system

Abstract

We provide the system. [Solution] Means of collecting user preference information, A means of generating an original story based on this preference information, A means of adjusting the story in real time based on user choices and reactions, A means of facilitating game progression through interactive dialogue with the user, A means of collecting user feedback after the game ends, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional mystery games and detective novel contents have a fixed storyline and ending, resulting in poor replayability and an inability to accommodate individual user preferences. Additionally, there have been many cases where the sense of immersion has decreased due to a lack of dynamic story development according to user choices and limitations in interactivity. Furthermore, there has been a lack of a mechanism to effectively utilize user feedback obtained after the game ends and reflect it in system improvements.

Means for Solving the Problems

[0005] This invention enables personalized experiences by providing a means for collecting user preference information and generating original stories based on it. Furthermore, it achieves dynamic game progression by including means for adjusting the story in real time based on user choices and reactions. In addition, it deepens user engagement through interactive dialogue and provides means for collecting feedback at the end of the game, allowing the obtained data to be analyzed and used to improve the system. As a result, users can enjoy a personalized and immersive experience, and replayability can be enhanced.

[0006] "User preference information" refers to data such as the genres, styles, and character preferences of each user.

[0007] An "original story" is a narrative newly created using generative AI based on the user's preferences, without relying on existing stories.

[0008] "Real-time adjustment" means that the system immediately receives user choices and reactions and changes the storyline on the spot.

[0009] "Interactive dialogue" is a two-way communication method in which users make choices and responses, which then drive the game or story forward.

[0010] "Collecting feedback" means compiling the opinions and impressions that users provide after finishing a game.

[0011] "Data analysis methods" refer to techniques for analyzing collected user feedback and game progress information to help improve the system in the future. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0015] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention relates to a system that dynamically generates stories based on user preferences and reactions, providing a personalized mystery game experience. The specific actions of each entity—the server, terminal, and user—are described below.

[0034] server

[0035] The server first receives information about the user's preferences and records it in a database. Based on this information, it uses generative AI to create individual game stories. This includes a process of designing characters and plots based on the user's preferred genres and settings. As the story progresses, the server analyzes the user's choices and reactions in real time and updates the data necessary to adjust the story development. After the game ends, feedback is collected and used to generate the next story and improve the system.

[0036] terminal

[0037] The terminal functions as the user interface. After the user logs in, it displays a screen for entering preference information. It visualizes and presents the generated story and choices to the user. It displays interactive puzzles and conversational prompts, and relays user input to the server. Finally, it displays a feedback form along with the ending to collect the user's thoughts on their game experience.

[0038] User

[0039] Users first log in using their device and input their preferences and expectations. Within the displayed story, they influence the plot's progression by making choices. Because these choices alter how the story unfolds, users can enjoy an interactive experience where their decisions directly impact the outcome. Furthermore, after completing the game, they can write their impressions and suggestions for improvement in a feedback form.

[0040] For example, if a user enters "suspense" as their preference, the server generates a story plotted around a disappearance in a specific city. During the user's investigation, the device presents evidence and prompts the user to search for the next clue. Because the truth of the case unfolds differently depending on the user's choices, there are new discoveries with each game experience. Finally, user feedback is collected on the server and used to develop future stories.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives the user's login information and performs authentication. If authentication is successful, the server retrieves the user's profile information and returns it to the device.

[0044] Step 2:

[0045] The device displays a screen where the user can input their mystery genre and preferences. The user selects their preferences and sends that data to the server.

[0046] Step 3:

[0047] The server uses a generative AI to construct personalized stories based on user preferences. This includes the automatic generation of character settings and story plots.

[0048] Step 4:

[0049] The server sends the initial plot points of the generated story to the terminal, which then presents them to the user in a visualized form. The user reads the presented prologue and gets a feel for the game's atmosphere.

[0050] Step 5:

[0051] The device displays options to the user and prompts them to choose an action. The user makes a selection and sends that selection to the server.

[0052] Step 6:

[0053] The server dynamically adjusts the story progression based on the selection information received from the user. It generates new events and scenes according to the selection results and sends the updated story to the device.

[0054] Step 7:

[0055] The device displays new scenes and character reactions to the user, prompting them to take their next action or make a choice. The user becomes more involved in the storytelling and progresses through the game.

[0056] Step 8:

[0057] When a player reaches the game's ending, the server records their play history and sends a feedback form to their device. Users can then fill in their comments and suggestions for improvement.

[0058] Step 9:

[0059] The server receives feedback information and analyzes user comments. This information is stored in a database to be used for system improvements and designing future stories.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] There is a growing need to cater to the diverse preferences of today's users and provide personalized virtual experiences through immersive interactions. However, conventional systems have struggled to generate and adjust stories that fully reflect user preferences in real time. Furthermore, there has been a lack of methods to effectively utilize user feedback and optimize the entire system.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for collecting user preference information using an information device, means for generating an original story using a generative model based on this preference information, and means for analyzing user choices and reactions to adjust the story in real time. This enables the provision of a personalized story experience and continuous system improvement that reflects user feedback.

[0065] "User preference information" refers to information about users' interests, preferences, and expectations, and is the data that forms the basis for story generation.

[0066] "Information device" is a general term for hardware or software used to receive and process user input.

[0067] A "generative model" is an algorithm or program that uses machine learning or other methods to generate original stories based on user preference information.

[0068] A "story" refers to an entire narrative created based on a specific theme or setting, encompassing a series of events and incidents, including characters and plot.

[0069] A "visual medium" is a means of displaying visual information, such as images and videos, to enable an interactive experience with the user.

[0070] "Interaction" refers to the two-way communication that a user has with a system, including choices and responses.

[0071] "Information analysis means" refers to methods or techniques for analyzing progress and feedback obtained from users and deriving insights necessary for improving the entire system.

[0072] This invention relates to a system that generates personalized stories tailored to user preferences and provides an interactive experience. The roles of the server, terminal, and user, as well as the hardware and software used, are described below.

[0073] server

[0074] The server processes preference information sent by the user and uses this information to generate stories using a generative AI model. By recording and analyzing preference information using a database, a plot that matches the user's tastes is designed. The generative AI model uses specific prompts such as, "If the user's preference is suspense, what would be an appropriate plot?" to reflect the genre specified by the user. The server's main function is to dynamically adjust the story by analyzing the user's choices and reactions in real time, according to the generated story.

[0075] terminal

[0076] The terminal primarily functions as a user interface. Upon user login, a screen is displayed to collect preference information, and user input is sent to the server. The server then visualizes and presents stories and choices to the user. The terminal assists the user in making choices by displaying interactive puzzles and conversational prompts, and relays this data to the server. Finally, at the end of the virtual experience, a feedback screen is displayed to collect the user's thoughts on the experience.

[0077] User

[0078] Users input their preferences through their device and influence the flow of the story by selecting options provided in the generated story. Because user choices significantly impact the story's progression, they can dynamically enjoy how their choices affect the narrative. At the end of the experience, they can provide feedback on their game experience and suggestions for system improvements through a feedback form. This allows users not only to interactively engage but also to contribute to future system improvements.

[0079] The system, configured in this way, provides new story experiences tailored to the individual preferences of users and is continuously optimized by utilizing user feedback.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The user logs into the system using a terminal. The terminal displays an interface for collecting preference information from the user and prompts the user for input. The input preference information, which includes elements of the user's interests and expectations, is sent to the server. The output at this stage is the user's preference information.

[0083] Step 2:

[0084] The server receives user preference information sent from the terminal and stores it in a database. Based on this information, the server inputs appropriate prompts into the generative AI model and begins the process of generating a personalized story. Specifically, it uses a prompt such as, "If the user's preference is suspense, what would be an appropriate plot?" The output at this stage is an outline of a story tailored to the user.

[0085] Step 3:

[0086] The server meticulously constructs the story outline obtained from the generative AI model and sets up multiple choices for the user to select. The story and choices are designed to change dynamically based on the user's choices and reactions. The output at this stage is the specific story and choices.

[0087] Step 4:

[0088] The device provides the user with a story and choices from the server. The story is visually represented, and the choices are displayed in a format that the user can select. The user chooses from the presented options, influencing the progression of the story. The user's choices are sent back to the server by the device. The output at this stage is the user's selection information.

[0089] Step 5:

[0090] The server analyzes the user's choices and adjusts the story's progression in real time. This adjusted story is then sent back to the device as needed, providing the user with updated information. This allows the user to experience a dynamically changing story. The output at this stage is the adjusted story.

[0091] Step 6:

[0092] Once the story is complete, the device displays the ending and provides the user with a feedback form. The user writes their impressions and suggestions for improvement and sends them to the server via the device. The output at this stage is the user's feedback.

[0093] Step 7:

[0094] The server analyzes the collected feedback and uses it to generate future stories and improve the system. This process takes user opinions and progress into consideration, leading to system optimization for the next version. The output at this stage provides design insights for the improved system.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] Providing interactive game experiences using personalized storylines requires real-time content generation and delivery tailored to user preferences. However, conventional systems lack the ability to dynamically adjust storylines based on user choices and support a variety of devices, making it difficult to improve user immersion and satisfaction.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes means for collecting user preference information, means for generating an original story, means for distributing the generated story through an information and communication network, and means for providing audio and augmented reality representations using multiple output devices. This enables real-time story adjustment based on user choices and reactions, and an immersive interactive experience using various devices.

[0100] "Means for collecting user preference information" refers to methods for identifying users' interests and preferences using information processing equipment and storing them as data.

[0101] "Methods for generating original stories" refers to methods for creating personalized narratives using generative AI based on user preference information.

[0102] "A means of adjusting the story in real time" refers to a function that dynamically changes the progression of the story on the spot in response to the user's choices and reactions.

[0103] "Means of facilitating game progression through interactive dialogue" refers to methods of advancing the story's development while exchanging information bi-directionally with the user.

[0104] "Methods for collecting feedback" refer to methods for gathering and analyzing user feedback and experiences to use in system improvement.

[0105] "Means of distributing generated stories through information and communication networks" refers to methods of providing generated stories to users using communication networks such as the internet.

[0106] "Means of providing audio and augmented reality representations using multiple output devices" refers to methods that utilize multiple devices such as speakers and displays to provide users with a sense of presence using audio and AR technology.

[0107] This invention provides a system that dynamically generates and delivers personalized content based on user preferences. It embodies a mechanism that adjusts the story in real time through interaction between the server, terminal, and user, thereby realizing an immersive gaming experience.

[0108] server

[0109] The server first collects user preference information and stores it in a database. Using Python and the generative AI TENSORFLOW® model, it creates personalized stories for each user. This includes a story plot creation process based on prompts. As the story progresses, the server analyzes user choices and reactions and adjusts the story in real time using Node.js. It delivers the story including audio and augmented reality elements, and after the game ends, it collects user feedback to help improve future stories.

[0110] terminal

[0111] The device functions as an interface for user access. Using the React Native framework, users input their preferences. It displays stories created by generative AI, and the user's choices are immediately reflected on the server. The device also provides users with visual and auditory experiences using voice and augmented reality technologies. Finally, it presents the user with a feedback form and sends the feedback to the server.

[0112] User

[0113] Users interact with the system through their devices. By inputting their interests and making choices within the presented story, users can influence the progression of the narrative. Because the story unfolds in different directions depending on the choices, users can enjoy new discoveries each time. For example, a prompt such as "What will the user discover inside the pyramid?" might lead to a mystery set in Egypt. After the game ends, users provide feedback to the system about their experience, which helps in future improvements.

[0114] In this way, users can enjoy a different story each time, making it possible to provide a highly customized and interactive gaming experience.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server receives preference information from users. The input is preference information provided by the user via their terminal, and this is stored in the database. The server then formats the preference information and registers it as an entry in the database so that it can be used for data inference.

[0118] Step 2:

[0119] The server generates prompts based on stored preference information and creates personalized stories using a generative AI model (TensorFlow). The input here is preference information retrieved from the database, which is converted into prompts and passed to the AI ​​model. The AI ​​model analyzes these prompts and generates a story structure suitable for the user. The output is the suggested story.

[0120] Step 3:

[0121] The server sends the generated story to the terminal via the information and communication network. The terminal receives this story and displays the plot and choices on the user interface. The input is the generated story, and the output is the choices displayed on the GUI.

[0122] Step 4:

[0123] The user selects an action based on the choices presented in the story. The device then returns the user's chosen option to the server. The input is the user's selection, which the device sends to the server as data.

[0124] Step 5:

[0125] The server adjusts the story in real time based on the user's selections and sends the expanded story back to the terminal. The input here is the user's selection, which is the branching point of the story generated in step 2. The output is the new story path.

[0126] Step 6:

[0127] The device displays the updated story received from the server back to the user, enhancing immersion with audio and augmented reality features. The input is the updated story information, and the output is the visual and auditory experience.

