System

Abstract

To provide systems.SOLUTION: A system includes: first means of: receiving input of a prompt sentence for simulating a business negotiation making a proposal of a new product by a user; second means of inputting the prompt sentence to a generative AI model, to generate a dialogue content with the user; third means of transmitting the generated dialogue content to the user terminal; fourth means of acquiring a reply of the user to the dialogue content; fifth means of feeding back the user with a result of the simulation on the basis of the reply of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the past, in order to conduct a simulation that utilized the knowledge and experience of a specific person, the cooperation of that person was required. However, even if that person actually existed, that person's time and resources were limited, making it difficult to handle all simulations. In addition, there were cases where that person no longer existed or where direct cooperation was difficult. [Means for solving the problem]

[0005] The present invention provides a system that uses generative AI to perform various simulations while assuming the role of a specific person. This system includes a means for proposing tactics and training menus based on the knowledge and experience of a specific person, and a means for simulating the behavior of a specific person. Furthermore, it also includes a means for simulating the performance of a specific person after joining the company or after being transferred based on information such as a resume and aptitude test results, based on the specific person's knowledge and experience, and a means for simulating conversations with business partners or complainers while assuming the role of a specific person. This makes it possible to perform simulations that utilize the knowledge and experience of a specific person without the direct cooperation of that person. [Brief explanation 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. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 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. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

[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 a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] One embodiment of the present invention is a system in which a generative AI plays the role of a specific person and performs various simulations. This system includes a means for proposing tactics and training programs based on the knowledge and experience of the specific person, and a means for simulating the behavior of the specific person. For example, in the sports industry, even if there is no professional coach, it is possible for players to freely select an actual professional coach and have them suggest tactics and training programs.

[0029] "Example 2"

[0030] Furthermore, it also includes a means of simulating the performance of a specific person after joining the company or after being transferred, based on the knowledge and experience of that person, information such as resumes and aptitude test results. For example, in the human resources industry, it is possible to simulate the performance of a person after joining the company or after being transferred, based on information such as resumes and aptitude test results, during job hunting or transfer interviews.

[0031] "Example 3"

[0032] It also includes a means of simulating conversations with a business partner or a complainer by pretending to be a specific person. For example, when practicing business negotiations or complaint handling, generative AI can pretend to be the business partner or the complainer and simulate actual conversations. This allows for practice of actual business negotiations or complaint handling, and the results can be used to identify areas for improvement.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: A user accesses the system and selects a specific person.

[0036] Step 2: The system uses generative AI to immerse itself in the role of the selected person, based on their knowledge and experience.

[0037] Step 3: When the user starts the simulation, the generative AI will suggest tactics and training menus based on the specific person's knowledge and experience.

[0038] "Example 2"

[0039] Step 1: A user accesses the system and enters information about a specific person, such as their resume and aptitude test results.

[0040] Step 2: The system uses generative AI to immerse itself in the role of a specific person based on the input information and their knowledge and experience.

[0041] Step 3: When the user starts the simulation, the generative AI simulates the employee's performance after joining the company or after being transferred.

[0042] "Example 3"

[0043] Step 1: The user accesses the system and enters a dialogue scenario between a specific person and a business partner or complainant.

[0044] Step 2: Based on the input scenario and the specific person's knowledge and experience, the system uses generative AI to immerse itself in that role.

[0045] Step 3: When the user starts the simulation, the generative AI simulates a conversation with a business partner or a complainant.

[0046] Example 1

[0047] 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 device 14 will be referred to as a "terminal."

[0048] With conventional simulation systems, it was difficult to propose tactics or training menus based on the knowledge and experience of a specific person, and they were not able to realistically simulate the behavior of a specific person. As a result, there were issues with not being able to carry out effective learning and training when there was no specialized coach or when the player wanted to learn the behavior of a specific person.

[0049] 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.

[0050] In this invention, the server includes a means for a user to input information about a specific person using a terminal, a means for the server to acquire data about the specific person from a database, a means for the server to preprocess the acquired data and convert it into a format that can be input to a generative AI model, a means for the server to execute a simulation using the generative AI model, and a means for the server to transmit the simulation results to the terminal and display them to the user. This makes it possible to propose tactics and training menus based on the knowledge and experience of a specific person, and to realistically simulate the behavior of a specific person.

[0051] "Generative AI" is an artificial intelligence that performs simulations based on the knowledge and experience of a specific person and suggests tactics and training menus.

[0052] A "specific person" is an individual for whom the system will perform simulations and suggestions, such as a professional coach or expert.

[0053] "Simulation" is the process of virtually reproducing the actions and tactics of a specific person and providing the results to the user.

[0054] "Tactics" refers to the optimal action or plan in a particular situation, especially strategic behavior in sports and business.

[0055] A "practice menu" is a series of exercises or training sessions designed to achieve a specific goal.

[0056] "User" refers to an individual or organization that uses the system to learn from the knowledge and experience of a specific person.

[0057] A "terminal" is a device that allows a user to access the system, input information, and receive results, and includes, for example, a personal computer or smartphone.

[0058] The "server" is the central computer of the system, and is the device that acquires data, pre-processes it, runs the simulation, and transmits the results.

[0059] A "database" is a repository of information that stores knowledge and experience data about a specific person and that can be accessed by a server as needed.

[0060] "Preprocessing" refers to the process of data cleaning and format conversion to convert acquired data into a format that can be input into a generative AI model.

[0061] A "generative AI model" is an artificial intelligence algorithm that performs simulations based on the knowledge and experience of a specific person, and includes, for example, GPT-4 (registered trademark).

[0062] "Simulation results" are the output data obtained after a generative AI model performs a simulation, and are information provided to the user.

[0063] This invention is a system that uses a generative AI model to perform various simulations by impersonating a specific person. This system includes a means for proposing tactics and training menus based on the knowledge and experience of the specific person, and a means for simulating the behavior of the specific person.

[0064] Hardware and software used

[0065] Server: The central computer of the system, which acquires data, preprocesses it, runs simulations, and transmits the results. Specifically, it uses a database management system (e.g., MySQL®) and a generative AI model (e.g., GPT-4).

[0066] Terminal: A device that allows a user to access the system, input information, and receive results. Examples include computers and smartphones.

[0067] Data processing and calculation

[0068] 1. User input:

[0069] A user accesses the system using a terminal and inputs information about a specific person, for example, a prompt such as "Please tell me the tactics of a specific professional coach."

[0070] 2. Data Acquisition:

[0071] The server receives input from the user and retrieves data related to a specific person from a database. For example, the server connects to a MySQL database and queries for tactics and training data related to a "specific professional coach."

[0072] 3. Data preprocessing:

[0073] The server preprocesses the acquired data. Specifically, it cleans the data and converts its format so that it can be input into a generative AI model. For example, it removes unnecessary spaces and special characters from text data and converts it to JSON format.

[0074] 4. Run the simulation:

[0075] The server inputs the preprocessed data into a generative AI model and runs a simulation. The generative AI model generates a response to the user's prompt based on the knowledge and experience of a specific person. For example, the generative AI model simulates "what tactics a specific professional coach will propose in the next game" and generates the results.

[0076] 5. Result output:

[0077] The server sends the simulation results obtained from the generative AI model to the device. The device then displays the received results to the user. For example, the device screen might say, "A specific professional coach suggests a 4-3-3 formation for the next match."

[0078] Examples of concrete examples and prompts

[0079] Consider the case where the user is an athlete and wants to learn the tactics of a particular professional coach.

[0080] Examples:

[0081] A user accesses the system using a terminal and inputs that he or she would like to learn the tactics of a particular professional coach.

[0082] The server retrieves data about the knowledge and experience of specific professional coaches from a database and inputs it into a generative AI model.

[0083] The server uses a generative AI model to simulate what tactics a specific professional coach would propose and displays the results to the user.

[0084] Example prompt sentence:

[0085] "Tell me what tactics a particular professional coach would suggest for the next game."

[0086] In this way, users can learn the tactics and training regimens of a particular professional coach.

[0087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0088] Step 1:

[0089] A user accesses the system using a terminal and inputs information about a specific person. Specifically, the user enters a prompt such as "Please tell me the tactics of a specific professional coach" into the input form on the terminal and clicks the submit button. The input data is in the form of text containing questions or requests about a specific person.

[0090] Step 2:

[0091] The server receives input from the user and retrieves data related to a specific person from the database. Specifically, the server connects to a MySQL database and queries data on tactics and training menus related to a "specific professional coach." The input is the user's prompt, and the output is the data related to the specific person retrieved from the database.

[0092] Step 3:

[0093] The server preprocesses the acquired data. Specifically, it cleans the data and converts its format so that it can be input into a generative AI model. For example, it removes unnecessary spaces and special characters from text data and converts it into JSON format. The input is raw data acquired from the database, and the output is preprocessed data.

[0094] Step 4:

[0095] The server inputs the preprocessed data into a generative AI model and runs a simulation. The generative AI model generates a response to a user prompt based on the knowledge and experience of a specific person. For example, the generative AI model simulates "what tactics a specific professional coach will propose in the next game" and generates the results. The input is the preprocessed data, and the output is the simulation result generated by the generative AI model.

[0096] Step 5:

[0097] The server sends the simulation results obtained from the generative AI model to the device. The device then displays the received results to the user. For example, the device screen may display a message such as, "A specific professional coach suggests a 4-3-3 formation for the next game." The input is the simulation results from the generative AI model, and the output is the information displayed to the user.

[0098] (Application example 1)

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

[0100] Conventional industrial robots have difficulty optimizing their movements and work procedures by utilizing the knowledge and experience of specific workers. As a result, efficient work procedures were not adequately proposed or optimized, limiting productivity improvements. In addition, there were limited means to transfer the knowledge and experience of skilled workers to new workers, making it difficult to pass on skills. To solve these issues, a system is needed that utilizes the knowledge and experience of specific workers to optimize the movements and work procedures of industrial robots.

[0101] 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.

[0102] In this invention, the server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and practice menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to optimize the operation and work procedures of the industrial robot based on the knowledge and experience of the specific worker. This makes it possible to optimize the operation and work procedures of the industrial robot by utilizing the knowledge and experience of the specific worker, thereby improving productivity and enabling the transfer of technology.

[0103] "Generative AI" is an artificial intelligence system that imitates the knowledge and experience of a specific person and performs various simulations.

[0104] A "specific person" refers to an individual person with knowledge and experience, whose actions and thoughts are to be imitated.

[0105] "Simulation" is a method of virtually recreating real-world situations and behaviors to make predictions and analyses.

[0106] "Tactics" refers to specific methods or means for achieving a specific goal.

[0107] A "practice menu" refers to planned training content designed to improve specific skills or abilities.

[0108] "Behavior" refers to the specific actions or reactions taken by a particular person.

[0109] "Worker" refers to a person who performs a specific task or work.

[0110] An "industrial robot" refers to an automated mechanical device used in factories and production lines.

[0111] "Action" refers to the specific movements or operations performed by machines or humans.

[0112] A "work procedure" refers to a series of procedures or methods for efficiently performing a specific task.

[0113] "Optimization" refers to adjusting something to maximize efficiency or effectiveness in order to achieve a specific purpose.

[0114] As an embodiment of the present invention, the following system is constructed.

[0115] System Configuration

[0116] The server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and training menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to optimize the operation and work procedures of an industrial robot based on the knowledge and experience of a specific worker.

[0117] Program processing explanation

[0118] The server implements a generative AI model using Python (registered trademark) and uses the OpenAI (registered trademark) API to generate optimal work procedures based on the knowledge and experience of specific workers. Specifically, it performs the following processes:

[0119] 1. Data entry: The user enters the name of a specific worker and the task.

[0120] 2. Prompt generation: The server generates a prompt sentence for the generative AI model based on the input data.

[0121] 3. Calling the AI ​​model: The server uses OpenAI's API to send prompts to the generative AI model to generate optimal work procedures.

[0122] 4. Result output: The server outputs the generated optimal work procedure to the user.

[0123] Hardware and software used

[0124] Hardware: Industrial robots (e.g., KUKA®, Fanuc®, etc.), computers (for robot control)

[0125] Software: Python, OpenAI API

[0126] Specific examples

[0127] For example, when optimizing the assembly of parts based on the knowledge and experience of skilled worker A, the following prompt sentence is generated.

[0128] Prompt Sentence Examples

[0129] Based on the knowledge and experience of skilled worker A, optimize the following tasks.

[0130] Work: Assembly of parts

[0131] Please suggest the best procedure.

[0132] In this way, it is possible to utilize the knowledge and experience of specific workers to optimize the movements and work procedures of industrial robots, thereby improving productivity and ensuring the succession of skills.

[0133] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0134] Step 1:

[0135] The user inputs the name of a specific worker and the task.

[0136] Input: Name of specific worker (e.g., skilled worker A), work content (e.g., parts assembly work)

[0137] Output: Input data (specific worker name, work content)

[0138] Specific operation: The user uses the terminal to enter the name of a specific worker and the work content into the input form and presses the submit button.

[0139] Step 2:

[0140] The server generates a prompt sentence for the generative AI model based on the input data.

[0141] Input: Data entered by the user (name of specific worker, work content)

[0142] Output: Generated prompt statement

[0143] Specific operation: The server receives the input data and generates a prompt like the following: "Based on the knowledge and experience of skilled worker A, please optimize the following task. Task: assembling parts. Please suggest the optimal work procedure."

[0144] Step 3:

[0145] The server uses OpenAI's API to send prompts to the generative AI model to generate optimal work procedures.

[0146] Input: Generated prompt text

[0147] Output: Response from the generative AI model (optimal work procedure)

[0148] How it works: The server sends the generated prompt to OpenAI's API and receives a response from the generative AI model, which includes the optimal work procedure.

[0149] Step 4:

[0150] The server outputs the generated optimal work procedure to the user.

[0151] Input: Response from the generative AI model (optimal work procedure)

[0152] Output: The optimal workflow displayed to the user

[0153] Specific operation: The server sends the optimal work procedure received from the generative AI model to the user's device and displays it on the user's screen.

[0154] Example 2

[0155] Next, a description will be given of 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."

[0156] With conventional talent evaluation systems, it was difficult to predict future performance based on a candidate's resume and aptitude test results. Furthermore, there was a lack of a way to utilize a specific person's knowledge and experience to simulate how they would perform after joining the company or being transferred. This made it difficult for companies to make appropriate personnel placement and hiring decisions, resulting in problems such as a decline in organizational efficiency and productivity.

[0157] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for a user to input candidate information, a means for a terminal to transmit the input data to the server, a means for the server to store the received data in a database, a means for the server to use a generative AI model to analyze the stored data, a means for the server to execute a simulation based on the analysis results, a means for the server to transmit the simulation results to the terminal, and a means for the terminal to display the results to the user. This makes it possible to predict future performance based on the candidate's resume and aptitude test results, allowing companies to make appropriate personnel placement and hiring decisions.

[0158] "Generative AI" is an artificial intelligence system that performs simulations based on the knowledge and experience of a specific person.

[0159] "User" means a person or organization that utilizes the system to enter candidate information.

[0160] A "terminal" is a device through which a user inputs information and displays simulation results.

[0161] A "server" is a computer system that receives, stores, analyzes, and runs simulations on data submitted by users.

[0162] A "database" is an information management system for storing data received by a server.

[0163] A "generative AI model" is an artificial intelligence algorithm that analyzes data based on the knowledge and experience of a specific person and generates simulation results.

[0164] A "resume" is a document that lists information such as a candidate's educational background, work history, and skills.

[0165] "Aptitude test results" are the results of a test to evaluate a candidate's abilities and personality.

[0166] A "simulation" is a hypothetical experiment designed to predict a candidate's future performance under specific conditions.

[0167] A "prompt statement" is an instruction statement entered into a generative AI model to perform analysis or simulation.

[0168] This invention is a system that simulates the performance of a specific person after joining the company or after being transferred, based on the person's knowledge and experience, as well as information such as their resume and aptitude test results. The system is composed of users, terminals, and a server.

[0169] Hardware and software used

[0170] Hardware: Servers, terminals

[0171] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), aptitude testing tools (e.g., SHL)

[0172] Specific operation of the system

[0173] 1. Data Entry

[0174] The user inputs the candidate's resume and aptitude test results into the terminal. Specifically, the user enters the required information into the web form and clicks the "Submit" button.

[0175] 2. Data Transmission

[0176] The terminal sends the input data to the server. Specifically, the terminal uses an HTTP POST request to send the input data to the server.

[0177] 3. Data storage

[0178] The server saves the received data in the database. Specifically, the server connects to the MySQL database and saves the data using the INSERT statement.

[0179] 4. Data Analysis

[0180] The server uses a generative AI model (e.g., GPT-4) to analyze the stored data. Specifically, the server runs a Python script to input prompts to the GPT-4 model and obtain the analysis results.

[0181] Example prompt: "Based on this candidate's resume and aptitude test results, simulate their performance as a software engineer."

[0182] 5. Run the simulation

[0183] Based on the analysis results, the server simulates the employee's performance after joining the company or after being transferred. Specifically, the server runs a simulation algorithm based on the analysis results obtained from the generative AI model and calculates predicted performance.

[0184] 6. Send results

[0185] The server sends the simulation results to the terminal. Specifically, the server generates an HTTP response and sends JSON data containing the simulation results to the terminal.

[0186] 7. Results display

[0187] The terminal then displays the results to the user by parsing the received JSON data and displaying the results on a web page, for example, visualizing the candidate's predicted performance in graphs or text format.

[0188] Specific examples

[0189] For example, suppose a candidate is applying for a software engineer position. The user inputs the candidate's resume and aptitude test results into the system. The server receives this data and analyzes it using a generative AI model (GPT-4). Based on the analysis results, the server simulates the candidate's performance after joining the company and sends the predicted results to the device. The device then displays the results to the user.

[0190] In this way, the system can simulate the candidate's future performance based on the data entered by the user and provide the results to the user.

[0191] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0192] Step 1:

[0193] Data Entry

[0194] The user inputs the candidate's resume and aptitude test results into the terminal.

[0195] Input: Resume, aptitude test results

[0196] What happens: A user fills in information on a web form and clicks the "Submit" button.

[0197] Output: The input data is saved to the device.

[0198] Step 2:

[0199] Data transmission

[0200] The terminal transmits the input data to the server.

[0201] Input: Data entered by the user

[0202] Specific operation: The device sends the input data to the server using an HTTP POST request.

[0203] Output: Data is sent to the server.

[0204] Step 3:

[0205] Data storage

[0206] The server stores the received data in a database.

[0207] Input: Data sent from the terminal

[0208] What happens: The server connects to the MySQL database and saves the data using an INSERT statement.

[0209] Output: The data is saved to a database.

[0210] Step 4:

[0211] Data analysis

[0212] The server uses a generative AI model (e.g., GPT-4) to analyze the stored data.

[0213] Input: Data stored in the database

[0214] Specific operation: The server runs a Python script, inputs a prompt to the GPT-4 model, and obtains the analysis results.

[0215] Example prompt: "Based on this candidate's resume and aptitude test results, simulate their performance as a software engineer."

[0216] Output: Analysis results are generated.

[0217] Step 5:

[0218] Simulation execution

[0219] Based on the analysis results, the server simulates how the employee will perform after joining the company or being transferred.

[0220] Input: Analysis results obtained from the generative AI model

[0221] What happens: The server runs a simulation algorithm to calculate predicted performance.

[0222] Output: Simulation results are generated.

[0223] Step 6:

[0224] Send results

[0225] The server transmits the simulation results to the terminal.

[0226] Input: Simulation results

[0227] Specific operation: The server generates an HTTP response and sends JSON data containing the simulation results to the terminal.

[0228] Output: Data is sent to the terminal.

[0229] Step 7:

[0230] Results display

[0231] The terminal displays the results to the user.

[0232] Input: JSON data sent from the server

[0233] What it does: The device parses the received JSON data and displays the results on a web page, for example, visualizing the candidate's predicted performance in graphs or text format.

[0234] Output: The user can check the simulation results.

[0235] (Application example 2)

[0236] 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."

[0237] Conventional simulations of personnel placement and robot operation rely heavily on experience and intuition, making it difficult to find optimal placement and operation. Furthermore, simulations based on resumes and aptitude test results are time-consuming and labor-intensive when performed manually, and suffer from low accuracy. This has prevented efficient personnel placement and robot operation within factories, hindering productivity improvements.

[0238] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to propose tactics, practice menus, etc. based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to simulate optimal personnel allocation and robot operations in a factory based on the resume and aptitude test results of the specific person. This enables highly accurate simulations based on resumes and aptitude test results, thereby realizing efficient personnel allocation and robot operations in a factory.

[0239] "Generative AI" is an artificial intelligence system that imitates the knowledge and experience of a specific person and performs various simulations and suggestions.

[0240] "Simulation" is a method of virtually recreating real-world situations based on specific conditions and data, and making predictions and analyses.

[0241] A "resume" is a document that lists information such as an individual's educational background, work history, and skills, and is used when applying for a job or transferring.

[0242] "Aptitude test results" are the results of tests used to evaluate an individual's abilities, personality, and aptitude, and are used to determine job suitability and placement.

[0243] "Staffing" refers to the allocation of the most suitable personnel to each position within an organization.

[0244] "Robot movement" refers to the series of tasks and movements performed by robots used in factories.

[0245] "Tactics" refers to specific methods or means for achieving a specific goal.

[0246] A "practice menu" refers to a training program or plan to improve a particular skill or ability.

[0247] The system for implementing this invention uses generative AI to mimic the knowledge and experience of a specific person and perform various simulations and proposals. Specifically, it includes a function to simulate optimal personnel allocation and robot operation within a factory based on resumes and aptitude test results.

[0248] The server uses the following hardware and software:

[0249] Hardware: PC or smartphone

[0250] Software: Python, Pandas, Scikit-learn (registered trademark)

[0251] The server first reads resume and aptitude test result data from a CSV file. Then, it separates the data into features (years of experience, education level, skill score, etc.) and labels (performance). This allows for data preprocessing.

[0252] The server then trains a model using a random forest classifier, which is then used to simulate optimal staffing and robot behavior within a factory based on a specific person's knowledge and experience.

[0253] The user inputs the data of a new candidate and requests the server to run a simulation. The server uses the trained model to predict the new candidate's performance and proposes optimal personnel placement and robot behavior.

[0254] As a concrete example, the following prompt sentence is input to the generative AI model:

[0255] "Based on the resume data of a new candidate, simulate the optimal placement within a factory. The candidate has 5 years of experience, an education level of 3, and a skill score of 85."

[0256] Using this prompt, the generative AI model can analyze candidate data and predict optimal placement and performance, leading to efficient personnel placement and robot operation within factories.

[0257] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0258] Step 1:

[0259] The server reads data such as resumes and aptitude test results from CSV files. The input is a CSV file, and the output is data in data frame format. Specifically, the CSV file is read using the Python Pandas library and converted to a data frame.

[0260] Step 2:

[0261] The server separates the data into features and labels. The input is data in data frame format, and the output is data separated into features (years of experience, education level, skill score, etc.) and labels (performance). Specifically, it extracts specific columns from the data frame and separates them into features and labels.

