System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting user gameplay; means for analyzing the collected gameplay to identify user behavior patterns and feedback; means for generating and AI new game elements based on the analysis; and means for delivering the generated game elements to user terminals.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In conventional game systems, the content provided to players is static, making it difficult to provide a personalized experience that reflects the player's behavior and preferences. This makes it impossible to maintain appropriate difficulty and enjoyment for diverse player needs and skill levels, resulting in a decrease in player satisfaction. It is also difficult to immediately reflect player feedback in the game content, making effective use of such feedback. The problem that this invention aims to solve is to solve the above problems and provide users with a personalized, dynamic game experience. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a means for collecting user gameplay data is provided. Next, a means for analyzing the collected game data to identify user behavior patterns and feedback is provided. Next, a generation AI means is used to generate new game elements based on the analysis results. Furthermore, a means for delivering the generated game elements to the user's device is provided, thereby providing personalized game content according to the user's behavior and feedback. In addition, a means for checking the generated game elements to determine their ethical and moral standards is provided, providing content that can be used with peace of mind. As a result, a dynamic game experience tailored to each user's individual needs and skill level can be provided, improving player satisfaction.

[0006] "User gameplay data" refers to data such as all actions taken by the user in the game, items operated, and stages cleared.

[0007] "Means for collecting" refers to a device or program that has the function of recording and storing users' game play data in real time.

[0008] "Means for analyzing" refers to a device or program for analyzing user behavioral patterns and tendencies based on collected gameplay data and identifying needs and feedback.

[0009] "Generative AI means" refers to a device or program that uses artificial intelligence technology to automatically generate new game elements or content based on the analysis results.

[0010] "Delivery means" refers to a device or program for transmitting and applying newly generated game elements and content to a user's device.

[0011] "Game elements" refers to all content that makes up the game, including level design, characters, items, and story.

[0012] "Ethical and moral checks" refer to processes or devices used to ensure that generated game elements are socially appropriate. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention provides an experiential action RPG in which scenarios and items evolve and change by utilizing user characteristics and feedback, and includes a system in which AI generates and adjusts and creates each element of the game (characters, levels, story) based on the user's behavioral patterns and opinions.

[0035] First, as users play the game, various behavioral patterns, choices, and operations occur. All user behavioral data (e.g., distance traveled, number of battles, number of items used, etc.) is collected in real time. The collected data is recorded in a database.

[0036] The server analyzes the vast amount of collected gameplay data. Big data analysis and machine learning technologies are used to identify user behavior patterns (e.g., play style at a particular level, frequently used items, etc.). At the same time, feedback from users (e.g., "This level is too difficult" or "I like this character design") is also analyzed using natural language processing technology.

[0037] Based on the analysis results, the server utilizes generative AI to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level will be generated with adjusted enemy strength and number. New quests and characters will also be generated based on the user's behavior patterns. These will be characterized by the application of designs and skill sets tailored to the user's preferences.

[0038] The generated game elements are then subjected to an ethical check to ensure that the expressions and content within the game are socially appropriate and do not include racism or excessive violence, providing a safe gaming environment.

[0039] The generated data is then delivered to the user's device, which receives the new game elements and integrates them with the existing game data. New levels and characters are instantly added to the user's game, allowing the user to experience new challenges.

[0040] As users enjoy the updated game, they provide further feedback, which is then collected, analyzed, and used to improve the system, ensuring a continuously optimized gaming experience for each individual user.

[0041] For example, if a user gives feedback that a certain level is too difficult, the server analyzes this data and generates a new version that adjusts the number of enemies and difficulty of the level. This is then distributed to the user's device, and when the user plays again, the server gives feedback that the difficulty level was appropriate. This feedback is collected again as data and used to generate the next game elements.

[0042] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] As users play the game, various behavioral patterns, choices, and operations occur. All user behavior data (e.g., distance traveled, number of battles, number of item usages, etc.) is recorded in real time.

[0046] Step 2:

[0047] The device transmits recorded gameplay data to a database, including the user's actions and choices during gameplay, levels completed, and more.

[0048] Step 3:

[0049] After the user has finished playing, they can enter their impressions and opinions of the game using a feedback form or dialog box. For example, they can provide feedback such as "The level is too difficult" or "I like the new character."

[0050] Step 4:

[0051] The device collects and sends this feedback data to the server, which includes all text data entered by the user.

[0052] Step 5:

[0053] The server stores the collected gameplay data and feedback data and passes it to a data analysis engine.

[0054] Step 6:

[0055] The server uses big data analytics tools and machine learning algorithms to analyze gameplay data and identify patterns of user behavior, such as detecting repeated defeats against a particular enemy.

[0056] Step 7:

[0057] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it performs sentiment analysis on feedback such as "This level is too difficult."

[0058] Step 8:

[0059] The server uses generative AI based on the analysis results to generate new game elements, such as adjusting the difficulty of certain levels or designing new characters and items.

[0060] Step 9:

[0061] The server performs an ethical check on the generated game elements to ensure that the generated content is appropriate, for example, by checking that it does not contain racist or excessive violence.

[0062] Step 10:

[0063] The server packages the content that has passed the ethical check and prepares it for distribution to the user's terminal.

[0064] Step 11:

[0065] The device receives updates from the server and applies new game elements to the existing game data, for example, adding new levels or characters to the game.

[0066] Step 12:

[0067] The user plays the updated game again, ensuring that the new content is functioning correctly and that it is enjoyable.

[0068] Step 13:

[0069] Users again provide feedback on the new game elements and adjusted gameplay, such as "The new level was fun" or "The new weapon was easy to use."

[0070] Step 14:

[0071] The device again collects play data and feedback and sends it to the server, which accumulates data for the next content generation.

[0072] Step 15:

[0073] The server then analyzes and generates the collected data again to provide the user with a more optimized gaming experience. By repeating this cycle, the user is continually provided with a personalized gaming experience.

[0074] Example 1

[0075] 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."

[0076] In conventional action RPGs, it was difficult to provide personalized game elements based on user behavior patterns and feedback, resulting in a generic and fixed game experience. Furthermore, there was a lack of mechanisms to ensure the ethical issues and appropriateness of the content of the generated game elements.

[0077] 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.

[0078] In this invention, the server includes means for collecting user gameplay data, means for analyzing the collected game data to identify user behavior patterns and feedback, generation AI means for generating new game elements based on the analysis results, means for conducting ethical checks on the generated game elements, and means for delivering the generated game elements to user devices and integrating them with existing game data. This makes it possible to provide each user with a personalized game experience while realizing a safe gaming environment with appropriate content and expression.

[0079] "Gameplay data" refers to behavioral information and operation history recorded when a user plays a game.

[0080] "Analysis" refers to the process of analyzing collected data using statistical methods and machine learning techniques to extract meaningful information and patterns.

[0081] "Behavioral patterns" refer to the tendency of a user to repeatedly take actions or make choices within a game.

[0082] "Feedback" refers to the impressions and opinions that users provide regarding their gaming experience.

[0083] "Generative AI means" refers to a function that automatically generates new game elements (levels, characters, quests, items, etc.) using artificial intelligence technology.

[0084] "Ethical check" refers to an evaluation process to ensure that generated game elements are socially appropriate and do not violate specific ethical or moral values.

[0085] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a user uses to play the game.

[0086] "Integration" refers to the process of incorporating new game elements into existing game data.

[0087] "Level design" refers to the structure and arrangement of stages and missions within a game.

[0088] "Character" refers to a character that a user controls or interacts with in a game.

[0089] A "quest" refers to a goal or mission provided to a user, and includes elements that serve as challenges in progressing through the game.

[0090] "Item" refers to an object or tool that can be used by a user in a game to obtain an effect.

[0091] This invention provides an action-packed RPG that individually optimizes the user's gaming experience, and includes a system that generates and adjusts game elements based on user behavior data and feedback. An embodiment of this system will be described in detail below.

[0092] First, when a user plays a game, a variety of behavioral patterns, choices, and operations occur. When a user plays a game using a device such as a smartphone or PC, behavioral data such as distance traveled, number of battles, and number of times an item is used is collected in real time. This data is sent to a server by software installed on the device and recorded in a database.

[0093] The server analyzes the vast amount of collected gameplay data using big data analysis techniques (e.g., Apache Hadoop) and machine learning algorithms (e.g., random forest, deep learning). This analysis identifies user behavior patterns (e.g., play style at a particular level, frequently used items, etc.). At the same time, feedback from users (e.g., "This level is too difficult" or "I like this character design") is also analyzed using natural language processing techniques (e.g., BERT).

[0094] The server then uses a generative AI model (e.g., GPT-4) based on the analysis results to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level with adjusted enemy strength and number may be generated. New quests and characters may also be generated based on the user's behavioral patterns, with designs and skill sets tailored to the user's preferences. An example of a prompt for the generative AI model is, "Generate new game elements (levels, characters, quests) based on the user's behavioral data and feedback. After generation, perform an ethical check and provide appropriate content."

[0095] The generated game elements are then subjected to an ethical check, which examines whether the expressions and content within the game are socially appropriate, and ensures that they do not contain racism or excessive violence. This check is carried out using a dedicated AI model.

[0096] The server delivers the new game elements to the user's device, which then integrates the received data with the existing game data, instantly updating the game with new levels and characters, allowing the user to experience new challenges.

[0097] Furthermore, users who enjoy the updated game will provide further feedback. This feedback will be collected and analyzed again and reflected in the next generation of game elements. This process ensures that each user's gaming experience is continually optimized.

[0098] For example, if a user gives feedback that a certain level is "too difficult," the server analyzes this data and generates a new level with the number and strength of enemies adjusted appropriately. If the user then plays the game and gives feedback that the difficulty level was "just right," this information can be used to adjust the next level.

[0099] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1: Collect user behavior data

[0102] Subject: Terminal

[0103] Specific operation: When a user plays a game, the device collects behavioral data such as distance traveled, number of battles, and number of items used in real time and sends it to the server.

[0104] Input: User's gameplay behavior (movement, combat, item use, etc.)

[0105] Data processing / calculation: Behavioral data is classified into categories and saved with a timestamp.

[0106] Output: Categorized behavioral data (distance traveled, number of battles, number of item usages, etc.)

[0107] Step 2: Analyzing behavioral and feedback data

[0108] Subject: Server

[0109] Specific operation: The server uses software to store the received behavioral data in a database, and analyzes it using big data analysis technology and machine learning models. It also analyzes user feedback using natural language processing technology.

[0110] Input: behavioral data, user feedback

[0111] Data processing / calculation: Behavioral data is statistically analyzed, and feedback is analyzed using natural language processing models to extract behavioral patterns and user intent.

[0112] Output: User behavior patterns and feedback analysis results

[0113] Step 3: Creating new game elements

[0114] Subject: Server

[0115] Specific operation: Based on the analysis results, the server uses the generative AI model to generate new game elements (levels, characters, quests), creates specific prompts for the generative AI model, and inputs them into the model.

[0116] Input: User behavior patterns and feedback analysis results

[0117] Data processing / calculation: Text generation and scenario construction using generative AI models

[0118] Example prompt: "Generate new game elements (levels, characters, quests) based on user behavioral data and feedback. After generation, perform an ethical check and provide appropriate content."

[0119] Output: New game elements (e.g. adjusted levels, stat-revised characters, new quests)

[0120] Step 4: Ethics check of generated game elements

[0121] Subject: Server

[0122] Specific operation: Generated game elements are evaluated using a dedicated AI model to check whether they are ethically appropriate.

[0123] Input: Generated game elements

[0124] Data processing / computation: Evaluation and filtering based on social appropriateness criteria

[0125] Output: Game elements that pass the ethical check

[0126] Step 5: Delivering and integrating the generated game elements

[0127] Subject: Server and Terminal

[0128] Specific operation: The server delivers the checked game elements to the user's terminal, and the terminal integrates them into the existing game data.

[0129] Input: Game elements that pass the ethical check

[0130] Data processing / calculation: Sending new data to the terminal and integrating it with existing data

[0131] Output: Game data with integrated game elements

[0132] Step 6: Play new game features and gather feedback

[0133] Subject: User and Device

[0134] Specific operation: The user plays new game elements, and the device again collects the user's play and feedback.

[0135] Input: User play, user feedback

[0136] Data processing / computation: collection and classification of new behavioral data and feedback

[0137] Output: Recollected behavioral data and feedback

[0138] These are the specific processing steps of this system. At each step, we also show what data processing and calculations are performed on the input data and what output is obtained. This makes it possible to provide users with a consistently optimized gaming experience.

[0139] (Application example 1)

[0140] 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."

[0141] In conventional virtual store experiences, users are provided with uniform content and product suggestions, making it difficult to meet individual user needs. This leads to problems such as reduced user satisfaction and reduced purchasing motivation. Furthermore, if product suggestions are inconsistent or do not match the user's interests, the user experience may be negatively impacted.

[0142] 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.

[0143] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data to identify user behavior patterns and feedback, generation AI means for generating new experience elements based on the analysis results, means for delivering the generated experience elements to the user's terminal, and means for displaying the generated experience elements on the terminal display, thereby enabling personalized product suggestions, interactive features, and promotions to be provided based on the behavioral characteristics and preferences of each individual user.

[0144] "User activity data" refers to data such as behavioral history, operation records, and feedback generated when a user uses the system.

[0145] A "behavioral pattern" refers to characteristics and tendencies identified by analyzing a user's series of actions, choices, operation methods, etc.

[0146] "Generative AI methods" refers to artificial intelligence technologies used to automatically generate new experience elements and content based on user behavior patterns and feedback.

[0147] "Experience elements" is a general term for new content, functions, interfaces, product proposals, etc. provided to users.

[0148] "Means for displaying on a terminal display" refers to the techniques and means for displaying the generated experience elements on the user's visual interface.

[0149] "Product suggestions" refers to a feature that recommends appropriate products and services based on a user's preferences and behavioral patterns.

[0150] "Interactive features" refers to functions and content that allow two-way communication between the user and the system.

[0151] "Promotion" refers to measures including advertising activities, campaigns, special offers, etc. aimed at promoting product sales.

[0152] "Ethics check measures" are measures that have the function of checking whether the experience elements and content generated are socially and culturally appropriate, and ensuring that inappropriate content is not included.

[0153] This invention is a system that provides a personalized virtual store experience using smart glasses. The system collects and analyzes user activity data to identify behavioral patterns and feedback, and generates new experience elements that are displayed on the user's smart glasses.

[0154] First, user activity data is collected. Specifically, the user's purchase history, browsing history, etc. are stored in a database. This data includes the user's actions and operations when visiting a virtual store.

[0155] Next, the server analyzes the user's behavioral patterns and feedback using big data analysis and machine learning technologies. For example, if a user frequently browses products in a specific category, the server profiles the user's purchasing tendencies. Based on the analysis results, the generative AI means generates new experience elements.

[0156] As a generative AI method, for example, we use GPT-3, a generative AI model. This AI generates new product suggestions using the following prompt sentence as input:

[0157] Generate product recommendations based on a user's profile:

[0158] Past purchase history: [Running shoes, fitness tracker, sports drink]

[0159] Browsing history: [New running shoes, yoga mats, training wear]

[0160] The generated experience elements are delivered by the server to the user's smart glasses, whose display visually displays the generated product suggestions, interactive features, and promotions.

[0161] For example, when a user wears smart glasses and accesses a virtual store, suggestions for new running shoes and promotions for fitness-related products are displayed based on the user's past behavioral data, allowing the user to intuitively receive product suggestions that match their preferences.

[0162] Additionally, the generated experience elements undergo an ethical check to ensure that the generated content is socially appropriate and does not contain excessive promotional or inappropriate content. Specifically, the AI ​​evaluates the content based on a checklist and makes corrections if there are any issues.

[0163] This system makes it possible to provide a personalized virtual store experience tailored to the needs of each user, thereby improving user satisfaction and increasing purchasing motivation.

[0164] The hardware used includes smart glasses and servers, and the software used includes Scikit-learn (for data analysis) and GPT-3 (a generative AI model).

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] A user visits a virtual store and puts on the smart glasses.

[0168] Input: User identification, smart glasses activation

[0169] Output: Activated smart glasses interface

[0170] Specific operation: A user puts on the smart glasses and launches the virtual store application, which causes the smart glasses to obtain the user's identity and begin the launch process.

[0171] Step 2:

[0172] The server collects activity data based on the user's identification information.

[0173] Input: User identity

[0174] Output: User purchase history, browsing history

[0175] Specific operation: The server accesses the database and obtains activity data such as the user's past purchase history and browsing history, thereby collecting the user's behavioral history.

[0176] Step 3:

[0177] The server analyzes the collected activity data to identify user behavior patterns and feedback.

[0178] Input: User purchase history, browsing history

[0179] Output: Identified behavioral patterns, feedback

[0180] How it works: The server uses analytical tools such as Scikit-learn to perform clustering analysis of user behavior patterns, and also analyzes feedback data using natural language processing techniques to identify user preferences and complaints.

[0181] Step 4:

[0182] The server uses a generative AI model to generate new experience elements based on the analysis results.

[0183] Input: Identified behavioral patterns, feedback

[0184] Output: New experience elements (product suggestions, promotions, etc.)

[0185] How it works: The server uses a generative AI model (e.g., GPT-3) to create prompts based on the user's behavioral patterns and feedback, and then inputs these into the AI ​​model to generate new experience elements.

[0186] Step 5:

[0187] The server performs an ethical check on the generated experience elements.

[0188] Input: New experience element

[0189] Output: Checked experience elements

[0190] What it does: The server evaluates the generated experience elements against an ethical checklist and corrects any inappropriate content, resulting in socially appropriate content.

[0191] Step 6:

[0192] The server delivers the checked experience elements to the user's smart glasses.

[0193] Input: Checked experience elements

[0194] Output: Delivered experience elements

[0195] Specific operation: The server sends the checked experience elements to the user's smart glasses, which then reflects the new experience elements on the user's device in real time.

[0196] Step 7:

[0197] Users experience new experiential elements through the smart glasses display.

[0198] Input: Delivered experience element

[0199] Output: User experience, feedback

[0200] Specific actions: The user browses the product suggestions and promotions displayed through the smart glasses, enjoys shopping and interactive features, and provides feedback again, which is collected as data for the next cycle.

[0201] 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.

[0202] This invention provides an experiential action RPG in which scenarios and items evolve and change by utilizing the user's characteristics and feedback. In addition to a system in which AI generates and adjusts and creates each element of the game (characters, levels, story) based on the user's behavioral patterns and opinions, by combining it with an emotion engine, it provides a personalized gaming experience that also takes into account the user's emotional reactions.

[0203] First, as a user plays a game, various behavioral patterns, choices, and operations occur. All user behavioral data (e.g., distance traveled, number of battles, number of times an item is used, etc.) is collected in real time. The device sends the recorded gameplay data to the server. This data includes the user's actions and choices during play, the levels cleared, etc.

[0204] In addition, after a user finishes playing, their impressions and opinions are collected using feedback forms and dialogues. For example, there is a mechanism for obtaining feedback from users, such as "The level is too difficult" or "I like the new character." The device collects this feedback data and sends it to the server.

[0205] The server accumulates the collected gameplay data and feedback data and passes it to a data analysis engine. The server uses big data analysis tools and machine learning algorithms to analyze the gameplay data and identify user behavior patterns. For example, it detects whether a player has been defeated by a particular enemy multiple times or frequently uses a particular item.

[0206] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it can analyze the sentiment of feedback such as "This level is too difficult."

