System

Abstract

To provide a system.SOLUTION: An interactive adventure story system for presenting progress of a story and an option includes: story development means for developing a story through interaction with a generative AI by referring to story-related data; development control means for controlling development of a story by referring to a user's selection information; development reflection means for receiving a user's property data as input and reflecting the data on the development of a story; providing means for referring to operation information of a puzzle by a user, requesting the development control means to develop a story when the operation information shows a correct answer, and providing the user with a hint and an answer for the puzzle when the operation information indicates an incorrect answer; and interaction means for realizing an interaction with a user by using various kinds of input / output means.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] An object of the present invention is to provide a system that provides an interactive adventure story to develop children's problem-solving ability and creativity. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. It allows children to experience an interactive adventure story by referencing story-related data and developing the story through dialogue with generative AI. The development of the story is controlled by referring to the user's selection information, allowing children to participate in the progression of the story. By taking the user's characteristic data as input and reflecting it in the development of the story, it provides an experience tailored to each child's individual characteristics. It helps children develop problem-solving skills by providing hints and solutions based on puzzle operation information. By using various input / output means, dialogue with the user is realized, providing an environment in which children can freely participate in the story. The above describes the problem that the present invention aims to solve and the means for solving the problem.

[0006] "Story-related data" refers to information such as summary data, choice data, and puzzle data. "Summary data" refers to information that briefly summarizes the overall picture, background, and goals of the story. "Choice data" refers to information about the choices and actions presented to the user at each scene of the story. "Puzzle data" refers to information about the difficult problems and puzzles to be solved in the story. "User characteristic data" refers to information about the user, and refers to personal characteristics and attributes such as age, gender, place of residence, and personality. "Generative AI" is an interactive artificial intelligence model that develops the story, presents choices, and solves puzzles through dialogue with the user. "Interactive adventure story system" refers to a system that allows children to experience interactive adventure stories in virtual reality. This system refers to story-related data and user characteristic data and develops the story through dialogue with the generative AI. It also presents choices and solves puzzles through dialogue with the user, helping to develop children's problem-solving abilities and creativity. [Brief description of the drawings]

[0007] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5]FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] 4 is a sequence diagram showing a process flow of the data processing system according to the first embodiment. FIG. [Figure 12] 11 is a sequence diagram showing a process flow of the data processing system in application example 1. FIG. [Figure 13] FIG. 11 is a sequence diagram showing the flow of processing of the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 11 is a sequence diagram showing the flow of processing in the data processing system in application example 2 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0009] First, the terms used in the following description will be explained.

[0010] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

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

[0012] In the following embodiments, the storage with the code is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., Examples include hard disks, or magnetic tapes.

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

[0014] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

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

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

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

[0026] Next, a description will be given of the specific processing by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0027] An embodiment of the present invention has the following configuration. 1. Server: Loads and manages story-related data. Receives user characteristic data and reflects it in the development of the story. It begins a dialogue with the generating AI, which progresses the story and presents options. The development of the story is controlled by referring to the user's selection information. Refer to the puzzle operation information and provide hints and solutions. 2. Terminal: The computer is provided with various input / output means such as a speaker, a microphone, a keyboard, various input devices, and a display device for enabling dialogue with a user. Through communication with the server, it receives information about story progress, choices, and puzzles, and transmits the user's choices and operations to the server. 3. User: Players connect to the server via their terminal to start the story, choose options, solve puzzles, and so on. Enter your characteristic data and enjoy a story experience tailored to your own unique traits. 4.Generation AI: It is an interactive artificial intelligence model that runs on a server and is responsible for developing the story, presenting options, solving puzzles, and so on. The above is an embodiment of the present invention. The server is responsible for managing story-related data, reflecting the user's characteristic data, and controlling the dialogue with the generating AI, while the terminal functions as an interface for realizing dialogue with the user. Through the terminal, the user can progress through the story, select options, solve puzzles, and receive responses from the generating AI. With this embodiment, the user can experience an interactive adventure story and develop problem-solving skills and creativity.

[0028] The process flow of each embodiment will be described below.

[0029] Step 1: The user connects to the server through a terminal. A user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. The server receives characteristic data provided by the user (age, gender, place of residence, personality, etc.). Step 3: The server loads the story-related data. The server loads pre-prepared story-related data (summary data, choice data, puzzle data, etc.).

[0030] Step 4: The user requests to start the story. The user requests the start of a story on the terminal and sends it to the server. Step 5: The server initiates a dialogue with the generated AI. The server initiates a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. The user selects an option from those displayed on the terminal and transmits it to the server.

[0031] Step 7: The server develops the story based on the user's selection. The server refers to the user's selection information and develops the story using a generation AI. The developed story is then sent from the server to the device. Step 8: The user solves the story puzzle. When a puzzle is presented in the story, the user performs operations on the terminal to solve the puzzle. Step 9: The server provides the solution to the puzzle. The server refers to the puzzle operation information and provides hints and answers to the user.

[0032] Step 10: Repeat steps 6 through 9 until the story is finished. The user progresses through the story by choosing options and solving puzzles until the story ends.

[0033] The above is the specific flow of the program's processing. The user connects to the server via their terminal to start the story, select options, and solve puzzles. The server receives the user's requests and selections, and develops the story through dialogue with the generation AI and provides solutions to puzzles. In this way, the user can experience an interactive adventure story and develop their problem-solving skills and creativity.

[0034] Step 1: A user connects to a server through a terminal. The user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. The server receives the characteristic data (age, sex, place of residence, personality, etc.) provided by the user. Step 3: The server loads the story-related data. The server loads the story-related data (summary data, choice data, puzzle data, etc.) that have been prepared in advance.

[0035] Step 4: The user requests the start of the story. The user requests the start of the story on the terminal and sends it to the server. Step 5: The server starts a dialogue with the generated AI. The server starts a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. The user selects an option from those displayed on the terminal and transmits it to the server.

[0036] Step 7: The server develops the story based on the user's selection. The server refers to the user's selection information and develops the story using the generation AI. The developed story is sent from the server to the terminal. Step 8: The user solves the story puzzle. When a puzzle is presented in the story, the user performs operations on the terminal to solve the puzzle.

[0037] Step 9: The server provides the answer to the puzzle. The server refers to the operation information of the puzzle and provides hints and the answer to the user. Step 10: Repeat steps 6 to 9 until the story ends. Until the story ends, the user continues to choose options and solve puzzles to progress through the story.

[0038] The above is the specific flow of the program's processing. The user connects to the server via their terminal to start the story, select options, and solve puzzles. The server receives the user's requests and selections, and develops the story through dialogue with the generation AI and provides solutions to puzzles. In this way, the user can experience an interactive adventure story and develop their problem-solving skills and creativity.

[0039] Example 1 Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the smart device 14 is referred to as a "terminal." Conventional interactive adventure story systems have had difficulty in providing a personalized story experience that fully utilizes the user's characteristic data. In addition, there was a problem that the progress of the story and the presentation of choices were inconsistent, which prevented the user from immersing themselves in the story. Furthermore, there was also a problem in that the presentation of puzzles and their solutions did not provide appropriate hints that reflected the user's characteristics.

[0040] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generative AI model, a means for referring to user selection information to control the development of the story, a means for receiving user characteristic data as input and reflecting the data in the development of the story, a means for generating a prompt sentence and sending it to the generative AI model to generate a story, a means for referring to puzzle operation information and providing hints and answers, a means for implementing dialogue with the user using various input / output means, and a means for reading story-related data and caching it in an internal memory. This makes it possible to provide a personalized story experience according to the user's characteristics. "Story-related data" refers to all data including information on the story's progression, characters, and scenario.

[0041] A "generative AI model" is a system that uses conversational artificial intelligence to develop a story and generate options. "User selection information" refers to data on options selected by the user during the course of the story. "User characteristic data" refers to data that indicates the unique characteristics of a user, such as age, gender, place of residence, and personality. A "prompt sentence" refers to a sentence sent by the server to the generative AI model to generate the next development in the story.

[0042] "Puzzle operation information" refers to data regarding operations performed by a user regarding puzzles that the user must solve in a story. "Hints and Solutions" refers to information that provides clues or solutions when a user gets stuck on a puzzle. "Input / output means" refers to devices or interfaces (e.g. keyboard, mouse, touch screen, speaker, microphone) used to exchange information between a user and a system.

[0043] "Caching in internal memory" refers to a method of temporarily storing data in a memory area that can be accessed quickly, so that subsequent processing can be performed quickly.

[0044] (Mode for carrying out the invention) DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will now be described in detail with reference to the accompanying drawings.

[0045] System Configuration This system mainly consists of a server, a terminal, a user, and a generative AI model. The server is responsible for managing story-related data and generating stories through dialogue with the generative AI model, while the terminal functions as an interface with the user. Through the terminal, the user participates in the progression of the story and experiences an interactive adventure story.

[0046] server The server has a database that manages story-related data and caches that data in its internal memory. The server receives the user's attribute data and selection information, and sends a prompt sentence to the generative AI model based on this. The generative AI model uses a natural language processing model such as ChatGPT (registered trademark). The server obtains the next part of the generated story and the options, and sends them to the terminal. It also monitors information about the puzzles the user operates, and provides hints and answers as necessary. For example, if the user enters the attribute data "brave warrior," the server generates the following prompt sentence and sends it to the AI ​​model: "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark, the other is light. Which way will he go?"

[0047] Terminal The terminal has various input / output means for interacting with the user. Specifically, these include a speaker, microphone, keyboard, touch screen, and display. The terminal communicates with the server and presents the user with information about the progress of the story, choices, and puzzles. The terminal transmits user input and selection information to the server, and plays a role in progressing the story in real time.

[0048] User Users input their characteristic data into the system through their terminals and receive a personalized story experience. For example, if a user inputs characteristic data for being a "brave warrior," that characteristic will be reflected in the story and the options generated will be accordingly. As the story progresses, the user selects the options presented, and the story unfolds based on those choices. When solving puzzles presented in the story, the user inputs the answer, and the answer information is sent to the server.

[0049] Generative AI Models The generative AI model runs on a server and develops the story, generates options, and solves puzzles. Specifically, it uses natural language processing technology such as CHATGPT (registered trademark). The server sends prompts to the generative AI model, which then generates responses based on those prompts, allowing the story to dynamically develop according to the user's choices and actions.

[0050] Examples If the user selects "Fantasy Adventure Story", the system will act as follows: 1. Server operation: The server executes the SQL query SELECT FROM stories WHERE id = '001'; to retrieve data for story ID "001". Receive the user's characteristic data "brave warrior" and send the following prompt to the generative AI model: "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark, the other is light. Which way will he go?"

[0051] 2. How generative AI models work: The generative AI model receives the prompt and generates the option, "Would a brave warrior choose the dark path or the light path?" This option is returned to the server.

[0052] 3. Terminal operation: The server sends the options received from the generative AI model to the terminal, which displays them to the user. The user selects "go down a dark road" and the selection information is sent to the server. 4. Story progression: The server takes the user's selection and sends the following prompt to the generative AI model: "The user has chosen a dark path. It is dark inside the cave and there are sounds of movement. Would you like to use a lantern?"

[0053] The generative AI model generates the next development and sends it to the terminal via the server. In this way, users experience an interactive adventure story in real time, progressing through choices and puzzles.

[0054] Although the embodiment of the present invention has been described in detail above, this is merely an example and does not limit the technical scope of the present invention. It goes without saying that many other variations and modifications are possible within the technical scope of the present invention.

[0055] The flow of the identification process in the first embodiment will be described with reference to FIG. Step 1: The server reads story-related data from the database and caches it in its internal memory. The input of this step is a query to the database and the output is the cached story-related data. Specifically, the server executes the SQL query SELECT FROM stories WHERE id = '001'; and stores the retrieved data in memory.

[0056] Step 2: The user inputs his / her own characteristic data through the terminal. The input of this step is the user's input data, and the output is to send the characteristic data to the server. Specifically, the user enters the characteristics of a "brave warrior" into the input form and presses the send button.

[0057] Step 3: The server receives the user's characteristic data and generates a prompt based on it. The input of this step is the user's characteristic data, and the output is the generated prompt. Specifically, the server generates the prompt "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark and the other is light. Which one will he go through?"

[0058] Step 4: The server sends the generated prompt sentence to the generative AI model to get the next development of the story. The input of this step is the prompt sentence, and the output is the response from the generative AI model. Specifically, the server sends the prompt sentence to the generative AI model API and receives the response, "Will the brave warrior choose the dark path or the light path?"

[0059] Step 5: The server sends the response from the generative AI model to the terminal and presents it to the user. The input of this step is the response from the generative AI model, and the output is the option displayed to the user. Specifically, the server sends the option "Would the brave warrior choose the dark path or the light path?" to the terminal and displays it on the terminal's display.

[0060] Step 6: The user selects one of the options presented and sends it to the server through the terminal. The input of this step is the user's selection information, and the output is sending the selection information to the server. Specifically, the user clicks "Go down the dark road" and sends the selection information to the server.

[0061] Step 7: The server receives the user's selection information, generates the next prompt sentence, and sends it to the generative AI model again. The input of this step is the user's selection information, and the output is a new prompt sentence and the next response from the generative AI model. Specifically, the server generates a prompt sentence such as "The user chose the dark path. It is dark inside the cave, and there is a sound of something moving. Would you like to use a lantern?" and sends it to the generative AI model.

[0062] Step 8: The server sends the response from the generative AI model to the terminal and presents the next development to the user. The input of this step is the response from the generative AI model, and the output is the next development that is displayed to the user. Specifically, the server sends the option "Use the lantern?" to the terminal and displays it to the user.

[0063] Step 9: When a puzzle is presented during the story, the user solves the puzzle. The input of this step is the operation information of the puzzle, and the output is the answer information of the puzzle sent to the server. Specifically, the user inputs the presented switch combination and sends the answer "turn on switch 1 and switch 3" to the server.

[0064] Step 10: The server receives the user's puzzle answer information and judges whether it is correct. The input for this step is the user's answer information, and the output is the judgement result (correct / incorrect). Specifically, the server verifies the user's answer, and if it is correct, it requests the generative AI model to develop the next story, and if it is incorrect, it generates a hint and provides it to the user. It sends the hint "Switch 1 is correct, but the other switch is incorrect."

[0065] (Application example 1) Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0066] In conventional interactive adventure story systems, the development of the story in response to user input is limited, and customization to the individual characteristics and preferences of the user is not sufficiently performed. In addition, the difficulty and content of puzzles and quizzes given during the story are not dynamically adjusted according to the user's skill and progress. This makes it difficult for users to tire of the story and to maintain continuous interest.

[0067] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0068] In this invention, the server includes: a means for referring to story-related data and developing a story through dialogue with the generation AI; a means for controlling the development of the story by referring to user selection information; a means for receiving user characteristic data as an input and reflecting it in the development of the story; a means for referring to puzzle operation information and providing hints and answers; a means for realizing dialogue with the user using various input / output means; a means for operating on a mobile information terminal and generating and displaying story developments and puzzles in real time; a means for saving user progress and selection information in a database; and a means for generating appropriate prompt sentences based on user input using a generation AI model, thereby determining the next development of the story. This makes it possible to customize the story experience to suit the individual characteristics and preferences of the user, thereby maintaining the user's interest and providing puzzles and quizzes of appropriate difficulty and content, thereby improving user satisfaction.

[0069] "Story-related data" is a set of information including story summary, choice, and puzzle data. "Generative AI" is an artificial intelligence system that uses an artificial intelligence model to develop a story in response to user input, generate options, and solve puzzles. "User selection information" refers to information about options selected by the user while the story is progressing. "User characteristic data" is data that indicates characteristics such as the user's age, sex, place of residence, personality, and taste for adventure.

[0070] "Puzzle operation information" refers to input information when the user operates the puzzle. The "various input / output means" refers to a speaker, a microphone, a keyboard, various input devices, and a display device for interacting with a user. The term "mobile information terminal" refers to a smartphone or tablet terminal that a user can carry with them. "Means of generating and displaying story developments and puzzles in real time" refers to a function that runs on a mobile information terminal and instantly generates story developments and puzzles through dialogue with a generation AI, and displays them to the user.

[0071] "Means for saving information about a user's progress and selections in a database" refers to a function for saving in a database the selections and progress made by a user as he or she progresses through the story. "A means for using a generative AI model to generate an appropriate prompt sentence based on user input, thereby determining the next development of the story" refers to a function that uses a generative AI model to generate a prompt sentence in response to user input, and determines the next development of the story based on that prompt sentence.

[0072] (Mode for carrying out the invention) An embodiment of the present invention has the following configuration.

[0073] The server has a database (e.g., Firebase Firestore) for reading and managing story-related data, and an interface for receiving user characteristic data. Based on the characteristic data and selection information entered by the user via the terminal, the server controls the development of the story by interacting with a generation AI (e.g., OpenAI (registered trademark) ChatGPT (registered trademark)). The server also receives information on the user's operation of the puzzle and processes it to provide hints and answers accordingly.

[0074] The terminal (e.g., a smartphone) is equipped with interfaces such as a speaker, microphone, keyboard, various input devices, and a display device to enable interaction with the user. It also requires a network connection to communicate with the server. The terminal presents the progress of the story, choices, and puzzles in real time, and transmits the user's choices and operations to the server.

[0075] The user can start a story through the terminal and input characteristic data. The characteristic data includes information such as age, gender, place of residence, personality, and adventure preferences. Based on this data, the content of the story is customized. The user answers choices and puzzles presented during the story, and the results of the selection are sent to the server.