[0128] Step 7:

[0129] After reaching the end of the game, the device displays a feedback form to the user, allowing them to enter their thoughts and suggestions for improvement. This input constitutes user feedback, which the device then transmits to the server.

[0130] Step 8:

[0131] The server analyzes the collected feedback to help generate future stories and improve the system. The input is user feedback data, which is then analyzed and output as design guidelines for the system. This feedback allows the system to provide stories that are more tailored to individual users in the future.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] This invention relates to a personalized mystery game system that incorporates an emotion engine to recognize user emotions. The specific operations of the server, terminal, and user are described below.

[0134] server

[0135] The server is responsible for the core processing of this system. First, it receives user preference information, and the generating AI creates an original story based on this information. After the story is generated, the emotion engine performs initial setup to recognize the user's emotional state. It receives user choices and reactions in real time and adjusts the story's progression by analyzing the emotional data collected by the emotion engine. Furthermore, after the game ends, it collects user feedback, records it in a database along with the emotional data, and uses it to improve the system.

[0136] terminal

[0137] The device provides the user interface. After logging in, it displays a preference input screen, allowing the user to enter their preferences. During gameplay, it presents the generated story and choices visually and audibly. The device is equipped with an emotion engine that analyzes the user's facial expressions and voice tone in real time to evaluate their emotions and sends this data to the server. The emotional information obtained by the emotion engine is used for feedback to improve game progression.

[0138] User

[0139] Users participate in the game via their devices. First, they log in and enter their individual preferences on a preference information input screen presented by the system. After the game starts, users influence the story's progression by choosing from the options presented. Based on their choices, the user's facial expressions and voice are analyzed by an emotion engine, and the story is adjusted in real time. In particular, if the system detects that the user is surprised or enjoying themselves, the story changes accordingly. After the game ends, users can provide their experience and feedback through a feedback form, and this information is used to improve future game experiences.

[0140] For example, if a user's facial expression indicates anxiety after selecting an option, the server will use this information to adjust the story and guide the plot in a direction that makes the user feel at ease. Conversely, if a joyful expression is detected, the story will progress by adding suspense elements to provide further excitement. This real-time story development based on the user's emotions can provide a deeper sense of immersion.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The server authenticates users when they log in to their devices. The end user enters their email address and password, and the server verifies this information. Upon successful authentication, the server retrieves the user's profile and past preference data from the database and sends it back to the device.

[0144] Step 2:

[0145] The device displays the user's preference settings screen. The user selects their preferred mystery genre and character settings, and sends this information to the server via the device. The server updates its database based on the selected settings.

[0146] Step 3:

[0147] The server uses a generative AI to create an original story based on preference information. The AI ​​generates a plot and character settings based on the user's preferences and constructs a series of scenes. This story information is then sent to the terminal.

[0148] Step 4:

[0149] The device displays the prologue and introduction to the generated story. As the game starts, the emotion engine activates and prepares to detect the user's facial expressions and voice tone in real time.

[0150] Step 5:

[0151] The user selects the next action based on the choices displayed during the story progression. This selection is sent to the server via the device. Simultaneously, the user's facial expressions and voice are analyzed by an emotion engine on the device, and this emotion data is sent to the server.

[0152] Step 6:

[0153] The server dynamically adjusts the story's progression based on user selection information and emotional data. For example, if the user indicates tension, it generates a scenario to provide a sense of reassurance. The updated story is then sent to the device.

[0154] Step 7:

[0155] The device displays new scenes and altered character reactions sent from the server to the user. The user makes further choices based on these interactive changes, continuing the story experience.

[0156] Step 8:

[0157] Upon reaching the ending, the server generates a form for collecting feedback along with the user's gameplay data. The device then displays this form to the user, allowing them to fill in their thoughts and suggestions.

[0158] Step 9:

[0159] Users submit their opinions on the game experience through a feedback form on their device. The server receives this information, stores it in a database, and uses it to improve the system and generate new storylines in the future.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0162] Traditional interactive game systems have a static user experience, making it difficult to develop flexible storylines that respond to user emotions and preferences. Furthermore, monotonous story progression that disregards user choices and emotions reduces immersion and lowers user satisfaction.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes means for acquiring user preference information, means for forming an original story using a generative AI model, and means for dynamically adjusting the story in real time, equipped with an emotion recognition function for analyzing the user's facial expressions and voice tone. This makes it possible to dynamically change the story based on the user's emotional state and preferences, providing a deeper sense of immersion.

[0165] "User preference information" refers to individual information about themes and styles that users are interested in, and serves as foundational data for personalizing the gaming experience.

[0166] A "generative AI model" is an artificial intelligence technology used to automatically generate stories and creative content based on user preference information.

[0167] "Emotion recognition functionality" is a technology that analyzes the user's facial expressions and tone of voice to determine their emotional state in real time.

[0168] "Interactive dialogue" is a two-way communication method that allows users to influence the story through game choices and receive feedback in real time.

[0169] "Feedback" refers to information provided by users after a game ends, sharing their thoughts and opinions about the experience, which is then used to improve future game experiences and systems.

[0170] "Immersion" refers to a state in which users become deeply immersed in a game, to the point of forgetting the real world and becoming completely absorbed in the experience.

[0171] This invention is a highly personalized mystery game system that users can enjoy through an interface. This system consists of a server, a terminal, and a user.

[0172] The server is responsible for the system's central processing. Based on preference information received from the user, it generates an original story using a "generative AI model" (e.g., general language modeling technology). During this process, the prompt message will look like this: "Generate the next story development. This user's preference is 'fantasy,' and their emotion data indicates 'fun.'" This ensures that the generated story provides a unique experience for each user. The server also initializes an engine with emotion recognition capabilities, analyzing the user's emotion data to dynamically adjust the story's progression. The server aggregates this data, and after the game ends, it saves user feedback to a database to use for system improvement.

[0173] The terminal serves as the user interface. Upon user login, the terminal displays a preference input screen to collect user preferences. This information is used to present stories and choices through visual and auditory media. The terminal is equipped with an emotion recognition engine that enables real-time sentiment analysis. This emotion engine analyzes the user's facial expressions and tone of voice and transmits that data to the server.

[0174] Users participate in the game via their devices and become part of the story. They first log in and enter preference information requested by the system. As the game progresses, they choose from presented options, and their choices, along with their facial expressions and tone of voice, directly influence the story's development. When facial expressions or voice convey emotions such as anxiety or joy, the system dynamically adjusts the story based on that data, providing users with a deeply immersive experience.

[0175] For example, if a user selects an option and expresses anxiety, the server adjusts the story to generate a reassuring narrative. Conversely, if positive emotions are detected, the plot develops into an exciting one. This allows the story to flexibly change according to the user's emotional state, creating a more engaging experience.

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1: Enter user preference information

[0178] When a user logs in, the terminal displays a preference information input screen. Through this screen, the user enters their interests, preferred themes, and story styles. The entered information is collected as digital data and sent to the server. At this stage, data regarding the user's preferences is delivered to the server as output.

[0179] Step 2: Generating the Story

[0180] The server receives user preference information as input. Based on this information, it uses a generative AI model to generate an original story. Specifically, it creates prompt statements to instruct the AI ​​to generate a story. For example, a prompt such as "Generate the next story development. This user's preference is 'fantasy,' and their emotion data indicates 'fun'" is used as input, and the generated story is obtained as output.

[0181] Step 3: Initial setup of the emotion engine

[0182] After receiving the generated story, the server performs the initial setup of its emotion recognition function. This includes configuring sensors and algorithms for analyzing the user's emotion data. Using the story and the system's initial setup data as input, the output is a ready state.

[0183] Step 4: Start the game

[0184] The device presents the user with a generated story and associated choices. This process displays story-based text, images, and audio, allowing the user to choose how to interact. The user's choices are received as input, and their actions and decisions are passed on to the next step as output.

[0185] Step 5: Collecting user emotions and reactions

[0186] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time. It uses the user's facial expression data and voice data acquired through the camera and microphone as input, generates emotional state data as output, and sends it to the server.

[0187] Step 6: Dynamically adjust the story

[0188] The server analyzes emotional state data received from the emotion engine as input. Based on the results, it dynamically adjusts the flow of the story. For example, if the user expresses anxiety, it prioritizes a reassuring development and generates an updated story as output.

[0189] Step 7: End the game and collect feedback

[0190] After completing a game, users submit their experiences and opinions through a feedback form. Based on this input, the server collects data on the overall success and areas for improvement of the game. As output, user feedback data is stored in a database and used to improve the system in the future.

[0191] (Application Example 2)

[0192] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0193] In recent years, there has been a growing demand for digital content that provides experiences tailored to individual user preferences. However, conventional systems have struggled to generate stories that reflect users' emotions in real time, resulting in insufficient immersion. Therefore, a system is needed that enables dynamic story development using emotion recognition.

[0194] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0195] In this invention, the server includes means for collecting user preference information, means for adjusting the story in real time based on the user's choices and reactions, and means for recognizing the user's emotions and further adjusting the story's progression based on those emotions. This enables a personalized story development that directly reflects the user's emotions.

[0196] "User preference information" refers to data that shows each user's individual preferences and interests, and is necessary information to provide personalized experiences.

[0197] "Methods for generating original stories" refers to a system that automatically creates unique storylines based on collected user preference information.

[0198] A "means of adjusting the story in real time" refers to a system that has the functionality to dynamically change the development of the story on the spot in response to the user's choices and reactions.

[0199] A "means of recognizing user emotions" refers to a system equipped with technology to analyze a user's facial expressions, tone of voice, etc., and determine their emotional state.

[0200] "Interactive dialogue with the user" refers to a two-way exchange where the system provides appropriate feedback based on the user's choices and responses.

[0201] "Means of facilitating the progression of the experience" are mechanisms that support the progression of the story so that users can experience it smoothly and immersively.

[0202] A "means of collecting feedback" refers to a system that has the function of collecting opinions and impressions from users after their experience.

[0203] The server has the function of collecting user preference information. Based on this information, an AI model can automatically generate an original story. After the story is generated, the server uses emotion recognition technology to collect data on the user's choices and reactions, and analyzes this in real time to dynamically adjust the story's progression. An emotion engine is used to adjust the story, branching the plot according to the user's emotions. After the game ends, data is accumulated to improve the entire system based on the user's emotional data and feedback.

[0204] The device presents the generated story and choices to the user visually and audibly through its user interface. The device is equipped with a camera and microphone, and incorporates an emotion engine that analyzes facial expressions and voice tone to evaluate the user's emotions in real time. This data is sent to a server and used to advance the story.

[0205] Users log in and input their preferences through the device's interface. During the game experience, users influence the story's progression through the choices presented, and their emotional data, such as facial expressions and voice, is reflected in the game in real time, providing an interactive experience. For example, when a user chooses either "adventure" or "romance," if emotions such as surprise or joy are detected, the plot unfolds accordingly.

[0206] An example of a prompt message would be: "If you were going on a university club trip, what kind of story would you want to experience? Are you looking for adventure, or do you want a heartwarming encounter? To make the experience even more exciting, we will adjust the scenario based on your facial expressions."

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server receives preference information from the user's device. This information is sent in XML or JSON format and contains elements that indicate the user's preferences. The server analyzes this data and prepares it for input into the generating AI model.

[0210] Step 2:

[0211] The server uses a generative AI model to generate an original story from the received preference information. The AI ​​model receives the user's preferences as prompts and generates a storyline. As output, the story's initial settings and plot information are generated and sent to the user's terminal.

[0212] Step 3:

[0213] The device presents the received narrative information to the user visually and audibly. The user is presented with multiple choices, each leading to a different development in the story. This information is displayed via the user interface, and the user's selection is entered.

[0214] Step 4:

[0215] The user selects one of the presented options and inputs it as selection information into the device. This choice will influence the progression of the story.

[0216] Step 5:

[0217] The device uses its camera and microphone to collect user facial and voice data. This data is analyzed through the device's emotion engine to assess the user's real-time emotional state.

[0218] Step 6:

[0219] Emotional data and selection information from the device are sent to the server. Based on this data, the server performs calculations to readjust the story plot. The adjusted plot incorporates changes that respond to the user's emotions, generating a new story development.

[0220] Step 7:

[0221] The revised plot is sent back to the device, presenting the user with a new narrative development. This process is repeated, resulting in an interactive experience based on the user's emotions.

[0222] Step 8:

[0223] After completing the story experience, users enter their opinions and impressions into a feedback form. This information is sent from the device to the server and stored in a database for system improvement.

[0224] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0225] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0226] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0227] [Second Embodiment]

[0228] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0229] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0230] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0231] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0232] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0233] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0234] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0235] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0236] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0237] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0238] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0239] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0240] This invention relates to a system that dynamically generates stories based on user preferences and reactions, providing a personalized mystery game experience. The specific actions of each entity—the server, terminal, and user—are described below.

