System

Abstract

A system is provided.SOLUTION: A system comprising: means for transmitting account information of a user to a server to initialize player information; means for selecting a specific dataset by the player; means for evaluating appropriateness of the selected dataset; means for causing a generative AI to learn based on the evaluated dataset; and means for transmitting a learning result of the generative AI to the server to be displayed on a device.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] While generative AI technology has advanced pattern recognition and data analysis capabilities, selecting which data to train requires specialized knowledge, making it difficult for average users. Furthermore, understanding the learning process and effects of generative AI is difficult, and there is a lack of tools for users to use it effectively. Therefore, there is a need for a method that allows users to intuitively understand the learning process of generative AI and develop the skills to select appropriate data. [Means for solving the problem]

[0005] The present invention provides a means for transmitting a user's account information to a server to initialize player data and allow the player to select a specific dataset. The server then evaluates the appropriateness of the selected dataset and trains the generated AI using that dataset. The generated AI's learning results are then transmitted from the server to the device and displayed on the device. Additionally, the present invention provides a means for confirming the appropriateness and quality of the evaluated dataset, as well as a means for updating the generated AI's growth status during the learning process and transmitting the results to the device. These means allow users to intuitively understand the generated AI's learning process and develop appropriate data selection skills. Furthermore, by providing a means for simulating the user's daily activities and interactions within the game, users can more realistically learn about the generated AI's growth process.

[0006] The "user" is the entity that operates the system, inputs data, and trains the generative AI.

[0007] "Account information" is a unique set of information for identifying and authenticating a user.

[0008] A "server" is a computer system that processes user requests, manages data, and trains the generative AI.

[0009] A "terminal" is a device, such as a computer or smart device, that a user uses to access the system.

[0010] "Player data" refers to a group of data including a user's account information, as well as their in-game progress and performance.

[0011] A "dataset" is a specific group of information provided to a generative AI, and is the data used as a learning target for the AI.

[0012] "Suitability" is a criterion for assessing whether a dataset is effective for training generative AI.

[0013] "Generative AI" is artificial intelligence that learns and generates information based on the data provided.

[0014] The "learning process" is a series of steps in which generative AI performs pattern recognition and data analysis based on a dataset to improve its performance.

[0015] "Learning results" are indicators of performance improvement or results obtained after a generative AI learns a dataset.

[0016] "Growth status" is an indicator that shows how much the generating AI has learned and its abilities have improved.

[0017] "Daily activities" are actions and events that users perform on a daily basis, and are elements that are simulated in the game.

[0018] "Interaction" refers to the act of a user communicating with other users or characters. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The present invention relates to a simulation game in which a user develops a generative AI. The system provides a process in which the user selects a specific data set and grows the generative AI by learning from that data.

[0041] First, when a user starts a game, the user's account information is sent from the device to the server. This causes the user's player data to be initialized on the server. The player data includes the user's basic information and game progress.

[0042] The user selects a specific dataset from the available dataset options on the game screen. The device then sends this selection to the server, which reviews the received dataset and evaluates its suitability and quality. The suitability evaluation determines whether the dataset is effective for training the generative AI.

[0043] If the server evaluates the selected dataset as appropriate, it will use that dataset to begin the learning process for the Generator AI. The Generator AI will then learn from the provided dataset and generate the results. These learning results include indicators of the Generator AI's growth status and reliability improvement. These results are sent from the server to the device and provided to the user.

[0044] As a concrete example, consider the case where a user selects an "image dataset." This selection information is sent from the device to the server, and the server evaluates the appropriateness of the dataset. If the evaluation results indicate that the dataset is appropriate, the image dataset is used to train the generative AI. Once the generative AI has completed its training, its growth status and reliability improvement information are sent to the device via the server, and the user can check this.

[0045] In addition, the system also has the ability to simulate users' daily activities and interactions. For example, users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. This feature allows users to gain a deeper understanding of the generated AI's growth process and effectively cultivate the AI ​​through in-game activities.

[0046] By using such a system, users can intuitively understand the learning process of generative AI and develop the skills to select and apply appropriate data, making it possible for even ordinary users to effectively utilize advanced generative AI technology.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The user starts the game.

[0050] User: Clicks the "Start Game" button.

[0051] Terminal: Sends the user's account information and a signal to start the game to the server.

[0052] Step 2:

[0053] The server initializes the player data and returns the initial data.

[0054] Server: Receives account information and initializes new player data.

[0055] Server: Sends initialized player data to the device.

[0056] Terminal: Displays the received player data to the user.

[0057] Step 3:

[0058] The user selects the dataset.

[0059] Users: Check the available dataset options from the game screen.

[0060] User: Select a specific dataset.

[0061] Terminal: Sends the selection results to the server.

[0062] Step 4:

[0063] The server evaluates the suitability of the dataset.

[0064] Server: Check the contents of the selected dataset.

[0065] Server: Evaluates the quality and appropriateness of the dataset.

[0066] Step 5:

[0067] The server accepts any data sets it deems appropriate and updates the user data.

[0068] Server: Accepts datasets that are deemed appropriate based on the evaluation results.

[0069] Server: Updates user data with dataset information.

[0070] Server: Sends updated user data to the device.

[0071] Terminal: Displays received updates to the user.

[0072] Step 6:

[0073] The server trains the generating AI.

[0074] Server: Starts the learning process of the generative AI based on the dataset.

[0075] Server: Inputs data into the AI ​​model and performs training.

[0076] Step 7:

[0077] The server generates the learning results and sends them to the terminal.

[0078] Server: Generates learning results and growth status.

[0079] Server: Sends the learning results to the terminal.

[0080] Terminal: Displays learning results and growth status to the user.

[0081] Step 8:

[0082] Users can check the progress of the generated AI.

[0083] User: Check the learning results and growth status displayed on the device.

[0084] User: Select a new dataset if necessary and repeat the process of training the generative AI.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] While modern generative AI technology is highly advanced, there is a lack of means to practically experience and understand the learning process. In particular, it is difficult for ordinary users to intuitively and effectively experience the learning process of generative AI and acquire the skills to select and apply appropriate datasets. Another problem is the lack of a way to instantly check the learning results of generative AI and receive feedback.

[0088] 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.

[0089] In this invention, the server includes: means for transmitting the user's account information to the server to initialize player data; means for the user to select a specific dataset from available dataset options; means for transmitting the selection information from the terminal to the server; means for evaluating the appropriateness of the dataset received by the server; means for the generating AI to learn from the dataset based on the evaluation results; and means for transmitting the learning results of the generating AI from the server to the terminal and displaying them on a user interface. This allows even ordinary users to intuitively understand the learning process of the generating AI in a game format, select an appropriate dataset, and train the generating AI effectively. Furthermore, the ability to quickly check the learning results of the generating AI and receive feedback deepens understanding of the learning process.

[0090] "User Account Information" means data used to identify the identity and access privileges of individuals using the System.

[0091] "Player Data" refers to a collection of data about a specific user, including basic information about the user and their game progress.

[0092] "Dataset options" refers to a list or menu that provides choices for datasets used for training.

[0093] "Selection information" refers to information about the dataset selected by the user, and is data sent from the terminal to the server.

[0094] "Relevance" is a criterion for assessing whether a particular dataset is useful for training a generative AI.

[0095] "Generative AI" refers to algorithms or systems that learn and generate results based on a given dataset.

[0096] "Evaluation results" are the results of an evaluation of the suitability and quality of a dataset, and are data that influence the learning process of the generative AI.

[0097] "Learning results" are output data generated by the generative AI after learning from a specific dataset, and include information on growth status and reliability improvement.

[0098] A "user interface" is a screen or operation panel that allows users to directly interact with the system and displays the learning results.

[0099] The present invention relates to a simulation game in which a user develops a generative AI. The system provides a process in which the user selects a specific data set and grows the generative AI by learning from that data.

[0100] First, when a user starts a game, the user's account information is sent from the terminal to the server. This allows the server to initialize the user's player data. The player data includes the user's basic information and game progress. The user's account information is data used to identify the identity and access privileges of individuals using the system.

[0101] Next, the user selects a specific dataset from the dataset options available on the game screen. The device then sends this selection to the server, which reviews the contents of the received dataset and evaluates its suitability and quality. Suitability is a criterion for assessing whether a particular dataset is useful for training a generative AI.

[0102] If the server evaluates the selected dataset as appropriate, it will use that dataset to begin the learning process of the generative AI. The server inputs the dataset into the generative AI model and runs the learning algorithm. Generative AI is an algorithm or system that learns based on a given dataset and generates results. The generated learning results include indicators of the generative AI's growth status and reliability improvement. Learning results are output data generated by the generative AI after learning based on a specific dataset, and include information on its growth status and reliability improvement. These results are sent from the server to the terminal and provided to the user.

[0103] As a concrete example, consider the case where a user selects "Image Dataset." When the user selects "Image Dataset" on the dataset selection screen and presses the "Confirm" button, the device sends the selection information to the server via API. The server uses an evaluation algorithm to evaluate the dataset based on the criteria of "Is this dataset useful for training the generative AI?" If the evaluation results indicate that the image dataset is appropriate, it is used to train the generative AI. The server inputs the dataset into the generative AI model and runs the training algorithm using a Python library (e.g., TensorFlow, PyTorch). Once the generative AI has completed training, its growth status and reliability improvement information are sent to the device via the server, where the user can check it.

[0104] Furthermore, the system also features a function that simulates the user's daily activities and interactions. Users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. This function allows users to gain a deeper understanding of the generated AI's growth process and effectively develop it through their in-game activities. This allows even ordinary users to effectively utilize advanced generative AI technology.

[0105] As an example of a prompt sentence, when a user sets a prompt for image generation, the following sentence may be considered:

[0106] "Generate an image of a cat using this dataset."

[0107] This system configuration allows users to intuitively understand the learning process of generative AI, select appropriate datasets, and develop the skills to effectively progress the learning process.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] A user starts a game. When the user presses the "Start" button in the application, the device makes an API call in the background and sends the user's account information to the server. The server receives this account information and authenticates the user by referencing the database. If authentication is successful, it initializes the player data, generates new player data, and saves it in the database. The initialized player data is obtained as output.

[0111] Step 2:

[0112] The user selects a specific dataset from the dataset options available on the game screen. For example, when the user selects "Image Dataset" and presses the "Confirm" button, the device sends the selection information to the server via API. The server receives this selection information and uses an evaluation algorithm to evaluate the suitability of the dataset. The input is the selection information, and the output is the evaluation result of the dataset's suitability.

[0113] Step 3:

[0114] Based on the results of the suitability assessment, the server inputs the dataset into the generative AI model and executes the learning algorithm. For example, a Python library (e.g., TensorFlow, PyTorch) is used to input the dataset into the generative AI model. Through learning, the generative AI grows, and the growth status and generated results are obtained as outputs.

[0115] Step 4:

[0116] After the generative AI has completed its training, the server stores the training results in a database and sends them to the device. The device then displays the received training results on its user interface. Specifically, the generated images and reliability improvement information are sent and displayed on the device screen along with the message "The generative AI has trained the image dataset. New images have been generated." The training results are then displayed to the user.

[0117] Step 5:

[0118] Users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. For example, when a user performs an activity such as "chatting with friends" in the game, that information is sent from the device to the server. The server receives the activity information and updates the growth status of the generated AI. The input is the activity information, and the output is the updated growth status.

[0119] In this way, the server and terminal process the data based on the input information and provide appropriate output, allowing the user to intuitively understand the learning process of the generative AI, select an appropriate dataset, and effectively develop the generative AI.

[0120] (Application example 1)

[0121] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0122] In conventional generative AI training simulation games, it was difficult for users to intuitively understand the generative AI's learning process and its growth status. Furthermore, in order to effectively use generative AI in virtual stores, users are required to understand and practically use techniques to improve the performance of generative AI, but there has been a lack of systems that enable this.

[0123] 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.

[0124] In this invention, the server includes means for initializing user account information, means for the player to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generating AI based on the evaluated data set, means for transmitting the learning results of the generating AI to the server and displaying them on the terminal, and means for training the generating AI through user operations in the virtual space and improving the accuracy of customer service and product recommendations. This allows the user to intuitively understand the generating AI's learning process and its growth status, making it possible to effectively use the generating AI in a virtual store.

[0125] "User account information" refers to information for managing a user's identification information, authentication information, and game player data.

[0126] "Initializing player data" refers to the process of creating new player data on the server using the user's account information and setting it to its initial state.

[0127] A "specific dataset" refers to a collection of data of a specific type or content that is used as training data for generative AI.

[0128] "Means for assessing the suitability of a dataset" refers to the process and methods for determining whether a selected dataset is suitable for training generative AI and is of sufficient quality.

[0129] "Means for training generative AI" refers to the process and system by which generative AI absorbs information and learns from the evaluated dataset.

[0130] "Means for transmitting the learning results of the generation AI to a server and displaying them on a terminal" refers to a system and method for transmitting the learning results of the generation AI to a user's terminal via a server, allowing the user to check them.

[0131] "User operations in a virtual space" refers to the actions and interactions that a user performs within a virtual environment.

[0132] "Developing a generative AI" refers to the process of improving the capabilities and performance of a generative AI through user choices and operations.

[0133] "Means for improving the accuracy of customer service and product recommendations" refers to methods and systems for improving the quality and effectiveness of customer service and product recommendations when generative AI is used in a virtual store.

[0134] The present invention relates to a simulation game system for training a generating AI and improving its performance, particularly in a virtual store. Users can operate this system using a device such as a smartphone.

[0135] Overall system overview

[0136] The server has the function of receiving the user's account information and initializing the player data. When the user starts a game, the user data is initialized on the server based on the account information sent from the terminal.

[0137] Next, the user selects the dataset to be trained by the generative AI through an interface for selecting a specific dataset, and this selection information is sent from the device to the server.

[0138] The server evaluates the suitability of the selected dataset and determines whether it is suitable. If it is, the generating AI begins learning using this dataset.

[0139] The results of the generative AI's learning are sent to a server and displayed on the user's device. The user can check the results and manipulate the AI ​​in virtual space to further improve its performance.

[0140] Hardware and Software Configuration

[0141] Terminal: A smartphone or tablet device that accepts user input and communicates with the server.

[0142] Servers: Database server and application server. The database server stores user data and datasets, while the application server evaluates the suitability of datasets and manages the learning process of the generative AI.

[0143] Communication: RESTful API using HTTP and HTTPS to ensure reliable data communication between the server and the device.

[0144] The software configuration consists of an application that provides a user interface running on the terminal side, and a program that initializes user data, evaluates datasets, and manages the learning of generative AI running on the server side.Specific development languages ​​used on the terminal side include Swift and Kotlin, and on the server side include Python and Java, as well as web frameworks such as Flask and Django.

[0145] Introduction of specific examples

[0146] A possible usage scenario would be the following prompt:

[0147] "Train an AI model with images of your new product line. Develop an AI model that will make optimal product recommendations to customers."

[0148] In this specific example, the user selects an "image dataset of a new product" on their device, and the dataset is sent to the server. The server evaluates the appropriateness of the dataset, and if the evaluation is successful, the generative AI begins learning using that data. The learning results are displayed on the device via the server, allowing the user to check the growth and effectiveness of the generative AI. The performance of the generative AI can also be tested in a virtual space, which can be used to assist with actual customer interactions and product recommendations.

[0149] This system allows users to intuitively understand the learning process of generative AI and realize the potential applications of generative AI in virtual stores, while selecting the optimal dataset and developing an AI model.

[0150] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0151] Step 1:

[0152] To start a game, a user sends account information from their device to the server. The input is the account information entered by the user into the device, and the output is the player data stored on the server. Specifically, the user opens the application, enters account information, and presses the "Start" button. This information is sent from the device to the server via an HTTP request.

[0153] Step 2:

[0154] The server initializes the player data. The input is the account information received in step 1, and the output is the initialized player data. Specifically, the server creates a new player data record in the database corresponding to the user ID based on the account information received.

[0155] Step 3:

[0156] The user selects a specific dataset on the game screen. The input is the user's selection operation, and the output is the dataset selection information sent from the device to the server. Specifically, the user selects an appropriate dataset from the list on the dataset selection screen and sends it to the server.

[0157] Step 4:

[0158] The server evaluates the appropriateness of the selected dataset. The input is the received dataset selection information, and the output is the evaluation result of whether the dataset is appropriate. Specifically, the server checks the contents of the selected dataset and evaluates whether it is suitable for learning.

[0159] Step 5:

[0160] The server trains the generative AI based on the evaluated dataset. The input is the evaluated dataset, and the output is the learning result of the generative AI. Specifically, the server uses the evaluated dataset to execute the learning process on the AI ​​model.

[0161] Step 6:

[0162] The learning results of the generative AI are sent to the server and then displayed on the device. The input is the learning results of the generative AI, and the output is the growth status of the generative AI and an indicator of reliability improvement that is displayed on the device. Specifically, the learning results are sent from the server to the device in JSON format or similar and displayed on the screen within the application.

[0163] Step 7:

[0164] The user performs operations in a virtual space to train the generating AI. The input is the user's operations, and the output is the performance improvement status of the generating AI. Specifically, the user performs operations and tasks in the virtual space, which are reflected in the growth of the generating AI. The results of these operations are sent to the server, and the generating AI's performance is updated.