[0076] A generative AI model (e.g., OpenAI ChatGPT) runs on a server and develops the story, presents choices, and solves puzzles. Based on the user's input, the generative AI generates appropriate prompts, which determine the next development of the story.

[0077] As a concrete example, if the user selects "Adventure in a fantasy world," the following prompt will be generated at the beginning of the story: "You are an apprentice in a wizard's village. How would you respond to a dragon that suddenly appears in your village? Choose from the following options: 1. Talk to the dragon 2. Hide 3. Attack."

[0078] The user selects one of these options, and the story unfolds based on that choice. Prompts are generated on demand based on the user's input, so the story progresses dynamically, allowing the user to enjoy the game without getting bored. The user's progress and selection information are stored in a database on the server, so the user can check their progress at any time. This allows the user to enjoy an individually customized story experience, and by providing puzzles and quizzes with appropriate difficulty and content, it is possible to maintain interest for a long period of time.

[0079] The flow of the specific process in the application example 1 will be described with reference to FIG. Step 1: A user logs into a terminal and inputs property data. Input: User login information, characteristic data (age, gender, place of residence, personality, adventure preferences) Operation: The terminal acquires the user's characteristic data and transmits it to the server. Output: User's attribute data stored on the server Step 2: The server receives the user's characteristic data and asks the AI ​​to generate a story outline. Input: User's property data Operation: The server asks the generation AI to generate a prompt, sending a request of the form "Generate a story synopsis based on the user's characterization data." Output: A summary of the generated story

[0080] Step 3: A summary of the generated story is obtained and sent to the terminal. Input: A story synopsis generated by a generative AI model Operation: The server sends the generated story summary to the terminal and instructs it to be displayed. Output: A summary of the story displayed on your terminal.

[0081] Step 4: The user selects a story option and sends it from the device to the server. Input: User's choice Operation: The terminal sends the user's selection to the server. Output: User selections stored on the server

[0082] Step 5: The server requests the generation AI to carry out the next development based on the user's selection information. Input: User's selection information Operation: The server instructs the generation AI to generate the next development with the user's selection information. It sends a request in the form of "Please proceed with the story based on the choice selected by the user." Output: The next storyline generated

[0083] Step 6: The generated next story development is transmitted to the terminal and displayed. Input: The next story development generated by the generative AI model Operation: The server sends the generated next storyline to the terminal and instructs it to display it. Output: The next storyline displayed on the terminal.

[0084] Step 7: The user answers puzzles and quizzes presented as the story progresses and sends the answers from the terminal to the server. Input: The user's answers to puzzles and quizzes Operation: The device sends the answers to puzzles and quizzes entered by the user to the server. Output: User's answer information stored on the server

[0085] Step 8: The server evaluates the answers to puzzles and quizzes and provides hints and answers as needed. Input: User's puzzle or quiz answer information How it works: The server evaluates the answer and asks the generation AI to provide appropriate hints and answers. Output: Generated hints and solutions

[0086] Step 9: Get hints and answers for puzzles and quizzes and send them to your device. Input: Hints and answers generated by the generative AI model Operation: The server sends the generated hints and answers to the terminal and instructs it to display them. Output: Hints and answers displayed on the terminal

[0087] Step 10: Save the user's progress and selections in a database. Input: User progress, selection information How it works: The server stores the user's progress and selections in a database. Output: User progress and selections stored in a database

[0088] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0089] An embodiment of the present invention has the following configuration. 1. Server: Loads and manages story-related data. Receives user characteristic data and reflects it in the development of the story. It begins a dialogue with the generating AI, which progresses the story and presents options. The development of the story is controlled by referring to the user's selection information. Refer to the puzzle operation information and provide hints and solutions. By combining it with an emotion engine, it recognizes the user's emotions and adjusts the story development and choices.

[0090] 2. Terminal: It is equipped with a speaker, a microphone, a keyboard, various input devices, a display device, etc. to realize dialogue with the user. Through communication with the server, it receives information about story progress, choices, and puzzles, and transmits the user's choices and operations to the server.

[0091] 3. User: Players connect to the server via their terminal to start the story, choose options, solve puzzles, and so on. Enter your characteristic data and enjoy a story experience tailored to your own unique traits. The emotion engine recognizes emotions through voice, facial expressions, language, and other means that express emotions.

[0092] 4.Generation AI: It is an interactive artificial intelligence model that runs on a server and is responsible for developing the story, presenting options, solving puzzles, and so on.

[0093] 5. Emotion Engine: It runs on a server and analyzes information such as the user's voice, facial expressions, and language to infer the user's emotional state. The story development and choices are adjusted based on the estimated emotional state.

[0094] The above is an embodiment of the present invention. The server is responsible for managing story-related data, reflecting user characteristic data, controlling dialogue with the generation AI, and recognizing and adjusting emotions using the emotion engine. The terminal functions as an interface for realizing dialogue with the user, and the user progresses through the story, selects options, and solves puzzles while expressing emotions. This embodiment allows the user to enjoy a personalized story experience that is tailored to their emotions.

[0095] The process flow of each embodiment will be described below.

[0096] Step 1: The user connects to the server through a terminal. A user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. The server receives characteristic data provided by the user (age, gender, place of residence, personality, etc.). Step 3: The server loads the story-related data. The server loads pre-prepared story-related data (summary data, choice data, puzzle data, etc.). Step 4: The user requests to start the story. The user requests the start of a story on the terminal and sends it to the server. Step 5: The server initiates a dialogue with the generated AI. The server initiates a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. The user selects an option from those displayed on the terminal and transmits it to the server. Step 7: The server develops the story based on the user's selection. The server refers to the user's selection information and develops the story using a generation AI. The developed story is then sent from the server to the device. Step 8: The user solves the story puzzle. When a puzzle is presented in the story, the user performs operations on the terminal to solve the puzzle. Step 9: The server provides the solution to the puzzle. The server refers to the puzzle operation information and provides hints and answers to the user.

[0097] Step 10: Recognize user's emotions The emotion engine analyzes the user's emotions. Information such as the user's voice, facial expressions, and language is collected on the device and sent to the emotion engine. Step 11: The emotion engine estimates the user's emotional state. The emotion engine analyzes the received information and infers the user's emotional state. Step 12: The emotion engine adjusts the story development and choices. Based on the inferred emotional state, the emotion engine adjusts the story development and the presentation of options.

[0098] The above is the specific flow of the program's processing. The user connects to the server via their device to start the story, select options, and solve puzzles. The server receives the user's requests and selections, develops the story using generative AI, and provides the answers to the puzzles. The emotion engine also recognizes the user's emotions, and adjusts the story development and options based on the estimated emotional state. This allows the user to enjoy a personalized story experience that is tailored to their emotions.

[0099] Example 2 Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the smart device 14 is referred to as a "terminal."

[0100] Conventional interactive storytelling systems can develop a story based on the user's selection, but they have not been able to develop a story that reflects the user's emotional state in real time. As a result, it has been difficult for users to enjoy a personalized story experience according to their emotions and preferences. In particular, there is a demand for advanced responses, such as presenting story options and puzzles in response to changes in emotions, and technology to realize these is needed.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0102] In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with a generative AI model, a means for referring to user selection information and controlling the development of the story, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using an input / output device of the terminal, and a means for analyzing the user's emotional state using an emotion engine and adjusting the options and development of the story. This enables a personalized story experience that takes the user's emotional state into account.

[0103] "Story-related data" refers to all information necessary for the progression and development of the story, such as the story plot, character details, choice data, and puzzle data. A "generative AI model" is an interactive artificial intelligence model, an algorithm that generates narrative text based on input or prompts from a user. "Selection information" refers to data indicating the selection made by the user from among the options presented. "Characteristic data" refers to individual attribute data, such as a user's age, gender, place of residence, personality, and preferences, that are reflected in the development of the story. "Puzzle operation information" refers to data on operations and answers related to puzzles that a user solves within an interactive storytelling system. "Input / output device" refers to any hardware installed on a terminal that enables interaction with a user, such as a speaker, microphone, keyboard, or touch screen. An "emotion engine" refers to an algorithm that analyzes a user's voice, facial expression, and language data to infer the user's emotional state.

[0104] (Mode for carrying out the invention) An embodiment of the present invention has the following configuration. First, the server loads and manages story-related data. Story-related data consists of the story plot, character details, choice data, puzzle data, etc. The server retrieves this data from the database and uses it as information necessary for the development of the story. Next, the server receives the user's characteristic data as input and reflects it in the development of the story. The characteristic data includes information such as the user's age, gender, place of residence, personality, and preferences. Based on this data, the server adjusts the content of the story to provide a personalized story experience.

[0105] The server also starts a dialogue with the generative AI model to progress the story and present options. For example, CHATGPT (registered trademark) is used as the generative AI model. The server inputs a prompt sentence into the generative AI model, causing it to automatically generate the text of the story. For example, the following prompt sentence could be input: "Generate a story in which the user embarks on an adventure in a mountainous region." As the story progresses, when the user makes a choice, the device sends the selection information to the server. The server controls the development of the story based on the selection information and inputs new prompts to the generative AI model to generate the next chapter. For example, a prompt might be, "The user has selected a mountainous area, so please generate the next event."

[0106] In addition, when a puzzle needs to be presented, the server refers to the puzzle operation information and provides appropriate hints and solutions. For example, if a user gets stuck on a puzzle, the server can present hints through a generative AI model, allowing the user's experience to proceed smoothly. These transactions are communicated with the user through the terminal's input / output devices, which may include speakers, microphones, keyboards, and touch screens, allowing the user to make choices while reading the story and solving puzzles.

[0107] In addition, the emotion engine analyzes the user's voice and facial expression data to estimate the user's emotional state. The server can adjust the story's options and development based on this emotional state, making the story progress more appealing in line with the user's emotions. For example, if the user is scared, the emotion engine analyzes that state and communicates it to the server. Based on this information, the server can ask the generative AI model to provide options that will reassure the user.

[0108] As a concrete example, when a user instructs the device that "I want to enjoy an adventure story today," the server can select an adventure-themed story from the story-related data and input the following prompt sentence into the generative AI model: "Today you will generate an adventure story where the user searches for treasure in a mountainous region." In this way, a personalized story experience is provided according to the user's emotions and preferences, and this process allows the user to enjoy the story in a deeper and more emotional way.

[0109] The flow of the identification process in the second embodiment will be described with reference to FIG. Step 1: The server reads and prepares the story-related data. Story-related data (input) is retrieved from a database and includes plot, character details, choice data, puzzle data, etc. The server loads this data into memory and makes it available for the story to unfold (output).

[0110] Step 2: The user starts up the terminal and enters their user ID and password on the login screen. The terminal sends this input information to the server. The server performs authentication processing (data calculation), and if authentication is successful, retrieves the user's characteristic data from the database (input). The retrieved characteristic data (output) is used in server processing. Step 3: The server generates a prompt sentence to send to the generative AI model based on the user's characteristics data. This prompt sentence contains a customized story start message according to the user's characteristics (input). For example, it might be "If the user is 25 years old and likes adventure, generate the prologue of an adventure story" (output). Step 4: The server inputs a prompt sentence into the generative AI model. The generative AI model generates a prologue of the story based on this prompt sentence (output). The generated story text is returned to the server.

[0111] Step 5: The server sends the generated prologue of the story to the terminal. The terminal displays this text to the user and informs the user that the story has started. The user can then read the story and select one of the options presented (input). Step 6: The device sends the user's selection information to the server. The server updates the story's progress based on this selection information (input) (data processing). Specifically, it inputs a new prompt into the generative AI model, which then becomes something like "The user selected the mountainous region, so generate the next scene" (output).

[0112] Step 7: The server receives the new story chapter returned by the generative AI model (output) and sends it to the device, which again displays the story text and the next choice to the user, who makes another choice (input).

[0113] Step 8: The server runs the emotion engine to collect and analyze the user's voice and facial expression data. The device collects this data (input) from the microphone and camera and sends it to the server. The server uses the emotion engine to estimate the user's emotional state (data calculation). The analysis results are obtained as the user's emotional state (output).

[0114] Step 9: The server adjusts the story options and developments based on the analyzed emotional state (input). For example, if the user is surprised, it adds an option to reduce tension. Based on this, it inputs a new prompt sentence into the generative AI model, which generates an appropriate story chapter (output).

[0115] Step 10: The server sends the generated story chapter to the terminal, which displays it to the user. The terminal also displays the puzzle question to the user if a puzzle is required. The user attempts to solve (input) the puzzle and inputs the answer to the terminal. The terminal sends the answer information to the server.

[0116] Step 11: The server analyzes the user's answer information (input) and determines whether it is correct or not (data calculation). If the answer is correct, the server requests the generative AI model to generate the next chapter of the story and advances the story (output). If the answer is incorrect, the server provides a hint through the generative AI model. The above steps provide a personalized narrative experience that responds to the user's emotions and preferences in real time.

[0117] (Application example 2) Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0118] Conventional interactive adventure story systems were able to develop a story based on the user's selection information and attribute data, but they did not provide a story experience that reflected the user's emotional state. For this reason, there is a demand for a deeper sense of immersion and empathy that corresponds to the user's emotions. In addition, the development of a system that realizes a story experience optimized for each individual user by providing different storylines depending on the user's emotional state was a challenge. The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0119] In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generation AI, a means for controlling the development of the story by referring to user selection information, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using various input / output means, an emotion analysis means for analyzing the user's emotional state and adjusting the development of the story and options, and a means for selecting a story segment according to the emotional state and presenting it to the user. This enables the progress of the story to reflect the user's emotional state, making it possible to provide a deeper immersive and personalized story experience.

[0120] "Story-related data" refers to a group of data necessary for the progression and development of the story, and includes summary data, choice data, puzzle data, and emotion data. "Generative AI" is an interactive artificial intelligence model that progresses the story, presents options, solves puzzles, and so on. "User selection information" refers to information about options selected by the user during the progress of the story, and is used to control the development of the story. "User attribute data" is data regarding the characteristics of a user, such as the user's age, sex, place of residence, personality, and emotional state.

[0121] "Puzzle operation information" is information obtained when a user operates a puzzle, and is used to provide hints and solutions. The "input / output means" refers to means for realizing dialogue with a user, such as a speaker, a microphone, a keyboard, various input devices, and a display device. The "emotion analysis means" is a means for analyzing information such as the user's voice, facial expression, and language, and for inferring the user's emotional state. A "narrative segment" is a collection of text and options that form part of a narrative and are presented to the user depending on their emotional state.

[0122] (Mode for carrying out the invention) In order to carry out this invention, a system consisting of three main components is required: a server, a terminal, and a user. Specifically, the system includes the following components:

[0123] server The server is the central point for progressing the story and presenting choices. The server includes the following mechanisms: A means of referencing story-related data and developing a story through dialogue with generative AI. A means for controlling the development of a story by referring to information selected by a user. A means of receiving user characteristic data as input and reflecting it in the development of the story. A means of referencing puzzle operation information and providing hints and solutions. A means of using emotion analysis to analyze the user's emotional state and adjust the story development and choices. A means for selecting and presenting narrative segments to a user according to an emotional state.

[0124] Terminal The terminal acts as an interface with the user and includes the following equipment and software: Input / output means include a speaker, a microphone, a keyboard, various input devices, and a display device. Through communication with the server, it receives information about story progress, choices, and puzzles, and transmits the user's choices and operations to the server.

[0125] User The user connects to the server through a terminal and starts the story, selects options, and solves puzzles. By inputting characteristic data, the user can experience a story that is tailored to their own characteristics. The emotion engine recognizes emotions through voice, facial expressions, language, and other elements that express emotions.

[0126] Hardware and software used The server is made up of computers with high processing power and is used to manage story-related data, run generative AI, and process sentiment analysis.

[0127] The emotion analysis means is software that operates as an emotion engine, and for example, uses image analysis by OpenCV and a natural language processing model (Hugging Face's Transformers pipeline). The device is equipped with a camera and microphone, making it possible to collect emotion data. This allows the user's facial expressions and voice to be analyzed, and their emotional state to be estimated.

[0128] Examples For example, if the user is analyzed as being in a stressful situation, the story progression will be adjusted to a relaxing content, whereas if the user is in a very positive emotional state, the story progression will present stimulating choices.

[0129] Examples of prompt statements "Write an interactive story application that recognizes the user's emotions from image data and progresses the story by choosing options according to the emotions." In this way, users can enjoy a more personal and emotionally connected narrative experience.

[0130] The flow of the specific process in the application example 2 will be described with reference to FIG. Step 1: The server loads the story-related data. The data required for the progression of the story, the presentation of choices, and the solving of puzzles is imported and stored on the server. The story-related data file is used as input, and the output is stored in the data storage in the server. Step 2: The user selects a story genre through the terminal and starts the story. The terminal receives the selected genre information from the user and sends it to the server. The input is the user's genre selection, and the output is a request containing that information sent to the server. Step 3: The server receives the user's characteristic data. This data includes age, gender, place of residence, personality, and emotional state. The input is the characteristic data sent from the terminal, and the output is the characteristic data stored in the server. The characteristic data is used as the basic information for the story development.