[0207] Furthermore, the emotion engine analyzes the user's emotional reactions. The emotion engine uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice. For example, if a user furrows their brow while playing a game, it is interpreted as meaning that they are feeling irritated or in a difficult situation. Similarly, if the user's voice is high-pitched, it is interpreted as meaning that they are feeling elated or excited.

[0208] Based on the analysis results, the server utilizes generative AI to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level will be generated with adjusted enemy strength and numbers. New quests and characters will also be generated based on the user's behavioral patterns and emotional reactions. These will be characterized by designs and skill sets tailored to the user's preferences.

[0209] The generated game elements are then subjected to an ethical check to ensure that the expressions and content within the game are socially appropriate and do not include racism or excessive violence, providing a safe gaming environment.

[0210] The generated data is then delivered to the user's device, which receives the new game elements and integrates them with the existing game data. New levels and characters are instantly added to the user's game, allowing the user to experience new challenges.

[0211] As users enjoy the updated game, they provide further feedback, which is then collected, analyzed, and used to improve the system, ensuring a continuously optimized gaming experience for each individual user.

[0212] For example, if a user gives feedback that a certain level is too difficult, or if the emotion engine detects frustration from the user's facial expression, the server analyzes this data and generates a new version of the level with adjusted enemy numbers and difficulty. This is then distributed to the user's device, and when the user plays again, the server gives feedback that the difficulty level was appropriate. This feedback and emotion data is then collected again and used to generate the next game elements.

[0213] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0214] The processing flow will be explained below.

[0215] Step 1:

[0216] The user plays the game. During the game, the user performs various actions (movement, attack, use of items, etc.).

[0217] Step 2:

[0218] The device records the user's behavioral data (distance traveled, number of battles, type and frequency of items used, etc.) in real time.

[0219] Step 3:

[0220] The device transmits recorded gameplay data to the server, including the user's actions and choices during gameplay, levels completed, and so on.

[0221] Step 4:

[0222] After playing, users can use a feedback form or dialog box to enter their impressions and opinions of the game. For example, they can enter specific impressions such as "The level is too difficult" or "I like the new character."

[0223] Step 5:

[0224] The device collects and sends this feedback data, including all text data entered by the user, to the server.

[0225] Step 6:

[0226] The server stores the collected gameplay data and feedback data and passes it to a data analysis engine.

[0227] Step 7:

[0228] The server uses big data analytics tools and machine learning algorithms to analyze gameplay data and identify patterns of user behavior, such as detecting repeated defeats against a particular enemy.

[0229] Step 8:

[0230] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it can analyze the sentiment of feedback such as "This level is too difficult."

[0231] Step 9:

[0232] The server uses an emotion engine to analyze the user's emotional response. The emotion engine uses the device's camera and microphone to determine the user's emotion (e.g., joy, anger, surprise, etc.) using facial recognition technology and voice analysis technology.

[0233] Step 10:

[0234] The server utilizes generative AI to generate new game elements based on the results of big data analysis and emotion engine analysis, such as adjusting the difficulty of certain levels or designing new characters and items.

[0235] Step 11:

[0236] The server will then perform an ethical check on the generated game elements to ensure that the generated content is socially appropriate, including checking for racism and excessive violence.

[0237] Step 12:

[0238] The server packages the content that has passed the ethical check and prepares it for distribution to the user's terminal.

[0239] Step 13:

[0240] The device receives updates from the server and applies new game elements to the existing game data, for example, adding new levels or characters to the game.

[0241] Step 14:

[0242] The user plays the updated game again, ensuring that the new content is functioning correctly and that it is enjoyable.

[0243] Step 15:

[0244] Users again provide feedback on the new game elements and adjusted gameplay, such as "The new level was fun" or "The new weapon was easy to use."

[0245] Step 16:

[0246] The terminal again collects play data, feedback, and emotional responses from the emotion engine, and transmits them to the server.

[0247] Step 17:

[0248] The server then analyzes and generates the collected data again to provide the user with a more optimized gaming experience. By repeating this cycle, the user is continually provided with a personalized gaming experience.

[0249] Example 2

[0250] 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."

[0251] In conventional action RPGs, it has been difficult to fully reflect user behavioral patterns and feedback to personalize the gaming experience. Furthermore, game elements are often not updated or adjusted appropriately, resulting in reduced user satisfaction. The present invention aims to solve these problems and provide a more personalized gaming experience by utilizing user behavioral data and emotional responses.

[0252] 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.

[0253] In this invention, the server includes means for collecting user gameplay data, means for analyzing the collected game data to identify user behavioral patterns and feedback, generation AI means for generating new game elements based on the analysis results, emotion analysis means for analyzing user emotional responses, and means for delivering the generated game elements to the user's device. This makes it possible to continuously and appropriately update game elements based on the user's behavioral data and emotional responses, thereby providing a personalized game experience.

[0254] "User" refers to a person who uses the system to play a game.

[0255] "Game play data" refers to various behavior records and operation histories generated when a user plays a game.

[0256] "Analysis tool" refers to a method or device for analyzing collected data to identify useful information or patterns.

[0257] "Behavioral patterns" refer to the tendencies and characteristics of a series of actions that a user takes in a game.

[0258] "Feedback" refers to opinions and impressions provided by users regarding a system or game.

[0259] "Generative AI means" refers to means of automatically generating new game elements using artificial intelligence technology.

[0260] "Emotion analysis means" refers to a method or device for analyzing a user's emotional response.

[0261] "Game elements" refers to all components that affect the user's gaming experience, such as level design, characters, items, and quests that exist within the game.

[0262] "Distribution means" refers to a method or device for transmitting generated game elements to a user's terminal.

[0263] "Ethics check" refers to the process of reviewing the social appropriateness of generated game elements.

[0264] "Terminal" refers to the computing device that a user uses to play a game.

[0265] This invention is a system that provides an experiential action RPG in which scenarios and items evolve and change by utilizing user characteristics and feedback. This allows for a gaming experience that is optimized for each individual user. This invention is primarily comprised of three parties: a server, a terminal, and a user.

[0266] Hardware and software used

[0267] Implementation of the present invention includes the following hardware and software:

[0268] Device: The device on which a user plays a game (e.g., PC, smartphone, game console, etc.).

[0269] Server: A central control unit for collecting, analyzing, generating, and distributing data.

[0270] Data analysis engines: Big data analysis tools (e.g., Apache Hadoop) and machine learning algorithms (e.g., TensorFlow)

[0271] Natural language processing technology: Google Cloud Natural Language API

[0272] Sentiment analysis engine: Facial recognition technology (e.g., Microsoft Azure Face API) and voice analysis technology (e.g., IBM Watson Speech to Text)

[0273] Generation AI: OpenAI GPT-3

[0274] Specific explanation of the system

[0275] 1. User Gameplay:

[0276] Users use their devices to play games, controlling characters to fight enemies, use items, and clear levels, which generates various behavioral data in real time, such as distance traveled and number of battles.

[0277] 2. Game Data Collection and Transmission:

[0278] The device collects user behavior data in real time, including distance traveled, number of battles, number of items used, and levels cleared. The device then transmits the collected data to the server in real time.

[0279] 3. Gathering Feedback:

[0280] After the user finishes the game, the device displays a feedback form or dialog to collect the user's thoughts and opinions. For example, the device asks the user to provide specific feedback such as "The level is too difficult" or "I like the new character." The device then sends this feedback data to the server.

[0281] 4. Data collection and analysis:

[0282] The server stores the collected gameplay data and feedback data. Big data analysis tools and machine learning algorithms are used to analyze the data and identify user behavior patterns and feedback. For example, patterns such as "a user being defeated by a specific enemy multiple times" or "a user frequently using a specific item" are detected.

[0283] 5. Natural Language Processing of Feedback:

[0284] The server uses natural language processing technology to analyze the feedback data and extract emotions and specific opinions. For example, it analyzes feedback such as "This level is too difficult" to understand the user's opinion.

[0285] 6. Emotion analysis:

[0286] The server uses an emotion analysis engine to analyze the user's emotional response. It uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice. For example, a furrowed brow indicates irritation, while a high-pitched voice indicates elation or excitement.

[0287] 7. Creating new game elements:

[0288] Based on the analysis results, the server uses a generative AI model to automatically generate new game elements. For example, if a user repeatedly fails a particular level, it will generate a new version of that level with adjusted enemy count and difficulty. It will also generate new quests and characters based on the user's preferences.

[0289] Examples of prompts:

[0290] "Users are repeatedly failing a particular level. Please generate a new version of this level with a slightly reduced number and difficulty of enemies. Also, please take into account user feedback."

[0291] 8. Ethics Check:

[0292] Generated game elements are checked to determine their ethical and moral standards, and to ensure they do not contain excessive violence or racist content.

[0293] 9. New game features released:

[0294] The server distributes the generated game elements to the user's terminal, which receives the new game elements and integrates them into the existing game data.

[0295] 10. Collect ongoing feedback:

[0296] The user plays the updated game and again provides feedback, which the device sends to the server and is again used in the analysis and generation process.

[0297] This process allows us to provide each user with a consistently personalized gaming experience.

[0298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0299] Step 1:

[0300] The user plays the game on the device.

[0301] Input: User actions (movement, combat, item use, level completion, etc.)

[0302] Specific actions: The user controls the character and performs various actions in the game, such as fighting enemies or using items. This generates behavioral data such as distance traveled and number of battles.

[0303] Output: Gameplay data (distance traveled, number of battles, number of items used, etc.)

[0304] Step 2:

[0305] The device collects gameplay data and transmits it to the server.

[0306] Input: Gameplay data (distance traveled, number of battles, number of items used, etc.)

[0307] Specific operation: The device records user behavior data in real time and transmits it to a server via the Internet.

[0308] Output: Gameplay data sent to the server

[0309] Step 3:

[0310] The user provides feedback at the device.

[0311] Input: Input into feedback forms and dialogues (level difficulty, thoughts on new characters, etc.)

[0312] Specific operation: After playing, the user enters their opinion in the displayed feedback form or dialog. For example, they provide comments such as "The level is too difficult" or "I like the new character."

[0313] Output: Feedback data

[0314] Step 4:

[0315] The terminal transmits the feedback data to the server.

[0316] Input: Feedback data (level difficulty, thoughts on new characters, etc.)

[0317] Specific operation: The terminal collects feedback data entered by the user and transmits it to a server via the Internet.

[0318] Output: Feedback data sent to the server

[0319] Step 5:

[0320] The server stores and analyzes gameplay data and feedback data.

[0321] Input: Gameplay and feedback data sent to the server

[0322] How it works: The server analyzes the data using big data analysis tools (e.g., Apache Hadoop) and machine learning algorithms (e.g., TensorFlow) to identify user behavior patterns and feedback. For example, it detects patterns such as "being defeated by a specific enemy multiple times" or "frequently using a specific item."

[0323] Output: Analysis results (identification of user behavior patterns and feedback)

[0324] Step 6:

[0325] The server analyzes the feedback data using natural language processing techniques.

[0326] Input: Feedback data (level difficulty, thoughts on new characters, etc.)

[0327] Specific operation: The server analyzes the feedback data using natural language processing technology (e.g., Google Cloud Natural Language API) to extract the user's opinions and wishes. For example, it analyzes feedback such as "This level is too difficult."

[0328] Output: Analyzed feedback data (extraction of user sentiment and opinions)

[0329] Step 7:

[0330] The server uses an emotion analysis engine to analyze the user's emotional response.

[0331] Input: User's facial recognition data and voice data

[0332] Specific operation: The server uses facial recognition technology (e.g., Microsoft Azure Face API) and voice analysis technology (e.g., IBM Watson Speech to Text) to analyze the user's facial expressions and tone of voice to determine their emotions. For example, a furrowed brow indicates irritation, and a higher-pitched voice indicates excitement.

[0333] Output: Sentiment analysis results (user's feelings such as irritation or excitement)

[0334] Step 8:

[0335] The server generates new game elements using generative AI models.

[0336] Input: behavioral pattern analysis results, emotion analysis results, feedback analysis results

[0337] How it works: The server uses generative AI (e.g., OpenAI GPT-3) to generate new game elements based on the analysis results. For example, if a user repeatedly fails a certain level, it generates a new level with adjusted enemy numbers and difficulty.

[0338] Output: New game elements (adjusted levels, new characters, etc.)

[0339] Examples of prompts:

[0340] "Users are repeatedly failing a particular level. Please generate a new version of this level with a slightly reduced number and difficulty of enemies. Also, please take into account user feedback."

[0341] Step 9:

[0342] The server performs a sanity check on the generated game elements.

[0343] Input: Generated game elements (adjusted levels, new characters, etc.)

[0344] Specific actions: The server checks whether the generated game elements are socially appropriate and reviews them to ensure they do not contain excessive violence or racist elements.

[0345] Output: Game elements that have passed ethical review

[0346] Step 10:

[0347] The server delivers new game elements to the user's device.

[0348] Input: New game elements that have passed ethical review

[0349] Specific operation: The server distributes new game elements to the user's device via the Internet.

[0350] Output: New game elements delivered to the user's device

[0351] Step 11:

[0352] The device integrates the new game elements into the existing game data.

[0353] Input: New game elements (adjusted levels, new characters, etc.)

[0354] Specific operation: The device will integrate new game elements into the existing game data and immediately reflect them in the game.

[0355] Output: Updated game data

[0356] Step 12:

[0357] The user plays the updated game and again provides feedback.

[0358] Input: Updated game data

[0359] Specific actions: The user plays the game with the new game elements and provides feedback again.

[0360] Output: New feedback data

[0361] Through this series of processing steps, a personalized gaming experience is provided to the user.

[0362] (Application example 2)

[0363] 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."

[0364] This invention improves the user's gaming experience and uses emotion analysis to provide a personalized experience based on the user's emotions and preferences during gameplay and shopping. Existing systems make changes and suggestions based solely on user behavioral data and feedback, which means they cannot adequately reflect the user's emotions and real-time reactions. This makes it difficult to recommend products and game elements that are appropriate for the user, and it is therefore difficult to provide consistent satisfaction.

[0365] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user game play data, means for analyzing the collected game data to identify the user's behavioral patterns and feedback, generation AI means for generating new game elements based on the analysis results, means for delivering the generated game elements to the user's terminal, emotion analysis means for analyzing the user's facial expressions and voice to identify emotions, and means for recommending products based on the emotion analysis results. This makes it possible to recommend new personalized game elements and products that reflect the user's behavioral data, feedback, and real-time emotions.

[0366] "Means for collecting user gameplay data" refers to a mechanism for recording and collecting behavioral data, choices, operations, etc. generated when a user actually plays a game.

[0367] "Means for analyzing collected game data to identify user behavioral patterns and feedback" refers to a mechanism for analyzing collected game play data to identify user behavioral trends and the content of the feedback provided.

[0368] "Generative AI means for generating new game elements" refers to artificial intelligence technology for automatically generating new game elements (level designs, characters, items, etc.) that adapt to users based on the analysis results.

[0369] "Means for delivering generated game elements to the user's device" refers to a mechanism for transmitting and delivering new game elements created by the generating AI to the device used by the user.

[0370] "Emotion analysis means for identifying emotions by analyzing a user's facial expressions and voice" refers to technology for analyzing a user's facial expressions and voice data to identify their emotions. This technology uses facial recognition and voice analysis technology.

[0371] "Means for recommending products based on the results of sentiment analysis" is a mechanism for selecting and recommending products and services suitable for users based on the results of sentiment analysis.

[0372] The system of the present invention includes a mechanism for collecting user gameplay data and generating and recommending new game elements and products based on the analysis results. Specific embodiments of this system are described below.

[0373] First, when a user plays a game, the user's behavioral data (distance traveled, number of battles, number of items used, etc.) as well as the choices and operations made during gameplay are collected. This data is sent in real time from the device to the server. The hardware used at this stage is the device held by the user (smart glasses or smartphone), and the software used is a client program for data collection.

[0374] The server analyzes the collected gameplay data to identify user behavior patterns. Big data analysis tools and machine learning algorithms are used for the analysis. Specific software used includes Python analysis libraries (e.g., Pandas, Scikit-learn) and natural language processing tools (e.g., NLTK, spaCy).

[0375] Furthermore, the server analyzes the user's feedback data (thoughts and opinions provided in feedback forms and dialogues) using natural language processing technology. Again, the natural language processing tool mentioned above is used to extract the user's opinions and wishes. This allows for specific feedback such as "The level is too difficult" or "I like the new character."

[0376] Emotion analysis is performed using technology that analyzes the user's facial expressions and voice. Using facial recognition and voice analysis technologies (e.g., OpenCV and Keras), emotions are determined from the user's facial expressions and tone of voice. For example, furrowing the brow while playing a game can be interpreted as irritation, and a high-pitched voice as excitement.

[0377] Based on the results of the analysis, the server automatically generates new game elements and products using a generative AI. A generative model endpoint (e.g., TensorFlow, PyTorch) is used for generation. Specifically, if a user repeatedly fails a particular level, the generative AI generates a new level with adjusted enemy strength and number.

[0378] New game elements and generated product recommendations are delivered in real time from the server to the user's device using communication software (e.g., WebSocket, REST API). The device that receives the new information integrates it with the existing game data, so that the new elements are immediately reflected when the user plays again.

[0379] Finally, user feedback and emotional data are collected again and reflected in the next game element generation and product recommendations, thereby continuously providing an optimized experience for each individual user.

[0380] For example, if a user visits a virtual shopping mall, frequently browses products from a particular brand, and provides positive feedback, the generative AI will prioritize displaying new products from that brand.

[0381] Example prompt sentence:

[0382] User behavior data: browsing time, purchase history, feedback data

[0383] User emotion data: facial expressions, tone of voice

[0384] New product suggestions tailored to the user: prioritize displaying products from a specific brand

[0385] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0386] Step 1:

[0387] The device collects the user's gameplay data (e.g., distance traveled, number of battles, number of items used) in real time. It uses a data collection tool to collect user behavior data and sends that data to the server. The input is gameplay data, and the output is collected data.

[0388] Step 2:

[0389] The server analyzes the collected gameplay data. This analysis uses big data analysis tools and machine learning algorithms to identify user behavior patterns (e.g., being defeated by a specific enemy multiple times, frequently using a specific item). The input is the collected gameplay data, and the output is user behavior pattern data.

[0390] Step 3:

[0391] The server collects user feedback data and analyzes it using natural language processing technology. User feedback (e.g., "The level is too difficult" or "I like the new character") is collected as text and sentiment analysis is performed. The input is the feedback data, and the output is extracted opinions and wishes.

[0392] Step 4:

[0393] The server analyzes the user's facial expressions and voice to identify their emotions. Using facial recognition and voice analysis technology, it determines emotions (e.g., irritation, excitement) from the user's facial expressions and tone of voice. The input is the user's video and voice data, and the output is emotional data.

[0394] Step 5:

[0395] The server generates new game elements and products based on the analysis results. Using a generative AI model, it generates new game elements and products that adapt to the user (e.g., new levels with adjusted enemy strength and number). The input is the user's behavioral patterns, feedback data, and emotional data, and the output is the generated game elements and products.

[0396] Step 6:

[0397] The server distributes the generated game elements and products to the user's device. Using communication software, the generated new game elements and products are sent to the user's device in real time. The input is the generated game elements and products, and the output is the data distributed to the device.

[0398] Step 7:

[0399] The data received by the device is integrated with existing game data. New game elements and products are integrated with existing data so that they are immediately reflected in the user's game. The input is the distributed data, and the output is the updated game data.