[0262] Step 3:

[0263] The server trains a model using a random forest classifier. The input is data divided into features and labels, and the output is a trained model. Specifically, it creates a random forest classifier using the Scikit-learn library and trains the model using the features and labels.

[0264] Step 4:

[0265] The user inputs data on a new candidate. The input data includes the new candidate's years of experience, education level, skill score, etc., and the output is a simulation request to the server. Specifically, the user inputs the new candidate's data using a smartphone or PC and sends it to the server.

[0266] Step 5:

[0267] The server uses the trained model to predict the performance of new candidates. The input is the new candidate's data, and the output is the predicted performance. Specifically, the server inputs the new candidate's data into the model and obtains the predicted result.

[0268] Step 6:

[0269] The server proposes optimal personnel placement and robot operation based on the prediction results. The input is predicted performance, and the output is a proposal for optimal personnel placement and robot operation. As a specific operation, the server analyzes the prediction results and proposes optimal placement and operation within the factory.

[0270] Step 7:

[0271] The user receives the proposals from the server and reflects them in the actual deployment of personnel and the operation of the robots. The input is the proposal from the server, and the output is the actual deployment and operation. In terms of specific operations, the user checks the proposals and adjusts the deployment and operation of the robots within the factory.

[0272] Example 3

[0273] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0274] Conventional simulation systems have limited functionality for interacting with specific people, making it difficult to simulate situations that closely resemble real situations when practicing business negotiations or handling complaints. Furthermore, feedback on the simulation results is insufficient, making it difficult for users to identify areas for improvement. This has led to the issue of users being unable to fully improve their skills.

[0275] 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.

[0276] In this invention, the server includes: means for a generative AI to pretend to be a specific person and perform various simulations; means for the generative AI to propose tactics, practice menus, etc. based on the specific person's knowledge and experience; means for the generative AI to simulate the specific person's behavior; means for a user to access the system using a terminal and input a prompt; means for the server to call the generative AI model and generate dialogue content based on the prompt; means for the server to send the generated dialogue content to the user's terminal; means for the user to perform dialogue simulation; and means for the server to provide feedback on the simulation results. This allows the user to perform simulations that are similar to actual business negotiations or complaint handling and to identify areas for improvement based on the results.

[0277] "Generative AI" is artificial intelligence that can take on the role of a specific person and simulate conversations and actions.

[0278] A "prompt sentence" is text that a user enters to specify a simulation scenario.

[0279] A "server" is a computer system that hosts a generative AI model and processes requests from users.

[0280] A "terminal" is a device such as a PC or smartphone that a user uses to access the system.

[0281] "Dialogue content" refers to the simulated conversation content generated by the generative AI based on the prompt text.

[0282] "Feedback" refers to information on improvements and evaluations that are provided to users after analyzing the results of the simulation.

[0283] A "simulation" is the reproduction of hypothetical interactions and behaviors that a generative AI performs based on a specific scenario.

[0284] "Knowledge and experience" refers to the specialized information that a particular person possesses and the skills and know-how based on past achievements.

[0285] "Tactics and training menus" are specific action plans and training contents proposed by generative AI.

[0286] This invention is a system that uses generative AI to simulate a conversation with a specific person, such as a business partner or a complainer. Specific embodiments of this system are described below.

[0287] Hardware and software used

[0288] server:

[0289] The server hosts the generative AI model and processes requests from users. Specifically, OpenAI's GPT-4 is used as the generative AI model. The server sends prompts received from users to the generative AI model and sends the generated dialogue content to the user's device.

[0290] Device:

[0291] A terminal is a device that a user uses to access the system. It can be a PC, a smartphone, or other device. The terminal accesses the server through a web browser and provides an interface for entering prompts.

[0292] User:

[0293] The user uses the system to simulate business negotiations and complaint handling. The user accesses the system using a terminal and inputs prompt statements.

[0294] Data processing and calculation

[0295] Enter the prompt statement:

[0296] The user inputs a prompt statement that corresponds to the scenario they want to simulate. For example, they might input something like, "I would like to simulate a business negotiation in which a new product is proposed. I would like the business partner to ask detailed questions about the product's features and price."

[0297] Invoke the generative AI model:

[0298] The server sends the prompt received from the user to the generative AI model, which then generates dialogue content based on the prompt. The generated dialogue content is then sent to the user's device via the server.

[0299] Conducting a dialogue simulation:

[0300] The user then proceeds through the simulation based on the generated dialogue, asking and answering questions during the dialogue, practicing actual business negotiations and handling complaints.

[0301] Providing feedback:

[0302] After the simulation is completed, the server analyzes the results and provides feedback to the user, who can then use this feedback to identify areas for improvement.

[0303] Specific examples

[0304] If a user wants to simulate a business negotiation in which a new product proposal is made, he or she enters the following prompt sentence:

[0305] Example prompt sentence:

[0306] "I'd like to simulate a business negotiation in which I propose a new product. I'd like the other party to ask detailed questions about the product's features and price."

[0307] When this prompt is entered, the generative AI model plays the role of a salesperson and starts a simulation in which the user proposes a new product. The generative AI model asks questions about the product's features and price, and the user answers them, allowing the model to practice a real sales negotiation.

[0308] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0309] Step 1:

[0310] A user accesses the system

[0311] A user accesses the system's web application using a terminal (PC or smartphone). The user enters authentication information on the login screen and logs in to the system.

[0312] Input: Username and Password

[0313] Output: Successful login to the system message

[0314] Specific behavior:

[0315] The user opens a browser and enters the system's URL.

[0316] The user enters their username and password on the login screen and clicks the "Login" button.

[0317] Step 2:

[0318] The user enters a prompt statement

[0319] The user inputs a prompt statement according to the scenario they want to simulate, such as "I would like to simulate a business negotiation in which a new product proposal is made."

[0320] Input: prompt statement

[0321] Output: Prompt statement sending confirmation message

[0322] Specific behavior:

[0323] The user moves to the simulation screen and enters a prompt sentence in the text box.

[0324] The user clicks the "Submit" button.

[0325] Step 3:

[0326] The server invokes the generative AI model

[0327] The server sends the prompt received from the user to the generative AI model, which then generates dialogue content based on the prompt.

[0328] Input: prompt statement

[0329] Output: Generated dialogue

[0330] Specific behavior:

[0331] The server receives the prompt and sends a request to the API of the generative AI model.

[0332] The generative AI model analyzes the prompt and generates the dialogue content.

[0333] Step 4:

[0334] The server sends the generated dialogue to the user

[0335] The server receives the dialogue content from the generative AI model and sends it to the user's device, where the user receives it and starts the dialogue simulation.

[0336] Input: Generated dialogue

[0337] Output: The dialogue displayed on the user's device

[0338] Specific behavior:

[0339] The server receives the generated dialogue content and transmits it to the user's terminal.

[0340] The user's terminal displays the contents of the conversation.

[0341] Step 5:

[0342] The user performs an interactive simulation

[0343] The user proceeds through the simulation based on the generated dialogue content, asking and answering questions during the dialogue, practicing actual business negotiations and handling complaints.

[0344] Input: Generated dialogue, user responses

[0345] Output: The progress of the conversation

[0346] Specific behavior:

[0347] The user reads the dialogue and enters an appropriate response.

[0348] The user clicks the "Submit" button and continues the conversation.

[0349] Step 6:

[0350] The server feeds back the simulation results

[0351] After the simulation is completed, the server provides the user with feedback on the results of the simulation, allowing the user to identify areas for improvement.

[0352] Input: Simulation log

[0353] Output: Feedback content

[0354] Specific behavior:

[0355] The server analyzes the simulation logs and generates feedback.

[0356] The server sends the feedback to the user's terminal.

[0357] Users review feedback and identify areas for improvement.

[0358] (Application example 3)

[0359] 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."

[0360] With conventional simulation systems, it was difficult to practice sales negotiations or handling complaints while pretending to be a specific person, making it difficult to improve staff ability to respond in real situations. Furthermore, there was a lack of evaluation of complaint handling and feedback on areas for improvement, limiting the ability to improve staff skills. This resulted in a decline in the quality of customer service in brick-and-mortar stores, making it difficult to improve customer satisfaction.

[0361] 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.

[0362] In this invention, the server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and practice menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to simulate handling of complaints and provide feedback on the response evaluation and areas for improvement. This enables staff at physical stores to practice handling realistic complaints and improve their response skills.

[0363] "Generative AI" is an artificial intelligence that imitates the knowledge and behavior of a specific person and performs various simulations.

[0364] "Simulation" is a method of virtually recreating a specific situation or environment and attempting to act or react within it.

[0365] "Tactics" are specific methods or plans for achieving a specific purpose.

[0366] A "practice menu" is a series of exercises designed to improve a particular skill or ability.

[0367] "Complaint handling" refers to the actions taken to appropriately respond to customer complaints and dissatisfaction and resolve the issues.

[0368] "Evaluation" is the act of judging the value or effectiveness of a particular action or result.

[0369] "Feedback" is the act of communicating areas for improvement or evaluation of specific actions or results.

[0370] A "brick and mortar store" is a store that exists in a physical location and where customers can visit in person to purchase goods or services.

[0371] The following system configuration is used as an embodiment of this invention: The system is composed of a server equipped with generative AI, a terminal (such as a smartphone) operated by the user, and necessary software.

[0372] The server includes a means for the generative AI to pretend to be a specific person and perform various simulations, a means for the generative AI to suggest tactics and training menus based on the knowledge and experience of a specific person, a means for the generative AI to simulate the actions of a specific person, and a means for the generative AI to simulate handling of a complaint and provide feedback on the response and areas for improvement.

[0373] A dedicated application is installed on the device operated by the user. This application provides an interface for the user to input the details of the complaint and has the function of sending the input information to a server. The server uses generative AI based on the received information to generate a dialogue that plays the role of the complainant and sends the result back to the device.

[0374] Specifically, a user inputs the details of a complaint into the application, such as "The product was broken and I would like to return it." The server receives this information and uses generative AI to generate a dialogue for the complainant, such as "This product broke immediately. I would like to return it. What should I do?" This dialogue is displayed on the device, allowing the user to practice responding to it.

[0375] The hardware used is a smartphone (iOS (registered trademark) or ANDROID (registered trademark)), and the software uses Python and OpenAI API, which enables the generative AI to simulate realistic complaint handling and provide feedback to the user on evaluations and areas for improvement.

[0376] An example of a prompt is as follows:

[0377] "You are a complainer. Please file a complaint in the following situation: I would like to return the product because it was broken."

[0378] In this way, store staff can practice dealing with real complaints and improve their response skills.

[0379] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0380] Step 1:

[0381] The user starts the application on the terminal and inputs the status of the complaint.

[0382] Input: Complaint status (e.g., "The product was broken and I would like to return it.")

[0383] Output: Status data of the entered complaint

[0384] Step 2:

[0385] The terminal transmits the entered complaint status data to the server.

[0386] Input: Claim status data

[0387] Output: Claim status data sent to the server

[0388] Step 3:

[0389] Based on the complaint status data received by the server, a prompt sentence is generated for the generative AI.

[0390] Input: Claim status data

[0391] Output: Generated prompt (e.g. "You are a complainer. Please complain in the following situation: I would like to return the product because it was broken.")

[0392] Step 4:

[0393] The server uses generative AI to generate dialogue for the complainer based on the generated prompt text.

[0394] Input: Generated prompt text

[0395] Output: Generated dialogue of the complainant (e.g., "This item broke immediately. I would like to return it. What should I do?")

[0396] Step 5:

[0397] The server transmits the generated dialogue of the complainer to the terminal.

[0398] Input: Generated dialogue for the complainer

[0399] Output: The complainer's dialogue sent to the terminal

[0400] Step 6:

[0401] The terminal displays the received dialogue of the complainer to the user.

[0402] Input: Received complaint dialogue

[0403] Output: The complainer's dialogue displayed to the user

[0404] Step 7:

[0405] The user responds to the dialogue of the complainer and inputs the response into the terminal.

[0406] Input: User response (e.g. "I'm sorry. We will process your return.")

[0407] Output: Input response data

[0408] Step 8:

[0409] The terminal transmits the inputted correspondence content data to the server.

[0410] Input: Response content data

[0411] Output: Response data sent to the server

[0412] Step 9:

[0413] Based on the response content data received by the server, the generative AI generates an evaluation of the response and areas for improvement.

[0414] Input: Response content data

[0415] Output: Generated assessment and improvements

[0416] Step 10:

[0417] The server sends the generated ratings and improvements to the device.

[0418] Input: Generated ratings and improvements

[0419] Output: Ratings and improvements sent to the device

[0420] Step 11:

[0421] The device displays the received ratings and improvements to the user.

[0422] Input: Received ratings and improvements

[0423] Output: User-visible rating and improvements

[0424] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0425] "Example 1"

[0426] The invention described in claim 4 combines a system including a means for a generative AI to pretend to be a specific person and perform various simulations, a means for the generative AI to suggest tactics and practice menus based on the specific person's knowledge and experience, and a means for the generative AI to simulate the specific person's behavior, with an emotion engine that recognizes the user's emotions. Specifically, a user accesses the system and selects a specific person. The system then uses the generative AI to pretend to be that person based on the selected person's knowledge and experience. Furthermore, the system incorporates an emotion engine that recognizes the user's emotions, and when the user starts a simulation, the generative AI suggests tactics and practice menus based on the specific person's knowledge and experience. In this case, the emotion engine recognizes the user's emotions and adjusts the generative AI's suggestions based on those emotions.

[0427] "Example 2"

[0428] The invention described in claim 5 is a system that combines an emotion engine that recognizes user emotions with a system that includes a means for a generative AI to simulate a specific person's performance after joining the company or after a transfer based on information such as a resume and aptitude test results, based on the person's knowledge and experience. Specifically, a user accesses the system and inputs information about the specific person, such as a resume and aptitude test results. The system utilizes the generative AI to become that person based on the input information and the specific person's knowledge and experience. Furthermore, the system is equipped with an emotion engine that recognizes user emotions, and when the user starts a simulation, the generative AI simulates the person's performance after joining the company or after a transfer. In this case, the emotion engine recognizes the user's emotions and adjusts the generative AI's simulation results based on those emotions.

[0429] "Example 3"

[0430] The invention described in claim 6 combines a system including a means for a generative AI to pretend to be a specific person and simulate a dialogue with a business partner or a complainer, with an emotion engine that recognizes the user's emotions. Specifically, a user accesses the system and inputs a dialogue scenario between a specific person and a business partner or a complainer. Based on the input scenario and the specific person's knowledge and experience, the system utilizes the generative AI to pretend to be that person. Furthermore, the system is equipped with an emotion engine that recognizes the user's emotions, and when the user starts a simulation, the generative AI simulates a dialogue with a business partner or a complainer. At this time, the emotion engine recognizes the user's emotions and adjusts the generative AI's simulation results based on those emotions.

[0431] The processing flow of each embodiment will be described below.

[0432] "Example 1"

[0433] Step 1: A user accesses the system and selects a specific person.

[0434] Step 2: The system uses generative AI to immerse itself in the role of the selected person, based on their knowledge and experience.

[0435] Step 3: When the user starts the simulation, the generative AI will suggest tactics and training menus based on the specific person's knowledge and experience.

[0436] Step 4: The emotion engine recognizes the user's emotions and adjusts the generative AI's suggestions based on those emotions.

[0437] "Example 2"

[0438] Step 1: A user accesses the system and enters information about a specific person, such as their resume and aptitude test results.

[0439] Step 2: The system uses generative AI to immerse itself in the role of a specific person based on the input information and their knowledge and experience.

[0440] Step 3: When the user starts the simulation, the generative AI simulates the employee's performance after joining the company or after being transferred.

[0441] Step 4: The emotion engine recognizes the user's emotions and adjusts the generative AI simulation results based on those emotions.

[0442] "Example 3"

[0443] Step 1: The user accesses the system and enters a dialogue scenario between a specific person and a business partner or complainant.

[0444] Step 2: Based on the input scenario and the specific person's knowledge and experience, the system uses generative AI to immerse itself in that role.

[0445] Step 3: When the user starts the simulation, the generative AI simulates a conversation with a business partner or a complainant.

[0446] Step 4: The emotion engine recognizes the user's emotions and adjusts the generative AI simulation results based on those emotions.

[0447] Example 1

[0448] 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 device 14 will be referred to as a "terminal."

[0449] Conventional generative AI systems can suggest tactics and training menus based on the knowledge and experience of a specific person, but they have the problem of not being able to make suggestions that take the user's emotions into account. This has led to the problem that they are unable to make optimal suggestions based on the user's condition, making it difficult to achieve effective simulations and training.

[0450] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for a generative AI to pose as a specific person and perform various simulations, a means for the generative AI to propose tactics, training menus, etc. based on the knowledge and experience of the specific person, a means for the generative AI to simulate the behavior of the specific person, and a means for adjusting the generative AI's proposals based on the user's emotions by combining an emotion engine that recognizes the user's emotions. This enables optimal proposals that take the user's emotions into consideration, resulting in more effective simulations and training.

[0451] "Generative AI" is artificial intelligence that mimics the knowledge and experience of a specific person and generates responses and suggestions by impersonating that person.

[0452] "Simulation" is a method of virtually recreating specific situations or conditions and predicting and analyzing the actions and results that would occur within them.

[0453] "Tactics" are specific methods or plans for achieving a specific purpose.

[0454] A "practice menu" is specific training content designed to improve a particular skill or ability.

[0455] An "emotion engine" is software or hardware for recognizing a user's emotions and analyzing the emotion data.

[0456] "Adjusting suggestions" means changing and optimizing the responses and suggestions provided by generative AI based on the user's emotions and state.

[0457] "User" means an individual or organization that uses the system.

[0458] A "server" is a computer that is the core of the system and is a device that includes hardware and software for executing various functions, including generative AI and emotion engines.

[0459] MODE FOR CARRYING OUT THE INVENTION

[0460] This invention is a system in which a generative AI takes on the role of a specific person and performs various simulations. A specific embodiment of this system is described below.

[0461] System configuration

[0462] 1. Hardware and Software Configuration

[0463] Server: The central computer of the system, including the hardware and software required to run the generative AI model and emotion engine. Specifically, a server equipped with a high-performance processor and large memory capacity is required.

[0464] Terminal: A device used by a user to access the system, such as a PC or smartphone. The system is accessed using a web browser (e.g., GOOGLE CHROME (registered trademark), Mozilla Firefox (registered trademark)).

[0465] Generative AI model: An artificial intelligence model that imitates the knowledge and experience of a specific person, specifically OpenAI's GPT-4.

[0466] Emotion engine: Software or hardware for recognizing the user's emotions. Specifically, the emotion recognition API from Affectiva (registered trademark) is used.

[0467] 2. Data processing and calculation

[0468] User access: The user accesses the system using a terminal and selects a specific person. The information of the selected person is sent to the server.

[0469] Activating the generative AI: The server retrieves the profile data of the selected person and activates the generative AI model, which generates responses and suggestions based on the selected person's knowledge and experience.

[0470] Emotion Recognition: The server uses the emotion engine to analyze the user's facial expressions and voice data in real time to recognize their emotional state. The recognized emotion data is sent to the server.

[0471] Suggestion Adjustment: The server uses generative AI to suggest tactics and practice exercises to the user, and these suggestions are adjusted taking into account the user's emotional data.

[0472] Specific examples

[0473] Let's say a user is looking for a basketball training menu. The user accesses the system and selects a professional basketball coach. The generative AI then immerses itself in the role of the coach, recognizing the user's emotions and suggesting an appropriate training menu.

[0474] Example prompt sentence:

[0475] "I'm a basketball player and I'd like to know what kind of training routine is most effective for my next game. As a professional basketball coach, please suggest the best training routine for me."

[0476] In this way, the user can utilize the knowledge and experience of a specific person and receive appropriate suggestions according to their emotions.

[0477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0478] Step 1:

[0479] A user accesses the system.

[0480] Specific operations: The user uses a device (PC, smartphone, etc.) to open a web browser (Google (registered trademark) Chrome, Mozilla Firefox, etc.).

[0481] Input: User login information (username, password).

[0482] Data processing: The server authenticates the user's login information.

[0483] Output: If authentication is successful, the user can access the main screen of the system.

[0484] Step 2:

[0485] The user selects a particular person.

[0486] Specific Actions: The user selects a specific person (e.g., a professional soccer coach) on the system interface using drop-down menus or the search function.

[0487] Input: The ID of the person selected by the user.

[0488] Data processing: The server retrieves the profile data of the selected person from the database.

[0489] Output: The profile data of the selected person is sent to the server.

[0490] Step 3:

[0491] The server activates a generative AI that takes on the role of the selected person.

[0492] Specific operation: The server retrieves the profile data of the selected person and launches a generative AI model (e.g., OpenAI's GPT-4).

[0493] Input: Profile data of the selected person.

[0494] Data processing: The server inputs the profile data into the generative AI, which prepares to generate a response based on the person's knowledge and experience.

[0495] Output: The generative AI is ready to mimic the tone and expertise of the selected person.

[0496] Step 4:

[0497] The server recognizes the user's emotions.

[0498] Specific operation: The server uses an emotion engine (e.g., Affectiva's emotion recognition API) to analyze the user's facial expressions and voice data in real time.

[0499] Input: User's facial expression and voice data.

[0500] Data processing: The emotion engine acquires data from the user's camera and microphone and recognizes their emotional state (e.g., joy, sadness, fatigue, etc.).

[0501] Output: The recognized emotion data is sent to the server.

[0502] Step 5:

[0503] The server will suggest tactics and training menus.

[0504] How it works: The server uses generative AI to suggest tactics and training options to the user, and these suggestions are adjusted based on the user's emotional data.

[0505] Input: User emotion data, selected person profile data.

[0506] Data processing: The server uses the emotion data to modify and optimize the responses and suggestions provided by the generative AI.

[0507] Output: The optimal tactics and training menus are suggested to the user based on their emotions.

[0508] (Application example 1)

[0509] Next, a description will be given of Application Example 1 of Embodiment 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."

[0510] Conventional generative AI systems can perform simulations based on the knowledge and experience of a specific person, but they cannot adjust their suggestions to take the user's emotions into account, making it difficult to reduce user stress and fatigue. Furthermore, in factory work environments, there is a need for efficient work procedures based on the knowledge and experience of skilled workers, but the lack of real-time feedback poses a challenge in that it is difficult to fully improve work efficiency.

[0511] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes: means for a generative AI to pretend to be a specific person and perform various simulations; means for the generative AI to suggest tactics, practice menus, etc. based on the specific person's knowledge and experience; means for the generative AI to simulate the specific person's behavior; means for an emotion engine to recognize a user's emotions and adjust the generative AI's suggestions based on those emotions; means for the generative AI to suggest work procedures and efficient work methods based on the knowledge and experience of a specific skilled worker; means for the emotion engine to recognize the worker's stress and fatigue and adjust the suggestions based on that; and means for providing feedback in real time. This makes it possible to adjust suggestions taking the user's emotions into consideration, thereby improving work efficiency and reducing stress and fatigue.

[0512] "Generative AI" is an artificial intelligence that performs simulations based on the knowledge and experience of a specific person and suggests tactics and training menus.

