system generates mock company data based on conditions entered by the user through a terminal, such as company size, number of members, and skill sets. Based on the generated data, it runs a simulation using a generative AI model and provides the results to the user.

[1723] Program Processing

[1724] The server receives input from the user and starts a simulation to run a mock company based on the specified conditions. Specifically, the process proceeds as follows:

[1725] 1. Receive user input:

[1726] A user accesses a web interface using a terminal and inputs conditions such as company size, number of members, skill set, etc. For example, the user inputs conditions such as "small to medium-sized business, 50 members, diverse skill sets."

[1727] 2. Conditional Data Generation:

[1728] The server generates data for a mock company based on the conditions entered by the user, including each member's skill set, job title, and job description, and uses a generative AI model to create and input prompts.

[1729] Example prompt:

[1730] "Please simulate the operation of a small or medium-sized company with 50 members and diverse skill sets. Please consider each member's job title, skills, and duties and simulate the overall operation of the company."

[1731] 3. Run the simulation:

[1732] The server starts a simulation based on the generated company data. The generative AI model simulates the behavior and work progress of each member and evaluates the overall operating status of the company.

[1733] 4. Result output:

[1734] The server provides the user with the results of the simulation, including the company's performance, the performance of each member, problems, and areas for improvement.

[1735] Examples

[1736] For example, if a user enters conditions such as "small to medium-sized business, 50 members, diverse skill sets," the server generates simulated company data based on these conditions. The generative AI model runs a simulation using prompt statements to evaluate the behavior of each member and the progress of work. The simulation results are provided to the user, displaying the company's performance, the performance of each member, problems, and areas for improvement.

[1737] This system allows users to perform realistic simulations based on specified conditions and obtain simulated company operations using generative AI models. It also provides specific means for consulting on future company operations.

[1738] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1739] Step 1:

[1740] Receiving user input

[1741] A user uses a terminal to access a web interface and inputs conditions such as company size, number of members, and skill sets. For example, the user may input conditions such as "small to medium-sized business, 50 members, diverse skill sets." The terminal sends the information entered by the user to the server. The server stores the received information in a database.

[1742] Input: Company size, number of members, skill set, and other criteria

[1743] Output: User input information stored in a database

[1744] Step 2:

[1745] Conditional Data Generation

[1746] The server retrieves the conditions entered by the user from the database. The server uses the generative AI model to generate data for a simulated company. This data includes each member's skill set, job title, and job description. The server creates and inputs a prompt sentence to the generative AI model.

[1747] Example prompt:

[1748] "Please simulate the operation of a small to medium-sized company with 50 members and diverse skill sets. Please consider each member's job title, skills, and duties and simulate the overall operation of the company."

[1749] Input: User criteria retrieved from the database

[1750] Output: Generated mock company data

[1751] Step 3:

[1752] Running the Simulation

[1753] The server starts a simulation based on the generated company data. The generative AI model simulates the actions and work progress of each member and evaluates the overall operational status of the company. The server creates and inputs a prompt for the simulation to the generative AI model.

[1754] Example prompt:

[1755] "Simulate the actions and work progress of each member based on the generated company data."

[1756] Input: Generated mock company data

[1757] Output: Simulation results

[1758] Step 4:

[1759] Output of results

[1760] The server formats the simulation results to provide them to the user. The terminal displays the simulation results to the user, such as the company's performance, the performance of each member, problems and areas for improvement, etc. The server stores the simulation results in a database.

[1761] Input: Simulation results

[1762] Output: Formatted simulation results provided to the user.

[1763] In this way, users can perform realistic simulations based on specified conditions and obtain simulated results of company operations using generative AI models.

[1764] (Application example 2)

[1765] Next, a description will be given of Application Example 2 of Form 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".

[1766] Conventional company management simulation systems allow users to specify the size of a company, the number of members, and the skill set to perform simulated operations, but lack simulations specialized for factory operations. In addition, they lack the functionality to automatically simulate a factory's production efficiency, cost management, and quality management and propose optimal operation methods, making it difficult to optimize actual factory operations. This creates the issue that no specific proposals can be made to improve the efficiency of factory operations, making it difficult to optimize operations.

[1767] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1768] In this invention, the server includes a means for assigning job titles and work content of each department to multiple generation AIs and having the AIs converse with each other to operate the company, a means for confirming whether the company can be appropriately managed based on a huge data backbone, a means for specifying the size of the factory, the number of employees, and the skill set, and for the AI ​​to simulate the operation of the factory, and a means for the AI ​​to automatically simulate the production efficiency, cost management, and quality management of the factory and propose the optimal operation method. This makes it possible to optimize the production efficiency, cost management, and quality management in the operation of the factory.

[1769] "Generative AI" refers to artificial intelligence that generates new information and content based on data.

[1770] A "position" indicates a rank of job or responsibility within an organization.

[1771] "Duties of each department" refers to the specific work and tasks that each division or section within an organization is responsible for.

[1772] A "data backbone" refers to the large amount of data that forms the foundation of systems and networks.

[1773] "Corporate management" refers to all activities involved in running and managing a business.

[1774] "Factory size" refers to the physical size and production capacity of the factory.

[1775] "Number of employees" refers to the total number of people working in an organization or factory.

[1776] A "skill set" is a collection of skills and abilities possessed by an individual or group.

[1777] "Running a simulated factory" means simulating actual factory operations.

[1778] "Production efficiency" indicates the ratio of production volume obtained to the resources input.