[0131] Step 4: The device collects the user's emotional state using the camera and microphone. The image data captured by the camera and the voice data collected by the microphone are input, and are temporarily stored in the device. The output is stored in the device as the user's emotional data. Step 5: The terminal sends image data and voice data to the server. The input is the emotion data stored in the terminal, and the output is a request including the emotion data being sent to the server. Step 6: The server analyzes the received image and audio data to estimate the user's emotional state. The emotion analysis method used here is OpenCV and the Hugging Face Transformers pipeline. The input is the image and audio data, and the output is the estimated emotional state.

[0132] Step 7: The server selects the next story segment based on the emotional state. Based on the emotional state obtained by the emotion analysis means, it selects an appropriate segment from the story related data. The input is the estimated emotional state and the output is the selected story segment. Step 8: The server sends the selected story segment to the terminal. The input is the selected story segment, and the output is a response including the story segment being sent to the terminal. Step 9: The terminal presents the received story segment to the user. Story text and options are displayed and the user selects an option to proceed. The input is the story segment from the server and the output is the user's selection.

[0133] Step 10: Send the user's selection from the terminal to the server. The selection is taken as input and sent to the server. The output is a request containing the selection. Step 11: The server advances the story based on the received selection information and repeats the process from step 6. This allows the story to progress in real time according to the user's selection and emotional state. The input is the user's selection information, and the output is the updated story segment.

[0134]

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0136] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0137] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0138] [Second embodiment]

[0139] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0140] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0142] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0143] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0146] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0149] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0150] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0151] An embodiment of the present invention has the following configuration. 1. Server: Loads and manages story-related data. Receives user characteristic data and reflects it in the development of the story. It begins a dialogue with the generating AI, which progresses the story and presents options. The development of the story is controlled by referring to the user's selection information. Refer to the puzzle operation information and provide hints and solutions. 2. Terminal: It is equipped with a speaker, a microphone, a keyboard, various input devices, a display device, etc. to realize dialogue with the user. Through communication with the server, it receives information about story progress, choices, and puzzles, and transmits the user's choices and operations to the server. 3. User: Players connect to the server via their terminal to start the story, choose options, solve puzzles, and so on. Enter your characteristic data and enjoy a story experience tailored to your own unique traits.

[0152] 4.Generation AI: It is an interactive artificial intelligence model that runs on a server and is responsible for developing the story, presenting options, solving puzzles, and so on. The above is an embodiment of the present invention. The server is responsible for managing story-related data, reflecting the user's characteristic data, and controlling the dialogue with the generating AI, while the terminal functions as an interface for realizing dialogue with the user. Through the terminal, the user can progress through the story, select options, solve puzzles, and receive responses from the generating AI. This allows users to experience an interactive adventure story and develop their problem-solving and creativity skills.

[0153] The process flow will be explained below.

[0154] Step 1: A user connects to a server through a terminal. The user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. The server receives the characteristic data (age, sex, place of residence, personality, etc.) provided by the user. Step 3: The server loads the story-related data. The server loads the story-related data (summary data, choice data, puzzle data, etc.) that have been prepared in advance. Step 4: The user requests the start of the story. The user requests the start of the story on the terminal and sends it to the server.

[0155] Step 5: The server starts a dialogue with the generated AI. The server starts a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. The user selects an option from the options displayed on the terminal and sends it to the server. Step 7: The server develops the story based on the user's selection. The server refers to the user's selection information and develops the story using the generation AI. The developed story is sent from the server to the terminal. Step 8: The user solves the story puzzle. When a puzzle is presented in the story, the user performs operations on the terminal to solve the puzzle.

[0156] Step 9: The server provides the answer to the puzzle. The server refers to the operation information of the puzzle and provides hints and the answer to the user. Step 10: Repeat steps 6 to 9 until the story ends. Until the story ends, the user continues to choose options and solve puzzles to progress through the story. The above is the specific flow of the program's processing. The user connects to the server via their terminal to start the story, select options, and solve puzzles. The server receives the user's requests and selections, and develops the story through dialogue with the generation AI and provides solutions to puzzles. In this way, the user can experience an interactive adventure story and develop their problem-solving skills and creativity.

[0157] Example 1 Next, a description will be given of Example 1. 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". Conventional interactive adventure story systems have had difficulty in providing a personalized story experience that fully utilizes the user's characteristic data. In addition, there was a problem that the progress of the story and the presentation of choices were inconsistent, which prevented the user from immersing themselves in the story. Furthermore, there was also a problem in that the presentation of puzzles and their solutions did not provide appropriate hints that reflected the user's characteristics.

[0158] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generative AI model, a means for referring to user selection information to control the development of the story, a means for receiving user characteristic data as input and reflecting the data in the development of the story, a means for generating a prompt sentence and sending it to the generative AI model to generate a story, a means for referring to puzzle operation information and providing hints and answers, a means for implementing dialogue with the user using various input / output means, and a means for reading story-related data and caching it in an internal memory. This makes it possible to provide a personalized story experience according to the user's characteristics.

[0159] "Story-related data" refers to all data including information on the story's progression, characters, and scenario. A "generative AI model" is a system that uses conversational artificial intelligence to develop a story and generate options. "User selection information" refers to data on options selected by the user during the course of the story. "User characteristic data" refers to data that indicates the unique characteristics of a user, such as age, gender, place of residence, and personality. A "prompt sentence" refers to a sentence sent by the server to the generative AI model to generate the next development in the story. "Puzzle operation information" refers to data regarding operations performed by a user regarding puzzles that the user must solve in a story.

[0160] "Hints and Solutions" refers to information that provides clues or solutions when a user gets stuck on a puzzle. "Input / output means" refers to devices or interfaces (e.g. keyboard, mouse, touch screen, speaker, microphone) used to exchange information between a user and a system. "Caching in internal memory" refers to a method of temporarily storing data in a memory area that can be accessed quickly, so that subsequent processing can be performed quickly.

[0161] System Configuration This system mainly consists of a server, a terminal, a user, and a generative AI model. The server is responsible for managing story-related data and generating stories through dialogue with the generative AI model, while the terminal functions as an interface with the user. Through the terminal, the user participates in the progression of the story and experiences an interactive adventure story.

[0162] server The server has a database that manages story-related data and caches the data in its internal memory. The server receives the user's characteristic data and selection information, and sends prompts to the generative AI model based on this. The generative AI model uses a natural language processing model such as CHATGPT (registered trademark). The server obtains the next part of the generated story and the options, and sends them to the terminal. It also monitors information about the puzzles the user operates, and provides hints and answers as necessary.

[0163] For example, if a user enters the attribute data "brave warrior," the server generates the following prompt text and sends it to the AI ​​model: "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark, the other is light. Which way will he go?"

[0164] Terminal The terminal has various input / output means for interacting with the user. Specifically, these include a speaker, microphone, keyboard, touch screen, and display. The terminal communicates with the server and presents the user with information about the progress of the story, choices, and puzzles. The terminal transmits user input and selection information to the server, and plays a role in progressing the story in real time.

[0165] User Users input their characteristic data into the system through their terminals and receive a personalized story experience. For example, if a user inputs characteristic data for being a "brave warrior," that characteristic will be reflected in the story and the options generated will be accordingly. As the story progresses, the user selects the options presented, and the story unfolds based on those choices. When solving puzzles presented in the story, the user inputs the answer, and the answer information is sent to the server.

[0166] Generative AI Models The generative AI model runs on a server and develops the story, generates options, and solves puzzles. Specifically, it uses natural language processing technology such as CHATGPT (registered trademark). The server sends prompts to the generative AI model, which then generates responses based on those prompts, allowing the story to dynamically develop according to the user's choices and actions.

[0167] Examples If the user selects "Fantasy Adventure Story", the system will act as follows: 1. Server operation: The server executes the SQL query SELECT FROM stories WHERE id = '001'; to retrieve data for story ID "001". Receive the user's characteristic data "brave warrior" and send the following prompt to the generative AI model: "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark, the other is light. Which way will he go?"

[0168] 2. How generative AI models work: The generative AI model receives the prompt and generates the option, "Would a brave warrior choose the dark path or the light path?" This option is returned to the server.

[0169] 3. Terminal operation: The server sends the options received from the generative AI model to the terminal, which displays them to the user. The user selects "go down a dark road" and the selection information is sent to the server. 4. Story progression: The server takes the user's selection and sends the following prompt to the generative AI model: "The user has chosen a dark path. It is dark inside the cave and there are sounds of movement. Would you like to use a lantern?" The generative AI model generates the next development and sends it to the terminal via the server.

[0170] In this way, users experience an interactive adventure story in real time, progressing through choices and puzzles.

[0171] Although the embodiment of the present invention has been described in detail above, this is merely an example and does not limit the technical scope of the present invention. It goes without saying that many other variations and modifications are possible within the technical scope of the present invention.

[0172] The flow of the identification process in the first embodiment will be described with reference to FIG. Step 1: The server reads story-related data from the database and caches it in its internal memory. The input of this step is a query to the database and the output is the cached story-related data. Specifically, the server executes the SQL query SELECT FROM stories WHERE id = '001'; and stores the retrieved data in memory. Step 2: The user inputs his / her own characteristic data through the terminal. The input of this step is the user's input data, and the output is to send the characteristic data to the server. Specifically, the user enters the characteristics of a "brave warrior" into the input form and presses the send button.

[0173] Step 3: The server receives the user's characteristic data and generates a prompt based on it. The input of this step is the user's characteristic data, and the output is the generated prompt. Specifically, the server generates the prompt "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark and the other is light. Which one will he go through?" Step 4: The server sends the generated prompt sentence to the generative AI model to get the next development of the story. The input of this step is the prompt sentence, and the output is the response from the generative AI model. Specifically, the server sends the prompt sentence to the generative AI model API and receives the response, "Will the brave warrior choose the dark path or the light path?"

[0174] Step 5: The server sends the response from the generative AI model to the terminal and presents it to the user. The input of this step is the response from the generative AI model, and the output is the option displayed to the user. Specifically, the server sends the option "Would the brave warrior choose the dark path or the light path?" to the terminal and displays it on the terminal's display.

[0175] Step 6: The user selects one of the options presented and sends it to the server through the terminal. The input of this step is the user's selection information, and the output is sending the selection information to the server. Specifically, the user clicks "Go down the dark road" and sends the selection information to the server. Step 7: The server receives the user's selection information, generates the next prompt sentence, and sends it to the generative AI model again. The input of this step is the user's selection information, and the output is a new prompt sentence and the next response from the generative AI model. Specifically, the server generates a prompt sentence such as "The user chose the dark path. It is dark inside the cave, and there is a sound of something moving. Would you like to use a lantern?" and sends it to the generative AI model.

[0176] Step 8: The server sends the response from the generative AI model to the terminal and presents the next development to the user. The input of this step is the response from the generative AI model, and the output is the next development that is displayed to the user. Specifically, the server sends the option "Use the lantern?" to the terminal and displays it to the user. Step 9: When a puzzle is presented during the story, the user solves the puzzle. The input of this step is the operation information of the puzzle, and the output is the answer information of the puzzle sent to the server. Specifically, the user inputs the presented switch combination and sends the answer "turn on switch 1 and switch 3" to the server.

[0177] Step 10: The server receives the user's puzzle answer information and judges whether it is correct. The input for this step is the user's answer information, and the output is the judgement result (correct / incorrect). Specifically, the server verifies the user's answer, and if it is correct, it requests the generative AI model to develop the next story, and if it is incorrect, it generates a hint and provides it to the user. It sends the hint "Switch 1 is correct, but the other switch is incorrect."

[0178] (Application example 1) Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal". In conventional interactive adventure story systems, the development of the story in response to user input is limited, and customization to the individual characteristics and preferences of the user is not sufficiently performed. In addition, the difficulty and content of puzzles and quizzes given during the story are not dynamically adjusted according to the user's skill and progress. This makes it difficult for users to tire of the story and to maintain continuous interest. The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0179] In this invention, the server includes: a means for referring to story-related data and developing a story through dialogue with the generation AI; a means for controlling the development of the story by referring to user selection information; a means for receiving user characteristic data as an input and reflecting it in the development of the story; a means for referring to puzzle operation information and providing hints and answers; a means for realizing dialogue with the user using various input / output means; a means for operating on a mobile information terminal and generating and displaying story developments and puzzles in real time; a means for saving user progress and selection information in a database; and a means for generating appropriate prompt sentences based on user input using a generation AI model, thereby determining the next development of the story. This makes it possible to customize the story experience to suit the individual characteristics and preferences of the user, thereby maintaining the user's interest and providing puzzles and quizzes of appropriate difficulty and content, thereby improving user satisfaction.

[0180] "Story-related data" is a set of information including story summary, choice, and puzzle data. "Generative AI" is an artificial intelligence system that uses an artificial intelligence model to develop a story in response to user input, generate options, and solve puzzles. "User selection information" refers to information about options selected by the user while the story is progressing. "User characteristic data" is data that indicates the user's characteristics such as age, sex, place of residence, personality, and taste for adventure.

[0181] "Puzzle operation information" refers to input information that is entered when the user operates the puzzle. The "various input / output means" refers to a speaker, a microphone, a keyboard, various input devices, and a display device for interacting with a user. The term "mobile information terminal" refers to a smartphone or tablet terminal that a user can carry with them. "Means of generating and displaying story developments and puzzles in real time" refers to a function that runs on a mobile information terminal and instantly generates story developments and puzzles through dialogue with a generation AI, and displays them to the user.

[0182] "Means for saving information about a user's progress and selections in a database" refers to a function for saving in a database the selections and progress made by a user as he or she progresses through the story. "A means for using a generative AI model to generate an appropriate prompt sentence based on user input, thereby determining the next development of the story" refers to a function that uses a generative AI model to generate a prompt sentence in response to user input, and determines the next development of the story based on that prompt sentence.

[0183] (Mode for carrying out the invention) An embodiment of the present invention has the following configuration. The server has a database (e.g., Firebase Firestore) for reading and managing story-related data, and an interface for receiving user characteristic data. Based on the characteristic data and selection information entered by the user via the terminal, the server controls the development of the story by interacting with a generation AI (e.g., OpenAI CHATGPT (registered trademark)). The server also receives information on the user's operation of the puzzle and processes it to provide hints and answers accordingly.

[0184] The terminal (e.g., a smartphone) is equipped with interfaces such as a speaker, microphone, keyboard, various input devices, and a display device to enable interaction with the user. It also requires a network connection to communicate with the server. The terminal presents the progress of the story, choices, and puzzles in real time, and transmits the user's choices and operations to the server.

[0185] The user can start a story through the terminal and input characteristic data. The characteristic data includes information such as age, gender, place of residence, personality, and adventure preferences. Based on this data, the content of the story is customized. The user answers choices and puzzles presented during the story, and the results of the selection are sent to the server.

[0186] A generative AI model (e.g., OpenAI CHATGPT (registered trademark)) runs on the server and develops the story, presents choices, and solves puzzles. This generative AI generates appropriate prompts based on the user's input, which determines the next development of the story.

[0187] As a concrete example, if the user selects "Adventure in a fantasy world," the following prompt will be generated at the beginning of the story: "You are an apprentice in a wizard's village. How would you respond to a dragon that suddenly appears in your village? Choose from the following options: 1. Talk to the dragon 2. Hide 3. Attack."

[0188] The user selects one of these options, and the story unfolds based on that choice. Prompts are generated as the user inputs, so the story progresses dynamically, allowing the user to enjoy the story without getting bored. Furthermore, the user's progress and selection information are stored in a database on the server, so the user can check their progress at any time.

[0189] This allows users to enjoy an individually customized story experience and keeps them interested for an extended period of time by providing puzzles and quizzes of appropriate difficulty and content.

[0190] The flow of the specific process in the application example 1 will be described with reference to FIG. Step 1: A user logs into a terminal and inputs property data. Input: User login information, characteristic data (age, gender, place of residence, personality, adventure preferences) Operation: The terminal acquires the user's characteristic data and transmits it to the server. Output: User's attribute data stored on the server

[0191] Step 2: The server receives the user's characteristic data and asks the AI ​​to generate a story outline. Input: User's property data Operation: The server asks the generation AI to generate a prompt, sending a request of the form "Generate a story synopsis based on the user's characterization data." Output: A summary of the generated story

[0192] Step 3: A summary of the generated story is obtained and sent to the terminal. Input: A story synopsis generated by a generative AI model Operation: The server sends the generated story summary to the terminal and instructs it to be displayed. Output: A summary of the story displayed on your terminal.

[0193] Step 4: The user selects a story option and sends it from the device to the server. Input: User's choice Operation: The terminal sends the user's selection to the server. Output: User selections stored on the server

[0194] Step 5: The server requests the generation AI to carry out the next development based on the user's selection information. Input: User's selection information Operation: The server instructs the generation AI to generate the next development with the user's selection information. It sends a request in the form of "Please proceed with the story based on the choice selected by the user." Output: The next storyline generated

[0195] Step 6: The generated next story development is transmitted to the terminal and displayed. Input: The next story development generated by the generative AI model Operation: The server sends the generated next storyline to the terminal and instructs it to display it. Output: The next storyline displayed on the terminal.