[0400] Step 8:

[0401] Users use the updated games and products offered and provide feedback again, which allows the system to be continuously optimized. The input is feedback after use, and the output is new data for the next analysis.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] [Second embodiment]

[0406] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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."

[0418] This invention provides an experiential action RPG in which scenarios and items evolve and change by utilizing user characteristics and feedback, and includes a system in which AI generates and adjusts and creates each element of the game (characters, levels, story) based on the user's behavioral patterns and opinions.

[0419] First, as users play the game, various behavioral patterns, choices, and operations occur. All user behavioral data (e.g., distance traveled, number of battles, number of items used, etc.) is collected in real time. The collected data is recorded in a database.

[0420] The server analyzes the vast amount of collected gameplay data. Big data analysis and machine learning technologies are used to identify user behavior patterns (e.g., play style at a particular level, frequently used items, etc.). At the same time, feedback from users (e.g., "This level is too difficult" or "I like this character design") is also analyzed using natural language processing technology.

[0421] Based on the analysis results, the server utilizes generative AI to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level will be generated with adjusted enemy strength and number. New quests and characters will also be generated based on the user's behavior patterns. These will be characterized by the application of designs and skill sets tailored to the user's preferences.

[0422] The generated game elements are then subjected to an ethical check to ensure that the expressions and content within the game are socially appropriate and do not include racism or excessive violence, providing a safe gaming environment.

[0423] The generated data is then delivered to the user's device, which receives the new game elements and integrates them with the existing game data. New levels and characters are instantly added to the user's game, allowing the user to experience new challenges.

[0424] As users enjoy the updated game, they provide further feedback, which is then collected, analyzed, and used to improve the system, ensuring a continuously optimized gaming experience for each individual user.

[0425] For example, if a user gives feedback that a certain level is too difficult, the server analyzes this data and generates a new version that adjusts the number of enemies and difficulty of the level. This is then distributed to the user's device, and when the user plays again, the server gives feedback that the difficulty level was appropriate. This feedback is collected again as data and used to generate the next game elements.

[0426] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0427] The processing flow will be explained below.

[0428] Step 1:

[0429] As users play the game, various behavioral patterns, choices, and operations occur. All user behavior data (e.g., distance traveled, number of battles, number of item usages, etc.) is recorded in real time.

[0430] Step 2:

[0431] The device transmits recorded gameplay data to a database, including the user's actions and choices during gameplay, levels completed, and more.

[0432] Step 3:

[0433] After the user has finished playing, they can enter their impressions and opinions of the game using a feedback form or dialog box. For example, they can provide feedback such as "The level is too difficult" or "I like the new character."

[0434] Step 4:

[0435] The device collects and sends this feedback data to the server, which includes all text data entered by the user.

[0436] Step 5:

[0437] The server stores the collected gameplay data and feedback data and passes it to a data analysis engine.

[0438] Step 6:

[0439] The server uses big data analytics tools and machine learning algorithms to analyze gameplay data and identify patterns of user behavior, such as detecting repeated defeats against a particular enemy.

[0440] Step 7:

[0441] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it performs sentiment analysis on feedback such as "This level is too difficult."

[0442] Step 8:

[0443] The server uses generative AI based on the analysis results to generate new game elements, such as adjusting the difficulty of certain levels or designing new characters and items.

[0444] Step 9:

[0445] The server performs an ethical check on the generated game elements to ensure that the generated content is appropriate, for example, by checking that it does not contain racist or excessive violence.

[0446] Step 10:

[0447] The server packages the content that has passed the ethical check and prepares it for distribution to the user's terminal.

[0448] Step 11:

[0449] The device receives updates from the server and applies new game elements to the existing game data, for example, adding new levels or characters to the game.

[0450] Step 12:

[0451] The user plays the updated game again, ensuring that the new content is functioning correctly and that it is enjoyable.

[0452] Step 13:

[0453] Users again provide feedback on the new game elements and adjusted gameplay, such as "The new level was fun" or "The new weapon was easy to use."

[0454] Step 14:

[0455] The device again collects play data and feedback and sends it to the server, which accumulates data for the next content generation.

[0456] Step 15:

[0457] The server then analyzes and generates the collected data again to provide the user with a more optimized gaming experience. By repeating this cycle, the user is continually provided with a personalized gaming experience.

[0458] Example 1

[0459] 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."

[0460] In conventional action RPGs, it was difficult to provide personalized game elements based on user behavior patterns and feedback, resulting in a generic and fixed game experience. Furthermore, there was a lack of mechanisms to ensure the ethical issues and appropriateness of the content of the generated game elements.

[0461] 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.

[0462] In this invention, the server includes means for collecting user gameplay data, means for analyzing the collected game data to identify user behavior patterns and feedback, generation AI means for generating new game elements based on the analysis results, means for conducting ethical checks on the generated game elements, and means for delivering the generated game elements to user devices and integrating them with existing game data. This makes it possible to provide each user with a personalized game experience while realizing a safe gaming environment with appropriate content and expression.

[0463] "Gameplay data" refers to behavioral information and operation history recorded when a user plays a game.

[0464] "Analysis" refers to the process of analyzing collected data using statistical methods and machine learning techniques to extract meaningful information and patterns.

[0465] "Behavioral patterns" refer to the tendency of a user to repeatedly take actions or make choices within a game.

[0466] "Feedback" refers to the impressions and opinions that users provide regarding their gaming experience.

[0467] "Generative AI means" refers to a function that automatically generates new game elements (levels, characters, quests, items, etc.) using artificial intelligence technology.

[0468] "Ethical check" refers to an evaluation process to ensure that generated game elements are socially appropriate and do not violate specific ethical or moral values.

[0469] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a user uses to play the game.

[0470] "Integration" refers to the process of incorporating new game elements into existing game data.

[0471] "Level design" refers to the structure and arrangement of stages and missions within a game.

[0472] "Character" refers to a character that a user controls or interacts with in a game.

[0473] A "quest" refers to a goal or mission provided to a user, and includes elements that serve as challenges in progressing through the game.

[0474] "Item" refers to an object or tool that can be used by a user in a game to obtain an effect.

[0475] This invention provides an action-packed RPG that individually optimizes the user's gaming experience, and includes a system that generates and adjusts game elements based on user behavior data and feedback. An embodiment of this system will be described in detail below.

[0476] First, when a user plays a game, a variety of behavioral patterns, choices, and operations occur. When a user plays a game using a device such as a smartphone or PC, behavioral data such as distance traveled, number of battles, and number of times an item is used is collected in real time. This data is sent to a server by software installed on the device and recorded in a database.

[0477] The server analyzes the vast amount of collected gameplay data using big data analysis techniques (e.g., Apache Hadoop) and machine learning algorithms (e.g., random forest, deep learning). This analysis identifies user behavior patterns (e.g., play style at a particular level, frequently used items, etc.). At the same time, feedback from users (e.g., "This level is too difficult" or "I like this character design") is also analyzed using natural language processing techniques (e.g., BERT).

[0478] The server then uses a generative AI model (e.g., GPT-4) based on the analysis results to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level with adjusted enemy strength and number may be generated. New quests and characters may also be generated based on the user's behavioral patterns, with designs and skill sets tailored to the user's preferences. An example of a prompt for the generative AI model is, "Generate new game elements (levels, characters, quests) based on the user's behavioral data and feedback. After generation, perform an ethical check and provide appropriate content."

[0479] The generated game elements are then subjected to an ethical check, which examines whether the expressions and content within the game are socially appropriate, and ensures that they do not contain racism or excessive violence. This check is carried out using a dedicated AI model.

[0480] The server delivers the new game elements to the user's device, which then integrates the received data with the existing game data, instantly updating the game with new levels and characters, allowing the user to experience new challenges.

[0481] Furthermore, users who enjoy the updated game will provide further feedback. This feedback will be collected and analyzed again and reflected in the next generation of game elements. This process ensures that each user's gaming experience is continually optimized.

[0482] For example, if a user gives feedback that a certain level is "too difficult," the server analyzes this data and generates a new level with the number and strength of enemies adjusted appropriately. If the user then plays the game and gives feedback that the difficulty level was "just right," this information can be used to adjust the next level.

[0483] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0484] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0485] Step 1: Collect user behavior data

[0486] Subject: Terminal

[0487] Specific operation: When a user plays a game, the device collects behavioral data such as distance traveled, number of battles, and number of items used in real time and sends it to the server.

[0488] Input: User's gameplay behavior (movement, combat, item use, etc.)

[0489] Data processing / calculation: Behavioral data is classified into categories and saved with a timestamp.

[0490] Output: Categorized behavioral data (distance traveled, number of battles, number of item usages, etc.)

[0491] Step 2: Analyzing behavioral and feedback data

[0492] Subject: Server

[0493] Specific operation: The server uses software to store the received behavioral data in a database, and analyzes it using big data analysis technology and machine learning models. It also analyzes user feedback using natural language processing technology.

[0494] Input: behavioral data, user feedback

[0495] Data processing / calculation: Behavioral data is statistically analyzed, and feedback is analyzed using natural language processing models to extract behavioral patterns and user intent.

[0496] Output: User behavior patterns and feedback analysis results

[0497] Step 3: Creating new game elements

[0498] Subject: Server

[0499] Specific operation: Based on the analysis results, the server uses the generative AI model to generate new game elements (levels, characters, quests), creates specific prompts for the generative AI model, and inputs them into the model.

[0500] Input: User behavior patterns and feedback analysis results

[0501] Data processing / calculation: Text generation and scenario construction using generative AI models

[0502] Example prompt: "Generate new game elements (levels, characters, quests) based on user behavioral data and feedback. After generation, perform an ethical check and provide appropriate content."

[0503] Output: New game elements (e.g. adjusted levels, stat-revised characters, new quests)

[0504] Step 4: Ethics check of generated game elements

[0505] Subject: Server

[0506] Specific operation: Generated game elements are evaluated using a dedicated AI model to check whether they are ethically appropriate.

[0507] Input: Generated game elements

[0508] Data processing / computation: Evaluation and filtering based on social appropriateness criteria

[0509] Output: Game elements that pass the ethical check

[0510] Step 5: Delivering and integrating the generated game elements

[0511] Subject: Server and Terminal

[0512] Specific operation: The server delivers the checked game elements to the user's terminal, and the terminal integrates them into the existing game data.

[0513] Input: Game elements that pass the ethical check

[0514] Data processing / calculation: Sending new data to the terminal and integrating it with existing data

[0515] Output: Game data with integrated game elements

[0516] Step 6: Play new game features and gather feedback

[0517] Subject: User and Device

[0518] Specific operation: The user plays new game elements, and the device again collects the user's play and feedback.

[0519] Input: User play, user feedback

[0520] Data processing / computation: collection and classification of new behavioral data and feedback

[0521] Output: Recollected behavioral data and feedback

[0522] These are the specific processing steps of this system. At each step, we also show what data processing and calculations are performed on the input data and what output is obtained. This makes it possible to provide users with a consistently optimized gaming experience.

[0523] (Application example 1)

[0524] 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."

[0525] In conventional virtual store experiences, users are provided with uniform content and product suggestions, making it difficult to meet individual user needs. This leads to problems such as reduced user satisfaction and reduced purchasing motivation. Furthermore, if product suggestions are inconsistent or do not match the user's interests, the user experience may be negatively impacted.

[0526] 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.

[0527] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data to identify user behavior patterns and feedback, generation AI means for generating new experience elements based on the analysis results, means for delivering the generated experience elements to the user's terminal, and means for displaying the generated experience elements on the terminal display, thereby enabling personalized product suggestions, interactive features, and promotions to be provided based on the behavioral characteristics and preferences of each individual user.

[0528] "User activity data" refers to data such as behavioral history, operation records, and feedback generated when a user uses the system.

[0529] A "behavioral pattern" refers to characteristics and tendencies identified by analyzing a user's series of actions, choices, operation methods, etc.

[0530] "Generative AI methods" refers to artificial intelligence technologies used to automatically generate new experience elements and content based on user behavior patterns and feedback.

[0531] "Experience elements" is a general term for new content, functions, interfaces, product proposals, etc. provided to users.

[0532] "Means for displaying on a terminal display" refers to the techniques and means for displaying the generated experience elements on the user's visual interface.

[0533] "Product suggestions" refers to a feature that recommends appropriate products and services based on a user's preferences and behavioral patterns.

[0534] "Interactive features" refers to functions and content that allow two-way communication between the user and the system.

[0535] "Promotion" refers to measures including advertising activities, campaigns, special offers, etc. aimed at promoting product sales.

[0536] "Ethics check measures" are measures that have the function of checking whether the experience elements and content generated are socially and culturally appropriate, and ensuring that inappropriate content is not included.

[0537] This invention is a system that provides a personalized virtual store experience using smart glasses. The system collects and analyzes user activity data to identify behavioral patterns and feedback, and generates new experience elements that are displayed on the user's smart glasses.

[0538] First, user activity data is collected. Specifically, the user's purchase history, browsing history, etc. are stored in a database. This data includes the user's actions and operations when visiting a virtual store.

[0539] Next, the server analyzes the user's behavioral patterns and feedback using big data analysis and machine learning technologies. For example, if a user frequently browses products in a specific category, the server profiles the user's purchasing tendencies. Based on the analysis results, the generative AI means generates new experience elements.

[0540] As a generative AI method, for example, we use GPT-3, a generative AI model. This AI generates new product suggestions using the following prompt sentence as input:

[0541] Generate product recommendations based on a user's profile:

[0542] Past purchase history: [Running shoes, fitness tracker, sports drink]

[0543] Browsing history: [New running shoes, yoga mats, training wear]

[0544] The generated experience elements are delivered by the server to the user's smart glasses, whose display visually displays the generated product suggestions, interactive features, and promotions.

[0545] For example, when a user wears smart glasses and accesses a virtual store, suggestions for new running shoes and promotions for fitness-related products are displayed based on the user's past behavioral data, allowing the user to intuitively receive product suggestions that match their preferences.

[0546] Additionally, the generated experience elements undergo an ethical check to ensure that the generated content is socially appropriate and does not contain excessive promotional or inappropriate content. Specifically, the AI ​​evaluates the content based on a checklist and makes corrections if there are any issues.

[0547] This system makes it possible to provide a personalized virtual store experience tailored to the needs of each user, thereby improving user satisfaction and increasing purchasing motivation.

[0548] The hardware used includes smart glasses and servers, and the software used includes Scikit-learn (for data analysis) and GPT-3 (a generative AI model).

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] A user visits a virtual store and puts on the smart glasses.

[0552] Input: User identification, smart glasses activation

[0553] Output: Activated smart glasses interface

[0554] Specific operation: A user puts on the smart glasses and launches the virtual store application, which causes the smart glasses to obtain the user's identity and begin the launch process.

[0555] Step 2:

[0556] The server collects activity data based on the user's identification information.

[0557] Input: User identity

[0558] Output: User purchase history, browsing history

[0559] Specific operation: The server accesses the database and obtains activity data such as the user's past purchase history and browsing history, thereby collecting the user's behavioral history.

[0560] Step 3:

[0561] The server analyzes the collected activity data to identify user behavior patterns and feedback.

[0562] Input: User purchase history, browsing history

[0563] Output: Identified behavioral patterns, feedback

[0564] How it works: The server uses analytical tools such as Scikit-learn to perform clustering analysis of user behavior patterns, and also analyzes feedback data using natural language processing techniques to identify user preferences and complaints.

[0565] Step 4:

[0566] The server uses a generative AI model to generate new experience elements based on the analysis results.

[0567] Input: Identified behavioral patterns, feedback

[0568] Output: New experience elements (product suggestions, promotions, etc.)

[0569] How it works: The server uses a generative AI model (e.g., GPT-3) to create prompts based on the user's behavioral patterns and feedback, and then inputs these into the AI ​​model to generate new experience elements.

[0570] Step 5:

[0571] The server performs an ethical check on the generated experience elements.

[0572] Input: New experience element

[0573] Output: Checked experience elements

[0574] What it does: The server evaluates the generated experience elements against an ethical checklist and corrects any inappropriate content, resulting in socially appropriate content.

[0575] Step 6:

[0576] The server delivers the checked experience elements to the user's smart glasses.

[0577] Input: Checked experience elements

[0578] Output: Delivered experience elements

[0579] Specific operation: The server sends the checked experience elements to the user's smart glasses, which then reflects the new experience elements on the user's device in real time.

[0580] Step 7:

[0581] Users experience new experiential elements through the smart glasses display.

[0582] Input: Delivered experience element

[0583] Output: User experience, feedback

[0584] Specific actions: The user browses the product suggestions and promotions displayed through the smart glasses, enjoys shopping and interactive features, and provides feedback again, which is collected as data for the next cycle.

[0585] 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.

[0586] This invention provides an experiential action RPG in which scenarios and items evolve and change by utilizing the user's characteristics and feedback. In addition to a system in which AI generates and adjusts and creates each element of the game (characters, levels, story) based on the user's behavioral patterns and opinions, by combining it with an emotion engine, it provides a personalized gaming experience that also takes into account the user's emotional reactions.

[0587] First, as a user plays a game, various behavioral patterns, choices, and operations occur. All user behavioral data (e.g., distance traveled, number of battles, number of times an item is used, etc.) is collected in real time. The device sends the recorded gameplay data to the server. This data includes the user's actions and choices during play, the levels cleared, etc.

[0588] In addition, after a user finishes playing, their impressions and opinions are collected using feedback forms and dialogues. For example, there is a mechanism for obtaining feedback from users, such as "The level is too difficult" or "I like the new character." The device collects this feedback data and sends it to the server.

[0589] The server accumulates the collected gameplay data and feedback data and passes it to a data analysis engine. The server uses big data analysis tools and machine learning algorithms to analyze the gameplay data and identify user behavior patterns. For example, it detects whether a player has been defeated by a particular enemy multiple times or frequently uses a particular item.

[0590] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it can analyze the sentiment of feedback such as "This level is too difficult."

[0591] Furthermore, the emotion engine analyzes the user's emotional reactions. The emotion engine uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice. For example, if a user furrows their brow while playing a game, it is interpreted as meaning that they are feeling irritated or in a difficult situation. Similarly, if the user's voice is high-pitched, it is interpreted as meaning that they are feeling elated or excited.

[0592] Based on the analysis results, the server utilizes generative AI to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level will be generated with adjusted enemy strength and numbers. New quests and characters will also be generated based on the user's behavioral patterns and emotional reactions. These will be characterized by designs and skill sets tailored to the user's preferences.

[0593] The generated game elements are then subjected to an ethical check to ensure that the expressions and content within the game are socially appropriate and do not include racism or excessive violence, providing a safe gaming environment.

[0594] The generated data is then delivered to the user's device, which receives the new game elements and integrates them with the existing game data. New levels and characters are instantly added to the user's game, allowing the user to experience new challenges.

[0595] As users enjoy the updated game, they provide further feedback, which is then collected, analyzed, and used to improve the system, ensuring a continuously optimized gaming experience for each individual user.

[0596] For example, if a user gives feedback that a certain level is too difficult, or if the emotion engine detects frustration from the user's facial expression, the server analyzes this data and generates a new version of the level with adjusted enemy numbers and difficulty. This is then distributed to the user's device, and when the user plays again, the server gives feedback that the difficulty level was appropriate. This feedback and emotion data is then collected again and used to generate the next game elements.

[0597] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0598] The processing flow will be explained below.

[0599] Step 1:

[0600] The user plays the game. During the game, the user performs various actions (movement, attack, use of items, etc.).

