System

Abstract

A system is provided.SOLUTION: A system comprising: a database for storing an initial pattern of a story; a generating means for dynamically generating a generated story; a sensor for measuring a user's facial expression, brightness of eyes, pulse, and amount of sweat; an analyzing means for analyzing the measured data and evaluating the user's interest and emotion; a control means for adjusting a direction of the story based on an evaluation result; and a storage means for storing the generated story and analysis data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditionally, it has been difficult to get children who do not read enough to become interested in reading. This problem arises particularly as today's children tend to spend more time on social media and games, resulting in a decline in interest in traditional books and educational content. Furthermore, traditional methods have made it difficult to customize the reading experience individually, making it impossible to provide stories that match the interests and emotions of specific users. To solve these challenges, a new way of providing a reading experience is needed. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system as follows. The system includes a database that stores initial story patterns, a generation unit that dynamically generates generated stories, sensors that measure a user's facial expressions, eye brightness, pulse rate, and sweat rate, and an analysis unit that analyzes the measured data to evaluate the user's interests and emotions. The system also includes a control unit that adjusts the direction of the story based on the evaluation results and a storage unit that saves the generated story and the analysis data. This system allows stories to be generated and updated in real time according to the user's responses, enabling the reading experience to be individually customized. Furthermore, by including a selection unit that provides initial story patterns based on the user's selection and a stop unit that stops story generation when a certain criterion is exceeded, a reading environment suited to the user can be provided.

[0006] An "initial story pattern" is a basic storyline prepared in advance to start generating a story.

[0007] "Generation means" refers to the technology or algorithms used to dynamically generate a story based on input data.

[0008] A "sensor" is a device that measures the user's physiological responses, and has the ability to detect facial expressions, eye brightness, pulse rate, amount of sweat, etc.

[0009] "Analysis means" refers to algorithms or systems that analyze data acquired by sensors and assess the user's interests and emotional state.

[0010] "Control measures" refer to techniques and systems for adjusting the generation and progression of a story based on the evaluation results of analytical measures.

[0011] "Storage means" refers to a storage device or system for storing the generated story and user response data.

[0012] "Selection means" refers to an interface or system that allows the user to select the initial pattern of the story.

[0013] "Stopping means" refers to techniques or systems that stop the generation of a story if user response exceeds a certain threshold. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] 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.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] 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.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system in which a user selects an initial story pattern, a generation AI dynamically generates a story based on that selection, and measures and analyzes the user's response in real time. This system customizes the story according to the user's interests and emotions, optimizing the reading experience for each individual.

[0036] System configuration

[0037] The system consists of the following main components:

[0038] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[0039] 2. Terminal: A device that the user uses to read the story and is equipped with sensors to measure the user's physiological responses.

[0040] 3. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[0041] Initial Setup

[0042] The server first stores a story template (for example, "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside") in a database. This prepares the database for when the user selects the first pattern of the story. The server also simultaneously prepares for story generation by configuring and initializing the generation AI.

[0043] Beginning of story generation

[0044] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends a request to the server. Based on the received request, the server passes the selected template to the generation AI, which generates the first part of the story. The generated story text is then sent to the device.

[0045] Displaying a story and measuring user responses

[0046] The device displays the generated story to the user. At the same time, sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate. This data is sent to the server in real time. For example, the sensors measure whether the user's heart rate or facial expression changes when an exciting scene is displayed.

[0047] Analyzing user responses and updating the story

[0048] The server analyzes the received sensor data and evaluates the user's level of excitement and interest. Based on the analysis results, it sends new instructions to the generation AI to adjust the direction of the story. For example, if the analysis results indicate that the user's level of excitement is low, it instructs the generation AI to add new adventures or surprise elements to the story.

[0049] End of story and data saving

[0050] After the story is finished, the server stores the user's reaction data and the generated story in a database, allowing the server to utilize this data the next time the story is generated to provide a more engaging story.

[0051] Specific examples

[0052] For example, a story starts based on the template "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside." After the user makes a selection, the server generates the following opening: "The boy visits his grandmother's house in the countryside during summer vacation." If the user's heart rate and facial expression data indicate a low level of excitement, the server adds a scene in which it is revealed that the grandmother is a witch, making the story more interesting.

[0053] In this way, the present invention aims to enhance the reading experience by dynamically generating and adjusting stories according to the user's interests and emotions.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] As an initial setting, the server stores some initial story patterns in the database, which prepares template data to be used in subsequent story generation.

[0057] Specific behavior:

[0058] 1. The server loads a story template (e.g., "A 17-year-old city boy hears an old folktale from his country grandmother") from a configuration file.

[0059] 2. Insert the loaded template data into the database.

[0060] 3. Set the API key and authentication information for the generated AI and initialize the AI.

[0061] Step 2:

[0062] The user selects one from a list of story templates displayed on the terminal, and once the selection is complete, the terminal sends the information to the server.

[0063] Specific behavior:

[0064] 1. The terminal displays a list of story templates to the user.

[0065] 2. The user selects the desired template (for example, "A 17-year-old boy living in the city hears an old story from a country grandmother") and presses the select button.

[0066] 3. The device sends a request including the selected template ID to the server.

[0067] Step 3:

[0068] Based on the received request, the server passes the selected template content to the generation AI to generate the first part of the story, and the generated text is sent to the device.

[0069] Specific behavior:

[0070] 1. The server analyzes the received template ID and retrieves the corresponding template content from the database.

[0071] 2. The obtained template content is input into the generation AI to generate the initial section of the story (for example, "The boy visited his grandmother's house in the countryside during his summer vacation").

[0072] 3. Send the generated text to the terminal.

[0073] Step 4:

[0074] The device displays the initial section of the story to the user, while sensors begin measuring the user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate).

[0075] Specific behavior:

[0076] 1. The device displays the received story text on the screen.

[0077] 2. The user begins reading the story.

[0078] 3. Sensors on the device measure the user's physiological responses in real time.

[0079] 4. The measured data is periodically sent to the server.

[0080] Step 5:

[0081] The server analyzes the received user response data and evaluates the user's level of excitement and interest. Based on the evaluation results, it instructs the generation AI to generate the next section.

[0082] Specific behavior:

[0083] 1. The server inputs the received sensor data into the machine learning model.