[0241] server

[0242] The server first receives information about the user's preferences and records it in a database. Based on this information, it uses generative AI to create individual game stories. This includes a process of designing characters and plots based on the user's preferred genres and settings. As the story progresses, the server analyzes the user's choices and reactions in real time and updates the data necessary to adjust the story development. After the game ends, feedback is collected and used to generate the next story and improve the system.

[0243] terminal

[0244] The terminal functions as the user interface. After the user logs in, it displays a screen for entering preference information. It visualizes and presents the generated story and choices to the user. It displays interactive puzzles and conversational prompts, and relays user input to the server. Finally, it displays a feedback form along with the ending to collect the user's thoughts on their game experience.

[0245] User

[0246] Users first log in using their device and input their preferences and expectations. Within the displayed story, they influence the plot's progression by making choices. Because these choices alter how the story unfolds, users can enjoy an interactive experience where their decisions directly impact the outcome. Furthermore, after completing the game, they can write their impressions and suggestions for improvement in a feedback form.

[0247] For example, if a user enters "suspense" as their preference, the server generates a story plotted around a disappearance in a specific city. During the user's investigation, the device presents evidence and prompts the user to search for the next clue. Because the truth of the case unfolds differently depending on the user's choices, there are new discoveries with each game experience. Finally, user feedback is collected on the server and used to develop future stories.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] The server receives the user's login information and performs authentication. If authentication is successful, the server retrieves the user's profile information and returns it to the device.

[0251] Step 2:

[0252] The device displays a screen where the user can input their mystery genre and preferences. The user selects their preferences and sends that data to the server.

[0253] Step 3:

[0254] The server uses a generative AI to construct personalized stories based on user preferences. This includes the automatic generation of character settings and story plots.

[0255] Step 4:

[0256] The server sends the initial plot points of the generated story to the terminal, which then presents them to the user in a visualized form. The user reads the presented prologue and gets a feel for the game's atmosphere.

[0257] Step 5:

[0258] The device displays options to the user and prompts them to choose an action. The user makes a selection and sends that selection to the server.

[0259] Step 6:

[0260] The server dynamically adjusts the story progression based on the selection information received from the user. It generates new events and scenes according to the selection results and sends the updated story to the device.

[0261] Step 7:

[0262] The device displays new scenes and character reactions to the user, prompting them to take their next action or make a choice. The user becomes more involved in the storytelling and progresses through the game.

[0263] Step 8:

[0264] When a player reaches the game's ending, the server records their play history and sends a feedback form to their device. Users can then fill in their comments and suggestions for improvement.

[0265] Step 9:

[0266] The server receives feedback information and analyzes user comments. This information is stored in a database to be used for system improvements and designing future stories.

[0267] (Example 1)

[0268] Next, we will describe Example 1. 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."

[0269] There is a growing need to cater to the diverse preferences of today's users and provide personalized virtual experiences through immersive interactions. However, conventional systems have struggled to generate and adjust stories that fully reflect user preferences in real time. Furthermore, there has been a lack of methods to effectively utilize user feedback and optimize the entire system.

[0270] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0271] In this invention, the server includes means for collecting user preference information using an information device, means for generating an original story using a generative model based on this preference information, and means for analyzing user choices and reactions to adjust the story in real time. This enables the provision of a personalized story experience and continuous system improvement that reflects user feedback.

[0272] "User preference information" refers to information about users' interests, preferences, and expectations, and is the data that forms the basis for story generation.

[0273] "Information device" is a general term for hardware or software used to receive and process user input.

[0274] A "generative model" is an algorithm or program that uses machine learning or other methods to generate original stories based on user preference information.

[0275] A "story" refers to an entire narrative created based on a specific theme or setting, encompassing a series of events and incidents, including characters and plot.

[0276] A "visual medium" is a means of displaying visual information, such as images and videos, to enable an interactive experience with the user.

[0277] "Interaction" refers to the two-way communication that a user has with a system, including choices and responses.

[0278] "Information analysis means" refers to methods or techniques for analyzing progress and feedback obtained from users and deriving insights necessary for improving the entire system.

[0279] This invention relates to a system that generates personalized stories according to user preferences and provides an interactive experience. Below, the roles of the server, terminal, and user, as well as the hardware and software used, will be described.

[0280] Server

[0281] The server is responsible for processing the preference information sent from the user and generating stories using a generated AI model based on this. By recording and analyzing the preference information using a database, a plot that matches the user's taste is designed. In the generated AI model, in order to reflect the genre specified by the user, a specific prompt sentence such as "If the user's preference is suspense, what is an appropriate plot?" is used. The main function of the server is to analyze the user's selections and reactions in real time according to the generated story and dynamically adjust the story.

[0282] Terminal

[0283] The terminal mainly functions as a user interface. A screen for collecting preference information is displayed when the user logs in, and the input from the user is sent to the server. Then, the story and options sent from the server are visualized and presented to the user. The terminal displays interactive puzzles and dialogue prompts to assist the user in making selections and relays the data to the server. Also, at the end of the virtual experience, a feedback screen is displayed to collect the user's feelings about the experience.

[0284] User

[0285] The user inputs their preferences through the terminal and selects options provided in the generated story, thereby influencing the flow of the story. Since the user's choices significantly affect the progression of the story, they can dynamically enjoy how their own choices impact the narrative. Additionally, at the end of the experience, the user provides feedback on the game experience and suggestions for the system through a feedback form. Through this, the user not only participates interactively but also can contribute to future system improvements.

[0286] The system configured as such provides a new story experience tailored to the individual preferences of the user and is continuously optimized by leveraging feedback from the user.

[0287] The flow of the specific process in Example 1 will be described using FIG. 11.

[0288] Step 1:

[0289] The user logs in to the system using the terminal. The terminal displays an interface for collecting preference information from the user and prompts the user for input. The input preference information includes the user's interests and expected elements and is sent to the server. The output at this stage is the user's preference information.

[0290] Step 2:

[0291] The server receives the user's preference information sent from the terminal and stores it in the database. Based on this information, the server inputs an appropriate prompt sentence into the generation AI model and starts the process of generating an individualized story. Specifically, a prompt such as "If the user's preference is suspense, what is an appropriate plot?" is used. The output at this stage is an outline of a story suitable for the user.

[0292] Step 3:

[0293] The server meticulously constructs the story outline obtained from the generative AI model and sets up multiple choices for the user to select. The story and choices are designed to change dynamically based on the user's choices and reactions. The output at this stage is the specific story and choices.

[0294] Step 4:

[0295] The device provides the user with a story and choices from the server. The story is visually represented, and the choices are displayed in a format that the user can select. The user chooses from the presented options, influencing the progression of the story. The user's choices are sent back to the server by the device. The output at this stage is the user's selection information.

[0296] Step 5:

[0297] The server analyzes the user's choices and adjusts the story's progression in real time. This adjusted story is then sent back to the device as needed, providing the user with updated information. This allows the user to experience a dynamically changing story. The output at this stage is the adjusted story.

[0298] Step 6:

[0299] Once the story is complete, the device displays the ending and provides the user with a feedback form. The user writes their impressions and suggestions for improvement and sends them to the server via the device. The output at this stage is the user's feedback.

[0300] Step 7:

[0301] The server analyzes the collected feedback and uses it to generate future stories and improve the system. This process takes user opinions and progress into consideration, leading to system optimization for the next version. The output at this stage provides design insights for the improved system.

[0302] (Application Example 1)

[0303] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0304] In providing an interactive game experience using individualized stories, real-time content generation and distribution according to user preferences are required. However, in conventional systems, there is a problem that dynamic story adjustment according to user selection and support for various devices are insufficient, making it difficult to improve user immersion and satisfaction.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0306] In this invention, the server includes means for collecting user preference information, means for generating an original story, means for distributing the generated story through an information communication network, and means for providing voice and augmented reality expressions using a plurality of output devices. Thereby, real-time story adjustment based on user selection and reaction and an immersive interactive experience using various devices become possible.

[0307] The "means for collecting user preference information" is a method for identifying the interests and concerns of users using an information processing device and storing them as data.

[0308] The "means for generating an original story" is a method for creating an individualized story by utilizing generative AI based on user preference information.

[0309] The "means for adjusting the story in real time" is a function for dynamically changing the progress of the story on the spot according to user selection and reaction.

[0310] "Means of facilitating game progression through interactive dialogue" refers to methods of advancing the story's development while exchanging information bi-directionally with the user.

[0311] "Methods for collecting feedback" refer to methods for gathering and analyzing user feedback and experiences to use in system improvement.

[0312] "Means of distributing generated stories through information and communication networks" refers to methods of providing generated stories to users using communication networks such as the internet.

[0313] "Means of providing audio and augmented reality representations using multiple output devices" refers to methods that utilize multiple devices such as speakers and displays to provide users with a sense of presence using audio and AR technology.

[0314] This invention provides a system that dynamically generates and delivers personalized content based on user preferences. It embodies a mechanism that adjusts the story in real time through interaction between the server, terminal, and user, thereby realizing an immersive gaming experience.

[0315] server

[0316] The server first collects user preference information and stores it in a database. Using Python and TensorFlow models, a generative AI, it creates personalized stories for each user. This includes a process of creating a story plot based on prompts. As the story progresses, the server analyzes the user's choices and reactions and adjusts the story in real time using Node.js. It delivers the story including audio and augmented reality elements, and after the game ends, it collects user feedback to help improve future stories.

[0317] terminal

[0318] The device functions as an interface for user access. Using the React Native framework, users input their preferences. It displays stories created by generative AI, and the user's choices are immediately reflected on the server. The device also provides users with visual and auditory experiences using voice and augmented reality technologies. Finally, it presents the user with a feedback form and sends the feedback to the server.

[0319] User

[0320] Users interact with the system through their devices. By inputting their interests and making choices within the presented story, users can influence the progression of the narrative. Because the story unfolds in different directions depending on the choices, users can enjoy new discoveries each time. For example, a prompt such as "What will the user discover inside the pyramid?" might lead to a mystery set in Egypt. After the game ends, users provide feedback to the system about their experience, which helps in future improvements.

[0321] In this way, users can enjoy a different story each time, making it possible to provide a highly customized and interactive gaming experience.

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The server receives preference information from users. The input is preference information provided by the user via their terminal, and this is stored in the database. The server then formats the preference information and registers it as an entry in the database so that it can be used for data inference.

[0325] Step 2:

[0326] The server generates prompts based on stored preference information and creates personalized stories using a generative AI model (TensorFlow). The input here is preference information retrieved from the database, which is converted into prompts and passed to the AI ​​model. The AI ​​model analyzes these prompts and generates a story structure suitable for the user. The output is the suggested story.

[0327] Step 3:

[0328] The server sends the generated story to the terminal via the information and communication network. The terminal receives this story and displays the plot and choices on the user interface. The input is the generated story, and the output is the choices displayed on the GUI.

[0329] Step 4:

[0330] The user selects an action based on the choices presented in the story. The device then returns the user's chosen option to the server. The input is the user's selection, which the device sends to the server as data.

[0331] Step 5:

[0332] The server adjusts the story in real time based on the user's selections and sends the expanded story back to the terminal. The input here is the user's selection, which is the branching point of the story generated in step 2. The output is the new story path.

[0333] Step 6:

[0334] The device displays the updated story received from the server back to the user, enhancing immersion with audio and augmented reality features. The input is the updated story information, and the output is the visual and auditory experience.

[0335] Step 7:

[0336] After reaching the end of the game, the device displays a feedback form to the user, allowing them to enter their thoughts and suggestions for improvement. This input constitutes user feedback, which the device then transmits to the server.

[0337] Step 8:

[0338] The server analyzes the collected feedback to help generate future stories and improve the system. The input is user feedback data, which is then analyzed and output as design guidelines for the system. This feedback allows the system to provide stories that are more tailored to individual users in the future.

[0339] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0340] This invention relates to a personalized mystery game system that incorporates an emotion engine to recognize user emotions. The specific operations of the server, terminal, and user are described below.

[0341] server

[0342] The server is responsible for the core processing of this system. First, it receives user preference information, and the generating AI creates an original story based on this information. After the story is generated, the emotion engine performs initial setup to recognize the user's emotional state. It receives user choices and reactions in real time and adjusts the story's progression by analyzing the emotional data collected by the emotion engine. Furthermore, after the game ends, it collects user feedback, records it in a database along with the emotional data, and uses it to improve the system.

[0343] terminal

[0344] The device provides the user interface. After logging in, it displays a preference input screen, allowing the user to enter their preferences. During gameplay, it presents the generated story and choices visually and audibly. The device is equipped with an emotion engine that analyzes the user's facial expressions and voice tone in real time to evaluate their emotions and sends this data to the server. The emotional information obtained by the emotion engine is used for feedback to improve game progression.