[0601] Step 2:

[0602] The device records the user's behavioral data (distance traveled, number of battles, type and frequency of items used, etc.) in real time.

[0603] Step 3:

[0604] The device transmits recorded gameplay data to the server, including the user's actions and choices during gameplay, levels completed, and so on.

[0605] Step 4:

[0606] After playing, users can use a feedback form or dialog box to enter their impressions and opinions of the game. For example, they can enter specific impressions such as "The level is too difficult" or "I like the new character."

[0607] Step 5:

[0608] The device collects and sends this feedback data, including all text data entered by the user, to the server.

[0609] Step 6:

[0610] The server stores the collected gameplay data and feedback data and passes it to a data analysis engine.

[0611] Step 7:

[0612] The server uses big data analytics tools and machine learning algorithms to analyze gameplay data and identify patterns of user behavior, such as detecting repeated defeats against a particular enemy.

[0613] Step 8:

[0614] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it can analyze the sentiment of feedback such as "This level is too difficult."

[0615] Step 9:

[0616] The server uses an emotion engine to analyze the user's emotional response. The emotion engine uses the device's camera and microphone to determine the user's emotion (e.g., joy, anger, surprise, etc.) using facial recognition technology and voice analysis technology.

[0617] Step 10:

[0618] The server utilizes generative AI to generate new game elements based on the results of big data analysis and emotion engine analysis, such as adjusting the difficulty of certain levels or designing new characters and items.

[0619] Step 11:

[0620] The server will then perform an ethical check on the generated game elements to ensure that the generated content is socially appropriate, including checking for racism and excessive violence.

[0621] Step 12:

[0622] The server packages the content that has passed the ethical check and prepares it for distribution to the user's terminal.

[0623] Step 13:

[0624] The device receives updates from the server and applies new game elements to the existing game data, for example, adding new levels or characters to the game.

[0625] Step 14:

[0626] The user plays the updated game again, ensuring that the new content is functioning correctly and that it is enjoyable.

[0627] Step 15:

[0628] Users again provide feedback on the new game elements and adjusted gameplay, such as "The new level was fun" or "The new weapon was easy to use."

[0629] Step 16:

[0630] The terminal again collects play data, feedback, and emotional responses from the emotion engine, and transmits them to the server.

[0631] Step 17:

[0632] The server then analyzes and generates the collected data again to provide the user with a more optimized gaming experience. By repeating this cycle, the user is continually provided with a personalized gaming experience.

[0633] Example 2

[0634] 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."

[0635] In conventional action RPGs, it has been difficult to fully reflect user behavioral patterns and feedback to personalize the gaming experience. Furthermore, game elements are often not updated or adjusted appropriately, resulting in reduced user satisfaction. The present invention aims to solve these problems and provide a more personalized gaming experience by utilizing user behavioral data and emotional responses.

[0636] 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.

[0637] In this invention, the server includes means for collecting user gameplay data, means for analyzing the collected game data to identify user behavioral patterns and feedback, generation AI means for generating new game elements based on the analysis results, emotion analysis means for analyzing user emotional responses, and means for delivering the generated game elements to the user's device. This makes it possible to continuously and appropriately update game elements based on the user's behavioral data and emotional responses, thereby providing a personalized game experience.

[0638] "User" refers to a person who uses the system to play a game.

[0639] "Game play data" refers to various behavior records and operation histories generated when a user plays a game.

[0640] "Analysis tool" refers to a method or device for analyzing collected data to identify useful information or patterns.

[0641] "Behavioral patterns" refer to the tendencies and characteristics of a series of actions that a user takes in a game.

[0642] "Feedback" refers to opinions and impressions provided by users regarding a system or game.

[0643] "Generative AI means" refers to means of automatically generating new game elements using artificial intelligence technology.

[0644] "Emotion analysis means" refers to a method or device for analyzing a user's emotional response.

[0645] "Game elements" refers to all components that affect the user's gaming experience, such as level design, characters, items, and quests that exist within the game.

[0646] "Distribution means" refers to a method or device for transmitting generated game elements to a user's terminal.

[0647] "Ethics check" refers to the process of reviewing the social appropriateness of generated game elements.

[0648] "Terminal" refers to the computing device that a user uses to play a game.

[0649] This invention is a system that provides an experiential action RPG in which scenarios and items evolve and change by utilizing user characteristics and feedback. This allows for a gaming experience that is optimized for each individual user. This invention is primarily comprised of three parties: a server, a terminal, and a user.

[0650] Hardware and software used

[0651] Implementation of the present invention includes the following hardware and software:

[0652] Device: The device on which a user plays a game (e.g., PC, smartphone, game console, etc.).

[0653] Server: A central control unit for collecting, analyzing, generating, and distributing data.

[0654] Data analysis engines: Big data analysis tools (e.g., Apache Hadoop) and machine learning algorithms (e.g., TensorFlow)

[0655] Natural language processing technology: Google Cloud Natural Language API

[0656] Sentiment analysis engine: Facial recognition technology (e.g., Microsoft Azure Face API) and voice analysis technology (e.g., IBM Watson Speech to Text)

[0657] Generation AI: OpenAI GPT-3

[0658] Specific explanation of the system

[0659] 1. User Gameplay:

[0660] Users use their devices to play games, controlling characters to fight enemies, use items, and clear levels, which generates various behavioral data in real time, such as distance traveled and number of battles.

[0661] 2. Game Data Collection and Transmission:

[0662] The device collects user behavior data in real time, including distance traveled, number of battles, number of items used, and levels cleared. The device then transmits the collected data to the server in real time.

[0663] 3. Gathering Feedback:

[0664] After the user finishes the game, the device displays a feedback form or dialog to collect the user's thoughts and opinions. For example, the device asks the user to provide specific feedback such as "The level is too difficult" or "I like the new character." The device then sends this feedback data to the server.

[0665] 4. Data collection and analysis:

[0666] The server stores the collected gameplay data and feedback data. Big data analysis tools and machine learning algorithms are used to analyze the data and identify user behavior patterns and feedback. For example, patterns such as "a user being defeated by a specific enemy multiple times" or "a user frequently using a specific item" are detected.

[0667] 5. Natural Language Processing of Feedback:

[0668] The server uses natural language processing technology to analyze the feedback data and extract emotions and specific opinions. For example, it analyzes feedback such as "This level is too difficult" to understand the user's opinion.

[0669] 6. Emotion analysis:

[0670] The server uses an emotion analysis engine to analyze the user's emotional response. It uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice. For example, a furrowed brow indicates irritation, while a high-pitched voice indicates elation or excitement.

[0671] 7. Creating new game elements:

[0672] Based on the analysis results, the server uses a generative AI model to automatically generate new game elements. For example, if a user repeatedly fails a particular level, it will generate a new version of that level with adjusted enemy count and difficulty. It will also generate new quests and characters based on the user's preferences.

[0673] Examples of prompts:

[0674] "Users are repeatedly failing a particular level. Please generate a new version of this level with a slightly reduced number and difficulty of enemies. Also, please take into account user feedback."

[0675] 8. Ethics Check:

[0676] Generated game elements are checked to determine their ethical and moral standards, and to ensure they do not contain excessive violence or racist content.

[0677] 9. New game features released:

[0678] The server distributes the generated game elements to the user's terminal, which receives the new game elements and integrates them into the existing game data.

[0679] 10. Collect ongoing feedback:

[0680] The user plays the updated game and again provides feedback, which the device sends to the server and is again used in the analysis and generation process.

[0681] This process allows us to provide each user with a consistently personalized gaming experience.

[0682] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0683] Step 1:

[0684] The user plays the game on the device.

[0685] Input: User actions (movement, combat, item use, level completion, etc.)

[0686] Specific actions: The user controls the character and performs various actions in the game, such as fighting enemies or using items. This generates behavioral data such as distance traveled and number of battles.

[0687] Output: Gameplay data (distance traveled, number of battles, number of items used, etc.)

[0688] Step 2:

[0689] The device collects gameplay data and transmits it to the server.

[0690] Input: Gameplay data (distance traveled, number of battles, number of items used, etc.)

[0691] Specific operation: The device records user behavior data in real time and transmits it to a server via the Internet.

[0692] Output: Gameplay data sent to the server

[0693] Step 3:

[0694] The user provides feedback at the device.

[0695] Input: Input into feedback forms and dialogues (level difficulty, thoughts on new characters, etc.)

[0696] Specific operation: After playing, the user enters their opinion in the displayed feedback form or dialog. For example, they provide comments such as "The level is too difficult" or "I like the new character."

[0697] Output: Feedback data

[0698] Step 4:

[0699] The terminal transmits the feedback data to the server.

[0700] Input: Feedback data (level difficulty, thoughts on new characters, etc.)

[0701] Specific operation: The terminal collects feedback data entered by the user and transmits it to a server via the Internet.

[0702] Output: Feedback data sent to the server

[0703] Step 5:

[0704] The server stores and analyzes gameplay data and feedback data.

[0705] Input: Gameplay and feedback data sent to the server

[0706] How it works: The server analyzes the data using big data analysis tools (e.g., Apache Hadoop) and machine learning algorithms (e.g., TensorFlow) to identify user behavior patterns and feedback. For example, it detects patterns such as "being defeated by a specific enemy multiple times" or "frequently using a specific item."

[0707] Output: Analysis results (identification of user behavior patterns and feedback)

[0708] Step 6:

[0709] The server analyzes the feedback data using natural language processing techniques.

[0710] Input: Feedback data (level difficulty, thoughts on new characters, etc.)

[0711] Specific operation: The server analyzes the feedback data using natural language processing technology (e.g., Google Cloud Natural Language API) to extract the user's opinions and wishes. For example, it analyzes feedback such as "This level is too difficult."

[0712] Output: Analyzed feedback data (extraction of user sentiment and opinions)

[0713] Step 7:

[0714] The server uses an emotion analysis engine to analyze the user's emotional response.

[0715] Input: User's facial recognition data and voice data

[0716] Specific operation: The server uses facial recognition technology (e.g., Microsoft Azure Face API) and voice analysis technology (e.g., IBM Watson Speech to Text) to analyze the user's facial expressions and tone of voice to determine their emotions. For example, a furrowed brow indicates irritation, and a higher-pitched voice indicates excitement.

[0717] Output: Sentiment analysis results (user's feelings such as irritation or excitement)

[0718] Step 8:

[0719] The server generates new game elements using generative AI models.

[0720] Input: behavioral pattern analysis results, emotion analysis results, feedback analysis results

[0721] How it works: The server uses generative AI (e.g., OpenAI GPT-3) to generate new game elements based on the analysis results. For example, if a user repeatedly fails a certain level, it generates a new level with adjusted enemy numbers and difficulty.

[0722] Output: New game elements (adjusted levels, new characters, etc.)

[0723] Examples of prompts:

[0724] "Users are repeatedly failing a particular level. Please generate a new version of this level with a slightly reduced number and difficulty of enemies. Also, please take into account user feedback."

[0725] Step 9:

[0726] The server performs a sanity check on the generated game elements.

[0727] Input: Generated game elements (adjusted levels, new characters, etc.)

[0728] Specific actions: The server checks whether the generated game elements are socially appropriate and reviews them to ensure they do not contain excessive violence or racist elements.

[0729] Output: Game elements that have passed ethical review

[0730] Step 10:

[0731] The server delivers new game elements to the user's device.

[0732] Input: New game elements that have passed ethical review

[0733] Specific operation: The server distributes new game elements to the user's device via the Internet.

[0734] Output: New game elements delivered to the user's device

[0735] Step 11:

[0736] The device integrates the new game elements into the existing game data.

[0737] Input: New game elements (adjusted levels, new characters, etc.)

[0738] Specific operation: The device will integrate new game elements into the existing game data and immediately reflect them in the game.

[0739] Output: Updated game data

[0740] Step 12:

[0741] The user plays the updated game and again provides feedback.

[0742] Input: Updated game data

[0743] Specific actions: The user plays the game with the new game elements and provides feedback again.

[0744] Output: New feedback data

[0745] Through this series of processing steps, a personalized gaming experience is provided to the user.

[0746] (Application example 2)

[0747] 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."

[0748] This invention improves the user's gaming experience and uses emotion analysis to provide a personalized experience based on the user's emotions and preferences during gameplay and shopping. Existing systems make changes and suggestions based solely on user behavioral data and feedback, which means they cannot adequately reflect the user's emotions and real-time reactions. This makes it difficult to recommend products and game elements that are appropriate for the user, and it is therefore difficult to provide consistent satisfaction.

[0749] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user game play data, means for analyzing the collected game data to identify the user's behavioral patterns and feedback, generation AI means for generating new game elements based on the analysis results, means for delivering the generated game elements to the user's terminal, emotion analysis means for analyzing the user's facial expressions and voice to identify emotions, and means for recommending products based on the emotion analysis results. This makes it possible to recommend new personalized game elements and products that reflect the user's behavioral data, feedback, and real-time emotions.

[0750] "Means for collecting user gameplay data" refers to a mechanism for recording and collecting behavioral data, choices, operations, etc. generated when a user actually plays a game.

[0751] "Means for analyzing collected game data to identify user behavioral patterns and feedback" refers to a mechanism for analyzing collected game play data to identify user behavioral trends and the content of the feedback provided.

[0752] "Generative AI means for generating new game elements" refers to artificial intelligence technology for automatically generating new game elements (level designs, characters, items, etc.) that adapt to users based on the analysis results.

[0753] "Means for delivering generated game elements to the user's device" refers to a mechanism for transmitting and delivering new game elements created by the generating AI to the device used by the user.

[0754] "Emotion analysis means for identifying emotions by analyzing a user's facial expressions and voice" refers to technology for analyzing a user's facial expressions and voice data to identify their emotions. This technology uses facial recognition and voice analysis technology.

[0755] "Means for recommending products based on the results of sentiment analysis" is a mechanism for selecting and recommending products and services suitable for users based on the results of sentiment analysis.

[0756] The system of the present invention includes a mechanism for collecting user gameplay data and generating and recommending new game elements and products based on the analysis results. Specific embodiments of this system are described below.

[0757] First, when a user plays a game, the user's behavioral data (distance traveled, number of battles, number of items used, etc.) as well as the choices and operations made during gameplay are collected. This data is sent in real time from the device to the server. The hardware used at this stage is the device held by the user (smart glasses or smartphone), and the software used is a client program for data collection.

[0758] The server analyzes the collected gameplay data to identify user behavior patterns. Big data analysis tools and machine learning algorithms are used for the analysis. Specific software used includes Python analysis libraries (e.g., Pandas, Scikit-learn) and natural language processing tools (e.g., NLTK, spaCy).

[0759] Furthermore, the server analyzes the user's feedback data (thoughts and opinions provided in feedback forms and dialogues) using natural language processing technology. Again, the natural language processing tool mentioned above is used to extract the user's opinions and wishes. This allows for specific feedback such as "The level is too difficult" or "I like the new character."

[0760] Emotion analysis is performed using technology that analyzes the user's facial expressions and voice. Using facial recognition and voice analysis technologies (e.g., OpenCV and Keras), emotions are determined from the user's facial expressions and tone of voice. For example, furrowing the brow while playing a game can be interpreted as irritation, and a high-pitched voice as excitement.

[0761] Based on the results of the analysis, the server automatically generates new game elements and products using a generative AI. A generative model endpoint (e.g., TensorFlow, PyTorch) is used for generation. Specifically, if a user repeatedly fails a particular level, the generative AI generates a new level with adjusted enemy strength and number.

[0762] New game elements and generated product recommendations are delivered in real time from the server to the user's device using communication software (e.g., WebSocket, REST API). The device that receives the new information integrates it with the existing game data, so that the new elements are immediately reflected when the user plays again.

[0763] Finally, user feedback and emotional data are collected again and reflected in the next game element generation and product recommendations, thereby continuously providing an optimized experience for each individual user.

[0764] For example, if a user visits a virtual shopping mall, frequently browses products from a particular brand, and provides positive feedback, the generative AI will prioritize displaying new products from that brand.

[0765] Example prompt sentence:

[0766] User behavior data: browsing time, purchase history, feedback data

[0767] User emotion data: facial expressions, tone of voice

[0768] New product suggestions tailored to the user: prioritize displaying products from a specific brand

[0769] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0770] Step 1:

[0771] The device collects the user's gameplay data (e.g., distance traveled, number of battles, number of items used) in real time. It uses a data collection tool to collect user behavior data and sends that data to the server. The input is gameplay data, and the output is collected data.

[0772] Step 2:

[0773] The server analyzes the collected gameplay data. This analysis uses big data analysis tools and machine learning algorithms to identify user behavior patterns (e.g., being defeated by a specific enemy multiple times, frequently using a specific item). The input is the collected gameplay data, and the output is user behavior pattern data.

[0774] Step 3:

[0775] The server collects user feedback data and analyzes it using natural language processing technology. User feedback (e.g., "The level is too difficult" or "I like the new character") is collected as text and sentiment analysis is performed. The input is the feedback data, and the output is extracted opinions and wishes.

[0776] Step 4:

[0777] The server analyzes the user's facial expressions and voice to identify their emotions. Using facial recognition and voice analysis technology, it determines emotions (e.g., irritation, excitement) from the user's facial expressions and tone of voice. The input is the user's video and voice data, and the output is emotional data.

[0778] Step 5:

[0779] The server generates new game elements and products based on the analysis results. Using a generative AI model, it generates new game elements and products that adapt to the user (e.g., new levels with adjusted enemy strength and number). The input is the user's behavioral patterns, feedback data, and emotional data, and the output is the generated game elements and products.

[0780] Step 6:

[0781] The server distributes the generated game elements and products to the user's device. Using communication software, the generated new game elements and products are sent to the user's device in real time. The input is the generated game elements and products, and the output is the data distributed to the device.

[0782] Step 7:

[0783] The data received by the device is integrated with existing game data. New game elements and products are integrated with existing data so that they are immediately reflected in the user's game. The input is the distributed data, and the output is the updated game data.

[0784] Step 8:

[0785] Users use the updated games and products offered and provide feedback again, which allows the system to be continuously optimized. The input is feedback after use, and the output is new data for the next analysis.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] [Third embodiment]

[0790] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0791] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0793] The 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.

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

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

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

[0797] Fig. 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.

[0798] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0799] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0800] In the 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.

[0801] 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."

[0802] This invention provides an experiential action RPG in which scenarios and items evolve and change by utilizing user characteristics and feedback, and includes a system in which AI generates and adjusts and creates each element of the game (characters, levels, story) based on the user's behavioral patterns and opinions.

[0803] First, as users play the game, various behavioral patterns, choices, and operations occur. All user behavioral data (e.g., distance traveled, number of battles, number of items used, etc.) is collected in real time. The collected data is recorded in a database.

[0804] The server analyzes the vast amount of collected gameplay data. Big data analysis and machine learning technologies are used to identify user behavior patterns (e.g., play style at a particular level, frequently used items, etc.). At the same time, feedback from users (e.g., "This level is too difficult" or "I like this character design") is also analyzed using natural language processing technology.

[0805] Based on the analysis results, the server utilizes generative AI to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level will be generated with adjusted enemy strength and number. New quests and characters will also be generated based on the user's behavior patterns. These will be characterized by the application of designs and skill sets tailored to the user's preferences.

[0806] The generated game elements are then subjected to an ethical check to ensure that the expressions and content within the game are socially appropriate and do not include racism or excessive violence, providing a safe gaming environment.