[0196] Step 7: The user answers puzzles and quizzes presented as the story progresses and sends the answers from the terminal to the server. Input: The user's answers to puzzles and quizzes Operation: The device sends the answers to puzzles and quizzes entered by the user to the server. Output: User's answer information stored on the server

[0197] Step 8: The server evaluates the answers to puzzles and quizzes and provides hints and answers as needed. Input: User's puzzle or quiz answer information How it works: The server evaluates the answer and asks the generation AI to provide appropriate hints and answers. Output: Generated hints and answers

[0198] Step 9: Get hints and answers for puzzles and quizzes and send them to your device. Input: Hints and answers generated by the generative AI model Operation: The server sends the generated hints and answers to the terminal and instructs it to display them. Output: Hints and answers displayed on the terminal

[0199] Step 10: Save the user's progress and selections in a database. Input: User progress, selection information How it works: The server stores the user's progress and selections in a database. Output: User progress and selections stored in a database

[0200] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0201] An embodiment of the present invention has the following configuration. 1. Server: - Load and manage story-related data. - Receives user characteristic data and reflects it in the development of the story. - Initiate a dialogue with the generating AI to progress the story and present options. - Control the development of the story by referring to the user's selection information. - Refer to the puzzle operation information and provide hints and solutions. - Combined with an emotion engine, it recognizes the user's emotions and adjusts the story development and choices.

[0202] 2. Terminal: - Equipped with a speaker, a microphone, a keyboard, various input devices, a display device, etc. for realizing dialogue with a user. - Receives story progress, choices, and puzzles through communication with the server, and transmits the user's choices and operations to the server.

[0203] 3. User: - Connect to the server via your terminal to start the story, choose options, solve puzzles, and more. - Enter your characteristic data and receive a story experience tailored to your own unique traits. - Emotions are recognized by the emotion engine through voice, facial expressions, language, etc. that express emotions.

[0204] 4.Generation AI: - An interactive artificial intelligence model that runs on a server and develops the story, presents options, solves puzzles, etc. 5. Emotion Engine: - It runs on the server and analyzes information such as the user's voice, facial expressions, and language to estimate the user's emotional state. - Adjust story development and choices based on estimated emotional state.

[0205] The above is an embodiment of the present invention. The server is responsible for managing story-related data, reflecting user characteristic data, controlling dialogue with the generation AI, and recognizing and adjusting emotions using the emotion engine. The terminal functions as an interface for realizing dialogue with the user, and the user progresses through the story, selects options, and solves puzzles while expressing emotions. This embodiment allows the user to enjoy a personalized story experience that is tailored to their emotions.

[0206] The process flow will be explained below.

[0207] Step 1: The user connects to the server through a terminal. - The user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. - The server receives characteristic data provided by the user (age, sex, place of residence, personality, etc.). Step 3: The server loads the story-related data. - The server loads pre-prepared story-related data (summary data, choice data, puzzle data, etc.).

[0208] Step 4: The user requests to start the story. - The user requests the start of the story on the terminal and sends it to the server. Step 5: The server initiates a dialogue with the generated AI. - The server initiates a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. - The user selects an option from the options displayed on the terminal and sends it to the server.

[0209] Step 7: The server develops the story based on the user's selection. - The server refers to the user's selection information and develops the story using the generation AI. The developed story is sent from the server to the terminal. Step 8: The user solves the story puzzle. - When a puzzle is presented in the story, the user performs operations on the device to solve the puzzle. Step 9: The server provides the solution to the puzzle. - The server refers to the puzzle operation information and provides hints and answers to the user.

[0210] Step 10: Recognize user's emotions The emotion engine analyzes the user's emotions. - Collect information such as the user's voice, facial expressions, and language on the device and send it to the emotion engine. Step 11: The emotion engine estimates the user's emotional state. - The emotion engine analyzes the received information and infers the user's emotional state. Step 12: The emotion engine adjusts the story development and choices. - Based on the estimated emotional state, the emotion engine adjusts the story development and the presentation of options.

[0211] The above is the specific flow of the program's processing. The user connects to the server via their device to start the story, select options, and solve puzzles. The server receives the user's requests and selections, develops the story using generative AI, and provides the answers to the puzzles. The emotion engine also recognizes the user's emotions, and adjusts the story development and options based on the estimated emotional state. This allows the user to enjoy a personalized story experience that is tailored to their emotions.

[0212] Example 2 Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0213] Conventional interactive storytelling systems can develop a story based on the user's selection, but they have not been able to develop a story that reflects the user's emotional state in real time. As a result, it has been difficult for users to enjoy a personalized story experience according to their emotions and preferences. In particular, there is a demand for advanced responses, such as presenting story options and puzzles in response to changes in emotions, and technology to realize these is needed.

[0214] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with a generative AI model, a means for referring to user selection information and controlling the development of the story, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using an input / output device of the terminal, and a means for analyzing the user's emotional state using an emotion engine and adjusting the options and development of the story. This enables a personalized story experience that takes the user's emotional state into account.

[0215] "Story-related data" refers to all information necessary for the progression and development of the story, such as the story plot, character details, choice data, and puzzle data. A "generative AI model" is an interactive artificial intelligence model, an algorithm that generates narrative text based on input or prompts from a user. "Selection information" refers to data indicating the selection made by the user from among the options presented. "Characteristic data" refers to individual attribute data, such as a user's age, gender, place of residence, personality, and preferences, that are reflected in the development of the story.

[0216] "Puzzle operation information" refers to data on operations and answers related to puzzles that a user solves within an interactive storytelling system. "Input / output device" refers to any hardware installed on a terminal that enables interaction with a user, such as a speaker, microphone, keyboard, or touch screen. An "emotion engine" refers to an algorithm that analyzes a user's voice, facial expression, and language data to infer the user's emotional state.

[0217] (Mode for carrying out the invention) An embodiment of the present invention has the following configuration. First, the server loads and manages story-related data. Story-related data consists of the story plot, character details, choice data, puzzle data, etc. The server retrieves this data from the database and uses it as information necessary for the development of the story.

[0218] Next, the server receives the user's characteristic data as input and reflects it in the development of the story. The characteristic data includes information such as the user's age, gender, place of residence, personality, and preferences. Based on this data, the server adjusts the content of the story to provide a personalized story experience.

[0219] The server also starts a dialogue with the generative AI model to progress the story and present options. For example, CHATGPT (registered trademark) is used as the generative AI model. The server inputs a prompt sentence into the generative AI model, causing it to automatically generate the text of the story. For example, the following prompt sentence could be input: "Generate a story in which the user embarks on an adventure in a mountainous region."

[0220] As the story progresses, when the user makes a choice, the device sends the selection information to the server. The server controls the development of the story based on the selection information and inputs new prompts to the generative AI model to generate the next chapter. For example, a prompt might be, "The user has selected a mountainous area, so please generate the next event."

[0221] Furthermore, when a puzzle needs to be presented, the server refers to the operation information of the puzzle and provides appropriate hints and solutions. For example, if a user gets stuck on a puzzle, the server can present hints through a generative AI model, allowing the user's experience to proceed smoothly. These processes are performed with the user through the input / output devices of the terminal. The terminal includes a speaker, microphone, keyboard, touch screen, etc. This allows the user to make choices and solve puzzles while reading the story.

[0222] In addition, the emotion engine analyzes the user's voice and facial expression data to estimate the user's emotional state. The server can adjust the story's options and development based on this emotional state, making the story progress more appealing in line with the user's emotions. For example, if the user is scared, the emotion engine analyzes that state and communicates it to the server. Based on this information, the server can ask the generative AI model to provide options that will reassure the user.

[0223] As a concrete example, when a user instructs the device that "I want to enjoy an adventure story today," the server can select an adventure-themed story from the story-related data and input the following prompt sentence into the generative AI model: "Today you will generate an adventure story where the user searches for treasure in a mountainous region."

[0224] In this way, a personalized story experience is provided according to the user's emotions and preferences, and this process allows the user to enjoy the story in a deeper and more emotional way.

[0225] The flow of the identification process in the second embodiment will be described with reference to FIG. Step 1: The server reads and prepares story-related data. Story-related data (input) is retrieved from a database and can include plot, character details, choice data, puzzle data, etc. The server loads this data into memory and makes it available for the story to unfold (output).

[0226] Step 2: The user starts up the terminal and enters their user ID and password on the login screen. The terminal sends this input information to the server. The server performs authentication processing (data calculation), and if authentication is successful, retrieves the user's characteristic data from the database (input). The retrieved characteristic data (output) is used in server processing.

[0227] Step 3: The server generates a prompt sentence to send to the generative AI model based on the user's characteristic data. This prompt sentence includes a customized story start message according to the user's characteristics (input). For example, the prompt sentence might be "If the user is 25 years old and likes adventure, generate the prologue of an adventure story" (output).

[0228] Step 4: The server inputs a prompt sentence into the generative AI model. The generative AI model generates a prologue of a story based on this prompt sentence (output). The generated story text is returned to the server.

[0229] Step 5: The server sends the prologue of the story to the terminal. The terminal displays this text to the user and informs the user that the story has started. The user can read the story and select one of the options presented (input).

[0230] Step 6: The device sends the user's selection information to the server. The server updates the story's progress based on this selection information (input) (data processing). Specifically, it inputs a new prompt into the generative AI model, which then becomes something like "The user selected the mountainous region, so generate the next scene" (output).

[0231] Step 7: The server receives the new story chapter returned by the generative AI model (output) and sends it to the device, which again displays the story text and the next choice to the user, who makes another choice (input).

[0232] Step 8: The server runs an emotion engine to collect and analyze the user's voice and facial expression data. The device collects this data (input) from a microphone and camera and sends it to the server. The server uses the emotion engine to estimate the user's emotional state (data calculation). The analysis results are obtained as the user's emotional state (output).

[0233] Step 9: The server adjusts the story options and development based on the analyzed emotional state (input). For example, if the user is surprised, it adds an option to reduce tension. Based on this, it inputs a new prompt sentence into the generative AI model, which then generates an appropriate story chapter (output).

[0234] Step 10: The server sends the generated story chapters to the terminal, which displays them to the user. The terminal also displays the puzzle questions to the user, if a puzzle is required. The user attempts to solve (input) the puzzle and enters the answer into the terminal. The terminal sends the answer information to the server.

[0235] Step 11: The server analyzes the user's answer information (input) and determines whether it is correct or not (data calculation). If the answer is correct, it requests the generative AI model to generate the next chapter of the story, and advances the story (output). If the answer is incorrect, it presents a hint through the generative AI model.

[0236] The above steps provide a personalized narrative experience that responds to the user's emotions and preferences in real time.

[0237] (Application example 2) Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0238] Conventional interactive adventure story systems were able to develop a story based on the user's selection information and attribute data, but they did not provide a story experience that reflected the user's emotional state. For this reason, there is a demand for a deeper sense of immersion and empathy that corresponds to the user's emotions. In addition, the development of a system that realizes a story experience optimized for each individual user by providing different storylines depending on the user's emotional state was a challenge.

[0239] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0240] In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generation AI, a means for controlling the development of the story by referring to user selection information, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using various input / output means, an emotion analysis means for analyzing the user's emotional state and adjusting the development of the story and options, and a means for selecting a story segment according to the emotional state and presenting it to the user. This enables the progress of the story to reflect the user's emotional state, making it possible to provide a deeper immersive and personalized story experience.

[0241] "Story-related data" refers to a group of data necessary for the progression and development of the story, and includes summary data, choice data, puzzle data, and emotion data. "Generative AI" is an interactive artificial intelligence model that progresses the story, presents options, solves puzzles, and so on. "User selection information" refers to information about options selected by the user during the progress of the story, and is used to control the development of the story. "User attribute data" is data regarding the characteristics of a user, such as the user's age, sex, place of residence, personality, and emotional state. "Puzzle operation information" is information obtained when a user operates a puzzle, and is used to provide hints and solutions.

[0242] The "input / output means" refers to means for realizing dialogue with a user, such as a speaker, a microphone, a keyboard, various input devices, and a display device. The "emotion analysis means" is a means for analyzing information such as the user's voice, facial expression, and language, and for inferring the user's emotional state. A "narrative segment" is a collection of text and options that form part of a narrative and are presented to the user depending on their emotional state.

[0243] (Mode for carrying out the invention) To implement this invention, a system consisting of three main components is required: a server, a terminal, and a user. Specifically, the system includes the following components:

[0244] server The server is the central point for progressing the story and presenting choices. The server includes the following mechanisms: A means of referencing story-related data and developing a story through dialogue with generative AI. A means for controlling the development of a story by referring to information selected by a user. A means of receiving user characteristic data as input and reflecting it in the development of the story. A means of referencing puzzle operation information and providing hints and solutions. A means of using emotion analysis to analyze the user's emotional state and adjust the story development and choices. A means for selecting and presenting narrative segments to a user according to an emotional state.

[0245] Terminal The terminal acts as an interface with the user and includes the following equipment and software: Input / output means include a speaker, a microphone, a keyboard, various input devices, and a display device. Through communication with the server, it receives information about story progress, choices, and puzzles, and transmits the user's choices and operations to the server.

[0246] User Users connect to the server via their terminal and begin the story, choose options, solve puzzles, and so on. Enter your characteristic data and enjoy a story experience tailored to your own unique traits. The emotion engine recognizes emotions through voice, facial expressions, language, and other means that express emotions.

[0247] Hardware and Software Used The server is made up of computers with high-performance processing power, and manages story-related data, runs generative AI, and processes sentiment analysis. The emotion analysis means is software that operates as an emotion engine, and uses, for example, image analysis by OpenCV and a natural language processing model (Hugging Face's Transformers pipeline). The device is equipped with a camera and microphone, and is capable of collecting emotional data, which allows the device to analyze the user's facial expressions and voice and estimate their emotional state.

[0248] Examples For example, if the user is analyzed as being in a stressful situation, the story progression will be adjusted to a relaxing content, whereas if the user is in a very positive emotional state, the story progression will present stimulating choices. Examples of prompt statements "Write an interactive story application that recognizes the user's emotions from image data and progresses the story by choosing options according to the emotions." In this way, users can enjoy a more personal and emotionally connected narrative experience.

[0249] The flow of the specific process in the application example 2 will be described with reference to FIG. Step 1: The server loads the story-related data. It imports data necessary for the progression of the story, the presentation of choices, and the solving of puzzles, and stores it on the server. Story-related data files are used as input, and the output is stored in the data storage in the server. Step 2: A user starts a story by selecting a story genre through a terminal. The terminal receives the selected genre information from the user and sends it to the server. The input is the user's genre selection, and the output is a request containing that information being sent to the server.

[0250] Step 3: The server receives the user's characteristic data. This data includes age, gender, place of residence, personality, and emotional state. The input is the characteristic data sent from the terminal, and the output is the characteristic data stored in the server. The characteristic data is used as basic information for the story development. Step 4: The device uses a camera and microphone to collect the user's emotional state. Image data captured by the camera and audio data collected by the microphone are input, and are temporarily stored in the device. The output is stored in the device as the user's emotional data.

[0251] Step 5: The terminal transmits image data and voice data to the server. The input is emotion data stored in the terminal, and the output is a request including the emotion data being transmitted to the server. Step 6: The server analyzes the received image and audio data to estimate the user's emotional state. The emotion analysis method used here is OpenCV and the Hugging Face Transformers pipeline. The input is image and audio data, and the output is the estimated emotional state.

[0252] Step 7: The server selects the next story segment based on the emotional state. The server chooses an appropriate segment from the story related data based on the emotional state obtained by the emotion analysis means. The input is the estimated emotional state and the output is the selected story segment. Step 8: The server sends the selected story segment to the terminal. The input is the selected story segment and the output is a response including the story segment sent to the terminal. Step 9: The terminal presents the received story segments to the user: story text and options are displayed and the user selects an option to proceed. The input is the story segment from the server and the output is the user's selection.

[0253] Step 10: The user's selection information is sent from the terminal to the server. The selection information is taken as input and sent to the server. The output is a request containing the selection information. Step 11: The server advances the story based on the received selection information and repeats the process from step 6. This allows the story to progress in real time according to the user's selections and emotional state. The input is the user's selection information, and the output is the updated story segment.

[0254] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0255] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generative AIs. Data generation model 58 is , obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0256] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0257] [Third embodiment]

[0258] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0259] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0260] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0261] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0262] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0263] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0264] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0265] Fig. 6 shows an example of main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0266] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0267] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0268] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0269] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server", and the headset type terminal 314 will be referred to as the "terminal".

[0270] An embodiment of the present invention has the following configuration. 1. Server: - Load and manage story-related data. - Receives user characteristic data and reflects it in the development of the story. - Initiate a dialogue with the generating AI to progress the story and present options. - Control the development of the story by referring to the user's selection information. - Refer to the puzzle operation information and provide hints and solutions. 2. Terminal: - Equipped with a speaker, a microphone, a keyboard, various input devices, a display device, etc. for realizing dialogue with a user. - Receives story progress, choices, and puzzles through communication with the server, and transmits the user's choices and operations to the server. 3. User: - Connect to the server via your terminal to start the story, choose options, solve puzzles, and more. - Enter your characteristic data and receive a story experience tailored to your own unique traits. 4.Generation AI: - An interactive artificial intelligence model that runs on a server and develops the story, presents options, solves puzzles, etc. The above is an embodiment of the present invention. The server is responsible for managing story-related data, reflecting the user's characteristic data, and controlling the dialogue with the generating AI, while the terminal functions as an interface for realizing dialogue with the user. Through the terminal, the user can progress through the story, select options, solve puzzles, and receive responses from the generating AI. With this embodiment, the user can experience an interactive adventure story and develop problem-solving skills and creativity.

[0271] The process flow will be explained below.

[0272] Step 1: A user connects to a server through a terminal. The user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. The server receives the characteristic data (age, sex, place of residence, personality, etc.) provided by the user. Step 3: The server loads the story-related data. The server loads the story-related data (summary data, choice data, puzzle data, etc.) that have been prepared in advance.