[0345] User

[0346] Users participate in the game via their devices. First, they log in and enter their individual preferences on a preference information input screen presented by the system. After the game starts, users influence the story's progression by choosing from the options presented. Based on their choices, the user's facial expressions and voice are analyzed by an emotion engine, and the story is adjusted in real time. In particular, if the system detects that the user is surprised or enjoying themselves, the story changes accordingly. After the game ends, users can provide their experience and feedback through a feedback form, and this information is used to improve future game experiences.

[0347] For example, if a user's facial expression indicates anxiety after selecting an option, the server will use this information to adjust the story and guide the plot in a direction that makes the user feel at ease. Conversely, if a joyful expression is detected, the story will progress by adding suspense elements to provide further excitement. This real-time story development based on the user's emotions can provide a deeper sense of immersion.

[0348] The following describes the processing flow.

[0349] Step 1:

[0350] The server authenticates users when they log in to their devices. The end user enters their email address and password, and the server verifies this information. Upon successful authentication, the server retrieves the user's profile and past preference data from the database and sends it back to the device.

[0351] Step 2:

[0352] The device displays the user's preference settings screen. The user selects their preferred mystery genre and character settings, and sends this information to the server via the device. The server updates its database based on the selected settings.

[0353] Step 3:

[0354] The server uses a generative AI to create an original story based on preference information. The AI ​​generates a plot and character settings based on the user's preferences and constructs a series of scenes. This story information is then sent to the terminal.

[0355] Step 4:

[0356] The device displays the prologue and introduction to the generated story. As the game starts, the emotion engine activates and prepares to detect the user's facial expressions and voice tone in real time.

[0357] Step 5:

[0358] The user selects the next action based on the choices displayed during the story progression. This selection is sent to the server via the device. Simultaneously, the user's facial expressions and voice are analyzed by an emotion engine on the device, and this emotion data is sent to the server.

[0359] Step 6:

[0360] The server dynamically adjusts the story's progression based on user selection information and emotional data. For example, if the user indicates tension, it generates a scenario to provide a sense of reassurance. The updated story is then sent to the device.

[0361] Step 7:

[0362] The device displays new scenes and altered character reactions sent from the server to the user. The user makes further choices based on these interactive changes, continuing the story experience.

[0363] Step 8:

[0364] Upon reaching the ending, the server generates a form for collecting feedback along with the user's gameplay data. The device then displays this form to the user, allowing them to fill in their thoughts and suggestions.

[0365] Step 9:

[0366] Users submit their opinions on the game experience through a feedback form on their device. The server receives this information, stores it in a database, and uses it to improve the system and generate new storylines in the future.

[0367] (Example 2)

[0368] Next, we will describe Example 2. 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".

[0369] Traditional interactive game systems have a static user experience, making it difficult to develop flexible storylines that respond to user emotions and preferences. Furthermore, monotonous story progression that disregards user choices and emotions reduces immersion and lowers user satisfaction.

[0370] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0371] In this invention, the server includes means for acquiring user preference information, means for forming an original story using a generative AI model, and means for dynamically adjusting the story in real time, equipped with an emotion recognition function for analyzing the user's facial expressions and voice tone. This makes it possible to dynamically change the story based on the user's emotional state and preferences, providing a deeper sense of immersion.

[0372] "User preference information" refers to individual information about themes and styles that users are interested in, and serves as foundational data for personalizing the gaming experience.

[0373] A "generative AI model" is an artificial intelligence technology used to automatically generate stories and creative content based on user preference information.

[0374] "Emotion recognition functionality" is a technology that analyzes the user's facial expressions and tone of voice to determine their emotional state in real time.

[0375] "Interactive dialogue" is a two-way communication method that allows users to influence the story through game choices and receive feedback in real time.

[0376] "Feedback" refers to information provided by users after a game ends, sharing their thoughts and opinions about the experience, which is then used to improve future game experiences and systems.

[0377] "Immersion" refers to a state in which users become deeply immersed in a game, to the point of forgetting the real world and becoming completely absorbed in the experience.

[0378] This invention is a highly personalized mystery game system that users can enjoy through an interface. This system consists of a server, a terminal, and a user.

[0379] The server is responsible for the system's central processing. Based on preference information received from the user, it generates an original story using a "generative AI model" (e.g., general language modeling technology). During this process, the prompt message will look like this: "Generate the next story development. This user's preference is 'fantasy,' and their emotion data indicates 'fun.'" This ensures that the generated story provides a unique experience for each user. The server also initializes an engine with emotion recognition capabilities, analyzing the user's emotion data to dynamically adjust the story's progression. The server aggregates this data, and after the game ends, it saves user feedback to a database to use for system improvement.

[0380] The terminal serves as the user interface. Upon user login, the terminal displays a preference input screen to collect user preferences. This information is used to present stories and choices through visual and auditory media. The terminal is equipped with an emotion recognition engine that enables real-time sentiment analysis. This emotion engine analyzes the user's facial expressions and tone of voice and transmits that data to the server.

[0381] Users participate in the game via their devices and become part of the story. They first log in and enter preference information requested by the system. As the game progresses, they choose from presented options, and their choices, along with their facial expressions and tone of voice, directly influence the story's development. When facial expressions or voice convey emotions such as anxiety or joy, the system dynamically adjusts the story based on that data, providing users with a deeply immersive experience.

[0382] For example, if a user selects an option and expresses anxiety, the server adjusts the story to generate a reassuring narrative. Conversely, if positive emotions are detected, the plot develops into an exciting one. This allows the story to flexibly change according to the user's emotional state, creating a more engaging experience.

[0383] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0384] Step 1: Enter user preference information

[0385] When a user logs in, the terminal displays a preference information input screen. Through this screen, the user enters their interests, preferred themes, and story styles. The entered information is collected as digital data and sent to the server. At this stage, data regarding the user's preferences is delivered to the server as output.

[0386] Step 2: Generating the Story

[0387] The server receives user preference information as input. Based on this information, it uses a generative AI model to generate an original story. Specifically, it creates prompt statements to instruct the AI ​​to generate a story. For example, a prompt such as "Generate the next story development. This user's preference is 'fantasy,' and their emotion data indicates 'fun'" is used as input, and the generated story is obtained as output.

[0388] Step 3: Initial setup of the emotion engine

[0389] After receiving the generated story, the server performs the initial setup of its emotion recognition function. This includes configuring sensors and algorithms for analyzing the user's emotion data. Using the story and the system's initial setup data as input, the output is a ready state.

[0390] Step 4: Start the game

[0391] The device presents the user with a generated story and associated choices. This process displays story-based text, images, and audio, allowing the user to choose how to interact. The user's choices are received as input, and their actions and decisions are passed on to the next step as output.

[0392] Step 5: Collecting user emotions and reactions

[0393] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time. It uses the user's facial expression data and voice data acquired through the camera and microphone as input, generates emotional state data as output, and sends it to the server.

[0394] Step 6: Dynamically adjust the story

[0395] The server analyzes emotional state data received from the emotion engine as input. Based on the results, it dynamically adjusts the flow of the story. For example, if the user expresses anxiety, it prioritizes a reassuring development and generates an updated story as output.

[0396] Step 7: End the game and collect feedback

[0397] After completing a game, users submit their experiences and opinions through a feedback form. Based on this input, the server collects data on the overall success and areas for improvement of the game. As output, user feedback data is stored in a database and used to improve the system in the future.

[0398] (Application Example 2)

[0399] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0400] In recent years, there has been a growing demand for digital content that provides experiences tailored to individual user preferences. However, conventional systems have struggled to generate stories that reflect users' emotions in real time, resulting in insufficient immersion. Therefore, a system is needed that enables dynamic story development using emotion recognition.

[0401] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0402] In this invention, the server includes means for collecting user preference information, means for adjusting the story in real time based on the user's choices and reactions, and means for recognizing the user's emotions and further adjusting the story's progression based on those emotions. This enables a personalized story development that directly reflects the user's emotions.

[0403] "User preference information" refers to data that shows each user's individual preferences and interests, and is necessary information to provide personalized experiences.

[0404] "Methods for generating original stories" refers to a system that automatically creates unique storylines based on collected user preference information.

[0405] A "means of adjusting the story in real time" refers to a system that has the functionality to dynamically change the development of the story on the spot in response to the user's choices and reactions.

[0406] A "means of recognizing user emotions" refers to a system equipped with technology to analyze a user's facial expressions, tone of voice, etc., and determine their emotional state.

[0407] "Interactive dialogue with the user" refers to a two-way exchange where the system provides appropriate feedback based on the user's choices and responses.

[0408] "Means of facilitating the progression of the experience" are mechanisms that support the progression of the story so that users can experience it smoothly and immersively.

[0409] A "means of collecting feedback" refers to a system that has the function of collecting opinions and impressions from users after their experience.

[0410] The server has the function of collecting user preference information. Based on this information, an AI model can automatically generate an original story. After the story is generated, the server uses emotion recognition technology to collect data on the user's choices and reactions, and analyzes this in real time to dynamically adjust the story's progression. An emotion engine is used to adjust the story, branching the plot according to the user's emotions. After the game ends, data is accumulated to improve the entire system based on the user's emotional data and feedback.

[0411] The device presents the generated story and choices to the user visually and audibly through its user interface. The device is equipped with a camera and microphone, and incorporates an emotion engine that analyzes facial expressions and voice tone to evaluate the user's emotions in real time. This data is sent to a server and used to advance the story.

[0412] Users log in and input their preferences through the device's interface. During the game experience, users influence the story's progression through the choices presented, and their emotional data, such as facial expressions and voice, is reflected in the game in real time, providing an interactive experience. For example, when a user chooses either "adventure" or "romance," if emotions such as surprise or joy are detected, the plot unfolds accordingly.

[0413] An example of a prompt message would be: "If you were going on a university club trip, what kind of story would you want to experience? Are you looking for adventure, or do you want a heartwarming encounter? To make the experience even more exciting, we will adjust the scenario based on your facial expressions."

[0414] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0415] Step 1:

[0416] The server receives preference information from the user's device. This information is sent in XML or JSON format and contains elements that indicate the user's preferences. The server analyzes this data and prepares it for input into the generating AI model.

[0417] Step 2:

[0418] The server uses a generative AI model to generate an original story from the received preference information. The AI ​​model receives the user's preferences as prompts and generates a storyline. As output, the story's initial settings and plot information are generated and sent to the user's terminal.

[0419] Step 3:

[0420] The device presents the received narrative information to the user visually and audibly. The user is presented with multiple choices, each leading to a different development in the story. This information is displayed via the user interface, and the user's selection is entered.

[0421] Step 4:

[0422] The user selects one of the presented options and inputs it as selection information into the device. This choice will influence the progression of the story.

[0423] Step 5:

[0424] The device uses its camera and microphone to collect user facial and voice data. This data is analyzed through the device's emotion engine to assess the user's real-time emotional state.

[0425] Step 6:

[0426] Emotional data and selection information from the device are sent to the server. Based on this data, the server performs calculations to readjust the story plot. The adjusted plot incorporates changes that respond to the user's emotions, generating a new story development.

[0427] Step 7:

[0428] The revised plot is sent back to the device, presenting the user with a new narrative development. This process is repeated, resulting in an interactive experience based on the user's emotions.

[0429] Step 8:

[0430] After completing the story experience, users enter their opinions and impressions into a feedback form. This information is sent from the device to the server and stored in a database for system improvement.

[0431] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0432] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0433] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0434] [Third Embodiment]

[0435] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0436] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0437] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0438] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0439] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0440] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0441] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0442] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0443] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0444] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0445] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0446] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0447] This invention relates to a system that dynamically generates stories based on user preferences and reactions, providing a personalized mystery game experience. The specific actions of each entity—the server, terminal, and user—are described below.

[0448] server

[0449] The server first receives information about the user's preferences and records it in a database. Based on this information, it uses generative AI to create individual game stories. This includes a process of designing characters and plots based on the user's preferred genres and settings. As the story progresses, the server analyzes the user's choices and reactions in real time and updates the data necessary to adjust the story development. After the game ends, feedback is collected and used to generate the next story and improve the system.

[0450] terminal

[0451] The terminal functions as the user interface. After the user logs in, it displays a screen for entering preference information. It visualizes and presents the generated story and choices to the user. It displays interactive puzzles and conversational prompts, and relays user input to the server. Finally, it displays a feedback form along with the ending to collect the user's thoughts on their game experience.

[0452] User

[0453] Users first log in using their device and input their preferences and expectations. Within the displayed story, they influence the plot's progression by making choices. Because these choices alter how the story unfolds, users can enjoy an interactive experience where their decisions directly impact the outcome. Furthermore, after completing the game, they can write their impressions and suggestions for improvement in a feedback form.

[0454] For example, if a user enters "suspense" as their preference, the server generates a story plotted around a disappearance in a specific city. During the user's investigation, the device presents evidence and prompts the user to search for the next clue. Because the truth of the case unfolds differently depending on the user's choices, there are new discoveries with each game experience. Finally, user feedback is collected on the server and used to develop future stories.

[0455] The following describes the processing flow.