[0165] 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.

[0166] This invention relates to a simulation game in which users train generative AI, and aims to improve the learning process of the generative AI and the user experience by combining it with an emotion engine that recognizes the user's emotions. This system allows users to select a dataset and train the generative AI by learning from that data, while also enabling feedback and adjustments based on the user's emotions.

[0167] First, when a user starts a game, the device sends a game start signal to the server along with the user's account information. The server initializes the player data based on the received account information and returns the initial data to the device. The user can then view and confirm the initialized player data on the game screen.

[0168] The user reviews the available dataset options on the screen and selects a specific dataset. The device sends this selection to the server, which reviews the dataset's contents and evaluates its appropriateness and quality. If the dataset is deemed appropriate as a result of the evaluation, it is used to train the generative AI. The server trains the generative AI based on the dataset, generates learning results and growth status, and sends them to the device, allowing the user to view the generative AI's learning results.

[0169] Furthermore, by integrating an emotion engine, the system can recognize the user's emotions in real time and adjust the generative AI's learning process and feedback based on those emotions. Specifically, the emotion engine collects user emotional data and uses it to help select a dataset to provide to the generative AI. For example, if the user is feeling stressed, the emotion engine can suggest a dataset with a lower level of difficulty. The emotion engine also adjusts the generative AI's learning results according to the user's emotions and provides more appropriate feedback.

[0170] For example, if the user feels "fun," the emotion engine will recognize this emotion and reinforce positive feedback to the generative AI through the learning process. Also, if the user feels "tired," the emotion engine will gently adjust the learning process to reduce the burden on the user.

[0171] In this way, the present invention, which incorporates an emotion engine, improves the quality of the user experience and makes the learning process of the generative AI more effective. Furthermore, users can train the generative AI in a way that matches their own emotions, resulting in a greater sense of satisfaction.

[0172] The processing flow will be explained below.

[0173] Step 1:

[0174] The user starts the game.

[0175] User: Clicks the "Start Game" button.

[0176] Terminal: Sends the user's account information and a signal to start the game to the server.

[0177] Step 2:

[0178] The server initializes the player data and returns the initial data.

[0179] Server: Receives account information and initializes new player data.

[0180] Server: Sends initialized player data to the device.

[0181] Terminal: Displays the received player data to the user.

[0182] Step 3:

[0183] The user selects the dataset.

[0184] Users: Check the available dataset options from the game screen.

[0185] User: Select a specific dataset.

[0186] Terminal: Sends the selection results to the server.

[0187] Step 4:

[0188] The server evaluates the suitability of the dataset.

[0189] Server: Check the contents of the selected dataset.

[0190] Server: Evaluates the quality and appropriateness of the dataset.

[0191] Step 5:

[0192] The server accepts any data sets it deems appropriate and updates the user data.

[0193] Server: Accepts datasets that are deemed appropriate based on the evaluation results.

[0194] Server: Updates user data with dataset information.

[0195] Server: Sends updated user data to the device.

[0196] Terminal: Displays received updates to the user.

[0197] Step 6:

[0198] The server trains the generating AI.

[0199] Server: Starts the learning process of the generative AI based on the dataset.

[0200] Server: Inputs data into the AI ​​model and performs training.

[0201] Step 7:

[0202] The server generates the learning results and sends them to the terminal.

[0203] Server: Generates learning results and growth status.

[0204] Server: Sends the learning results to the terminal.

[0205] Terminal: Displays learning results and growth status to the user.

[0206] Step 8:

[0207] The emotion engine recognizes the user's emotions.

[0208] User: Expresses emotions through facial expressions and voice during gameplay.

[0209] Terminal: Collects user emotion data using sensor devices such as cameras and microphones.

[0210] Terminal: Sends collected emotion data to the server.

[0211] Server: The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0212] Step 9:

[0213] The emotion engine regulates the learning process of generative AI.

[0214] Server: Adjusts the learning process of the generative AI based on the perceived emotional state of the user.

[0215] Server: In the case of positive sentiment, it selects a more difficult dataset or provides quick feedback.

[0216] Server: For negative emotions, we choose an easier dataset and make adjustments to reduce the burden on the learning process.

[0217] Step 10:

[0218] Users can check the progress and feedback of the generated AI.

[0219] User: View learning results, progress status, and emotional feedback displayed on the device.

[0220] User: Select a new dataset if necessary and repeat the process of training the generative AI.

[0221] Example 2

[0222] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0223] Conventional generative AI training simulation games provide a uniform learning process and feedback without considering the user's emotions, which limits the user experience and reduces game continuity and learning effectiveness. Furthermore, if the user selects an inappropriate dataset, the growth of the generative AI can be hindered.

[0224] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0225] In this invention, the server includes means for transmitting user account information to the server and initializing player data, means for the player to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generating AI based on the evaluated data set, means for transmitting the learning results of the generating AI to the server and displaying them on the terminal, means for collecting and analyzing user emotion data, and means for adjusting the learning process and feedback of the generating AI based on the analyzed emotion data. This enables appropriate feedback and adjustment of the learning process according to the user's emotions, providing a more advanced and sustainable user experience.

[0226] "User" refers to the person who operates the system and participates in the generative AI's learning process.

[0227] "Server" refers to a central computing device that processes, manages, and communicates data.

[0228] "Terminal" refers to an input and output device that is directly operated by a user.

[0229] "Account information" refers to information that includes a user's identification information and initial configuration data.

[0230] "Player Data" refers to data that indicates a user's progress and status in the game.

[0231] "Dataset" refers to the set of training data used to train generative AI.

[0232] "Evaluation" refers to the process of checking the suitability and quality of a dataset and determining whether it is suitable for training generative AI.

[0233] "Generative AI" refers to an AI model that learns knowledge based on input data and generates new information and responses.

[0234] The "learning process" refers to the series of steps that generative AI takes to acquire knowledge based on a dataset.

[0235] "Learning results" refers to the output and model status generated after the generative artificial intelligence learns from a dataset.

[0236] "Emotional data" refers to information that indicates the user's emotional state, including facial expressions, tone of voice, and other sensory data.

[0237] "Analysis" refers to the process of analyzing collected emotional data to determine the user's current emotional state.

[0238] "Feedback" refers to information including users' reactions and opinions regarding the learning process and results.

[0239] "Tuning" refers to the process of optimizing the learning process and feedback based on analyzed emotional data.

[0240] The following describes how to specifically put the present invention into practice.

[0241] First, this system is a simulation game for users to train generative AI. By combining it with an emotion engine, the aim is to improve the learning process of generative AI and the user experience.

[0242] Hardware and software used

[0243] 1. Hardware:

[0244] User devices: PCs, smartphones, tablets, etc.

[0245] Server: a central computing device that processes and manages data

[0246] Emotion data collection devices: cameras, microphones, and other sensors

[0247] 2. Software:

[0248] Game application: an interface for user operation

[0249] Emotion Engine: A component for analyzing user emotions in real time

[0250] Dataset Selection Algorithm: Software for assessing the suitability of datasets

[0251] Generative AI models: machine learning algorithms such as GPT-3

[0252] Specific processing of the program

[0253] 1. Starting the game and initializing your account:

[0254] To start a game, a user launches a game application and enters account information, which the device then sends to the server.

[0255] The server initializes the user's player data based on the received account information, including the user's basic information and initial points.

[0256] The server sends initialization data to the terminal, which displays this data on its screen.

[0257] 2. Dataset selection and evaluation:

[0258] The user selects an available dataset from the options on the game screen.

[0259] The terminal transmits the user's selection information to the server, which includes the data set identification information.

[0260] The server evaluates the suitability and quality of the dataset based on the identification information.

[0261] The server notifies the device of the evaluation results, and datasets deemed appropriate are used to train the generative AI.

[0262] 3. Training generative AI and displaying results:

[0263] The server trains a generative AI model based on the dataset that is assessed as appropriate.

[0264] Once training is complete, the server generates the learning results and growth status of the generated model.

[0265] The server sends these results to the terminal, which displays them on the screen for the user to confirm.

[0266] 4. Feedback adjustment by emotion engine:

[0267] The device uses a camera and microphone to collect user emotional data.

[0268] The collected emotion data is sent to a server, which analyzes the emotion.

[0269] Based on the analysis results, the server adjusts the learning process and feedback of the generative AI. For example, if the user feels "fun," it increases positive feedback. If the user feels "tired," it slows down the learning process.

[0270] The server sends the adjusted feedback to the device, which displays it on the screen.

[0271] Examples of concrete examples and prompts

[0272] Example: If the user feels "fun," the emotion engine will recognize this emotion and reinforce the positive feedback to the generative AI through the learning process. Conversely, if the user feels "tired," the emotion engine will analyze this emotion and slow down the learning process.

[0273] Example prompt sentence:

[0274] Prompt to emotion engine: "The user is currently feeling happy. Based on this emotion, please choose an appropriate dataset to provide positive feedback for training the generative AI."

[0275] Prompt for dataset selection algorithm: "Please rate the relevance and quality of dataset A selected by the user and return the results."

[0276] In this way, the present invention enables appropriate feedback and adjustment of the learning process according to the user's emotions, providing a more advanced and sustainable user experience.

[0277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0278] Step 1: Start the game and initialize your account

[0279] Specific operation: The user launches the game application and presses the "Start" button.

[0280] Input: User account information (e.g., user ID, password)

[0281] Processing: The device sends the entered account information to the server. The server then initializes the user's player data based on the received information. This initialization includes the user's basic information and initial points.

[0282] Output: Initialized player data

[0283] Specific operation: The server sends the generated initial data to the terminal, and the terminal displays this data on the screen.

[0284] Step 2: Dataset selection and evaluation

[0285] Specific behavior: The user selects an available dataset from the options on the game screen, for example, "Dataset A."

[0286] Input: User selection information (e.g., dataset ID)

[0287] Processing: The device sends this selection information to the server, which evaluates the suitability and quality of the received dataset information.

[0288] Output: Evaluation result (whether the dataset is suitable or not)

[0289] Specific operation: The server notifies the terminal of the evaluation result, and the terminal displays the result on the screen.

[0290] Step 3: Training the generative AI and displaying the results

[0291] Specific operation: The server trains a generative AI model based on the dataset that is evaluated as appropriate.

[0292] Input: The evaluated dataset

[0293] Processing: The server inputs the dataset into a generative AI model (e.g., GPT-3) and trains the model, updating its growth status along the way.

[0294] Output: Learning results and growth status

[0295] Specific operation: The server sends the training results to the terminal, which displays them on the screen for the user to confirm.

[0296] Step 4: Feedback adjustment by the emotion engine

[0297] Specific operation: The device collects the user's emotional data using a camera and microphone. For example, if the user is feeling "happy," their facial expression and tone of voice are collected as data.

[0298] Input: Collected emotional data (e.g., facial expressions, tone of voice)

[0299] Processing: The device sends the emotion data to the server, which analyzes the data and identifies the user's emotional state (e.g., "happy," "tired," etc.).

[0300] Output: Analysis results (user's emotional state)

[0301] Specific operation: The server adjusts the learning process and feedback of the generative AI based on the analyzed emotional data. For example, if the user feels "fun," it increases the positive feedback of the learning process. If the user feels "tired," it slows down the learning process.

[0302] Output: Adjusted feedback

[0303] Specific operation: The server sends the adjusted feedback to the device, and the device displays the feedback on the screen.

[0304] (Application example 2)

[0305] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0306] Conventional content distribution services provide content uniformly without considering user emotions, making it difficult to provide services optimized for individual users' moods, hobbies, and preferences. Furthermore, simulation games using generative AI have the problem of being unable to provide feedback or adjust the learning process based on user emotions, making it difficult to improve the quality of the user experience. To solve these issues, a system is needed that recognizes user emotions in real time and optimizes the generative AI's learning process and content provision based on those emotions.

[0307] 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.

[0308] In this invention, the server includes means for transmitting user identification information to the information processing device and initializing user data, means for the user to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generation AI based on the evaluated data set, means for transmitting the learning results of the generation AI to the information processing device and displaying them on a display device, means for collecting user emotion data and adjusting the learning process of the generation AI based on the emotion data, and means for providing feedback according to the user's emotion. This makes it possible to provide content that reflects the user's emotions and to optimize the learning process of the generation AI.

[0309] "User identification information" is data for distinguishing a specific user from other users.

[0310] An "information processing device" is a device for processing digital data.

[0311] "User Data" is data that includes information related to a particular user.

[0312] A "specific dataset" is a specific collection of data used to train a generative AI.

[0313] "Relevance" is a measure of how well something is suited to a particular purpose.

[0314] "Generative AI" is artificial intelligence that automatically generates various outputs through learning.

[0315] "Learning results" refer to the results and performance that generative AI achieves through the learning process.

[0316] A "display device" is a device for visually displaying digital data.

[0317] "Emotion data" is data that indicates the emotional state of the user.

[0318] "Feedback" is information used to make further adjustments and improvements based on the system's output information.

[0319] The present invention relates to a system for realizing content distribution and simulation games using generative AI while recognizing user emotions. The purpose of this invention is to improve the user experience by exchanging data between an information processing device and a user terminal and adjusting the learning process of the generative AI.

[0320] 1. System Programming and Configuration

[0321] This system consists of hardware and software for both an information processing device (server) and a display device (terminal). The server receives the user's identification information and initializes the user data. The terminal then sends a specific data set selected by the user to the server, which evaluates its appropriateness. The evaluated data set is learned by the generative AI, and the learning results are sent to the terminal and displayed. The terminal also collects the user's emotional data in real time and sends it to the server. The server adjusts the generative AI's learning process based on the emotional data and provides appropriate feedback to the user.

[0322] 2. Hardware and Software Used

[0323] On the server side, emotion recognition and generation AI training is performed using Python, TensorFlow, and OpenCV. On the device side, a smartphone camera is used to capture the user's facial image and generate emotion data. This allows the entire system to achieve consistent data processing and feedback.

[0324] 3. Examples of concrete examples and prompts

[0325] In a specific example, the system recommends entertainment content based on emotional data if the user feels happy, and adjusts the system to play relaxing music tracks if the user feels sad.

[0326] Example prompt sentence:

[0327] "If the user's emotion is recognized as 'Happy', optimize to recommend videos in the entertainment category."

[0328] "If the user's emotion is recognized as 'Sad', optimize to play a relaxing music track."

[0329] As a result, the present invention makes it possible to recognize user emotions in real time and provide content based on them, as well as adjust the learning process of the AI ​​generator, thereby significantly improving the quality of the user experience.

[0330] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0331] Step 1:

[0332] The user starts the application and enters the identification information (account information).

[0333] Input: User account information

[0334] Output: Sending identification information to the server

[0335] How it works: A user launches the application and enters their account information on the login screen. The device receives this and sends the identification information to the server.

[0336] Step 2:

[0337] The server initializes the user data based on the received identification information.

[0338] Input: User's identity

[0339] Output: Initialized user data

[0340] Operation: The server recognizes the user based on the user's identification information and initializes new user data, including the user's game progress and current settings.

[0341] Step 3:

[0342] The user selects a particular data set from the terminal.

[0343] Input: list of available datasets, user selection

[0344] Output: Information about the selected dataset

[0345] Operation: The terminal displays multiple data set options, from which the user selects one. This selection is sent from the terminal to the server.

[0346] Step 4:

[0347] The server evaluates the appropriateness of the selected data set.

[0348] Input: Information about the selected data set

[0349] Output: Evaluation result (appropriate or inappropriate)

[0350] How it works: The server analyzes the content of the selected dataset and evaluates its quality and appropriateness. If deemed appropriate, the dataset is used to train the generative AI.

[0351] Step 5:

[0352] The server trains the generative AI based on the evaluated data set.

[0353] Input: The dataset to be evaluated

[0354] Output: Learning results of generative AI

[0355] How it works: The server uses the evaluated dataset to train a generative AI model, allowing it to learn useful patterns and information from new data.

[0356] Step 6:

[0357] The server sends the learning results of the generation AI to the terminal, where they are displayed.

[0358] Input: Generative AI learning results

[0359] Output: Training results displayed on the terminal

[0360] Operation: The server sends the learning results of the generative AI to the device, which displays them on the screen. The user can check the progress and results of the generative AI.

[0361] Step 7:

[0362] The device collects the user's emotional data and sends it to the server.

[0363] Input: User's emotions (facial expressions, voice, etc.)

[0364] Output: Sending emotion data to the server

[0365] How it works: The device (smartphone camera and microphone) collects emotional data from the user's facial expressions and voice. This data is sent to a server in real time.

[0366] Step 8:

[0367] The server adjusts the learning process of the generative AI based on the emotion data.

[0368] Input: User emotion data

[0369] Output: The adjusted generative AI learning process

[0370] How it works: The server analyzes the collected emotional data and adjusts the learning process of the generative AI based on that data. For example, if the user is feeling stressed, the learning process will be slowed down.

[0371] Step 9:

[0372] The server provides feedback according to the user's emotions.