[0273] Step 4: The user requests the start of the story. The user requests the start of the story on the terminal and sends it to the server. Step 5: The server starts a dialogue with the generated AI. The server starts a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. The user selects an option from the options displayed on the terminal and sends it to the server.

[0274] Step 7: The server develops the story based on the user's selection. The server refers to the user's selection information and develops the story using the generation AI. The developed story is sent from the server to the terminal. Step 8: The user solves the story puzzle. When a puzzle is presented in the story, the user performs operations on the terminal to solve the puzzle. Step 9: The server provides the answer to the puzzle. The server refers to the operation information of the puzzle and provides hints and the answer to the user. Step 10: Repeat steps 6 to 9 until the story ends. Until the story ends, the user continues to choose options and solve puzzles to progress through the story.

[0275] The above is the specific flow of the program's processing. The user connects to the server via their terminal to start the story, select options, and solve puzzles. The server receives the user's requests and selections, and develops the story through dialogue with the generation AI and provides solutions to puzzles. In this way, the user can experience an interactive adventure story and develop their problem-solving skills and creativity.

[0276] Example 1 Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal". Conventional interactive adventure story systems have had difficulty in providing a personalized story experience that fully utilizes the user's characteristic data. In addition, there was a problem that the progress of the story and the presentation of choices were inconsistent, which prevented the user from immersing themselves in the story. Furthermore, there was also a problem in that the presentation of puzzles and their solutions did not provide appropriate hints that reflected the user's characteristics.

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

[0278] In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generative AI model, a means for referring to user selection information to control the development of the story, a means for receiving user characteristic data as input and reflecting the data in the development of the story, a means for generating a prompt sentence and sending it to the generative AI model to generate a story, a means for referring to puzzle operation information and providing hints and answers, a means for implementing dialogue with the user using various input / output means, and a means for reading story-related data and caching it in an internal memory. This makes it possible to provide a personalized story experience according to the user's characteristics. "Story-related data" refers to all data including information on the story's progression, characters, and scenario.

[0279] A "generative AI model" is a system that uses conversational artificial intelligence to develop a story and generate options. "User selection information" refers to data on options selected by the user during the course of the story. "User characteristic data" refers to data that indicates the unique characteristics of a user, such as age, gender, place of residence, and personality. A "prompt sentence" refers to a sentence sent by the server to the generative AI model to generate the next development in the story. "Puzzle operation information" refers to data regarding operations performed by a user regarding puzzles that the user must solve in a story. "Hints and Solutions" refers to information that provides clues or solutions when a user gets stuck on a puzzle. "Input / output means" refers to devices or interfaces (e.g. keyboard, mouse, touch screen, speaker, microphone) used to exchange information between a user and a system. "Caching in internal memory" refers to a method of temporarily storing data in a memory area that can be accessed quickly, so that subsequent processing can be performed quickly.

[0280] (Mode for Carrying Out the Invention) Mode for carrying out the invention will be described below. System Configuration This system mainly consists of a server, a terminal, a user, and a generative AI model. The server is responsible for managing story-related data and generating stories through dialogue with the generative AI model, while the terminal functions as an interface with the user. Through the terminal, the user participates in the progression of the story and experiences an interactive adventure story.

[0281] server The server has a database that manages story-related data and caches that data in its internal memory. The server receives the user's attribute data and selection information, and sends a prompt sentence to the generative AI model based on this. The generative AI model uses a natural language processing model such as CHATGPT (registered trademark). The server obtains the next part of the generated story and the options, and sends them to the terminal. It also monitors information about the puzzles the user operates, and provides hints and answers as necessary. For example, if the user enters the attribute data "brave warrior," the server generates the following prompt sentence and sends it to the AI ​​model: "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark, the other is light. Which way will he go?"

[0282] Terminal The terminal has various input / output means for interacting with the user. Specifically, these include a speaker, microphone, keyboard, touch screen, and display. The terminal communicates with the server and presents the user with information about the progress of the story, choices, and puzzles. The terminal transmits user input and selection information to the server, and plays a role in progressing the story in real time.

[0283] User Users input their characteristic data into the system through their terminals and receive a personalized story experience. For example, if a user inputs characteristic data for being a "brave warrior," that characteristic will be reflected in the story and the options generated will be accordingly. As the story progresses, the user selects the options presented, and the story unfolds based on those choices. When solving puzzles presented in the story, the user inputs the answer, and the answer information is sent to the server. Generative AI Models

[0284] The generative AI model runs on a server and develops the story, generates options, and solves puzzles. Specifically, it uses natural language processing technology such as CHATGPT (registered trademark). The server sends prompts to the generative AI model, which then generates responses based on those prompts, allowing the story to dynamically develop according to the user's choices and actions.

[0285] Examples If the user selects "Fantasy Adventure Story", the system will act as follows: 1. Server operation: The server executes the SQL query SELECT FROM stories WHERE id = '001'; to retrieve data for story ID "001". Receive the user's characteristic data "brave warrior" and send the following prompt to the generative AI model: "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark, the other is light. Which way will he go?" 2. How generative AI models work: The generative AI model receives the prompt and generates the option, "Would a brave warrior choose the dark path or the light path?" This option is returned to the server.

[0286] 3. Terminal operation: The server sends the options received from the generative AI model to the terminal, which displays them to the user. The user selects "go down a dark road" and the selection information is sent to the server.

[0287] 4. Story progression: The server takes the user's selection and sends the following prompt to the generative AI model: "The user has chosen a dark path. It is dark inside the cave and there are sounds of movement. Would you like to use a lantern?" The generative AI model generates the next development and sends it to the terminal via the server. In this way, users experience an interactive adventure story in real time, progressing through choices and puzzles.

[0288] Although the embodiment of the present invention has been described in detail above, this is merely an example and does not limit the technical scope of the present invention. It goes without saying that many other variations and modifications are possible within the technical scope of the present invention.

[0289] The flow of the identification process in the first embodiment will be described with reference to FIG. Step 1: The server reads story-related data from the database and caches it in its internal memory. The input of this step is a query to the database and the output is the cached story-related data. Specifically, the server executes the SQL query SELECT FROM stories WHERE id = '001'; and stores the retrieved data in memory. Step 2: The user inputs his / her own characteristic data through the terminal. The input of this step is the user's input data, and the output is to send the characteristic data to the server. Specifically, the user enters the characteristics of a "brave warrior" into the input form and presses the send button. Step 3: The server receives the user's characteristic data and generates a prompt based on it. The input of this step is the user's characteristic data, and the output is the generated prompt. Specifically, the server generates the prompt "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark and the other is light. Which one will he go through?"

[0290] Step 4: The server sends the generated prompt sentence to the generative AI model to get the next development of the story. The input of this step is the prompt sentence, and the output is the response from the generative AI model. Specifically, the server sends the prompt sentence to the generative AI model API and receives the response, "Will the brave warrior choose the dark path or the light path?"

[0291] Step 5: The server sends the response from the generative AI model to the terminal and presents it to the user. The input of this step is the response from the generative AI model, and the output is the option displayed to the user. Specifically, the server sends the option "Would the brave warrior choose the dark path or the light path?" to the terminal and displays it on the terminal's display. Step 6: The user selects one of the options presented and sends it to the server through the terminal. The input of this step is the user's selection information, and the output is sending the selection information to the server. Specifically, the user clicks "Go down the dark road" and sends the selection information to the server. Step 7: The server receives the user's selection information, generates the next prompt sentence, and sends it to the generative AI model again. The input of this step is the user's selection information, and the output is a new prompt sentence and the next response from the generative AI model. Specifically, the server generates a prompt sentence such as "The user chose the dark path. It is dark inside the cave, and there is a sound of something moving. Would you like to use a lantern?" and sends it to the generative AI model.

[0292] Step 8: The server sends the response from the generative AI model to the terminal and presents the next development to the user. The input of this step is the response from the generative AI model, and the output is the next development that is displayed to the user. Specifically, the server sends the option "Use the lantern?" to the terminal and displays it to the user. Step 9: When a puzzle is presented during the story, the user solves the puzzle. The input of this step is the operation information of the puzzle, and the output is the answer information of the puzzle sent to the server. Specifically, the user inputs the presented switch combination and sends the answer "turn on switch 1 and switch 3" to the server. Step 10: The server receives the user's puzzle answer information and judges whether it is correct. The input for this step is the user's answer information, and the output is the judgement result (correct / incorrect). Specifically, the server verifies the user's answer, and if it is correct, it requests the generative AI model to develop the next story, and if it is incorrect, it generates a hint and provides it to the user. It sends the hint "Switch 1 is correct, but the other switch is incorrect."

[0293] (Application example 1) Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0294] In conventional interactive adventure story systems, the development of the story in response to user input is limited, and customization to the individual characteristics and preferences of the user is not sufficiently performed. In addition, the difficulty and content of puzzles and quizzes given during the story are not dynamically adjusted according to the user's skill and progress. This makes it difficult for users to tire of the story and to maintain continuous interest.

[0295] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generation AI, a means for controlling the development of the story by referring to user selection information, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using various input / output means, a means for operating on a mobile information terminal and generating and displaying the development of the story and puzzles in real time, a means for saving the user's progress and selection information in a database, and a means for generating an appropriate prompt sentence based on the user's input using a generation AI model, thereby determining the next development of the story. This makes it possible to customize the story experience to suit the individual characteristics and preferences of the user, and it is possible to maintain the user's interest and provide puzzles and quizzes of appropriate difficulty and content, thereby improving the user's satisfaction.

[0296] "Story-related data" is a set of information including story summary, choice, and puzzle data. "Generative AI" is an artificial intelligence system that uses an artificial intelligence model to develop a story in response to user input, generate options, and solve puzzles. "User selection information" refers to information about options selected by the user while the story is progressing. "User characteristic data" is data that indicates characteristics such as the user's age, sex, place of residence, personality, and taste for adventure.

[0297] "Puzzle operation information" refers to input information when the user operates the puzzle. The "various input / output means" refers to a speaker, a microphone, a keyboard, various input devices, and a display device for interacting with a user. The term "mobile information terminal" refers to a smartphone or tablet terminal that a user can carry with them. "Means of generating and displaying story developments and puzzles in real time" refers to a function that runs on a mobile information terminal and instantly generates story developments and puzzles through dialogue with a generation AI, and displays them to the user.

[0298] "Means for saving information about a user's progress and selections in a database" refers to a function for saving in a database the selections and progress made by a user as he or she progresses through the story. "A means for using a generative AI model to generate an appropriate prompt sentence based on user input, thereby determining the next development of the story" refers to a function that uses a generative AI model to generate a prompt sentence in response to user input, and determines the next development of the story based on that prompt sentence.

[0299] (Mode for Carrying Out the Invention) The mode for carrying out the present invention has the following configuration. The server has a database (e.g., Firebase Firestore) for reading and managing story-related data, and an interface for receiving user characteristic data. Based on the characteristic data and selection information entered by the user via the terminal, the server controls the development of the story by interacting with a generation AI (e.g., OpenAI CHATGPT (registered trademark)). The server also receives information on the user's operation of the puzzle and processes it to provide hints and answers accordingly.

[0300] The terminal (e.g., a smartphone) is equipped with interfaces such as a speaker, microphone, keyboard, various input devices, and a display device to enable interaction with the user. It also requires a network connection to communicate with the server. The terminal presents the progress of the story, choices, and puzzles in real time, and transmits the user's choices and operations to the server.

[0301] The user can start a story through the terminal and input characteristic data. The characteristic data includes information such as age, gender, place of residence, personality, and adventure preferences. Based on this data, the content of the story is customized. The user answers choices and puzzles presented during the story, and the results of the selection are sent to the server.

[0302] A generative AI model (e.g., OpenAI CHATGPT (registered trademark)) runs on the server and develops the story, presents choices, and solves puzzles. This generative AI generates appropriate prompts based on the user's input, which determines the next development of the story. As a concrete example, if the user selects "Adventure in a fantasy world," the following prompt will be generated at the beginning of the story:

[0303] "You are an apprentice in a wizard's village. How would you respond to a dragon that suddenly appears in your village? Choose from the following options: 1. Talk to the dragon 2. Hide 3. Attack." The user selects one of these options, and the story unfolds based on that choice. Prompts are generated on demand based on the user's input, so the story progresses dynamically, allowing the user to enjoy the game without getting bored. The user's progress and selection information are stored in a database on the server, so the user can check their progress at any time. This allows the user to enjoy an individually customized story experience, and by providing puzzles and quizzes with appropriate difficulty and content, it is possible to maintain interest for a long period of time.

[0304] The flow of the specific process in the application example 1 will be described with reference to FIG. Step 1: The user logs in to the terminal and enters the property data. Input: User login information, characteristic data (age, gender, place of residence, personality, adventure preferences) Operation: The terminal acquires the user's characteristic data and sends it to the server. Output: User's characteristic data stored on the server

[0305] Step 2: The server receives the user's characteristic data and requests the generation AI to generate a story summary. Input: User's characteristic data Action: The server instructs the generation AI to generate a prompt text. It sends a request in the form of "Please generate a story summary based on the user's characteristic data." Output: Generated story summary

[0306] Step 3: Obtain the generated story summary and send it to the terminal. Input: Story summary generated by the generative AI model Operation: The server sends the generated story summary to the terminal and instructs it to display it. Output: Story summary displayed on the terminal

[0307] Step 4: The user selects a story option and sends it from the device to the server. Input: User's option Action: The device sends the user's selected option to the server. Output: User's selection information saved on the server

[0308] Step 5: The server requests the generation AI to generate the next development based on the user's selection information. Input: User's selection information Action: The server instructs the generation AI to generate the next development along with the user's selection information. It sends a request in the form of "Please proceed with the story based on the options selected by the user." Output: The next story development generated

[0309] Step 6: The generated next story development is sent to the terminal and displayed. Input: The next story development generated by the generative AI model Operation: The server sends the generated next story development to the terminal and instructs it to display it. Output: The next story development displayed on the terminal

[0310] Step 7: The user answers the puzzles and quizzes presented during the story and sends them from the device to the server. Input: User's answers to puzzles and quizzes Operation: The device sends the answers to puzzles and quizzes entered by the user to the server. Output: User's answers stored on the server

[0311] Step 8: The server evaluates the puzzle or quiz answer and provides hints or answers as necessary. Input: User's puzzle or quiz answer information Action: The server evaluates the answer and asks the generation AI to provide appropriate hints or answers. Output: Generated hints or answers

[0312] Step 9: Obtain hints and answers for puzzles and quizzes and send them to the device. Input: Hints and answers generated by the generative AI model. Operation: The server sends the generated hints and answers to the device and instructs it to display them. Output: Hints and answers displayed on the device.

[0313] Step 10: Save the user's progress and selections to the database. Input: User's progress and selections Action: The server saves the user's progress and selections to the database. Output: User's progress and selections saved in the database

[0314] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0315] An embodiment of the present invention has the following configuration. 1. Server: - Load and manage story-related data. - Receives user characteristic data and reflects it in the development of the story. - Initiate a dialogue with the generating AI to progress the story and present options. - Control the development of the story by referring to the user's selection information. - Refer to the puzzle operation information and provide hints and solutions. - Combined with an emotion engine, it recognizes the user's emotions and adjusts the story development and choices.

[0316] 2. Terminal: - Equipped with a speaker, a microphone, a keyboard, various input devices, a display device, etc. for realizing dialogue with a user. - Receives story progress, choices, and puzzles through communication with the server, and transmits the user's choices and operations to the server.

[0317] 3. User: - Connect to the server via your terminal to start the story, choose options, solve puzzles, and more. - Enter your characteristic data and receive a story experience tailored to your own unique traits. - Emotions are recognized by the emotion engine through voice, facial expressions, language, etc. that express emotions.

[0318] 4.Generation AI: - An interactive artificial intelligence model that runs on a server and develops the story, presents options, solves puzzles, etc.

[0319] 5. Emotion Engine: - It runs on the server and analyzes information such as the user's voice, facial expressions, and language to estimate the user's emotional state. - Adjust story development and choices based on estimated emotional state.

[0320] The above is an embodiment of the present invention. The server is responsible for managing story-related data, reflecting user characteristic data, controlling dialogue with the generation AI, and recognizing and adjusting emotions using the emotion engine. The terminal functions as an interface for realizing dialogue with the user, and the user progresses through the story, selects options, and solves puzzles while expressing emotions. This embodiment allows the user to enjoy a personalized story experience that is tailored to their emotions.

[0321] The process flow will be explained below.

[0322] Step 1: The user connects to the server through a terminal. - The user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. - The server receives characteristic data provided by the user (age, sex, place of residence, personality, etc.). Step 3: The server loads the story-related data. - The server loads pre-prepared story-related data (summary data, choice data, puzzle data, etc.).

[0323] Step 4: The user requests to start the story. - The user requests the start of the story on the terminal and sends it to the server. Step 5: The server initiates a dialogue with the generated AI. - The server initiates a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. - The user selects an option from the options displayed on the terminal and sends it to the server. Step 7: The server develops the story based on the user's selection. - The server refers to the user's selection information and develops the story using the generation AI. The developed story is sent from the server to the terminal.

[0324] Step 8: The user solves the story puzzle. - When a puzzle is presented in the story, the user performs operations on the device to solve the puzzle. Step 9: The server provides the solution to the puzzle. - The server refers to the puzzle operation information and provides hints and answers to the user. Step 10: Recognize user's emotions The emotion engine analyzes the user's emotions. - Collect information such as the user's voice, facial expressions, and language on the device and send it to the emotion engine.