[0513] An "emotion engine" is a system that recognizes the user's emotions and adjusts the generative AI's suggestions based on those emotions.

[0514] A "specific person" is an individual who has the knowledge and experience that the generative AI will simulate.

[0515] "Simulation" is the process of virtually recreating the actions and tactics of a particular individual.

[0516] "Tactics" are specific methods or means for achieving a specific purpose.

[0517] A "practice menu" is a training program designed to improve a particular skill or ability.

[0518] A "work procedure" is a specific step or method for efficiently performing a specific task.

[0519] An "efficient work method" is a way of working that achieves maximum results with minimum time and effort.

[0520] "Real-time feedback" refers to evaluation and advice provided immediately while you work.

[0521] "Stress" refers to the mental or physical strain or tension felt by workers.

[0522] "Fatigue" refers to the physical or mental tiredness or exhaustion experienced by a worker.

[0523] A system for implementing this invention includes a generative AI, an emotion engine, and a real-time feedback function. A specific embodiment of this system will be described below.

[0524] System Configuration

[0525] The system uses the following hardware and software:

[0526] Hardware: Factory robots, emotion-recognition cameras

[0527] Software: OpenAI API, emotion_recognition library

[0528] Program processing

[0529] The server uses generative AI to suggest work procedures and efficient methods based on the knowledge and experience of specific skilled workers. The emotion engine recognizes the worker's stress and fatigue through an emotion-recognition camera and adjusts the generative AI's suggestions based on those emotions. Furthermore, by providing feedback in real time, it aims to improve work efficiency and reduce worker stress and fatigue.

[0530] Specific examples

[0531] For example, when a factory robot is tasked with assembling parts, a generative AI might suggest an efficient workflow using the following prompt:

[0532] You are Yamada, a skilled worker. Please suggest steps to efficiently perform the following tasks:

[0533] 1. Assembling the parts

[0534] 2. Inspection

[0535] 3. Packaging

[0536] If the emotion-aware camera detects that a worker is stressed or fatigued, the emotion engine will use that information to tailor its suggestions. For example, if a worker is feeling stressed, the generative AI will add advice such as, "It's recommended that you take a break."

[0537] In this way, by combining generative AI with an emotion engine, the server can adjust suggestions to take the user's emotions into account, improving work efficiency and reducing stress and fatigue.

[0538] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0539] Step 1:

[0540] The server acquires video data of the worker through an emotion recognition camera. The input is video data, and the output is data passed to the emotion recognition engine. Specifically, the camera captures the worker's facial expressions and sends the data to the server in real time.

[0541] Step 2:

[0542] The server uses an emotion recognition engine to recognize the worker's emotions from the video data. The input is the video data acquired in step 1, and the output is the recognized emotion data. Specifically, the emotion recognition engine analyzes the video data and determines the worker's stress and fatigue levels.

[0543] Step 3:

[0544] The server sends prompts to the generative AI to generate work procedures and efficient work methods. The input is the prompt, and the output is the generated work procedures. Specifically, the server sends the following prompt to the generative AI:

[0545] You are Yamada, a skilled worker. Please suggest steps to efficiently perform the following tasks:

[0546] 1. Assembling the parts

[0547] 2. Inspection

[0548] 3. Packaging

[0549] Step 4:

[0550] The generative AI generates a work procedure based on the prompt sentence and sends it back to the server. The input is the prompt sentence and the output is the generated work procedure. Specifically, the generative AI generates an efficient work procedure based on the knowledge and experience of a specific skilled worker.

[0551] Step 5:

[0552] The server adjusts the generated work steps based on the emotion data from the emotion recognition engine. The input is the emotion data and the generated work steps, and the output is the adjusted work steps. Specifically, the server adds advice such as "We recommend taking a break" to the work steps depending on the worker's stress and fatigue level.

[0553] Step 6:

[0554] The server provides feedback of the adjusted work procedures to the worker in real time. The input is the adjusted work procedures, and the output is the feedback provided to the worker. Specifically, the server communicates the adjusted work procedures to the worker via a display or voice.

[0555] Step 7:

[0556] The user (worker) performs work based on the feedback provided by the server. The input is the feedback from the server, and the output is the actual work result. In concrete terms, the worker assembles, inspects, and packs parts according to the adjusted work procedures.

[0557] Example 2

[0558] Next, a description will be given of 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."

[0559] Conventional simulation systems were able to run simulations based on the knowledge and experience of specific individuals, but they were unable to adjust the simulation results to take into account the user's emotions. As a result, the simulation results sometimes deviated from the real situation, making them less useful to users. In addition, simulations based on information such as resumes and aptitude test results were limited, making it difficult to accurately predict how an individual would perform after joining the company or being transferred.

[0560] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for a generative AI to pretend to be a specific person and perform various simulations; a means for the generative AI to propose tactics, practice menus, etc. based on the specific person's knowledge and experience; a means for the generative AI to simulate the specific person's behavior; a means for an emotion engine to recognize a user's emotions and adjust the simulation results of the generative AI based on the emotions; a means for a user to input information such as a specific person's resume or aptitude test results; a means for the server to receive input data and pass the data to the generative AI model; a means for the generative AI model to execute a simulation and adjust the simulation results based on data from the emotion engine; and a means for the server to display the final simulation results to the user. This makes it possible to provide realistic simulation results that take the user's emotions into consideration.

[0561] "Generative AI" is an artificial intelligence that performs various simulations by taking on the role of a specific person based on their knowledge and experience.

[0562] An "emotion engine" is software that recognizes emotions from the user's facial expressions and voice, and adjusts the simulation results based on those emotions.

[0563] A "server" is a computer system whose role is to receive input data from users, pass the data to the generative AI model, and display the final simulation results to the user.

[0564] A "resume" is a document that lists information such as a person's educational background, work history, and skill set.

[0565] "Aptitude test results" are data that show the results of an evaluation of a specific person's abilities, personality, aptitude, etc.

[0566] "Simulation" is the process of virtually recreating a real-world situation based on specific conditions and data.

[0567] A "user" is a person who accesses the system, enters information about a specific person, and runs a simulation.

[0568] A "database" is a collection of data that stores input information and can be retrieved as needed.

[0569] An "input form" is an interface that allows a user to input specific information into a system.

[0570] A "prompt sentence" is a sentence that prompts the user to input specific information.

[0571] MODE FOR CARRYING OUT THE INVENTION

[0572] This invention is a system that simulates a specific person's performance after joining the company or after being transferred, based on their knowledge and experience, using information such as their resume and aptitude test results.It also has the function of recognizing the user's emotions and adjusting the simulation results based on those emotions.

[0573] Hardware and software used

[0574] This system uses the following hardware and software:

[0575] Hardware: Servers, terminals

[0576] Software: Generative AI model, emotion engine

[0577] System Operation

[0578] The server receives input data from users and passes the data to the generative AI model. When a user enters a specific person's resume or aptitude test results, the server processes this data and passes it to the generative AI model.

[0579] The generative AI model runs a simulation based on the input information and the knowledge and experience of a specific person, and predicts how they will perform after joining the company or being transferred.

[0580] The emotion engine has the ability to recognize the user's emotions. When the user starts a simulation, the emotion engine analyzes the user's emotions in real time and adjusts the simulation results of the generative AI model based on those emotions.

[0581] Specific examples

[0582] For example, consider the case where this system is used in the human resources industry for job hunting or transfer interviews. A user accesses the system and inputs a specific person's resume and aptitude test results. For example, a person's resume information might include "Education: University, Work History: Engineer, Skills: Programming." The server receives this data and passes it to the generative AI model. The generative AI model uses the specific person's knowledge and experience to simulate how well they will perform after joining the company or being transferred.

[0583] During the simulation, the emotion engine recognizes "expectations" from the user's facial expressions. The server passes this emotion data to the generative AI model, which then adjusts the simulation results. Finally, the server displays the adjusted simulation results to the user. For example, it displays a result such as "This person is likely to be promoted to project leader within three months of joining the company."

[0584] Prompt Sentence Examples

[0585] "Enter a specific person's resume and aptitude test results. The system will use this information to simulate how they will perform after joining the company or being transferred. The system will also reflect the emotions felt during the simulation, so please feel free to use it."

[0586] In this way, the system can provide more realistic simulation results while taking into account the user's emotions.

[0587] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0588] Step 1:

[0589] A user accesses the system. The user accesses the system using a web browser or a dedicated application. For example, the user opens a web browser and enters the system's URL to access it. The input is the system's URL, and the output is the system's home screen.

[0590] Step 2:

[0591] A user inputs a resume or aptitude test results for a specific person. A user inputs a resume or aptitude test results for a specific person into an input form in the system. For example, the user inputs information such as name, educational background, work history, and skill set. The input is the data of the resume or aptitude test results, and the output is the transmission of the input data.

[0592] Step 3:

[0593] The server receives input data. The server receives data entered by the user and saves it in a database. For example, the information entered in a resume is stored in a database. The input is the data sent by the user, and the output is saving it in a database.

[0594] Step 4:

[0595] The server passes data to the generative AI model. The server passes stored data to the generative AI model. For example, data such as resumes or aptitude test results are sent to the generative AI model. The input is data stored in the database, and the output is data sent to the generative AI model.

[0596] Step 5:

[0597] The generative AI model runs a simulation based on the data it receives. For example, it predicts how a specific person will perform after joining the company or being transferred based on their knowledge and experience. The input is the data sent from the server, and the output is the simulation results.

[0598] Step 6:

[0599] The emotion engine recognizes the user's emotions. The emotion engine recognizes emotions from the user's facial expressions and voice. For example, if the user is connected to the system via a camera or microphone, the emotion engine analyzes the user's emotions in real time. The input is the user's facial expressions and voice data, and the output is the recognized emotion data.

[0600] Step 7:

[0601] The server passes data from the emotion engine to the generative AI model. The server passes the user's emotion data recognized by the emotion engine to the generative AI model. For example, if the user is feeling anxious, that information is sent to the generative AI model. The input is emotion data from the emotion engine, and the output is data sent to the generative AI model.

[0602] Step 8:

[0603] The generative AI model adjusts the simulation results. The generative AI model adjusts the simulation results based on the user's emotional data. For example, if the user is feeling anxious, the simulation results are fine-tuned taking that emotion into account. The input is emotional data, and the output is the adjusted simulation results.

[0604] Step 9:

[0605] The server displays the final simulation results to the user. The server displays the adjusted simulation results to the user. For example, it displays the simulation results as graphs or text on a web browser. The input is the adjusted simulation results, and the output is what is displayed to the user.

[0606] (Application example 2)

[0607] 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."

[0608] Conventional simulation systems were capable of running simulations based on the knowledge and experience of a specific person, but were unable to run simulations based on the historical data or performance evaluation results of a specific machine or robot. Furthermore, simulation results were not adjusted to take user emotions into account, making it difficult to accurately predict performance in a real work environment. This led to problems such as factory managers being unable to obtain sufficient information when evaluating the suitability of a new robot, making it difficult to make appropriate decisions.

[0609] 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.

[0610] In this invention, the server includes: means for the generative AI to pretend to be a specific person and perform various simulations; means for the generative AI to suggest tactics and training menus based on the specific person's knowledge and experience; means for the generative AI to simulate the specific person's behavior; means for the generative AI to simulate performance in a specific work environment based on the historical data and performance evaluation results of a specific machine; and means including an emotion engine that recognizes the user's emotions and adjusts the simulation results based on those emotions. This enables factory managers to more accurately evaluate the suitability of new robots.

[0611] "Generative AI" is artificial intelligence that performs various simulations based on the knowledge and experience of a specific person or machine.

[0612] "Simulation" is a means of virtually reproducing behavior or performance under specific conditions or environments.

[0613] "Knowledge and experience" is a general term for the information and achievements that a specific person or machine has acquired in the past.

[0614] "Historical data" is a record of the work a particular machine or robot has done in the past and the results of that work.

[0615] "Performance evaluation results" are evaluation results such as the work speed, accuracy, and failure rate of a specific machine or robot.

[0616] An "emotion engine" is a system that recognizes the user's emotions and adjusts the simulation results based on those emotions.

[0617] "Work environment" is a general term for the location and conditions under which a particular machine or robot actually performs its work.

[0618] "Performance" refers to the efficiency or effectiveness with which a particular machine or robot performs a task.

[0619] A "factory manager" is a person responsible for managing the operation of machines and robots within a factory.

[0620] A system for implementing this invention includes a generative AI, an emotion engine, an interface for inputting historical data and performance evaluation results, and a display for displaying simulation results. Specific embodiments of this system are described below.

[0621] The server uses generative AI to perform simulations based on the knowledge and experience of specific people and machines. The generative AI simulates performance in specific work environments based on historical data and performance evaluation results of specific machines. In addition, an emotion engine recognizes the user's emotions and adjusts the simulation results based on those emotions.

[0622] Specifically, the server performs the following process: First, the user inputs the historical data and performance evaluation results of a specific machine through the interface. Next, the emotion engine analyzes the user's facial expressions and voice data to recognize the user's emotions. This can be done using software such as the Emotion Recognition API. The recognized emotion data is fed back to the generative AI, which adjusts the simulation results.

[0623] Generative AI uses OpenAI's API to run simulations based on input data and prompts, such as the following:

[0624] Robot history data: Working speed: High, Accuracy: High, Failure rate: Low

[0625] User Emotion: Stress

[0626] Simulate how this robot would perform in a specific work environment.

[0627] The simulation results are displayed on a screen, allowing users to evaluate the suitability of a new robot. For example, when a factory manager introduces a new robot, they input data such as the robot's past work speed, accuracy, and failure rate, and the emotion engine recognizes the manager's current emotions (e.g., stress or anxiety). The generative AI model then adjusts the simulation results based on those emotions, allowing the manager to more accurately evaluate the suitability of the new robot.

[0628] In this way, by combining generative AI with an emotion engine, the server can provide simulation results that take into account the user's emotions and more accurately evaluate the suitability of specific machines or robots.

[0629] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0630] Step 1:

[0631] The user uses a terminal to input historical data and performance evaluation results for a specific machine. The input data includes work speed, accuracy, failure rate, etc. This data is then sent to the server.

[0632] Step 2:

[0633] The server analyzes the received historical data and performance evaluation results and passes them to the generative AI. Analysis includes formatting and normalizing the data. For example, it complements missing values ​​and converts the data into a unified format.

[0634] Step 3:

[0635] The user uses a terminal to input information to the emotion engine to recognize their emotions. The input includes facial expression images and voice data. This data is then sent to the server.

[0636] Step 4:

[0637] The server uses an emotion engine to analyze the user's emotions. For the analysis, software such as the Emotion Recognition API is used. The analysis result is the user's emotions (e.g., stress, anxiety, joy, etc.).

[0638] Step 5:

[0639] The server generates prompts for the generative AI based on historical data, performance evaluation results, and user emotions. An example of a prompt is, "Robot historical data: Work speed: Fast, Accuracy: High, Failure rate: Low, User emotion: Stress. Please simulate how this robot would perform in a specific work environment."

[0640] Step 6:

[0641] The server uses a generative AI to run a simulation based on the prompt text. The generative AI uses OpenAI's API to analyze the input data and the prompt text and generate simulation results.

[0642] Step 7:

[0643] The server transmits the generated simulation results to the terminal, which include the performance of the machine in a specific working environment.

[0644] Step 8:

[0645] The user can use the terminal to check the simulation results, and based on the results, the user can evaluate the suitability of the new robot and make appropriate decisions.

[0646] Example 3

[0647] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0648] Conventional simulation systems have the problem that the responses of generative AI, which pretends to be a specific person, are fixed and cannot respond flexibly to the user's emotions. Furthermore, they lack the ability to generate responses in real time based on dialogue scenarios entered by the user, making it difficult to obtain effective feedback when practicing actual business negotiations or handling complaints. Furthermore, they lack the ability to recognize the user's emotions and adjust the generative AI's responses based on them, making it impossible to reduce the user's tension and stress.

[0649] 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.

[0650] In this invention, the server includes a means for a user to input a dialogue scenario, a means for the server to analyze the scenario, a means for the server to call a generative AI model, a means for the server to activate an emotion engine, a means for the server to recognize the user's emotions, a means for the server to adjust the response of the generative AI model, and a means for the user to check the simulation results. This allows responses to be generated in real time based on the dialogue scenario input by the user, enabling flexible responses according to the user's emotions. It also reduces tension and stress for the user and provides effective feedback.

[0651] "Generative AI" is an artificial intelligence that takes on the role of a specific person and performs various simulations based on that person's knowledge and experience.

[0652] A "dialogue scenario" is text data input by a user that indicates the content and flow of a dialogue based on a specific situation or purpose.

[0653] A "server" is a computer system that receives input from the user and performs processes such as analyzing the scenario, calling the generative AI model, activating the emotion engine, recognizing the user's emotions, and adjusting the response of the generative AI model.

[0654] The "emotion engine" is software that analyzes the user's facial expressions and voice data to recognize the user's emotional state in real time.

[0655] A "generative AI model" is an artificial intelligence model that generates responses in natural language based on input data.

[0656] "Simulation results" are data that includes the content of the dialogue that the generative AI conducted based on user input, as well as the user's emotional state as recognized by the emotion engine.

[0657] "Response adjustment" is the process of changing the response content of the generative AI model based on the user's emotions recognized by the emotion engine.

[0658] This invention is a system in which a generative AI plays the role of a specific person and performs various simulations. The system involves a user inputting a dialogue scenario, a server analyzing the scenario, calling up a generative AI model, activating an emotion engine to recognize the user's emotions, and adjusting the generative AI model's response, allowing the user to check the simulation results.

[0659] Hardware and software used

[0660] Hardware

[0661] Server: A high-performance computer system that receives input from users and performs processes such as analyzing scenarios, calling generative AI models, activating emotion engines, recognizing user emotions, and adjusting the generative AI model's responses.

[0662] Terminal: A device used by a user to access the system, including PCs and smartphones.

[0663] software

[0664] Generative AI models: Artificial intelligence models that generate responses in natural language based on input data, such as OpenAI's GPT-4.

[0665] Emotion engine: Software such as Affectiva's emotion recognition software that analyzes a user's facial expressions and voice data to recognize the user's emotional state in real time.

[0666] Text analysis engine: Natural language processing technology, such as SpaCy (registered trademark), for analyzing scenario data entered by the user.

[0667] Data processing and calculation

[0668] The server receives the dialogue scenario entered by the user and analyzes it using a text analysis engine. Based on the analysis results, it invokes a generative AI model and generates a response appropriate to the scenario. The emotion engine collects the user's facial expressions and voice data and analyzes their emotional state. The server adjusts the generative AI model's response based on the recognized user emotion and provides appropriate feedback to the user.

[0669] Specific examples

[0670] For example, a user inputs a "sales negotiation scenario in which a new product is proposed" and starts a simulation. In response to the question, "What are the features of this new product?", the generative AI model responds, "This new product is equipped with the latest technology and is more efficient than previous products." If the emotion engine detects tension in the user's facial expression, the generative AI model responds, "Please relax and speak, it's okay," and adjusts to ease the user's tension.

[0671] Prompt Sentence Examples

[0672] "Enter a sales scenario where you are proposing a new product. For example, ask, 'What are the features of this new product?'"

[0673] This system allows users to practice actual business negotiations and complaint handling, and based on the results, identify areas for improvement. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0674] Step 1:

[0675] A user accesses the system

[0676] A user accesses the system's web interface using a terminal (PC or smartphone). Specifically, the user opens a browser and enters the system's URL. The input is the user's access request, and the output is the system's homepage display.

[0677] Step 2:

[0678] The user inputs a dialogue scenario

[0679] The user inputs a dialogue scenario on the system interface. For example, for a "business negotiation scenario to propose a new product," the user might input "What are the features of this new product?" The input is the user's scenario text, and the output is the transmission of the scenario data to the server.

[0680] Step 3:

[0681] The server analyzes the scenario

[0682] The server receives the scenario entered by the user and analyzes it using natural language processing (NLP) technology. Specifically, it uses a text analysis engine (e.g., SpaCy) to understand the context and intent of the scenario. The input is the scenario data, and the output is the analysis results.

[0683] Step 4:

[0684] The server calls the generative AI model

[0685] The server invokes a generative AI model (such as OpenAI's GPT-4) based on the analysis results to generate a response appropriate to the scenario. For example, it generates a response such as, "This new product is equipped with the latest technology and is more efficient than our previous product." The input is the analysis result, and the output is the generated response.

[0686] Step 5:

[0687] The server starts the emotion engine

[0688] The server runs an emotion engine (e.g., Affectiva's emotion recognition software) to recognize the user's emotions in real time. The emotion engine collects the user's facial and voice data and analyzes their emotional state. The input is the user's facial and voice data, and the output is the emotion analysis result.

[0689] Step 6:

[0690] The server starts the simulation

[0691] The server connects the generative AI model and the emotion engine to start a dialogue simulation. The user interacts with the generative AI model on the system. The input is the generated response and the emotion analysis results, and the output is a dialogue log with the user.

[0692] Step 7:

[0693] The server recognizes the user's emotions

[0694] The server recognizes the user's emotions in real time through the emotion engine. For example, if the user is nervous, the emotion engine will detect that nervousness. The input is the user's facial expression and voice data, and the output is the emotion recognition result.

[0695] Step 8:

[0696] The server adjusts the response of the generative AI model

[0697] The server adjusts the response of the generative AI model based on the recognized user emotion. For example, if the user is nervous, the generative AI model responds by saying, "Please relax and speak freely." The input is the emotion recognition result, and the output is the adjusted response.

[0698] Step 9:

[0699] The user checks the simulation results

[0700] After the dialogue simulation is completed, the user checks the simulation results. The system displays the dialogue log and changes in emotions, providing feedback to help the user identify areas for improvement. The input is the dialogue log and emotion recognition results, and the output is a display of the simulation results.

[0701] (Application example 3)

[0702] 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."

[0703] With conventional customer service training methods, it was difficult to simulate actual customer interactions, limiting the ability to improve staff skills. Furthermore, there was no system that could recognize users' emotions in real time and provide corresponding feedback, making it impossible to effectively improve staff's ability to respond in actual customer service situations. This was an obstacle to improving customer satisfaction and staff growth.

[0704] 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.

[0705] In this invention, the server includes a means for a generative AI to pretend to be a specific person and perform various simulations, a means for the generative AI to suggest tactics and training menus based on the specific person's knowledge and experience, a means for the generative AI to simulate the specific person's behavior, a means for an emotion recognition engine to recognize a user's emotions and adjust the results of the generative AI's simulation based on those emotions, and a means for a user to perform a dialogue simulation using a smart device. This enables store staff to improve their skills through realistic customer service simulations.

[0706] "Generative AI" is an artificial intelligence that takes on the role of a specific person and performs various simulations based on that person's knowledge and experience.

[0707] An "emotion recognition engine" is an engine that recognizes the user's emotions in real time and adjusts the simulation results based on those emotions.

[0708] A "smart device" is an electronic device, such as a smartphone or a head-mounted display, that users use to conduct interactive simulations.