[0373] Input: trained learning process and emotion data

[0374] Output: Send feedback message

[0375] Operation: The server coordinates the learning process of the generation AI and generates feedback messages based on the results. The feedback messages are sent to the terminal and displayed to the user.

[0376] 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.

[0377] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0378] 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.

[0379] [Second embodiment]

[0380] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0381] 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.

[0382] 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).

[0383] 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.

[0384] 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.

[0385] 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).

[0386] 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.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0392] The present invention relates to a simulation game in which a user develops a generative AI. The system provides a process in which the user selects a specific data set and grows the generative AI by learning from that data.

[0393] First, when a user starts a game, the user's account information is sent from the device to the server. This causes the user's player data to be initialized on the server. The player data includes the user's basic information and game progress.

[0394] The user selects a specific dataset from the available dataset options on the game screen. The device then sends this selection to the server, which reviews the received dataset and evaluates its suitability and quality. The suitability evaluation determines whether the dataset is effective for training the generative AI.

[0395] If the server evaluates the selected dataset as appropriate, it will use that dataset to begin the learning process for the Generator AI. The Generator AI will then learn from the provided dataset and generate the results. These learning results include indicators of the Generator AI's growth status and reliability improvement. These results are sent from the server to the device and provided to the user.

[0396] As a concrete example, consider the case where a user selects an "image dataset." This selection information is sent from the device to the server, and the server evaluates the appropriateness of the dataset. If the evaluation results indicate that the dataset is appropriate, the image dataset is used to train the generative AI. Once the generative AI has completed its training, its growth status and reliability improvement information are sent to the device via the server, and the user can check this.

[0397] In addition, the system also has the ability to simulate users' daily activities and interactions. For example, users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. This feature allows users to gain a deeper understanding of the generated AI's growth process and effectively cultivate the AI ​​through in-game activities.

[0398] By using such a system, users can intuitively understand the learning process of generative AI and develop the skills to select and apply appropriate data, making it possible for even ordinary users to effectively utilize advanced generative AI technology.

[0399] The processing flow will be explained below.

[0400] Step 1:

[0401] The user starts the game.

[0402] User: Clicks the "Start Game" button.

[0403] Terminal: Sends the user's account information and a signal to start the game to the server.

[0404] Step 2:

[0405] The server initializes the player data and returns the initial data.

[0406] Server: Receives account information and initializes new player data.

[0407] Server: Sends initialized player data to the device.

[0408] Terminal: Displays the received player data to the user.

[0409] Step 3:

[0410] The user selects the dataset.

[0411] Users: Check the available dataset options from the game screen.

[0412] User: Select a specific dataset.

[0413] Terminal: Sends the selection results to the server.

[0414] Step 4:

[0415] The server evaluates the suitability of the dataset.

[0416] Server: Check the contents of the selected dataset.

[0417] Server: Evaluates the quality and appropriateness of the dataset.

[0418] Step 5:

[0419] The server accepts any data sets it deems appropriate and updates the user data.

[0420] Server: Accepts datasets that are deemed appropriate based on the evaluation results.

[0421] Server: Updates user data with dataset information.

[0422] Server: Sends updated user data to the device.

[0423] Terminal: Displays received updates to the user.

[0424] Step 6:

[0425] The server trains the generating AI.

[0426] Server: Starts the learning process of the generative AI based on the dataset.

[0427] Server: Inputs data into the AI ​​model and performs training.

[0428] Step 7:

[0429] The server generates the learning results and sends them to the terminal.

[0430] Server: Generates learning results and growth status.

[0431] Server: Sends the learning results to the terminal.

[0432] Terminal: Displays learning results and growth status to the user.

[0433] Step 8:

[0434] Users can check the progress of the generated AI.

[0435] User: Check the learning results and growth status displayed on the device.

[0436] User: Select a new dataset if necessary and repeat the process of training the generative AI.

[0437] Example 1

[0438] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0439] While modern generative AI technology is highly advanced, there is a lack of means to practically experience and understand the learning process. In particular, it is difficult for ordinary users to intuitively and effectively experience the learning process of generative AI and acquire the skills to select and apply appropriate datasets. Another problem is the lack of a way to instantly check the learning results of generative AI and receive feedback.

[0440] 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.

[0441] In this invention, the server includes: means for transmitting the user's account information to the server to initialize player data; means for the user to select a specific dataset from available dataset options; means for transmitting the selection information from the terminal to the server; means for evaluating the appropriateness of the dataset received by the server; means for the generating AI to learn from the dataset based on the evaluation results; and means for transmitting the learning results of the generating AI from the server to the terminal and displaying them on a user interface. This allows even ordinary users to intuitively understand the learning process of the generating AI in a game format, select an appropriate dataset, and train the generating AI effectively. Furthermore, the ability to quickly check the learning results of the generating AI and receive feedback deepens understanding of the learning process.

[0442] "User Account Information" means data used to identify the identity and access privileges of individuals using the System.

[0443] "Player Data" refers to a collection of data about a specific user, including basic information about the user and their game progress.

[0444] "Dataset options" refers to a list or menu that provides choices for datasets used for training.

[0445] "Selection information" refers to information about the dataset selected by the user, and is data sent from the terminal to the server.

[0446] "Relevance" is a criterion for assessing whether a particular dataset is useful for training a generative AI.

[0447] "Generative AI" refers to algorithms or systems that learn and generate results based on a given dataset.

[0448] "Evaluation results" are the results of an evaluation of the suitability and quality of a dataset, and are data that influence the learning process of the generative AI.

[0449] "Learning results" are output data generated by the generative AI after learning from a specific dataset, and include information on growth status and reliability improvement.

[0450] A "user interface" is a screen or operation panel that allows users to directly interact with the system and displays the learning results.

[0451] The present invention relates to a simulation game in which a user develops a generative AI. The system provides a process in which the user selects a specific data set and grows the generative AI by learning from that data.

[0452] First, when a user starts a game, the user's account information is sent from the terminal to the server. This allows the server to initialize the user's player data. The player data includes the user's basic information and game progress. The user's account information is data used to identify the identity and access privileges of individuals using the system.

[0453] Next, the user selects a specific dataset from the dataset options available on the game screen. The device then sends this selection to the server, which reviews the contents of the received dataset and evaluates its suitability and quality. Suitability is a criterion for assessing whether a particular dataset is useful for training a generative AI.

[0454] If the server evaluates the selected dataset as appropriate, it will use that dataset to begin the learning process of the generative AI. The server inputs the dataset into the generative AI model and runs the learning algorithm. Generative AI is an algorithm or system that learns based on a given dataset and generates results. The generated learning results include indicators of the generative AI's growth status and reliability improvement. Learning results are output data generated by the generative AI after learning based on a specific dataset, and include information on its growth status and reliability improvement. These results are sent from the server to the terminal and provided to the user.

[0455] As a concrete example, consider the case where a user selects "Image Dataset." When the user selects "Image Dataset" on the dataset selection screen and presses the "Confirm" button, the device sends the selection information to the server via API. The server uses an evaluation algorithm to evaluate the dataset based on the criteria of "Is this dataset useful for training the generative AI?" If the evaluation results indicate that the image dataset is appropriate, it is used to train the generative AI. The server inputs the dataset into the generative AI model and runs the training algorithm using a Python library (e.g., TensorFlow, PyTorch). Once the generative AI has completed training, its growth status and reliability improvement information are sent to the device via the server, where the user can check it.

[0456] Furthermore, the system also features a function that simulates the user's daily activities and interactions. Users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. This function allows users to gain a deeper understanding of the generated AI's growth process and effectively develop it through their in-game activities. This allows even ordinary users to effectively utilize advanced generative AI technology.

[0457] As an example of a prompt sentence, when a user sets a prompt for image generation, the following sentence may be considered:

[0458] "Generate an image of a cat using this dataset."

[0459] This system configuration allows users to intuitively understand the learning process of generative AI, select appropriate datasets, and develop the skills to effectively progress the learning process.

[0460] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0461] Step 1:

[0462] A user starts a game. When the user presses the "Start" button in the application, the device makes an API call in the background and sends the user's account information to the server. The server receives this account information and authenticates the user by referencing the database. If authentication is successful, it initializes the player data, generates new player data, and saves it in the database. The initialized player data is obtained as output.

[0463] Step 2:

[0464] The user selects a specific dataset from the dataset options available on the game screen. For example, when the user selects "Image Dataset" and presses the "Confirm" button, the device sends the selection information to the server via API. The server receives this selection information and uses an evaluation algorithm to evaluate the suitability of the dataset. The input is the selection information, and the output is the evaluation result of the dataset's suitability.

[0465] Step 3:

[0466] Based on the results of the suitability assessment, the server inputs the dataset into the generative AI model and executes the learning algorithm. For example, a Python library (e.g., TensorFlow, PyTorch) is used to input the dataset into the generative AI model. Through learning, the generative AI grows, and the growth status and generated results are obtained as outputs.

[0467] Step 4:

[0468] After the generative AI has completed its training, the server stores the training results in a database and sends them to the device. The device then displays the received training results on its user interface. Specifically, the generated images and reliability improvement information are sent and displayed on the device screen along with the message "The generative AI has trained the image dataset. New images have been generated." The training results are then displayed to the user.

[0469] Step 5:

[0470] Users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. For example, when a user performs an activity such as "chatting with friends" in the game, that information is sent from the device to the server. The server receives the activity information and updates the growth status of the generated AI. The input is the activity information, and the output is the updated growth status.

[0471] In this way, the server and terminal process the data based on the input information and provide appropriate output, allowing the user to intuitively understand the learning process of the generative AI, select an appropriate dataset, and effectively develop the generative AI.

[0472] (Application example 1)

[0473] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0474] In conventional generative AI training simulation games, it was difficult for users to intuitively understand the generative AI's learning process and its growth status. Furthermore, in order to effectively use generative AI in virtual stores, users are required to understand and practically use techniques to improve the performance of generative AI, but there has been a lack of systems that enable this.

[0475] 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.

[0476] In this invention, the server includes means for initializing user account information, means for the player to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generating AI based on the evaluated data set, means for transmitting the learning results of the generating AI to the server and displaying them on the terminal, and means for training the generating AI through user operations in the virtual space and improving the accuracy of customer service and product recommendations. This allows the user to intuitively understand the generating AI's learning process and its growth status, making it possible to effectively use the generating AI in a virtual store.

[0477] "User account information" refers to information for managing a user's identification information, authentication information, and game player data.

[0478] "Initializing player data" refers to the process of creating new player data on the server using the user's account information and setting it to its initial state.

[0479] A "specific dataset" refers to a collection of data of a specific type or content that is used as training data for generative AI.

[0480] "Means for assessing the suitability of a dataset" refers to the process and methods for determining whether a selected dataset is suitable for training generative AI and is of sufficient quality.

[0481] "Means for training generative AI" refers to the process and system by which generative AI absorbs information and learns from the evaluated dataset.

[0482] "Means for transmitting the learning results of the generation AI to a server and displaying them on a terminal" refers to a system and method for transmitting the learning results of the generation AI to a user's terminal via a server, allowing the user to check them.

[0483] "User operations in a virtual space" refers to the actions and interactions that a user performs within a virtual environment.

[0484] "Developing a generative AI" refers to the process of improving the capabilities and performance of a generative AI through user choices and operations.

[0485] "Means for improving the accuracy of customer service and product recommendations" refers to methods and systems for improving the quality and effectiveness of customer service and product recommendations when generative AI is used in a virtual store.

[0486] The present invention relates to a simulation game system for training a generating AI and improving its performance, particularly in a virtual store. Users can operate this system using a device such as a smartphone.

[0487] Overall system overview

[0488] The server has the function of receiving the user's account information and initializing the player data. When the user starts a game, the user data is initialized on the server based on the account information sent from the terminal.

[0489] Next, the user selects the dataset to be trained by the generative AI through an interface for selecting a specific dataset, and this selection information is sent from the device to the server.

[0490] The server evaluates the appropriateness of the selected dataset and determines whether it is suitable. If it is, the generating AI begins learning using this dataset.

[0491] The results of the generative AI's learning are sent to a server and displayed on the user's device. The user can check the results and manipulate the AI ​​in virtual space to further improve its performance.

[0492] Hardware and Software Configuration

[0493] Terminal: A smartphone or tablet device that accepts user input and communicates with the server.

[0494] Servers: Database server and application server. The database server stores user data and datasets, while the application server evaluates the suitability of datasets and manages the learning process of the generative AI.

[0495] Communication: RESTful API using HTTP and HTTPS to ensure reliable data communication between the server and the device.

[0496] The software configuration consists of an application that provides a user interface running on the terminal side, and a program that initializes user data, evaluates datasets, and manages the learning of generative AI running on the server side.Specific development languages ​​used on the terminal side include Swift and Kotlin, and on the server side include Python and Java, as well as web frameworks such as Flask and Django.

[0497] Introduction of specific examples

[0498] A possible usage scenario would be the following prompt:

[0499] "Train an AI model with images of your new product line. Develop an AI model that will make optimal product recommendations to customers."

[0500] In this specific example, the user selects an "image dataset of a new product" on their device, and the dataset is sent to the server. The server evaluates the appropriateness of the dataset, and if the evaluation is successful, the generative AI begins learning using that data. The learning results are displayed on the device via the server, allowing the user to check the growth and effectiveness of the generative AI. The performance of the generative AI can also be tested in a virtual space, which can be used to assist with actual customer interactions and product recommendations.

[0501] This system allows users to intuitively understand the learning process of generative AI and realize the potential applications of generative AI in virtual stores, while selecting the optimal dataset and developing an AI model.

[0502] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0503] Step 1:

[0504] To start a game, a user sends account information from their device to the server. The input is the account information entered by the user into the device, and the output is the player data stored on the server. Specifically, the user opens the application, enters account information, and presses the "Start" button. This information is sent from the device to the server via an HTTP request.

[0505] Step 2:

[0506] The server initializes the player data. The input is the account information received in step 1, and the output is the initialized player data. Specifically, the server creates a new player data record in the database corresponding to the user ID based on the account information received.

[0507] Step 3:

[0508] The user selects a specific dataset on the game screen. The input is the user's selection operation, and the output is the dataset selection information sent from the device to the server. Specifically, the user selects an appropriate dataset from the list on the dataset selection screen and sends it to the server.

[0509] Step 4:

[0510] The server evaluates the appropriateness of the selected dataset. The input is the received dataset selection information, and the output is the evaluation result of whether the dataset is appropriate. Specifically, the server checks the contents of the selected dataset and evaluates whether it is suitable for learning.

[0511] Step 5:

[0512] The server trains the generative AI based on the evaluated dataset. The input is the evaluated dataset, and the output is the learning result of the generative AI. Specifically, the server uses the evaluated dataset to execute the learning process on the AI ​​model.

[0513] Step 6:

[0514] The learning results of the generative AI are sent to the server and then displayed on the device. The input is the learning results of the generative AI, and the output is the growth status of the generative AI and an indicator of reliability improvement that is displayed on the device. Specifically, the learning results are sent from the server to the device in JSON format or similar and displayed on the screen within the application.

[0515] Step 7:

[0516] The user performs operations in a virtual space to train the generating AI. The input is the user's operations, and the output is the performance improvement status of the generating AI. Specifically, the user performs operations and tasks in the virtual space, which are reflected in the growth of the generating AI. The results of these operations are sent to the server, and the generating AI's performance is updated.

[0517] 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.

[0518] This invention relates to a simulation game in which users train generative AI, and aims to improve the learning process of the generative AI and the user experience by combining it with an emotion engine that recognizes the user's emotions. This system allows users to select a dataset and train the generative AI by learning from that data, while also enabling feedback and adjustments based on the user's emotions.

[0519] First, when a user starts a game, the device sends a game start signal to the server along with the user's account information. The server initializes the player data based on the received account information and returns the initial data to the device. The user can then view and confirm the initialized player data on the game screen.

[0520] The user reviews the available dataset options on the screen and selects a specific dataset. The device sends this selection to the server, which reviews the dataset's contents and evaluates its appropriateness and quality. If the dataset is deemed appropriate as a result of the evaluation, it is used to train the generative AI. The server trains the generative AI based on the dataset, generates learning results and growth status, and sends them to the device, allowing the user to view the generative AI's learning results.

[0521] Furthermore, by integrating an emotion engine, the system can recognize the user's emotions in real time and adjust the generative AI's learning process and feedback based on those emotions. Specifically, the emotion engine collects user emotional data and uses it to help select a dataset to provide to the generative AI. For example, if the user is feeling stressed, the emotion engine can suggest a dataset with a lower level of difficulty. The emotion engine also adjusts the generative AI's learning results according to the user's emotions and provides more appropriate feedback.

[0522] For example, if the user feels "fun," the emotion engine will recognize this emotion and reinforce positive feedback to the generative AI through the learning process. Also, if the user feels "tired," the emotion engine will gently adjust the learning process to reduce the burden on the user.

[0523] In this way, the present invention, which incorporates an emotion engine, improves the quality of the user experience and makes the learning process of the generative AI more effective. Furthermore, users can train the generative AI in a way that matches their own emotions, resulting in a greater sense of satisfaction.

[0524] The processing flow will be explained below.