[0807] The generated data is then delivered to the user's device, which receives the new game elements and integrates them with the existing game data. New levels and characters are instantly added to the user's game, allowing the user to experience new challenges.

[0808] As users enjoy the updated game, they provide further feedback, which is then collected, analyzed, and used to improve the system, ensuring a continuously optimized gaming experience for each individual user.

[0809] For example, if a user gives feedback that a certain level is too difficult, the server analyzes this data and generates a new version that adjusts the number of enemies and difficulty of the level. This is then distributed to the user's device, and when the user plays again, the server gives feedback that the difficulty level was appropriate. This feedback is collected again as data and used to generate the next game elements.

[0810] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0811] The processing flow will be explained below.

[0812] Step 1:

[0813] As users play the game, various behavioral patterns, choices, and operations occur. All user behavior data (e.g., distance traveled, number of battles, number of item usages, etc.) is recorded in real time.

[0814] Step 2:

[0815] The device transmits recorded gameplay data to a database, including the user's actions and choices during gameplay, levels completed, and more.

[0816] Step 3:

[0817] After the user has finished playing, they can enter their impressions and opinions of the game using a feedback form or dialog box. For example, they can provide feedback such as "The level is too difficult" or "I like the new character."

[0818] Step 4:

[0819] The device collects and sends this feedback data to the server, which includes all text data entered by the user.

[0820] Step 5:

[0821] The server stores the collected gameplay data and feedback data and passes it to a data analysis engine.

[0822] Step 6:

[0823] The server uses big data analytics tools and machine learning algorithms to analyze gameplay data and identify patterns of user behavior, such as detecting repeated defeats against a particular enemy.

[0824] Step 7:

[0825] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it performs sentiment analysis on feedback such as "This level is too difficult."

[0826] Step 8:

[0827] The server uses generative AI based on the analysis results to generate new game elements, such as adjusting the difficulty of certain levels or designing new characters and items.

[0828] Step 9:

[0829] The server performs an ethical check on the generated game elements to ensure that the generated content is appropriate, for example, by checking that it does not contain racist or excessive violence.

[0830] Step 10:

[0831] The server packages the content that has passed the ethical check and prepares it for distribution to the user's terminal.

[0832] Step 11:

[0833] The device receives updates from the server and applies new game elements to the existing game data, for example, adding new levels or characters to the game.

[0834] Step 12:

[0835] The user plays the updated game again, ensuring that the new content is functioning correctly and that it is enjoyable.

[0836] Step 13:

[0837] Users again provide feedback on the new game elements and adjusted gameplay, such as "The new level was fun" or "The new weapon was easy to use."

[0838] Step 14:

[0839] The device again collects play data and feedback and sends it to the server, which accumulates data for the next content generation.

[0840] Step 15:

[0841] The server then analyzes and generates the collected data again to provide the user with a more optimized gaming experience. By repeating this cycle, the user is continually provided with a personalized gaming experience.

[0842] Example 1

[0843] 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."

[0844] In conventional action RPGs, it was difficult to provide personalized game elements based on user behavior patterns and feedback, resulting in a generic and fixed game experience. Furthermore, there was a lack of mechanisms to ensure the ethical issues and appropriateness of the content of the generated game elements.

[0845] 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.

[0846] In this invention, the server includes means for collecting user gameplay data, means for analyzing the collected game data to identify user behavior patterns and feedback, generation AI means for generating new game elements based on the analysis results, means for conducting ethical checks on the generated game elements, and means for delivering the generated game elements to user devices and integrating them with existing game data. This makes it possible to provide each user with a personalized game experience while realizing a safe gaming environment with appropriate content and expression.

[0847] "Gameplay data" refers to behavioral information and operation history recorded when a user plays a game.

[0848] "Analysis" refers to the process of analyzing collected data using statistical methods and machine learning techniques to extract meaningful information and patterns.

[0849] "Behavioral patterns" refer to the tendency of a user to repeatedly take actions or make choices within a game.

[0850] "Feedback" refers to the impressions and opinions that users provide regarding their gaming experience.

[0851] "Generative AI means" refers to a function that automatically generates new game elements (levels, characters, quests, items, etc.) using artificial intelligence technology.

[0852] "Ethical check" refers to an evaluation process to ensure that generated game elements are socially appropriate and do not violate specific ethical or moral values.

[0853] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a user uses to play the game.

[0854] "Integration" refers to the process of incorporating new game elements into existing game data.

[0855] "Level design" refers to the structure and arrangement of stages and missions within a game.

[0856] "Character" refers to a character that a user controls or interacts with in a game.

[0857] A "quest" refers to a goal or mission provided to a user, and includes elements that serve as challenges in progressing through the game.

[0858] "Item" refers to an object or tool that can be used by a user in a game to obtain an effect.

[0859] This invention provides an action-packed RPG that individually optimizes the user's gaming experience, and includes a system that generates and adjusts game elements based on user behavior data and feedback. An embodiment of this system will be described in detail below.

[0860] First, when a user plays a game, a variety of behavioral patterns, choices, and operations occur. When a user plays a game using a device such as a smartphone or PC, behavioral data such as distance traveled, number of battles, and number of times an item is used is collected in real time. This data is sent to a server by software installed on the device and recorded in a database.

[0861] The server analyzes the vast amount of collected gameplay data using big data analysis techniques (e.g., Apache Hadoop) and machine learning algorithms (e.g., random forest, deep learning). This analysis identifies user behavior patterns (e.g., play style at a particular level, frequently used items, etc.). At the same time, feedback from users (e.g., "This level is too difficult" or "I like this character design") is also analyzed using natural language processing techniques (e.g., BERT).

[0862] The server then uses a generative AI model (e.g., GPT-4) based on the analysis results to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level with adjusted enemy strength and number may be generated. New quests and characters may also be generated based on the user's behavioral patterns, with designs and skill sets tailored to the user's preferences. An example of a prompt for the generative AI model is, "Generate new game elements (levels, characters, quests) based on the user's behavioral data and feedback. After generation, perform an ethical check and provide appropriate content."

[0863] The generated game elements are then subjected to an ethical check, which examines whether the expressions and content within the game are socially appropriate, and ensures that they do not contain racism or excessive violence. This check is carried out using a dedicated AI model.

[0864] The server delivers the new game elements to the user's device, which then integrates the received data with the existing game data, instantly updating the game with new levels and characters, allowing the user to experience new challenges.

[0865] Furthermore, users who enjoy the updated game will provide further feedback. This feedback will be collected and analyzed again and reflected in the next generation of game elements. This process ensures that each user's gaming experience is continually optimized.

[0866] For example, if a user gives feedback that a certain level is "too difficult," the server analyzes this data and generates a new level with the number and strength of enemies adjusted appropriately. If the user then plays the game and gives feedback that the difficulty level was "just right," this information can be used to adjust the next level.

[0867] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0868] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0869] Step 1: Collect user behavior data

[0870] Subject: Terminal

[0871] Specific operation: When a user plays a game, the device collects behavioral data such as distance traveled, number of battles, and number of items used in real time and sends it to the server.

[0872] Input: User's gameplay behavior (movement, combat, item use, etc.)

[0873] Data processing / calculation: Behavioral data is classified into categories and saved with a timestamp.

[0874] Output: Categorized behavioral data (distance traveled, number of battles, number of item usages, etc.)

[0875] Step 2: Analyzing behavioral and feedback data

[0876] Subject: Server

[0877] Specific operation: The server uses software to store the received behavioral data in a database, and analyzes it using big data analysis technology and machine learning models. It also analyzes user feedback using natural language processing technology.

[0878] Input: behavioral data, user feedback

[0879] Data processing / calculation: Behavioral data is statistically analyzed, and feedback is analyzed using natural language processing models to extract behavioral patterns and user intent.

[0880] Output: User behavior patterns and feedback analysis results

[0881] Step 3: Creating new game elements

[0882] Subject: Server

[0883] Specific operation: Based on the analysis results, the server uses the generative AI model to generate new game elements (levels, characters, quests), creates specific prompts for the generative AI model, and inputs them into the model.

[0884] Input: User behavior patterns and feedback analysis results

[0885] Data processing / calculation: Text generation and scenario construction using generative AI models

[0886] Example prompt: "Generate new game elements (levels, characters, quests) based on user behavioral data and feedback. After generation, perform an ethical check and provide appropriate content."

[0887] Output: New game elements (e.g. adjusted levels, stat-revised characters, new quests)

[0888] Step 4: Ethics check of generated game elements

[0889] Subject: Server

[0890] Specific operation: Generated game elements are evaluated using a dedicated AI model to check whether they are ethically appropriate.

[0891] Input: Generated game elements

[0892] Data processing / computation: Evaluation and filtering based on social appropriateness criteria

[0893] Output: Game elements that pass the ethical check

[0894] Step 5: Delivering and integrating the generated game elements

[0895] Subject: Server and Terminal

[0896] Specific operation: The server delivers the checked game elements to the user's terminal, and the terminal integrates them into the existing game data.

[0897] Input: Game elements that pass the ethical check

[0898] Data processing / calculation: Sending new data to the terminal and integrating it with existing data

[0899] Output: Game data with integrated game elements

[0900] Step 6: Play new game features and gather feedback

[0901] Subject: User and Device

[0902] Specific operation: The user plays new game elements, and the device again collects the user's play and feedback.

[0903] Input: User play, user feedback

[0904] Data processing / computation: collection and classification of new behavioral data and feedback

[0905] Output: Recollected behavioral data and feedback

[0906] These are the specific processing steps of this system. At each step, we also show what data processing and calculations are performed on the input data and what output is obtained. This makes it possible to provide users with a consistently optimized gaming experience.

[0907] (Application example 1)

[0908] 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."

[0909] In conventional virtual store experiences, users are provided with uniform content and product suggestions, making it difficult to meet individual user needs. This leads to problems such as reduced user satisfaction and reduced purchasing motivation. Furthermore, if product suggestions are inconsistent or do not match the user's interests, the user experience may be negatively impacted.

[0910] 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.

[0911] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data to identify user behavior patterns and feedback, generation AI means for generating new experience elements based on the analysis results, means for delivering the generated experience elements to the user's terminal, and means for displaying the generated experience elements on the terminal display, thereby enabling personalized product suggestions, interactive features, and promotions to be provided based on the behavioral characteristics and preferences of each individual user.

[0912] "User activity data" refers to data such as behavioral history, operation records, and feedback generated when a user uses the system.

[0913] A "behavioral pattern" refers to characteristics and tendencies identified by analyzing a user's series of actions, choices, operation methods, etc.

[0914] "Generative AI methods" refers to artificial intelligence technologies used to automatically generate new experience elements and content based on user behavior patterns and feedback.

[0915] "Experience elements" is a general term for new content, functions, interfaces, product proposals, etc. provided to users.

[0916] "Means for displaying on a terminal display" refers to the techniques and means for displaying the generated experience elements on the user's visual interface.

[0917] "Product suggestions" refers to a feature that recommends appropriate products and services based on a user's preferences and behavioral patterns.

[0918] "Interactive features" refers to functions and content that allow two-way communication between the user and the system.

[0919] "Promotion" refers to measures including advertising activities, campaigns, special offers, etc. aimed at promoting product sales.

[0920] "Ethics check measures" are measures that have the function of checking whether the experience elements and content generated are socially and culturally appropriate, and ensuring that inappropriate content is not included.

[0921] This invention is a system that provides a personalized virtual store experience using smart glasses. The system collects and analyzes user activity data to identify behavioral patterns and feedback, and generates new experience elements that are displayed on the user's smart glasses.

[0922] First, user activity data is collected. Specifically, the user's purchase history, browsing history, etc. are stored in a database. This data includes the user's actions and operations when visiting a virtual store.

[0923] Next, the server analyzes the user's behavioral patterns and feedback using big data analysis and machine learning technologies. For example, if a user frequently browses products in a specific category, the server profiles the user's purchasing tendencies. Based on the analysis results, the generative AI means generates new experience elements.

[0924] As a generative AI method, for example, we use GPT-3, a generative AI model. This AI generates new product suggestions using the following prompt sentence as input:

[0925] Generate product recommendations based on a user's profile:

[0926] Past purchase history: [Running shoes, fitness tracker, sports drink]

[0927] Browsing history: [New running shoes, yoga mats, training wear]

[0928] The generated experience elements are delivered by the server to the user's smart glasses, whose display visually displays the generated product suggestions, interactive features, and promotions.

[0929] For example, when a user wears smart glasses and accesses a virtual store, suggestions for new running shoes and promotions for fitness-related products are displayed based on the user's past behavioral data, allowing the user to intuitively receive product suggestions that match their preferences.

[0930] Additionally, the generated experience elements undergo an ethical check to ensure that the generated content is socially appropriate and does not contain excessive promotional or inappropriate content. Specifically, the AI ​​evaluates the content based on a checklist and makes corrections if there are any issues.

[0931] This system makes it possible to provide a personalized virtual store experience tailored to the needs of each user, thereby improving user satisfaction and increasing purchasing motivation.

[0932] The hardware used includes smart glasses and servers, and the software used includes Scikit-learn (for data analysis) and GPT-3 (a generative AI model).

[0933] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0934] Step 1:

[0935] A user visits a virtual store and puts on the smart glasses.

[0936] Input: User identification, smart glasses activation

[0937] Output: Activated smart glasses interface

[0938] Specific operation: A user puts on the smart glasses and launches the virtual store application, which causes the smart glasses to obtain the user's identity and begin the launch process.

[0939] Step 2:

[0940] The server collects activity data based on the user's identification information.

[0941] Input: User identity

[0942] Output: User purchase history, browsing history

[0943] Specific operation: The server accesses the database and obtains activity data such as the user's past purchase history and browsing history, thereby collecting the user's behavioral history.

[0944] Step 3:

[0945] The server analyzes the collected activity data to identify user behavior patterns and feedback.

[0946] Input: User purchase history, browsing history

[0947] Output: Identified behavioral patterns, feedback

[0948] How it works: The server uses analytical tools such as Scikit-learn to perform clustering analysis of user behavior patterns, and also analyzes feedback data using natural language processing techniques to identify user preferences and complaints.

[0949] Step 4:

[0950] The server uses a generative AI model to generate new experience elements based on the analysis results.

[0951] Input: Identified behavioral patterns, feedback

[0952] Output: New experience elements (product suggestions, promotions, etc.)

[0953] How it works: The server uses a generative AI model (e.g., GPT-3) to create prompts based on the user's behavioral patterns and feedback, and then inputs these into the AI ​​model to generate new experience elements.

[0954] Step 5:

[0955] The server performs an ethical check on the generated experience elements.

[0956] Input: New experience element

[0957] Output: Checked experience elements

[0958] What it does: The server evaluates the generated experience elements against an ethical checklist and corrects any inappropriate content, resulting in socially appropriate content.

[0959] Step 6:

[0960] The server delivers the checked experience elements to the user's smart glasses.

[0961] Input: Checked experience elements

[0962] Output: Delivered experience elements

[0963] Specific operation: The server sends the checked experience elements to the user's smart glasses, which then reflects the new experience elements on the user's device in real time.

[0964] Step 7:

[0965] Users experience new experiential elements through the smart glasses display.

[0966] Input: Delivered experience element

[0967] Output: User experience, feedback

[0968] Specific actions: The user browses the product suggestions and promotions displayed through the smart glasses, enjoys shopping and interactive features, and provides feedback again, which is collected as data for the next cycle.

[0969] 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.

[0970] This invention provides an experiential action RPG in which scenarios and items evolve and change by utilizing the user's characteristics and feedback. In addition to a system in which AI generates and adjusts and creates each element of the game (characters, levels, story) based on the user's behavioral patterns and opinions, by combining it with an emotion engine, it provides a personalized gaming experience that also takes into account the user's emotional reactions.

[0971] First, as a user plays a game, various behavioral patterns, choices, and operations occur. All user behavioral data (e.g., distance traveled, number of battles, number of times an item is used, etc.) is collected in real time. The device sends the recorded gameplay data to the server. This data includes the user's actions and choices during play, the levels cleared, etc.

[0972] In addition, after a user finishes playing, their impressions and opinions are collected using feedback forms and dialogues. For example, there is a mechanism for obtaining feedback from users, such as "The level is too difficult" or "I like the new character." The device collects this feedback data and sends it to the server.

[0973] The server accumulates the collected gameplay data and feedback data and passes it to a data analysis engine. The server uses big data analysis tools and machine learning algorithms to analyze the gameplay data and identify user behavior patterns. For example, it detects whether a player has been defeated by a particular enemy multiple times or frequently uses a particular item.

[0974] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it can analyze the sentiment of feedback such as "This level is too difficult."

[0975] Furthermore, the emotion engine analyzes the user's emotional reactions. The emotion engine uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice. For example, if a user furrows their brow while playing a game, it is interpreted as meaning that they are feeling irritated or in a difficult situation. Similarly, if the user's voice is high-pitched, it is interpreted as meaning that they are feeling elated or excited.

[0976] Based on the analysis results, the server utilizes generative AI to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level will be generated with adjusted enemy strength and numbers. New quests and characters will also be generated based on the user's behavioral patterns and emotional reactions. These will be characterized by designs and skill sets tailored to the user's preferences.

[0977] The generated game elements are then subjected to an ethical check to ensure that the expressions and content within the game are socially appropriate and do not include racism or excessive violence, providing a safe gaming environment.

[0978] The generated data is then delivered to the user's device, which receives the new game elements and integrates them with the existing game data. New levels and characters are instantly added to the user's game, allowing the user to experience new challenges.

[0979] As users enjoy the updated game, they provide further feedback, which is then collected, analyzed, and used to improve the system, ensuring a continuously optimized gaming experience for each individual user.

[0980] For example, if a user gives feedback that a certain level is too difficult, or if the emotion engine detects frustration from the user's facial expression, the server analyzes this data and generates a new version of the level with adjusted enemy numbers and difficulty. This is then distributed to the user's device, and when the user plays again, the server gives feedback that the difficulty level was appropriate. This feedback and emotion data is then collected again and used to generate the next game elements.

[0981] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[0982] The processing flow will be explained below.

[0983] Step 1:

[0984] The user plays the game. During the game, the user performs various actions (movement, attack, use of items, etc.).

[0985] Step 2:

[0986] The device records the user's behavioral data (distance traveled, number of battles, type and frequency of items used, etc.) in real time.

[0987] Step 3:

[0988] The device transmits recorded gameplay data to the server, including the user's actions and choices during gameplay, levels completed, and so on.

[0989] Step 4:

[0990] After playing, users can use a feedback form or dialog box to enter their impressions and opinions of the game. For example, they can enter specific impressions such as "The level is too difficult" or "I like the new character."

[0991] Step 5:

[0992] The device collects and sends this feedback data, including all text data entered by the user, to the server.

[0993] Step 6:

[0994] The server stores the collected gameplay data and feedback data and passes it to a data analysis engine.

[0995] Step 7:

[0996] The server uses big data analytics tools and machine learning algorithms to analyze gameplay data and identify patterns of user behavior, such as detecting repeated defeats against a particular enemy.

[0997] Step 8:

[0998] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it can analyze the sentiment of feedback such as "This level is too difficult."

[0999] Step 9:

[1000] The server uses an emotion engine to analyze the user's emotional response. The emotion engine uses the device's camera and microphone to determine the user's emotion (e.g., joy, anger, surprise, etc.) using facial recognition technology and voice analysis technology.

[1001] Step 10:

[1002] The server utilizes generative AI to generate new game elements based on the results of big data analysis and emotion engine analysis, such as adjusting the difficulty of certain levels or designing new characters and items.