[0709] "Dialogue simulation" is a system in which generative AI takes on the role of a specific person and engages in dialogue with the user, practicing actual customer service and business negotiations.

[0710] "Tactics and training menus" are specific methods and plans for users to improve their skills that are suggested by generative AI based on the knowledge and experience of a specific person.

[0711] "Simulation results" are the responses and actions based on a specific scenario that are generated by generative AI through dialogue with the user.

[0712] The following describes the mode for carrying out the present invention: First, the system includes the following main components:

[0713] 1. Generative AI

[0714] Generative AI is an artificial intelligence that performs various simulations by taking on the role of a specific person based on their knowledge and experience. Generative AI generates dialogue based on a scenario entered by the user and interacts with the user.

[0715] 2. Emotion Recognition Engine

[0716] The emotion recognition engine is an engine that recognizes the user's emotions in real time and adjusts the simulation results based on those emotions. The emotion recognition engine analyzes the user's voice and text input to identify their emotional state.

[0717] 3. Smart Devices

[0718] Smart devices are electronic devices such as smartphones and head-mounted displays that users use to simulate interactions. These devices work in conjunction with generative AI and emotion recognition engines.

[0719] Program processing explanation

[0720] The server integrates generative AI, emotion recognition engines, and smart devices to operate. Specifically, it performs the following processes:

[0721] 1. Scenario input

[0722] The user inputs a dialogue scenario through a smart device. For example, a scenario in which a customer is asking about the features of a new product.

[0723] 2. Emotion recognition

[0724] The emotion recognition engine analyzes user input (voice or text) to identify the user's emotion. For example, if a user asks, "What are the features of this product?", the engine will recognize the user's emotion as "interest."

[0725] 3. Dialogue Generation

[0726] The generative AI generates appropriate dialogue based on user input and the results of the emotion recognition engine, for example, responding, "This product uses the latest technology and is particularly notable for its long battery life."

[0727] 4. Simulation Adjustment

[0728] The emotion recognition engine adjusts the generative AI's simulation results based on the user's emotions. For example, if the user expresses dissatisfaction, the generative AI will provide more detailed explanations or additional suggestions.

[0729] Specific examples

[0730] scenario

[0731] A customer is asking about the features of a new product.

[0732] User Input

[0733] "What are the features of this product?"

[0734] Emotion recognition results

[0735] interest

[0736] Generative AI response

[0737] "This product uses the latest technology, especially with its long battery life."

[0738] Prompt Sentence Examples

[0739] You are a staff member at a brick-and-mortar store. Please interact with customers based on the following scenario:

[0740] Scenario: A customer has a question about the features of a new product.

[0741] User: What are the features of this product?

[0742] Emotion: Interest

[0743] AI:

[0744] In this way, store staff can improve their skills through realistic customer service simulations.

[0745] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0746] Step 1:

[0747] The user inputs a dialogue scenario through a smart device.

[0748] Input: The user enters a scenario in which a customer is asking about the features of a new product.

[0749] Output: The input scenario is sent to the server.

[0750] Step 2:

[0751] The server receives the input scenario and generates a prompt for the generative AI.

[0752] Input: The scenario entered by the user.

[0753] Output: The prompt sent to the generative AI.

[0754] Specific operation: The server analyzes the scenario and generates a prompt for the generative AI: "You are a staff member at a physical store. Please interact with customers based on the following scenario."

[0755] Step 3:

[0756] The user inputs a question via a smart device.

[0757] Input: User types, "What are the features of this product?"

[0758] Output: The entered question is sent to the server.

[0759] Step 4:

[0760] The server receives the user's input and analyzes the emotion using an emotion recognition engine.

[0761] Input: The question entered by the user.

[0762] Output: Parsed emotion (e.g. interest).

[0763] Specific operation: The server uses an emotion recognition engine to identify emotions from the user's input text.

[0764] Step 5:

[0765] The server instructs the generative AI to generate a response based on the user's input and emotions.

[0766] Input: User input and parsed sentiment.

[0767] Output: The response generated by the generative AI.

[0768] Specific operation: The server sends the generative AI the instruction, "The user is interested, so please explain in detail the product's features."

[0769] Step 6:

[0770] The generative AI generates a response and sends it to the server.

[0771] Input: Instructions sent to the generative AI.

[0772] Output: The generated response (e.g., "This product uses the latest technology, especially its long battery life.").

[0773] Specific operation: The generative AI generates an appropriate response based on the prompt, user input, and emotion recognition results.

[0774] Step 7:

[0775] The server generates a response and sends it to the user's smart device.

[0776] Input: The response generated by the generative AI.

[0777] Output: The response that is displayed on the user's smart device.

[0778] Specific operation: The server sends the generated response to the user's smart device and displays it to the user.

[0779] Step 8:

[0780] The user reviews the response and enters their next question or feedback.

[0781] Input: The user enters their next question or feedback.

[0782] Output: The entered questions and feedback are sent to the server.

[0783] Specific operation: The user inputs the following questions and feedback through the smart device and sends them to the server.

[0784] In this way, users can improve their customer service skills through realistic dialogue simulations.

[0785] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0786] 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 engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0787] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0788] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0789] [Second embodiment]

[0790] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0791] 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.

[0792] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0793] 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.

[0794] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0795] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0796] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0797] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0802] "Example 1"

[0803] One embodiment of the present invention is a system in which a generative AI plays the role of a specific person and performs various simulations. This system includes a means for proposing tactics and training programs based on the knowledge and experience of the specific person, and a means for simulating the behavior of the specific person. For example, in the sports industry, even if there is no professional coach, it is possible for players to freely select an actual professional coach and have them suggest tactics and training programs.

[0804] "Example 2"

[0805] Furthermore, it also includes a means of simulating the performance of a specific person after joining the company or after being transferred, based on the knowledge and experience of that person, information such as resumes and aptitude test results. For example, in the human resources industry, it is possible to simulate the performance of a person after joining the company or after being transferred, based on information such as resumes and aptitude test results, during job hunting or transfer interviews.

[0806] "Example 3"

[0807] It also includes a means of simulating conversations with a business partner or a complainer by pretending to be a specific person. For example, when practicing business negotiations or complaint handling, generative AI can pretend to be the business partner or the complainer and simulate actual conversations. This allows for practice of actual business negotiations or complaint handling, and the results can be used to identify areas for improvement.

[0808] The processing flow of each embodiment will be described below.

[0809] "Example 1"

[0810] Step 1: A user accesses the system and selects a specific person.

[0811] Step 2: The system uses generative AI to immerse itself in the role of the selected person, based on their knowledge and experience.

[0812] Step 3: When the user starts the simulation, the generative AI will suggest tactics and training menus based on the specific person's knowledge and experience.

[0813] "Example 2"

[0814] Step 1: A user accesses the system and enters information about a specific person, such as their resume and aptitude test results.

[0815] Step 2: The system uses generative AI to immerse itself in the role of a specific person based on the input information and their knowledge and experience.

[0816] Step 3: When the user starts the simulation, the generative AI simulates the employee's performance after joining the company or after being transferred.

[0817] "Example 3"

[0818] Step 1: The user accesses the system and enters a dialogue scenario between a specific person and a business partner or complainant.

[0819] Step 2: Based on the input scenario and the specific person's knowledge and experience, the system uses generative AI to immerse itself in that role.

[0820] Step 3: When the user starts the simulation, the generative AI simulates a conversation with a business partner or a complainant.

[0821] Example 1

[0822] 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."

[0823] With conventional simulation systems, it was difficult to propose tactics or training menus based on the knowledge and experience of a specific person, and they were not able to realistically simulate the behavior of a specific person. As a result, there were issues with not being able to carry out effective learning and training when there was no specialized coach or when the player wanted to learn the behavior of a specific person.

[0824] 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.

[0825] In this invention, the server includes a means for a user to input information about a specific person using a terminal, a means for the server to acquire data about the specific person from a database, a means for the server to preprocess the acquired data and convert it into a format that can be input to a generative AI model, a means for the server to execute a simulation using the generative AI model, and a means for the server to transmit the simulation results to the terminal and display them to the user. This makes it possible to propose tactics and training menus based on the knowledge and experience of a specific person, and to realistically simulate the behavior of a specific person.

[0826] "Generative AI" is an artificial intelligence that performs simulations based on the knowledge and experience of a specific person and suggests tactics and training menus.

[0827] A "specific person" is an individual for whom the system will perform simulations and suggestions, such as a professional coach or expert.

[0828] "Simulation" is the process of virtually reproducing the actions and tactics of a specific person and providing the results to the user.

[0829] "Tactics" refers to the optimal action or plan in a particular situation, especially strategic behavior in sports and business.

[0830] A "practice menu" is a series of exercises or training sessions designed to achieve a specific goal.

[0831] "User" refers to an individual or organization that uses the system to learn from the knowledge and experience of a specific person.

[0832] A "terminal" is a device that allows a user to access the system, input information, and receive results, and includes, for example, a personal computer or smartphone.

[0833] The "server" is the central computer of the system, and is the device that acquires data, pre-processes it, runs the simulation, and transmits the results.

[0834] A "database" is a repository of information that stores knowledge and experience data about a specific person and that can be accessed by a server as needed.

[0835] "Preprocessing" refers to the process of data cleaning and format conversion to convert acquired data into a format that can be input into a generative AI model.

[0836] A "generative AI model" is an artificial intelligence algorithm that performs simulations based on the knowledge and experience of a specific person, and includes, for example, GPT-4.

[0837] "Simulation results" are the output data obtained after a generative AI model performs a simulation, and are information provided to the user.

[0838] This invention is a system that uses a generative AI model to perform various simulations by impersonating a specific person. This system includes a means for proposing tactics and training menus based on the knowledge and experience of the specific person, and a means for simulating the behavior of the specific person.

[0839] Hardware and software used

[0840] Server: The central computer of the system that acquires data, pre-processes it, runs simulations, and transmits the results. Specifically, it uses a database management system (e.g., MySQL) and a generative AI model (e.g., GPT-4).

[0841] Terminal: A device that allows a user to access the system, input information, and receive results. Examples include computers and smartphones.

[0842] Data processing and calculation

[0843] 1. User input:

[0844] A user accesses the system using a terminal and inputs information about a specific person, for example, a prompt such as "Please tell me the tactics of a specific professional coach."

[0845] 2. Data Acquisition:

[0846] The server receives input from the user and retrieves data related to a specific person from a database. For example, the server connects to a MySQL database and queries for tactics and training data related to a "specific professional coach."

[0847] 3. Data preprocessing:

[0848] The server preprocesses the acquired data. Specifically, it cleans the data and converts its format so that it can be input into a generative AI model. For example, it removes unnecessary spaces and special characters from text data and converts it to JSON format.

[0849] 4. Run the simulation:

[0850] The server inputs the preprocessed data into a generative AI model and runs a simulation. The generative AI model generates a response to the user's prompt based on the knowledge and experience of a specific person. For example, the generative AI model simulates "what tactics a specific professional coach will propose in the next game" and generates the results.

[0851] 5. Result output:

[0852] The server sends the simulation results obtained from the generative AI model to the device. The device then displays the received results to the user. For example, the device screen might say, "A specific professional coach suggests a 4-3-3 formation for the next match."

[0853] Examples of concrete examples and prompts

[0854] Consider the case where the user is an athlete and wants to learn the tactics of a particular professional coach.

[0855] Examples:

[0856] A user accesses the system using a terminal and inputs that he or she would like to learn the tactics of a particular professional coach.

[0857] The server retrieves data about the knowledge and experience of specific professional coaches from a database and inputs it into a generative AI model.

[0858] The server uses a generative AI model to simulate what tactics a specific professional coach would propose and displays the results to the user.

[0859] Example prompt sentence:

[0860] "Tell me what tactics a particular professional coach would suggest for the next game."

[0861] In this way, users can learn the tactics and training regimens of a particular professional coach.

[0862] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0863] Step 1:

[0864] A user accesses the system using a terminal and inputs information about a specific person. Specifically, the user enters a prompt such as "Please tell me the tactics of a specific professional coach" into the input form on the terminal and clicks the submit button. The input data is in the form of text containing questions or requests about a specific person.

[0865] Step 2:

[0866] The server receives input from the user and retrieves data related to a specific person from the database. Specifically, the server connects to a MySQL database and queries data on tactics and training menus related to a "specific professional coach." The input is the user's prompt, and the output is the data related to the specific person retrieved from the database.

[0867] Step 3:

[0868] The server preprocesses the acquired data. Specifically, it cleans the data and converts its format so that it can be input into a generative AI model. For example, it removes unnecessary spaces and special characters from text data and converts it into JSON format. The input is raw data acquired from the database, and the output is preprocessed data.

[0869] Step 4:

[0870] The server inputs the preprocessed data into a generative AI model and runs a simulation. The generative AI model generates a response to a user prompt based on the knowledge and experience of a specific person. For example, the generative AI model simulates "what tactics a specific professional coach will propose in the next game" and generates the results. The input is the preprocessed data, and the output is the simulation result generated by the generative AI model.

[0871] Step 5:

[0872] The server sends the simulation results obtained from the generative AI model to the device. The device then displays the received results to the user. For example, the device screen may display a message such as, "A specific professional coach suggests a 4-3-3 formation for the next game." The input is the simulation results from the generative AI model, and the output is the information displayed to the user.

[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] Conventional industrial robots have difficulty optimizing their movements and work procedures by utilizing the knowledge and experience of specific workers. As a result, efficient work procedures were not adequately proposed or optimized, limiting productivity improvements. In addition, there were limited means to transfer the knowledge and experience of skilled workers to new workers, making it difficult to pass on skills. To solve these issues, a system is needed that utilizes the knowledge and experience of specific workers to optimize the movements and work procedures of industrial robots.

[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 means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and practice menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to optimize the operation and work procedures of the industrial robot based on the knowledge and experience of the specific worker. This makes it possible to optimize the operation and work procedures of the industrial robot by utilizing the knowledge and experience of the specific worker, thereby improving productivity and enabling the transfer of technology.

[0878] "Generative AI" is an artificial intelligence system that imitates the knowledge and experience of a specific person and performs various simulations.

[0879] A "specific person" refers to an individual person with knowledge and experience, whose actions and thoughts are to be imitated.

[0880] "Simulation" is a method of virtually recreating real-world situations and behaviors to make predictions and analyses.

[0881] "Tactics" refers to specific methods or means for achieving a specific goal.

[0882] A "practice menu" refers to planned training content designed to improve specific skills or abilities.

[0883] "Behavior" refers to the specific actions or reactions taken by a particular person.

[0884] "Worker" refers to a person who performs a specific task or work.

[0885] An "industrial robot" refers to an automated mechanical device used in factories and production lines.

[0886] "Action" refers to the specific movements or operations performed by machines or humans.

[0887] A "work procedure" refers to a series of procedures or methods for efficiently performing a specific task.

[0888] "Optimization" refers to adjusting something to maximize efficiency or effectiveness in order to achieve a specific purpose.

[0889] As an embodiment of the present invention, the following system is constructed.

[0890] System Configuration

[0891] The server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and training menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to optimize the operation and work procedures of an industrial robot based on the knowledge and experience of a specific worker.

[0892] Program processing explanation

[0893] The server implements a generative AI model using Python and uses the OpenAI API to generate optimal work procedures based on the knowledge and experience of specific workers. Specifically, it performs the following processes:

[0894] 1. Data entry: The user enters the name of a specific worker and the task.

[0895] 2. Prompt generation: The server generates a prompt sentence for the generative AI model based on the input data.

[0896] 3. Calling the AI ​​model: The server uses OpenAI's API to send prompts to the generative AI model to generate optimal work procedures.

[0897] 4. Result output: The server outputs the generated optimal work procedure to the user.

[0898] Hardware and software used

[0899] Hardware: Industrial robots (e.g. KUKA, Fanuc, etc.), computers (for robot control)

[0900] Software: Python, OpenAI API

[0901] Specific examples

[0902] For example, when optimizing the assembly of parts based on the knowledge and experience of skilled worker A, the following prompt sentence is generated.

[0903] Prompt Sentence Examples

[0904] Based on the knowledge and experience of skilled worker A, optimize the following tasks.

[0905] Work: Assembly of parts

[0906] Please suggest the best procedure.

[0907] In this way, it is possible to utilize the knowledge and experience of specific workers to optimize the movements and work procedures of industrial robots, thereby improving productivity and ensuring the succession of skills.

[0908] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0909] Step 1:

[0910] The user inputs the name of a specific worker and the task.

[0911] Input: Name of specific worker (e.g., skilled worker A), work content (e.g., parts assembly work)

[0912] Output: Input data (specific worker name, work content)

[0913] Specific operation: The user uses the terminal to enter the name of a specific worker and the work content into the input form and presses the submit button.

[0914] Step 2:

[0915] The server generates a prompt sentence for the generative AI model based on the input data.

[0916] Input: Data entered by the user (name of specific worker, work content)

[0917] Output: Generated prompt statement

[0918] Specific operation: The server receives the input data and generates a prompt like the following: "Based on the knowledge and experience of skilled worker A, please optimize the following task. Task: assembling parts. Please suggest the optimal work procedure."

[0919] Step 3:

[0920] The server uses OpenAI's API to send prompts to the generative AI model to generate optimal work procedures.

[0921] Input: Generated prompt text

[0922] Output: Response from the generative AI model (optimal work procedure)

[0923] How it works: The server sends the generated prompt to OpenAI's API and receives a response from the generative AI model, which includes the optimal work procedure.

[0924] Step 4:

[0925] The server outputs the generated optimal work procedure to the user.

[0926] Input: Response from the generative AI model (optimal work procedure)

[0927] Output: The optimal workflow displayed to the user

[0928] Specific operation: The server sends the optimal work procedure received from the generative AI model to the user's device and displays it on the user's screen.

[0929] Example 2

[0930] Next, a description will be given of 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."

[0931] With conventional talent evaluation systems, it was difficult to predict future performance based on a candidate's resume and aptitude test results. Furthermore, there was a lack of a way to utilize a specific person's knowledge and experience to simulate how they would perform after joining the company or being transferred. This made it difficult for companies to make appropriate personnel placement and hiring decisions, resulting in problems such as a decline in organizational efficiency and productivity.

[0932] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for a user to input candidate information, a means for a terminal to transmit the input data to the server, a means for the server to store the received data in a database, a means for the server to use a generative AI model to analyze the stored data, a means for the server to execute a simulation based on the analysis results, a means for the server to transmit the simulation results to the terminal, and a means for the terminal to display the results to the user. This makes it possible to predict future performance based on the candidate's resume and aptitude test results, allowing companies to make appropriate personnel placement and hiring decisions.

[0933] "Generative AI" is an artificial intelligence system that performs simulations based on the knowledge and experience of a specific person.

[0934] "User" means a person or organization that utilizes the system to enter candidate information.

[0935] A "terminal" is a device through which a user inputs information and displays simulation results.

[0936] A "server" is a computer system that receives, stores, analyzes, and runs simulations on data submitted by users.

[0937] A "database" is an information management system for storing data received by a server.

[0938] A "generative AI model" is an artificial intelligence algorithm that analyzes data based on the knowledge and experience of a specific person and generates simulation results.

[0939] A "resume" is a document that lists information such as a candidate's educational background, work history, and skills.

[0940] "Aptitude test results" are the results of a test to evaluate a candidate's abilities and personality.

[0941] A "simulation" is a hypothetical experiment designed to predict a candidate's future performance under specific conditions.

[0942] A "prompt statement" is an instruction statement entered into a generative AI model to perform analysis or simulation.

[0943] This invention is a system that simulates the performance of a specific person after joining the company or after being transferred, based on the person's knowledge and experience, as well as information such as their resume and aptitude test results. The system is composed of users, terminals, and a server.

[0944] Hardware and software used

[0945] Hardware: Servers, terminals

[0946] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), aptitude testing tools (e.g., SHL)

[0947] Specific operation of the system

[0948] 1. Data Entry

[0949] The user inputs the candidate's resume and aptitude test results into the terminal. Specifically, the user enters the required information into the web form and clicks the "Submit" button.

[0950] 2. Data Transmission

[0951] The terminal sends the input data to the server. Specifically, the terminal uses an HTTP POST request to send the input data to the server.

[0952] 3. Data storage

[0953] The server saves the received data in the database. Specifically, the server connects to the MySQL database and saves the data using the INSERT statement.

[0954] 4. Data Analysis

[0955] The server uses a generative AI model (e.g., GPT-4) to analyze the stored data. Specifically, the server runs a Python script to input prompts to the GPT-4 model and obtain the analysis results.

[0956] Example prompt: "Based on this candidate's resume and aptitude test results, simulate their performance as a software engineer."

[0957] 5. Run the simulation

[0958] Based on the analysis results, the server simulates the employee's performance after joining the company or after being transferred. Specifically, the server runs a simulation algorithm based on the analysis results obtained from the generative AI model and calculates predicted performance.

[0959] 6. Send results

[0960] The server sends the simulation results to the terminal. Specifically, the server generates an HTTP response and sends JSON data containing the simulation results to the terminal.

[0961] 7. Results display

[0962] The terminal then displays the results to the user by parsing the received JSON data and displaying the results on a web page, for example, visualizing the candidate's predicted performance in graphs or text format.

[0963] Specific examples

[0964] For example, suppose a candidate is applying for a software engineer position. The user inputs the candidate's resume and aptitude test results into the system. The server receives this data and analyzes it using a generative AI model (GPT-4). Based on the analysis results, the server simulates the candidate's performance after joining the company and sends the predicted results to the device. The device then displays the results to the user.

[0965] In this way, the system can simulate the candidate's future performance based on the data entered by the user and provide the results to the user.

[0966] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0967] Step 1:

[0968] Data Entry

[0969] The user inputs the candidate's resume and aptitude test results into the terminal.

[0970] Input: Resume, aptitude test results

[0971] What happens: A user fills in information on a web form and clicks the "Submit" button.

[0972] Output: The input data is saved to the device.

[0973] Step 2:

[0974] Data transmission

[0975] The terminal transmits the input data to the server.

[0976] Input: Data entered by the user

[0977] Specific operation: The device sends the input data to the server using an HTTP POST request.

[0978] Output: Data is sent to the server.

[0979] Step 3:

[0980] Data storage

[0981] The server stores the received data in a database.

[0982] Input: Data sent from the terminal

[0983] What happens: The server connects to the MySQL database and saves the data using an INSERT statement.

[0984] Output: The data is saved to a database.

[0985] Step 4:

[0986] Data analysis

[0987] The server uses a generative AI model (e.g., GPT-4) to analyze the stored data.

[0988] Input: Data stored in the database

[0989] Specific operation: The server runs a Python script, inputs a prompt to the GPT-4 model, and obtains the analysis results.

[0990] Example prompt: "Based on this candidate's resume and aptitude test results, simulate their performance as a software engineer."

[0991] Output: Analysis results are generated.

[0992] Step 5:

[0993] Simulation execution

[0994] Based on the analysis results, the server simulates how the employee will perform after joining the company or being transferred.

[0995] Input: Analysis results obtained from the generative AI model

[0996] What happens: The server runs a simulation algorithm to calculate predicted performance.

[0997] Output: Simulation results are generated.