[0456] Step 1:

[0457] The server receives the user's login information and performs authentication. If authentication is successful, the server retrieves the user's profile information and returns it to the device.

[0458] Step 2:

[0459] The device displays a screen where the user can input their mystery genre and preferences. The user selects their preferences and sends that data to the server.

[0460] Step 3:

[0461] The server uses a generative AI to construct personalized stories based on user preferences. This includes the automatic generation of character settings and story plots.

[0462] Step 4:

[0463] The server sends the initial plot points of the generated story to the terminal, which then presents them to the user in a visualized form. The user reads the presented prologue and gets a feel for the game's atmosphere.

[0464] Step 5:

[0465] The device displays options to the user and prompts them to choose an action. The user makes a selection and sends that selection to the server.

[0466] Step 6:

[0467] The server dynamically adjusts the story progression based on the selection information received from the user. It generates new events and scenes according to the selection results and sends the updated story to the device.

[0468] Step 7:

[0469] The device displays new scenes and character reactions to the user, prompting them to take their next action or make a choice. The user becomes more involved in the storytelling and progresses through the game.

[0470] Step 8:

[0471] When a player reaches the game's ending, the server records their play history and sends a feedback form to their device. Users can then fill in their comments and suggestions for improvement.

[0472] Step 9:

[0473] The server receives feedback information and analyzes user comments. This information is stored in a database to be used for system improvements and designing future stories.

[0474] (Example 1)

[0475] Next, we will describe Example 1. 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."

[0476] There is a growing need to cater to the diverse preferences of today's users and provide personalized virtual experiences through immersive interactions. However, conventional systems have struggled to generate and adjust stories that fully reflect user preferences in real time. Furthermore, there has been a lack of methods to effectively utilize user feedback and optimize the entire system.

[0477] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0478] In this invention, the server includes means for collecting user preference information using an information device, means for generating an original story using a generative model based on this preference information, and means for analyzing user choices and reactions to adjust the story in real time. This enables the provision of a personalized story experience and continuous system improvement that reflects user feedback.

[0479] "User preference information" refers to information about users' interests, preferences, and expectations, and is the data that forms the basis for story generation.

[0480] "Information device" is a general term for hardware or software used to receive and process user input.

[0481] A "generative model" is an algorithm or program that uses machine learning or other methods to generate original stories based on user preference information.

[0482] A "story" refers to an entire narrative created based on a specific theme or setting, encompassing a series of events and incidents, including characters and plot.

[0483] A "visual medium" is a means of displaying visual information, such as images and videos, to enable an interactive experience with the user.

[0484] "Interaction" refers to the two-way communication that a user has with a system, including choices and responses.

[0485] "Information analysis means" refers to methods or techniques for analyzing progress and feedback obtained from users and deriving insights necessary for improving the entire system.

[0486] This invention relates to a system that generates personalized stories tailored to user preferences and provides an interactive experience. The roles of the server, terminal, and user, as well as the hardware and software used, are described below.

[0487] server

[0488] The server processes preference information sent by the user and uses this information to generate stories using a generative AI model. By recording and analyzing preference information using a database, a plot that matches the user's tastes is designed. The generative AI model uses specific prompts such as, "If the user's preference is suspense, what would be an appropriate plot?" to reflect the genre specified by the user. The server's main function is to dynamically adjust the story by analyzing the user's choices and reactions in real time, according to the generated story.

[0489] terminal

[0490] The terminal primarily functions as a user interface. Upon user login, a screen is displayed to collect preference information, and user input is sent to the server. The server then visualizes and presents stories and choices to the user. The terminal assists the user in making choices by displaying interactive puzzles and conversational prompts, and relays this data to the server. Finally, at the end of the virtual experience, a feedback screen is displayed to collect the user's thoughts on the experience.

[0491] User

[0492] Users input their preferences through their device and influence the flow of the story by selecting options provided in the generated story. Because user choices significantly impact the story's progression, they can dynamically enjoy how their choices affect the narrative. At the end of the experience, they can provide feedback on their game experience and suggestions for system improvements through a feedback form. This allows users not only to interactively engage but also to contribute to future system improvements.

[0493] The system, configured in this way, provides new story experiences tailored to the individual preferences of users and is continuously optimized by utilizing user feedback.

[0494] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0495] Step 1:

[0496] The user logs into the system using a terminal. The terminal displays an interface for collecting preference information from the user and prompts the user for input. The input preference information, which includes elements of the user's interests and expectations, is sent to the server. The output at this stage is the user's preference information.

[0497] Step 2:

[0498] The server receives user preference information sent from the terminal and stores it in a database. Based on this information, the server inputs appropriate prompts into the generative AI model and begins the process of generating a personalized story. Specifically, it uses a prompt such as, "If the user's preference is suspense, what would be an appropriate plot?" The output at this stage is an outline of a story tailored to the user.

[0499] Step 3:

[0500] The server meticulously constructs the story outline obtained from the generative AI model and sets up multiple choices for the user to select. The story and choices are designed to change dynamically based on the user's choices and reactions. The output at this stage is the specific story and choices.

[0501] Step 4:

[0502] The device provides the user with a story and choices from the server. The story is visually represented, and the choices are displayed in a format that the user can select. The user chooses from the presented options, influencing the progression of the story. The user's choices are sent back to the server by the device. The output at this stage is the user's selection information.

[0503] Step 5:

[0504] The server analyzes the user's choices and adjusts the story's progression in real time. This adjusted story is then sent back to the device as needed, providing the user with updated information. This allows the user to experience a dynamically changing story. The output at this stage is the adjusted story.

[0505] Step 6:

[0506] Once the story is complete, the device displays the ending and provides the user with a feedback form. The user writes their impressions and suggestions for improvement and sends them to the server via the device. The output at this stage is the user's feedback.

[0507] Step 7:

[0508] The server analyzes the collected feedback and uses it to generate future stories and improve the system. This process takes user opinions and progress into consideration, leading to system optimization for the next version. The output at this stage provides design insights for the improved system.

[0509] (Application Example 1)

[0510] Next, we will explain Application Example 1. In the following explanation, 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."

[0511] Providing interactive game experiences using personalized storylines requires real-time content generation and delivery tailored to user preferences. However, conventional systems lack the ability to dynamically adjust storylines based on user choices and support a variety of devices, making it difficult to improve user immersion and satisfaction.

[0512] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0513] In this invention, the server includes means for collecting user preference information, means for generating an original story, means for distributing the generated story through an information and communication network, and means for providing audio and augmented reality representations using multiple output devices. This enables real-time story adjustment based on user choices and reactions, and an immersive interactive experience using various devices.

[0514] "Means for collecting user preference information" refers to methods for identifying users' interests and preferences using information processing equipment and storing them as data.

[0515] "Methods for generating original stories" refers to methods for creating personalized narratives using generative AI based on user preference information.

[0516] "A means of adjusting the story in real time" refers to a function that dynamically changes the progression of the story on the spot in response to the user's choices and reactions.

[0517] "Means of facilitating game progression through interactive dialogue" refers to methods of advancing the story's development while exchanging information bi-directionally with the user.

[0518] "Methods for collecting feedback" refer to methods for gathering and analyzing user feedback and experiences to use in system improvement.

[0519] "Means of distributing generated stories through information and communication networks" refers to methods of providing generated stories to users using communication networks such as the internet.

[0520] "Means of providing audio and augmented reality representations using multiple output devices" refers to methods that utilize multiple devices such as speakers and displays to provide users with a sense of presence using audio and AR technology.

[0521] This invention provides a system that dynamically generates and delivers personalized content based on user preferences. It embodies a mechanism that adjusts the story in real time through interaction between the server, terminal, and user, thereby realizing an immersive gaming experience.

[0522] server

[0523] The server first collects user preference information and stores it in a database. Using Python and TensorFlow models, a generative AI, it creates personalized stories for each user. This includes a process of creating a story plot based on prompts. As the story progresses, the server analyzes the user's choices and reactions and adjusts the story in real time using Node.js. It delivers the story including audio and augmented reality elements, and after the game ends, it collects user feedback to help improve future stories.

[0524] terminal

[0525] The device functions as an interface for user access. Using the React Native framework, users input their preferences. It displays stories created by generative AI, and the user's choices are immediately reflected on the server. The device also provides users with visual and auditory experiences using voice and augmented reality technologies. Finally, it presents the user with a feedback form and sends the feedback to the server.

[0526] User

[0527] Users interact with the system through their devices. By inputting their interests and making choices within the presented story, users can influence the progression of the narrative. Because the story unfolds in different directions depending on the choices, users can enjoy new discoveries each time. For example, a prompt such as "What will the user discover inside the pyramid?" might lead to a mystery set in Egypt. After the game ends, users provide feedback to the system about their experience, which helps in future improvements.

[0528] In this way, users can enjoy a different story each time, making it possible to provide a highly customized and interactive gaming experience.

[0529] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0530] Step 1:

[0531] The server receives preference information from users. The input is preference information provided by the user via their terminal, and this is stored in the database. The server then formats the preference information and registers it as an entry in the database so that it can be used for data inference.

[0532] Step 2:

[0533] The server generates prompts based on stored preference information and creates personalized stories using a generative AI model (TensorFlow). The input here is preference information retrieved from the database, which is converted into prompts and passed to the AI ​​model. The AI ​​model analyzes these prompts and generates a story structure suitable for the user. The output is the suggested story.

[0534] Step 3:

[0535] The server sends the generated story to the terminal via the information and communication network. The terminal receives this story and displays the plot and choices on the user interface. The input is the generated story, and the output is the choices displayed on the GUI.

[0536] Step 4:

[0537] The user selects an action based on the choices presented in the story. The device then returns the user's chosen option to the server. The input is the user's selection, which the device sends to the server as data.

[0538] Step 5:

[0539] The server adjusts the story in real time based on the user's selections and sends the expanded story back to the terminal. The input here is the user's selection, which is the branching point of the story generated in step 2. The output is the new story path.

[0540] Step 6:

[0541] The device displays the updated story received from the server back to the user, enhancing immersion with audio and augmented reality features. The input is the updated story information, and the output is the visual and auditory experience.

[0542] Step 7:

[0543] After reaching the end of the game, the device displays a feedback form to the user, allowing them to enter their thoughts and suggestions for improvement. This input constitutes user feedback, which the device then transmits to the server.

[0544] Step 8:

[0545] The server analyzes the collected feedback to help generate future stories and improve the system. The input is user feedback data, which is then analyzed and output as design guidelines for the system. This feedback allows the system to provide stories that are more tailored to individual users in the future.

[0546] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0547] This invention relates to a personalized mystery game system that incorporates an emotion engine to recognize user emotions. The specific operations of the server, terminal, and user are described below.

[0548] server

[0549] The server is responsible for the core processing of this system. First, it receives user preference information, and the generating AI creates an original story based on this information. After the story is generated, the emotion engine performs initial setup to recognize the user's emotional state. It receives user choices and reactions in real time and adjusts the story's progression by analyzing the emotional data collected by the emotion engine. Furthermore, after the game ends, it collects user feedback, records it in a database along with the emotional data, and uses it to improve the system.

[0550] terminal

[0551] The device provides the user interface. After logging in, it displays a preference input screen, allowing the user to enter their preferences. During gameplay, it presents the generated story and choices visually and audibly. The device is equipped with an emotion engine that analyzes the user's facial expressions and voice tone in real time to evaluate their emotions and sends this data to the server. The emotional information obtained by the emotion engine is used for feedback to improve game progression.

[0552] User

[0553] Users participate in the game via their devices. First, they log in and enter their individual preferences on a preference information input screen presented by the system. After the game starts, users influence the story's progression by choosing from the options presented. Based on their choices, the user's facial expressions and voice are analyzed by an emotion engine, and the story is adjusted in real time. In particular, if the system detects that the user is surprised or enjoying themselves, the story changes accordingly. After the game ends, users can provide their experience and feedback through a feedback form, and this information is used to improve future game experiences.

[0554] For example, if a user's facial expression indicates anxiety after selecting an option, the server will use this information to adjust the story and guide the plot in a direction that makes the user feel at ease. Conversely, if a joyful expression is detected, the story will progress by adding suspense elements to provide further excitement. This real-time story development based on the user's emotions can provide a deeper sense of immersion.

[0555] The following describes the processing flow.

[0556] Step 1:

[0557] The server authenticates users when they log in to their devices. The end user enters their email address and password, and the server verifies this information. Upon successful authentication, the server retrieves the user's profile and past preference data from the database and sends it back to the device.

[0558] Step 2:

[0559] The device displays the user's preference settings screen. The user selects their preferred mystery genre and character settings, and sends this information to the server via the device. The server updates its database based on the selected settings.

[0560] Step 3:

[0561] The server uses a generative AI to create an original story based on preference information. The AI ​​generates a plot and character settings based on the user's preferences and constructs a series of scenes. This story information is then sent to the terminal.