[0525] Step 1:

[0526] The user starts the game.

[0527] User: Clicks the "Start Game" button.

[0528] Terminal: Sends the user's account information and a signal to start the game to the server.

[0529] Step 2:

[0530] The server initializes the player data and returns the initial data.

[0531] Server: Receives account information and initializes new player data.

[0532] Server: Sends initialized player data to the device.

[0533] Terminal: Displays the received player data to the user.

[0534] Step 3:

[0535] The user selects the dataset.

[0536] Users: Check the available dataset options from the game screen.

[0537] User: Select a specific dataset.

[0538] Terminal: Sends the selection results to the server.

[0539] Step 4:

[0540] The server evaluates the suitability of the dataset.

[0541] Server: Check the contents of the selected dataset.

[0542] Server: Evaluates the quality and appropriateness of the dataset.

[0543] Step 5:

[0544] The server accepts any data sets it deems appropriate and updates the user data.

[0545] Server: Accepts datasets that are deemed appropriate based on the evaluation results.

[0546] Server: Updates user data with dataset information.

[0547] Server: Sends updated user data to the device.

[0548] Terminal: Displays received updates to the user.

[0549] Step 6:

[0550] The server trains the generating AI.

[0551] Server: Starts the learning process of the generative AI based on the dataset.

[0552] Server: Inputs data into the AI ​​model and performs training.

[0553] Step 7:

[0554] The server generates the learning results and sends them to the terminal.

[0555] Server: Generates learning results and growth status.

[0556] Server: Sends the learning results to the terminal.

[0557] Terminal: Displays learning results and growth status to the user.

[0558] Step 8:

[0559] The emotion engine recognizes the user's emotions.

[0560] User: Expresses emotions through facial expressions and voice during gameplay.

[0561] Terminal: Collects user emotion data using sensor devices such as cameras and microphones.

[0562] Terminal: Sends collected emotion data to the server.

[0563] Server: The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0564] Step 9:

[0565] The emotion engine regulates the learning process of generative AI.

[0566] Server: Adjusts the learning process of the generative AI based on the perceived emotional state of the user.

[0567] Server: In the case of positive sentiment, it selects a more difficult dataset or provides quick feedback.

[0568] Server: For negative emotions, we choose an easier dataset and make adjustments to reduce the burden on the learning process.

[0569] Step 10:

[0570] Users can check the progress and feedback of the generated AI.

[0571] User: View learning results, progress status, and emotional feedback displayed on the device.

[0572] User: Select a new dataset if necessary and repeat the process of training the generative AI.

[0573] Example 2

[0574] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0575] Conventional generative AI training simulation games provide a uniform learning process and feedback without considering the user's emotions, which limits the user experience and reduces game continuity and learning effectiveness. Furthermore, if the user selects an inappropriate dataset, the growth of the generative AI can be hindered.

[0576] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0577] In this invention, the server includes means for transmitting user account information to the server and initializing player data, means for the player to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generating AI based on the evaluated data set, means for transmitting the learning results of the generating AI to the server and displaying them on the terminal, means for collecting and analyzing user emotion data, and means for adjusting the learning process and feedback of the generating AI based on the analyzed emotion data. This enables appropriate feedback and adjustment of the learning process according to the user's emotions, providing a more advanced and sustainable user experience.

[0578] "User" refers to the person who operates the system and participates in the generative AI's learning process.

[0579] "Server" refers to a central computing device that processes, manages, and communicates data.

[0580] "Terminal" refers to an input and output device that is directly operated by a user.

[0581] "Account information" refers to information that includes a user's identification information and initial configuration data.

[0582] "Player Data" refers to data that indicates a user's progress and status in the game.

[0583] "Dataset" refers to the set of training data used to train generative AI.

[0584] "Evaluation" refers to the process of checking the suitability and quality of a dataset and determining whether it is suitable for training generative AI.

[0585] "Generative AI" refers to an AI model that learns knowledge based on input data and generates new information and responses.

[0586] The "learning process" refers to the series of steps that generative AI takes to acquire knowledge based on a dataset.

[0587] "Learning results" refers to the output and model status generated after the generative artificial intelligence learns from a dataset.

[0588] "Emotional data" refers to information that indicates the user's emotional state, including facial expressions, tone of voice, and other sensory data.

[0589] "Analysis" refers to the process of analyzing collected emotional data to determine the user's current emotional state.

[0590] "Feedback" refers to information including users' reactions and opinions regarding the learning process and results.

[0591] "Tuning" refers to the process of optimizing the learning process and feedback based on analyzed emotional data.

[0592] The following describes how to specifically put the present invention into practice.

[0593] First, this system is a simulation game for users to train generative AI. By combining it with an emotion engine, the aim is to improve the learning process of generative AI and the user experience.

[0594] Hardware and software used

[0595] 1. Hardware:

[0596] User devices: PCs, smartphones, tablets, etc.

[0597] Server: a central computing device that processes and manages data

[0598] Emotion data collection devices: cameras, microphones, and other sensors

[0599] 2. Software:

[0600] Game application: an interface for user operation

[0601] Emotion Engine: A component for analyzing user emotions in real time

[0602] Dataset Selection Algorithm: Software for assessing the suitability of datasets

[0603] Generative AI models: machine learning algorithms such as GPT-3

[0604] Specific processing of the program

[0605] 1. Starting the game and initializing your account:

[0606] To start a game, a user launches a game application and enters account information, which the device then sends to the server.

[0607] The server initializes the user's player data based on the received account information, including the user's basic information and initial points.

[0608] The server sends initialization data to the terminal, which displays this data on its screen.

[0609] 2. Dataset selection and evaluation:

[0610] The user selects an available dataset from the options on the game screen.

[0611] The terminal transmits the user's selection information to the server, which includes the data set identification information.

[0612] The server evaluates the suitability and quality of the dataset based on the identification information.

[0613] The server notifies the device of the evaluation results, and datasets deemed appropriate are used to train the generative AI.

[0614] 3. Training generative AI and displaying results:

[0615] The server trains a generative AI model based on the dataset that is assessed as appropriate.

[0616] Once training is complete, the server generates the learning results and growth status of the generated model.

[0617] The server sends these results to the terminal, which displays them on the screen for the user to confirm.

[0618] 4. Feedback adjustment by emotion engine:

[0619] The device uses a camera and microphone to collect user emotional data.

[0620] The collected emotion data is sent to a server, which analyzes the emotion.

[0621] Based on the analysis results, the server adjusts the learning process and feedback of the generative AI. For example, if the user feels "fun," it increases positive feedback. If the user feels "tired," it slows down the learning process.

[0622] The server sends the adjusted feedback to the device, which displays it on the screen.

[0623] Examples of concrete examples and prompts

[0624] Example: If the user feels "fun," the emotion engine will recognize this emotion and reinforce the positive feedback to the generative AI throughout the learning process. Conversely, if the user feels "tired," the emotion engine will analyze this emotion and slow down the learning process.

[0625] Example prompt sentence:

[0626] Prompt to emotion engine: "The user is currently feeling happy. Based on this emotion, please choose an appropriate dataset to provide positive feedback for training the generative AI."

[0627] Prompt for dataset selection algorithm: "Please rate the relevance and quality of dataset A selected by the user and return the results."

[0628] In this way, the present invention enables appropriate feedback and adjustment of the learning process according to the user's emotions, providing a more advanced and sustainable user experience.

[0629] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0630] Step 1: Start the game and initialize your account

[0631] Specific operation: The user launches the game application and presses the "Start" button.

[0632] Input: User account information (e.g., user ID, password)

[0633] Processing: The device sends the entered account information to the server. The server then initializes the user's player data based on the received information. This initialization includes the user's basic information and initial points.

[0634] Output: Initialized player data

[0635] Specific operation: The server sends the generated initial data to the terminal, and the terminal displays this data on the screen.

[0636] Step 2: Dataset selection and evaluation

[0637] Specific behavior: The user selects an available dataset from the options on the game screen, for example, "Dataset A."

[0638] Input: User selection information (e.g., dataset ID)

[0639] Processing: The device sends this selection information to the server, which evaluates the suitability and quality of the received dataset information.

[0640] Output: Evaluation result (whether the dataset is suitable or not)

[0641] Specific operation: The server notifies the terminal of the evaluation result, and the terminal displays the result on the screen.

[0642] Step 3: Training the generative AI and displaying the results

[0643] Specific operation: The server trains a generative AI model based on the dataset that is evaluated as appropriate.

[0644] Input: The evaluated dataset

[0645] Processing: The server inputs the dataset into a generative AI model (e.g., GPT-3) and trains the model, updating its growth status along the way.

[0646] Output: Learning results and growth status

[0647] Specific operation: The server sends the training results to the terminal, which displays them on the screen for the user to confirm.

[0648] Step 4: Feedback adjustment by the emotion engine

[0649] Specific operation: The device collects the user's emotional data using a camera and microphone. For example, if the user is feeling "happy," their facial expression and tone of voice are collected as data.

[0650] Input: Collected emotional data (e.g., facial expressions, tone of voice)

[0651] Processing: The device sends the emotion data to the server, which analyzes the data and identifies the user's emotional state (e.g., "happy," "tired," etc.).

[0652] Output: Analysis results (user's emotional state)

[0653] Specific operation: The server adjusts the learning process and feedback of the generative AI based on the analyzed emotional data. For example, if the user feels "fun," it increases the positive feedback of the learning process. If the user feels "tired," it slows down the learning process.

[0654] Output: Adjusted feedback

[0655] Specific operation: The server sends the adjusted feedback to the device, and the device displays the feedback on the screen.

[0656] (Application example 2)

[0657] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0658] Conventional content distribution services provide content uniformly without considering user emotions, making it difficult to provide services optimized for individual users' moods, hobbies, and preferences. Furthermore, simulation games using generative AI have the problem of being unable to provide feedback or adjust the learning process based on user emotions, making it difficult to improve the quality of the user experience. To solve these issues, a system is needed that recognizes user emotions in real time and optimizes the generative AI's learning process and content provision based on those emotions.

[0659] 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.

[0660] In this invention, the server includes means for transmitting user identification information to the information processing device and initializing user data, means for the user to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generation AI based on the evaluated data set, means for transmitting the learning results of the generation AI to the information processing device and displaying them on a display device, means for collecting user emotion data and adjusting the learning process of the generation AI based on the emotion data, and means for providing feedback according to the user's emotion. This makes it possible to provide content that reflects the user's emotions and to optimize the learning process of the generation AI.

[0661] "User identification information" is data for distinguishing a specific user from other users.

[0662] An "information processing device" is a device for processing digital data.

[0663] "User Data" is data that includes information related to a particular user.

[0664] A "specific dataset" is a specific collection of data used to train a generative AI.

[0665] "Relevance" is a measure of how well something is suited to a particular purpose.

[0666] "Generative AI" is artificial intelligence that automatically generates various outputs through learning.

[0667] "Learning results" refer to the results and performance that generative AI achieves through the learning process.

[0668] A "display device" is a device for visually displaying digital data.

[0669] "Emotion data" is data that indicates the emotional state of the user.

[0670] "Feedback" is information used to make further adjustments and improvements based on the system's output information.

[0671] The present invention relates to a system for realizing content distribution and simulation games using generative AI while recognizing user emotions. The purpose of this invention is to improve the user experience by exchanging data between an information processing device and a user terminal and adjusting the learning process of the generative AI.

[0672] 1. System Programming and Configuration

[0673] This system consists of hardware and software for both an information processing device (server) and a display device (terminal). The server receives the user's identification information and initializes the user data. The terminal then sends a specific data set selected by the user to the server, which evaluates its appropriateness. The evaluated data set is learned by the generative AI, and the learning results are sent to the terminal and displayed. The terminal also collects the user's emotional data in real time and sends it to the server. The server adjusts the generative AI's learning process based on the emotional data and provides appropriate feedback to the user.

[0674] 2. Hardware and Software Used

[0675] On the server side, emotion recognition and generation AI training is performed using Python, TensorFlow, and OpenCV. On the device side, a smartphone camera is used to capture the user's facial image and generate emotion data. This allows the entire system to achieve consistent data processing and feedback.

[0676] 3. Examples of concrete examples and prompts

[0677] In a specific example, the system recommends entertainment content based on emotional data if the user is feeling happy, and adjusts the system to play relaxing music tracks if the user is feeling sad.

[0678] Example prompt sentence:

[0679] "If the user's emotion is recognized as 'Happy', optimize to recommend videos in the entertainment category."

[0680] "If the user's emotion is recognized as 'Sad', optimize to play a relaxing music track."

[0681] As a result, the present invention makes it possible to recognize user emotions in real time and provide content based on them, as well as adjust the learning process of the AI ​​generator, thereby significantly improving the quality of the user experience.

[0682] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0683] Step 1:

[0684] The user starts the application and enters the identification information (account information).

[0685] Input: User account information

[0686] Output: Sending identification information to the server

[0687] How it works: A user launches the application and enters their account information on the login screen. The device receives this and sends the identification information to the server.

[0688] Step 2:

[0689] The server initializes the user data based on the received identification information.

[0690] Input: User identification information

[0691] Output: Initialized user data

[0692] Operation: The server recognizes the user based on the user's identification information and initializes new user data, including the user's game progress and current settings.

[0693] Step 3:

[0694] The user selects a particular data set from the terminal.

[0695] Input: list of available datasets, user selection

[0696] Output: Information about the selected dataset

[0697] Operation: The terminal displays multiple data set options, from which the user selects one. This selection is sent from the terminal to the server.

[0698] Step 4:

[0699] The server evaluates the appropriateness of the selected data set.

[0700] Input: Information about the selected data set

[0701] Output: Evaluation result (appropriate or inappropriate)

[0702] How it works: The server analyzes the content of the selected dataset and evaluates its quality and appropriateness. If deemed appropriate, the dataset is used to train the generative AI.

[0703] Step 5:

[0704] The server trains the generative AI based on the evaluated data set.

[0705] Input: The dataset to be evaluated

[0706] Output: Learning results of generative AI

[0707] How it works: The server uses the evaluated dataset to train a generative AI model, allowing it to learn useful patterns and information from new data.

[0708] Step 6:

[0709] The server sends the learning results of the generation AI to the terminal, where they are displayed.

[0710] Input: Generative AI learning results

[0711] Output: Training results displayed on the terminal

[0712] Operation: The server sends the learning results of the generative AI to the device, which displays them on the screen. The user can check the progress and results of the generative AI.

[0713] Step 7:

[0714] The device collects the user's emotional data and sends it to the server.

[0715] Input: User's emotions (facial expressions, voice, etc.)

[0716] Output: Sending emotion data to the server

[0717] How it works: The device (smartphone camera and microphone) collects emotional data from the user's facial expressions and voice. This data is sent to a server in real time.

[0718] Step 8:

[0719] The server adjusts the learning process of the generative AI based on the emotion data.

[0720] Input: User emotion data

[0721] Output: The adjusted generative AI learning process

[0722] How it works: The server analyzes the collected emotional data and adjusts the learning process of the generative AI based on that data. For example, if the user is feeling stressed, the learning process will be slowed down.

[0723] Step 9:

[0724] The server provides feedback according to the user's emotions.

[0725] Input: trained learning process and emotion data

[0726] Output: Send feedback message

[0727] Operation: The server coordinates the learning process of the generation AI and generates feedback messages based on the results. The feedback messages are sent to the terminal and displayed to the user.

[0728] 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.

[0729] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0730] 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.

[0731] [Third embodiment]

[0732] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0733] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0734] 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).

[0735] 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.

[0736] 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.

[0737] 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).

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0744] The present invention relates to a simulation game in which a user develops a generative AI. The system provides a process in which the user selects a specific data set and grows the generative AI by learning from that data.

[0745] First, when a user starts a game, the user's account information is sent from the device to the server. This causes the user's player data to be initialized on the server. The player data includes the user's basic information and game progress.

[0746] The user selects a specific dataset from the available dataset options on the game screen. The device then sends this selection to the server, which reviews the received dataset and evaluates its suitability and quality. The suitability evaluation determines whether the dataset is effective for training the generative AI.

[0747] If the server evaluates the selected dataset as appropriate, it will use that dataset to begin the learning process for the Generator AI. The Generator AI will then learn from the provided dataset and generate the results. These learning results include indicators of the Generator AI's growth status and reliability improvement. These results are sent from the server to the device and provided to the user.

[0748] As a concrete example, consider the case where a user selects an "image dataset." This selection information is sent from the device to the server, and the server evaluates the appropriateness of the dataset. If the evaluation results indicate that the dataset is appropriate, the image dataset is used to train the generative AI. Once the generative AI has completed its training, its growth status and reliability improvement information are sent to the device via the server, and the user can check this.

[0749] In addition, the system also has the ability to simulate users' daily activities and interactions. For example, users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. This feature allows users to gain a deeper understanding of the generated AI's growth process and effectively cultivate the AI ​​through in-game activities.

[0750] By using such a system, users can intuitively understand the learning process of generative AI and develop the skills to select and apply appropriate data, making it possible for even ordinary users to effectively utilize advanced generative AI technology.

[0751] The processing flow will be explained below.