[0998] Step 6:

[0999] Send results

[1000] The server transmits the simulation results to the terminal.

[1001] Input: Simulation results

[1002] Specific operation: The server generates an HTTP response and sends JSON data containing the simulation results to the terminal.

[1003] Output: Data is sent to the terminal.

[1004] Step 7:

[1005] Results display

[1006] The terminal displays the results to the user.

[1007] Input: JSON data sent from the server

[1008] What it does: The device parses the received JSON data and displays the results on a web page, for example, visualizing the candidate's predicted performance in graphs or text format.

[1009] Output: The user can check the simulation results.

[1010] (Application example 2)

[1011] 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."

[1012] Conventional simulations of personnel placement and robot operation rely heavily on experience and intuition, making it difficult to find optimal placement and operation. Furthermore, simulations based on resumes and aptitude test results are time-consuming and labor-intensive when performed manually, and suffer from low accuracy. This has prevented efficient personnel placement and robot operation within factories, hindering productivity improvements.

[1013] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to propose tactics, practice menus, etc. based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to simulate optimal personnel allocation and robot operations in a factory based on the resume and aptitude test results of the specific person. This enables highly accurate simulations based on resumes and aptitude test results, thereby realizing efficient personnel allocation and robot operations in a factory.

[1014] "Generative AI" is an artificial intelligence system that imitates the knowledge and experience of a specific person and performs various simulations and suggestions.

[1015] "Simulation" is a method of virtually recreating real-world situations based on specific conditions and data, and making predictions and analyses.

[1016] A "resume" is a document that lists information such as an individual's educational background, work history, and skills, and is used when applying for a job or transferring.

[1017] "Aptitude test results" are the results of tests used to evaluate an individual's abilities, personality, and aptitude, and are used to determine job suitability and placement.

[1018] "Staffing" refers to the allocation of the most suitable personnel to each position within an organization.

[1019] "Robot movement" refers to the series of tasks and movements performed by robots used in factories.

[1020] "Tactics" refers to specific methods or means for achieving a specific goal.

[1021] A "practice menu" refers to a training program or plan to improve a particular skill or ability.

[1022] The system for implementing this invention uses generative AI to mimic the knowledge and experience of a specific person and perform various simulations and proposals. Specifically, it includes a function to simulate optimal personnel allocation and robot operation within a factory based on resumes and aptitude test results.

[1023] The server uses the following hardware and software:

[1024] Hardware: PC or smartphone

[1025] Software: Python, Pandas, Scikit-learn

[1026] The server first reads resume and aptitude test result data from a CSV file. Then, it separates the data into features (years of experience, education level, skill score, etc.) and labels (performance). This allows for data preprocessing.

[1027] The server then trains a model using a random forest classifier, which is then used to simulate optimal staffing and robot behavior within a factory based on a specific person's knowledge and experience.

[1028] The user inputs the data of a new candidate and requests the server to run a simulation. The server uses the trained model to predict the new candidate's performance and proposes optimal personnel placement and robot behavior.

[1029] As a concrete example, the following prompt sentence is input to the generative AI model:

[1030] "Based on the resume data of a new candidate, simulate the optimal placement within a factory. The candidate has 5 years of experience, an education level of 3, and a skill score of 85."

[1031] Using this prompt, the generative AI model can analyze candidate data and predict optimal placement and performance, leading to efficient personnel placement and robot operation within factories.

[1032] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1033] Step 1:

[1034] The server reads data such as resumes and aptitude test results from CSV files. The input is a CSV file, and the output is data in data frame format. Specifically, the CSV file is read using the Python Pandas library and converted to a data frame.

[1035] Step 2:

[1036] The server separates the data into features and labels. The input is data in data frame format, and the output is data separated into features (years of experience, education level, skill score, etc.) and labels (performance). Specifically, it extracts specific columns from the data frame and separates them into features and labels.

[1037] Step 3:

[1038] The server trains a model using a random forest classifier. The input is data divided into features and labels, and the output is a trained model. Specifically, it creates a random forest classifier using the Scikit-learn library and trains the model using the features and labels.

[1039] Step 4:

[1040] The user inputs data on a new candidate. The input data includes the new candidate's years of experience, education level, skill score, etc., and the output is a simulation request to the server. Specifically, the user inputs the new candidate's data using a smartphone or PC and sends it to the server.

[1041] Step 5:

[1042] The server uses the trained model to predict the performance of new candidates. The input is the new candidate's data, and the output is the predicted performance. Specifically, the server inputs the new candidate's data into the model and obtains the predicted result.

[1043] Step 6:

[1044] The server proposes optimal personnel placement and robot operation based on the prediction results. The input is predicted performance, and the output is a proposal for optimal personnel placement and robot operation. As a specific operation, the server analyzes the prediction results and proposes optimal placement and operation within the factory.

[1045] Step 7:

[1046] The user receives the proposals from the server and reflects them in the actual deployment of personnel and the operation of the robots. The input is the proposal from the server, and the output is the actual deployment and operation. In terms of specific operations, the user checks the proposals and adjusts the deployment and operation of the robots within the factory.

[1047] Example 3

[1048] Next, a description will be given of 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."

[1049] Conventional simulation systems have limited functionality for interacting with specific people, making it difficult to simulate situations that closely resemble real situations when practicing business negotiations or handling complaints. Furthermore, feedback on the simulation results is insufficient, making it difficult for users to identify areas for improvement. This has led to the issue of users being unable to fully improve their skills.

[1050] 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.

[1051] In this invention, the server includes: means for a generative AI to pretend to be a specific person and perform various simulations; means for the generative AI to propose tactics, practice menus, etc. based on the specific person's knowledge and experience; means for the generative AI to simulate the specific person's behavior; means for a user to access the system using a terminal and input a prompt; means for the server to call the generative AI model and generate dialogue content based on the prompt; means for the server to send the generated dialogue content to the user's terminal; means for the user to perform dialogue simulation; and means for the server to provide feedback on the simulation results. This allows the user to perform simulations that are similar to actual business negotiations or complaint handling and to identify areas for improvement based on the results.

[1052] "Generative AI" is artificial intelligence that can take on the role of a specific person and simulate conversations and actions.

[1053] A "prompt sentence" is text that a user enters to specify a simulation scenario.

[1054] A "server" is a computer system that hosts a generative AI model and processes requests from users.

[1055] A "terminal" is a device such as a PC or smartphone that a user uses to access the system.

[1056] "Dialogue content" refers to the simulated conversation content generated by the generative AI based on the prompt text.

[1057] "Feedback" refers to information on improvements and evaluations that are provided to users after analyzing the results of the simulation.

[1058] A "simulation" is the reproduction of hypothetical interactions and behaviors that a generative AI performs based on a specific scenario.

[1059] "Knowledge and experience" refers to the specialized information that a particular person possesses and the skills and know-how based on past achievements.

[1060] "Tactics and training menus" are specific action plans and training contents proposed by generative AI.

[1061] This invention is a system that uses generative AI to simulate a conversation with a specific person, such as a business partner or a complainer. Specific embodiments of this system are described below.

[1062] Hardware and software used

[1063] server:

[1064] The server hosts the generative AI model and processes requests from users. Specifically, OpenAI's GPT-4 is used as the generative AI model. The server sends prompts received from users to the generative AI model and sends the generated dialogue content to the user's device.

[1065] Device:

[1066] A terminal is a device that a user uses to access the system. It can be a PC, a smartphone, or other device. The terminal accesses the server through a web browser and provides an interface for entering prompts.

[1067] User:

[1068] The user uses the system to simulate business negotiations and complaint handling. The user accesses the system using a terminal and inputs prompt statements.

[1069] Data processing and calculation

[1070] Enter the prompt statement:

[1071] The user inputs a prompt statement that corresponds to the scenario they want to simulate. For example, they might input something like, "I would like to simulate a business negotiation in which a new product is proposed. I would like the business partner to ask detailed questions about the product's features and price."

[1072] Invoke the generative AI model:

[1073] The server sends the prompt received from the user to the generative AI model, which then generates dialogue content based on the prompt. The generated dialogue content is then sent to the user's device via the server.

[1074] Conducting a dialogue simulation:

[1075] The user then proceeds through the simulation based on the generated dialogue, asking and answering questions during the dialogue, practicing actual business negotiations and handling complaints.

[1076] Providing feedback:

[1077] After the simulation is completed, the server analyzes the results and provides feedback to the user, who can then use this feedback to identify areas for improvement.

[1078] Specific examples

[1079] If a user wants to simulate a business negotiation in which a new product proposal is made, he or she enters the following prompt sentence:

[1080] Example prompt sentence:

[1081] "I'd like to simulate a business negotiation in which I propose a new product. I'd like the other party to ask detailed questions about the product's features and price."

[1082] When this prompt is entered, the generative AI model plays the role of a salesperson and starts a simulation in which the user proposes a new product. The generative AI model asks questions about the product's features and price, and the user answers them, allowing the model to practice a real sales negotiation.

[1083] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1084] Step 1:

[1085] A user accesses the system

[1086] A user accesses the system's web application using a terminal (PC or smartphone). The user enters authentication information on the login screen and logs in to the system.

[1087] Input: Username and Password

[1088] Output: Successful login to the system message

[1089] Specific behavior:

[1090] The user opens a browser and enters the system's URL.

[1091] The user enters their username and password on the login screen and clicks the "Login" button.

[1092] Step 2:

[1093] The user enters a prompt statement

[1094] The user inputs a prompt statement according to the scenario they want to simulate, such as "I would like to simulate a business negotiation in which a new product proposal is made."

[1095] Input: prompt statement

[1096] Output: Prompt statement sending confirmation message

[1097] Specific behavior:

[1098] The user moves to the simulation screen and enters a prompt sentence in the text box.

[1099] The user clicks the "Submit" button.

[1100] Step 3:

[1101] The server invokes the generative AI model

[1102] The server sends the prompt received from the user to the generative AI model, which then generates dialogue content based on the prompt.

[1103] Input: prompt statement

[1104] Output: Generated dialogue

[1105] Specific behavior:

[1106] The server receives the prompt and sends a request to the API of the generative AI model.

[1107] The generative AI model analyzes the prompt and generates the dialogue content.

[1108] Step 4:

[1109] The server sends the generated dialogue to the user

[1110] The server receives the dialogue content from the generative AI model and sends it to the user's device, where the user receives it and starts the dialogue simulation.

[1111] Input: Generated dialogue

[1112] Output: The dialogue displayed on the user's device

[1113] Specific behavior:

[1114] The server receives the generated dialogue content and transmits it to the user's terminal.

[1115] The user's terminal displays the contents of the conversation.

[1116] Step 5:

[1117] The user performs an interactive simulation

[1118] The user proceeds through the simulation based on the generated dialogue content, asking and answering questions during the dialogue, practicing actual business negotiations and handling complaints.

[1119] Input: Generated dialogue, user responses

[1120] Output: The progress of the conversation

[1121] Specific behavior:

[1122] The user reads the dialogue and enters an appropriate response.

[1123] The user clicks the "Submit" button and continues the conversation.

[1124] Step 6:

[1125] The server feeds back the simulation results

[1126] After the simulation is completed, the server provides the user with feedback on the results of the simulation, allowing the user to identify areas for improvement.

[1127] Input: Simulation log

[1128] Output: Feedback content

[1129] Specific behavior:

[1130] The server analyzes the simulation logs and generates feedback.

[1131] The server sends the feedback to the user's terminal.

[1132] Users review feedback and identify areas for improvement.

[1133] (Application example 3)

[1134] 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."

[1135] With conventional simulation systems, it was difficult to practice sales negotiations or handling complaints while pretending to be a specific person, making it difficult to improve staff ability to respond in real situations. Furthermore, there was a lack of evaluation of complaint handling and feedback on areas for improvement, limiting the ability to improve staff skills. This resulted in a decline in the quality of customer service in brick-and-mortar stores, making it difficult to improve customer satisfaction.

[1136] 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.

[1137] In this invention, the server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and practice menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to simulate handling of complaints and provide feedback on the response evaluation and areas for improvement. This enables staff at physical stores to practice handling realistic complaints and improve their response skills.

[1138] "Generative AI" is an artificial intelligence that imitates the knowledge and behavior of a specific person and performs various simulations.

[1139] "Simulation" is a method of virtually recreating a specific situation or environment and attempting to act or react within it.

[1140] "Tactics" are specific methods or plans for achieving a specific purpose.

[1141] A "practice menu" is a series of exercises designed to improve a particular skill or ability.

[1142] "Complaint handling" refers to the actions taken to appropriately respond to customer complaints and dissatisfaction and resolve the issues.

[1143] "Evaluation" is the act of judging the value or effectiveness of a particular action or result.

[1144] "Feedback" is the act of communicating areas for improvement or evaluation of specific actions or results.

[1145] A "brick and mortar store" is a store that exists in a physical location and where customers can visit in person to purchase goods or services.

[1146] The following system configuration is used as an embodiment of this invention: The system is composed of a server equipped with generative AI, a terminal (such as a smartphone) operated by the user, and necessary software.

[1147] The server includes a means for the generative AI to pretend to be a specific person and perform various simulations, a means for the generative AI to suggest tactics and training menus based on the knowledge and experience of a specific person, a means for the generative AI to simulate the actions of a specific person, and a means for the generative AI to simulate handling of a complaint and provide feedback on the response and areas for improvement.

[1148] A dedicated application is installed on the device operated by the user. This application provides an interface for the user to input the details of the complaint and has the function of sending the input information to a server. The server uses generative AI based on the received information to generate a dialogue that plays the role of the complainant and sends the result back to the device.

[1149] Specifically, a user inputs the details of a complaint into the application, such as "The product was broken and I would like to return it." The server receives this information and uses generative AI to generate a dialogue for the complainant, such as "This product broke immediately. I would like to return it. What should I do?" This dialogue is displayed on the device, allowing the user to practice responding to it.

[1150] The hardware used is a smartphone (iOS or Android), and the software uses Python and the OpenAI API, which allows the generative AI to simulate realistic complaint handling and provide feedback to the user on evaluations and areas for improvement.

[1151] An example of a prompt is as follows:

[1152] "You are a complainer. Please file a complaint in the following situation: I would like to return the product because it was broken."

[1153] In this way, store staff can practice dealing with real complaints and improve their response skills.

[1154] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1155] Step 1:

[1156] The user starts the application on the terminal and inputs the status of the complaint.

[1157] Input: Complaint status (e.g., "The product was broken and I would like to return it.")

[1158] Output: Status data of the entered complaint

[1159] Step 2:

[1160] The terminal transmits the entered complaint status data to the server.

[1161] Input: Claim status data

[1162] Output: Claim status data sent to the server

[1163] Step 3:

[1164] Based on the complaint status data received by the server, a prompt sentence is generated for the generative AI.

[1165] Input: Claim status data

[1166] Output: Generated prompt (e.g. "You are a complainer. Please complain in the following situation: I would like to return the product because it was broken.")

[1167] Step 4:

[1168] The server uses generative AI to generate dialogue for the complainer based on the generated prompt text.

[1169] Input: Generated prompt text

[1170] Output: Generated dialogue of the complainant (e.g., "This item broke immediately. I would like to return it. What should I do?")

[1171] Step 5:

[1172] The server transmits the generated dialogue of the complainer to the terminal.

[1173] Input: Generated dialogue for the complainer

[1174] Output: The complainer's dialogue sent to the terminal

[1175] Step 6:

[1176] The terminal displays the received dialogue of the complainer to the user.

[1177] Input: Received complaint dialogue

[1178] Output: The complainer's dialogue displayed to the user

[1179] Step 7:

[1180] The user responds to the dialogue of the complainer and inputs the response into the terminal.

[1181] Input: User response (e.g. "I'm sorry. We will process your return.")

[1182] Output: Input response data

[1183] Step 8:

[1184] The terminal transmits the inputted correspondence content data to the server.

[1185] Input: Response content data

[1186] Output: Response data sent to the server

[1187] Step 9:

[1188] Based on the response content data received by the server, the generative AI generates an evaluation of the response and areas for improvement.

[1189] Input: Response content data

[1190] Output: Generated assessment and improvements

[1191] Step 10:

[1192] The server sends the generated ratings and improvements to the device.

[1193] Input: Generated ratings and improvements

[1194] Output: Ratings and improvements sent to the device

[1195] Step 11:

[1196] The device displays the received ratings and improvements to the user.

[1197] Input: Received ratings and improvements

[1198] Output: User-visible rating and improvements

[1199] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1200] "Example 1"

[1201] The invention described in claim 4 combines a system including a means for a generative AI to pretend to be a specific person and perform various simulations, a means for the generative AI to suggest tactics and practice menus based on the specific person's knowledge and experience, and a means for the generative AI to simulate the specific person's behavior, with an emotion engine that recognizes the user's emotions. Specifically, a user accesses the system and selects a specific person. The system then uses the generative AI to pretend to be that person based on the selected person's knowledge and experience. Furthermore, the system incorporates an emotion engine that recognizes the user's emotions, and when the user starts a simulation, the generative AI suggests tactics and practice menus based on the specific person's knowledge and experience. In this case, the emotion engine recognizes the user's emotions and adjusts the generative AI's suggestions based on those emotions.

[1202] "Example 2"

[1203] The invention described in claim 5 is a system that combines an emotion engine that recognizes user emotions with a system that includes a means for a generative AI to simulate a specific person's performance after joining the company or after a transfer based on information such as a resume and aptitude test results, based on the person's knowledge and experience. Specifically, a user accesses the system and inputs information about the specific person, such as a resume and aptitude test results. The system utilizes the generative AI to become that person based on the input information and the specific person's knowledge and experience. Furthermore, the system is equipped with an emotion engine that recognizes user emotions, and when the user starts a simulation, the generative AI simulates the person's performance after joining the company or after a transfer. In this case, the emotion engine recognizes the user's emotions and adjusts the generative AI's simulation results based on those emotions.

[1204] "Example 3"

[1205] The invention described in claim 6 combines a system including a means for a generative AI to pretend to be a specific person and simulate a dialogue with a business partner or a complainer, with an emotion engine that recognizes the user's emotions. Specifically, a user accesses the system and inputs a dialogue scenario between a specific person and a business partner or a complainer. Based on the input scenario and the specific person's knowledge and experience, the system utilizes the generative AI to pretend to be that person. Furthermore, the system is equipped with an emotion engine that recognizes the user's emotions, and when the user starts a simulation, the generative AI simulates a dialogue with a business partner or a complainer. At this time, the emotion engine recognizes the user's emotions and adjusts the generative AI's simulation results based on those emotions.

[1206] The processing flow of each embodiment will be described below.

[1207] "Example 1"

[1208] Step 1: A user accesses the system and selects a specific person.

[1209] Step 2: The system uses generative AI to immerse itself in the role of the selected person, based on their knowledge and experience.

[1210] Step 3: When the user starts the simulation, the generative AI will suggest tactics and training menus based on the specific person's knowledge and experience.

[1211] Step 4: The emotion engine recognizes the user's emotions and adjusts the generative AI's suggestions based on those emotions.

[1212] "Example 2"

[1213] Step 1: A user accesses the system and enters information about a specific person, such as their resume and aptitude test results.

[1214] Step 2: The system uses generative AI to immerse itself in the role of a specific person based on the input information and their knowledge and experience.

[1215] Step 3: When the user starts the simulation, the generative AI simulates the employee's performance after joining the company or after being transferred.

[1216] Step 4: The emotion engine recognizes the user's emotions and adjusts the generative AI simulation results based on those emotions.

[1217] "Example 3"

[1218] Step 1: The user accesses the system and enters a dialogue scenario between a specific person and a business partner or complainant.

[1219] Step 2: Based on the input scenario and the specific person's knowledge and experience, the system uses generative AI to immerse itself in that role.

[1220] Step 3: When the user starts the simulation, the generative AI simulates a conversation with a business partner or a complainant.

[1221] Step 4: The emotion engine recognizes the user's emotions and adjusts the generative AI simulation results based on those emotions.

[1222] Example 1

[1223] 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."

[1224] Conventional generative AI systems can suggest tactics and training menus based on the knowledge and experience of a specific person, but they have the problem of not being able to make suggestions that take the user's emotions into account. This has led to the problem that they are unable to make optimal suggestions based on the user's condition, making it difficult to achieve effective simulations and training.

[1225] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for a generative AI to pose as a specific person and perform various simulations, a means for the generative AI to propose tactics, training menus, etc. based on the knowledge and experience of the specific person, a means for the generative AI to simulate the behavior of the specific person, and a means for adjusting the generative AI's proposals based on the user's emotions by combining an emotion engine that recognizes the user's emotions. This enables optimal proposals that take the user's emotions into consideration, resulting in more effective simulations and training.

[1226] "Generative AI" is artificial intelligence that mimics the knowledge and experience of a specific person and generates responses and suggestions by impersonating that person.

[1227] "Simulation" is a method of virtually recreating specific situations or conditions and predicting and analyzing the actions and results that would occur within them.

[1228] "Tactics" are specific methods or plans for achieving a specific purpose.

[1229] A "practice menu" is specific training content designed to improve a particular skill or ability.

[1230] An "emotion engine" is software or hardware for recognizing a user's emotions and analyzing the emotion data.

[1231] "Adjusting suggestions" means changing and optimizing the responses and suggestions provided by generative AI based on the user's emotions and state.

[1232] "User" means an individual or organization that uses the system.

[1233] A "server" is a computer that is the core of the system and is a device that includes hardware and software for executing various functions, including generative AI and emotion engines.

[1234] MODE FOR CARRYING OUT THE INVENTION

[1235] This invention is a system in which a generative AI takes on the role of a specific person and performs various simulations. A specific embodiment of this system is described below.

[1236] System configuration

[1237] 1. Hardware and Software Configuration

[1238] Server: The central computer of the system, including the hardware and software required to run the generative AI model and emotion engine. Specifically, a server equipped with a high-performance processor and large memory capacity is required.

[1239] Terminal: A device used by a user to access the system, such as a PC or smartphone. The system is accessed using a web browser (e.g., Google Chrome, Mozilla Firefox).

[1240] Generative AI model: An artificial intelligence model that imitates the knowledge and experience of a specific person, specifically OpenAI's GPT-4.

[1241] Emotion engine: Software or hardware for recognizing user emotions, specifically Affectiva's emotion recognition API.

[1242] 2. Data processing and calculation

[1243] User access: The user accesses the system using a terminal and selects a specific person. The information of the selected person is sent to the server.

[1244] Activating the generative AI: The server retrieves the profile data of the selected person and activates the generative AI model, which generates responses and suggestions based on the selected person's knowledge and experience.

[1245] Emotion Recognition: The server uses the emotion engine to analyze the user's facial expressions and voice data in real time to recognize their emotional state. The recognized emotion data is sent to the server.

[1246] Suggestion Adjustment: The server uses generative AI to suggest tactics and practice exercises to the user, and these suggestions are adjusted taking into account the user's emotional data.

[1247] Specific examples

[1248] Let's say a user is looking for a basketball training menu. The user accesses the system and selects a professional basketball coach. The generative AI then immerses itself in the role of the coach, recognizing the user's emotions and suggesting an appropriate training menu.