[1003] Step 11:

[1004] The server will then perform an ethical check on the generated game elements to ensure that the generated content is socially appropriate, including checking for racism and excessive violence.

[1005] Step 12:

[1006] The server packages the content that has passed the ethical check and prepares it for distribution to the user's terminal.

[1007] Step 13:

[1008] The device receives updates from the server and applies new game elements to the existing game data, for example, adding new levels or characters to the game.

[1009] Step 14:

[1010] The user plays the updated game again, ensuring that the new content is functioning correctly and that it is enjoyable.

[1011] Step 15:

[1012] Users again provide feedback on the new game elements and adjusted gameplay, such as "The new level was fun" or "The new weapon was easy to use."

[1013] Step 16:

[1014] The terminal again collects play data, feedback, and emotional responses from the emotion engine, and transmits them to the server.

[1015] Step 17:

[1016] The server then analyzes and generates the collected data again to provide the user with a more optimized gaming experience. By repeating this cycle, the user is continually provided with a personalized gaming experience.

[1017] Example 2

[1018] 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."

[1019] In conventional action RPGs, it has been difficult to fully reflect user behavioral patterns and feedback to personalize the gaming experience. Furthermore, game elements are often not updated or adjusted appropriately, resulting in reduced user satisfaction. The present invention aims to solve these problems and provide a more personalized gaming experience by utilizing user behavioral data and emotional responses.

[1020] 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.

[1021] In this invention, the server includes means for collecting user gameplay data, means for analyzing the collected game data to identify user behavioral patterns and feedback, generation AI means for generating new game elements based on the analysis results, emotion analysis means for analyzing user emotional responses, and means for delivering the generated game elements to the user's device. This makes it possible to continuously and appropriately update game elements based on the user's behavioral data and emotional responses, thereby providing a personalized game experience.

[1022] "User" refers to a person who uses the system to play a game.

[1023] "Game play data" refers to various behavior records and operation histories generated when a user plays a game.

[1024] "Analysis tool" refers to a method or device for analyzing collected data to identify useful information or patterns.

[1025] "Behavioral patterns" refer to the tendencies and characteristics of a series of actions that a user takes in a game.

[1026] "Feedback" refers to opinions and impressions provided by users regarding a system or game.

[1027] "Generative AI means" refers to means of automatically generating new game elements using artificial intelligence technology.

[1028] "Emotion analysis means" refers to a method or device for analyzing a user's emotional response.

[1029] "Game elements" refers to all components that affect the user's gaming experience, such as level design, characters, items, and quests that exist within the game.

[1030] "Distribution means" refers to a method or device for transmitting generated game elements to a user's terminal.

[1031] "Ethics check" refers to the process of reviewing the social appropriateness of generated game elements.

[1032] "Terminal" refers to the computing device that a user uses to play a game.

[1033] This invention is a system that provides an experiential action RPG in which scenarios and items evolve and change by utilizing user characteristics and feedback. This allows for a gaming experience that is optimized for each individual user. This invention is primarily comprised of three parties: a server, a terminal, and a user.

[1034] Hardware and software used

[1035] Implementation of the present invention includes the following hardware and software:

[1036] Device: The device on which a user plays a game (e.g., PC, smartphone, game console, etc.).

[1037] Server: A central control unit for collecting, analyzing, generating, and distributing data.

[1038] Data analysis engines: Big data analysis tools (e.g., Apache Hadoop) and machine learning algorithms (e.g., TensorFlow)

[1039] Natural language processing technology: Google Cloud Natural Language API

[1040] Sentiment analysis engine: Facial recognition technology (e.g., Microsoft Azure Face API) and voice analysis technology (e.g., IBM Watson Speech to Text)

[1041] Generation AI: OpenAI GPT-3

[1042] Specific explanation of the system

[1043] 1. User Gameplay:

[1044] Users use their devices to play games, controlling characters to fight enemies, use items, and clear levels, which generates various behavioral data in real time, such as distance traveled and number of battles.

[1045] 2. Game Data Collection and Transmission:

[1046] The device collects user behavior data in real time, including distance traveled, number of battles, number of items used, and levels cleared. The device then transmits the collected data to the server in real time.

[1047] 3. Gathering Feedback:

[1048] After the user finishes the game, the device displays a feedback form or dialog to collect the user's thoughts and opinions. For example, the device asks the user to provide specific feedback such as "The level is too difficult" or "I like the new character." The device then sends this feedback data to the server.

[1049] 4. Data collection and analysis:

[1050] The server stores the collected gameplay data and feedback data. Big data analysis tools and machine learning algorithms are used to analyze the data and identify user behavior patterns and feedback. For example, patterns such as "a user being defeated by a specific enemy multiple times" or "a user frequently using a specific item" are detected.

[1051] 5. Natural Language Processing of Feedback:

[1052] The server uses natural language processing technology to analyze the feedback data and extract emotions and specific opinions. For example, it analyzes feedback such as "This level is too difficult" to understand the user's opinion.

[1053] 6. Emotion analysis:

[1054] The server uses an emotion analysis engine to analyze the user's emotional response. It uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice. For example, a furrowed brow indicates irritation, while a high-pitched voice indicates elation or excitement.

[1055] 7. Creating new game elements:

[1056] Based on the analysis results, the server uses a generative AI model to automatically generate new game elements. For example, if a user repeatedly fails a particular level, it will generate a new version of that level with adjusted enemy count and difficulty. It will also generate new quests and characters based on the user's preferences.

[1057] Examples of prompts:

[1058] "Users are repeatedly failing a particular level. Please generate a new version of this level with a slightly reduced number and difficulty of enemies. Also, please take into account user feedback."

[1059] 8. Ethics Check:

[1060] Generated game elements are checked to determine their ethical and moral standards, and to ensure they do not contain excessive violence or racist content.

[1061] 9. New game features released:

[1062] The server distributes the generated game elements to the user's terminal, which receives the new game elements and integrates them into the existing game data.

[1063] 10. Collect ongoing feedback:

[1064] The user plays the updated game and again provides feedback, which the device sends to the server and is again used in the analysis and generation process.

[1065] This process allows us to provide each user with a consistently personalized gaming experience.

[1066] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1067] Step 1:

[1068] The user plays the game on the device.

[1069] Input: User actions (movement, combat, item use, level completion, etc.)

[1070] Specific actions: The user controls the character and performs various actions in the game, such as fighting enemies or using items. This generates behavioral data such as distance traveled and number of battles.

[1071] Output: Gameplay data (distance traveled, number of battles, number of items used, etc.)

[1072] Step 2:

[1073] The device collects gameplay data and transmits it to the server.

[1074] Input: Gameplay data (distance traveled, number of battles, number of items used, etc.)

[1075] Specific operation: The device records user behavior data in real time and transmits it to a server via the Internet.

[1076] Output: Gameplay data sent to the server

[1077] Step 3:

[1078] The user provides feedback at the device.

[1079] Input: Input into feedback forms and dialogues (level difficulty, thoughts on new characters, etc.)

[1080] Specific operation: After playing, the user enters their opinion in the displayed feedback form or dialog. For example, they provide comments such as "The level is too difficult" or "I like the new character."

[1081] Output: Feedback data

[1082] Step 4:

[1083] The terminal transmits the feedback data to the server.

[1084] Input: Feedback data (level difficulty, thoughts on new characters, etc.)

[1085] Specific operation: The terminal collects feedback data entered by the user and transmits it to a server via the Internet.

[1086] Output: Feedback data sent to the server

[1087] Step 5:

[1088] The server stores and analyzes gameplay data and feedback data.

[1089] Input: Gameplay and feedback data sent to the server

[1090] How it works: The server analyzes the data using big data analysis tools (e.g., Apache Hadoop) and machine learning algorithms (e.g., TensorFlow) to identify user behavior patterns and feedback. For example, it detects patterns such as "being defeated by a specific enemy multiple times" or "frequently using a specific item."

[1091] Output: Analysis results (identification of user behavior patterns and feedback)

[1092] Step 6:

[1093] The server analyzes the feedback data using natural language processing techniques.

[1094] Input: Feedback data (level difficulty, thoughts on new characters, etc.)

[1095] Specific operation: The server analyzes the feedback data using natural language processing technology (e.g., Google Cloud Natural Language API) to extract the user's opinions and wishes. For example, it analyzes feedback such as "This level is too difficult."

[1096] Output: Analyzed feedback data (extraction of user sentiment and opinions)

[1097] Step 7:

[1098] The server uses an emotion analysis engine to analyze the user's emotional response.

[1099] Input: User's facial recognition data and voice data

[1100] Specific operation: The server uses facial recognition technology (e.g., Microsoft Azure Face API) and voice analysis technology (e.g., IBM Watson Speech to Text) to analyze the user's facial expressions and tone of voice to determine their emotions. For example, a furrowed brow indicates irritation, and a higher-pitched voice indicates excitement.

[1101] Output: Sentiment analysis results (user's feelings such as irritation or excitement)

[1102] Step 8:

[1103] The server generates new game elements using generative AI models.

[1104] Input: behavioral pattern analysis results, emotion analysis results, feedback analysis results

[1105] How it works: The server uses generative AI (e.g., OpenAI GPT-3) to generate new game elements based on the analysis results. For example, if a user repeatedly fails a certain level, it generates a new level with adjusted enemy numbers and difficulty.

[1106] Output: New game elements (adjusted levels, new characters, etc.)

[1107] Examples of prompts:

[1108] "Users are repeatedly failing a particular level. Please generate a new version of this level with a slightly reduced number and difficulty of enemies. Also, please take into account user feedback."

[1109] Step 9:

[1110] The server performs a sanity check on the generated game elements.

[1111] Input: Generated game elements (adjusted levels, new characters, etc.)

[1112] Specific actions: The server checks whether the generated game elements are socially appropriate and reviews them to ensure they do not contain excessive violence or racist elements.

[1113] Output: Game elements that have passed ethical review

[1114] Step 10:

[1115] The server delivers new game elements to the user's device.

[1116] Input: New game elements that have passed ethical review

[1117] Specific operation: The server distributes new game elements to the user's device via the Internet.

[1118] Output: New game elements delivered to the user's device

[1119] Step 11:

[1120] The device integrates the new game elements into the existing game data.

[1121] Input: New game elements (adjusted levels, new characters, etc.)

[1122] Specific operation: The device will integrate new game elements into the existing game data and immediately reflect them in the game.

[1123] Output: Updated game data

[1124] Step 12:

[1125] The user plays the updated game and again provides feedback.

[1126] Input: Updated game data

[1127] Specific actions: The user plays the game with the new game elements and provides feedback again.

[1128] Output: New feedback data

[1129] Through this series of processing steps, a personalized gaming experience is provided to the user.

[1130] (Application example 2)

[1131] 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."

[1132] This invention improves the user's gaming experience and uses emotion analysis to provide a personalized experience based on the user's emotions and preferences during gameplay and shopping. Existing systems make changes and suggestions based solely on user behavioral data and feedback, which means they cannot adequately reflect the user's emotions and real-time reactions. This makes it difficult to recommend products and game elements that are appropriate for the user, and it is therefore difficult to provide consistent satisfaction.

[1133] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user game play data, means for analyzing the collected game data to identify the user's behavioral patterns and feedback, generation AI means for generating new game elements based on the analysis results, means for delivering the generated game elements to the user's terminal, emotion analysis means for analyzing the user's facial expressions and voice to identify emotions, and means for recommending products based on the emotion analysis results. This makes it possible to recommend new personalized game elements and products that reflect the user's behavioral data, feedback, and real-time emotions.

[1134] "Means for collecting user gameplay data" refers to a mechanism for recording and collecting behavioral data, choices, operations, etc. generated when a user actually plays a game.

[1135] "Means for analyzing collected game data to identify user behavioral patterns and feedback" refers to a mechanism for analyzing collected game play data to identify user behavioral trends and the content of the feedback provided.

[1136] "Generative AI means for generating new game elements" refers to artificial intelligence technology for automatically generating new game elements (level designs, characters, items, etc.) that adapt to users based on the analysis results.

[1137] "Means for delivering generated game elements to the user's device" refers to a mechanism for transmitting and delivering new game elements created by the generating AI to the device used by the user.

[1138] "Emotion analysis means for identifying emotions by analyzing a user's facial expressions and voice" refers to technology for analyzing a user's facial expressions and voice data to identify their emotions. This technology uses facial recognition and voice analysis technology.

[1139] "Means for recommending products based on the results of sentiment analysis" is a mechanism for selecting and recommending products and services suitable for users based on the results of sentiment analysis.

[1140] The system of the present invention includes a mechanism for collecting user gameplay data and generating and recommending new game elements and products based on the analysis results. Specific embodiments of this system are described below.

[1141] First, when a user plays a game, the user's behavioral data (distance traveled, number of battles, number of items used, etc.) as well as the choices and operations made during gameplay are collected. This data is sent in real time from the device to the server. The hardware used at this stage is the device held by the user (smart glasses or smartphone), and the software used is a client program for data collection.

[1142] The server analyzes the collected gameplay data to identify user behavior patterns. Big data analysis tools and machine learning algorithms are used for the analysis. Specific software used includes Python analysis libraries (e.g., Pandas, Scikit-learn) and natural language processing tools (e.g., NLTK, spaCy).

[1143] Furthermore, the server analyzes the user's feedback data (thoughts and opinions provided in feedback forms and dialogues) using natural language processing technology. Again, the natural language processing tool mentioned above is used to extract the user's opinions and wishes. This allows for specific feedback such as "The level is too difficult" or "I like the new character."

[1144] Emotion analysis is performed using technology that analyzes the user's facial expressions and voice. Using facial recognition and voice analysis technologies (e.g., OpenCV and Keras), emotions are determined from the user's facial expressions and tone of voice. For example, furrowing the brow while playing a game can be interpreted as irritation, and a high-pitched voice as excitement.

[1145] Based on the results of the analysis, the server automatically generates new game elements and products using a generative AI. A generative model endpoint (e.g., TensorFlow, PyTorch) is used for generation. Specifically, if a user repeatedly fails a particular level, the generative AI generates a new level with adjusted enemy strength and number.

[1146] New game elements and generated product recommendations are delivered in real time from the server to the user's device using communication software (e.g., WebSocket, REST API). The device that receives the new information integrates it with the existing game data, so that the new elements are immediately reflected when the user plays again.

[1147] Finally, user feedback and emotional data are collected again and reflected in the next game element generation and product recommendations, thereby continuously providing an optimized experience for each individual user.

[1148] For example, if a user visits a virtual shopping mall, frequently browses products from a particular brand, and provides positive feedback, the generative AI will prioritize displaying new products from that brand.

[1149] Example prompt sentence:

[1150] User behavior data: browsing time, purchase history, feedback data

[1151] User emotion data: facial expressions, tone of voice

[1152] New product suggestions tailored to the user: prioritize displaying products from a specific brand

[1153] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1154] Step 1:

[1155] The device collects the user's gameplay data (e.g., distance traveled, number of battles, number of items used) in real time. It uses a data collection tool to collect user behavior data and sends that data to the server. The input is gameplay data, and the output is collected data.

[1156] Step 2:

[1157] The server analyzes the collected gameplay data. This analysis uses big data analysis tools and machine learning algorithms to identify user behavior patterns (e.g., being defeated by a specific enemy multiple times, frequently using a specific item). The input is the collected gameplay data, and the output is user behavior pattern data.

[1158] Step 3:

[1159] The server collects user feedback data and analyzes it using natural language processing technology. User feedback (e.g., "The level is too difficult" or "I like the new character") is collected as text and sentiment analysis is performed. The input is the feedback data, and the output is extracted opinions and wishes.

[1160] Step 4:

[1161] The server analyzes the user's facial expressions and voice to identify their emotions. Using facial recognition and voice analysis technology, it determines emotions (e.g., irritation, excitement) from the user's facial expressions and tone of voice. The input is the user's video and voice data, and the output is emotional data.

[1162] Step 5:

[1163] The server generates new game elements and products based on the analysis results. Using a generative AI model, it generates new game elements and products that adapt to the user (e.g., new levels with adjusted enemy strength and number). The input is the user's behavioral patterns, feedback data, and emotional data, and the output is the generated game elements and products.

[1164] Step 6:

[1165] The server distributes the generated game elements and products to the user's device. Using communication software, the generated new game elements and products are sent to the user's device in real time. The input is the generated game elements and products, and the output is the data distributed to the device.

[1166] Step 7:

[1167] The data received by the device is integrated with existing game data. New game elements and products are integrated with existing data so that they are immediately reflected in the user's game. The input is the distributed data, and the output is the updated game data.

[1168] Step 8:

[1169] Users use the updated games and products offered and provide feedback again, which allows the system to be continuously optimized. The input is feedback after use, and the output is new data for the next analysis.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] [Fourth embodiment]

[1174] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1175] 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.

[1176] 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).

[1177] 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.

[1178] 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.

[1179] 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).

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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."

[1187] This invention provides an experiential action RPG in which scenarios and items evolve and change by utilizing user characteristics and feedback, and includes a system in which AI generates and adjusts and creates each element of the game (characters, levels, story) based on the user's behavioral patterns and opinions.

[1188] First, as users play the game, various behavioral patterns, choices, and operations occur. All user behavioral data (e.g., distance traveled, number of battles, number of items used, etc.) is collected in real time. The collected data is recorded in a database.

[1189] The server analyzes the vast amount of collected gameplay data. Big data analysis and machine learning technologies are used to identify user behavior patterns (e.g., play style at a particular level, frequently used items, etc.). At the same time, feedback from users (e.g., "This level is too difficult" or "I like this character design") is also analyzed using natural language processing technology.

[1190] Based on the analysis results, the server utilizes generative AI to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level will be generated with adjusted enemy strength and number. New quests and characters will also be generated based on the user's behavior patterns. These will be characterized by the application of designs and skill sets tailored to the user's preferences.

[1191] The generated game elements are then subjected to an ethical check to ensure that the expressions and content within the game are socially appropriate and do not include racism or excessive violence, providing a safe gaming environment.

[1192] The generated data is then delivered to the user's device, which receives the new game elements and integrates them with the existing game data. New levels and characters are instantly added to the user's game, allowing the user to experience new challenges.

[1193] As users enjoy the updated game, they provide further feedback, which is then collected, analyzed, and used to improve the system, ensuring a continuously optimized gaming experience for each individual user.

[1194] For example, if a user gives feedback that a certain level is too difficult, the server analyzes this data and generates a new version that adjusts the number of enemies and difficulty of the level. This is then distributed to the user's device, and when the user plays again, the server gives feedback that the difficulty level was appropriate. This feedback is collected again as data and used to generate the next game elements.

[1195] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[1196] The processing flow will be explained below.

[1197] Step 1:

[1198] As users play the game, various behavioral patterns, choices, and operations occur. All user behavior data (e.g., distance traveled, number of battles, number of item usages, etc.) is recorded in real time.

[1199] Step 2:

[1200] The device transmits recorded gameplay data to a database, including the user's actions and choices during gameplay, levels completed, and more.

[1201] Step 3:

[1202] After the user has finished playing, they can enter their impressions and opinions of the game using a feedback form or dialog box. For example, they can provide feedback such as "The level is too difficult" or "I like the new character."

[1203] Step 4:

[1204] The device collects and sends this feedback data to the server, which includes all text data entered by the user.

[1205] Step 5:

[1206] The server stores the collected gameplay data and feedback data and passes it to a data analysis engine.