[0752] Step 1:

[0753] The user starts the game.

[0754] User: Clicks the "Start Game" button.

[0755] Terminal: Sends the user's account information and a signal to start the game to the server.

[0756] Step 2:

[0757] The server initializes the player data and returns the initial data.

[0758] Server: Receives account information and initializes new player data.

[0759] Server: Sends initialized player data to the device.

[0760] Terminal: Displays the received player data to the user.

[0761] Step 3:

[0762] The user selects the dataset.

[0763] Users: Check the available dataset options from the game screen.

[0764] User: Select a specific dataset.

[0765] Terminal: Sends the selection results to the server.

[0766] Step 4:

[0767] The server evaluates the suitability of the dataset.

[0768] Server: Check the contents of the selected dataset.

[0769] Server: Evaluates the quality and appropriateness of the dataset.

[0770] Step 5:

[0771] The server accepts any data sets it deems appropriate and updates the user data.

[0772] Server: Accepts datasets that are deemed appropriate based on the evaluation results.

[0773] Server: Updates user data with dataset information.

[0774] Server: Sends updated user data to the device.

[0775] Terminal: Displays received updates to the user.

[0776] Step 6:

[0777] The server trains the generating AI.

[0778] Server: Starts the learning process of the generative AI based on the dataset.

[0779] Server: Inputs data into the AI ​​model and performs training.

[0780] Step 7:

[0781] The server generates the learning results and sends them to the terminal.

[0782] Server: Generates learning results and growth status.

[0783] Server: Sends the learning results to the terminal.

[0784] Terminal: Displays learning results and growth status to the user.

[0785] Step 8:

[0786] Users can check the progress of the generated AI.

[0787] User: Check the learning results and growth status displayed on the device.

[0788] User: Select a new dataset if necessary and repeat the process of training the generative AI.

[0789] Example 1

[0790] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0791] While modern generative AI technology is highly advanced, there is a lack of means to practically experience and understand the learning process. In particular, it is difficult for ordinary users to intuitively and effectively experience the learning process of generative AI and acquire the skills to select and apply appropriate datasets. Another problem is the lack of a way to instantly check the learning results of generative AI and receive feedback.

[0792] 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.

[0793] In this invention, the server includes: means for transmitting the user's account information to the server to initialize player data; means for the user to select a specific dataset from available dataset options; means for transmitting the selection information from the terminal to the server; means for evaluating the appropriateness of the dataset received by the server; means for the generating AI to learn from the dataset based on the evaluation results; and means for transmitting the learning results of the generating AI from the server to the terminal and displaying them on a user interface. This allows even ordinary users to intuitively understand the learning process of the generating AI in a game format, select an appropriate dataset, and train the generating AI effectively. Furthermore, the ability to quickly check the learning results of the generating AI and receive feedback deepens understanding of the learning process.

[0794] "User Account Information" means data used to identify the identity and access privileges of individuals using the System.

[0795] "Player Data" refers to a collection of data about a specific user, including basic information about the user and their game progress.

[0796] "Dataset options" refers to a list or menu that provides choices for datasets used for training.

[0797] "Selection information" refers to information about the dataset selected by the user, and is data sent from the terminal to the server.

[0798] "Relevance" is a criterion for assessing whether a particular dataset is useful for training a generative AI.

[0799] "Generative AI" refers to algorithms or systems that learn and generate results based on a given dataset.

[0800] "Evaluation results" are the results of an evaluation of the suitability and quality of a dataset, and are data that influence the learning process of the generative AI.

[0801] "Learning results" are output data generated by the generative AI after learning from a specific dataset, and include information on growth status and reliability improvement.

[0802] A "user interface" is a screen or operation panel that allows users to directly interact with the system and displays the learning results.

[0803] The present invention relates to a simulation game in which a user develops a generative AI. The system provides a process in which the user selects a specific data set and grows the generative AI by learning from that data.

[0804] First, when a user starts a game, the user's account information is sent from the terminal to the server. This allows the server to initialize the user's player data. The player data includes the user's basic information and game progress. The user's account information is data used to identify the identity and access privileges of individuals using the system.

[0805] Next, the user selects a specific dataset from the dataset options available on the game screen. The device then sends this selection to the server, which reviews the contents of the received dataset and evaluates its suitability and quality. Suitability is a criterion for assessing whether a particular dataset is useful for training a generative AI.

[0806] If the server evaluates the selected dataset as appropriate, it will use that dataset to begin the learning process of the generative AI. The server inputs the dataset into the generative AI model and runs the learning algorithm. Generative AI is an algorithm or system that learns based on a given dataset and generates results. The generated learning results include indicators of the generative AI's growth status and reliability improvement. Learning results are output data generated by the generative AI after learning based on a specific dataset, and include information on its growth status and reliability improvement. These results are sent from the server to the terminal and provided to the user.

[0807] As a concrete example, consider the case where a user selects "Image Dataset." When the user selects "Image Dataset" on the dataset selection screen and presses the "Confirm" button, the device sends the selection information to the server via API. The server uses an evaluation algorithm to evaluate the dataset based on the criteria of "Is this dataset useful for training the generative AI?" If the evaluation results indicate that the image dataset is appropriate, it is used to train the generative AI. The server inputs the dataset into the generative AI model and runs the training algorithm using a Python library (e.g., TensorFlow, PyTorch). Once the generative AI has completed training, its growth status and reliability improvement information are sent to the device via the server, where the user can check it.

[0808] Furthermore, the system also features a function that simulates the user's daily activities and interactions. Users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. This function allows users to gain a deeper understanding of the generated AI's growth process and effectively develop it through their in-game activities. This allows even ordinary users to effectively utilize advanced generative AI technology.

[0809] As an example of a prompt sentence, when a user sets a prompt for image generation, the following sentence may be considered:

[0810] "Generate an image of a cat using this dataset."

[0811] This system configuration allows users to intuitively understand the learning process of generative AI, select appropriate datasets, and develop the skills to effectively progress the learning process.

[0812] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0813] Step 1:

[0814] A user starts a game. When the user presses the "Start" button in the application, the device makes an API call in the background and sends the user's account information to the server. The server receives this account information and authenticates the user by referencing the database. If authentication is successful, it initializes the player data, generates new player data, and saves it in the database. The initialized player data is obtained as output.

[0815] Step 2:

[0816] The user selects a specific dataset from the dataset options available on the game screen. For example, when the user selects "Image Dataset" and presses the "Confirm" button, the device sends the selection information to the server via API. The server receives this selection information and uses an evaluation algorithm to evaluate the suitability of the dataset. The input is the selection information, and the output is the evaluation result of the dataset's suitability.

[0817] Step 3:

[0818] Based on the results of the suitability assessment, the server inputs the dataset into the generative AI model and executes the learning algorithm. For example, a Python library (e.g., TensorFlow, PyTorch) is used to input the dataset into the generative AI model. Through learning, the generative AI grows, and the growth status and generated results are obtained as outputs.

[0819] Step 4:

[0820] After the generative AI has completed its training, the server stores the training results in a database and sends them to the device. The device then displays the received training results on its user interface. Specifically, the generated images and reliability improvement information are sent and displayed on the device screen along with the message "The generative AI has trained the image dataset. New images have been generated." The training results are then displayed to the user.

[0821] Step 5:

[0822] Users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. For example, when a user performs an activity such as "chatting with friends" in the game, that information is sent from the device to the server. The server receives the activity information and updates the growth status of the generated AI. The input is the activity information, and the output is the updated growth status.

[0823] In this way, the server and terminal process the data based on the input information and provide appropriate output, allowing the user to intuitively understand the learning process of the generative AI, select an appropriate dataset, and effectively develop the generative AI.

[0824] (Application example 1)

[0825] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0826] In conventional generative AI training simulation games, it was difficult for users to intuitively understand the generative AI's learning process and its growth status. Furthermore, in order to effectively use generative AI in virtual stores, users are required to understand and practically use techniques to improve the performance of generative AI, but there has been a lack of systems that enable this.

[0827] 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.

[0828] In this invention, the server includes means for initializing user account information, means for the player to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generating AI based on the evaluated data set, means for transmitting the learning results of the generating AI to the server and displaying them on the terminal, and means for training the generating AI through user operations in the virtual space and improving the accuracy of customer service and product recommendations. This allows the user to intuitively understand the generating AI's learning process and its growth status, making it possible to effectively use the generating AI in a virtual store.

[0829] "User account information" refers to information for managing a user's identification information, authentication information, and game player data.

[0830] "Initializing player data" refers to the process of creating new player data on the server using the user's account information and setting it to its initial state.

[0831] A "specific dataset" refers to a collection of data of a specific type or content that is used as training data for generative AI.

[0832] "Means for assessing the suitability of a dataset" refers to the process and methods for determining whether a selected dataset is suitable for training generative AI and is of sufficient quality.

[0833] "Means for training generative AI" refers to the process and system by which generative AI absorbs information and learns from the evaluated dataset.

[0834] "Means for transmitting the learning results of the generation AI to a server and displaying them on a terminal" refers to a system and method for transmitting the learning results of the generation AI to a user's terminal via a server, allowing the user to check them.

[0835] "User operations in a virtual space" refers to the actions and interactions that a user performs within a virtual environment.

[0836] "Developing a generative AI" refers to the process of improving the capabilities and performance of a generative AI through user choices and operations.

[0837] "Means for improving the accuracy of customer service and product recommendations" refers to methods and systems for improving the quality and effectiveness of customer service and product recommendations when generative AI is used in a virtual store.

[0838] The present invention relates to a simulation game system for training a generating AI and improving its performance, particularly in a virtual store. Users can operate this system using a device such as a smartphone.

[0839] Overall system overview

[0840] The server has the function of receiving the user's account information and initializing the player data. When the user starts a game, the user data is initialized on the server based on the account information sent from the terminal.

[0841] Next, the user selects the dataset to be trained by the generative AI through an interface for selecting a specific dataset, and this selection information is sent from the device to the server.

[0842] The server evaluates the appropriateness of the selected dataset and determines whether it is suitable. If it is, the generating AI begins learning using this dataset.

[0843] The results of the generative AI's learning are sent to a server and displayed on the user's device. The user can check the results and manipulate the AI ​​in virtual space to further improve its performance.

[0844] Hardware and Software Configuration

[0845] Terminal: A smartphone or tablet device that accepts user input and communicates with the server.

[0846] Servers: Database server and application server. The database server stores user data and datasets, while the application server evaluates the suitability of datasets and manages the learning process of the generative AI.

[0847] Communication: RESTful API using HTTP and HTTPS to ensure reliable data communication between the server and the device.

[0848] The software configuration consists of an application that provides a user interface running on the terminal side, and a program that initializes user data, evaluates datasets, and manages the learning of generative AI running on the server side.Specific development languages ​​used on the terminal side include Swift and Kotlin, and on the server side include Python and Java, as well as web frameworks such as Flask and Django.

[0849] Introduction of specific examples

[0850] A possible usage scenario would be the following prompt:

[0851] "Train an AI model with images of your new product line. Develop an AI model that will make optimal product recommendations to customers."

[0852] In this specific example, the user selects an "image dataset of a new product" on their device, and the dataset is sent to the server. The server evaluates the appropriateness of the dataset, and if the evaluation is successful, the generative AI begins learning using that data. The learning results are displayed on the device via the server, allowing the user to check the growth and effectiveness of the generative AI. The performance of the generative AI can also be tested in a virtual space, which can be used to assist with actual customer interactions and product recommendations.

[0853] This system allows users to intuitively understand the learning process of generative AI and realize the potential applications of generative AI in virtual stores, while selecting the optimal dataset and developing an AI model.

[0854] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0855] Step 1:

[0856] To start a game, a user sends account information from their device to the server. The input is the account information entered by the user into the device, and the output is the player data stored on the server. Specifically, the user opens the application, enters account information, and presses the "Start" button. This information is sent from the device to the server via an HTTP request.

[0857] Step 2:

[0858] The server initializes the player data. The input is the account information received in step 1, and the output is the initialized player data. Specifically, the server creates a new player data record in the database corresponding to the user ID based on the account information received.

[0859] Step 3:

[0860] The user selects a specific dataset on the game screen. The input is the user's selection operation, and the output is the dataset selection information sent from the device to the server. Specifically, the user selects an appropriate dataset from the list on the dataset selection screen and sends it to the server.

[0861] Step 4:

[0862] The server evaluates the appropriateness of the selected dataset. The input is the received dataset selection information, and the output is the evaluation result of whether the dataset is appropriate. Specifically, the server checks the contents of the selected dataset and evaluates whether it is suitable for learning.

[0863] Step 5:

[0864] The server trains the generative AI based on the evaluated dataset. The input is the evaluated dataset, and the output is the learning result of the generative AI. Specifically, the server uses the evaluated dataset to execute the learning process on the AI ​​model.

[0865] Step 6:

[0866] The learning results of the generative AI are sent to the server and then displayed on the device. The input is the learning results of the generative AI, and the output is the growth status of the generative AI and an indicator of reliability improvement that is displayed on the device. Specifically, the learning results are sent from the server to the device in JSON format or similar and displayed on the screen within the application.

[0867] Step 7:

[0868] The user performs operations in a virtual space to train the generating AI. The input is the user's operations, and the output is the performance improvement status of the generating AI. Specifically, the user performs operations and tasks in the virtual space, which are reflected in the growth of the generating AI. The results of these operations are sent to the server, and the generating AI's performance is updated.

[0869] 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.

[0870] This invention relates to a simulation game in which users train generative AI, and aims to improve the learning process of the generative AI and the user experience by combining it with an emotion engine that recognizes the user's emotions. This system allows users to select a dataset and train the generative AI by learning from that data, while also enabling feedback and adjustments based on the user's emotions.

[0871] First, when a user starts a game, the device sends a game start signal to the server along with the user's account information. The server initializes the player data based on the received account information and returns the initial data to the device. The user can then view and confirm the initialized player data on the game screen.

[0872] The user reviews the available dataset options on the screen and selects a specific dataset. The device sends this selection to the server, which reviews the dataset's contents and evaluates its appropriateness and quality. If the dataset is deemed appropriate as a result of the evaluation, it is used to train the generative AI. The server trains the generative AI based on the dataset, generates learning results and growth status, and sends them to the device, allowing the user to view the generative AI's learning results.

[0873] Furthermore, by integrating an emotion engine, the system can recognize the user's emotions in real time and adjust the generative AI's learning process and feedback based on those emotions. Specifically, the emotion engine collects user emotional data and uses it to help select a dataset to provide to the generative AI. For example, if the user is feeling stressed, the emotion engine can suggest a dataset with a lower level of difficulty. The emotion engine also adjusts the generative AI's learning results according to the user's emotions and provides more appropriate feedback.

[0874] For example, if the user feels "fun," the emotion engine will recognize this emotion and reinforce positive feedback to the generative AI through the learning process. Also, if the user feels "tired," the emotion engine will gently adjust the learning process to reduce the burden on the user.

[0875] In this way, the present invention, which incorporates an emotion engine, improves the quality of the user experience and makes the learning process of the generative AI more effective. Furthermore, users can train the generative AI in a way that matches their own emotions, resulting in a greater sense of satisfaction.

[0876] The processing flow will be explained below.

[0877] Step 1:

[0878] The user starts the game.

[0879] User: Clicks the "Start Game" button.

[0880] Terminal: Sends the user's account information and a signal to start the game to the server.

[0881] Step 2:

[0882] The server initializes the player data and returns the initial data.

[0883] Server: Receives account information and initializes new player data.

[0884] Server: Sends initialized player data to the device.

[0885] Terminal: Displays the received player data to the user.

[0886] Step 3:

[0887] The user selects the dataset.

[0888] Users: Check the available dataset options from the game screen.

[0889] User: Select a specific dataset.

[0890] Terminal: Sends the selection results to the server.

[0891] Step 4:

[0892] The server evaluates the suitability of the dataset.

[0893] Server: Check the contents of the selected dataset.

[0894] Server: Evaluates the quality and appropriateness of the dataset.

[0895] Step 5:

[0896] The server accepts any data sets it deems appropriate and updates the user data.

[0897] Server: Accepts datasets that are deemed appropriate based on the evaluation results.

[0898] Server: Updates user data with dataset information.

[0899] Server: Sends updated user data to the device.

[0900] Terminal: Displays received updates to the user.

[0901] Step 6:

[0902] The server trains the generating AI.

[0903] Server: Starts the learning process of the generative AI based on the dataset.

[0904] Server: Inputs data into the AI ​​model and performs training.

[0905] Step 7:

[0906] The server generates the learning results and sends them to the terminal.

[0907] Server: Generates learning results and growth status.

[0908] Server: Sends the learning results to the terminal.

[0909] Terminal: Displays learning results and growth status to the user.

[0910] Step 8:

[0911] The emotion engine recognizes the user's emotions.

[0912] User: Expresses emotions through facial expressions and voice during gameplay.

[0913] Terminal: Collects user emotion data using sensor devices such as cameras and microphones.

[0914] Terminal: Sends collected emotion data to the server.

[0915] Server: The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0916] Step 9:

[0917] The emotion engine regulates the learning process of generative AI.