[0084] 2. The model analyzes and scores the user's emotion and interest level (e.g., excitement is rated as low).

[0085] 3. Decide on the direction of the story based on the score (e.g., add an adventure element to the story).

[0086] 4. The server sends new instructions to the generation AI to generate the next section (e.g., "The old woman claims to have once been a witch").

[0087] 5. Send the next generated section to the terminal.

[0088] Step 6:

[0089] Once the story is finished, the server saves all user response data and the generated story, allowing it to be used the next time a story is generated.

[0090] Specific behavior:

[0091] 1. The server generates the story's ending (e.g., "The boy accompanied his grandmother on a magical adventure, reaffirming his precious family bond").

[0092] 2. When the story is completed, all response data and the generated story are saved in a database.

[0093] 3. The saved data is used as training data for the generative AI.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Conventional story generation systems have the problem of being unable to customize the story according to the user's interests and emotions, resulting in a uniform experience. Furthermore, because they were unable to dynamically adjust the story based on the user's real-time reactions, it was difficult to provide an optimal reading experience for each individual user. As a result, there were issues with lower satisfaction with the reading experience and lower continuity of use.

[0097] 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.

[0098] In this invention, the server includes a database means for storing the initial pattern of the story, a generation means for dynamically generating a generated story, a sensor means for measuring the user's facial expression, eye brightness, pulse rate, and amount of sweat, an analysis means for analyzing the measured data and evaluating the user's interests and emotions, a control means for adjusting the direction of the story based on the evaluation results, a means for passing the initial pattern of the story to a generative AI model based on user selection information and presenting a newly generated story, and a storage means for saving the generated story and analysis data. This makes it possible to dynamically customize the story according to the user's real-time reactions and provide an individually optimized reading experience.

[0099] "The initial pattern of the story" refers to the initial setting or beginning scenario of the story that the user can select.

[0100] "Database" refers to a system for structuring and storing information such as initial story patterns, generated stories, and user response data.

[0101] "Generation means" refers to AI systems or software that dynamically generate stories based on user selection information.

[0102] "Sensor" refers to a hardware device that measures a user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate, etc.).

[0103] "Analysis means" refers to the algorithms and software used to process and analyze data acquired by sensors and evaluate user interests and emotions.

[0104] "Control measures" refer to systems or software that adjust the direction of the story based on the results of the analytical measures.

[0105] "Generative AI model" refers to a model of artificial intelligence (e.g., generative AI) used to generate a story.

[0106] "Storage means" refers to a storage system or database for storing generated stories and analytical data.

[0107] "Selection means" refers to an interface or system that allows the user to select the initial pattern of the story.

[0108] "Stopping means" refers to a system or software that stops the generation of a story if the user's response exceeds a certain threshold.

[0109] This system allows users to select an initial story pattern, and then a generative AI model dynamically generates a story based on that selection, and then measures and analyzes the user's response in real time. The system consists of the following main components: a server, a terminal, and a user.

[0110] First, the server has a database that stores story templates. This database stores multiple initial story patterns for users to choose from. For example, a template such as "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside" is provided. The server also uses a generative AI model (e.g., generative AI) and is responsible for the initial setup and operation of this AI model. A cloud server (e.g., AWS) is typically used.

[0111] The user can select the first pattern of the story by operating a device (e.g., a smartphone or tablet). The device is equipped with sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat volume. Specific sensors used include a camera (for facial expression detection), a heart rate sensor (e.g., Polar H10), and a sweat sensor. The information selected by the user is sent from the device to the server, which then passes this information to the generative AI model as a prompt. The following prompts are used:

[0112] Start your story with the theme "A 17-year-old city boy hears old stories from his country grandmother." The story begins with the boy visiting his country grandmother's house during summer vacation. Add a scene where it turns out the grandmother is a witch.

[0113] The generative AI model generates the first part of the story based on this prompt, and the server sends that text to the device. The device displays the generated story to the user while measuring the user's physiological responses in real time with sensors and sending the data to the server. For example, it measures whether the user's heart rate or facial expression changes when an exciting scene is displayed.

[0114] The server analyzes the received sensor data using analytical methods (e.g., machine learning models) to assess the user's level of excitement and interest. Based on the results of this analysis, the server sends new instructions to the generative AI model, instructing it to adjust the direction of the story. For example, if the server determines that the user's level of excitement is low, it will instruct the model to add new adventures or surprises to the story.

[0115] After the story is finished, the server stores the user's reaction data and the generated story in a database. This allows the server to utilize this data the next time the story is generated, thereby providing a more engaging story.

[0116] This invention dynamically changes the content according to the user's reactions as they read the story, providing an individually optimized reading experience. As a specific example, a story may be generated based on a template of "a 17-year-old boy living in the city hears an old folktale from his grandmother in the countryside," and if the user is not excited by the displayed content, a scene in which it is revealed that the grandmother is a witch may be added.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] The server stores story templates in a database. This includes templates such as "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside." This template data is stored in a database (e.g., MySQL) using an INSERT statement. The server also performs initial setup of the generative AI model (e.g., the generative AI). Specifically, it sets the API key and prepares the initial prompt. The input data is the story template and the configuration data for the generative AI model, and the output is the registration of the template in the database and the initialization of the generative AI model.

[0120] Step 2:

[0121] The user operates the device to select the first pattern for the story. A list of templates is displayed through the device's UI, and the user selects one from the list. The selected template ID is sent from the device to the server as a request. Specifically, the user clicks on a template and presses the "Send" button. The input data is the user's selection information, and the output is a request sent to the server.

[0122] Step 3:

[0123] Based on the received request, the server passes the selected template ID to the generative AI model as a prompt sentence. Based on this prompt sentence, the generative AI model generates the first part of the story. The generated story text is sent from the server to the device. The input data is the selected template ID, and the output is the generated story text. Specifically, the server sends a request to the generative AI model's API to obtain the generated text. It then returns the text in JSON format to the device as a response.

[0124] Step 4:

[0125] The device displays the generated story to the user. At the same time, sensors installed on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate in real time. These data are periodically sent to the server. The input data is the generated story text and the user's physiological response data, and the output is displaying the story to the user and sending sensor data to the server. Specifically, the device displays the story on the screen, obtains data collected from the camera and heart rate sensor via Bluetooth, and sends it to the server using an HTTP POST request.