[1249] Example prompt sentence:

[1250] "I'm a basketball player and I'd like to know what kind of training routine is most effective for my next game. As a professional basketball coach, please suggest the best training routine for me."

[1251] In this way, the user can utilize the knowledge and experience of a specific person and receive appropriate suggestions according to their emotions.

[1252] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1253] Step 1:

[1254] A user accesses the system.

[1255] Specific actions: The user opens a web browser (Google Chrome, Mozilla Firefox, etc.) using a device (PC, smartphone, etc.).

[1256] Input: User login information (username, password).

[1257] Data processing: The server authenticates the user's login information.

[1258] Output: If authentication is successful, the user can access the main screen of the system.

[1259] Step 2:

[1260] The user selects a particular person.

[1261] Specific Actions: The user selects a specific person (e.g., a professional soccer coach) on the system interface using drop-down menus or the search function.

[1262] Input: The ID of the person selected by the user.

[1263] Data processing: The server retrieves the profile data of the selected person from the database.

[1264] Output: The profile data of the selected person is sent to the server.

[1265] Step 3:

[1266] The server activates a generative AI that takes on the role of the selected person.

[1267] Specific operation: The server retrieves the profile data of the selected person and launches a generative AI model (e.g., OpenAI's GPT-4).

[1268] Input: Profile data of the selected person.

[1269] Data processing: The server inputs the profile data into the generative AI, which prepares to generate a response based on the person's knowledge and experience.

[1270] Output: The generative AI is ready to mimic the tone and expertise of the selected person.

[1271] Step 4:

[1272] The server recognizes the user's emotions.

[1273] Specific operation: The server uses an emotion engine (e.g., Affectiva's emotion recognition API) to analyze the user's facial expressions and voice data in real time.

[1274] Input: User's facial expression and voice data.

[1275] Data processing: The emotion engine acquires data from the user's camera and microphone and recognizes their emotional state (e.g., joy, sadness, fatigue, etc.).

[1276] Output: The recognized emotion data is sent to the server.

[1277] Step 5:

[1278] The server will suggest tactics and training menus.

[1279] How it works: The server uses generative AI to suggest tactics and training options to the user, and these suggestions are adjusted based on the user's emotional data.

[1280] Input: User emotion data, selected person profile data.

[1281] Data processing: The server uses the emotion data to modify and optimize the responses and suggestions provided by the generative AI.

[1282] Output: The optimal tactics and training menus are suggested to the user based on their emotions.

[1283] (Application example 1)

[1284] 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."

[1285] Conventional generative AI systems can perform simulations based on the knowledge and experience of a specific person, but they cannot adjust their suggestions to take the user's emotions into account, making it difficult to reduce user stress and fatigue. Furthermore, in factory work environments, there is a need for efficient work procedures based on the knowledge and experience of skilled workers, but the lack of real-time feedback poses a challenge in that it is difficult to fully improve work efficiency.

[1286] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes: means for a generative AI to pretend to be a specific person and perform various simulations; means for the generative AI to suggest tactics, practice menus, etc. based on the specific person's knowledge and experience; means for the generative AI to simulate the specific person's behavior; means for an emotion engine to recognize a user's emotions and adjust the generative AI's suggestions based on those emotions; means for the generative AI to suggest work procedures and efficient work methods based on the knowledge and experience of a specific skilled worker; means for the emotion engine to recognize the worker's stress and fatigue and adjust the suggestions based on that; and means for providing feedback in real time. This makes it possible to adjust suggestions taking the user's emotions into consideration, thereby improving work efficiency and reducing stress and fatigue.

[1287] "Generative AI" is an artificial intelligence that performs simulations based on the knowledge and experience of a specific person and suggests tactics and training menus.

[1288] An "emotion engine" is a system that recognizes the user's emotions and adjusts the generative AI's suggestions based on those emotions.

[1289] A "specific person" is an individual who has the knowledge and experience that the generative AI will simulate.

[1290] "Simulation" is the process of virtually recreating the actions and tactics of a particular individual.

[1291] "Tactics" are specific methods or means for achieving a specific purpose.

[1292] A "practice menu" is a training program designed to improve a particular skill or ability.

[1293] A "work procedure" is a specific step or method for efficiently performing a specific task.

[1294] An "efficient work method" is a way of working that achieves maximum results with minimum time and effort.

[1295] "Real-time feedback" refers to evaluation and advice provided immediately while you work.

[1296] "Stress" refers to the mental or physical strain or tension felt by workers.

[1297] "Fatigue" refers to the physical or mental tiredness or exhaustion experienced by a worker.

[1298] A system for implementing this invention includes a generative AI, an emotion engine, and a real-time feedback function. A specific embodiment of this system will be described below.

[1299] System Configuration

[1300] The system uses the following hardware and software:

[1301] Hardware: Factory robots, emotion-recognition cameras

[1302] Software: OpenAI API, emotion_recognition library

[1303] Program processing

[1304] The server uses generative AI to suggest work procedures and efficient methods based on the knowledge and experience of specific skilled workers. The emotion engine recognizes the worker's stress and fatigue through an emotion-recognition camera and adjusts the generative AI's suggestions based on those emotions. Furthermore, by providing feedback in real time, it aims to improve work efficiency and reduce worker stress and fatigue.

[1305] Specific examples

[1306] For example, when a factory robot is tasked with assembling parts, a generative AI might suggest an efficient workflow using the following prompt:

[1307] You are Yamada, a skilled worker. Please suggest steps to efficiently perform the following tasks:

[1308] 1. Assembling the parts

[1309] 2. Inspection

[1310] 3. Packaging

[1311] If the emotion-aware camera detects that a worker is stressed or fatigued, the emotion engine will use that information to tailor its suggestions. For example, if a worker is feeling stressed, the generative AI will add advice such as, "It's recommended that you take a break."

[1312] In this way, by combining generative AI with an emotion engine, the server can adjust suggestions to take the user's emotions into account, improving work efficiency and reducing stress and fatigue.

[1313] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1314] Step 1:

[1315] The server acquires video data of the worker through an emotion recognition camera. The input is video data, and the output is data passed to the emotion recognition engine. Specifically, the camera captures the worker's facial expressions and sends the data to the server in real time.

[1316] Step 2:

[1317] The server uses an emotion recognition engine to recognize the worker's emotions from the video data. The input is the video data acquired in step 1, and the output is the recognized emotion data. Specifically, the emotion recognition engine analyzes the video data and determines the worker's stress and fatigue levels.

[1318] Step 3:

[1319] The server sends prompts to the generative AI to generate work procedures and efficient work methods. The input is the prompt, and the output is the generated work procedures. Specifically, the server sends the following prompt to the generative AI:

[1320] You are Yamada, a skilled worker. Please suggest steps to efficiently perform the following tasks:

[1321] 1. Assembling the parts

[1322] 2. Inspection

[1323] 3. Packaging

[1324] Step 4:

[1325] The generative AI generates a work procedure based on the prompt sentence and sends it back to the server. The input is the prompt sentence and the output is the generated work procedure. Specifically, the generative AI generates an efficient work procedure based on the knowledge and experience of a specific skilled worker.

[1326] Step 5:

[1327] The server adjusts the generated work steps based on the emotion data from the emotion recognition engine. The input is the emotion data and the generated work steps, and the output is the adjusted work steps. Specifically, the server adds advice such as "We recommend taking a break" to the work steps depending on the worker's stress and fatigue level.

[1328] Step 6:

[1329] The server provides feedback of the adjusted work procedures to the worker in real time. The input is the adjusted work procedures, and the output is the feedback provided to the worker. Specifically, the server communicates the adjusted work procedures to the worker via a display or voice.

[1330] Step 7:

[1331] The user (worker) performs work based on the feedback provided by the server. The input is the feedback from the server, and the output is the actual work result. In concrete terms, the worker assembles, inspects, and packs parts according to the adjusted work procedures.

[1332] Example 2

[1333] Next, a description will be given of 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."

[1334] Conventional simulation systems were able to run simulations based on the knowledge and experience of specific individuals, but they were unable to adjust the simulation results to take into account the user's emotions. As a result, the simulation results sometimes deviated from the real situation, making them less useful to users. In addition, simulations based on information such as resumes and aptitude test results were limited, making it difficult to accurately predict how an individual would perform after joining the company or being transferred.

[1335] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for a generative AI to pretend to be a specific person and perform various simulations; a means for the generative AI to propose tactics, practice menus, etc. based on the specific person's knowledge and experience; a means for the generative AI to simulate the specific person's behavior; a means for an emotion engine to recognize a user's emotions and adjust the simulation results of the generative AI based on the emotions; a means for a user to input information such as a specific person's resume or aptitude test results; a means for the server to receive input data and pass the data to the generative AI model; a means for the generative AI model to execute a simulation and adjust the simulation results based on data from the emotion engine; and a means for the server to display the final simulation results to the user. This makes it possible to provide realistic simulation results that take the user's emotions into consideration.

[1336] "Generative AI" is an artificial intelligence that performs various simulations by taking on the role of a specific person based on their knowledge and experience.

[1337] An "emotion engine" is software that recognizes emotions from the user's facial expressions and voice, and adjusts the simulation results based on those emotions.

[1338] A "server" is a computer system whose role is to receive input data from users, pass the data to the generative AI model, and display the final simulation results to the user.

[1339] A "resume" is a document that lists information such as a person's educational background, work history, and skill set.

[1340] "Aptitude test results" are data that show the results of an evaluation of a specific person's abilities, personality, aptitude, etc.

[1341] "Simulation" is the process of virtually recreating a real-world situation based on specific conditions and data.

[1342] A "user" is a person who accesses the system, enters information about a specific person, and runs a simulation.

[1343] A "database" is a collection of data that stores input information and can be retrieved as needed.

[1344] An "input form" is an interface that allows a user to input specific information into a system.

[1345] A "prompt sentence" is a sentence that prompts the user to input specific information.

[1346] MODE FOR CARRYING OUT THE INVENTION

[1347] This invention is a system that simulates a specific person's performance after joining the company or after being transferred, based on their knowledge and experience, using information such as their resume and aptitude test results.It also has the function of recognizing the user's emotions and adjusting the simulation results based on those emotions.

[1348] Hardware and software used

[1349] This system uses the following hardware and software:

[1350] Hardware: Servers, terminals

[1351] Software: Generative AI model, emotion engine

[1352] System Operation

[1353] The server receives input data from users and passes the data to the generative AI model. When a user enters a specific person's resume or aptitude test results, the server processes this data and passes it to the generative AI model.

[1354] The generative AI model runs a simulation based on the input information and the knowledge and experience of a specific person, and predicts how they will perform after joining the company or being transferred.

[1355] The emotion engine has the ability to recognize the user's emotions. When the user starts a simulation, the emotion engine analyzes the user's emotions in real time and adjusts the simulation results of the generative AI model based on those emotions.

[1356] Specific examples

[1357] For example, consider the case where this system is used in the human resources industry for job hunting or transfer interviews. A user accesses the system and inputs a specific person's resume and aptitude test results. For example, a person's resume information might include "Education: University, Work History: Engineer, Skills: Programming." The server receives this data and passes it to the generative AI model. The generative AI model uses the specific person's knowledge and experience to simulate how well they will perform after joining the company or being transferred.

[1358] During the simulation, the emotion engine recognizes "expectations" from the user's facial expressions. The server passes this emotion data to the generative AI model, which then adjusts the simulation results. Finally, the server displays the adjusted simulation results to the user. For example, it displays a result such as "This person is likely to be promoted to project leader within three months of joining the company."

[1359] Prompt Sentence Examples

[1360] "Enter a specific person's resume and aptitude test results. The system will use this information to simulate how they will perform after joining the company or being transferred. The system will also reflect the emotions felt during the simulation, so please feel free to use it."

[1361] In this way, the system can provide more realistic simulation results while taking into account the user's emotions.

[1362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1363] Step 1:

[1364] A user accesses the system. The user accesses the system using a web browser or a dedicated application. For example, the user opens a web browser and enters the system's URL to access it. The input is the system's URL, and the output is the system's home screen.

[1365] Step 2:

[1366] A user inputs a resume or aptitude test results for a specific person. A user inputs a resume or aptitude test results for a specific person into an input form in the system. For example, the user inputs information such as name, educational background, work history, and skill set. The input is the data of the resume or aptitude test results, and the output is the transmission of the input data.

[1367] Step 3:

[1368] The server receives input data. The server receives data entered by the user and saves it in a database. For example, the information entered in a resume is stored in a database. The input is the data sent by the user, and the output is saving it in a database.

[1369] Step 4:

[1370] The server passes data to the generative AI model. The server passes stored data to the generative AI model. For example, data such as resumes or aptitude test results are sent to the generative AI model. The input is data stored in the database, and the output is data sent to the generative AI model.

[1371] Step 5:

[1372] The generative AI model runs a simulation based on the data it receives. For example, it predicts how a specific person will perform after joining the company or being transferred based on their knowledge and experience. The input is the data sent from the server, and the output is the simulation results.

[1373] Step 6:

[1374] The emotion engine recognizes the user's emotions. The emotion engine recognizes emotions from the user's facial expressions and voice. For example, if the user is connected to the system via a camera or microphone, the emotion engine analyzes the user's emotions in real time. The input is the user's facial expressions and voice data, and the output is the recognized emotion data.

[1375] Step 7:

[1376] The server passes data from the emotion engine to the generative AI model. The server passes the user's emotion data recognized by the emotion engine to the generative AI model. For example, if the user is feeling anxious, that information is sent to the generative AI model. The input is emotion data from the emotion engine, and the output is data sent to the generative AI model.

[1377] Step 8:

[1378] The generative AI model adjusts the simulation results. The generative AI model adjusts the simulation results based on the user's emotional data. For example, if the user is feeling anxious, the simulation results are fine-tuned taking that emotion into account. The input is emotional data, and the output is the adjusted simulation results.

[1379] Step 9:

[1380] The server displays the final simulation results to the user. The server displays the adjusted simulation results to the user. For example, it displays the simulation results as graphs or text on a web browser. The input is the adjusted simulation results, and the output is what is displayed to the user.

[1381] (Application example 2)

[1382] 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."

[1383] Conventional simulation systems were capable of running simulations based on the knowledge and experience of a specific person, but were unable to run simulations based on the historical data or performance evaluation results of a specific machine or robot. Furthermore, simulation results were not adjusted to take user emotions into account, making it difficult to accurately predict performance in a real work environment. This led to problems such as factory managers being unable to obtain sufficient information when evaluating the suitability of a new robot, making it difficult to make appropriate decisions.

[1384] 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.

[1385] In this invention, the server includes: means for the generative AI to pretend to be a specific person and perform various simulations; means for the generative AI to suggest tactics and training menus based on the specific person's knowledge and experience; means for the generative AI to simulate the specific person's behavior; means for the generative AI to simulate performance in a specific work environment based on the historical data and performance evaluation results of a specific machine; and means including an emotion engine that recognizes the user's emotions and adjusts the simulation results based on those emotions. This enables factory managers to more accurately evaluate the suitability of new robots.

[1386] "Generative AI" is artificial intelligence that performs various simulations based on the knowledge and experience of a specific person or machine.

[1387] "Simulation" is a means of virtually reproducing behavior or performance under specific conditions or environments.

[1388] "Knowledge and experience" is a general term for the information and achievements that a specific person or machine has acquired in the past.

[1389] "Historical data" is a record of the work a particular machine or robot has done in the past and the results of that work.

[1390] "Performance evaluation results" are evaluation results such as the work speed, accuracy, and failure rate of a specific machine or robot.

[1391] An "emotion engine" is a system that recognizes the user's emotions and adjusts the simulation results based on those emotions.

[1392] "Work environment" is a general term for the location and conditions under which a particular machine or robot actually performs its work.

[1393] "Performance" refers to the efficiency or effectiveness with which a particular machine or robot performs a task.

[1394] A "factory manager" is a person responsible for managing the operation of machines and robots within a factory.

[1395] A system for implementing this invention includes a generative AI, an emotion engine, an interface for inputting historical data and performance evaluation results, and a display for displaying simulation results. Specific embodiments of this system are described below.

[1396] The server uses generative AI to perform simulations based on the knowledge and experience of specific people and machines. The generative AI simulates performance in specific work environments based on historical data and performance evaluation results of specific machines. In addition, an emotion engine recognizes the user's emotions and adjusts the simulation results based on those emotions.

[1397] Specifically, the server performs the following process: First, the user inputs the historical data and performance evaluation results of a specific machine through the interface. Next, the emotion engine analyzes the user's facial expressions and voice data to recognize the user's emotions. This can be done using software such as the Emotion Recognition API. The recognized emotion data is fed back to the generative AI, which adjusts the simulation results.

[1398] Generative AI uses OpenAI's API to run simulations based on input data and prompts, such as the following:

[1399] Robot history data: Working speed: High, Accuracy: High, Failure rate: Low

[1400] User Emotion: Stress

[1401] Simulate how this robot would perform in a specific work environment.

[1402] The simulation results are displayed on a screen, allowing users to evaluate the suitability of a new robot. For example, when a factory manager introduces a new robot, they input data such as the robot's past work speed, accuracy, and failure rate, and the emotion engine recognizes the manager's current emotions (e.g., stress or anxiety). The generative AI model then adjusts the simulation results based on those emotions, allowing the manager to more accurately evaluate the suitability of the new robot.

[1403] In this way, by combining generative AI with an emotion engine, the server can provide simulation results that take into account the user's emotions and more accurately evaluate the suitability of specific machines or robots.

[1404] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1405] Step 1:

[1406] The user uses a terminal to input historical data and performance evaluation results for a specific machine. The input data includes work speed, accuracy, failure rate, etc. This data is then sent to the server.

[1407] Step 2:

[1408] The server analyzes the received historical data and performance evaluation results and passes them to the generative AI. Analysis includes formatting and normalizing the data. For example, it complements missing values ​​and converts the data into a unified format.

[1409] Step 3:

[1410] The user uses a terminal to input information to the emotion engine to recognize their emotions. The input includes facial expression images and voice data. This data is then sent to the server.

[1411] Step 4:

[1412] The server uses an emotion engine to analyze the user's emotions. For the analysis, software such as the Emotion Recognition API is used. The analysis result is the user's emotions (e.g., stress, anxiety, joy, etc.).

[1413] Step 5:

[1414] The server generates prompts for the generative AI based on historical data, performance evaluation results, and user emotions. An example of a prompt is, "Robot historical data: Work speed: Fast, Accuracy: High, Failure rate: Low, User emotion: Stress. Please simulate how this robot would perform in a specific work environment."

[1415] Step 6:

[1416] The server uses a generative AI to run a simulation based on the prompt text. The generative AI uses OpenAI's API to analyze the input data and the prompt text and generate simulation results.

[1417] Step 7:

[1418] The server transmits the generated simulation results to the terminal, which include the performance of the machine in a specific working environment.

[1419] Step 8:

[1420] The user can use the terminal to check the simulation results, and based on the results, the user can evaluate the suitability of the new robot and make appropriate decisions.

[1421] Example 3

[1422] Next, a description will be given of 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."

[1423] Conventional simulation systems have the problem that the responses of generative AI, which pretends to be a specific person, are fixed and cannot respond flexibly to the user's emotions. Furthermore, they lack the ability to generate responses in real time based on dialogue scenarios entered by the user, making it difficult to obtain effective feedback when practicing actual business negotiations or handling complaints. Furthermore, they lack the ability to recognize the user's emotions and adjust the generative AI's responses based on them, making it impossible to reduce the user's tension and stress.

[1424] 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.

[1425] In this invention, the server includes a means for a user to input a dialogue scenario, a means for the server to analyze the scenario, a means for the server to call a generative AI model, a means for the server to activate an emotion engine, a means for the server to recognize the user's emotions, a means for the server to adjust the response of the generative AI model, and a means for the user to check the simulation results. This allows responses to be generated in real time based on the dialogue scenario input by the user, enabling flexible responses according to the user's emotions. It also reduces tension and stress for the user and provides effective feedback.

[1426] "Generative AI" is an artificial intelligence that takes on the role of a specific person and performs various simulations based on that person's knowledge and experience.

[1427] A "dialogue scenario" is text data input by a user that indicates the content and flow of a dialogue based on a specific situation or purpose.

[1428] A "server" is a computer system that receives input from the user and performs processes such as analyzing the scenario, calling the generative AI model, activating the emotion engine, recognizing the user's emotions, and adjusting the response of the generative AI model.

[1429] The "emotion engine" is software that analyzes the user's facial expressions and voice data to recognize the user's emotional state in real time.

[1430] A "generative AI model" is an artificial intelligence model that generates responses in natural language based on input data.

[1431] "Simulation results" are data that includes the content of the dialogue that the generative AI conducted based on user input, as well as the user's emotional state as recognized by the emotion engine.

[1432] "Response adjustment" is the process of changing the response content of the generative AI model based on the user's emotions recognized by the emotion engine.

[1433] This invention is a system in which a generative AI plays the role of a specific person and performs various simulations. The system involves a user inputting a dialogue scenario, a server analyzing the scenario, calling up a generative AI model, activating an emotion engine to recognize the user's emotions, and adjusting the generative AI model's response, allowing the user to check the simulation results.

[1434] Hardware and software used

[1435] Hardware

[1436] Server: A high-performance computer system that receives input from users and performs processes such as analyzing scenarios, calling generative AI models, activating emotion engines, recognizing user emotions, and adjusting the generative AI model's responses.

[1437] Terminal: A device used by a user to access the system, including PCs and smartphones.

[1438] software

[1439] Generative AI models: Artificial intelligence models that generate responses in natural language based on input data, such as OpenAI's GPT-4.

[1440] Emotion engine: Software such as Affectiva's emotion recognition software that analyzes a user's facial expressions and voice data to recognize the user's emotional state in real time.

[1441] Text analysis engine: Natural language processing technology, such as SpaCy, for analyzing user-entered scenario data.

[1442] Data processing and calculation

[1443] The server receives the dialogue scenario entered by the user and analyzes it using a text analysis engine. Based on the analysis results, it invokes a generative AI model and generates a response appropriate to the scenario. The emotion engine collects the user's facial expressions and voice data and analyzes their emotional state. The server adjusts the generative AI model's response based on the recognized user emotion and provides appropriate feedback to the user.

[1444] Specific examples

[1445] For example, a user inputs a "sales negotiation scenario in which a new product is proposed" and starts a simulation. In response to the question, "What are the features of this new product?", the generative AI model responds, "This new product is equipped with the latest technology and is more efficient than previous products." If the emotion engine detects tension in the user's facial expression, the generative AI model responds, "Please relax and speak, it's okay," and adjusts to ease the user's tension.

[1446] Prompt Sentence Examples

[1447] "Enter a sales scenario where you are proposing a new product. For example, ask, 'What are the features of this new product?'"

[1448] This system allows users to practice actual business negotiations and complaint handling, and based on the results, identify areas for improvement. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1449] Step 1:

[1450] A user accesses the system

[1451] A user accesses the system's web interface using a terminal (PC or smartphone). Specifically, the user opens a browser and enters the system's URL. The input is the user's access request, and the output is the system's homepage display.