[0325] Step 11: The emotion engine estimates the user's emotional state. - The emotion engine analyzes the received information and infers the user's emotional state. Step 12: The emotion engine adjusts the story development and choices. - Based on the estimated emotional state, the emotion engine adjusts the story development and the presentation of options.

[0326] The above is the specific flow of the program's processing. The user connects to the server via their device to start the story, select options, and solve puzzles. The server receives the user's requests and selections, develops the story using generative AI, and provides the answers to the puzzles. The emotion engine also recognizes the user's emotions, and adjusts the story development and options based on the estimated emotional state. This allows the user to enjoy a personalized story experience that is tailored to their emotions.

[0327] Example 2 Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal". Conventional interactive storytelling systems can develop a story based on the user's selection, but they have not been able to develop a story that reflects the user's emotional state in real time. As a result, it has been difficult for users to enjoy a personalized story experience according to their emotions and preferences. In particular, there is a demand for advanced responses, such as presenting story options and puzzles in response to changes in emotions, and technology to realize these is needed.

[0328] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with a generation AI model, a means for controlling the development of the story by referring to user selection information, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using an input / output device of the terminal, and a means for analyzing the user's emotional state using an emotion engine and adjusting the options and development of the story. This enables an individualized story experience that takes into account the user's emotional state.

[0329] "Story-related data" refers to all information necessary for the progression and development of the story, such as the story plot, character details, choice data, and puzzle data. A "generative AI model" is an interactive artificial intelligence model, an algorithm that generates narrative text based on input or prompts from a user. "Selection information" refers to data indicating the selection made by the user from among the options presented. "Characteristic data" refers to individual attribute data, such as a user's age, gender, place of residence, personality, and preferences, that are reflected in the development of the story.

[0330] "Puzzle operation information" refers to data on operations and answers related to puzzles that a user solves within an interactive storytelling system. "Input / output device" refers to any hardware installed on a terminal that enables interaction with a user, such as a speaker, microphone, keyboard, or touch screen. An "emotion engine" refers to an algorithm that analyzes a user's voice, facial expression, and language data to infer the user's emotional state.

[0331] (Mode for carrying out the invention) The embodiment of the present invention has the following configuration. First, the server reads and manages story-related data. Story-related data consists of the story plot, character details, choice data, puzzle data, etc. The server obtains this data from the database and uses it as information necessary for the development of the story.

[0332] Next, the server receives the user's characteristic data as input and reflects it in the development of the story. The characteristic data includes information such as the user's age, gender, place of residence, personality, and preferences. Based on this data, the server adjusts the content of the story to provide a personalized story experience.

[0333] The server also starts a dialogue with the generative AI model to progress the story and present options. For example, CHATGPT (registered trademark) is used as the generative AI model. The server inputs a prompt sentence into the generative AI model, causing it to automatically generate the text of the story. For example, the following prompt sentence could be input: "Generate a story in which the user embarks on an adventure in a mountainous region."

[0334] As the story progresses, when the user makes a choice, the device sends the selection information to the server. The server controls the development of the story based on the selection information and inputs new prompts to the generative AI model to generate the next chapter. For example, a prompt might be, "The user has selected a mountainous area, so please generate the next event."

[0335] Furthermore, when a puzzle needs to be presented, the server refers to the operation information of the puzzle and provides appropriate hints and solutions. For example, if a user gets stuck on a puzzle, the server can present hints through a generative AI model, allowing the user's experience to proceed smoothly. These processes are performed with the user through the input / output devices of the terminal. The terminal includes a speaker, microphone, keyboard, touch screen, etc. This allows the user to make choices and solve puzzles while reading the story.

[0336] In addition, the emotion engine analyzes the user's voice and facial expression data to estimate the user's emotional state. The server can adjust the story's options and development based on this emotional state, making the story progress more appealing in line with the user's emotions. For example, if the user is scared, the emotion engine analyzes that state and communicates it to the server. Based on this information, the server can ask the generative AI model to provide options that will reassure the user.

[0337] As a concrete example, when a user instructs the device that "I want to enjoy an adventure story today," the server can select an adventure-themed story from the story-related data and input the following prompt sentence into the generative AI model: "Today you will generate an adventure story where the user searches for treasure in a mountainous region." In this way, a personalized story experience is provided according to the user's emotions and preferences, and this process allows the user to enjoy the story in a deeper and more emotional way.

[0338] The flow of the identification process in the second embodiment will be described with reference to FIG. Step 1: The server reads and prepares the story-related data. Story-related data (input) is retrieved from a database and includes plot, character details, choice data, puzzle data, etc. The server loads this data into memory and makes it available for the story to unfold (output). Step 2: The user starts up the terminal and enters their user ID and password on the login screen. The terminal sends this input information to the server. The server performs authentication processing (data calculation), and if authentication is successful, retrieves the user's characteristic data from the database (input). The retrieved characteristic data (output) is used in server processing.

[0339] Step 3: The server generates a prompt sentence to send to the generative AI model based on the user's characteristics data. This prompt sentence contains a customized story start message according to the user's characteristics (input). For example, it might be "If the user is 25 years old and likes adventure, generate the prologue of an adventure story" (output). Step 4: The server inputs a prompt sentence into the generative AI model. The generative AI model generates a prologue of the story based on this prompt sentence (output). The generated story text is returned to the server.

[0340] Step 5: The server sends the generated prologue of the story to the terminal. The terminal displays this text to the user and informs the user that the story has started. The user can then read the story and select one of the options presented (input).

[0341] Step 6: The device sends the user's selection information to the server. The server updates the story's progress based on this selection information (input) (data processing). Specifically, it inputs a new prompt into the generative AI model, which then becomes something like "The user selected the mountainous region, so generate the next scene" (output).

[0342] Step 7: The server receives the new story chapter returned by the generative AI model (output) and sends it to the device, which again displays the story text and the next choice to the user, who makes another choice (input).

[0343] Step 8: The server runs the emotion engine to collect and analyze the user's voice and facial expression data. The device collects this data (input) from the microphone and camera and sends it to the server. The server uses the emotion engine to estimate the user's emotional state (data calculation). The analysis results are obtained as the user's emotional state (output).

[0344] Step 9: The server adjusts the story options and developments based on the analyzed emotional state (input). For example, if the user is surprised, it adds an option to reduce tension. Based on this, it inputs a new prompt sentence into the generative AI model, which generates an appropriate story chapter (output).

[0345] Step 10: The server sends the generated story chapter to the terminal, which displays it to the user. The terminal also displays the puzzle question to the user if a puzzle is required. The user attempts to solve (input) the puzzle and inputs the answer to the terminal. The terminal sends the answer information to the server.

[0346] Step 11: The server analyzes the user's answer information (input) and determines whether it is correct or not (data calculation). If the answer is correct, the server requests the generative AI model to generate the next chapter of the story and advances the story (output). If the answer is incorrect, the server provides a hint through the generative AI model. The above steps provide a personalized narrative experience that responds to the user's emotions and preferences in real time.

[0347] (Application example 2) Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[0348] Conventional interactive adventure story systems were able to develop a story based on the user's selection information and attribute data, but they did not provide a story experience that reflected the user's emotional state. For this reason, there is a demand for a deeper sense of immersion and empathy that corresponds to the user's emotions. In addition, the development of a system that realizes a story experience optimized for each individual user by providing different storylines depending on the user's emotional state was a challenge.

[0349] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generation AI, a means for controlling the development of the story by referring to user selection information, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using various input / output means, an emotion analysis means for analyzing the user's emotional state and adjusting the development of the story and options, and a means for selecting a story segment according to the emotional state and presenting it to the user. This enables the progress of the story to reflect the user's emotional state, making it possible to provide a deeper immersive and personalized story experience.

[0350] "Story-related data" refers to a group of data necessary for the progression and development of the story, and includes summary data, choice data, puzzle data, and emotion data. "Generative AI" is an interactive artificial intelligence model that progresses the story, presents options, solves puzzles, and so on. "User selection information" refers to information about options selected by the user during the progress of the story, and is used to control the development of the story. "User attribute data" is data regarding the characteristics of a user, such as the user's age, sex, place of residence, personality, and emotional state.

[0351] "Puzzle operation information" is information obtained when a user operates a puzzle, and is used to provide hints and solutions. The "input / output means" refers to means for realizing dialogue with a user, such as a speaker, a microphone, a keyboard, various input devices, and a display device. The "emotion analysis means" is a means for analyzing information such as the user's voice, facial expression, and language, and for inferring the user's emotional state. A "narrative segment" is a collection of text and options that form part of a narrative and are presented to the user depending on their emotional state.

[0352] (Mode for carrying out the invention) To implement this invention, a system consisting of three main components is required: a server, a terminal, and a user. Specifically, the system includes the following components:

[0353] server The server plays a central role in progressing the story and presenting options. The server includes the following means: a means for referring to story-related data and developing the story through dialogue with the generation AI; a means for controlling the development of the story by referring to the user's selection information; a means for receiving user characteristic data as input and reflecting it in the development of the story; a means for referring to puzzle operation information and providing hints and answers; a means for analyzing the user's emotional state using emotion analysis means and adjusting the development of the story and options; and a means for selecting story segments according to the emotional state and presenting them to the user.

[0354] Terminal The terminal functions as an interface with the user. It includes the following devices and software: a speaker, microphone, keyboard, various input devices, and a display device as input / output means. It receives information about the progress of the story, choices, and puzzles through communication with the server, and transmits the user's choices and operations to the server.

[0355] User The user connects to the server through a terminal and starts the story, selects options, and solves puzzles. By inputting characteristic data, the user can experience a story that is tailored to their own characteristics. The emotion engine recognizes emotions through voice, facial expressions, language, and other elements that express emotions.

[0356] The hardware and software servers used are comprised of computers with high processing power, and are used to manage story-related data, run generative AI, and process sentiment analysis.

[0357] The emotion analysis means is software that operates as an emotion engine, and uses, for example, image analysis by OpenCV and a natural language processing model (Hugging Face's Transformers pipeline).

[0358] The device is equipped with a camera and microphone, and is capable of collecting emotional data, which allows the device to analyze the user's facial expressions and voice and estimate their emotional state.

[0359] Examples For example, if the user is analyzed as being in a stressful situation, the story progression will be adjusted to a relaxing content, whereas if the user is in a very positive emotional state, the story progression will present stimulating choices. Examples of prompt statements "Write an interactive story application that recognizes the user's emotions from image data and progresses the story by choosing options according to the emotions." In this way, users can enjoy a more personal and emotionally connected narrative experience. The flow of the specific process in the application example 2 will be described with reference to FIG.

[0360] Step 1: The server loads the story-related data. The data required for the progression of the story, the presentation of choices, and the solving of puzzles is imported and stored on the server. The story-related data file is used as input, and the output is stored in the data storage in the server.

[0361] Step 2: The user selects a story genre through the terminal and starts the story. The terminal receives the selected genre information from the user and sends it to the server. The input is the user's genre selection, and the output is a request containing that information sent to the server.

[0362] Step 3: The server receives the user's characteristic data. This data includes age, gender, place of residence, personality, and emotional state. The input is the characteristic data sent from the terminal, and the output is the characteristic data stored in the server. The characteristic data is used as the basic information for the story development.

[0363] Step 4: The device collects the user's emotional state using the camera and microphone. The image data captured by the camera and the voice data collected by the microphone are input, and are temporarily stored in the device. The output is stored in the device as the user's emotional data.

[0364] Step 5: The terminal transmits image data and voice data to the server. The input is emotion data stored in the terminal, and the output is a request including the emotion data being transmitted to the server.

[0365] Step 6: The server analyzes the received image and audio data to estimate the user's emotional state. The emotion analysis method used here is OpenCV and the Hugging Face Transformers pipeline. The input is the image and audio data, and the output is the estimated emotional state.

[0366] Step 7: The server selects the next story segment based on the emotional state. Based on the emotional state obtained by the emotion analysis means, it selects an appropriate segment from the story related data. The input is the estimated emotional state and the output is the selected story segment.

[0367] Step 8: The server sends the selected story segment to the terminal. The input is the selected story segment, and the output is a response including the story segment being sent to the terminal.

[0368] Step 9: The terminal presents the received story segment to the user. Story text and options are displayed and the user selects an option to proceed. The input is the story segment from the server and the output is the user's selection.

[0369] Step 10: Send the user's selection from the terminal to the server. The selection is taken as input and sent to the server. The output is a request containing the selection.

[0370] Step 11: The server advances the story based on the received selection information and repeats the process from step 6. This allows the story to progress in real time according to the user's selection and emotional state. The input is the user's selection information, and the output is the updated story segment.

[0371] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0372] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0373] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314. [Fourth embodiment]

[0374] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0375] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0376] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0377] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0378] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0379] The camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. For example, an imaging range defined by an angle of view equivalent to the width of the visual field of a typical healthy person is imaged.

[0380] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0381] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0382] Fig. 8 shows an example of main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0383] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0384] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0385] In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0386] Next, a description will be given of the specific processing by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[0387] An embodiment of the present invention has the following configuration. 1. Server: - Load and manage story-related data. - Receives user characteristic data and reflects it in the development of the story. - Initiate a dialogue with the generating AI to progress the story and present options. - Control the development of the story by referring to the user's selection information. - Refer to the puzzle operation information and provide hints and solutions. 2. Terminal: - Equipped with a speaker, a microphone, a keyboard, various input devices, a display device, etc. for realizing dialogue with a user. - Receives story progress, choices, and puzzles through communication with the server, and transmits the user's choices and operations to the server. 3. User: - Connect to the server via your terminal to start the story, choose options, solve puzzles, and more. - Enter your characteristic data and receive a story experience tailored to your own unique traits. 4.Generation AI: - An interactive artificial intelligence model that runs on a server and develops the story, presents options, solves puzzles, etc. The above is an embodiment of the present invention. The server is responsible for managing story-related data, reflecting the user's characteristic data, and controlling the dialogue with the generating AI, while the terminal functions as an interface for realizing dialogue with the user. Through the terminal, the user can progress through the story, select options, solve puzzles, and receive responses from the generating AI. With this embodiment, the user can experience an interactive adventure story and develop problem-solving skills and creativity.

[0388] The process flow will be explained below.

[0389] Step 1: A user connects to a server through a terminal. The user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. The server receives the characteristic data (age, sex, place of residence, personality, etc.) provided by the user. Step 3: The server loads the story-related data. The server loads the story-related data (summary data, choice data, puzzle data, etc.) that have been prepared in advance.

[0390] Step 4: The user requests the start of the story. The user requests the start of the story on the terminal and sends it to the server. Step 5: The server starts a dialogue with the generated AI. The server starts a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. The user selects an option from the options displayed on the terminal and sends it to the server.

[0391] Step 7: The server develops the story based on the user's selection. The server refers to the user's selection information and develops the story using the generation AI. The developed story is sent from the server to the terminal. Step 8: The user solves the story puzzle. When a puzzle is presented in the story, the user performs operations on the terminal to solve the puzzle.

[0392] Step 9: The server provides the answer to the puzzle. The server refers to the operation information of the puzzle and provides hints and the answer to the user. Step 10: Repeat steps 6 to 9 until the story ends. Until the story ends, the user continues to choose options and solve puzzles to progress through the story.

[0393] The above is the specific flow of the program's processing. The user connects to the server via their terminal to start the story, select options, and solve puzzles. The server receives the user's requests and selections, and develops the story through dialogue with the generation AI and provides solutions to puzzles. In this way, the user can experience an interactive adventure story and develop their problem-solving skills and creativity.

[0394] Example 1 Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the robot 414 is referred to as a "terminal."

[0395] Conventional interactive adventure story systems have had difficulty in providing a personalized story experience that fully utilizes the user's characteristic data. In addition, there was a problem that the progress of the story and the presentation of choices were inconsistent, which prevented the user from immersing themselves in the story. Furthermore, there was also a problem in that the presentation of puzzles and their solutions did not provide appropriate hints that reflected the user's characteristics.

[0396] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generative AI model, a means for referring to user selection information to control the development of the story, a means for receiving user characteristic data as input and reflecting the data in the development of the story, a means for generating a prompt sentence and sending it to the generative AI model to generate a story, a means for referring to puzzle operation information and providing hints and answers, a means for implementing dialogue with the user using various input / output means, and a means for reading story-related data and caching it in an internal memory. This makes it possible to provide a personalized story experience according to the user's characteristics.

[0397] "Story-related data" refers to all data including information on the story's progression, characters, and scenario. A "generative AI model" is a system that uses conversational artificial intelligence to develop a story and generate options. "User selection information" refers to data on options selected by the user during the course of the story. "User characteristic data" refers to data that indicates the unique characteristics of a user, such as age, gender, place of residence, and personality. A "prompt sentence" refers to a sentence sent by the server to the generative AI model to generate the next development in the story.

[0398] "Puzzle operation information" refers to data regarding operations performed by a user regarding puzzles that the user must solve in a story. "Hints and Solutions" refers to information that provides clues or solutions when a user gets stuck on a puzzle. "Input / output means" refers to devices or interfaces (e.g. keyboard, mouse, touch screen, speaker, microphone) used to exchange information between a user and a system. "Caching in internal memory" refers to a method of temporarily storing data in a memory area that can be accessed quickly, so that subsequent processing can be performed quickly.