[0126] Step 5:

[0127] The server analyzes the received sensor data and evaluates the user's excitement and interest. It uses an analysis algorithm (e.g., a machine learning model) to quantify the sensor data and evaluate the user's emotional state. Based on the analysis results, the server sends new instructions to the generative AI model and adjusts the direction of the story. The input data is the user's sensor data, and the output is the user's emotional evaluation result and new instructions to the generative AI model. Specifically, the server executes the analysis algorithm and sends the analysis results to the generative AI model as a new prompt.

[0128] Step 6:

[0129] After the story is finished, the server saves the user's reaction data and the generated story in a database. By utilizing this data in the next story generation, the aim is to provide a more compelling story. The input data is the user's reaction data and the generated story text, and the output is saving to the database. Specifically, the server executes the SQL statement for saving and stores the data in the database.

[0130] (Application example 1)

[0131] 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."

[0132] Conventional story generation systems struggle to reflect a user's interests and emotional responses in real time, making it difficult to optimize an individual reading experience. Furthermore, there is a lack of technology that can effectively measure a user's physiological responses and dynamically adjust the story content based on them. This makes it difficult to maintain a user's interest and provide an engaging story experience.

[0133] 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.

[0134] In this invention, the server includes a database that stores initial story patterns, a generation unit that dynamically generates a generated story, sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, an analysis unit that analyzes the measured data to evaluate the user's interests and emotions, a control unit that adjusts the direction of the story based on the evaluation results, a storage unit that saves the generated story and analysis data, and a terminal that operates a smartphone to display the story and measure the user's reaction. This enables individually optimized dynamic story generation and customization based on the user's physiological reaction.

[0135] "Story start patterns" are templates of different themes and settings that users can choose from at the start of a story.

[0136] A "database" is an information storage system for storing story patterns, generated stories, and user response data.

[0137] "Generation means" refers to algorithms or software that dynamically generate a story based on the story pattern selected by the user.

[0138] "Sensor" refers to a device that measures physiological data such as a user's facial expression, eye brightness, pulse rate, and sweat rate.

[0139] "Analysis means" refers to algorithms or software that analyze the user's physiological data collected by the sensors and evaluate the user's interests and emotions.

[0140] "Control means" refers to algorithms or software that adjust the direction of the story based on the evaluation results obtained by the analysis means.

[0141] "Memory means" refers to a recording device or storage for saving the generated stories and analyzed data.

[0142] A "terminal" is a device such as a smartphone that a user uses to measure physiological responses while reading a story.

[0143] This invention is a system in which a user selects the initial pattern of a story, a generation AI dynamically generates a story based on that, and measures and analyzes the user's reaction in real time. Specific embodiments are described below.

[0144] System configuration

[0145] The system consists of the following major components:

[0146] 1. Server: This is the central component responsible for story generation, database management, analysis, control, and storage. A Transformer-based generative AI model (e.g., GPT-4) is used to generate stories.

[0147] 2. Device: A device such as a smartphone that the user uses to read the story. The device is equipped with sensors such as a camera and a fingerprint sensor (for measuring pulse) to measure the user's physiological responses.

[0148] 3. User: The individual who actually reads the story, and their reaction data is fed back to the server.

[0149] Program processing overview

[0150] Server Processing

[0151] The server first stores a story template in a database (e.g., MongoDB). This template is used when the user selects the first pattern of the story. When the user operates the device to select a pattern of the story, the information is sent to the server. The server then uses generative AI to dynamically generate a story and sends the text to the device.

[0152] The server also analyzes sensor data (facial expressions, pulse rate, sweat rate, etc.) sent from the device in real time. Based on the analysis results, it sends new instructions to the generation AI and adjusts the direction of the story. The generated story and analysis data are stored in a database for later use.

[0153] Terminal handling

[0154] The device sends the initial story pattern selected by the user to the server and receives the generated story text. While displaying the story, the device captures the user's facial expressions with a camera and measures their pulse with a pulse sensor. These data are sent to the server in real time.

[0155] User Roles

[0156] The user operates the device to select a story pattern. While the story is displayed, the user's natural reactions are measured as sensor data. The user's reaction data is reflected in the customization of the story, providing an individually optimized reading experience.

[0157] Examples of concrete examples and prompts

[0158] For example, if the user selects the "Adventure" pattern, the server generates the following story:

[0159] "The boy sensed the beginning of an adventure and stepped into the unknown..."

[0160] If the user's heart rate increases and their facial expression shows surprise, the following prompt is fed to the generative AI model:

[0161] Q: The user selected "Adventure" as the beginning of the story. The current storyline has lowered the user's excitement level, so a more exciting scene is needed. Add a monster encounter or treasure hunt element.

[0162] A:

[0163] Based on these prompts, the generative AI model adds new adventures and surprises to the story, and adjusts the direction of the story based on its analysis.

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] The server stores story templates in a database, which are used when a user selects the first pattern of a story. The input data is a prepared story template, which is saved in the database. The output is the saved template data.

[0167] Step 2:

[0168] The user operates the terminal to select the first pattern of the story. The terminal collects the user's selection data and sends it to the server. The input data is the pattern of the story selected by the user, and the output is a request sent to the server.

[0169] Step 3:

[0170] The server generates the initial part of the story using a generative AI model based on the received request. The input data is the story pattern selected by the user, which is input to the generative AI model as a prompt sentence. The output is the initial text of the generated story.

[0171] Step 4:

[0172] The device displays the initial text of the generated story to the user. It uses a built-in camera and biometric sensors to measure the user's facial expressions, pulse rate, sweat rate, and other physiological responses. The input data is the generated story text and the measured physiological data, and the output is the displayed story text and the collected physiological data.

[0173] Step 5:

[0174] The terminal transmits the collected physiological data to the server, where the input data is the measured physiological data and the output is the transmitted data to the server.

[0175] Step 6:

[0176] The server analyzes the received sensor data and evaluates the user's interest and emotions. Using analytical means, it analyzes data such as facial expressions and pulse rate to quantify the user's excitement and interest. The input data is the measurement data, and the output is the evaluation result.