[1452] Step 2:

[1453] The user inputs a dialogue scenario

[1454] The user inputs a dialogue scenario on the system interface. For example, for a "business negotiation scenario to propose a new product," the user might input "What are the features of this new product?" The input is the user's scenario text, and the output is the transmission of the scenario data to the server.

[1455] Step 3:

[1456] The server analyzes the scenario

[1457] The server receives the scenario entered by the user and analyzes it using natural language processing (NLP) technology. Specifically, it uses a text analysis engine (e.g., SpaCy) to understand the context and intent of the scenario. The input is the scenario data, and the output is the analysis results.

[1458] Step 4:

[1459] The server calls the generative AI model

[1460] The server invokes a generative AI model (such as OpenAI's GPT-4) based on the analysis results to generate a response appropriate to the scenario. For example, it generates a response such as, "This new product is equipped with the latest technology and is more efficient than our previous product." The input is the analysis result, and the output is the generated response.

[1461] Step 5:

[1462] The server starts the emotion engine

[1463] The server runs an emotion engine (e.g., Affectiva's emotion recognition software) to recognize the user's emotions in real time. The emotion engine collects the user's facial and voice data and analyzes their emotional state. The input is the user's facial and voice data, and the output is the emotion analysis result.

[1464] Step 6:

[1465] The server starts the simulation

[1466] The server connects the generative AI model and the emotion engine to start a dialogue simulation. The user interacts with the generative AI model on the system. The input is the generated response and the emotion analysis results, and the output is a dialogue log with the user.

[1467] Step 7:

[1468] The server recognizes the user's emotions

[1469] The server recognizes the user's emotions in real time through the emotion engine. For example, if the user is nervous, the emotion engine will detect that nervousness. The input is the user's facial expression and voice data, and the output is the emotion recognition result.

[1470] Step 8:

[1471] The server adjusts the response of the generative AI model

[1472] The server adjusts the response of the generative AI model based on the recognized user emotion. For example, if the user is nervous, the generative AI model responds by saying, "Please relax and speak freely." The input is the emotion recognition result, and the output is the adjusted response.

[1473] Step 9:

[1474] The user checks the simulation results

[1475] After the dialogue simulation is completed, the user checks the simulation results. The system displays the dialogue log and changes in emotions, providing feedback to help the user identify areas for improvement. The input is the dialogue log and emotion recognition results, and the output is a display of the simulation results.

[1476] (Application example 3)

[1477] 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."

[1478] With conventional customer service training methods, it was difficult to simulate actual customer interactions, limiting the ability to improve staff skills. Furthermore, there was no system that could recognize users' emotions in real time and provide corresponding feedback, making it impossible to effectively improve staff's ability to respond in actual customer service situations. This was an obstacle to improving customer satisfaction and staff growth.

[1479] 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.

[1480] In this invention, the server includes a means for a generative AI to pretend to be a specific person and perform various simulations, a means for the generative AI to suggest tactics and training menus based on the specific person's knowledge and experience, a means for the generative AI to simulate the specific person's behavior, a means for an emotion recognition engine to recognize a user's emotions and adjust the results of the generative AI's simulation based on those emotions, and a means for a user to perform a dialogue simulation using a smart device. This enables store staff to improve their skills through realistic customer service simulations.

[1481] "Generative AI" is an artificial intelligence that takes on the role of a specific person and performs various simulations based on that person's knowledge and experience.

[1482] An "emotion recognition engine" is an engine that recognizes the user's emotions in real time and adjusts the simulation results based on those emotions.

[1483] A "smart device" is an electronic device, such as a smartphone or a head-mounted display, that users use to conduct interactive simulations.

[1484] "Dialogue simulation" is a system in which generative AI takes on the role of a specific person and engages in dialogue with the user, practicing actual customer service and business negotiations.

[1485] "Tactics and training menus" are specific methods and plans for users to improve their skills that are suggested by generative AI based on the knowledge and experience of a specific person.

[1486] "Simulation results" are the responses and actions based on a specific scenario that are generated by generative AI through dialogue with the user.

[1487] The following describes the mode for carrying out the present invention: First, the system includes the following main components:

[1488] 1. Generative AI

[1489] Generative AI is an artificial intelligence that performs various simulations by taking on the role of a specific person based on their knowledge and experience. Generative AI generates dialogue based on a scenario entered by the user and interacts with the user.

[1490] 2. Emotion Recognition Engine

[1491] The emotion recognition engine is an engine that recognizes the user's emotions in real time and adjusts the simulation results based on those emotions. The emotion recognition engine analyzes the user's voice and text input to identify their emotional state.

[1492] 3. Smart Devices

[1493] Smart devices are electronic devices such as smartphones and head-mounted displays that users use to simulate interactions. These devices work in conjunction with generative AI and emotion recognition engines.

[1494] Program processing explanation

[1495] The server integrates generative AI, emotion recognition engines, and smart devices to operate. Specifically, it performs the following processes:

[1496] 1. Scenario input

[1497] The user inputs a dialogue scenario through a smart device. For example, a scenario in which a customer is asking about the features of a new product.

[1498] 2. Emotion recognition

[1499] The emotion recognition engine analyzes user input (voice or text) to identify the user's emotion. For example, if a user asks, "What are the features of this product?", the engine will recognize the user's emotion as "interest."

[1500] 3. Dialogue Generation

[1501] The generative AI generates appropriate dialogue based on user input and the results of the emotion recognition engine, for example, responding, "This product uses the latest technology and is particularly notable for its long battery life."

[1502] 4. Simulation Adjustment

[1503] The emotion recognition engine adjusts the generative AI's simulation results based on the user's emotions. For example, if the user expresses dissatisfaction, the generative AI will provide more detailed explanations or additional suggestions.

[1504] Specific examples

[1505] scenario

[1506] A customer is asking about the features of a new product.

[1507] User Input

[1508] "What are the features of this product?"

[1509] Emotion recognition results

[1510] interest

[1511] Generative AI response

[1512] "This product uses the latest technology, especially with its long battery life."

[1513] Prompt Sentence Examples

[1514] You are a staff member at a brick-and-mortar store. Please interact with customers based on the following scenario:

[1515] Scenario: A customer has a question about the features of a new product.

[1516] User: What are the features of this product?

[1517] Emotion: Interest

[1518] AI:

[1519] In this way, store staff can improve their skills through realistic customer service simulations.

[1520] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1521] Step 1:

[1522] The user inputs a dialogue scenario through a smart device.

[1523] Input: The user enters a scenario in which a customer is asking about the features of a new product.

[1524] Output: The input scenario is sent to the server.

[1525] Step 2:

[1526] The server receives the input scenario and generates a prompt for the generative AI.

[1527] Input: The scenario entered by the user.

[1528] Output: The prompt sent to the generative AI.

[1529] Specific operation: The server analyzes the scenario and generates a prompt for the generative AI: "You are a staff member at a physical store. Please interact with customers based on the following scenario."

[1530] Step 3:

[1531] The user inputs a question via a smart device.

[1532] Input: User types, "What are the features of this product?"

[1533] Output: The entered question is sent to the server.

[1534] Step 4:

[1535] The server receives the user's input and analyzes the emotion using an emotion recognition engine.

[1536] Input: The question entered by the user.

[1537] Output: Parsed emotion (e.g. interest).

[1538] Specific operation: The server uses an emotion recognition engine to identify emotions from the user's input text.

[1539] Step 5:

[1540] The server instructs the generative AI to generate a response based on the user's input and emotions.

[1541] Input: User input and parsed sentiment.

[1542] Output: The response generated by the generative AI.

[1543] Specific operation: The server sends the generative AI the instruction, "The user is interested, so please explain in detail the product's features."

[1544] Step 6:

[1545] The generative AI generates a response and sends it to the server.

[1546] Input: Instructions sent to the generative AI.

[1547] Output: The generated response (e.g., "This product uses the latest technology, especially its long battery life.").

[1548] Specific operation: The generative AI generates an appropriate response based on the prompt, user input, and emotion recognition results.

[1549] Step 7:

[1550] The server generates a response and sends it to the user's smart device.

[1551] Input: The response generated by the generative AI.

[1552] Output: The response that is displayed on the user's smart device.

[1553] Specific operation: The server sends the generated response to the user's smart device and displays it to the user.

[1554] Step 8:

[1555] The user reviews the response and enters their next question or feedback.

[1556] Input: The user enters their next question or feedback.

[1557] Output: The entered questions and feedback are sent to the server.

[1558] Specific operation: The user inputs the following questions and feedback through the smart device and sends them to the server.

[1559] In this way, users can improve their customer service skills through realistic dialogue simulations.

[1560] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1561] 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1562] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1563] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1564] [Third embodiment]

[1565] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1566] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1567] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1568] 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.

[1569] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1570] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1571] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1572] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1573] 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.

[1574] 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.

[1575] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1576] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1577] "Example 1"

[1578] One embodiment of the present invention is a system in which a generative AI plays the role of a specific person and performs various simulations. This system includes a means for proposing tactics and training programs based on the knowledge and experience of the specific person, and a means for simulating the behavior of the specific person. For example, in the sports industry, even if there is no professional coach, it is possible for players to freely select an actual professional coach and have them suggest tactics and training programs.

[1579] "Example 2"

[1580] Furthermore, it also includes a means of simulating the performance of a specific person after joining the company or after being transferred, based on the knowledge and experience of that person, information such as resumes and aptitude test results. For example, in the human resources industry, it is possible to simulate the performance of a person after joining the company or after being transferred, based on information such as resumes and aptitude test results, during job hunting or transfer interviews.

[1581] "Example 3"

[1582] It also includes a means of simulating conversations with a business partner or a complainer by pretending to be a specific person. For example, when practicing business negotiations or complaint handling, generative AI can pretend to be the business partner or the complainer and simulate actual conversations. This allows for practice of actual business negotiations or complaint handling, and the results can be used to identify areas for improvement.

[1583] The processing flow of each embodiment will be described below.

[1584] "Example 1"

[1585] Step 1: A user accesses the system and selects a specific person.

[1586] Step 2: The system uses generative AI to immerse itself in the role of the selected person, based on their knowledge and experience.

[1587] Step 3: When the user starts the simulation, the generative AI will suggest tactics and training menus based on the specific person's knowledge and experience.

[1588] "Example 2"

[1589] Step 1: A user accesses the system and enters information about a specific person, such as their resume and aptitude test results.

[1590] Step 2: The system uses generative AI to immerse itself in the role of a specific person based on the input information and their knowledge and experience.

[1591] Step 3: When the user starts the simulation, the generative AI simulates the employee's performance after joining the company or after being transferred.

[1592] "Example 3"

[1593] Step 1: The user accesses the system and enters a dialogue scenario between a specific person and a business partner or complainant.

[1594] Step 2: Based on the input scenario and the specific person's knowledge and experience, the system uses generative AI to immerse itself in that role.

[1595] Step 3: When the user starts the simulation, the generative AI simulates a conversation with a business partner or a complainant.

[1596] Example 1

[1597] 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 headset type terminal 314 will be referred to as a "terminal."

[1598] With conventional simulation systems, it was difficult to propose tactics or training menus based on the knowledge and experience of a specific person, and they were not able to realistically simulate the behavior of a specific person. As a result, there were issues with not being able to carry out effective learning and training when there was no specialized coach or when the player wanted to learn the behavior of a specific person.

[1599] 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.

[1600] In this invention, the server includes a means for a user to input information about a specific person using a terminal, a means for the server to acquire data about the specific person from a database, a means for the server to preprocess the acquired data and convert it into a format that can be input to a generative AI model, a means for the server to execute a simulation using the generative AI model, and a means for the server to transmit the simulation results to the terminal and display them to the user. This makes it possible to propose tactics and training menus based on the knowledge and experience of a specific person, and to realistically simulate the behavior of a specific person.

[1601] "Generative AI" is an artificial intelligence that performs simulations based on the knowledge and experience of a specific person and suggests tactics and training menus.

[1602] A "specific person" is an individual for whom the system will perform simulations and suggestions, such as a professional coach or expert.

[1603] "Simulation" is the process of virtually reproducing the actions and tactics of a specific person and providing the results to the user.

[1604] "Tactics" refers to the optimal action or plan in a particular situation, especially strategic behavior in sports and business.

[1605] A "practice menu" is a series of exercises or training sessions designed to achieve a specific goal.

[1606] "User" refers to an individual or organization that uses the system to learn from the knowledge and experience of a specific person.

[1607] A "terminal" is a device that allows a user to access the system, input information, and receive results, and includes, for example, a personal computer or smartphone.

[1608] The "server" is the central computer of the system, and is the device that acquires data, pre-processes it, runs the simulation, and transmits the results.

[1609] A "database" is a repository of information that stores knowledge and experience data about a specific person and that can be accessed by a server as needed.

[1610] "Preprocessing" refers to the process of data cleaning and format conversion to convert acquired data into a format that can be input into a generative AI model.

[1611] A "generative AI model" is an artificial intelligence algorithm that performs simulations based on the knowledge and experience of a specific person, and includes, for example, GPT-4.

[1612] "Simulation results" are the output data obtained after a generative AI model performs a simulation, and are information provided to the user.

[1613] This invention is a system that uses a generative AI model to perform various simulations by impersonating a specific person. This system includes a means for proposing tactics and training menus based on the knowledge and experience of the specific person, and a means for simulating the behavior of the specific person.

[1614] Hardware and software used

[1615] Server: The central computer of the system that acquires data, pre-processes it, runs simulations, and transmits the results. Specifically, it uses a database management system (e.g., MySQL) and a generative AI model (e.g., GPT-4).

[1616] Terminal: A device that allows a user to access the system, input information, and receive results. Examples include computers and smartphones.

[1617] Data processing and calculation

[1618] 1. User input:

[1619] A user accesses the system using a terminal and inputs information about a specific person, for example, a prompt such as "Please tell me the tactics of a specific professional coach."

[1620] 2. Data Acquisition:

[1621] The server receives input from the user and retrieves data related to a specific person from a database. For example, the server connects to a MySQL database and queries for tactics and training data related to a "specific professional coach."

[1622] 3. Data preprocessing:

[1623] The server preprocesses the acquired data. Specifically, it cleans the data and converts its format so that it can be input into a generative AI model. For example, it removes unnecessary spaces and special characters from text data and converts it to JSON format.

[1624] 4. Run the simulation:

[1625] The server inputs the preprocessed data into a generative AI model and runs a simulation. The generative AI model generates a response to the user's prompt based on the knowledge and experience of a specific person. For example, the generative AI model simulates "what tactics a specific professional coach will propose in the next game" and generates the results.

[1626] 5. Result output:

[1627] The server sends the simulation results obtained from the generative AI model to the device. The device then displays the received results to the user. For example, the device screen might say, "A specific professional coach suggests a 4-3-3 formation for the next match."

[1628] Examples of concrete examples and prompts

[1629] Consider the case where the user is an athlete and wants to learn the tactics of a particular professional coach.

[1630] Examples:

[1631] A user accesses the system using a terminal and inputs that he or she would like to learn the tactics of a particular professional coach.

[1632] The server retrieves data about the knowledge and experience of specific professional coaches from a database and inputs it into a generative AI model.

[1633] The server uses a generative AI model to simulate what tactics a specific professional coach would propose and displays the results to the user.

[1634] Example prompt sentence:

[1635] "Tell me what tactics a particular professional coach would suggest for the next game."

[1636] In this way, users can learn the tactics and training regimens of a particular professional coach.

[1637] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1638] Step 1:

[1639] A user accesses the system using a terminal and inputs information about a specific person. Specifically, the user enters a prompt such as "Please tell me the tactics of a specific professional coach" into the input form on the terminal and clicks the submit button. The input data is in the form of text containing questions or requests about a specific person.

[1640] Step 2:

[1641] The server receives input from the user and retrieves data related to a specific person from the database. Specifically, the server connects to a MySQL database and queries data on tactics and training menus related to a "specific professional coach." The input is the user's prompt, and the output is the data related to the specific person retrieved from the database.

[1642] Step 3:

[1643] The server preprocesses the acquired data. Specifically, it cleans the data and converts its format so that it can be input into a generative AI model. For example, it removes unnecessary spaces and special characters from text data and converts it into JSON format. The input is raw data acquired from the database, and the output is preprocessed data.

[1644] Step 4:

[1645] The server inputs the preprocessed data into a generative AI model and runs a simulation. The generative AI model generates a response to a user prompt based on the knowledge and experience of a specific person. For example, the generative AI model simulates "what tactics a specific professional coach will propose in the next game" and generates the results. The input is the preprocessed data, and the output is the simulation result generated by the generative AI model.

[1646] Step 5:

[1647] The server sends the simulation results obtained from the generative AI model to the device. The device then displays the received results to the user. For example, the device screen may display a message such as, "A specific professional coach suggests a 4-3-3 formation for the next game." The input is the simulation results from the generative AI model, and the output is the information displayed to the user.

[1648] (Application example 1)

[1649] 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."

[1650] Conventional industrial robots have difficulty optimizing their movements and work procedures by utilizing the knowledge and experience of specific workers. As a result, efficient work procedures were not adequately proposed or optimized, limiting productivity improvements. In addition, there were limited means to transfer the knowledge and experience of skilled workers to new workers, making it difficult to pass on skills. To solve these issues, a system is needed that utilizes the knowledge and experience of specific workers to optimize the movements and work procedures of industrial robots.

[1651] 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.

[1652] In this invention, the server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and practice menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to optimize the operation and work procedures of the industrial robot based on the knowledge and experience of the specific worker. This makes it possible to optimize the operation and work procedures of the industrial robot by utilizing the knowledge and experience of the specific worker, thereby improving productivity and enabling the transfer of technology.

[1653] "Generative AI" is an artificial intelligence system that imitates the knowledge and experience of a specific person and performs various simulations.

[1654] A "specific person" refers to an individual person with knowledge and experience, whose actions and thoughts are to be imitated.

[1655] "Simulation" is a method of virtually recreating real-world situations and behaviors to make predictions and analyses.

[1656] "Tactics" refers to specific methods or means for achieving a specific goal.

[1657] A "practice menu" refers to planned training content designed to improve specific skills or abilities.

[1658] "Behavior" refers to the specific actions or reactions taken by a particular person.

[1659] "Worker" refers to a person who performs a specific task or work.

[1660] An "industrial robot" refers to an automated mechanical device used in factories and production lines.

[1661] "Action" refers to the specific movements or operations performed by machines or humans.

[1662] A "work procedure" refers to a series of procedures or methods for efficiently performing a specific task.

[1663] "Optimization" refers to adjusting something to maximize efficiency or effectiveness in order to achieve a specific purpose.

[1664] As an embodiment of the present invention, the following system is constructed.

[1665] System Configuration

[1666] The server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and training menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to optimize the operation and work procedures of an industrial robot based on the knowledge and experience of a specific worker.

[1667] Program processing explanation

[1668] The server implements a generative AI model using Python and uses the OpenAI API to generate optimal work procedures based on the knowledge and experience of specific workers. Specifically, it performs the following processes:

[1669] 1. Data entry: The user enters the name of a specific worker and the task.

[1670] 2. Prompt generation: The server generates a prompt sentence for the generative AI model based on the input data.

[1671] 3. Calling the AI ​​model: The server uses OpenAI's API to send prompts to the generative AI model to generate optimal work procedures.

[1672] 4. Result output: The server outputs the generated optimal work procedure to the user.

[1673] Hardware and software used

[1674] Hardware: Industrial robots (e.g. KUKA, Fanuc, etc.), computers (for robot control)

[1675] Software: Python, OpenAI API

[1676] Specific examples

[1677] For example, when optimizing the assembly of parts based on the knowledge and experience of skilled worker A, the following prompt sentence is generated.

[1678] Prompt Sentence Examples

[1679] Based on the knowledge and experience of skilled worker A, optimize the following tasks.

[1680] Work: Assembly of parts

[1681] Please suggest the best procedure.

[1682] In this way, it is possible to utilize the knowledge and experience of specific workers to optimize the movements and work procedures of industrial robots, thereby improving productivity and ensuring the succession of skills.

[1683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1684] Step 1:

[1685] The user inputs the name of a specific worker and the task.

[1686] Input: Name of specific worker (e.g., skilled worker A), work content (e.g., parts assembly work)

[1687] Output: Input data (specific worker name, work content)

[1688] Specific operation: The user uses the terminal to enter the name of a specific worker and the work content into the input form and presses the submit button.

[1689] Step 2:

[1690] The server generates a prompt sentence for the generative AI model based on the input data.

[1691] Input: Data entered by the user (name of specific worker, work content)

[1692] Output: Generated prompt statement

[1693] Specific operation: The server receives the input data and generates a prompt like the following: "Based on the knowledge and experience of skilled worker A, please optimize the following task. Task: assembling parts. Please suggest the optimal work procedure."

[1694] Step 3:

[1695] The server uses OpenAI's API to send prompts to the generative AI model to generate optimal work procedures.

[1696] Input: Generated prompt text

[1697] Output: Response from the generative AI model (optimal work procedure)

[1698] How it works: The server sends the generated prompt to OpenAI's API and receives a response from the generative AI model, which includes the optimal work procedure.

[1699] Step 4:

[1700] The server outputs the generated optimal work procedure to the user.

[1701] Input: Response from the generative AI model (optimal work procedure)

[1702] Output: The optimal workflow displayed to the user

[1703] Specific operation: The server sends the optimal work procedure received from the generative AI model to the user's device and displays it on the user's screen.

[1704] Example 2

[1705] Next, a description will be given of 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."

[1706] With conventional talent evaluation systems, it was difficult to predict future performance based on a candidate's resume and aptitude test results. Furthermore, there was a lack of a way to utilize a specific person's knowledge and experience to simulate how they would perform after joining the company or being transferred. This made it difficult for companies to make appropriate personnel placement and hiring decisions, resulting in problems such as a decline in organizational efficiency and productivity.

[1707] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for a user to input candidate information, a means for a terminal to transmit the input data to the server, a means for the server to store the received data in a database, a means for the server to use a generative AI model to analyze the stored data, a means for the server to execute a simulation based on the analysis results, a means for the server to transmit the simulation results to the terminal, and a means for the terminal to display the results to the user. This makes it possible to predict future performance based on the candidate's resume and aptitude test results, allowing companies to make appropriate personnel placement and hiring decisions.

[1708] "Generative AI" is an artificial intelligence system that performs simulations based on the knowledge and experience of a specific person.

[1709] "User" means a person or organization that utilizes the system to enter candidate information.

[1710] A "terminal" is a device through which a user inputs information and displays simulation results.

[1711] A "server" is a computer system that receives, stores, analyzes, and runs simulations on data submitted by users.

[1712] A "database" is an information management system for storing data received by a server.

[1713] A "generative AI model" is an artificial intelligence algorithm that analyzes data based on the knowledge and experience of a specific person and generates simulation results.

[1714] A "resume" is a document that lists information such as a candidate's educational background, work history, and skills.

[1715] "Aptitude test results" are the results of a test to evaluate a candidate's abilities and personality.

[1716] A "simulation" is a hypothetical experiment designed to predict a candidate's future performance under specific conditions.