[0918] Server: Adjusts the learning process of the generative AI based on the perceived emotional state of the user.

[0919] Server: In the case of positive sentiment, it selects a more difficult dataset or provides quick feedback.

[0920] Server: For negative emotions, we choose an easier dataset and make adjustments to reduce the burden on the learning process.

[0921] Step 10:

[0922] Users can check the progress and feedback of the generated AI.

[0923] User: View learning results, progress status, and emotional feedback displayed on the device.

[0924] User: Select a new dataset if necessary and repeat the process of training the generative AI.

[0925] Example 2

[0926] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0927] Conventional generative AI training simulation games provide a uniform learning process and feedback without considering the user's emotions, which limits the user experience and reduces game continuity and learning effectiveness. Furthermore, if the user selects an inappropriate dataset, the growth of the generative AI can be hindered.

[0928] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0929] In this invention, the server includes means for transmitting user account information to the server and initializing player data, means for the player to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generating AI based on the evaluated data set, means for transmitting the learning results of the generating AI to the server and displaying them on the terminal, means for collecting and analyzing user emotion data, and means for adjusting the learning process and feedback of the generating AI based on the analyzed emotion data. This enables appropriate feedback and adjustment of the learning process according to the user's emotions, providing a more advanced and sustainable user experience.

[0930] "User" refers to the person who operates the system and participates in the generative AI's learning process.

[0931] "Server" refers to a central computing device that processes, manages, and communicates data.

[0932] "Terminal" refers to an input and output device that is directly operated by a user.

[0933] "Account information" refers to information that includes a user's identification information and initial configuration data.

[0934] "Player Data" refers to data that indicates a user's progress and status in the game.

[0935] "Dataset" refers to the set of training data used to train generative AI.

[0936] "Evaluation" refers to the process of checking the suitability and quality of a dataset and determining whether it is suitable for training generative AI.

[0937] "Generative AI" refers to an AI model that learns knowledge based on input data and generates new information and responses.

[0938] The "learning process" refers to the series of steps that generative AI takes to acquire knowledge based on a dataset.

[0939] "Learning results" refers to the output and model status generated after the generative artificial intelligence learns from a dataset.

[0940] "Emotional data" refers to information that indicates the user's emotional state, including facial expressions, tone of voice, and other sensory data.

[0941] "Analysis" refers to the process of analyzing collected emotional data to determine the user's current emotional state.

[0942] "Feedback" refers to information including users' reactions and opinions regarding the learning process and results.

[0943] "Tuning" refers to the process of optimizing the learning process and feedback based on analyzed emotional data.

[0944] The following describes how to specifically put the present invention into practice.

[0945] First, this system is a simulation game for users to train generative AI. By combining it with an emotion engine, the aim is to improve the learning process of generative AI and the user experience.

[0946] Hardware and software used

[0947] 1. Hardware:

[0948] User devices: PCs, smartphones, tablets, etc.

[0949] Server: a central computing device that processes and manages data

[0950] Emotion data collection devices: cameras, microphones, and other sensors

[0951] 2. Software:

[0952] Game application: an interface for user operation

[0953] Emotion Engine: A component for analyzing user emotions in real time

[0954] Dataset Selection Algorithm: Software for assessing the suitability of datasets

[0955] Generative AI models: machine learning algorithms such as GPT-3

[0956] Specific processing of the program

[0957] 1. Starting the game and initializing your account:

[0958] To start a game, a user launches a game application and enters account information, which the device then sends to the server.

[0959] The server initializes the user's player data based on the received account information, including the user's basic information and initial points.

[0960] The server sends initialization data to the terminal, which displays this data on its screen.

[0961] 2. Dataset selection and evaluation:

[0962] The user selects an available dataset from the options on the game screen.

[0963] The terminal transmits the user's selection information to the server, which includes the data set identification information.

[0964] The server evaluates the suitability and quality of the dataset based on the identification information.

[0965] The server notifies the device of the evaluation results, and datasets deemed appropriate are used to train the generative AI.

[0966] 3. Training generative AI and displaying results:

[0967] The server trains a generative AI model based on the dataset that is assessed as appropriate.

[0968] Once training is complete, the server generates the learning results and growth status of the generated model.

[0969] The server sends these results to the terminal, which displays them on the screen for the user to confirm.

[0970] 4. Feedback adjustment by emotion engine:

[0971] The device uses a camera and microphone to collect user emotional data.

[0972] The collected emotion data is sent to a server, which analyzes the emotion.

[0973] Based on the analysis results, the server adjusts the learning process and feedback of the generative AI. For example, if the user feels "fun," it increases positive feedback. If the user feels "tired," it slows down the learning process.

[0974] The server sends the adjusted feedback to the device, which displays it on the screen.

[0975] Examples of concrete examples and prompts

[0976] Example: If the user feels "fun," the emotion engine will recognize this emotion and reinforce the positive feedback to the generative AI throughout the learning process. Conversely, if the user feels "tired," the emotion engine will analyze this emotion and slow down the learning process.

[0977] Example prompt sentence:

[0978] Prompt to emotion engine: "The user is currently feeling happy. Based on this emotion, please choose an appropriate dataset to provide positive feedback for training the generative AI."

[0979] Prompt for dataset selection algorithm: "Please rate the relevance and quality of dataset A selected by the user and return the results."

[0980] In this way, the present invention enables appropriate feedback and adjustment of the learning process according to the user's emotions, providing a more advanced and sustainable user experience.

[0981] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0982] Step 1: Start the game and initialize your account

[0983] Specific operation: The user launches the game application and presses the "Start" button.

[0984] Input: User account information (e.g., user ID, password)

[0985] Processing: The device sends the entered account information to the server. The server then initializes the user's player data based on the received information. This initialization includes the user's basic information and initial points.

[0986] Output: Initialized player data

[0987] Specific operation: The server sends the generated initial data to the terminal, and the terminal displays this data on the screen.

[0988] Step 2: Dataset selection and evaluation

[0989] Specific behavior: The user selects an available dataset from the options on the game screen, for example, "Dataset A."

[0990] Input: User selection information (e.g., dataset ID)

[0991] Processing: The device sends this selection information to the server, which evaluates the suitability and quality of the received dataset information.

[0992] Output: Evaluation result (whether the dataset is suitable or not)

[0993] Specific operation: The server notifies the terminal of the evaluation result, and the terminal displays the result on the screen.

[0994] Step 3: Training the generative AI and displaying the results

[0995] Specific operation: The server trains a generative AI model based on the dataset that is evaluated as appropriate.

[0996] Input: The evaluated dataset

[0997] Processing: The server inputs the dataset into a generative AI model (e.g., GPT-3) and trains the model, updating its growth status along the way.

[0998] Output: Learning results and growth status

[0999] Specific operation: The server sends the training results to the terminal, which displays them on the screen for the user to confirm.

[1000] Step 4: Feedback adjustment by the emotion engine

[1001] Specific operation: The device collects the user's emotional data using a camera and microphone. For example, if the user is feeling "happy," their facial expression and tone of voice are collected as data.

[1002] Input: Collected emotional data (e.g., facial expressions, tone of voice)

[1003] Processing: The device sends the emotion data to the server, which analyzes the data and identifies the user's emotional state (e.g., "happy," "tired," etc.).

[1004] Output: Analysis results (user's emotional state)

[1005] Specific operation: The server adjusts the learning process and feedback of the generative AI based on the analyzed emotional data. For example, if the user feels "fun," it increases the positive feedback of the learning process. If the user feels "tired," it slows down the learning process.

[1006] Output: Adjusted feedback

[1007] Specific operation: The server sends the adjusted feedback to the device, and the device displays the feedback on the screen.

[1008] (Application example 2)

[1009] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1010] Conventional content distribution services provide content uniformly without considering user emotions, making it difficult to provide services optimized for individual users' moods, hobbies, and preferences. Furthermore, simulation games using generative AI have the problem of being unable to provide feedback or adjust the learning process based on user emotions, making it difficult to improve the quality of the user experience. To solve these issues, a system is needed that recognizes user emotions in real time and optimizes the generative AI's learning process and content provision based on those emotions.

[1011] 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.

[1012] In this invention, the server includes means for transmitting user identification information to the information processing device and initializing user data, means for the user to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generation AI based on the evaluated data set, means for transmitting the learning results of the generation AI to the information processing device and displaying them on a display device, means for collecting user emotion data and adjusting the learning process of the generation AI based on the emotion data, and means for providing feedback according to the user's emotion. This makes it possible to provide content that reflects the user's emotions and to optimize the learning process of the generation AI.

[1013] "User identification information" is data for distinguishing a specific user from other users.

[1014] An "information processing device" is a device for processing digital data.

[1015] "User Data" is data that includes information related to a particular user.

[1016] A "specific dataset" is a specific collection of data used to train a generative AI.

[1017] "Relevance" is a measure of how well something is suited to a particular purpose.

[1018] "Generative AI" is artificial intelligence that automatically generates various outputs through learning.

[1019] "Learning results" refer to the results and performance that generative AI achieves through the learning process.

[1020] A "display device" is a device for visually displaying digital data.

[1021] "Emotion data" is data that indicates the emotional state of the user.

[1022] "Feedback" is information used to make further adjustments and improvements based on the system's output information.

[1023] The present invention relates to a system for realizing content distribution and simulation games using generative AI while recognizing user emotions. The purpose of this invention is to improve the user experience by exchanging data between an information processing device and a user terminal and adjusting the learning process of the generative AI.

[1024] 1. System Programming and Configuration

[1025] This system consists of hardware and software for both an information processing device (server) and a display device (terminal). The server receives the user's identification information and initializes the user data. The terminal then sends a specific data set selected by the user to the server, which evaluates its appropriateness. The evaluated data set is learned by the generative AI, and the learning results are sent to the terminal and displayed. The terminal also collects the user's emotional data in real time and sends it to the server. The server adjusts the generative AI's learning process based on the emotional data and provides appropriate feedback to the user.

[1026] 2. Hardware and Software Used

[1027] On the server side, emotion recognition and generation AI training is performed using Python, TensorFlow, and OpenCV. On the device side, a smartphone camera is used to capture the user's facial image and generate emotion data. This allows the entire system to achieve consistent data processing and feedback.

[1028] 3. Examples of concrete examples and prompts

[1029] In a specific example, the system recommends entertainment content based on emotional data if the user is feeling happy, and adjusts the system to play relaxing music tracks if the user is feeling sad.

[1030] Example prompt sentence:

[1031] "If the user's emotion is recognized as 'Happy', optimize to recommend videos in the entertainment category."

[1032] "If the user's emotion is recognized as 'Sad', optimize to play a relaxing music track."

[1033] As a result, the present invention makes it possible to recognize user emotions in real time and provide content based on them, as well as adjust the learning process of the AI ​​generator, thereby significantly improving the quality of the user experience.

[1034] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1035] Step 1:

[1036] The user starts the application and enters the identification information (account information).

[1037] Input: User account information

[1038] Output: Sending identification information to the server

[1039] How it works: A user launches the application and enters their account information on the login screen. The device receives this and sends the identification information to the server.

[1040] Step 2:

[1041] The server initializes the user data based on the received identification information.

[1042] Input: User identification information

[1043] Output: Initialized user data

[1044] Operation: The server recognizes the user based on the user's identification information and initializes new user data, including the user's game progress and current settings.

[1045] Step 3:

[1046] The user selects a particular data set from the terminal.

[1047] Input: list of available datasets, user selection

[1048] Output: Information about the selected dataset

[1049] Operation: The terminal displays multiple data set options, from which the user selects one. This selection is sent from the terminal to the server.

[1050] Step 4:

[1051] The server evaluates the appropriateness of the selected data set.

[1052] Input: Information about the selected data set

[1053] Output: Evaluation result (appropriate or inappropriate)

[1054] How it works: The server analyzes the content of the selected dataset and evaluates its quality and appropriateness. If deemed appropriate, the dataset is used to train the generative AI.

[1055] Step 5:

[1056] The server trains the generative AI based on the evaluated data set.

[1057] Input: The dataset to be evaluated

[1058] Output: Learning results of generative AI

[1059] How it works: The server uses the evaluated dataset to train a generative AI model, allowing it to learn useful patterns and information from new data.

[1060] Step 6:

[1061] The server sends the learning results of the generation AI to the terminal, where they are displayed.

[1062] Input: Generative AI learning results

[1063] Output: Training results displayed on the terminal

[1064] Operation: The server sends the learning results of the generative AI to the device, which displays them on the screen. The user can check the progress and results of the generative AI.

[1065] Step 7:

[1066] The device collects the user's emotional data and sends it to the server.

[1067] Input: User's emotions (facial expressions, voice, etc.)

[1068] Output: Sending emotion data to the server

[1069] How it works: The device (smartphone camera and microphone) collects emotional data from the user's facial expressions and voice. This data is sent to a server in real time.

[1070] Step 8:

[1071] The server adjusts the learning process of the generative AI based on the emotion data.

[1072] Input: User emotion data

[1073] Output: The adjusted generative AI learning process

[1074] How it works: The server analyzes the collected emotional data and adjusts the learning process of the generative AI based on that data. For example, if the user is feeling stressed, the learning process will be slowed down.

[1075] Step 9:

[1076] The server provides feedback according to the user's emotions.

[1077] Input: trained learning process and emotion data

[1078] Output: Send feedback message

[1079] Operation: The server coordinates the learning process of the generation AI and generates feedback messages based on the results. The feedback messages are sent to the terminal and displayed to the user.

[1080] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1081] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1082] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1083] [Fourth embodiment]

[1084] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1085] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1086] 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).

[1087] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1088] 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.

[1089] 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).

[1090] 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.

[1091] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1092] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1093] 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.

[1094] 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.

[1095] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1096] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1097] The present invention relates to a simulation game in which a user develops a generative AI. The system provides a process in which the user selects a specific data set and grows the generative AI by learning from that data.

[1098] First, when a user starts a game, the user's account information is sent from the device to the server. This causes the user's player data to be initialized on the server. The player data includes the user's basic information and game progress.

[1099] The user selects a specific dataset from the available dataset options on the game screen. The device then sends this selection to the server, which reviews the received dataset and evaluates its suitability and quality. The suitability evaluation determines whether the dataset is effective for training the generative AI.

[1100] If the server evaluates the selected dataset as appropriate, it will use that dataset to begin the learning process for the Generator AI. The Generator AI will then learn from the provided dataset and generate the results. These learning results include indicators of the Generator AI's growth status and reliability improvement. These results are sent from the server to the device and provided to the user.

[1101] As a concrete example, consider the case where a user selects an "image dataset." This selection information is sent from the device to the server, and the server evaluates the appropriateness of the dataset. If the evaluation results indicate that the dataset is appropriate, the image dataset is used to train the generative AI. Once the generative AI has completed its training, its growth status and reliability improvement information are sent to the device via the server, and the user can check this.

[1102] In addition, the system also has the ability to simulate users' daily activities and interactions. For example, users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. This feature allows users to gain a deeper understanding of the generated AI's growth process and effectively cultivate the AI ​​through in-game activities.

[1103] By using such a system, users can intuitively understand the learning process of generative AI and develop the skills to select and apply appropriate data, making it possible for even ordinary users to effectively utilize advanced generative AI technology.

[1104] The processing flow will be explained below.

[1105] Step 1:

[1106] The user starts the game.

[1107] User: Clicks the "Start Game" button.

[1108] Terminal: Sends the user's account information and a signal to start the game to the server.

[1109] Step 2:

[1110] The server initializes the player data and returns the initial data.

[1111] Server: Receives account information and initializes new player data.

[1112] Server: Sends initialized player data to the device.

[1113] Terminal: Displays the received player data to the user.

[1114] Step 3:

[1115] The user selects the dataset.

[1116] Users: Check the available dataset options from the game screen.

[1117] User: Select a specific dataset.

[1118] Terminal: Sends the selection results to the server.

[1119] Step 4:

[1120] The server evaluates the suitability of the dataset.

[1121] Server: Check the contents of the selected dataset.

[1122] Server: Evaluates the quality and appropriateness of the dataset.

[1123] Step 5:

[1124] The server accepts any data sets it deems appropriate and updates the user data.

[1125] Server: Accepts datasets that are deemed appropriate based on the evaluation results.

[1126] Server: Updates user data with dataset information.

[1127] Server: Sends updated user data to the device.

[1128] Terminal: Displays received updates to the user.

[1129] Step 6:

[1130] The server trains the generating AI.

[1131] Server: Starts the learning process of the generative AI based on the dataset.

[1132] Server: Inputs data into the AI ​​model and performs training.

[1133] Step 7:

[1134] The server generates the learning results and sends them to the terminal.

[1135] Server: Generates learning results and growth status.

[1136] Server: Sends the learning results to the terminal.

[1137] Terminal: Displays learning results and growth status to the user.

[1138] Step 8:

[1139] Users can check the progress of the generated AI.

[1140] User: Check the learning results and growth status displayed on the device.

[1141] User: Select a new dataset if necessary and repeat the process of training the generative AI.