[0177] Step 7:

[0178] Based on the evaluation results, the server sends new instructions to the generative AI model to adjust the direction of the story. For example, if the user's excitement level is evaluated as low, the server instructs the model to add a new episode to the story. In this case, the following prompt sentence is input to the generative AI model:

[0179] Q: The user selected "Adventure" as the opening part of the story. The current story flow has lowered the user's excitement level, so a more exciting scene is needed. Please add a monster encounter or treasure hunt element. A:

[0180] The input data are the evaluation results and instructions for the generative AI model, and the output is the tailored narrative text.

[0181] Step 8:

[0182] The server sends the adjusted story text to the terminal. The input data is the adjusted story text, and the output is the data sent to the terminal.

[0183] Step 9:

[0184] The terminal then displays the newly generated story text back to the user. The input data is the adjusted story text, and the output is the new text of the displayed story.

[0185] Step 10:

[0186] As the user continues to read the story, the device and server repeat the above steps, dynamically adjusting the story based on the user's responses to continuously optimize the reading experience. Finally, the generated story and analysis data are stored on the server and used for the next story generation.

[0187] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0188] The present invention is a system incorporating an emotion engine that recognizes the user's emotions, which dynamically generates stories based on the user's interests and emotions, optimizing the reading experience for each individual.

[0189] System configuration

[0190] The system consists of the following main components:

[0191] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[0192] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses.

[0193] 3. Emotion engine: This engine recognizes the user's emotions, analyzes their state, and reflects them in the story generation.

[0194] 4. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[0195] Initial Setup

[0196] The server first stores the story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generation AI, preparing to generate the story.

[0197] Beginning of story generation

[0198] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into the generation AI to generate the initial section of the story. The generated text is then sent to the device.

[0199] Displaying a story and measuring user responses

[0200] The device displays the generated story to the user, while sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmit this data to the server in real time.

[0201] Emotion Recognition and Analysis

[0202] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generation AI.

[0203] Story Updates

[0204] Once the story direction is determined, the server uses generative AI to generate the next section of the story, for example, by adding new adventures or suspense elements to the story if it determines that the user's excitement level is low.

[0205] End of story and data saving

[0206] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[0207] Specific examples

[0208] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read this story, the device continuously measures the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the user's level of excitement is deemed low, the server instructs the generation AI to develop a new plot development, such as "The grandmother reveals that she was once a witch."

[0209] In this way, our invention can dynamically generate and adjust the story according to the user's emotional state, optimizing the reading experience for each individual. By flexibly changing and updating the direction of the story based on detailed sensor data and the analysis results of the emotion engine, it is possible to provide a consistently engaging reading experience for the user.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] The server initially stores some initial story patterns in a database.

[0213] Specific behavior:

[0214] 1. The server loads the story template from the configuration file.

[0215] 2. Insert the loaded template data into the database.

[0216] 3. Set the API key and authentication information for the generated AI and initialize the AI.

[0217] Step 2:

[0218] The user selects one from a list of story templates displayed on the terminal, and the terminal transmits the information to the server.

[0219] Specific behavior:

[0220] 1. The terminal displays a list of story templates to the user.

[0221] 2. The user selects the desired template and presses the Select button.

[0222] 3. The device sends a request including the selected template ID to the server.

[0223] Step 3:

[0224] Based on the received request, the server passes the selected template content to the generation AI to generate the first part of the story, and the generated text is sent to the device.

[0225] Specific behavior:

[0226] 1. The server analyzes the received template ID and retrieves the corresponding template content from the database.

[0227] 2. The acquired template content is input into the generation AI to generate the initial section of the story.

[0228] 3. Send the generated text to the terminal.

[0229] Step 4:

[0230] The device displays the initial section of the story to the user, while sensors begin measuring the user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate).

[0231] Specific behavior:

[0232] 1. The device displays the received story text on the screen.

[0233] 2. The user begins reading the story.

[0234] 3. Sensors on the device measure the user's physiological responses in real time.

[0235] 4. The measured data is periodically sent to the server.

[0236] Step 5:

[0237] The server inputs the received user reaction data into the emotion engine, recognizes and evaluates the user's emotional state, and instructs the generation AI to generate the next section based on the evaluation results.

[0238] Specific behavior:

[0239] 1. The server inputs the received sensor data into the emotion engine.

[0240] 2. The emotion engine analyzes and scores the user's emotional state.

[0241] 3. Determine the direction of the story based on the score.

[0242] 4. The server sends new instructions to the generation AI to generate the next section.

[0243] 5. Send the next generated section to the terminal.

[0244] Step 6:

[0245] The device then displays the next generated section to the user, and the sensors again measure the user's response, repeating this process until the user has finished reading the story.

[0246] Specific behavior:

[0247] 1. Your device will display a new story section on the screen.

[0248] 2. The user reads the story.

[0249] 3. The device's sensors again measure the user's reaction and send it to the server.

[0250] Step 7:

[0251] Once the story is finished, the server stores all user response data and the generated story, and uses this data the next time a story is generated.

[0252] Specific behavior:

[0253] 1. The server generates the ending of the story.

[0254] 2. Upon completion of the story, all response data and the generated story are stored in a database.

[0255] 3. The stored data is used as training data for generative AI and emotion engines.

[0256] Example 2

[0257] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0258] Conventional story generation systems have had difficulty dynamically generating and adjusting a story based on the user's emotions and interests. Furthermore, there has been a lack of technology that can evaluate the user's physiological responses in real time and flexibly change the direction of the story based on those responses. As a result, it has been difficult for users to obtain an individually optimized reading experience.

[0259] 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.

[0260] In this invention, the server includes database means for storing initial story patterns, generation means for dynamically generating generated stories, sensor means for measuring the user's facial expressions, eye brightness, pulse rate, and sweat rate, analysis means for analyzing the measured data to evaluate the user's excitement level and interest, control means for adjusting the direction of the story based on the evaluation results, storage means for saving the generated story and analysis data, display means for displaying the generated story, selection means for the user to select a story template, and generation means for generating story sections using a generative AI model. This enables dynamic story generation according to the user's emotional state and individual optimization of the reading experience based on the generated story.

[0261] A "narrative" refers to a series of stories or texts presented to a user.

[0262] "Pattern" refers to the basic structure or template of a story.

[0263] A "database" refers to a system or repository for storing data such as initial story patterns.