[0562] Step 4:

[0563] The device displays the prologue and introduction to the generated story. As the game starts, the emotion engine activates and prepares to detect the user's facial expressions and voice tone in real time.

[0564] Step 5:

[0565] The user selects the next action based on the choices displayed during the story progression. This selection is sent to the server via the device. Simultaneously, the user's facial expressions and voice are analyzed by an emotion engine on the device, and this emotion data is sent to the server.

[0566] Step 6:

[0567] The server dynamically adjusts the story's progression based on user selection information and emotional data. For example, if the user indicates tension, it generates a scenario to provide a sense of reassurance. The updated story is then sent to the device.

[0568] Step 7:

[0569] The device displays new scenes and altered character reactions sent from the server to the user. The user makes further choices based on these interactive changes, continuing the story experience.

[0570] Step 8:

[0571] Upon reaching the ending, the server generates a form for collecting feedback along with the user's gameplay data. The device then displays this form to the user, allowing them to fill in their thoughts and suggestions.

[0572] Step 9:

[0573] Users submit their opinions on the game experience through a feedback form on their device. The server receives this information, stores it in a database, and uses it to improve the system and generate new storylines in the future.

[0574] (Example 2)

[0575] Next, we will describe Example 2. 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."

[0576] Traditional interactive game systems have a static user experience, making it difficult to develop flexible storylines that respond to user emotions and preferences. Furthermore, monotonous story progression that disregards user choices and emotions reduces immersion and lowers user satisfaction.

[0577] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0578] In this invention, the server includes means for acquiring user preference information, means for forming an original story using a generative AI model, and means for dynamically adjusting the story in real time, equipped with an emotion recognition function for analyzing the user's facial expressions and voice tone. This makes it possible to dynamically change the story based on the user's emotional state and preferences, providing a deeper sense of immersion.

[0579] "User preference information" refers to individual information about themes and styles that users are interested in, and serves as foundational data for personalizing the gaming experience.

[0580] A "generative AI model" is an artificial intelligence technology used to automatically generate stories and creative content based on user preference information.

[0581] "Emotion recognition functionality" is a technology that analyzes the user's facial expressions and tone of voice to determine their emotional state in real time.

[0582] "Interactive dialogue" is a two-way communication method that allows users to influence the story through game choices and receive feedback in real time.

[0583] "Feedback" refers to information provided by users after a game ends, sharing their thoughts and opinions about the experience, which is then used to improve future game experiences and systems.

[0584] "Immersion" refers to a state in which users become deeply immersed in a game, to the point of forgetting the real world and becoming completely absorbed in the experience.

[0585] This invention is a highly personalized mystery game system that users can enjoy through an interface. This system consists of a server, a terminal, and a user.

[0586] The server is responsible for the system's central processing. Based on preference information received from the user, it generates an original story using a "generative AI model" (e.g., general language modeling technology). During this process, the prompt message will look like this: "Generate the next story development. This user's preference is 'fantasy,' and their emotion data indicates 'fun.'" This ensures that the generated story provides a unique experience for each user. The server also initializes an engine with emotion recognition capabilities, analyzing the user's emotion data to dynamically adjust the story's progression. The server aggregates this data, and after the game ends, it saves user feedback to a database to use for system improvement.

[0587] The terminal serves as the user interface. Upon user login, the terminal displays a preference input screen to collect user preferences. This information is used to present stories and choices through visual and auditory media. The terminal is equipped with an emotion recognition engine that enables real-time sentiment analysis. This emotion engine analyzes the user's facial expressions and tone of voice and transmits that data to the server.

[0588] Users participate in the game via their devices and become part of the story. They first log in and enter preference information requested by the system. As the game progresses, they choose from presented options, and their choices, along with their facial expressions and tone of voice, directly influence the story's development. When facial expressions or voice convey emotions such as anxiety or joy, the system dynamically adjusts the story based on that data, providing users with a deeply immersive experience.

[0589] For example, if a user selects an option and expresses anxiety, the server adjusts the story to generate a reassuring narrative. Conversely, if positive emotions are detected, the plot develops into an exciting one. This allows the story to flexibly change according to the user's emotional state, creating a more engaging experience.

[0590] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0591] Step 1: Enter user preference information

[0592] When a user logs in, the terminal displays a preference information input screen. Through this screen, the user enters their interests, preferred themes, and story styles. The entered information is collected as digital data and sent to the server. At this stage, data regarding the user's preferences is delivered to the server as output.

[0593] Step 2: Generating the Story

[0594] The server receives user preference information as input. Based on this information, it uses a generative AI model to generate an original story. Specifically, it creates prompt statements to instruct the AI ​​to generate a story. For example, a prompt such as "Generate the next story development. This user's preference is 'fantasy,' and their emotion data indicates 'fun'" is used as input, and the generated story is obtained as output.

[0595] Step 3: Initial setup of the emotion engine

[0596] After receiving the generated story, the server performs the initial setup of its emotion recognition function. This includes configuring sensors and algorithms for analyzing the user's emotion data. Using the story and the system's initial setup data as input, the output is a ready state.

[0597] Step 4: Start the game

[0598] The device presents the user with a generated story and associated choices. This process displays story-based text, images, and audio, allowing the user to choose how to interact. The user's choices are received as input, and their actions and decisions are passed on to the next step as output.

[0599] Step 5: Collecting user emotions and reactions

[0600] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time. It uses the user's facial expression data and voice data acquired through the camera and microphone as input, generates emotional state data as output, and sends it to the server.

[0601] Step 6: Dynamically adjust the story

[0602] The server analyzes emotional state data received from the emotion engine as input. Based on the results, it dynamically adjusts the flow of the story. For example, if the user expresses anxiety, it prioritizes a reassuring development and generates an updated story as output.

[0603] Step 7: End the game and collect feedback

[0604] After completing a game, users submit their experiences and opinions through a feedback form. Based on this input, the server collects data on the overall success and areas for improvement of the game. As output, user feedback data is stored in a database and used to improve the system in the future.

[0605] (Application Example 2)

[0606] Next, we will explain application example 2. In the following explanation, 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."

[0607] In recent years, there has been a growing demand for digital content that provides experiences tailored to individual user preferences. However, conventional systems have struggled to generate stories that reflect users' emotions in real time, resulting in insufficient immersion. Therefore, a system is needed that enables dynamic story development using emotion recognition.

[0608] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0609] In this invention, the server includes means for collecting user preference information, means for adjusting the story in real time based on the user's choices and reactions, and means for recognizing the user's emotions and further adjusting the story's progression based on those emotions. This enables a personalized story development that directly reflects the user's emotions.

[0610] "User preference information" refers to data that shows each user's individual preferences and interests, and is necessary information to provide personalized experiences.

[0611] "Methods for generating original stories" refers to a system that automatically creates unique storylines based on collected user preference information.

[0612] A "means of adjusting the story in real time" refers to a system that has the functionality to dynamically change the development of the story on the spot in response to the user's choices and reactions.

[0613] A "means of recognizing user emotions" refers to a system equipped with technology to analyze a user's facial expressions, tone of voice, etc., and determine their emotional state.

[0614] "Interactive dialogue with the user" refers to a two-way exchange where the system provides appropriate feedback based on the user's choices and responses.

[0615] "Means of facilitating the progression of the experience" are mechanisms that support the progression of the story so that users can experience it smoothly and immersively.

[0616] A "means of collecting feedback" refers to a system that has the function of collecting opinions and impressions from users after their experience.

[0617] The server has the function of collecting user preference information. Based on this information, an AI model can automatically generate an original story. After the story is generated, the server uses emotion recognition technology to collect data on the user's choices and reactions, and analyzes this in real time to dynamically adjust the story's progression. An emotion engine is used to adjust the story, branching the plot according to the user's emotions. After the game ends, data is accumulated to improve the entire system based on the user's emotional data and feedback.

[0618] The device presents the generated story and choices to the user visually and audibly through its user interface. The device is equipped with a camera and microphone, and incorporates an emotion engine that analyzes facial expressions and voice tone to evaluate the user's emotions in real time. This data is sent to a server and used to advance the story.

[0619] Users log in and input their preferences through the device's interface. During the game experience, users influence the story's progression through the choices presented, and their emotional data, such as facial expressions and voice, is reflected in the game in real time, providing an interactive experience. For example, when a user chooses either "adventure" or "romance," if emotions such as surprise or joy are detected, the plot unfolds accordingly.

[0620] An example of a prompt message would be: "If you were going on a university club trip, what kind of story would you want to experience? Are you looking for adventure, or do you want a heartwarming encounter? To make the experience even more exciting, we will adjust the scenario based on your facial expressions."

[0621] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0622] Step 1:

[0623] The server receives preference information from the user's device. This information is sent in XML or JSON format and contains elements that indicate the user's preferences. The server analyzes this data and prepares it for input into the generating AI model.

[0624] Step 2:

[0625] The server uses a generative AI model to generate an original story from the received preference information. The AI ​​model receives the user's preferences as prompts and generates a storyline. As output, the story's initial settings and plot information are generated and sent to the user's terminal.

[0626] Step 3:

[0627] The device presents the received narrative information to the user visually and audibly. The user is presented with multiple choices, each leading to a different development in the story. This information is displayed via the user interface, and the user's selection is entered.

[0628] Step 4:

[0629] The user selects one of the presented options and inputs it as selection information into the device. This choice will influence the progression of the story.

[0630] Step 5:

[0631] The device uses its camera and microphone to collect user facial and voice data. This data is analyzed through the device's emotion engine to assess the user's real-time emotional state.

[0632] Step 6:

[0633] Emotional data and selection information from the device are sent to the server. Based on this data, the server performs calculations to readjust the story plot. The adjusted plot incorporates changes that respond to the user's emotions, generating a new story development.

[0634] Step 7:

[0635] The revised plot is sent back to the device, presenting the user with a new narrative development. This process is repeated, resulting in an interactive experience based on the user's emotions.

[0636] Step 8:

[0637] After completing the story experience, users enter their opinions and impressions into a feedback form. This information is sent from the device to the server and stored in a database for system improvement.

[0638] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0639] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0640] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0641] [Fourth Embodiment]

[0642] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0643] As shown in Figure 7, the 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.

[0644] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0645] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0646] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0647] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0648] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0649] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0650] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0651] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0652] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0653] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0654] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0655] This invention relates to a system that dynamically generates stories based on user preferences and reactions, providing a personalized mystery game experience. The specific actions of each entity—the server, terminal, and user—are described below.

[0656] server

[0657] The server first receives information about the user's preferences and records it in a database. Based on this information, it uses generative AI to create individual game stories. This includes a process of designing characters and plots based on the user's preferred genres and settings. As the story progresses, the server analyzes the user's choices and reactions in real time and updates the data necessary to adjust the story development. After the game ends, feedback is collected and used to generate the next story and improve the system.

[0658] terminal

[0659] The terminal functions as the user interface. After the user logs in, it displays a screen for entering preference information. It visualizes and presents the generated story and choices to the user. It displays interactive puzzles and conversational prompts, and relays user input to the server. Finally, it displays a feedback form along with the ending to collect the user's thoughts on their game experience.

[0660] User

[0661] Users first log in using their device and input their preferences and expectations. Within the displayed story, they influence the plot's progression by making choices. Because these choices alter how the story unfolds, users can enjoy an interactive experience where their decisions directly impact the outcome. Furthermore, after completing the game, they can write their impressions and suggestions for improvement in a feedback form.

[0662] For example, if a user enters "suspense" as their preference, the server generates a story plotted around a disappearance in a specific city. During the user's investigation, the device presents evidence and prompts the user to search for the next clue. Because the truth of the case unfolds differently depending on the user's choices, there are new discoveries with each game experience. Finally, user feedback is collected on the server and used to develop future stories.

[0663] The following describes the processing flow.

[0664] Step 1:

[0665] The server receives the user's login information and performs authentication. If authentication is successful, the server retrieves the user's profile information and returns it to the device.

[0666] Step 2:

[0667] The device displays a screen where the user can input their mystery genre and preferences. The user selects their preferences and sends that data to the server.

[0668] Step 3:

[0669] The server uses a generative AI to construct personalized stories based on user preferences. This includes the automatic generation of character settings and story plots.

[0670] Step 4:

[0671] The server sends the initial plot points of the generated story to the terminal, which then presents them to the user in a visualized form. The user reads the presented prologue and gets a feel for the game's atmosphere.

[0672] Step 5:

[0673] The device displays options to the user and prompts them to choose an action. The user makes a selection and sends that selection to the server.

[0674] Step 6:

[0675] The server dynamically adjusts the story progression based on the selection information received from the user. It generates new events and scenes according to the selection results and sends the updated story to the device.

[0676] Step 7:

[0677] The device displays new scenes and character reactions to the user, prompting them to take their next action or make a choice. The user becomes more involved in the storytelling and progresses through the game.