[0399] (Mode for carrying out the invention) DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will now be described in detail with reference to the accompanying drawings.

[0400] System Configuration This system mainly consists of a server, a terminal, a user, and a generative AI model. The server is responsible for managing story-related data and generating stories through dialogue with the generative AI model, while the terminal functions as an interface with the user. Through the terminal, the user participates in the progression of the story and experiences an interactive adventure story.

[0401] server The server has a database that manages story-related data and caches the data in its internal memory. The server receives the user's characteristic data and selection information, and sends prompts to the generative AI model based on this. The generative AI model uses a natural language processing model such as CHATGPT (registered trademark). The server obtains the next part of the generated story and the options, and sends them to the terminal. It also monitors information about the puzzles the user operates, and provides hints and answers as necessary. For example, if a user enters the attribute data "brave warrior," the server generates the following prompt text and sends it to the AI ​​model: "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark, the other is light. Which way will he go?"

[0402] Terminal The terminal has various input / output means for interacting with the user. Specifically, these include a speaker, microphone, keyboard, touch screen, and display. The terminal communicates with the server and presents the user with information about the progress of the story, choices, and puzzles. The terminal transmits user input and selection information to the server, and plays a role in progressing the story in real time.

[0403] User Users input their characteristic data into the system through their terminals and receive a personalized story experience. For example, if a user inputs characteristic data for being a "brave warrior," that characteristic will be reflected in the story and the options generated will be accordingly. As the story progresses, the user selects the options presented, and the story unfolds based on those choices. When solving puzzles presented in the story, the user inputs the answer, and the answer information is sent to the server.

[0404] Generative AI Models The generative AI model runs on a server and develops the story, generates options, and solves puzzles. Specifically, it uses natural language processing technology such as CHATGPT (registered trademark). The server sends prompts to the generative AI model, which then generates responses based on those prompts, allowing the story to dynamically develop according to the user's choices and actions.

[0405] Examples If the user selects "Fantasy Adventure Story", the system will act as follows: 1. Server operation: The server executes the SQL query SELECT FROM stories WHERE id = '001'; to retrieve data for story ID "001". Receive the user's characteristic data "brave warrior" and send the following prompt to the generative AI model: "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark, the other is light. Which way will he go?" 2. How generative AI models work: The generative AI model receives the prompt and generates the option, "Would a brave warrior choose the dark path or the light path?" This option is returned to the server. 3. Terminal operation: The server sends the options received from the generative AI model to the terminal, which displays them to the user. The user selects "go down a dark road" and the selection information is sent to the server. 4. Story progression: The server takes the user's selection and sends the following prompt to the generative AI model: "The user has chosen a dark path. It is dark inside the cave and there are sounds of movement. Would you like to use a lantern?"

[0406] The generative AI model generates the next development and sends it to the terminal via the server. In this way, users experience an interactive adventure story in real time, progressing through choices and puzzles.

[0407] Although the embodiment of the present invention has been described in detail above, this is merely an example and does not limit the technical scope of the present invention. It goes without saying that many other variations and modifications are possible within the technical scope of the present invention.

[0408] The flow of the identification process in the first embodiment will be described with reference to FIG. Step 1: The server reads story-related data from the database and caches it in its internal memory. The input of this step is a query to the database and the output is the cached story-related data. Specifically, the server executes the SQL query SELECT FROM stories WHERE id = '001'; and stores the retrieved data in memory. Step 2: The user inputs his / her own characteristic data through the terminal. The input of this step is the user's input data, and the output is to send the characteristic data to the server. Specifically, the user enters the characteristics of a "brave warrior" into the input form and presses the send button. Step 3: The server receives the user's characteristic data and generates a prompt based on it. The input of this step is the user's characteristic data, and the output is the generated prompt. Specifically, the server generates the prompt "The user is a brave warrior. There are two paths in the cave he is exploring. One is dark and the other is light. Which one will he go through?"

[0409] Step 4: The server sends the generated prompt sentence to the generative AI model to get the next development of the story. The input of this step is the prompt sentence, and the output is the response from the generative AI model. Specifically, the server sends the prompt sentence to the generative AI model API and receives the response, "Will the brave warrior choose the dark path or the light path?"

[0410] Step 5: The server sends the response from the generative AI model to the terminal and presents it to the user. The input of this step is the response from the generative AI model, and the output is the option displayed to the user. Specifically, the server sends the option "Would the brave warrior choose the dark path or the light path?" to the terminal and displays it on the terminal's display.

[0411] Step 6: The user selects one of the options presented and sends it to the server through the terminal. The input of this step is the user's selection information, and the output is sending the selection information to the server. Specifically, the user clicks "Go down the dark road" and sends the selection information to the server.

[0412] Step 7: The server receives the user's selection information, generates the next prompt sentence, and sends it to the generative AI model again. The input of this step is the user's selection information, and the output is a new prompt sentence and the next response from the generative AI model. Specifically, the server generates a prompt sentence such as "The user chose the dark path. It is dark inside the cave, and there is a sound of something moving. Would you like to use a lantern?" and sends it to the generative AI model.

[0413] Step 8: The server sends the response from the generative AI model to the terminal and presents the next development to the user. The input of this step is the response from the generative AI model, and the output is the next development that is displayed to the user. Specifically, the server sends the option "Use the lantern?" to the terminal and displays it to the user.

[0414] Step 9: When a puzzle is presented during the story, the user solves the puzzle. The input of this step is the operation information of the puzzle, and the output is the answer information of the puzzle sent to the server. Specifically, the user inputs the presented switch combination and sends the answer "turn on switch 1 and switch 3" to the server.

[0415] Step 10: The server receives the user's puzzle answer information and judges whether it is correct. The input for this step is the user's answer information, and the output is the judgement result (correct / incorrect). Specifically, the server verifies the user's answer, and if it is correct, it requests the generative AI model to develop the next story, and if it is incorrect, it generates a hint and provides it to the user. It sends the hint "Switch 1 is correct, but the other switch is incorrect."

[0416] (Application example 1) Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal." In conventional interactive adventure story systems, the development of the story in response to user input is limited, and customization to the individual characteristics and preferences of the user is not sufficiently performed. In addition, the difficulty and content of puzzles and quizzes given during the story are not dynamically adjusted according to the user's skill and progress. This makes it difficult for users to tire of the story and to maintain continuous interest. The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0417] In this invention, the server includes: a means for referring to story-related data and developing a story through dialogue with the generation AI; a means for controlling the development of the story by referring to user selection information; a means for receiving user characteristic data as an input and reflecting it in the development of the story; a means for referring to puzzle operation information and providing hints and answers; a means for realizing dialogue with the user using various input / output means; a means for operating on a mobile information terminal and generating and displaying story developments and puzzles in real time; a means for saving user progress and selection information in a database; and a means for generating appropriate prompt sentences based on user input using a generation AI model, thereby determining the next development of the story. This makes it possible to customize the story experience to suit the individual characteristics and preferences of the user, thereby maintaining the user's interest and providing puzzles and quizzes of appropriate difficulty and content, thereby improving user satisfaction.

[0418] "Story-related data" is a set of information including story summary, choice, and puzzle data. "Generative AI" is an artificial intelligence system that uses an artificial intelligence model to develop a story in response to user input, generate options, and solve puzzles. "User selection information" refers to information about options selected by the user while the story is progressing. "User characteristic data" is data that indicates the user's characteristics such as age, sex, place of residence, personality, and taste for adventure. "Puzzle operation information" refers to input information when the user operates the puzzle. The "various input / output means" refers to a speaker, a microphone, a keyboard, various input devices, and a display device for interacting with a user.

[0419] The term "mobile information terminal" refers to a smartphone or tablet terminal that a user can carry with them. "Means of generating and displaying story developments and puzzles in real time" refers to a function that runs on a mobile information terminal and instantly generates story developments and puzzles through dialogue with a generation AI, and displays them to the user. "Means for saving information about a user's progress and selections in a database" refers to a function for saving in a database the selections and progress made by a user as he or she progresses through the story. "A means for using a generative AI model to generate an appropriate prompt sentence based on user input, thereby determining the next development of the story" refers to a function that uses a generative AI model to generate a prompt sentence in response to user input, and determines the next development of the story based on that prompt sentence.

[0420] (Mode for carrying out the invention) An embodiment of the present invention has the following configuration.

[0421] The server has a database (e.g., Firebase Firestore) for reading and managing story-related data, and an interface for receiving user characteristic data. Based on the characteristic data and selection information entered by the user via the terminal, the server controls the development of the story by interacting with a generation AI (e.g., OpenAI CHATGPT (registered trademark)). The server also receives information on the user's operation of the puzzle and processes it to provide hints and answers accordingly.

[0422] The terminal (e.g., a smartphone) is equipped with interfaces such as a speaker, microphone, keyboard, various input devices, and a display device to enable interaction with the user. It also requires a network connection to communicate with the server. The terminal presents the progress of the story, choices, and puzzles in real time, and transmits the user's choices and operations to the server.

[0423] The user can start a story through the terminal and input characteristic data. The characteristic data includes information such as age, gender, place of residence, personality, and adventure preferences. Based on this data, the content of the story is customized. The user answers choices and puzzles presented during the story, and the results of the selection are sent to the server.

[0424] A generative AI model (e.g., OpenAI CHATGPT (registered trademark)) runs on the server and develops the story, presents options, and solves puzzles. This generative AI generates appropriate prompts based on the user's input, which then determine the next development of the story. As a concrete example, if the user selects "Adventure in a fantasy world," the following prompt is generated at the beginning of the story: "You are an apprentice in a wizard's village. How would you respond to a dragon that suddenly appears in your village? Choose from the following options: 1. Talk to the dragon 2. Hide 3. Attack."

[0425] The user selects one of these options, and the story unfolds based on that choice. Prompts are generated as the user inputs, so the story progresses dynamically, allowing the user to enjoy the story without getting bored. Furthermore, the user's progress and selection information are stored in a database on the server, so the user can check their progress at any time.

[0426] This allows users to enjoy an individually customized story experience and keeps them interested for an extended period of time by providing puzzles and quizzes of appropriate difficulty and content.

[0427] The flow of the specific process in the application example 1 will be described with reference to FIG. Step 1: A user logs into a terminal and inputs property data. Input: User login information, characteristic data (age, gender, place of residence, personality, adventure preferences) Operation: The terminal acquires the user's characteristic data and transmits it to the server. Output: User's attribute data stored on the server

[0428] Step 2: The server receives the user's characteristic data and asks the AI ​​to generate a story outline. Input: User's property data Operation: The server asks the generation AI to generate a prompt, sending a request of the form "Generate a story synopsis based on the user's characterization data." Output: A summary of the generated story

[0429] Step 3: A summary of the generated story is obtained and sent to the terminal. Input: A story synopsis generated by a generative AI model Operation: The server sends the generated story summary to the terminal and instructs it to be displayed. Output: A summary of the story displayed on your terminal.

[0430] Step 4: The user selects a story option and sends it from the device to the server. Input: User's choice Operation: The terminal sends the user's selection to the server. Output: User selections stored on the server

[0431] Step 5: The server requests the generation AI to carry out the next development based on the user's selection information. Input: User's selection information Operation: The server instructs the generation AI to generate the next development with the user's selection information. It sends a request in the form of "Please proceed with the story based on the choice selected by the user." Output: The next storyline generated

[0432] Step 6: The generated next story development is transmitted to the terminal and displayed. Input: The next story development generated by the generative AI model Operation: The server sends the generated next storyline to the terminal and instructs it to display it. Output: The next storyline displayed on the terminal.

[0433] Step 7: The user answers puzzles and quizzes presented as the story progresses and sends the answers from the terminal to the server. Input: The user's answers to puzzles and quizzes Operation: The device sends the answers to puzzles and quizzes entered by the user to the server. Output: User's answer information stored on the server

[0434] Step 8: The server evaluates the answers to puzzles and quizzes and provides hints and answers as needed. Input: User's puzzle or quiz answer information How it works: The server evaluates the answer and asks the generation AI to provide appropriate hints and answers. Output: Generated hints and solutions

[0435] Step 9: Get hints and answers for puzzles and quizzes and send them to your device. Input: Hints and answers generated by the generative AI model Operation: The server sends the generated hints and answers to the terminal and instructs it to display them. Output: Hints and answers displayed on the terminal

[0436] Step 10: Save the user's progress and selections in a database. Input: User progress, selection information How it works: The server stores the user's progress and selections in a database. Output: User progress and selections stored in a database

[0437] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0438] An embodiment of the present invention has the following configuration. 1. Server: - Load and manage story-related data. - Receives user characteristic data and reflects it in the development of the story. - Initiate a dialogue with the generating AI to progress the story and present options. - Control the development of the story by referring to the user's selection information. - Refer to the puzzle operation information and provide hints and solutions. - Combined with an emotion engine, it recognizes the user's emotions and adjusts the story development and choices.

[0439] 2. Terminal: - Equipped with a speaker, a microphone, a keyboard, various input devices, a display device, etc. for realizing dialogue with a user. - Receives story progress, choices, and puzzles through communication with the server, and transmits the user's choices and operations to the server.

[0440] 3. User: - Connect to the server via your terminal to start the story, choose options, solve puzzles, and more. - Enter your characteristic data and receive a story experience tailored to your own unique traits. - Emotions are recognized by the emotion engine through voice, facial expressions, language, etc. that express emotions.

[0441] 4.Generation AI: - An interactive artificial intelligence model that runs on a server and develops the story, presents options, solves puzzles, etc. 5. Emotion Engine: - It runs on the server and analyzes information such as the user's voice, facial expressions, and language to estimate the user's emotional state.

[0442] The story development and choices are adjusted based on the estimated emotional state. The above is an embodiment of the present invention. The server is responsible for managing story-related data, reflecting user characteristic data, controlling dialogue with the generation AI, and recognizing and adjusting emotions using the emotion engine. The terminal functions as an interface for realizing dialogue with the user, and the user progresses through the story, selects options, and solves puzzles while expressing emotions. This embodiment allows the user to enjoy a personalized story experience that is tailored to their emotions.

[0443] The process flow will be explained below.

[0444] Step 1: The user connects to the server through a terminal. - The user launches a specific application on the terminal and initiates a connection to the server. Step 2: The server receives the user's characteristic data. - The server receives characteristic data provided by the user (age, sex, place of residence, personality, etc.). Step 3: The server loads the story-related data. - The server loads pre-prepared story-related data (summary data, choice data, puzzle data, etc.).

[0445] Step 4: The user requests to start the story. - The user requests the start of the story on the terminal and sends it to the server. Step 5: The server initiates a dialogue with the generated AI. - The server initiates a dialogue with the generated AI, progressing the story and presenting options. Step 6: The user selects a story option. - The user selects an option from the options displayed on the terminal and sends it to the server.

[0446] Step 7: The server develops the story based on the user's selection. - The server refers to the user's selection information and develops the story using the generation AI. The developed story is sent from the server to the terminal. Step 8: The user solves the story puzzle. - When a puzzle is presented in the story, the user performs operations on the device to solve the puzzle. Step 9: The server provides the solution to the puzzle. - The server refers to the puzzle operation information and provides hints and answers to the user.

[0447] Step 10: Recognize user's emotions The emotion engine analyzes the user's emotions. - Collect information such as the user's voice, facial expressions, and language on the device and send it to the emotion engine. Step 11: The emotion engine estimates the user's emotional state. - The emotion engine analyzes the received information and infers the user's emotional state. Step 12: The emotion engine adjusts the story development and choices. - Based on the estimated emotional state, the emotion engine adjusts the story development and the presentation of options.

[0448] The above is the specific flow of the program's processing. The user connects to the server through their terminal, and starts the story, selects options, and answers puzzles. The server receives the user's requests and selections, develops the story using a generation AI, and provides the answers to the puzzles. The emotion engine recognizes the user's emotions and adjusts story development and choices based on the estimated emotional state, allowing the user to enjoy a personalized story experience that is tailored to their emotions.

[0449] Example 2 Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the robot 414 is referred to as a "terminal."

[0450] Conventional interactive storytelling systems can develop a story based on the user's selection, but they have not been able to develop a story that reflects the user's emotional state in real time. As a result, it has been difficult for users to enjoy a personalized story experience according to their emotions and preferences. In particular, there is a demand for advanced responses, such as presenting story options and puzzles in response to changes in emotions, and technology to realize these is needed.

[0451] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0452] In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with a generative AI model, a means for referring to user selection information and controlling the development of the story, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using an input / output device of the terminal, and a means for analyzing the user's emotional state using an emotion engine and adjusting the options and development of the story. This enables a personalized story experience that takes the user's emotional state into account.

[0453] "Story-related data" refers to all information necessary for the progression and development of the story, such as the story plot, character details, choice data, and puzzle data. A "generative AI model" is an interactive artificial intelligence model, an algorithm that generates narrative text based on input or prompts from a user. "Selection information" refers to data indicating the selection made by the user from among the options presented. "Characteristic data" refers to individual attribute data, such as a user's age, gender, place of residence, personality, and preferences, that are reflected in the development of the story. "Puzzle operation information" refers to data on operations and answers related to puzzles that a user solves within an interactive storytelling system.

[0454] "Input / output device" refers to any hardware installed on a terminal that enables interaction with a user, such as a speaker, microphone, keyboard, or touch screen. An "emotion engine" refers to an algorithm that analyzes a user's voice, facial expression, and language data to infer the user's emotional state.