[0264] "Generative means" refers to means for dynamically creating narrative sections or stories using generative AI models.

[0265] "Sensor" refers to a device used to measure a user's facial expressions and physiological responses.

[0266] "Analysis means" refers to a means for analyzing sensor data to assess the user's excitement level and interest.

[0267] "Control measures" refer to means for adjusting the direction of the story based on the analysis results.

[0268] "Storage means" refers to means for storing generated stories and user response data.

[0269] "Display means" refers to a means for visually presenting the generated story to the user.

[0270] "Selection means" refers to the interface or mechanism by which a user selects a story template.

[0271] "Generative AI Model" refers to the artificial intelligence model used to generate a section of a story.

[0272] The present invention is a system that utilizes an emotion engine that recognizes the user's emotions to dynamically generate stories based on the user's interests and emotions, providing an individually optimized reading experience.

[0273] System configuration

[0274] The system consists of the following main components:

[0275] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[0276] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses.

[0277] 3. Emotion engine: This engine recognizes the user's emotions, analyzes their state, and reflects them in the story generation.

[0278] 4. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[0279] Initial Setup

[0280] The server first stores story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generative AI model (e.g., a general generative AI model) to prepare for story generation.

[0281] Story Generation

[0282] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into a generative AI model to generate the initial section of the story. The generated text is then sent to the device.

[0283] Displaying a story and measuring user responses

[0284] The device displays the generated story to the user, while sensors on the device measure the user's physiological responses, such as facial expressions, eye brightness, pulse rate, and sweat rate, and transmits this data to a server in real time.

[0285] Emotion Recognition and Analysis

[0286] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generative AI model.

[0287] Story Updates

[0288] Once the story direction is determined, the server uses a generative AI model to generate the next section of the story, for example, by adding new adventures or suspense elements to the story if it determines that the user's excitement level is low.

[0289] End of story and data saving

[0290] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[0291] Specific examples

[0292] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read the story, the device continuously monitors the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the server determines that the user's level of excitement is low, it instructs the generative AI model to develop a new plot, such as "The grandmother reveals that she was once a witch."

[0293] In this way, the present invention can dynamically generate and adjust the story according to the user's emotional state, thereby optimizing the reading experience for each individual. By flexibly changing and updating the direction of the story based on detailed sensor data and the analysis results of the emotion engine, the present invention provides a constantly engaging reading experience for the user.

[0294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0295] Step 1:

[0296] Initial Setup

[0297] Input: story template, generative AI model

[0298] The server stores templates in a database containing initial patterns of stories, and this information is used by the user when selecting a story.

[0299] The server configures and initializes the generative AI model, including parameter setting and initialization processing for the generative model.

[0300] Output: Templates stored in a database, an initialized generative AI model

[0301] Step 2:

[0302] Beginning of story generation

[0303] Input: User-selected story template

[0304] The user operates the terminal to select a story template.

[0305] The terminal transmits the selected template information to the server.

[0306] The server inputs prompts into the generative AI model based on the received template information to generate the initial section of the story, for example, "A 17-year-old boy living in the city hears an old folktale from his grandmother in the countryside."

[0307] Output: The initial section of the generated story

[0308] Step 3:

[0309] Displaying a story and measuring user responses

[0310] Input: The initial section of the generated story

[0311] The device displays the generated story to the user, who then reads the story on the screen.

[0312] At the same time, sensors installed in the device measure the user's facial expressions, eye brightness, pulse rate, sweat rate, etc. in real time, collecting physiological response data.

[0313] Output: User's physiological response data (facial expression, pulse rate, amount of sweat, etc.)

[0314] Step 4:

[0315] Emotion Recognition and Analysis

[0316] Input: User's physiological response data

[0317] The server inputs the received sensor data into the emotion engine.

[0318] The emotion engine analyzes the user's physiological response data to evaluate the user's level of excitement and interest. For example, if the user's pulse rate increases or their eyes sparkle above a certain level, it will evaluate the user's level of excitement as high.

[0319] Output: Evaluation results of excitement and interest

[0320] Step 5:

[0321] Determining and updating the story direction

[0322] Input: Excitement and interest evaluation results

[0323] The server decides the direction of the story based on the evaluation results obtained from the emotion engine. For example, if the excitement level is low, it adds new adventures or suspense elements.

[0324] Based on the evaluation results, the server re-enters the prompt into the generative AI model, generating a new section, such as "The old woman reveals that she was once a witch."

[0325] Output: Updated narrative section

[0326] Step 6:

[0327] Narrative display and data feedback

[0328] Input: Updated story section

[0329] The device displays the updated story to the user, who then proceeds to read the next section of the story.

[0330] The server then repeats the process of collecting and evaluating new physiological response data from the user.

[0331] Output: Continuously updated narrative, additional physiological response data

[0332] Step 7:

[0333] End of story and data saving

[0334] Input: All generated story sections, all physiological response data of the user

[0335] Once the story is finished, the server stores all user reaction data and the generated story.

[0336] The saved data will be used the next time a story is generated and will be used as learning data to make the generation process more suitable.

[0337] Output: Stored story and user response data

[0338] (Application example 2)

[0339] 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."

[0340] Current reading experiences are static, with the story content set once and not changing based on the user's reactions. This makes it difficult to provide a personalized reading experience that reflects the user's interests and emotions. Furthermore, no system effectively utilizes user emotional data to dynamically adjust the direction of the story. As a result, users tend to lose interest while reading, which leads to issues with the quality of the reading experience.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a database that stores initial story patterns, a generation means that dynamically generates a generated story, sensors that measure the user's facial expression, eye brightness, pulse rate, and sweat rate, an analysis means that analyzes the measured data and evaluates the user's emotions, a control means that adjusts the direction of the story based on the evaluation results, a storage means that saves the generated story and analysis data, a generative AI model that dynamically changes the content of the story depending on the user's state, and an input means for a prompt sentence that generates a new section of the story based on the user's emotions. This enables dynamic story generation according to the user's emotional state, making it possible to provide an individually optimized reading experience.

[0342] The "initial story pattern" is initial setting information including the opening part and basic structure of the story, and is a template that can be selected by the user.

[0343] "Generation means" refers to algorithms or software that dynamically generate a story from input information.