[0678] Step 8:

[0679] When a player reaches the game's ending, the server records their play history and sends a feedback form to their device. Users can then fill in their comments and suggestions for improvement.

[0680] Step 9:

[0681] The server receives feedback information and analyzes user comments. This information is stored in a database to be used for system improvements and designing future stories.

[0682] (Example 1)

[0683] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0684] There is a growing need to cater to the diverse preferences of today's users and provide personalized virtual experiences through immersive interactions. However, conventional systems have struggled to generate and adjust stories that fully reflect user preferences in real time. Furthermore, there has been a lack of methods to effectively utilize user feedback and optimize the entire system.

[0685] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0686] In this invention, the server includes means for collecting user preference information using an information device, means for generating an original story using a generative model based on this preference information, and means for analyzing user choices and reactions to adjust the story in real time. This enables the provision of a personalized story experience and continuous system improvement that reflects user feedback.

[0687] "User preference information" refers to information about users' interests, preferences, and expectations, and is the data that forms the basis for story generation.

[0688] "Information device" is a general term for hardware or software used to receive and process user input.

[0689] A "generative model" is an algorithm or program that uses machine learning or other methods to generate original stories based on user preference information.

[0690] A "story" refers to an entire narrative created based on a specific theme or setting, encompassing a series of events and incidents, including characters and plot.

[0691] A "visual medium" is a means of displaying visual information, such as images and videos, to enable an interactive experience with the user.

[0692] "Interaction" refers to the two-way communication that a user has with a system, including choices and responses.

[0693] "Information analysis means" refers to methods or techniques for analyzing progress and feedback obtained from users and deriving insights necessary for improving the entire system.

[0694] This invention relates to a system that generates personalized stories tailored to user preferences and provides an interactive experience. The roles of the server, terminal, and user, as well as the hardware and software used, are described below.

[0695] server

[0696] The server processes preference information sent by the user and uses this information to generate stories using a generative AI model. By recording and analyzing preference information using a database, a plot that matches the user's tastes is designed. The generative AI model uses specific prompts such as, "If the user's preference is suspense, what would be an appropriate plot?" to reflect the genre specified by the user. The server's main function is to dynamically adjust the story by analyzing the user's choices and reactions in real time, according to the generated story.

[0697] terminal

[0698] The terminal primarily functions as a user interface. Upon user login, a screen is displayed to collect preference information, and user input is sent to the server. The server then visualizes and presents stories and choices to the user. The terminal assists the user in making choices by displaying interactive puzzles and conversational prompts, and relays this data to the server. Finally, at the end of the virtual experience, a feedback screen is displayed to collect the user's thoughts on the experience.

[0699] User

[0700] Users input their preferences through their device and influence the flow of the story by selecting options provided in the generated story. Because user choices significantly impact the story's progression, they can dynamically enjoy how their choices affect the narrative. At the end of the experience, they can provide feedback on their game experience and suggestions for system improvements through a feedback form. This allows users not only to interactively engage but also to contribute to future system improvements.

[0701] The system, configured in this way, provides new story experiences tailored to the individual preferences of users and is continuously optimized by utilizing user feedback.

[0702] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0703] Step 1:

[0704] The user logs into the system using a terminal. The terminal displays an interface for collecting preference information from the user and prompts the user for input. The input preference information, which includes elements of the user's interests and expectations, is sent to the server. The output at this stage is the user's preference information.

[0705] Step 2:

[0706] The server receives user preference information sent from the terminal and stores it in a database. Based on this information, the server inputs appropriate prompts into the generative AI model and begins the process of generating a personalized story. Specifically, it uses a prompt such as, "If the user's preference is suspense, what would be an appropriate plot?" The output at this stage is an outline of a story tailored to the user.

[0707] Step 3:

[0708] The server meticulously constructs the story outline obtained from the generative AI model and sets up multiple choices for the user to select. The story and choices are designed to change dynamically based on the user's choices and reactions. The output at this stage is the specific story and choices.

[0709] Step 4:

[0710] The device provides the user with a story and choices from the server. The story is visually represented, and the choices are displayed in a format that the user can select. The user chooses from the presented options, influencing the progression of the story. The user's choices are sent back to the server by the device. The output at this stage is the user's selection information.

[0711] Step 5:

[0712] The server analyzes the user's choices and adjusts the story's progression in real time. This adjusted story is then sent back to the device as needed, providing the user with updated information. This allows the user to experience a dynamically changing story. The output at this stage is the adjusted story.

[0713] Step 6:

[0714] Once the story is complete, the device displays the ending and provides the user with a feedback form. The user writes their impressions and suggestions for improvement and sends them to the server via the device. The output at this stage is the user's feedback.

[0715] Step 7:

[0716] The server analyzes the collected feedback and uses it to generate future stories and improve the system. This process takes user opinions and progress into consideration, leading to system optimization for the next version. The output at this stage provides design insights for the improved system.

[0717] (Application Example 1)

[0718] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0719] Providing interactive game experiences using personalized storylines requires real-time content generation and delivery tailored to user preferences. However, conventional systems lack the ability to dynamically adjust storylines based on user choices and support a variety of devices, making it difficult to improve user immersion and satisfaction.

[0720] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0721] In this invention, the server includes means for collecting user preference information, means for generating an original story, means for distributing the generated story through an information and communication network, and means for providing audio and augmented reality representations using multiple output devices. This enables real-time story adjustment based on user choices and reactions, and an immersive interactive experience using various devices.

[0722] "Means for collecting user preference information" refers to methods for identifying users' interests and preferences using information processing equipment and storing them as data.

[0723] "Methods for generating original stories" refers to methods for creating personalized narratives using generative AI based on user preference information.

[0724] "A means of adjusting the story in real time" refers to a function that dynamically changes the progression of the story on the spot in response to the user's choices and reactions.

[0725] "Means of facilitating game progression through interactive dialogue" refers to methods of advancing the story's development while exchanging information bi-directionally with the user.

[0726] "Methods for collecting feedback" refer to methods for gathering and analyzing user feedback and experiences to use in system improvement.

[0727] "Means of distributing generated stories through information and communication networks" refers to methods of providing generated stories to users using communication networks such as the internet.

[0728] "Means of providing audio and augmented reality representations using multiple output devices" refers to methods that utilize multiple devices such as speakers and displays to provide users with a sense of presence using audio and AR technology.

[0729] This invention provides a system that dynamically generates and delivers personalized content based on user preferences. It embodies a mechanism that adjusts the story in real time through interaction between the server, terminal, and user, thereby realizing an immersive gaming experience.

[0730] server

[0731] The server first collects user preference information and stores it in a database. Using Python and TensorFlow models, a generative AI, it creates personalized stories for each user. This includes a process of creating a story plot based on prompts. As the story progresses, the server analyzes the user's choices and reactions and adjusts the story in real time using Node.js. It delivers the story including audio and augmented reality elements, and after the game ends, it collects user feedback to help improve future stories.

[0732] terminal

[0733] The device functions as an interface for user access. Using the React Native framework, users input their preferences. It displays stories created by generative AI, and the user's choices are immediately reflected on the server. The device also provides users with visual and auditory experiences using voice and augmented reality technologies. Finally, it presents the user with a feedback form and sends the feedback to the server.

[0734] User

[0735] Users interact with the system through their devices. By inputting their interests and making choices within the presented story, users can influence the progression of the narrative. Because the story unfolds in different directions depending on the choices, users can enjoy new discoveries each time. For example, a prompt such as "What will the user discover inside the pyramid?" might lead to a mystery set in Egypt. After the game ends, users provide feedback to the system about their experience, which helps in future improvements.

[0736] In this way, users can enjoy a different story each time, making it possible to provide a highly customized and interactive gaming experience.

[0737] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0738] Step 1:

[0739] The server receives preference information from users. The input is preference information provided by the user via their terminal, and this is stored in the database. The server then formats the preference information and registers it as an entry in the database so that it can be used for data inference.

[0740] Step 2:

[0741] The server generates prompts based on stored preference information and creates personalized stories using a generative AI model (TensorFlow). The input here is preference information retrieved from the database, which is converted into prompts and passed to the AI ​​model. The AI ​​model analyzes these prompts and generates a story structure suitable for the user. The output is the suggested story.

[0742] Step 3:

[0743] The server sends the generated story to the terminal via the information and communication network. The terminal receives this story and displays the plot and choices on the user interface. The input is the generated story, and the output is the choices displayed on the GUI.

[0744] Step 4:

[0745] The user selects an action based on the choices presented in the story. The device then returns the user's chosen option to the server. The input is the user's selection, which the device sends to the server as data.

[0746] Step 5:

[0747] The server adjusts the story in real time based on the user's selections and sends the expanded story back to the terminal. The input here is the user's selection, which is the branching point of the story generated in step 2. The output is the new story path.

[0748] Step 6:

[0749] The device displays the updated story received from the server back to the user, enhancing immersion with audio and augmented reality features. The input is the updated story information, and the output is the visual and auditory experience.

[0750] Step 7:

[0751] After reaching the end of the game, the device displays a feedback form to the user, allowing them to enter their thoughts and suggestions for improvement. This input constitutes user feedback, which the device then transmits to the server.

[0752] Step 8:

[0753] The server analyzes the collected feedback to help generate future stories and improve the system. The input is user feedback data, which is then analyzed and output as design guidelines for the system. This feedback allows the system to provide stories that are more tailored to individual users in the future.

[0754] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0755] This invention relates to a personalized mystery game system that incorporates an emotion engine to recognize user emotions. The specific operations of the server, terminal, and user are described below.

[0756] server

[0757] The server is responsible for the core processing of this system. First, it receives user preference information, and the generating AI creates an original story based on this information. After the story is generated, the emotion engine performs initial setup to recognize the user's emotional state. It receives user choices and reactions in real time and adjusts the story's progression by analyzing the emotional data collected by the emotion engine. Furthermore, after the game ends, it collects user feedback, records it in a database along with the emotional data, and uses it to improve the system.

[0758] terminal

[0759] The device provides the user interface. After logging in, it displays a preference input screen, allowing the user to enter their preferences. During gameplay, it presents the generated story and choices visually and audibly. The device is equipped with an emotion engine that analyzes the user's facial expressions and voice tone in real time to evaluate their emotions and sends this data to the server. The emotional information obtained by the emotion engine is used for feedback to improve game progression.

[0760] User

[0761] Users participate in the game via their devices. First, they log in and enter their individual preferences on a preference information input screen presented by the system. After the game starts, users influence the story's progression by choosing from the options presented. Based on their choices, the user's facial expressions and voice are analyzed by an emotion engine, and the story is adjusted in real time. In particular, if the system detects that the user is surprised or enjoying themselves, the story changes accordingly. After the game ends, users can provide their experience and feedback through a feedback form, and this information is used to improve future game experiences.

[0762] For example, if a user's facial expression indicates anxiety after selecting an option, the server will use this information to adjust the story and guide the plot in a direction that makes the user feel at ease. Conversely, if a joyful expression is detected, the story will progress by adding suspense elements to provide further excitement. This real-time story development based on the user's emotions can provide a deeper sense of immersion.

[0763] The following describes the processing flow.

[0764] Step 1:

[0765] The server authenticates users when they log in to their devices. The end user enters their email address and password, and the server verifies this information. Upon successful authentication, the server retrieves the user's profile and past preference data from the database and sends it back to the device.

[0766] Step 2:

[0767] The device displays the user's preference settings screen. The user selects their preferred mystery genre and character settings, and sends this information to the server via the device. The server updates its database based on the selected settings.

[0768] Step 3:

[0769] The server uses a generative AI to create an original story based on preference information. The AI ​​generates a plot and character settings based on the user's preferences and constructs a series of scenes. This story information is then sent to the terminal.

[0770] Step 4:

[0771] The device displays the prologue and introduction to the generated story. As the game starts, the emotion engine activates and prepares to detect the user's facial expressions and voice tone in real time.

[0772] Step 5:

[0773] The user selects the next action based on the choices displayed during the story progression. This selection is sent to the server via the device. Simultaneously, the user's facial expressions and voice are analyzed by an emotion engine on the device, and this emotion data is sent to the server.

[0774] Step 6:

[0775] The server dynamically adjusts the story's progression based on user selection information and emotional data. For example, if the user indicates tension, it generates a scenario to provide a sense of reassurance. The updated story is then sent to the device.

[0776] Step 7:

[0777] The device displays new scenes and altered character reactions sent from the server to the user. The user makes further choices based on these interactive changes, continuing the story experience.

[0778] Step 8:

[0779] Upon reaching the ending, the server generates a form for collecting feedback along with the user's gameplay data. The device then displays this form to the user, allowing them to fill in their thoughts and suggestions.

[0780] Step 9:

[0781] Users submit their opinions on the game experience through a feedback form on their device. The server receives this information, stores it in a database, and uses it to improve the system and generate new storylines in the future.