[1779] "Cost management" is the activity of planning, monitoring and controlling expenses in a business or factory.

[1780] "Quality control" refers to activities for maintaining and improving the quality of products and services.

[1781] "Proposing the optimal management method" means presenting specific methods and strategies for maximizing management efficiency.

[1782] The system for implementing this invention has the function of assigning job titles and work content for each department to multiple generation AIs, and having the AIs converse with each other to operate the company. It also has a function to check whether the company can be managed appropriately based on a huge data backbone. Furthermore, it has a function to specify the size of the factory, the number of employees, and the skill set, and have the AI ​​simulate the operation of the factory, and includes a function to automatically simulate the production efficiency, cost management, and quality management of the factory and propose the optimal operation method.

[1783] Hardware and Software Used

[1784] Hardware: Factory robots (e.g. ABB's IRB series), servers (e.g. AWS EC2 instances)

[1785] Software: Python 3.x, machine learning libraries (e.g. TensorFlow, PyTorch), databases (e.g. MySQL)

[1786] Data processing and calculation

[1787] The server first randomly generates employee skill sets. To do this, it uses Python random functions to randomly assign skills such as "assembly," "quality control," "maintenance," and "logistics" to each employee. Next, it simulates the operating efficiency of the factory based on the generated skill sets. Specifically, it aggregates the skill sets of each employee and calculates the production efficiency of the entire factory.

[1788] Examples

[1789] For example, when simulating a factory with 100 employees and four skill sets - assembly, quality control, maintenance, and logistics - the server will perform the following process.

[1790] 1. Data generation: Randomly generate employee skill sets using the generate_employees function.

[1791] 2. Simulation: The simulate_operation method calculates the operational efficiency of the factory. Based on the skill sets of the employees, the efficiency of the entire factory is evaluated.

[1792] 3. Result output: Output the simulation results to help optimize factory operations.

[1793] Examples of prompt statements

[1794] An example of a prompt to be input to the generative AI model is as follows:

[1795] "Simulate the operational efficiency of a factory with 100 employees and the skill sets of 'Assembly', 'Quality Control', 'Maintenance' and 'Logistics'."

[1796] In this way, the factory operation simulator can evaluate the factory's operating efficiency and propose optimal operating methods.

[1797] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1798] Step 1:

[1799] The server randomly generates employee skill sets. Specifically, it uses Python random functions to randomly assign skills such as "assembly," "quality control," "maintenance," and "logistics" to each employee. The input requires the number of employees and a list of skill sets, and the output is the generated skill set for each employee.

[1800] Step 2:

[1801] The server simulates the factory's operational efficiency based on the generated skill sets. Specifically, it aggregates the skill sets of each employee and calculates the production efficiency of the entire factory. The input is the skill set of each employee, and the output is the operational efficiency of the entire factory.

[1802] Step 3:

[1803] The server generates optimization proposals for factory operations based on the simulation results. Specifically, it uses a generative AI model to present specific methods and strategies for maximizing operational efficiency. Simulation results are required as input, and optimization proposals are obtained as output.

[1804] Step 4:

[1805] The server presents the optimization proposal to the user by sending the generated proposal to the user's terminal for the user to review. As input, an optimization proposal is required, and as output, a proposal is obtained that is displayed on the user's terminal.

[1806] Step 5:

[1807] The user implements improvements to factory operations based on the presented optimization proposals. Specifically, the user applies the proposed methods and strategies to actual factory operations and confirms their effectiveness. The input is the optimization proposals, and the output is the improved factory operations.

[1808] Example 3

[1809] Next, a third embodiment of the third embodiment will be described. 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".

[1810] Conventional organizational management simulation systems did not sufficiently simulate operations using generative artificial intelligence, making it difficult to evaluate the effectiveness of strategies in actual operations in advance. In addition, they lacked the functionality to effectively utilize past operational data and market data and propose specific improvement measures based on simulation results. As a result, organizational management efficiency and strategy optimization were not fully achieved.

[1811] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1812] In this invention, the server includes a means for assigning job titles and work contents of each department to a plurality of generative AIs and having the AIs converse with each other to operate the organization, a means for confirming whether the organization can be appropriately managed based on a huge data backbone, a means for collecting past operational data and market data, a means for simulating a simulated organization operation using a generative AI model based on the collect...

Claims

1. A means for assigning a position in an organization and a plurality of business contents included in the organization to each of the plurality of generated AIs, and having the plurality of generated AIs converse with each other to operate the organization; A means to confirm whether organizational management can be carried out based on the data that forms the basis of the system, An analysis means for inputting a scenario of a simulated organizational management input by a user into a generating AI model, and analyzing the results of the simulated organizational management; an emotion engine that recognizes the user's emotions; A means for inputting a specific prompt sentence into a generative AI model, and for identifying problems in the organization based on the results of the simulated organization management by the analysis means and the emotions, and for proposing solutions to the identified problems; a means for feeding back said emotions to a simulation engine to reinforce successful strategies of said organization and to correct unsuccessful strategies of said organization; A system including:

2. 2. The system according to claim 1, further comprising a means for performing a simulated production line operation and providing consulting for improving production efficiency based on the results of said production line operation.

3. 2. The system according to claim 1, further comprising means for analyzing the cause of failure of the strategy for acquiring new customers and proposing a remedy if the strategy proves unsuccessful as a result of said simulated organizational management.

Images