[0344] A "sensor" is a device for measuring a user's physiological responses (facial expression, eye brightness, pulse rate, amount of sweat, etc.).

[0345] "Analysis means" refers to methods and software for assessing the user's state of emotions and interests based on data obtained from sensors.

[0346] "Control means" refers to algorithms or programs that adjust the direction of the story based on the evaluation results of the analysis means.

[0347] "Storage means" refers to a system including a storage device and software for storing the generated story and user response data.

[0348] A "generative AI model" is an artificial intelligence model that takes a user's emotional state as input and generates new sections of a story based on it.

[0349] "Means for inputting prompt sentences" refers to the interface and method for inputting specific instructions to a generative AI model.

[0350] In order to implement this invention, it is necessary to build a system in which a server, terminal, sensor, generative AI model, and prompt sentence input means work in cooperation with each other.

[0351] System configuration

[0352] The system consists of the following main components:

[0353] 1. Server: This is the central component responsible for story generation, database management, analysis, control, and storage. It uses the generative AI model and a means of inputting prompts to generate the next section of the story.

[0354] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses. Specific examples include smartphones and smart glasses.

[0355] 3. Sensor: A device that measures the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmits this data to a server in real time.

[0356] 4. Generative AI model: An artificial intelligence model that analyzes the user's emotional state and generates new sections of the story based on the results.

[0357] 5. Prompt sentence input means: An interface for inputting specific instructions to the generative AI model.

[0358] Initial Setup

[0359] The server first stores the story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generation AI, preparing to generate the story.

[0360] Beginning of story generation

[0361] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into a generative AI model to generate the initial section of the story. The generated text is then sent to the device.

[0362] Displaying a story and measuring user responses

[0363] The device displays the generated story to the user, while sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmit this data to the server in real time.

[0364] Emotion Recognition and Analysis

[0365] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generative AI model.

[0366] Story Updates

[0367] Once the story direction is determined, the server uses a generative AI model to generate the next section of the story, for example, designing it to add new adventures or suspense elements if it determines that the user's excitement level is low.

[0368] End of story and data saving

[0369] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[0370] Specific examples

[0371] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read the story, the device continuously monitors the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the server determines that the user's level of excitement is low, it instructs the generative AI model to develop a new plot, such as "The grandmother reveals that she was once a witch."

[0372] Example prompts to input to the generative AI model:

[0373] "We've determined that users are bored, so add an element of surprise to your story."

[0374] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0375] Step 1:

[0376] Initial Setup

[0377] The server prepares a database to store the initial story patterns, and configures and initializes the generative AI model and the prompt sentence input method. At this stage, the server saves the available story templates in the database.

[0378] Input: Story template information

[0379] Output: Initialized generative AI model and database

[0380] Specific operation: The server stores the story template in a database and initializes the parameters of the generative AI model.

[0381] Step 2:

[0382] Choosing the first pattern of the story

[0383] The user selects the first pattern of the story through the terminal, and once the selection is complete, the terminal sends the information to the server.

[0384] Input: User selection of story patterns

[0385] Output: Sends the selection information to the server

[0386] Specific operation: The user operates the device screen to select a story template from the list.

[0387] Step 3:

[0388] Generating the initial section of the story

[0389] The server inputs the received pattern information into a generative AI model to generate the initial section of the story, and the generated text is sent to the device.

[0390] Input: Selected story pattern information

[0391] Output: The initial section of the generated story

[0392] Specific operation: The generative AI model generates an initial section based on the selected template and sends it to the terminal.

[0393] Step 4:

[0394] Displaying a story and measuring user responses

[0395] The device displays the generated story to the user, while sensors on the device measure the user's facial expression, eye brightness, pulse rate, and sweat rate, and transmit this data to a server in real time.

[0396] Input: The initial section of the generated story and the user's physiological response data

[0397] Output: Sending sensor data to the server

[0398] Specific operation: The device displays the story text to the user, and the built-in sensors begin measuring the user's reactions.

[0399] Step 5:

[0400] Emotion Recognition and Analysis

[0401] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine analyzes the user's excitement level and interest.

[0402] Input: User's physiological response data

[0403] Output: User's emotional state evaluation result

[0404] Specific operation: The emotion engine analyzes the received data and evaluates the user's emotions in real time.

[0405] Step 6:

[0406] Adjusting the direction of the story

[0407] The server inputs prompt sentences into the generative AI model to determine the direction of the story based on the evaluation results.

[0408] Input: User's emotional state assessment results

[0409] Output: Instructions and prompts that generate the following sections:

[0410] Specific operation: The server instructs the generative AI model, "It has been determined that the user is bored, so please add an element of surprise to the story."

[0411] Step 7:

[0412] Story Updates and Display

[0413] The server uses the generative AI model to generate the next section of the story, which is then sent back to the device and displayed to the user.

[0414] Input: A prompt sentence entered into the generative AI model

[0415] Output: Updated narrative section

[0416] How it works: The generative AI model generates a new section, and the server sends it to the device for display.

[0417] Step 8:

[0418] End of story and data saving

[0419] When the story is finished, the server stores all user reaction data and the generated story data in a storage means, so that this data can be used the next time a story is generated.

[0420] Input: All user response data and generated story data

[0421] Output: Saved data

[0422] Specific operation: The server saves the data in a memory device and uses it as a reference for future story generation.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0424] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0426] [Second embodiment]

[0427] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0428] 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.

[0429] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] 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.

[0431] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0433] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0434] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0439] This invention is a system in which a user selects an initial story pattern, a generation AI dynamically generates a story based on that selection, and measures and analyzes the user's response in real time. This system customizes the story according to the user's interests and emotions, optimizing the reading experience for each individual.

[0440] System configuration

[0441] The system consists of the following main components:

[0442] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[0443] 2. Terminal: A device that the user uses to read the story and is equipped with sensors to measure the user's physiological responses.

[0444] 3. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[0445] Initial Setup

[0446] The server first stores a story template (for example, "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside") in a database. This prepares the database for when the user selects the first pattern of the story. The server also simultaneously prepares for story generation by configuring and initializing the generation AI.

[0447] Beginning of story generation

[0448] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends a request to the server. Based on the received request, the server passes the selected template to the generation AI, which generates the first part of the story. The generated story text is then sent to the device.