[0782] (Example 2)

[0783] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0784] Traditional interactive game systems have a static user experience, making it difficult to develop flexible storylines that respond to user emotions and preferences. Furthermore, monotonous story progression that disregards user choices and emotions reduces immersion and lowers user satisfaction.

[0785] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0786] In this invention, the server includes means for acquiring user preference information, means for forming an original story using a generative AI model, and means for dynamically adjusting the story in real time, equipped with an emotion recognition function for analyzing the user's facial expressions and voice tone. This makes it possible to dynamically change the story based on the user's emotional state and preferences, providing a deeper sense of immersion.

[0787] "User preference information" refers to individual information about themes and styles that users are interested in, and serves as foundational data for personalizing the gaming experience.

[0788] A "generative AI model" is an artificial intelligence technology used to automatically generate stories and creative content based on user preference information.

[0789] "Emotion recognition functionality" is a technology that analyzes the user's facial expressions and tone of voice to determine their emotional state in real time.

[0790] "Interactive dialogue" is a two-way communication method that allows users to influence the story through game choices and receive feedback in real time.

[0791] "Feedback" refers to information provided by users after a game ends, sharing their thoughts and opinions about the experience, which is then used to improve future game experiences and systems.

[0792] "Immersion" refers to a state in which users become deeply immersed in a game, to the point of forgetting the real world and becoming completely absorbed in the experience.

[0793] This invention is a highly personalized mystery game system that users can enjoy through an interface. This system consists of a server, a terminal, and a user.

[0794] The server is responsible for the system's central processing. Based on preference information received from the user, it generates an original story using a "generative AI model" (e.g., general language modeling technology). During this process, the prompt message will look like this: "Generate the next story development. This user's preference is 'fantasy,' and their emotion data indicates 'fun.'" This ensures that the generated story provides a unique experience for each user. The server also initializes an engine with emotion recognition capabilities, analyzing the user's emotion data to dynamically adjust the story's progression. The server aggregates this data, and after the game ends, it saves user feedback to a database to use for system improvement.

[0795] The terminal serves as the user interface. Upon user login, the terminal displays a preference input screen to collect user preferences. This information is used to present stories and choices through visual and auditory media. The terminal is equipped with an emotion recognition engine that enables real-time sentiment analysis. This emotion engine analyzes the user's facial expressions and tone of voice and transmits that data to the server.

[0796] Users participate in the game via their devices and become part of the story. They first log in and enter preference information requested by the system. As the game progresses, they choose from presented options, and their choices, along with their facial expressions and tone of voice, directly influence the story's development. When facial expressions or voice convey emotions such as anxiety or joy, the system dynamically adjusts the story based on that data, providing users with a deeply immersive experience.

[0797] For example, if a user selects an option and expresses anxiety, the server adjusts the story to generate a reassuring narrative. Conversely, if positive emotions are detected, the plot develops into an exciting one. This allows the story to flexibly change according to the user's emotional state, creating a more engaging experience.

[0798] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0799] Step 1: Enter user preference information

[0800] When a user logs in, the terminal displays a preference information input screen. Through this screen, the user enters their interests, preferred themes, and story styles. The entered information is collected as digital data and sent to the server. At this stage, data regarding the user's preferences is delivered to the server as output.

[0801] Step 2: Generating the Story

[0802] The server receives user preference information as input. Based on this information, it uses a generative AI model to generate an original story. Specifically, it creates prompt statements to instruct the AI ​​to generate a story. For example, a prompt such as "Generate the next story development. This user's preference is 'fantasy,' and their emotion data indicates 'fun'" is used as input, and the generated story is obtained as output.

[0803] Step 3: Initial setup of the emotion engine

[0804] After receiving the generated story, the server performs the initial setup of its emotion recognition function. This includes configuring sensors and algorithms for analyzing the user's emotion data. Using the story and the system's initial setup data as input, the output is a ready state.

[0805] Step 4: Start the game

[0806] The device presents the user with a generated story and associated choices. This process displays story-based text, images, and audio, allowing the user to choose how to interact. The user's choices are received as input, and their actions and decisions are passed on to the next step as output.

[0807] Step 5: Collecting user emotions and reactions

[0808] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time. It uses the user's facial expression data and voice data acquired through the camera and microphone as input, generates emotional state data as output, and sends it to the server.

[0809] Step 6: Dynamically adjust the story

[0810] The server analyzes emotional state data received from the emotion engine as input. Based on the results, it dynamically adjusts the flow of the story. For example, if the user expresses anxiety, it prioritizes a reassuring development and generates an updated story as output.

[0811] Step 7: End the game and collect feedback

[0812] After completing a game, users submit their experiences and opinions through a feedback form. Based on this input, the server collects data on the overall success and areas for improvement of the game. As output, user feedback data is stored in a database and used to improve the system in the future.

[0813] (Application Example 2)

[0814] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0815] In recent years, there has been a growing demand for digital content that provides experiences tailored to individual user preferences. However, conventional systems have struggled to generate stories that reflect users' emotions in real time, resulting in insufficient immersion. Therefore, a system is needed that enables dynamic story development using emotion recognition.

[0816] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0817] In this invention, the server includes means for collecting user preference information, means for adjusting the story in real time based on the user's choices and reactions, and means for recognizing the user's emotions and further adjusting the story's progression based on those emotions. This enables a personalized story development that directly reflects the user's emotions.

[0818] "User preference information" refers to data that shows each user's individual preferences and interests, and is necessary information to provide personalized experiences.

[0819] "Methods for generating original stories" refers to a system that automatically creates unique storylines based on collected user preference information.

[0820] A "means of adjusting the story in real time" refers to a system that has the functionality to dynamically change the development of the story on the spot in response to the user's choices and reactions.

[0821] A "means of recognizing user emotions" refers to a system equipped with technology to analyze a user's facial expressions, tone of voice, etc., and determine their emotional state.

[0822] "Interactive dialogue with the user" refers to a two-way exchange where the system provides appropriate feedback based on the user's choices and responses.

[0823] "Means of facilitating the progression of the experience" are mechanisms that support the progression of the story so that users can experience it smoothly and immersively.

[0824] A "means of collecting feedback" refers to a system that has the function of collecting opinions and impressions from users after their experience.

[0825] The server has the function of collecting user preference information. Based on this information, an AI model can automatically generate an original story. After the story is generated, the server uses emotion recognition technology to collect data on the user's choices and reactions, and analyzes this in real time to dynamically adjust the story's progression. An emotion engine is used to adjust the story, branching the plot according to the user's emotions. After the game ends, data is accumulated to improve the entire system based on the user's emotional data and feedback.

[0826] The device presents the generated story and choices to the user visually and audibly through its user interface. The device is equipped with a camera and microphone, and incorporates an emotion engine that analyzes facial expressions and voice tone to evaluate the user's emotions in real time. This data is sent to a server and used to advance the story.

[0827] Users log in and input their preferences through the device's interface. During the game experience, users influence the story's progression through the choices presented, and their emotional data, such as facial expressions and voice, is reflected in the game in real time, providing an interactive experience. For example, when a user chooses either "adventure" or "romance," if emotions such as surprise or joy are detected, the plot unfolds accordingly.

[0828] An example of a prompt message would be: "If you were going on a university club trip, what kind of story would you want to experience? Are you looking for adventure, or do you want a heartwarming encounter? To make the experience even more exciting, we will adjust the scenario based on your facial expressions."

[0829] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0830] Step 1:

[0831] The server receives preference information from the user's device. This information is sent in XML or JSON format and contains elements that indicate the user's preferences. The server analyzes this data and prepares it for input into the generating AI model.

[0832] Step 2:

[0833] The server uses a generative AI model to generate an original story from the received preference information. The AI ​​model receives the user's preferences as prompts and generates a storyline. As output, the story's initial settings and plot information are generated and sent to the user's terminal.

[0834] Step 3:

[0835] The device presents the received narrative information to the user visually and audibly. The user is presented with multiple choices, each leading to a different development in the story. This information is displayed via the user interface, and the user's selection is entered.

[0836] Step 4:

[0837] The user selects one of the presented options and inputs it as selection information into the device. This choice will influence the progression of the story.

[0838] Step 5:

[0839] The device uses its camera and microphone to collect user facial and voice data. This data is analyzed through the device's emotion engine to assess the user's real-time emotional state.

[0840] Step 6:

[0841] Emotional data and selection information from the device are sent to the server. Based on this data, the server performs calculations to readjust the story plot. The adjusted plot incorporates changes that respond to the user's emotions, generating a new story development.

[0842] Step 7:

[0843] The revised plot is sent back to the device, presenting the user with a new narrative development. This process is repeated, resulting in an interactive experience based on the user's emotions.

[0844] Step 8:

[0845] After completing the story experience, users enter their opinions and impressions into a feedback form. This information is sent from the device to the server and stored in a database for system improvement.

[0846] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0847] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0848] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0849] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0850] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0851] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0852] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0853] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0854] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0855] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0856] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0857] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0858] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0859] 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.

[0860] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0861] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0862] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0863] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0864] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0865] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0866] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0867] The following is further disclosed regarding the embodiments described above.

[0868] (Claim 1)

[0869] Means of collecting user preference information,

[0870] A means of generating an original story based on this preference information,

[0871] A means of adjusting the story in real time based on user choices and reactions,

[0872] A means of facilitating game progression through interactive dialogue with the user,

[0873] A means of collecting user feedback after the game ends,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, further comprising means of enhancing user immersion by providing audio and images in accordance with the generated story and game progression.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising data analysis means for improving the entire system based on user progress and feedback.

[0879] "Example 1"

[0880] (Claim 1)

[0881] A means of collecting user preference information using an information device,

[0882] A means of generating an original story using a generative model based on this preference information,

[0883] A means of analyzing user choices and reactions to adjust the story in real time,

[0884] A means of facilitating the progress of a virtual experience through interactive dialogue using visual media,

[0885] A means of collecting user feedback after the virtual experience ends,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, further comprising means for providing visual and auditory information in accordance with the progression of a generated story or virtual experience to enhance sensory immersion.

[0889] (Claim 3)

[0890] The system according to claim 1, further comprising information analysis means for improving the entire system based on the user's progress and feedback.

[0891] "Application Example 1"

[0892] (Claim 1)

[0893] Means of collecting user preference information,

[0894] A means of generating an original story based on this preference information,

[0895] A means of adjusting the story in real time based on user choices and reactions,

[0896] A means of facilitating game progression through interactive dialogue with the user,

[0897] A means of collecting user feedback after the game ends,

[0898] A means of distributing the generated story through an information and communication network,

[0899] A means of providing audio and augmented reality representations using multiple output devices,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1 further includes means of enhancing user immersion by providing audio and augmented reality representations in accordance with the generated story and game progression.

[0903] (Claim 3)

[0904] The system according to claim 1, further comprising data analysis means for improving the entire system based on user progress and feedback.

[0905] "Example 2 of combining an emotion engine"

[0906] (Claim 1)

[0907] Means for obtaining user preference information,

[0908] A means of creating original stories by utilizing a generative AI model based on this preference information,

[0909] It features emotion recognition capabilities to analyze the user's facial expressions and voice tone, and provides a means to dynamically adjust the narrative in real time.

[0910] A means of supporting game progression using interactive dialogue that adapts to the user's different emotional states,

[0911] A means of collecting user feedback on their experience after the game ends,

[0912] A system that includes this.

[0913] (Claim 2)

[0914] The system according to claim 1, further comprising means for providing audio and visual information related to the generated story or game progression to enhance the user's emotional immersion.

[0915] (Claim 3)

[0916] The system according to claim 1, further comprising data processing means for improving the overall performance of the system based on user progress, sentiment data, and feedback.

[0917] "Application example 2 of combining emotional engines"

[0918] (Claim 1)

[0919] Means of collecting user preference information,

[0920] A means of generating an original story based on this preference information,

[0921] A means of adjusting the story in real time based on user choices and reactions,

[0922] A means of recognizing the user's emotions and further adjusting the progression of the story based on those emotions,

[0923] A means of facilitating the progression of the experience through interactive dialogue with the user,

[0924] A means of collecting user feedback after the experience ends,

[0925] A system that includes this.

[0926] (Claim 2)

[0927] The system according to claim 1, further comprising means of providing audio and images in accordance with the generated story and the progression of the experience to enhance user immersion.

[0928] (Claim 3)

[0929] The system according to claim 1, further comprising data analysis means for improving the entire system based on user sentiment data. [Explanation of Symbols]

[0930] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting user preference information, A means of generating an original story based on this preference information, A means of adjusting the story in real time based on user choices and reactions, A means of facilitating game progression through interactive dialogue with the user, A means of collecting user feedback after the game ends, A system that includes this.

2. The system according to claim 1, further comprising means of enhancing user immersion by providing audio and images in accordance with the generated story and game progression.

3. The system according to claim 1, further comprising data analysis means for improving the entire system based on user progress and feedback.

Images