[0455] (Mode for carrying out the invention) An embodiment of the present invention has the following configuration. First, the server loads and manages story-related data. Story-related data consists of the story plot, character details, choice data, puzzle data, etc. The server retrieves this data from the database and uses it as information necessary for the development of the story. Next, the server receives the user's characteristic data as input and reflects it in the development of the story. The characteristic data includes information such as the user's age, gender, place of residence, personality, and preferences. Based on this data, the server adjusts the content of the story to provide a personalized story experience.

[0456] The server also starts a dialogue with the generative AI model to progress the story and present options. For example, CHATGPT (registered trademark) is used as the generative AI model. The server inputs a prompt sentence into the generative AI model, causing it to automatically generate the text of the story. For example, the following prompt sentence could be input: "Generate a story in which the user embarks on an adventure in a mountainous region."

[0457] As the story progresses, when the user makes a choice, the device sends the selection information to the server. The server controls the development of the story based on the selection information and inputs new prompts to the generative AI model to generate the next chapter. For example, a prompt might be, "The user has selected a mountainous area, so please generate the next event."

[0458] In addition, when a puzzle needs to be presented, the server refers to the puzzle operation information and provides appropriate hints and solutions. For example, if a user gets stuck on a puzzle, the server can present hints through a generative AI model, allowing the user's experience to proceed smoothly.

[0459] These transactions are communicated with the user through the terminal's input / output devices, which may include speakers, microphones, keyboards, and touch screens, allowing the user to make choices while reading the story and solving puzzles.

[0460] In addition, the emotion engine analyzes the user's voice and facial expression data to estimate the user's emotional state. The server can adjust the story's options and development based on this emotional state, making the story progress more appealing in line with the user's emotions. For example, if the user is scared, the emotion engine analyzes that state and communicates it to the server. Based on this information, the server can ask the generative AI model to provide options that will reassure the user.

[0461] As a concrete example, when a user instructs the device that "I want to enjoy an adventure story today," the server can select an adventure-themed story from the story-related data and input the following prompt sentence into the generative AI model: "Today you will generate an adventure story where the user searches for treasure in a mountainous region."

[0462] In this way, a personalized story experience is provided according to the user's emotions and preferences, and this process allows the user to enjoy the story in a deeper and more emotional way.

[0463] The flow of the identification process in the second embodiment will be described with reference to FIG. Step 1: The server reads and prepares story-related data. Story-related data (input) is retrieved from a database and can include plot, character details, choice data, puzzle data, etc. The server loads this data into memory and makes it available for the story to unfold (output).

[0464] Step 2: The user starts up the terminal and enters their user ID and password on the login screen. The terminal sends this input information to the server. The server performs authentication processing (data calculation), and if authentication is successful, retrieves the user's characteristic data from the database (input). The retrieved characteristic data (output) is used in server processing.

[0465] Step 3: The server generates a prompt sentence to send to the generative AI model based on the user's characteristic data. This prompt sentence includes a customized story start message according to the user's characteristics (input). For example, the prompt sentence might be "If the user is 25 years old and likes adventure, generate the prologue of an adventure story" (output).

[0466] Step 4: The server inputs a prompt sentence into the generative AI model. The generative AI model generates a prologue of a story based on this prompt sentence (output). The generated story text is returned to the server.

[0467] Step 5: The server sends the prologue of the generated story to the terminal. The terminal displays this text to the user and informs the user that the story has started. The user can then read the story and select one of the options presented (input).

[0468] Step 6: The device sends the user's selection information to the server. The server updates the story's progress based on this selection information (input) (data processing). Specifically, it inputs a new prompt into the generative AI model, which then becomes something like "The user selected the mountainous region, so generate the next scene" (output).

[0469] Step 7: The server receives the new story chapter returned by the generative AI model (output) and sends it to the device, which again displays the story text and the next choice to the user, who makes another choice (input).

[0470] Step 8: The server runs an emotion engine to collect and analyze the user's voice and facial expression data. The device collects this data (input) from a microphone and camera and sends it to the server. The server uses the emotion engine to estimate the user's emotional state (data calculation). The analysis results are obtained as the user's emotional state (output).

[0471] Step 9: The server adjusts the story options and development based on the analyzed emotional state (input). For example, if the user is surprised, it adds an option to reduce tension. Based on this, it inputs a new prompt sentence into the generative AI model, which then generates an appropriate story chapter (output).

[0472] Step 10: The server sends the generated story chapters to the terminal, which displays them to the user. The terminal also displays the puzzle questions to the user, if a puzzle is required. The user attempts to solve (input) the puzzle and enters the answer into the terminal. The terminal sends the answer information to the server.

[0473] Step 11: The server analyzes the user's answer information (input) and determines whether it is correct or not (data calculation). If the answer is correct, it requests the generative AI model to generate the next chapter of the story, and advances the story (output). If the answer is incorrect, it presents a hint through the generative AI model. The above steps provide a personalized narrative experience that responds to the user's emotions and preferences in real time.

[0474] (Application example 2) Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[0475] Conventional interactive adventure story systems were able to develop a story based on the user's selection information and attribute data, but they did not provide a story experience that reflected the user's emotional state. For this reason, there is a demand for a deeper sense of immersion and empathy that corresponds to the user's emotions. In addition, the development of a system that realizes a story experience optimized for each individual user by providing different storylines depending on the user's emotional state was a challenge.

[0476] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for referring to story-related data and developing a story through dialogue with the generation AI, a means for controlling the development of the story by referring to user selection information, a means for receiving user characteristic data as an input and reflecting it in the development of the story, a means for referring to puzzle operation information and providing hints and answers, a means for realizing dialogue with the user using various input / output means, an emotion analysis means for analyzing the user's emotional state and adjusting the development of the story and options, and a means for selecting a story segment according to the emotional state and presenting it to the user. This enables the progress of the story to reflect the user's emotional state, making it possible to provide a deeper immersive and personalized story experience.

[0477] "Story-related data" refers to a group of data necessary for the progression and development of the story, and includes summary data, choice data, puzzle data, and emotion data. "Generative AI" is an interactive artificial intelligence model that progresses the story, presents options, solves puzzles, and so on. "User selection information" refers to information about options selected by the user during the progress of the story, and is used to control the development of the story. "User attribute data" is data regarding the characteristics of a user, such as the user's age, sex, place of residence, personality, and emotional state. "Puzzle operation information" is information obtained when a user operates a puzzle, and is used to provide hints and solutions. The "input / output means" refers to means for realizing dialogue with a user, such as a speaker, a microphone, a keyboard, various input devices, and a display device. The "emotion analysis means" is a means for analyzing information such as the user's voice, facial expression, and language, and for inferring the user's emotional state. A "narrative segment" is a collection of text and options that form part of a narrative and are presented to the user depending on their emotional state.

[0478] (Mode for carrying out the invention) To implement this invention, a system consisting of three main components is required: a server, a terminal, and a user. Specifically, the system includes the following components:

[0479] server The server is the central point for progressing the story and presenting choices. The server includes the following mechanisms: A means of referencing story-related data and developing a story through dialogue with generative AI. A means for controlling the development of a story by referring to information selected by a user. A means of receiving user characteristic data as input and reflecting it in the development of the story. A means of referencing puzzle operation information and providing hints and solutions. A means of using emotion analysis to analyze the user's emotional state and adjust the story development and choices. A means for selecting and presenting narrative segments to a user according to an emotional state.

[0480] Terminal The terminal acts as an interface with the user and includes the following equipment and software: Input / output means include a speaker, a microphone, a keyboard, various input devices, and a display device. Through communication with the server, it receives information about story progress, choices, and puzzles, and transmits the user's choices and operations to the server.

[0481] User Users connect to the server via their terminal and begin the story, choose options, solve puzzles, and so on. Enter your characteristic data and enjoy a story experience tailored to your own unique traits. The emotion engine recognizes emotions through voice, facial expressions, language, and other means that express emotions.

[0482] Hardware and Software Used The server is made up of computers with high-performance processing power, and manages story-related data, runs generative AI, and processes sentiment analysis. The emotion analysis means is software that operates as an emotion engine, and uses, for example, image analysis by OpenCV and a natural language processing model (Hugging Face's Transformers pipeline). The device is equipped with a camera and microphone, and is capable of collecting emotional data, which allows the device to analyze the user's facial expressions and voice and estimate their emotional state.

[0483] Examples For example, if the user is analyzed as being in a stressful situation, the story progression will be adjusted to a relaxing content, whereas if the user is in a very positive emotional state, the story progression will present stimulating choices. Examples of prompt statements "Write an interactive story application that recognizes the user's emotions from image data and progresses the story by choosing options according to the emotions." In this way, users can enjoy a more personal and emotionally connected narrative experience.

[0484] The flow of the specific process in the application example 2 will be described with reference to FIG. Step 1: The server loads the story-related data. It imports data necessary for the progression of the story, the presentation of choices, and the solving of puzzles, and stores it on the server. Story-related data files are used as input, and the output is stored in the data storage in the server.

[0485] Step 2: A user starts a story by selecting a story genre through a terminal. The terminal receives the selected genre information from the user and sends it to the server. The input is the user's genre selection, and the output is a request containing that information being sent to the server.

[0486] Step 3: The server receives the user's characteristic data. This data includes age, gender, place of residence, personality, and emotional state. The input is the characteristic data sent from the terminal, and the output is the characteristic data stored in the server. The characteristic data is used as basic information for the story development.

[0487] Step 4: The device uses a camera and microphone to collect the user's emotional state. Image data captured by the camera and audio data collected by the microphone are input, and are temporarily stored in the device. The output is stored in the device as the user's emotional data.

[0488] Step 5: The terminal transmits image data and voice data to the server. The input is emotion data stored in the terminal, and the output is a request including the emotion data being transmitted to the server.

[0489] Step 6: The server analyzes the received image and audio data to estimate the user's emotional state. The emotion analysis method used here is OpenCV and the Hugging Face Transformers pipeline. The input is image and audio data, and the output is the estimated emotional state.

[0490] Step 7: The server selects the next story segment based on the emotional state. The server chooses an appropriate segment from the story related data based on the emotional state obtained by the emotion analysis means. The input is the estimated emotional state and the output is the selected story segment.

[0491] Step 8: The server sends the selected story segment to the terminal. The input is the selected story segment and the output is a response including the story segment sent to the terminal.

[0492] Step 9: The terminal presents the received story segments to the user: story text and options are displayed and the user selects an option to proceed. The input is the story segment from the server and the output is the user's selection.

[0493] Step 10: The user's selection information is sent from the terminal to the server. The selection information is taken as input and sent to the server. The output is a request containing the selection information.

[0494] Step 11: The server advances the story based on the received selection information and repeats the process from step 6. This allows the story to progress in real time according to the user's selections and emotional state. The input is the user's selection information, and the output is the updated story segment.

[0495] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0496] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generative AIs. Data generation model 58 is , obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0497] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the robot 414.

[0498] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0499] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In 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 emotions are arranged. Emotions that represent states and actions arising from mental states are arranged on the outer sides of the concentric circles. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, the emotion of "pleasure" is placed on the upper side of the concentric circles, and the emotion of "discomfort" is placed on the lower side. In this way, in emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that tend to occur simultaneously are mapped close to each other.

[0500] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0501] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0502] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0503] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0504] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0505] Although the system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, the system according to the present disclosure is not necessarily implemented in a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program that runs on a personal computer, or an application that runs on a smartphone or the like. The method according to the present disclosure may be provided to a user in the form of SaaS (Software as a Service). In the above embodiment, an example is given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to input data.

[0506] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0507] In addition, 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 upon request from the data processing device 12.

[0508] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0509] The hardware resource for executing the specific process may be any of the following various processors. An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. In addition, an example of a processor is a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application specific integrated circuit (ASIC), which is specially designed to execute a specific process. A dedicated electrical circuit is a processor having a circuit configuration. Each processor has a built-in memory or is connected to the memory, and each processor executes a specific process by using the memory.

[0510] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0511] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0512] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0513] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[0514] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or standard was specifically and individually indicated to be incorporated by reference.

[0515] The following is further disclosed regarding the above embodiment.

[0516] [Claim 1] An interactive adventure story system for progressing a story and presenting options, comprising: A means to develop a story through dialogue with the generation AI by referring to story-related data; A means for controlling the development of a story by referring to information selected by a user; A means for receiving characteristic data of a user as an input and reflecting the data in the development of a story; A means to refer to the operation information of the puzzle and provide hints and solutions; Using speakers, microphones, keyboards, various input devices, display devices, etc. A means for enabling interaction with a user; A system including: [Claim 2] In the system described in claim 1, the story-related data includes summary data, choice data, and puzzle data. [Claim 3] In the system described in claim 1, the user's characteristic data includes age, sex, place of residence, personality, etc.

[0517] [Claim 4] The system according to claim 1 is characterized in that it is combined with an emotion engine that recognizes the user's emotions. [Claim 5] In the system described in claim 4, the emotion engine analyzes information such as voice, facial expressions, and language, and estimates the user's emotional state. [Claim 6] In the system described in claim 4 or 5, the emotion engine adjusts the development of the story and the presentation of options according to the user's emotions.

[0518] The above is the added claim. This provides a more personalized story experience by combining the system with an emotion engine that recognizes the user's emotions. The emotion engine analyzes information such as the user's voice, facial expression, and language to estimate the user's emotional state. Then, by adjusting the development of the story and the presentation of options according to the user's emotions, a more emotionally appealing experience is realized. "Example 1" (Claim 1) An interactive adventure story system for progressing a story and presenting choices, comprising: A means of developing a story through dialogue with a generative AI model, referencing story-related data; and A means for controlling the development of a story by referring to information selected by a user; A means for receiving characteristic data of a user as an input and reflecting the data in the development of a story; A means for generating a narrative by generating prompt sentences and sending the prompts to a generative AI model; A means to refer to the operation information of the puzzle and provide hints and solutions; A means for realizing a dialogue with a user using various input / output means; A means for loading story-related data and caching it in internal memory; A system including: (Claim 2) 2. The system of claim 1, wherein the story-related data includes summary data, choice data, and puzzle data. (Claim 3) 2. The system according to claim 1, wherein the user characteristic data includes age, sex, place of residence, and personality. "Application example 1" (Claim 1) An interactive adventure story system for progressing a story and presenting options, comprising: means for referring to story-related data and developing the story through dialogue with a generative AI; means for referring to user selection information and controlling the development of the story; means for receiving user characteristic data as input and reflecting this in the development of the story; means for referring to puzzle operation information and providing hints and answers; means for realizing dialogue with the user using various input / output means; means that operates on a mobile information terminal and generates and displays the development of the story and puzzles in real time; means for saving user progress and selection information in a database; and means for using a generative AI model to generate appropriate prompt sentences based on the user's input, thereby determining the next development of the story. (Claim 2) The system of claim 1, characterized in that the story-related data includes summary data, choice data, puzzle data, and progress data. (Claim 3) The system according to claim 1, characterized in that the user's characteristic data includes age, gender, place of residence, personality, and adventure preferences.

[0519] "Example 2 of combining emotion engines" (Claim 1) An interactive narrative system for progressing a story and presenting options, comprising: means for referring to story-related data and developing a story through dialogue with a generative AI model; means for controlling the development of the story by referring to user selection information; means for receiving user characteristic data as input and reflecting this in the development of the story; means for referring to puzzle operation information and providing hints and answers; means for realizing dialogue with the user using an input / output device of the terminal; and means for analyzing the user's emotional state using an emotion engine and adjusting the options and development of the story. (Claim 2) The system of claim 1, characterized in that the story-related data includes plot data, choice data, and puzzle data. (Claim 3) The system according to claim 1, characterized in that the user's characteristic data includes age, gender, place of residence, personality, and preferences.

[0520] "Application example 2 when combining emotion engines" (Claim 1) An interactive adventure story system for progressing a story and presenting options, comprising: means for referring to story-related data and developing a story through dialogue with a generation AI; means for controlling the development of the story by referring to user selection information; means for receiving user characteristic data as input and reflecting this in the development of the story; means for referring to puzzle operation information and providing hints and answers; means for realizing dialogue with the user using various input / output means; emotion analysis means for analyzing the user's emotional state and adjusting the development of the story and the options; and means for selecting story segments according to the emotional state and presenting them to the user. (Claim 2) The system of claim 1, characterized in that the story-related data includes summary data, choice data, puzzle data, and emotion data. (Claim 3) The system according to claim 1, characterized in that the user's characteristic data includes age, gender, place of residence, personality, and emotional state. [Explanation of symbols]

[0521] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:>

Claims

1. An interactive adventure story system for progressing a story and presenting choices, comprising: A story development means for developing a story through dialogue with the generation AI by referring to story-related data; A development control means for controlling the development of a story by referring to information selected by a user; A development reflection means for receiving user characteristic data as an input and reflecting the data on the development of the story; a providing means for referring to operation information of a puzzle by a user, and if the operation information indicates a correct answer, requesting the development control means to develop a story, and if the operation information indicates an incorrect answer, providing the user with hints and an answer to the puzzle; A dialogue means for realizing dialogue with a user using various input / output means; A system including:

2. 2. The system according to claim 1, wherein the story-related data includes summary data indicating an outline of the story, choice data indicating choices in the story, and puzzle data relating to the puzzle.

3. 2. The system according to claim 1, wherein the user characteristic data includes the user's age, sex, place of residence, personality, etc.

4. 2. The system of claim 1, further comprising an emotion engine for recognizing the emotion of the user.

Images