[0449] Displaying a story and measuring user responses

[0450] The device displays the generated story to the user. At the same time, sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate. This data is sent to the server in real time. For example, the sensors measure whether the user's heart rate or facial expression changes when an exciting scene is displayed.

[0451] Analyzing user responses and updating the story

[0452] The server analyzes the received sensor data and evaluates the user's level of excitement and interest. Based on the analysis results, it sends new instructions to the generation AI to adjust the direction of the story. For example, if the analysis results indicate that the user's level of excitement is low, it instructs the generation AI to add new adventures or surprise elements to the story.

[0453] End of story and data saving

[0454] After the story is finished, the server stores the user's reaction data and the generated story in a database, allowing the server to utilize this data the next time the story is generated to provide a more engaging story.

[0455] Specific examples

[0456] For example, a story starts based on the template "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside." After the user makes a selection, the server generates the following opening: "The boy visits his grandmother's house in the countryside during summer vacation." If the user's heart rate and facial expression data indicate a low level of excitement, the server adds a scene in which it is revealed that the grandmother is a witch, making the story more interesting.

[0457] In this way, the present invention aims to enhance the reading experience by dynamically generating and adjusting stories according to the user's interests and emotions.

[0458] The processing flow will be explained below.

[0459] Step 1:

[0460] As an initial setting, the server stores some initial story patterns in the database, which prepares template data to be used in subsequent story generation.

[0461] Specific behavior:

[0462] 1. The server loads a story template (e.g., "A 17-year-old city boy hears an old folktale from his country grandmother") from a configuration file.

[0463] 2. Insert the loaded template data into the database.

[0464] 3. Set the API key and authentication information for the generated AI and initialize the AI.

[0465] Step 2:

[0466] The user selects one from a list of story templates displayed on the terminal, and once the selection is complete, the terminal sends the information to the server.

[0467] Specific behavior:

[0468] 1. The terminal displays a list of story templates to the user.

[0469] 2. The user selects the desired template (for example, "A 17-year-old boy living in the city hears an old story from a country grandmother") and presses the select button.

[0470] 3. The device sends a request including the selected template ID to the server.

[0471] Step 3:

[0472] Based on the received request, the server passes the selected template content to the generation AI to generate the first part of the story, and the generated text is sent to the device.

[0473] Specific behavior:

[0474] 1. The server analyzes the received template ID and retrieves the corresponding template content from the database.

[0475] 2. The obtained template content is input into the generation AI to generate the initial section of the story (for example, "The boy visited his grandmother's house in the countryside during his summer vacation").

[0476] 3. Send the generated text to the terminal.

[0477] Step 4:

[0478] The device displays the initial section of the story to the user, while sensors begin measuring the user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate).

[0479] Specific behavior:

[0480] 1. The device displays the received story text on the screen.

[0481] 2. The user begins reading the story.

[0482] 3. Sensors on the device measure the user's physiological responses in real time.

[0483] 4. The measured data is periodically sent to the server.

[0484] Step 5:

[0485] The server analyzes the received user response data and evaluates the user's level of excitement and interest. Based on the evaluation results, it instructs the generation AI to generate the next section.

[0486] Specific behavior:

[0487] 1. The server inputs the received sensor data into the machine learning model.

[0488] 2. The model analyzes and scores the user's emotion and interest level (e.g., excitement is rated as low).

[0489] 3. Decide on the direction of the story based on the score (e.g., add an adventure element to the story).

[0490] 4. The server sends new instructions to the generation AI to generate the next section (e.g., "The old woman claims to have once been a witch").

[0491] 5. Send the next generated section to the terminal.

[0492] Step 6:

[0493] Once the story is finished, the server saves all user response data and the generated story, allowing it to be used the next time a story is generated.

[0494] Specific behavior:

[0495] 1. The server generates the story's ending (e.g., "The boy accompanied his grandmother on a magical adventure, reaffirming his precious family bond").

[0496] 2. When the story is completed, all response data and the generated story are saved in a database.

[0497] 3. The saved data is used as training data for the generative AI.

[0498] Example 1

[0499] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0500] Conventional story generation systems have the problem of being unable to customize the story according to the user's interests and emotions, resulting in a uniform experience. Furthermore, because they were unable to dynamically adjust the story based on the user's real-time reactions, it was difficult to provide an optimal reading experience for each individual user. As a result, there were issues with lower satisfaction with the reading experience and lower continuity of use.

[0501] 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.

[0502] In this invention, the server includes a database means for storing the initial pattern of the story, a generation means for dynamically generating a generated story, a sensor means for measuring the user's facial expression, eye brightness, pulse rate, and amount of sweat, an analysis means for analyzing the measured data and evaluating the user's interests and emotions, a control means for adjusting the direction of the story based on the evaluation results, a means for passing the initial pattern of the story to a generative AI model based on user selection information and presenting a newly generated story, and a storage means for saving the generated story and analysis data. This makes it possible to dynamically customize the story according to the user's real-time reactions and provide an individually optimized reading experience.

[0503] "The initial pattern of the story" refers to the initial setting or beginning scenario of the story that the user can select.

[0504] "Database" refers to a system for structuring and storing information such as initial story patterns, generated stories, and user response data.

[0505] "Generation means" refers to AI systems or software that dynamically generate stories based on user selection information.

[0506] "Sensor" refers to a hardware device that measures a user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate, etc.).

[0507] "Analysis means" refers to the algorithms and software used to process and analyze data acquired by sensors and evaluate user interests and emotions.

[0508] "Control measures" refer to systems or software that adjust the direction of the story based on the results of the analytical measures.

[0509] "Generative AI model" refers to a model of artificial intelligence (e.g., generative AI) used to generate a story.

[0510] "Storage means" refers to a storage system or database for storing generated stories and analytical data.

[0511] "Selection means" refers to an interface or system that allows the user to select the initial pattern of the story.

[0512] "Stopping means" refers to a system or software that stops the generation of a story if the user's response exceeds a certain threshold.

[0513] This system allows users to select an initial story pattern, and then a generative AI model dynamically generates a story based on that selection, and then measures and analyzes the user's response in real time. The system consists of the following main components: a server, a terminal, and a user.