[1207] Step 6:

[1208] The server uses big data analytics tools and machine learning algorithms to analyze gameplay data and identify patterns of user behavior, such as detecting repeated defeats against a particular enemy.

[1209] Step 7:

[1210] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it performs sentiment analysis on feedback such as "This level is too difficult."

[1211] Step 8:

[1212] The server uses generative AI based on the analysis results to generate new game elements, such as adjusting the difficulty of certain levels or designing new characters and items.

[1213] Step 9:

[1214] The server performs an ethical check on the generated game elements to ensure that the generated content is appropriate, for example, by checking that it does not contain racist or excessive violence.

[1215] Step 10:

[1216] The server packages the content that has passed the ethical check and prepares it for distribution to the user's terminal.

[1217] Step 11:

[1218] The device receives updates from the server and applies new game elements to the existing game data, for example, adding new levels or characters to the game.

[1219] Step 12:

[1220] The user plays the updated game again, ensuring that the new content is functioning correctly and that it is enjoyable.

[1221] Step 13:

[1222] Users again provide feedback on the new game elements and adjusted gameplay, such as "The new level was fun" or "The new weapon was easy to use."

[1223] Step 14:

[1224] The device again collects play data and feedback and sends it to the server, which accumulates data for the next content generation.

[1225] Step 15:

[1226] The server then analyzes and generates the collected data again to provide the user with a more optimized gaming experience. By repeating this cycle, the user is continually provided with a personalized gaming experience.

[1227] Example 1

[1228] 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."

[1229] In conventional action RPGs, it was difficult to provide personalized game elements based on user behavior patterns and feedback, resulting in a generic and fixed game experience. Furthermore, there was a lack of mechanisms to ensure the ethical issues and appropriateness of the content of the generated game elements.

[1230] 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.

[1231] In this invention, the server includes means for collecting user gameplay data, means for analyzing the collected game data to identify user behavior patterns and feedback, generation AI means for generating new game elements based on the analysis results, means for conducting ethical checks on the generated game elements, and means for delivering the generated game elements to user devices and integrating them with existing game data. This makes it possible to provide each user with a personalized game experience while realizing a safe gaming environment with appropriate content and expression.

[1232] "Gameplay data" refers to behavioral information and operation history recorded when a user plays a game.

[1233] "Analysis" refers to the process of analyzing collected data using statistical methods and machine learning techniques to extract meaningful information and patterns.

[1234] "Behavioral patterns" refer to the tendency of a user to repeatedly take actions or make choices within a game.

[1235] "Feedback" refers to the impressions and opinions that users provide regarding their gaming experience.

[1236] "Generative AI means" refers to a function that automatically generates new game elements (levels, characters, quests, items, etc.) using artificial intelligence technology.

[1237] "Ethical check" refers to an evaluation process to ensure that generated game elements are socially appropriate and do not violate specific ethical or moral values.

[1238] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a user uses to play the game.

[1239] "Integration" refers to the process of incorporating new game elements into existing game data.

[1240] "Level design" refers to the structure and arrangement of stages and missions within a game.

[1241] "Character" refers to a character that a user controls or interacts with in a game.

[1242] A "quest" refers to a goal or mission provided to a user, and includes elements that serve as challenges in progressing through the game.

[1243] "Item" refers to an object or tool that can be used by a user in a game to obtain an effect.

[1244] This invention provides an action-packed RPG that individually optimizes the user's gaming experience, and includes a system that generates and adjusts game elements based on user behavior data and feedback. An embodiment of this system will be described in detail below.

[1245] First, when a user plays a game, a variety of behavioral patterns, choices, and operations occur. When a user plays a game using a device such as a smartphone or PC, behavioral data such as distance traveled, number of battles, and number of times an item is used is collected in real time. This data is sent to a server by software installed on the device and recorded in a database.

[1246] The server analyzes the vast amount of collected gameplay data using big data analysis techniques (e.g., Apache Hadoop) and machine learning algorithms (e.g., random forest, deep learning). This analysis identifies user behavior patterns (e.g., play style at a particular level, frequently used items, etc.). At the same time, feedback from users (e.g., "This level is too difficult" or "I like this character design") is also analyzed using natural language processing techniques (e.g., BERT).

[1247] The server then uses a generative AI model (e.g., GPT-4) based on the analysis results to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level with adjusted enemy strength and number may be generated. New quests and characters may also be generated based on the user's behavioral patterns, with designs and skill sets tailored to the user's preferences. An example of a prompt for the generative AI model is, "Generate new game elements (levels, characters, quests) based on the user's behavioral data and feedback. After generation, perform an ethical check and provide appropriate content."

[1248] The generated game elements are then subjected to an ethical check, which examines whether the expressions and content within the game are socially appropriate, and ensures that they do not contain racism or excessive violence. This check is carried out using a dedicated AI model.

[1249] The server delivers the new game elements to the user's device, which then integrates the received data with the existing game data, instantly updating the game with new levels and characters, allowing the user to experience new challenges.

[1250] Furthermore, users who enjoy the updated game will provide further feedback. This feedback will be collected and analyzed again and reflected in the next generation of game elements. This process ensures that each user's gaming experience is continually optimized.

[1251] For example, if a user gives feedback that a certain level is "too difficult," the server analyzes this data and generates a new level with the number and strength of enemies adjusted appropriately. If the user then plays the game and gives feedback that the difficulty level was "just right," this information can be used to adjust the next level.

[1252] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[1253] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1254] Step 1: Collect user behavior data

[1255] Subject: Terminal

[1256] Specific operation: When a user plays a game, the device collects behavioral data such as distance traveled, number of battles, and number of items used in real time and sends it to the server.

[1257] Input: User's gameplay behavior (movement, combat, item use, etc.)

[1258] Data processing / calculation: Behavioral data is classified into categories and saved with a timestamp.

[1259] Output: Categorized behavioral data (distance traveled, number of battles, number of item usages, etc.)

[1260] Step 2: Analyzing behavioral and feedback data

[1261] Subject: Server

[1262] Specific operation: The server uses software to store the received behavioral data in a database, and analyzes it using big data analysis technology and machine learning models. It also analyzes user feedback using natural language processing technology.

[1263] Input: behavioral data, user feedback

[1264] Data processing / calculation: Behavioral data is statistically analyzed, and feedback is analyzed using natural language processing models to extract behavioral patterns and user intent.

[1265] Output: User behavior patterns and feedback analysis results

[1266] Step 3: Creating new game elements

[1267] Subject: Server

[1268] Specific operation: Based on the analysis results, the server uses the generative AI model to generate new game elements (levels, characters, quests), creates specific prompts for the generative AI model, and inputs them into the model.

[1269] Input: User behavior patterns and feedback analysis results

[1270] Data processing / calculation: Text generation and scenario construction using generative AI models

[1271] Example prompt: "Generate new game elements (levels, characters, quests) based on user behavioral data and feedback. After generation, perform an ethical check and provide appropriate content."

[1272] Output: New game elements (e.g. adjusted levels, stat-revised characters, new quests)

[1273] Step 4: Ethics check of generated game elements

[1274] Subject: Server

[1275] Specific operation: Generated game elements are evaluated using a dedicated AI model to check whether they are ethically appropriate.

[1276] Input: Generated game elements

[1277] Data processing / computation: Evaluation and filtering based on social appropriateness criteria

[1278] Output: Game elements that pass the ethical check

[1279] Step 5: Delivering and integrating the generated game elements

[1280] Subject: Server and Terminal

[1281] Specific operation: The server delivers the checked game elements to the user's terminal, and the terminal integrates them into the existing game data.

[1282] Input: Game elements that pass the ethical check

[1283] Data processing / calculation: Sending new data to the terminal and integrating it with existing data

[1284] Output: Game data with integrated game elements

[1285] Step 6: Play new game features and gather feedback

[1286] Subject: User and Device

[1287] Specific operation: The user plays new game elements, and the device again collects the user's play and feedback.

[1288] Input: User play, user feedback

[1289] Data processing / computation: collection and classification of new behavioral data and feedback

[1290] Output: Recollected behavioral data and feedback

[1291] These are the specific processing steps of this system. At each step, we also show what data processing and calculations are performed on the input data and what output is obtained. This makes it possible to provide users with a consistently optimized gaming experience.

[1292] (Application example 1)

[1293] 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."

[1294] In conventional virtual store experiences, users are provided with uniform content and product suggestions, making it difficult to meet individual user needs. This leads to problems such as reduced user satisfaction and reduced purchasing motivation. Furthermore, if product suggestions are inconsistent or do not match the user's interests, the user experience may be negatively impacted.

[1295] 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.

[1296] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data to identify user behavior patterns and feedback, generation AI means for generating new experience elements based on the analysis results, means for delivering the generated experience elements to the user's terminal, and means for displaying the generated experience elements on the terminal display, thereby enabling personalized product suggestions, interactive features, and promotions to be provided based on the behavioral characteristics and preferences of each individual user.

[1297] "User activity data" refers to data such as behavioral history, operation records, and feedback generated when a user uses the system.

[1298] A "behavioral pattern" refers to characteristics and tendencies identified by analyzing a user's series of actions, choices, operation methods, etc.

[1299] "Generative AI methods" refers to artificial intelligence technologies used to automatically generate new experience elements and content based on user behavior patterns and feedback.

[1300] "Experience elements" is a general term for new content, functions, interfaces, product proposals, etc. provided to users.

[1301] "Means for displaying on a terminal display" refers to the techniques and means for displaying the generated experience elements on the user's visual interface.

[1302] "Product suggestions" refers to a feature that recommends appropriate products and services based on a user's preferences and behavioral patterns.

[1303] "Interactive features" refers to functions and content that allow two-way communication between the user and the system.

[1304] "Promotion" refers to measures including advertising activities, campaigns, special offers, etc. aimed at promoting product sales.

[1305] "Ethics check measures" are measures that have the function of checking whether the experience elements and content generated are socially and culturally appropriate, and ensuring that inappropriate content is not included.

[1306] This invention is a system that provides a personalized virtual store experience using smart glasses. The system collects and analyzes user activity data to identify behavioral patterns and feedback, and generates new experience elements that are displayed on the user's smart glasses.

[1307] First, user activity data is collected. Specifically, the user's purchase history, browsing history, etc. are stored in a database. This data includes the user's actions and operations when visiting a virtual store.

[1308] Next, the server analyzes the user's behavioral patterns and feedback using big data analysis and machine learning technologies. For example, if a user frequently browses products in a specific category, the server profiles the user's purchasing tendencies. Based on the analysis results, the generative AI means generates new experience elements.

[1309] As a generative AI method, for example, we use GPT-3, a generative AI model. This AI generates new product suggestions using the following prompt sentence as input:

[1310] Generate product recommendations based on a user's profile:

[1311] Past purchase history: [Running shoes, fitness tracker, sports drink]

[1312] Browsing history: [New running shoes, yoga mats, training wear]

[1313] The generated experience elements are delivered by the server to the user's smart glasses, whose display visually displays the generated product suggestions, interactive features, and promotions.

[1314] For example, when a user wears smart glasses and accesses a virtual store, suggestions for new running shoes and promotions for fitness-related products are displayed based on the user's past behavioral data, allowing the user to intuitively receive product suggestions that match their preferences.

[1315] Additionally, the generated experience elements undergo an ethical check to ensure that the generated content is socially appropriate and does not contain excessive promotional or inappropriate content. Specifically, the AI ​​evaluates the content based on a checklist and makes corrections if there are any issues.

[1316] This system makes it possible to provide a personalized virtual store experience tailored to the needs of each user, thereby improving user satisfaction and increasing purchasing motivation.

[1317] The hardware used includes smart glasses and servers, and the software used includes Scikit-learn (for data analysis) and GPT-3 (a generative AI model).

[1318] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1319] Step 1:

[1320] A user visits a virtual store and puts on the smart glasses.

[1321] Input: User identification, smart glasses activation

[1322] Output: Activated smart glasses interface

[1323] Specific operation: A user puts on the smart glasses and launches the virtual store application, which causes the smart glasses to obtain the user's identity and begin the launch process.

[1324] Step 2:

[1325] The server collects activity data based on the user's identification information.

[1326] Input: User identity

[1327] Output: User purchase history, browsing history

[1328] Specific operation: The server accesses the database and obtains activity data such as the user's past purchase history and browsing history, thereby collecting the user's behavioral history.

[1329] Step 3:

[1330] The server analyzes the collected activity data to identify user behavior patterns and feedback.

[1331] Input: User purchase history, browsing history

[1332] Output: Identified behavioral patterns, feedback

[1333] How it works: The server uses analytical tools such as Scikit-learn to perform clustering analysis of user behavior patterns, and also analyzes feedback data using natural language processing techniques to identify user preferences and complaints.

[1334] Step 4:

[1335] The server uses a generative AI model to generate new experience elements based on the analysis results.

[1336] Input: Identified behavioral patterns, feedback

[1337] Output: New experience elements (product suggestions, promotions, etc.)

[1338] How it works: The server uses a generative AI model (e.g., GPT-3) to create prompts based on the user's behavioral patterns and feedback, and then inputs these into the AI ​​model to generate new experience elements.

[1339] Step 5:

[1340] The server performs an ethical check on the generated experience elements.

[1341] Input: New experience element

[1342] Output: Checked experience elements

[1343] What it does: The server evaluates the generated experience elements against an ethical checklist and corrects any inappropriate content, resulting in socially appropriate content.

[1344] Step 6:

[1345] The server delivers the checked experience elements to the user's smart glasses.

[1346] Input: Checked experience elements

[1347] Output: Delivered experience elements

[1348] Specific operation: The server sends the checked experience elements to the user's smart glasses, which then reflects the new experience elements on the user's device in real time.

[1349] Step 7:

[1350] Users experience new experiential elements through the smart glasses display.

[1351] Input: Delivered experience element

[1352] Output: User experience, feedback

[1353] Specific actions: The user browses the product suggestions and promotions displayed through the smart glasses, enjoys shopping and interactive features, and provides feedback again, which is collected as data for the next cycle.

[1354] 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.

[1355] This invention provides an experiential action RPG in which scenarios and items evolve and change by utilizing the user's characteristics and feedback. In addition to a system in which AI generates and adjusts and creates each element of the game (characters, levels, story) based on the user's behavioral patterns and opinions, by combining it with an emotion engine, it provides a personalized gaming experience that also takes into account the user's emotional reactions.

[1356] First, as a user plays a game, various behavioral patterns, choices, and operations occur. All user behavioral data (e.g., distance traveled, number of battles, number of times an item is used, etc.) is collected in real time. The device sends the recorded gameplay data to the server. This data includes the user's actions and choices during play, the levels cleared, etc.

[1357] In addition, after a user finishes playing, their impressions and opinions are collected using feedback forms and dialogues. For example, there is a mechanism for obtaining feedback from users, such as "The level is too difficult" or "I like the new character." The device collects this feedback data and sends it to the server.

[1358] The server accumulates the collected gameplay data and feedback data and passes it to a data analysis engine. The server uses big data analysis tools and machine learning algorithms to analyze the gameplay data and identify user behavior patterns. For example, it detects whether a player has been defeated by a particular enemy multiple times or frequently uses a particular item.

[1359] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it can analyze the sentiment of feedback such as "This level is too difficult."

[1360] Furthermore, the emotion engine analyzes the user's emotional reactions. The emotion engine uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice. For example, if a user furrows their brow while playing a game, it is interpreted as meaning that they are feeling irritated or in a difficult situation. Similarly, if the user's voice is high-pitched, it is interpreted as meaning that they are feeling elated or excited.

[1361] Based on the analysis results, the server utilizes generative AI to automatically generate new game elements. For example, if a user repeatedly fails at a particular level, a new version of the level will be generated with adjusted enemy strength and numbers. New quests and characters will also be generated based on the user's behavioral patterns and emotional reactions. These will be characterized by designs and skill sets tailored to the user's preferences.

[1362] The generated game elements are then subjected to an ethical check to ensure that the expressions and content within the game are socially appropriate and do not include racism or excessive violence, providing a safe gaming environment.

[1363] The generated data is then delivered to the user's device, which receives the new game elements and integrates them with the existing game data. New levels and characters are instantly added to the user's game, allowing the user to experience new challenges.

[1364] As users enjoy the updated game, they provide further feedback, which is then collected, analyzed, and used to improve the system, ensuring a continuously optimized gaming experience for each individual user.

[1365] For example, if a user gives feedback that a certain level is too difficult, or if the emotion engine detects frustration from the user's facial expression, the server analyzes this data and generates a new version of the level with adjusted enemy numbers and difficulty. This is then distributed to the user's device, and when the user plays again, the server gives feedback that the difficulty level was appropriate. This feedback and emotion data is then collected again and used to generate the next game elements.

[1366] The above is an embodiment of the present invention, and this process provides a consistently personalized gaming experience for the user.

[1367] The processing flow will be explained below.

[1368] Step 1:

[1369] The user plays the game. During the game, the user performs various actions (movement, attack, use of items, etc.).

[1370] Step 2:

[1371] The device records the user's behavioral data (distance traveled, number of battles, type and frequency of items used, etc.) in real time.

[1372] Step 3:

[1373] The device transmits recorded gameplay data to the server, including the user's actions and choices during gameplay, levels completed, and so on.

[1374] Step 4:

[1375] After playing, users can use a feedback form or dialog box to enter their impressions and opinions of the game. For example, they can enter specific impressions such as "The level is too difficult" or "I like the new character."

[1376] Step 5:

[1377] The device collects and sends this feedback data, including all text data entered by the user, to the server.

[1378] Step 6:

[1379] The server stores the collected gameplay data and feedback data and passes it to a data analysis engine.

[1380] Step 7:

[1381] The server uses big data analytics tools and machine learning algorithms to analyze gameplay data and identify patterns of user behavior, such as detecting repeated defeats against a particular enemy.

[1382] Step 8:

[1383] The server uses natural language processing technology to analyze the feedback data and extract the user's opinions and wishes. For example, it can analyze the sentiment of feedback such as "This level is too difficult."

[1384] Step 9:

[1385] The server uses an emotion engine to analyze the user's emotional response. The emotion engine uses the device's camera and microphone to determine the user's emotion (e.g., joy, anger, surprise, etc.) using facial recognition technology and voice analysis technology.

[1386] Step 10:

[1387] The server utilizes generative AI to generate new game elements based on the results of big data analysis and emotion engine analysis, such as adjusting the difficulty of certain levels or designing new characters and items.

[1388] Step 11:

[1389] The server will then perform an ethical check on the generated game elements to ensure that the generated content is socially appropriate, including checking for racism and excessive violence.

[1390] Step 12:

[1391] The server packages the content that has passed the ethical check and prepares it for distribution to the user's terminal.

[1392] Step 13:

[1393] The device receives updates from the server and applies new game elements to the existing game data, for example, adding new levels or characters to the game.

[1394] Step 14:

[1395] The user plays the updated game again, ensuring that the new content is functioning correctly and that it is enjoyable.

[1396] Step 15:

[1397] Users again provide feedback on the new game elements and adjusted gameplay, such as "The new level was fun" or "The new weapon was easy to use."

[1398] Step 16:

[1399] The terminal again collects play data, feedback, and emotional responses from the emotion engine, and transmits them to the server.

[1400] Step 17:

[1401] The server then analyzes and generates the collected data again to provide the user with a more optimized gaming experience. By repeating this cycle, the user is continually provided with a personalized gaming experience.