[1142] Example 1

[1143] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1144] While modern generative AI technology is highly advanced, there is a lack of means to practically experience and understand the learning process. In particular, it is difficult for ordinary users to intuitively and effectively experience the learning process of generative AI and acquire the skills to select and apply appropriate datasets. Another problem is the lack of a way to instantly check the learning results of generative AI and receive feedback.

[1145] 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.

[1146] In this invention, the server includes: means for transmitting the user's account information to the server to initialize player data; means for the user to select a specific dataset from available dataset options; means for transmitting the selection information from the terminal to the server; means for evaluating the appropriateness of the dataset received by the server; means for the generating AI to learn from the dataset based on the evaluation results; and means for transmitting the learning results of the generating AI from the server to the terminal and displaying them on a user interface. This allows even ordinary users to intuitively understand the learning process of the generating AI in a game format, select an appropriate dataset, and train the generating AI effectively. Furthermore, the ability to quickly check the learning results of the generating AI and receive feedback deepens understanding of the learning process.

[1147] "User Account Information" means data used to identify the identity and access privileges of individuals using the System.

[1148] "Player Data" refers to a collection of data about a specific user, including basic information about the user and their game progress.

[1149] "Dataset options" refers to a list or menu that provides choices for datasets used for training.

[1150] "Selection information" refers to information about the dataset selected by the user, and is data sent from the terminal to the server.

[1151] "Relevance" is a criterion for assessing whether a particular dataset is useful for training a generative AI.

[1152] "Generative AI" refers to algorithms or systems that learn and generate results based on a given dataset.

[1153] "Evaluation results" are the results of an evaluation of the suitability and quality of a dataset, and are data that influence the learning process of the generative AI.

[1154] "Learning results" are output data generated by the generative AI after learning from a specific dataset, and include information on growth status and reliability improvement.

[1155] A "user interface" is a screen or operation panel that allows users to directly interact with the system and displays the learning results.

[1156] The present invention relates to a simulation game in which a user develops a generative AI. The system provides a process in which the user selects a specific data set and grows the generative AI by learning from that data.

[1157] First, when a user starts a game, the user's account information is sent from the terminal to the server. This allows the server to initialize the user's player data. The player data includes the user's basic information and game progress. The user's account information is data used to identify the identity and access privileges of individuals using the system.

[1158] Next, the user selects a specific dataset from the dataset options available on the game screen. The device then sends this selection to the server, which reviews the contents of the received dataset and evaluates its suitability and quality. Suitability is a criterion for assessing whether a particular dataset is useful for training a generative AI.

[1159] If the server evaluates the selected dataset as appropriate, it will use that dataset to begin the learning process of the generative AI. The server inputs the dataset into the generative AI model and runs the learning algorithm. Generative AI is an algorithm or system that learns based on a given dataset and generates results. The generated learning results include indicators of the generative AI's growth status and reliability improvement. Learning results are output data generated by the generative AI after learning based on a specific dataset, and include information on its growth status and reliability improvement. These results are sent from the server to the terminal and provided to the user.

[1160] As a concrete example, consider the case where a user selects "Image Dataset." When the user selects "Image Dataset" on the dataset selection screen and presses the "Confirm" button, the device sends the selection information to the server via API. The server uses an evaluation algorithm to evaluate the dataset based on the criteria of "Is this dataset useful for training the generative AI?" If the evaluation results indicate that the image dataset is appropriate, it is used to train the generative AI. The server inputs the dataset into the generative AI model and runs the training algorithm using a Python library (e.g., TensorFlow, PyTorch). Once the generative AI has completed training, its growth status and reliability improvement information are sent to the device via the server, where the user can check it.

[1161] Furthermore, the system also features a function that simulates the user's daily activities and interactions. Users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. This function allows users to gain a deeper understanding of the generated AI's growth process and effectively develop it through their in-game activities. This allows even ordinary users to effectively utilize advanced generative AI technology.

[1162] As an example of a prompt sentence, when a user sets a prompt for image generation, the following sentence may be considered:

[1163] "Generate an image of a cat using this dataset."

[1164] This system configuration allows users to intuitively understand the learning process of generative AI, select appropriate datasets, and develop the skills to effectively progress the learning process.

[1165] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1166] Step 1:

[1167] A user starts a game. When the user presses the "Start" button in the application, the device makes an API call in the background and sends the user's account information to the server. The server receives this account information and authenticates the user by referencing the database. If authentication is successful, it initializes the player data, generates new player data, and saves it in the database. The initialized player data is obtained as output.

[1168] Step 2:

[1169] The user selects a specific dataset from the dataset options available on the game screen. For example, when the user selects "Image Dataset" and presses the "Confirm" button, the device sends the selection information to the server via API. The server receives this selection information and uses an evaluation algorithm to evaluate the suitability of the dataset. The input is the selection information, and the output is the evaluation result of the dataset's suitability.

[1170] Step 3:

[1171] Based on the results of the suitability assessment, the server inputs the dataset into the generative AI model and executes the learning algorithm. For example, a Python library (e.g., TensorFlow, PyTorch) is used to input the dataset into the generative AI model. Through learning, the generative AI grows, and the growth status and generated results are obtained as outputs.

[1172] Step 4:

[1173] After the generative AI has completed its training, the server stores the training results in a database and sends them to the device. The device then displays the received training results on its user interface. Specifically, the generated images and reliability improvement information are sent and displayed on the device screen along with the message "The generative AI has trained the image dataset. New images have been generated." The training results are then displayed to the user.

[1174] Step 5:

[1175] Users can influence the growth of the generated AI by interacting with friends in the game or completing specific tasks. For example, when a user performs an activity such as "chatting with friends" in the game, that information is sent from the device to the server. The server receives the activity information and updates the growth status of the generated AI. The input is the activity information, and the output is the updated growth status.

[1176] In this way, the server and terminal process the data based on the input information and provide appropriate output, allowing the user to intuitively understand the learning process of the generative AI, select an appropriate dataset, and effectively develop the generative AI.

[1177] (Application example 1)

[1178] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1179] In conventional generative AI training simulation games, it was difficult for users to intuitively understand the generative AI's learning process and its growth status. Furthermore, in order to effectively use generative AI in virtual stores, users are required to understand and practically use techniques to improve the performance of generative AI, but there has been a lack of systems that enable this.

[1180] 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.

[1181] In this invention, the server includes means for initializing user account information, means for the player to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generating AI based on the evaluated data set, means for transmitting the learning results of the generating AI to the server and displaying them on the terminal, and means for training the generating AI through user operations in the virtual space and improving the accuracy of customer service and product recommendations. This allows the user to intuitively understand the generating AI's learning process and its growth status, making it possible to effectively use the generating AI in a virtual store.

[1182] "User account information" refers to information for managing a user's identification information, authentication information, and game player data.

[1183] "Initializing player data" refers to the process of creating new player data on the server using the user's account information and setting it to its initial state.

[1184] A "specific dataset" refers to a collection of data of a specific type or content that is used as training data for generative AI.

[1185] "Means for assessing the suitability of a dataset" refers to the process and methods for determining whether a selected dataset is suitable for training generative AI and is of sufficient quality.

[1186] "Means for training generative AI" refers to the process and system by which generative AI absorbs information and learns from the evaluated dataset.

[1187] "Means for transmitting the learning results of the generation AI to a server and displaying them on a terminal" refers to a system and method for transmitting the learning results of the generation AI to a user's terminal via a server, allowing the user to check them.

[1188] "User operations in a virtual space" refers to the actions and interactions that a user performs within a virtual environment.

[1189] "Developing a generative AI" refers to the process of improving the capabilities and performance of a generative AI through user choices and operations.

[1190] "Means for improving the accuracy of customer service and product recommendations" refers to methods and systems for improving the quality and effectiveness of customer service and product recommendations when generative AI is used in a virtual store.

[1191] The present invention relates to a simulation game system for training a generating AI and improving its performance, particularly in a virtual store. Users can operate this system using a device such as a smartphone.

[1192] Overall system overview

[1193] The server has the function of receiving the user's account information and initializing the player data. When the user starts a game, the user data is initialized on the server based on the account information sent from the terminal.

[1194] Next, the user selects the dataset to be trained by the generative AI through an interface for selecting a specific dataset, and this selection information is sent from the device to the server.

[1195] The server evaluates the appropriateness of the selected dataset and determines whether it is suitable. If it is, the generating AI begins learning using this dataset.

[1196] The results of the generative AI's learning are sent to a server and displayed on the user's device. The user can check the results and manipulate the AI ​​in virtual space to further improve its performance.

[1197] Hardware and Software Configuration

[1198] Terminal: A smartphone or tablet device that accepts user input and communicates with the server.

[1199] Servers: Database server and application server. The database server stores user data and datasets, while the application server evaluates the suitability of datasets and manages the learning process of the generative AI.

[1200] Communication: RESTful API using HTTP and HTTPS to ensure reliable data communication between the server and the device.

[1201] The software configuration consists of an application that provides a user interface running on the terminal side, and a program that initializes user data, evaluates datasets, and manages the learning of generative AI running on the server side.Specific development languages ​​used on the terminal side include Swift and Kotlin, and on the server side include Python and Java, as well as web frameworks such as Flask and Django.

[1202] Introduction of specific examples

[1203] A possible usage scenario would be the following prompt:

[1204] "Train an AI model with images of your new product line. Develop an AI model that will make optimal product recommendations to customers."

[1205] In this specific example, the user selects an "image dataset of a new product" on their device, and the dataset is sent to the server. The server evaluates the appropriateness of the dataset, and if the evaluation is successful, the generative AI begins learning using that data. The learning results are displayed on the device via the server, allowing the user to check the growth and effectiveness of the generative AI. The performance of the generative AI can also be tested in a virtual space, which can be used to assist with actual customer interactions and product recommendations.

[1206] This system allows users to intuitively understand the learning process of generative AI and realize the potential applications of generative AI in virtual stores, while selecting the optimal dataset and developing an AI model.

[1207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1208] Step 1:

[1209] To start a game, a user sends account information from their device to the server. The input is the account information entered by the user into the device, and the output is the player data stored on the server. Specifically, the user opens the application, enters account information, and presses the "Start" button. This information is sent from the device to the server via an HTTP request.

[1210] Step 2:

[1211] The server initializes the player data. The input is the account information received in step 1, and the output is the initialized player data. Specifically, the server creates a new player data record in the database corresponding to the user ID based on the account information received.

[1212] Step 3:

[1213] The user selects a specific dataset on the game screen. The input is the user's selection operation, and the output is the dataset selection information sent from the device to the server. Specifically, the user selects an appropriate dataset from the list on the dataset selection screen and sends it to the server.

[1214] Step 4:

[1215] The server evaluates the appropriateness of the selected dataset. The input is the received dataset selection information, and the output is the evaluation result of whether the dataset is appropriate. Specifically, the server checks the contents of the selected dataset and evaluates whether it is suitable for learning.

[1216] Step 5:

[1217] The server trains the generative AI based on the evaluated dataset. The input is the evaluated dataset, and the output is the learning result of the generative AI. Specifically, the server uses the evaluated dataset to execute the learning process on the AI ​​model.

[1218] Step 6:

[1219] The learning results of the generative AI are sent to the server and then displayed on the device. The input is the learning results of the generative AI, and the output is the growth status of the generative AI and an indicator of reliability improvement that is displayed on the device. Specifically, the learning results are sent from the server to the device in JSON format or similar and displayed on the screen within the application.

[1220] Step 7:

[1221] The user performs operations in a virtual space to train the generating AI. The input is the user's operations, and the output is the performance improvement status of the generating AI. Specifically, the user performs operations and tasks in the virtual space, which are reflected in the growth of the generating AI. The results of these operations are sent to the server, and the generating AI's performance is updated.

[1222] 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.

[1223] This invention relates to a simulation game in which users train generative AI, and aims to improve the learning process of the generative AI and the user experience by combining it with an emotion engine that recognizes the user's emotions. This system allows users to select a dataset and train the generative AI by learning from that data, while also enabling feedback and adjustments based on the user's emotions.

[1224] First, when a user starts a game, the device sends a game start signal to the server along with the user's account information. The server initializes the player data based on the received account information and returns the initial data to the device. The user can then view and confirm the initialized player data on the game screen.

[1225] The user reviews the available dataset options on the screen and selects a specific dataset. The device sends this selection to the server, which reviews the dataset's contents and evaluates its appropriateness and quality. If the dataset is deemed appropriate as a result of the evaluation, it is used to train the generative AI. The server trains the generative AI based on the dataset, generates learning results and growth status, and sends them to the device, allowing the user to view the generative AI's learning results.

[1226] Furthermore, by integrating an emotion engine, the system can recognize the user's emotions in real time and adjust the generative AI's learning process and feedback based on those emotions. Specifically, the emotion engine collects user emotional data and uses it to help select a dataset to provide to the generative AI. For example, if the user is feeling stressed, the emotion engine can suggest a dataset with a lower level of difficulty. The emotion engine also adjusts the generative AI's learning results according to the user's emotions and provides more appropriate feedback.

[1227] For example, if the user feels "fun," the emotion engine will recognize this emotion and reinforce positive feedback to the generative AI through the learning process. Also, if the user feels "tired," the emotion engine will gently adjust the learning process to reduce the burden on the user.

[1228] In this way, the present invention, which incorporates an emotion engine, improves the quality of the user experience and makes the learning process of the generative AI more effective. Furthermore, users can train the generative AI in a way that matches their own emotions, resulting in a greater sense of satisfaction.

[1229] The processing flow will be explained below.

[1230] Step 1:

[1231] The user starts the game.

[1232] User: Clicks the "Start Game" button.

[1233] Terminal: Sends the user's account information and a signal to start the game to the server.

[1234] Step 2:

[1235] The server initializes the player data and returns the initial data.

[1236] Server: Receives account information and initializes new player data.

[1237] Server: Sends initialized player data to the device.

[1238] Terminal: Displays the received player data to the user.

[1239] Step 3:

[1240] The user selects the dataset.

[1241] Users: Check the available dataset options from the game screen.

[1242] User: Select a specific dataset.

[1243] Terminal: Sends the selection results to the server.

[1244] Step 4:

[1245] The server evaluates the suitability of the dataset.

[1246] Server: Check the contents of the selected dataset.

[1247] Server: Evaluates the quality and appropriateness of the dataset.

[1248] Step 5:

[1249] The server accepts any data sets it deems appropriate and updates the user data.

[1250] Server: Accepts datasets that are deemed appropriate based on the evaluation results.

[1251] Server: Updates user data with dataset information.

[1252] Server: Sends updated user data to the device.

[1253] Terminal: Displays received updates to the user.

[1254] Step 6:

[1255] The server trains the generating AI.

[1256] Server: Starts the learning process of the generative AI based on the dataset.

[1257] Server: Inputs data into the AI ​​model and performs training.

[1258] Step 7:

[1259] The server generates the learning results and sends them to the terminal.

[1260] Server: Generates learning results and growth status.

[1261] Server: Sends the learning results to the terminal.

[1262] Terminal: Displays learning results and growth status to the user.

[1263] Step 8:

[1264] The emotion engine recognizes the user's emotions.

[1265] User: Expresses emotions through facial expressions and voice during gameplay.

[1266] Terminal: Collects user emotion data using sensor devices such as cameras and microphones.

[1267] Terminal: Sends collected emotion data to the server.

[1268] Server: The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1269] Step 9:

[1270] The emotion engine regulates the learning process of generative AI.

[1271] Server: Adjusts the learning process of the generative AI based on the perceived emotional state of the user.

[1272] Server: In the case of positive sentiment, it selects a more difficult dataset or provides quick feedback.

[1273] Server: For negative emotions, we choose an easier dataset and make adjustments to reduce the burden on the learning process.

[1274] Step 10:

[1275] Users can check the progress and feedback of the generated AI.

[1276] User: View learning results, progress status, and emotional feedback displayed on the device.

[1277] User: Select a new dataset if necessary and repeat the process of training the generative AI.

[1278] Example 2

[1279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1280] Conventional generative AI training simulation games provide a uniform learning process and feedback without considering the user's emotions, which limits the user experience and reduces game continuity and learning effectiveness. Furthermore, if the user selects an inappropriate dataset, the growth of the generative AI can be hindered.

[1281] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1282] In this invention, the server includes means for transmitting user account information to the server and initializing player data, means for the player to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generating AI based on the evaluated data set, means for transmitting the learning results of the generating AI to the server and displaying them on the terminal, means for collecting and analyzing user emotion data, and means for adjusting the learning process and feedback of the generating AI based on the analyzed emotion data. This enables appropriate feedback and adjustment of the learning process according to the user's emotions, providing a more advanced and sustainable user experience.

[1283] "User" refers to the person who operates the system and participates in the generative AI's learning process.

[1284] "Server" refers to a central computing device that processes, manages, and communicates data.

[1285] "Terminal" refers to an input and output device that is directly operated by a user.

[1286] "Account information" refers to information that includes a user's identification information and initial configuration data.

[1287] "Player Data" refers to data that indicates a user's progress and status in the game.

[1288] "Dataset" refers to the set of training data used to train generative AI.

[1289] "Evaluation" refers to the process of checking the suitability and quality of a dataset and determining whether it is suitable for training generative AI.