[1717] A "prompt statement" is an instruction statement entered into a generative AI model to perform analysis or simulation.

[1718] This invention is a system that simulates the performance of a specific person after joining the company or after being transferred, based on the person's knowledge and experience, as well as information such as their resume and aptitude test results. The system is composed of users, terminals, and a server.

[1719] Hardware and software used

[1720] Hardware: Servers, terminals

[1721] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), aptitude testing tools (e.g., SHL)

[1722] Specific operation of the system

[1723] 1. Data Entry

[1724] The user inputs the candidate's resume and aptitude test results into the terminal. Specifically, the user enters the required information into the web form and clicks the "Submit" button.

[1725] 2. Data Transmission

[1726] The terminal sends the input data to the server. Specifically, the terminal uses an HTTP POST request to send the input data to the server.

[1727] 3. Data storage

[1728] The server saves the received data in the database. Specifically, the server connects to the MySQL database and saves the data using the INSERT statement.

[1729] 4. Data Analysis

[1730] The server uses a generative AI model (e.g., GPT-4) to analyze the stored data. Specifically, the server runs a Python script to input prompts to the GPT-4 model and obtain the analysis results.

[1731] Example prompt: "Based on this candidate's resume and aptitude test results, simulate their performance as a software engineer."

[1732] 5. Run the simulation

[1733] Based on the analysis results, the server simulates the employee's performance after joining the company or after being transferred. Specifically, the server runs a simulation algorithm based on the analysis results obtained from the generative AI model and calculates predicted performance.

[1734] 6. Send results

[1735] The server sends the simulation results to the terminal. Specifically, the server generates an HTTP response and sends JSON data containing the simulation results to the terminal.

[1736] 7. Results display

[1737] The terminal then displays the results to the user by parsing the received JSON data and displaying the results on a web page, for example, visualizing the candidate's predicted performance in graphs or text format.

[1738] Specific examples

[1739] For example, suppose a candidate is applying for a software engineer position. The user inputs the candidate's resume and aptitude test results into the system. The server receives this data and analyzes it using a generative AI model (GPT-4). Based on the analysis results, the server simulates the candidate's performance after joining the company and sends the predicted results to the device. The device then displays the results to the user.

[1740] In this way, the system can simulate the candidate's future performance based on the data entered by the user and provide the results to the user.

[1741] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1742] Step 1:

[1743] Data Entry

[1744] The user inputs the candidate's resume and aptitude test results into the terminal.

[1745] Input: Resume, aptitude test results

[1746] What happens: A user fills in information on a web form and clicks the "Submit" button.

[1747] Output: The input data is saved to the device.

[1748] Step 2:

[1749] Data transmission

[1750] The terminal transmits the input data to the server.

[1751] Input: Data entered by the user

[1752] Specific operation: The device sends the input data to the server using an HTTP POST request.

[1753] Output: Data is sent to the server.

[1754] Step 3:

[1755] Data storage

[1756] The server stores the received data in a database.

[1757] Input: Data sent from the terminal

[1758] What happens: The server connects to the MySQL database and saves the data using an INSERT statement.

[1759] Output: The data is saved to a database.

[1760] Step 4:

[1761] Data analysis

[1762] The server uses a generative AI model (e.g., GPT-4) to analyze the stored data.

[1763] Input: Data stored in the database

[1764] Specific operation: The server runs a Python script, inputs a prompt to the GPT-4 model, and obtains the analysis results.

[1765] Example prompt: "Based on this candidate's resume and aptitude test results, simulate their performance as a software engineer."

[1766] Output: Analysis results are generated.

[1767] Step 5:

[1768] Simulation execution

[1769] Based on the analysis results, the server simulates how the employee will perform after joining the company or being transferred.

[1770] Input: Analysis results obtained from the generative AI model

[1771] What happens: The server runs a simulation algorithm to calculate predicted performance.

[1772] Output: Simulation results are generated.

[1773] Step 6:

[1774] Send results

[1775] The server transmits the simulation results to the terminal.

[1776] Input: Simulation results

[1777] Specific operation: The server generates an HTTP response and sends JSON data containing the simulation results to the terminal.

[1778] Output: Data is sent to the terminal.

[1779] Step 7:

[1780] Results display

[1781] The terminal displays the results to the user.

[1782] Input: JSON data sent from the server

[1783] What it does: The device parses the received JSON data and displays the results on a web page, for example, visualizing the candidate's predicted performance in graphs or text format.

[1784] Output: The user can check the simulation results.

[1785] (Application example 2)

[1786] 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."

[1787] Conventional simulations of personnel placement and robot operation rely heavily on experience and intuition, making it difficult to find optimal placement and operation. Furthermore, simulations based on resumes and aptitude test results are time-consuming and labor-intensive when performed manually, and suffer from low accuracy. This has prevented efficient personnel placement and robot operation within factories, hindering productivity improvements.

[1788] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to propose tactics, practice menus, etc. based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to simulate optimal personnel allocation and robot operations in a factory based on the resume and aptitude test results of the specific person. This enables highly accurate simulations based on resumes and aptitude test results, thereby realizing efficient personnel allocation and robot operations in a factory.

[1789] "Generative AI" is an artificial intelligence system that imitates the knowledge and experience of a specific person and performs various simulations and suggestions.

[1790] "Simulation" is a method of virtually recreating real-world situations based on specific conditions and data, and making predictions and analyses.

[1791] A "resume" is a document that lists information such as an individual's educational background, work history, and skills, and is used when applying for a job or transferring.

[1792] "Aptitude test results" are the results of tests used to evaluate an individual's abilities, personality, and aptitude, and are used to determine job suitability and placement.

[1793] "Staffing" refers to the allocation of the most suitable personnel to each position within an organization.

[1794] "Robot movement" refers to the series of tasks and movements performed by robots used in factories.

[1795] "Tactics" refers to specific methods or means for achieving a specific goal.

[1796] A "practice menu" refers to a training program or plan to improve a particular skill or ability.

[1797] The system for implementing this invention uses generative AI to mimic the knowledge and experience of a specific person and perform various simulations and proposals. Specifically, it includes a function to simulate optimal personnel allocation and robot operation within a factory based on resumes and aptitude test results.

[1798] The server uses the following hardware and software:

[1799] Hardware: PC or smartphone

[1800] Software: Python, Pandas, Scikit-learn

[1801] The server first reads resume and aptitude test result data from a CSV file. Then, it separates the data into features (years of experience, education level, skill score, etc.) and labels (performance). This allows for data preprocessing.

[1802] The server then trains a model using a random forest classifier, which is then used to simulate optimal staffing and robot behavior within a factory based on a specific person's knowledge and experience.

[1803] The user inputs the data of a new candidate and requests the server to run a simulation. The server uses the trained model to predict the new candidate's performance and proposes optimal personnel placement and robot behavior.

[1804] As a concrete example, the following prompt sentence is input to the generative AI model:

[1805] "Based on the resume data of a new candidate, simulate the optimal placement within a factory. The candidate has 5 years of experience, an education level of 3, and a skill score of 85."

[1806] Using this prompt, the generative AI model can analyze candidate data and predict optimal placement and performance, leading to efficient personnel placement and robot operation within factories.

[1807] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1808] Step 1:

[1809] The server reads data such as resumes and aptitude test results from CSV files. The input is a CSV file, and the output is data in data frame format. Specifically, the CSV file is read using the Python Pandas library and converted to a data frame.

[1810] Step 2:

[1811] The server separates the data into features and labels. The input is data in data frame format, and the output is data separated into features (years of experience, education level, skill score, etc.) and labels (performance). Specifically, it extracts specific columns from the data frame and separates them into features and labels.

[1812] Step 3:

[1813] The server trains a model using a random forest classifier. The input is data divided into features and labels, and the output is a trained model. Specifically, it creates a random forest classifier using the Scikit-learn library and trains the model using the features and labels.

[1814] Step 4:

[1815] The user inputs data on a new candidate. The input data includes the new candidate's years of experience, education level, skill score, etc., and the output is a simulation request to the server. Specifically, the user inputs the new candidate's data using a smartphone or PC and sends it to the server.

[1816] Step 5:

[1817] The server uses the trained model to predict the performance of new candidates. The input is the new candidate's data, and the output is the predicted performance. Specifically, the server inputs the new candidate's data into the model and obtains the predicted result.

[1818] Step 6:

[1819] The server proposes optimal personnel placement and robot operation based on the prediction results. The input is predicted performance, and the output is a proposal for optimal personnel placement and robot operation. As a specific operation, the server analyzes the prediction results and proposes optimal placement and operation within the factory.

[1820] Step 7:

[1821] The user receives the proposals from the server and reflects them in the actual deployment of personnel and the operation of the robots. The input is the proposal from the server, and the output is the actual deployment and operation. In terms of specific operations, the user checks the proposals and adjusts the deployment and operation of the robots within the factory.

[1822] Example 3

[1823] 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."

[1824] Conventional simulation systems have limited functionality for interacting with specific people, making it difficult to simulate situations that closely resemble real situations when practicing business negotiations or handling complaints. Furthermore, feedback on the simulation results is insufficient, making it difficult for users to identify areas for improvement. This has led to the issue of users being unable to fully improve their skills.

[1825] 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.

[1826] In this invention, the server includes: means for a generative AI to pretend to be a specific person and perform various simulations; means for the generative AI to propose tactics, practice menus, etc. based on the specific person's knowledge and experience; means for the generative AI to simulate the specific person's behavior; means for a user to access the system using a terminal and input a prompt; means for the server to call the generative AI model and generate dialogue content based on the prompt; means for the server to send the generated dialogue content to the user's terminal; means for the user to perform dialogue simulation; and means for the server to provide feedback on the simulation results. This allows the user to perform simulations that are similar to actual business negotiations or complaint handling and to identify areas for improvement based on the results.

[1827] "Generative AI" is artificial intelligence that can take on the role of a specific person and simulate conversations and actions.

[1828] A "prompt sentence" is text that a user enters to specify a simulation scenario.

[1829] A "server" is a computer system that hosts a generative AI model and processes requests from users.

[1830] A "terminal" is a device such as a PC or smartphone that a user uses to access the system.

[1831] "Dialogue content" refers to the simulated conversation content generated by the generative AI based on the prompt text.

[1832] "Feedback" refers to information on improvements and evaluations that are provided to users after analyzing the results of the simulation.

[1833] A "simulation" is the reproduction of hypothetical interactions and behaviors that a generative AI performs based on a specific scenario.

[1834] "Knowledge and experience" refers to the specialized information that a particular person possesses and the skills and know-how based on past achievements.

[1835] "Tactics and training menus" are specific action plans and training contents proposed by generative AI.

[1836] This invention is a system that uses generative AI to simulate a conversation with a specific person, such as a business partner or a complainer. Specific embodiments of this system are described below.

[1837] Hardware and software used

[1838] server:

[1839] The server hosts the generative AI model and processes requests from users. Specifically, OpenAI's GPT-4 is used as the generative AI model. The server sends prompts received from users to the generative AI model and sends the generated dialogue content to the user's device.

[1840] Device:

[1841] A terminal is a device that a user uses to access the system. It can be a PC, a smartphone, or other device. The terminal accesses the server through a web browser and provides an interface for entering prompts.

[1842] User:

[1843] The user uses the system to simulate business negotiations and complaint handling. The user accesses the system using a terminal and inputs prompt statements.

[1844] Data processing and calculation

[1845] Enter the prompt statement:

[1846] The user inputs a prompt statement that corresponds to the scenario they want to simulate. For example, they might input something like, "I would like to simulate a business negotiation in which a new product is proposed. I would like the business partner to ask detailed questions about the product's features and price."

[1847] Invoke the generative AI model:

[1848] The server sends the prompt received from the user to the generative AI model, which then generates dialogue content based on the prompt. The generated dialogue content is then sent to the user's device via the server.

[1849] Conducting a dialogue simulation:

[1850] The user then proceeds through the simulation based on the generated dialogue, asking and answering questions during the dialogue, practicing actual business negotiations and handling complaints.

[1851] Providing feedback:

[1852] After the simulation is completed, the server analyzes the results and provides feedback to the user, who can then use this feedback to identify areas for improvement.

[1853] Specific examples

[1854] If a user wants to simulate a business negotiation in which a new product proposal is made, he or she enters the following prompt sentence:

[1855] Example prompt sentence:

[1856] "I'd like to simulate a business negotiation in which I propose a new product. I'd like the other party to ask detailed questions about the product's features and price."

[1857] When this prompt is entered, the generative AI model plays the role of a salesperson and starts a simulation in which the user proposes a new product. The generative AI model asks questions about the product's features and price, and the user answers them, allowing the model to practice a real sales negotiation.

[1858] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1859] Step 1:

[1860] A user accesses the system

[1861] A user accesses the system's web application using a terminal (PC or smartphone). The user enters authentication information on the login screen and logs in to the system.

[1862] Input: Username and Password

[1863] Output: Successful login to the system message

[1864] Specific behavior:

[1865] The user opens a browser and enters the system's URL.

[1866] The user enters their username and password on the login screen and clicks the "Login" button.

[1867] Step 2:

[1868] The user enters a prompt statement

[1869] The user inputs a prompt statement according to the scenario they want to simulate, such as "I would like to simulate a business negotiation in which a new product proposal is made."

[1870] Input: prompt statement

[1871] Output: Prompt statement sending confirmation message

[1872] Specific behavior:

[1873] The user moves to the simulation screen and enters a prompt sentence in the text box.

[1874] The user clicks the "Submit" button.

[1875] Step 3:

[1876] The server invokes the generative AI model

[1877] The server sends the prompt received from the user to the generative AI model, which then generates dialogue content based on the prompt.

[1878] Input: prompt statement

[1879] Output: Generated dialogue

[1880] Specific behavior:

[1881] The server receives the prompt and sends a request to the API of the generative AI model.

[1882] The generative AI model analyzes the prompt and generates the dialogue content.

[1883] Step 4:

[1884] The server sends the generated dialogue to the user

[1885] The server receives the dialogue content from the generative AI model and sends it to the user's device, where the user receives it and starts the dialogue simulation.

[1886] Input: Generated dialogue

[1887] Output: The dialogue displayed on the user's device

[1888] Specific behavior:

[1889] The server receives the generated dialogue content and transmits it to the user's terminal.

[1890] The user's terminal displays the contents of the conversation.

[1891] Step 5:

[1892] The user performs an interactive simulation

[1893] The user proceeds through the simulation based on the generated dialogue content, asking and answering questions during the dialogue, practicing actual business negotiations and handling complaints.

[1894] Input: Generated dialogue, user responses

[1895] Output: The progress of the conversation

[1896] Specific behavior:

[1897] The user reads the dialogue and enters an appropriate response.

[1898] The user clicks the "Submit" button and continues the conversation.

[1899] Step 6:

[1900] The server feeds back the simulation results

[1901] After the simulation is completed, the server provides the user with feedback on the results of the simulation, allowing the user to identify areas for improvement.

[1902] Input: Simulation log

[1903] Output: Feedback content

[1904] Specific behavior:

[1905] The server analyzes the simulation logs and generates feedback.

[1906] The server sends the feedback to the user's terminal.

[1907] Users review feedback and identify areas for improvement.

[1908] (Application example 3)

[1909] 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 headset type terminal 314 will be referred to as a "terminal."

[1910] With conventional simulation systems, it was difficult to practice sales negotiations or handling complaints while pretending to be a specific person, making it difficult to improve staff ability to respond in real situations. Furthermore, there was a lack of evaluation of complaint handling and feedback on areas for improvement, limiting the ability to improve staff skills. This resulted in a decline in the quality of customer service in brick-and-mortar stores, making it difficult to improve customer satisfaction.

[1911] 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.

[1912] In this invention, the server includes means for the generative AI to pretend to be a specific person and perform various simulations, means for the generative AI to suggest tactics and practice menus based on the knowledge and experience of the specific person, means for the generative AI to simulate the behavior of the specific person, and means for the generative AI to simulate handling of complaints and provide feedback on the response evaluation and areas for improvement. This enables staff at physical stores to practice handling realistic complaints and improve their response skills.

[1913] "Generative AI" is an artificial intelligence that imitates the knowledge and behavior of a specific person and performs various simulations.

[1914] "Simulation" is a method of virtually recreating a specific situation or environment and attempting to act or react within it.

[1915] "Tactics" are specific methods or plans for achieving a specific purpose.

[1916] A "practice menu" is a series of exercises designed to improve a particular skill or ability.

[1917] "Complaint handling" refers to the actions taken to appropriately respond to customer complaints and dissatisfaction and resolve the issues.

[1918] "Evaluation" is the act of judging the value or effectiveness of a particular action or result.

[1919] "Feedback" is the act of communicating areas for improvement or evaluation of specific actions or results.

[1920] A "brick and mortar store" is a store that exists in a physical location and where customers can visit in person to purchase goods or services.

[1921] The following system configuration is used as an embodiment of this invention: The system is composed of a server equipped with generative AI, a terminal (such as a smartphone) operated by the user, and necessary software.

[1922] The server includes a means for the generative AI to pretend to be a specific person and perform various simulations, a means for the generative AI to suggest tactics and training menus based on the knowledge and experience of a specific person, a means for the generative AI to simulate the actions of a specific person, and a means for the generative AI to simulate handling of a complaint and provide feedback on the response and areas for improvement.

[1923] A dedicated application is installed on the device operated by the user. This application provides an interface for the user to input the details of the complaint and has the function of sending the input information to a server. The server uses generative AI based on the received information to generate a dialogue that plays the role of the complainant and sends the result back to the device.

[1924] Specifically, a user inputs the details of a complaint into the application, such as "The product was broken and I would like to return it." The server receives this information and uses generative AI to generate a dialogue for the complainant, such as "This product broke immediately. I would like to return it. What should I do?" This dialogue is displayed on the device, allowing the user to practice responding to it.

[1925] The hardware used is a smartphone (iOS or Android), and the software uses Python and the OpenAI API, which allows the generative AI to simulate realistic complaint handling and provide feedback to the user on evaluations and areas for improvement.

[1926] An example of a prompt is as follows:

[1927] "You are a complainer. Please file a complaint in the following situation: I would like to return the product because it was broken."

[1928] In this way, store staff can practice dealing with real complaints and improve their response skills.

[1929] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1930] Step 1:

[1931] The user starts the application on the terminal and inputs the status of the complaint.

[1932] Input: Complaint status (e.g., "The product was broken and I would like to return it.")

[1933] Output: Status data of the entered complaint

[1934] Step 2:

[1935] The terminal transmits the entered complaint status data to the server.

[1936] Input: Claim status data

[1937] Output: Claim status data sent to the server

[1938] Step 3:

[1939] Based on the complaint status data received by the server, a prompt sentence is generated for the generative AI.

[1940] Input: Claim status data

[1941] Output: Generated prompt (e.g. "You are a complainer. Please complain in the following situation: I would like to return the product because it was broken.")

[1942] Step 4:

[1943] The server uses generative AI to generate dialogue for the complainer based on the generated prompt text.

[1944] Input: Generated prompt text

[1945] Output: Generated dialogue of the complainant (e.g., "This item broke immediately. I would like to return it. What should I do?")

[1946] Step 5:

[1947] The server transmits the generated dialogue of the complainer to the terminal.

[1948] Input: Generated dialogue for the complainer

[1949] Output: The complainer's dialogue sent to the terminal

[1950] Step 6:

[1951] The terminal displays the received dialogue of the complainer to the user.

[1952] Input: Received complaint dialogue

[1953] Output: The complainer's dialogue displayed to the user

[1954] Step 7:

[1955] The user responds to the dialogue of the complainer and inputs the response into the terminal.

[1956] Input: User response (e.g. "I'm sorry. We will process your return.")

[1957] Output: Input response data

[1958] Step 8:

[1959] The terminal transmits the inputted correspondence content data to the server.

[1960] Input: Response content data

[1961] Output: Response data sent to the server

[1962] Step 9:

[1963] Based on the response content data received by the server, the generative AI generates an evaluation of the response and areas for improvement.

[1964] Input: Response content data

[1965] Output: Generated assessment and improvements

[1966] Step 10:

[1967] The server sends the generated ratings and improvements to the device.

[1968] Input: Generated ratings and improvements

[1969] Output: Ratings and improvements sent to the device

[1970] Step 11:

[1971] The device displays the received ratings and improvements to the user.

[1972] Input: Received ratings and improvements

[1973] Output: User-visible rating and improvements

[1974] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1975] "Example 1"

[1976] The invention described in claim 4 combines a system including a means for a generative AI to pretend to be a specific person and perform various simulations, a means for the generative AI to suggest tactics and practice menus based on the specific person's knowledge and experience, and a means for the generative AI to simulate the specific person's behavior, with an emotion engine that recognizes the user's emotions. Specifically, a user accesses the system and selects a specific person. The system then uses the generative AI to pretend to be that person based on the selected person's knowledge and experience. Furthermore, the system incorporates an emotion engine that recognizes the user's emotions, and when the user starts a simulation, the generative AI suggests tactics and practice menus based on the specific person's knowledge and experience. In this case, the emotion engine recognizes the user's emotions and adjusts the generative AI's suggestions based on those emotions.

[1977] "Example 2"

[1978] The invention described in claim 5 is a system that combines an emotion engine that recognizes user emotions with a system that includes a means for a generative AI to simulate a specific person's performance after joining the company or after a transfer based on information such as a resume and aptitude test results, based on the person's knowledge and experience. Specifically, a user accesses the system and inputs information about the specific person, such as a resume and aptitude test results. The system utilizes the generative AI to become that person based on the input information and the specific person's knowledge and experience. Furthermore, the system is equipped with an emotion engine that recognizes user emotions, and when the user starts a simulation, the generative AI simulates the person's performance after joining the company or after a transfer. In this case, the emotion engine recognizes the user's emotions and adjusts the generative AI's simulation results based on those emotions.

[1979] "Example 3"

[1980] The invention described in claim 6 combines a system including a means for a generative AI to pretend to be a specific person and simulate a dialogue with a business partner or a complainer, with an emotion engine that recognizes the user's emotions. Specifically, a user accesses the system and inputs a dialogue scenario between a specific person and a business partner or a complainer. Based on the input scenario and the specific person's knowledge and experience, the system utilizes the generative AI to pretend to be that person. Furthermore, the system is equipped with an emotion engine that recognizes the user's emotions, and when the user starts a simulation, the generative AI simulates a dialogue with a business partner or a complainer. At this time, the emotion engine recognizes the user's e...

Claims

1. a first means for accepting an input of a prompt sentence for performing a simulation of a business negotiation in which a user proposes a new product; A second means for inputting the prompt sentence into a generative AI model to generate a dialogue content with the user; a third means for transmitting the generated dialogue content to a terminal of the user; A fourth means for acquiring a response from the user to the dialogue content; a fifth means for feeding back a result of the simulation to the user based on the answer of the user; A system including:

2. A sixth means for recognizing an emotion of the user from a facial expression and a voice of the user using an emotion engine; and a seventh means for adjusting a result of the simulation based on the emotion of the user. The system of claim 1 .

3. and an eighth means for adjusting a response of a generative AI model that performs a simulation with the user based on the emotion of the user. The system of claim 2.

Images