[1402] Example 2

[1403] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1404] In conventional action RPGs, it has been difficult to fully reflect user behavioral patterns and feedback to personalize the gaming experience. Furthermore, game elements are often not updated or adjusted appropriately, resulting in reduced user satisfaction. The present invention aims to solve these problems and provide a more personalized gaming experience by utilizing user behavioral data and emotional responses.

[1405] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1406] In this invention, the server includes means for collecting user gameplay data, means for analyzing the collected game data to identify user behavioral patterns and feedback, generation AI means for generating new game elements based on the analysis results, emotion analysis means for analyzing user emotional responses, and means for delivering the generated game elements to the user's device. This makes it possible to continuously and appropriately update game elements based on the user's behavioral data and emotional responses, thereby providing a personalized game experience.

[1407] "User" refers to a person who uses the system to play a game.

[1408] "Game play data" refers to various behavior records and operation histories generated when a user plays a game.

[1409] "Analysis tool" refers to a method or device for analyzing collected data to identify useful information or patterns.

[1410] "Behavioral patterns" refer to the tendencies and characteristics of a series of actions that a user takes in a game.

[1411] "Feedback" refers to opinions and impressions provided by users regarding a system or game.

[1412] "Generative AI means" refers to means of automatically generating new game elements using artificial intelligence technology.

[1413] "Emotion analysis means" refers to a method or device for analyzing a user's emotional response.

[1414] "Game elements" refers to all components that affect the user's gaming experience, such as level design, characters, items, and quests that exist within the game.

[1415] "Distribution means" refers to a method or device for transmitting generated game elements to a user's terminal.

[1416] "Ethics check" refers to the process of reviewing the social appropriateness of generated game elements.

[1417] "Terminal" refers to the computing device that a user uses to play a game.

[1418] This invention is a system that provides an experiential action RPG in which scenarios and items evolve and change by utilizing user characteristics and feedback. This allows for a gaming experience that is optimized for each individual user. This invention is primarily comprised of three parties: a server, a terminal, and a user.

[1419] Hardware and software used

[1420] Implementation of the present invention includes the following hardware and software:

[1421] Device: The device on which a user plays a game (e.g., PC, smartphone, game console, etc.).

[1422] Server: A central control unit for collecting, analyzing, generating, and distributing data.

[1423] Data analysis engines: Big data analysis tools (e.g., Apache Hadoop) and machine learning algorithms (e.g., TensorFlow)

[1424] Natural language processing technology: Google Cloud Natural Language API

[1425] Sentiment analysis engine: Facial recognition technology (e.g., Microsoft Azure Face API) and voice analysis technology (e.g., IBM Watson Speech to Text)

[1426] Generation AI: OpenAI GPT-3

[1427] Specific explanation of the system

[1428] 1. User Gameplay:

[1429] Users use their devices to play games, controlling characters to fight enemies, use items, and clear levels, which generates various behavioral data in real time, such as distance traveled and number of battles.

[1430] 2. Game Data Collection and Transmission:

[1431] The device collects user behavior data in real time, including distance traveled, number of battles, number of items used, and levels cleared. The device then transmits the collected data to the server in real time.

[1432] 3. Gathering Feedback:

[1433] After the user finishes the game, the device displays a feedback form or dialog to collect the user's thoughts and opinions. For example, the device asks the user to provide specific feedback such as "The level is too difficult" or "I like the new character." The device then sends this feedback data to the server.

[1434] 4. Data collection and analysis:

[1435] The server stores the collected gameplay data and feedback data. Big data analysis tools and machine learning algorithms are used to analyze the data and identify user behavior patterns and feedback. For example, patterns such as "a user being defeated by a specific enemy multiple times" or "a user frequently using a specific item" are detected.

[1436] 5. Natural Language Processing of Feedback:

[1437] The server uses natural language processing technology to analyze the feedback data and extract emotions and specific opinions. For example, it analyzes feedback such as "This level is too difficult" to understand the user's opinion.

[1438] 6. Emotion analysis:

[1439] The server uses an emotion analysis engine to analyze the user's emotional response. It uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice. For example, a furrowed brow indicates irritation, while a high-pitched voice indicates elation or excitement.

[1440] 7. Creating new game elements:

[1441] Based on the analysis results, the server uses a generative AI model to automatically generate new game elements. For example, if a user repeatedly fails a particular level, it will generate a new version of that level with adjusted enemy count and difficulty. It will also generate new quests and characters based on the user's preferences.

[1442] Examples of prompts:

[1443] "Users are repeatedly failing a particular level. Please generate a new version of this level with a slightly reduced number and difficulty of enemies. Also, please take into account user feedback."

[1444] 8. Ethics Check:

[1445] Generated game elements are checked to determine their ethical and moral standards, and to ensure they do not contain excessive violence or racist content.

[1446] 9. New game features released:

[1447] The server distributes the generated game elements to the user's terminal, which receives the new game elements and integrates them into the existing game data.

[1448] 10. Collect ongoing feedback:

[1449] The user plays the updated game and again provides feedback, which the device sends to the server and is again used in the analysis and generation process.

[1450] This process allows us to provide each user with a consistently personalized gaming experience.

[1451] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1452] Step 1:

[1453] The user plays the game on the device.

[1454] Input: User actions (movement, combat, item use, level completion, etc.)

[1455] Specific actions: The user controls the character and performs various actions in the game, such as fighting enemies or using items. This generates behavioral data such as distance traveled and number of battles.

[1456] Output: Gameplay data (distance traveled, number of battles, number of items used, etc.)

[1457] Step 2:

[1458] The device collects gameplay data and transmits it to the server.

[1459] Input: Gameplay data (distance traveled, number of battles, number of items used, etc.)

[1460] Specific operation: The device records user behavior data in real time and transmits it to a server via the Internet.

[1461] Output: Gameplay data sent to the server

[1462] Step 3:

[1463] The user provides feedback at the device.

[1464] Input: Input into feedback forms and dialogues (level difficulty, thoughts on new characters, etc.)

[1465] Specific operation: After playing, the user enters their opinion in the displayed feedback form or dialog. For example, they provide comments such as "The level is too difficult" or "I like the new character."

[1466] Output: Feedback data

[1467] Step 4:

[1468] The terminal transmits the feedback data to the server.

[1469] Input: Feedback data (level difficulty, thoughts on new characters, etc.)

[1470] Specific operation: The terminal collects feedback data entered by the user and transmits it to a server via the Internet.

[1471] Output: Feedback data sent to the server

[1472] Step 5:

[1473] The server stores and analyzes gameplay data and feedback data.

[1474] Input: Gameplay and feedback data sent to the server

[1475] How it works: The server analyzes the data using big data analysis tools (e.g., Apache Hadoop) and machine learning algorithms (e.g., TensorFlow) to identify user behavior patterns and feedback. For example, it detects patterns such as "being defeated by a specific enemy multiple times" or "frequently using a specific item."

[1476] Output: Analysis results (identification of user behavior patterns and feedback)

[1477] Step 6:

[1478] The server analyzes the feedback data using natural language processing techniques.

[1479] Input: Feedback data (level difficulty, thoughts on new characters, etc.)

[1480] Specific operation: The server analyzes the feedback data using natural language processing technology (e.g., Google Cloud Natural Language API) to extract the user's opinions and wishes. For example, it analyzes feedback such as "This level is too difficult."

[1481] Output: Analyzed feedback data (extraction of user sentiment and opinions)

[1482] Step 7:

[1483] The server uses an emotion analysis engine to analyze the user's emotional response.

[1484] Input: User's facial recognition data and voice data

[1485] Specific operation: The server uses facial recognition technology (e.g., Microsoft Azure Face API) and voice analysis technology (e.g., IBM Watson Speech to Text) to analyze the user's facial expressions and tone of voice to determine their emotions. For example, a furrowed brow indicates irritation, and a higher-pitched voice indicates excitement.

[1486] Output: Sentiment analysis results (user's feelings such as irritation or excitement)

[1487] Step 8:

[1488] The server generates new game elements using generative AI models.

[1489] Input: behavioral pattern analysis results, emotion analysis results, feedback analysis results

[1490] How it works: The server uses generative AI (e.g., OpenAI GPT-3) to generate new game elements based on the analysis results. For example, if a user repeatedly fails a certain level, it generates a new level with adjusted enemy numbers and difficulty.

[1491] Output: New game elements (adjusted levels, new characters, etc.)

[1492] Examples of prompts:

[1493] "Users are repeatedly failing a particular level. Please generate a new version of this level with a slightly reduced number and difficulty of enemies. Also, please take into account user feedback."

[1494] Step 9:

[1495] The server performs a sanity check on the generated game elements.

[1496] Input: Generated game elements (adjusted levels, new characters, etc.)

[1497] Specific actions: The server checks whether the generated game elements are socially appropriate and reviews them to ensure they do not contain excessive violence or racist elements.

[1498] Output: Game elements that have passed ethical review

[1499] Step 10:

[1500] The server delivers new game elements to the user's device.

[1501] Input: New game elements that have passed ethical review

[1502] Specific operation: The server distributes new game elements to the user's device via the Internet.

[1503] Output: New game elements delivered to the user's device

[1504] Step 11:

[1505] The device integrates the new game elements into the existing game data.

[1506] Input: New game elements (adjusted levels, new characters, etc.)

[1507] Specific operation: The device will integrate new game elements into the existing game data and immediately reflect them in the game.

[1508] Output: Updated game data

[1509] Step 12:

[1510] The user plays the updated game and again provides feedback.

[1511] Input: Updated game data

[1512] Specific actions: The user plays the game with the new game elements and provides feedback again.

[1513] Output: New feedback data

[1514] Through this series of processing steps, a personalized gaming experience is provided to the user.

[1515] (Application example 2)

[1516] 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."

[1517] This invention improves the user's gaming experience and uses emotion analysis to provide a personalized experience based on the user's emotions and preferences during gameplay and shopping. Existing systems make changes and suggestions based solely on user behavioral data and feedback, which means they cannot adequately reflect the user's emotions and real-time reactions. This makes it difficult to recommend products and game elements that are appropriate for the user, and it is therefore difficult to provide consistent satisfaction.

[1518] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user game play data, means for analyzing the collected game data to identify the user's behavioral patterns and feedback, generation AI means for generating new game elements based on the analysis results, means for delivering the generated game elements to the user's terminal, emotion analysis means for analyzing the user's facial expressions and voice to identify emotions, and means for recommending products based on the emotion analysis results. This makes it possible to recommend new personalized game elements and products that reflect the user's behavioral data, feedback, and real-time emotions.

[1519] "Means for collecting user gameplay data" refers to a mechanism for recording and collecting behavioral data, choices, operations, etc. generated when a user actually plays a game.

[1520] "Means for analyzing collected game data to identify user behavioral patterns and feedback" refers to a mechanism for analyzing collected game play data to identify user behavioral trends and the content of the feedback provided.

[1521] "Generative AI means for generating new game elements" refers to artificial intelligence technology for automatically generating new game elements (level designs, characters, items, etc.) that adapt to users based on the analysis results.

[1522] "Means for delivering generated game elements to the user's device" refers to a mechanism for transmitting and delivering new game elements created by the generating AI to the device used by the user.

[1523] "Emotion analysis means for identifying emotions by analyzing a user's facial expressions and voice" refers to technology for analyzing a user's facial expressions and voice data to identify their emotions. This technology uses facial recognition and voice analysis technology.

[1524] "Means for recommending products based on the results of sentiment analysis" is a mechanism for selecting and recommending products and services suitable for users based on the results of sentiment analysis.

[1525] The system of the present invention includes a mechanism for collecting user gameplay data and generating and recommending new game elements and products based on the analysis results. Specific embodiments of this system are described below.

[1526] First, when a user plays a game, the user's behavioral data (distance traveled, number of battles, number of items used, etc.) as well as the choices and operations made during gameplay are collected. This data is sent in real time from the device to the server. The hardware used at this stage is the device held by the user (smart glasses or smartphone), and the software used is a client program for data collection.

[1527] The server analyzes the collected gameplay data to identify user behavior patterns. Big data analysis tools and machine learning algorithms are used for the analysis. Specific software used includes Python analysis libraries (e.g., Pandas, Scikit-learn) and natural language processing tools (e.g., NLTK, spaCy).

[1528] Furthermore, the server analyzes the user's feedback data (thoughts and opinions provided in feedback forms and dialogues) using natural language processing technology. Again, the natural language processing tool mentioned above is used to extract the user's opinions and wishes. This allows for specific feedback such as "The level is too difficult" or "I like the new character."

[1529] Emotion analysis is performed using technology that analyzes the user's facial expressions and voice. Using facial recognition and voice analysis technologies (e.g., OpenCV and Keras), emotions are determined from the user's facial expressions and tone of voice. For example, furrowing the brow while playing a game can be interpreted as irritation, and a high-pitched voice as excitement.

[1530] Based on the results of the analysis, the server automatically generates new game elements and products using a generative AI. A generative model endpoint (e.g., TensorFlow, PyTorch) is used for generation. Specifically, if a user repeatedly fails a particular level, the generative AI generates a new level with adjusted enemy strength and number.

[1531] New game elements and generated product recommendations are delivered in real time from the server to the user's device using communication software (e.g., WebSocket, REST API). The device that receives the new information integrates it with the existing game data, so that the new elements are immediately reflected when the user plays again.

[1532] Finally, user feedback and emotional data are collected again and reflected in the next game element generation and product recommendations, thereby continuously providing an optimized experience for each individual user.

[1533] For example, if a user visits a virtual shopping mall, frequently browses products from a particular brand, and provides positive feedback, the generative AI will prioritize displaying new products from that brand.

[1534] Example prompt sentence:

[1535] User behavior data: browsing time, purchase history, feedback data

[1536] User emotion data: facial expressions, tone of voice

[1537] New product suggestions tailored to the user: prioritize displaying products from a specific brand

[1538] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1539] Step 1:

[1540] The device collects the user's gameplay data (e.g., distance traveled, number of battles, number of items used) in real time. It uses a data collection tool to collect user behavior data and sends that data to the server. The input is gameplay data, and the output is collected data.

[1541] Step 2:

[1542] The server analyzes the collected gameplay data. This analysis uses big data analysis tools and machine learning algorithms to identify user behavior patterns (e.g., being defeated by a specific enemy multiple times, frequently using a specific item). The input is the collected gameplay data, and the output is user behavior pattern data.

[1543] Step 3:

[1544] The server collects user feedback data and analyzes it using natural language processing technology. User feedback (e.g., "The level is too difficult" or "I like the new character") is collected as text and sentiment analysis is performed. The input is the feedback data, and the output is extracted opinions and wishes.

[1545] Step 4:

[1546] The server analyzes the user's facial expressions and voice to identify their emotions. Using facial recognition and voice analysis technology, it determines emotions (e.g., irritation, excitement) from the user's facial expressions and tone of voice. The input is the user's video and voice data, and the output is emotional data.

[1547] Step 5:

[1548] The server generates new game elements and products based on the analysis results. Using a generative AI model, it generates new game elements and products that adapt to the user (e.g., new levels with adjusted enemy strength and number). The input is the user's behavioral patterns, feedback data, and emotional data, and the output is the generated game elements and products.

[1549] Step 6:

[1550] The server distributes the generated game elements and products to the user's device. Using communication software, the generated new game elements and products are sent to the user's device in real time. The input is the generated game elements and products, and the output is the data distributed to the device.

[1551] Step 7:

[1552] The data received by the device is integrated with existing game data. New game elements and products are integrated with existing data so that they are immediately reflected in the user's game. The input is the distributed data, and the output is the updated game data.

[1553] Step 8:

[1554] Users use the updated games and products offered and provide feedback again, which allows the system to be continuously optimized. The input is feedback after use, and the output is new data for the next analysis.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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.

[1561] 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).

[1562] 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.

[1563] 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."

[1564] 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.

[1565] 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).

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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.

[1575] 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.

[1576] The following is further disclosed regarding the above embodiment.

[1577] (Claim 1)

[1578] means for collecting user gameplay data;

[1579] means for analyzing the collected game data to identify user behavior patterns and feedback;

[1580] A generation AI means for generating new game elements based on the analysis results;

[1581] means for delivering the generated game elements to a user's terminal;

[1582] A system including:

[1583] (Claim 2)

[1584] The system of claim 1 , wherein the new game elements include level designs, characters, and items.

[1585] (Claim 3)

[1586] 10. The system of claim 1, further comprising means for performing an ethical or moral check on the generated game elements.

[1587] "Example 1"

[1588] (Claim 1)

[1589] means for collecting user gameplay data;

[1590] means for analyzing the collected game data to identify user behavior patterns and feedback;

[1591] A generation AI means for generating new game elements based on the analysis results;

[1592] means for performing an ethical check on the generated game elements;

[1593] means for delivering the generated game elements to a user's terminal and integrating them into existing game data;

[1594] A system including:

[1595] (Claim 2)

[1596] 10. The system of claim 1, wherein the new game elements include level designs, characters, quests, and items.

[1597] (Claim 3)

[1598] 10. The system of claim 1, further comprising means for performing checks on the generated game elements to ensure appropriate expression and content.

[1599] "Application Example 1"

[1600] (Claim 1)

[1601] means for collecting user activity data;

[1602] means for analyzing the collected activity data to identify user behavior patterns and feedback;

[1603] A generation AI means for generating new experience elements based on the analysis results;

[1604] means for delivering the generated experience elements to a user's terminal;

[1605] means for displaying the generated experience elements on a terminal display;

[1606] A system including:

[1607] (Claim 2)

[1608] The system of claim 1 , wherein the new experience elements include product suggestions, interactive features, and promotions.

[1609] (Claim 3)

[1610] 10. The system of claim 1, further comprising means for performing an ethical or moral check on the generated experience element.

[1611] "Example 2: Combining Emotion Engines"

[1612] (Claim 1)

[1613] means for collecting user gameplay data;

[1614] means for analyzing the collected game data to identify user behavior patterns and feedback;

[1615] A generation AI means for generating new game elements based on the analysis results;

[1616] emotion analysis means for analyzing the user's emotional response;

[1617] means for delivering the generated game elements to a user's terminal;

[1618] A system including:

[1619] (Claim 2)

[1620] 10. The system of claim 1, wherein the new game elements include level designs, characters, items, and quests.

[1621] (Claim 3)

[1622] 10. The system of claim 1, further comprising means for performing an ethical or moral check on the generated game elements.

[1623] "Application example 2 when combining emotion engines"

[1624] (Claim 1)

[1625] means for collecting user gameplay data;

[1626] means for analyzing the collected game data to identify user behavior patterns and feedback;

[1627] A generation AI means for generating new game elements based on the analysis results;

[1628] means for delivering the generated game elements to a user's terminal;

[1629] Furthermore, an emotion analysis means for identifying emotions by analyzing the user's facial expressions and voice;

[1630] means for recommending products based on the emotion analysis results;

[1631] A system including:

[1632] (Claim 2)

[1633] 2. The system of claim 1, wherein the new game elements and recommended products include level designs, characters, and items.

[1634] (Claim 3)

[1635] 10. The system of claim 1, further comprising means for performing an ethical and moral check on the generated game elements and recommended products. [Explanation of symbols]

[1636] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting user gameplay data; means for analyzing the collected game data to identify user behavior patterns and feedback; A generation AI means for generating new game elements based on the analysis results; means for delivering the generated game elements to a user's terminal; A system including:

2. The system of claim 1 , wherein the new game elements include level designs, characters, and items.

3. The system of claim 1 further comprising means for performing an ethical or moral check on the generated game elements.

Images