[1290] "Generative AI" refers to an AI model that learns knowledge based on input data and generates new information and responses.

[1291] The "learning process" refers to the series of steps that generative AI takes to acquire knowledge based on a dataset.

[1292] "Learning results" refers to the output and model status generated after the generative artificial intelligence learns from a dataset.

[1293] "Emotional data" refers to information that indicates the user's emotional state, including facial expressions, tone of voice, and other sensory data.

[1294] "Analysis" refers to the process of analyzing collected emotional data to determine the user's current emotional state.

[1295] "Feedback" refers to information including users' reactions and opinions regarding the learning process and results.

[1296] "Tuning" refers to the process of optimizing the learning process and feedback based on analyzed emotional data.

[1297] The following describes how to specifically put the present invention into practice.

[1298] First, this system is a simulation game for users to train generative AI. By combining it with an emotion engine, the aim is to improve the learning process of generative AI and the user experience.

[1299] Hardware and software used

[1300] 1. Hardware:

[1301] User devices: PCs, smartphones, tablets, etc.

[1302] Server: a central computing device that processes and manages data

[1303] Emotion data collection devices: cameras, microphones, and other sensors

[1304] 2. Software:

[1305] Game application: an interface for user operation

[1306] Emotion Engine: A component for analyzing user emotions in real time

[1307] Dataset Selection Algorithm: Software for assessing the suitability of datasets

[1308] Generative AI models: machine learning algorithms such as GPT-3

[1309] Specific processing of the program

[1310] 1. Starting the game and initializing your account:

[1311] To start a game, a user launches a game application and enters account information, which the device then sends to the server.

[1312] The server initializes the user's player data based on the received account information, including the user's basic information and initial points.

[1313] The server sends initialization data to the terminal, which displays this data on its screen.

[1314] 2. Dataset selection and evaluation:

[1315] The user selects an available dataset from the options on the game screen.

[1316] The terminal transmits the user's selection information to the server, which includes the data set identification information.

[1317] The server evaluates the suitability and quality of the dataset based on the identification information.

[1318] The server notifies the device of the evaluation results, and datasets deemed appropriate are used to train the generative AI.

[1319] 3. Training generative AI and displaying results:

[1320] The server trains a generative AI model based on the dataset that is assessed as appropriate.

[1321] Once training is complete, the server generates the learning results and growth status of the generated model.

[1322] The server sends these results to the terminal, which displays them on the screen for the user to confirm.

[1323] 4. Feedback adjustment by emotion engine:

[1324] The device uses a camera and microphone to collect user emotional data.

[1325] The collected emotion data is sent to a server, which analyzes the emotion.

[1326] Based on the analysis results, the server adjusts the learning process and feedback of the generative AI. For example, if the user feels "fun," it increases positive feedback. If the user feels "tired," it slows down the learning process.

[1327] The server sends the adjusted feedback to the device, which displays it on the screen.

[1328] Examples of concrete examples and prompts

[1329] Example: If the user feels "fun," the emotion engine will recognize this emotion and reinforce the positive feedback to the generative AI throughout the learning process. Conversely, if the user feels "tired," the emotion engine will analyze this emotion and slow down the learning process.

[1330] Example prompt sentence:

[1331] Prompt to emotion engine: "The user is currently feeling happy. Based on this emotion, please choose an appropriate dataset to provide positive feedback for training the generative AI."

[1332] Prompt for dataset selection algorithm: "Please rate the relevance and quality of dataset A selected by the user and return the results."

[1333] In this way, the present invention enables appropriate feedback and adjustment of the learning process according to the user's emotions, providing a more advanced and sustainable user experience.

[1334] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1335] Step 1: Start the game and initialize your account

[1336] Specific operation: The user launches the game application and presses the "Start" button.

[1337] Input: User account information (e.g., user ID, password)

[1338] Processing: The device sends the entered account information to the server. The server then initializes the user's player data based on the received information. This initialization includes the user's basic information and initial points.

[1339] Output: Initialized player data

[1340] Specific operation: The server sends the generated initial data to the terminal, and the terminal displays this data on the screen.

[1341] Step 2: Dataset selection and evaluation

[1342] Specific behavior: The user selects an available dataset from the options on the game screen, for example, "Dataset A."

[1343] Input: User selection information (e.g., dataset ID)

[1344] Processing: The device sends this selection information to the server, which evaluates the suitability and quality of the received dataset information.

[1345] Output: Evaluation result (whether the dataset is suitable or not)

[1346] Specific operation: The server notifies the terminal of the evaluation result, and the terminal displays the result on the screen.

[1347] Step 3: Training the generative AI and displaying the results

[1348] Specific operation: The server trains a generative AI model based on the dataset that is evaluated as appropriate.

[1349] Input: The evaluated dataset

[1350] Processing: The server inputs the dataset into a generative AI model (e.g., GPT-3) and trains the model, updating its growth status along the way.

[1351] Output: Learning results and growth status

[1352] Specific operation: The server sends the training results to the terminal, which displays them on the screen for the user to confirm.

[1353] Step 4: Feedback adjustment by the emotion engine

[1354] Specific operation: The device collects the user's emotional data using a camera and microphone. For example, if the user is feeling "happy," their facial expression and tone of voice are collected as data.

[1355] Input: Collected emotional data (e.g., facial expressions, tone of voice)

[1356] Processing: The device sends the emotion data to the server, which analyzes the data and identifies the user's emotional state (e.g., "happy," "tired," etc.).

[1357] Output: Analysis results (user's emotional state)

[1358] Specific operation: The server adjusts the learning process and feedback of the generative AI based on the analyzed emotional data. For example, if the user feels "fun," it increases the positive feedback of the learning process. If the user feels "tired," it slows down the learning process.

[1359] Output: Adjusted feedback

[1360] Specific operation: The server sends the adjusted feedback to the device, and the device displays the feedback on the screen.

[1361] (Application example 2)

[1362] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1363] Conventional content distribution services provide content uniformly without considering user emotions, making it difficult to provide services optimized for individual users' moods, hobbies, and preferences. Furthermore, simulation games using generative AI have the problem of being unable to provide feedback or adjust the learning process based on user emotions, making it difficult to improve the quality of the user experience. To solve these issues, a system is needed that recognizes user emotions in real time and optimizes the generative AI's learning process and content provision based on those emotions.

[1364] 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.

[1365] In this invention, the server includes means for transmitting user identification information to the information processing device and initializing user data, means for the user to select a specific data set, means for evaluating the appropriateness of the selected data set, means for training the generation AI based on the evaluated data set, means for transmitting the learning results of the generation AI to the information processing device and displaying them on a display device, means for collecting user emotion data and adjusting the learning process of the generation AI based on the emotion data, and means for providing feedback according to the user's emotion. This makes it possible to provide content that reflects the user's emotions and to optimize the learning process of the generation AI.

[1366] "User identification information" is data for distinguishing a specific user from other users.

[1367] An "information processing device" is a device for processing digital data.

[1368] "User Data" is data that includes information related to a particular user.

[1369] A "specific dataset" is a specific collection of data used to train a generative AI.

[1370] "Relevance" is a measure of how well something is suited to a particular purpose.

[1371] "Generative AI" is artificial intelligence that automatically generates various outputs through learning.

[1372] "Learning results" refer to the results and performance that generative AI achieves through the learning process.

[1373] A "display device" is a device for visually displaying digital data.

[1374] "Emotion data" is data that indicates the emotional state of the user.

[1375] "Feedback" is information used to make further adjustments and improvements based on the system's output information.

[1376] The present invention relates to a system for realizing content distribution and simulation games using generative AI while recognizing user emotions. The purpose of this invention is to improve the user experience by exchanging data between an information processing device and a user terminal and adjusting the learning process of the generative AI.

[1377] 1. System Programming and Configuration

[1378] This system consists of hardware and software for both an information processing device (server) and a display device (terminal). The server receives the user's identification information and initializes the user data. The terminal then sends a specific data set selected by the user to the server, which evaluates its appropriateness. The evaluated data set is learned by the generative AI, and the learning results are sent to the terminal and displayed. The terminal also collects the user's emotional data in real time and sends it to the server. The server adjusts the generative AI's learning process based on the emotional data and provides appropriate feedback to the user.

[1379] 2. Hardware and Software Used

[1380] On the server side, emotion recognition and generation AI training is performed using Python, TensorFlow, and OpenCV. On the device side, a smartphone camera is used to capture the user's facial image and generate emotion data. This allows the entire system to achieve consistent data processing and feedback.

[1381] 3. Examples of concrete examples and prompts

[1382] In a specific example, the system recommends entertainment content based on emotional data if the user is feeling happy, and adjusts the system to play relaxing music tracks if the user is feeling sad.

[1383] Example prompt sentence:

[1384] "If the user's emotion is recognized as 'Happy', optimize to recommend videos in the entertainment category."

[1385] "If the user's emotion is recognized as 'Sad', optimize to play a relaxing music track."

[1386] As a result, the present invention makes it possible to recognize user emotions in real time and provide content based on them, as well as adjust the learning process of the AI ​​generator, thereby significantly improving the quality of the user experience.

[1387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1388] Step 1:

[1389] The user starts the application and enters the identification information (account information).

[1390] Input: User account information

[1391] Output: Sending identification information to the server

[1392] How it works: A user launches the application and enters their account information on the login screen. The device receives this and sends the identification information to the server.

[1393] Step 2:

[1394] The server initializes the user data based on the received identification information.

[1395] Input: User identification information

[1396] Output: Initialized user data

[1397] Operation: The server recognizes the user based on the user's identification information and initializes new user data, including the user's game progress and current settings.

[1398] Step 3:

[1399] The user selects a particular data set from the terminal.

[1400] Input: list of available datasets, user selection

[1401] Output: Information about the selected dataset

[1402] Operation: The terminal displays multiple data set options, from which the user selects one. This selection is sent from the terminal to the server.

[1403] Step 4:

[1404] The server evaluates the appropriateness of the selected data set.

[1405] Input: Information about the selected data set

[1406] Output: Evaluation result (appropriate or inappropriate)

[1407] How it works: The server analyzes the content of the selected dataset and evaluates its quality and appropriateness. If deemed appropriate, the dataset is used to train the generative AI.

[1408] Step 5:

[1409] The server trains the generative AI based on the evaluated data set.

[1410] Input: The dataset to be evaluated

[1411] Output: Learning results of generative AI

[1412] How it works: The server uses the evaluated dataset to train a generative AI model, allowing it to learn useful patterns and information from new data.

[1413] Step 6:

[1414] The server sends the learning results of the generation AI to the terminal, where they are displayed.

[1415] Input: Generative AI learning results

[1416] Output: Training results displayed on the terminal

[1417] Operation: The server sends the learning results of the generative AI to the device, which displays them on the screen. The user can check the progress and results of the generative AI.

[1418] Step 7:

[1419] The device collects the user's emotional data and sends it to the server.

[1420] Input: User's emotions (facial expressions, voice, etc.)

[1421] Output: Sending emotion data to the server

[1422] How it works: The device (smartphone camera and microphone) collects emotional data from the user's facial expressions and voice. This data is sent to a server in real time.

[1423] Step 8:

[1424] The server adjusts the learning process of the generative AI based on the emotion data.

[1425] Input: User emotion data

[1426] Output: The adjusted generative AI learning process

[1427] How it works: The server analyzes the collected emotional data and adjusts the learning process of the generative AI based on that data. For example, if the user is feeling stressed, the learning process will be slowed down.

[1428] Step 9:

[1429] The server provides feedback according to the user's emotions.

[1430] Input: trained learning process and emotion data

[1431] Output: Send feedback message

[1432] Operation: The server coordinates the learning process of the generation AI and generates feedback messages based on the results. The feedback messages are sent to the terminal and displayed to the user.

[1433] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1434] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1435] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1436] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1437] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1438] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1439] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1440] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1441] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1442] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1443] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1444] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1445] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1446] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1447] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1448] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1449] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1450] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1451] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1452] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1453] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1454] The following is further disclosed regarding the above embodiment.

[1455] (Claim 1)

[1456] A means for initializing player data by transmitting user account information to a server;

[1457] A means for the player to select a particular dataset;

[1458] a means of assessing the appropriateness of the selected dataset;

[1459] A means to train a generative AI based on the evaluated dataset; and

[1460] A means for transmitting the learning results of the generation AI to a server and displaying them on a terminal;

[1461] A system including:

[1462] (Claim 2)

[1463] 10. The system of claim 1, further comprising means for verifying the appropriateness and quality of the evaluated data set.

[1464] (Claim 3)

[1465] The system of claim 1, further comprising means for updating the AI's growth status and transmitting the results to the terminal during the learning process of the generated AI.

[1466] (Claim 4)

[1467] The system according to claim 1, further comprising a means for displaying the growth status of the generating AI on a screen according to the contents of the dataset provided by the user.

[1468] (Claim 5)

[1469] 10. The system of claim 1, further comprising means for simulating the user's daily activities and interactions within the game.

[1470] "Example 1"

[1471] (Claim 1)

[1472] A means for initializing player data by transmitting user account information to a server;

[1473] a means for a user to select a particular dataset from the available dataset options;

[1474] means for transmitting the selection information from the terminal to the server;

[1475] means for the server to evaluate the appropriateness of the received data set;

[1476] A means for training the generative AI based on the dataset based on the evaluation results;

[1477] A means for transmitting the learning results of the generation AI from the server to the terminal and displaying them on a user interface;

[1478] A system including:

[1479] (Claim 2)

[1480] 10. The system of claim 1, further comprising means for verifying the appropriateness and quality of the evaluated data set.

[1481] (Claim 3)

[1482] The system according to claim 1, further comprising means for updating the AI's growth status during the learning process of the generation AI and transmitting the results from the server to the terminal.

[1483] "Application Example 1"

[1484] (Claim 1)

[1485] A means for initializing player data by transmitting user account information to a server;

[1486] A means for the player to select a particular dataset;

[1487] a means of assessing the appropriateness of the selected dataset;

[1488] A means to train a generative AI based on the evaluated dataset; and

[1489] A means for transmitting the learning results of the generation AI to a server and displaying them on a terminal;

[1490] A means to develop generative AI through user operations in virtual space and improve the accuracy of customer service and product recommendations,

[1491] A system including:

[1492] (Claim 2)

[1493] 10. The system of claim 1, further comprising means for verifying the appropriateness and quality of the evaluated data set.

[1494] (Claim 3)

[1495] The system of claim 1, further comprising means for updating the AI's growth status and transmitting the results to the terminal during the learning process of the generated AI.

[1496] "Example 2: Combining Emotion Engines"

[1497] (Claim 1)

[1498] A means for initializing player data by transmitting user account information to a server;

[1499] A means for the player to select a particular dataset;

[1500] a means of assessing the appropriateness of the selected dataset;

[1501] A means for training a generative artificial intelligence based on the evaluated dataset; and

[1502] A means for transmitting the learning results of the generating artificial intelligence to a server and displaying them on a terminal;

[1503] means for collecting and analyzing user emotion data;

[1504] A means for adjusting the learning process and feedback of the generative artificial intelligence based on the analyzed emotion data;

[1505] A system including:

[1506] (Claim 2)

[1507] 2. The system of claim 1, further comprising means for verifying the appropriateness and quality of the evaluated datasets, and for automatically selecting the datasets to be used for training based on the user's emotional data.

[1508] (Claim 3)

[1509] The system of claim 1, further comprising means for updating the growth status of the artificial intelligence during the learning process of the generative artificial intelligence and providing appropriate feedback to the user based on the analyzed emotional data.

[1510] "Application example 2 when combining emotion engines"

[1511] (Claim 1)

[1512] means for transmitting user identification information to an information processing device to initialize user data;

[1513] a means for a user to select a particular data set;

[1514] means for assessing the suitability of the selected data set;

[1515] A means for training the generative AI based on the evaluated dataset; and

[1516] A means for transmitting the learning result of the generation AI to an information processing device and displaying it on a display device;

[1517] A means for collecting user emotional data and adjusting the learning process of the generative AI based on the emotional data;

[1518] A means for providing feedback according to the user's emotions;

[1519] A system including:

[1520] (Claim 2)

[1521] 10. The system of claim 1, further comprising means for verifying the appropriateness and quality of the evaluated data set.

[1522] (Claim 3)

[1523] 2. The system of claim 1, further comprising means for updating the AI's growth status and transmitting the results to a display device during the learning process of the generation AI. [Explanation of symbols]

[1524] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for initializing player data by transmitting user account information to a server; A means for the player to select a particular dataset; a means of assessing the appropriateness of the selected dataset; A means to train a generative AI based on the evaluated dataset; and A means for transmitting the learning results of the generation AI to a server and displaying them on a terminal; A system including:

2. 10. The system of claim 1, further comprising means for verifying the appropriateness and quality of the evaluated data set.

3. 2. The system according to claim 1, further comprising means for updating the AI's growth status and transmitting the results to the terminal during the learning process of the generated AI.

4. The system according to claim 1, further comprising means for displaying the growth status of the generating AI on a screen in accordance with the contents of the data set provided by the user.

5. 10. The system of claim 1, further comprising means for simulating the user's daily activities and interactions within the game.

Images