[0514] First, the server has a database that stores story templates. This database stores multiple initial story patterns for users to choose from. For example, a template such as "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside" is provided. The server also uses a generative AI model (e.g., generative AI) and is responsible for the initial setup and operation of this AI model. A cloud server (e.g., AWS) is typically used.

[0515] The user can select the first pattern of the story by operating a device (e.g., a smartphone or tablet). The device is equipped with sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat volume. Specific sensors used include a camera (for facial expression detection), a heart rate sensor (e.g., Polar H10), and a sweat sensor. The information selected by the user is sent from the device to the server, which then passes this information to the generative AI model as a prompt. The following prompts are used:

[0516] Start your story with the theme "A 17-year-old city boy hears old stories from his country grandmother." The story begins with the boy visiting his country grandmother's house during summer vacation. Add a scene where it turns out the grandmother is a witch.

[0517] The generative AI model generates the first part of the story based on this prompt, and the server sends that text to the device. The device displays the generated story to the user while measuring the user's physiological responses in real time with sensors and sending the data to the server. For example, it measures whether the user's heart rate or facial expression changes when an exciting scene is displayed.

[0518] The server analyzes the received sensor data using analytical methods (e.g., machine learning models) to assess the user's level of excitement and interest. Based on the results of this analysis, the server sends new instructions to the generative AI model, instructing it to adjust the direction of the story. For example, if the server determines that the user's level of excitement is low, it will instruct the model to add new adventures or surprises to the story.

[0519] After the story is finished, the server stores the user's reaction data and the generated story in a database. This allows the server to utilize this data the next time the story is generated, thereby providing a more engaging story.

[0520] This invention dynamically changes the content according to the user's reactions as they read the story, providing an individually optimized reading experience. As a specific example, a story may be generated based on a template of "a 17-year-old boy living in the city hears an old folktale from his grandmother in the countryside," and if the user is not excited by the displayed content, a scene in which it is revealed that the grandmother is a witch may be added.

[0521] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0522] Step 1:

[0523] The server stores story templates in a database. This includes templates such as "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside." This template data is stored in a database (e.g., MySQL) using an INSERT statement. The server also performs initial setup of the generative AI model (e.g., the generative AI). Specifically, it sets the API key and prepares the initial prompt. The input data is the story template and the configuration data for the generative AI model, and the output is the registration of the template in the database and the initialization of the generative AI model.

[0524] Step 2:

[0525] The user operates the device to select the first pattern for the story. A list of templates is displayed through the device's UI, and the user selects one from the list. The selected template ID is sent from the device to the server as a request. Specifically, the user clicks on a template and presses the "Send" button. The input data is the user's selection information, and the output is a request sent to the server.

[0526] Step 3:

[0527] Based on the received request, the server passes the selected template ID to the generative AI model as a prompt sentence. Based on this prompt sentence, the generative AI model generates the first part of the story. The generated story text is sent from the server to the device. The input data is the selected template ID, and the output is the generated story text. Specifically, the server sends a request to the generative AI model's API to obtain the generated text. It then returns the text in JSON format to the device as a response.

[0528] Step 4:

[0529] The device displays the generated story to the user. At the same time, sensors installed on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate in real time. These data are periodically sent to the server. The input data is the generated story text and the user's physiological response data, and the output is displaying the story to the user and sending sensor data to the server. Specifically, the device displays the story on the screen, obtains data collected from the camera and heart rate sensor via Bluetooth, and sends it to the server using an HTTP POST request.

[0530] Step 5:

[0531] The server analyzes the received sensor data and evaluates the user's excitement and interest. It uses an analysis algorithm (e.g., a machine learning model) to quantify the sensor data and evaluate the user's emotional state. Based on the analysis results, the server sends new instructions to the generative AI model and adjusts the direction of the story. The input data is the user's sensor data, and the output is the user's emotional evaluation result and new instructions to the generative AI model. Specifically, the server executes the analysis algorithm and sends the analysis results to the generative AI model as a new prompt.

[0532] Step 6:

[0533] After the story is finished, the server saves the user's reaction data and the generated story in a database. By utilizing this data in the next story generation, the aim is to provide a more compelling story. The input data is the user's reaction data and the generated story text, and the output is saving to the database. Specifically, the server executes the SQL statement for saving and stores the data in the database.

[0534] (Application example 1)

[0535] 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."

[0536] Conventional story generation systems struggle to reflect a user's interests and emotional responses in real time, making it difficult to optimize an individual reading experience. Furthermore, there is a lack of technology that can effectively measure a user's physiological responses and dynamically adjust the story content based on them. This makes it difficult to maintain a user's interest and provide an engaging story experience.

[0537] 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.

[0538] In this invention, the server includes a database that stores initial story patterns, a generation unit that dynamically generates a generated story, sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, an analysis unit that analyzes the measured data to evaluate the user's interests and emotions, a control unit that adjusts the direction of the story based on the evaluation results, a storage unit that saves the generated story and analysis data, and a terminal that operates a smartphone to display the story and measure the user's reaction. This enables individually optimized dynamic story generation and customization based on the user's physiological reaction.

[0539] "Story start patterns" are templates of different themes and settings that users can choose from at the start of a story.

[0540] A "database" is an information storage system for storing story patterns, generated stories, and user response data.

[0541] "Generation means" refers to algorithms or software that dynamically generate a story based on the story pattern selected by the user.

[0542] "Sensor" refers to a device that measures physiological data such as a user's facial expression, eye brightness, pulse rate, and sweat rate.

[0543] "Analysis means" refers to algorithms or software that analyze the user's physiological data collected by the sensors and evaluate the user's interests and emotions.

[0544] "Control means" refers to algorithms or software that adjust the direction of the story based on the evaluation results obtained by the analysis means.

[0545] "Memory means" refers to a recording device or storage for saving the generated stories and analyzed data.

[0546] A "terminal" is a device such as a smartphone that a user uses to measure physiological responses while reading a story.

[0547] This invention is a system in which a user selects the initial pattern of a story, a generation AI dynamically generates a story based on that, and measures and analyzes the user's reaction in real time. Specific embodiments are described below.

[0548] System configuration

[0549] The system consists of the following major components:

[0550] 1. Server: This is the central component responsible for story generation, database management, analysis, control, and storage. A Transformer-based generative AI model (e.g., GPT-4) is used to generate stories.

[0551] 2. Device: A device such as a smartphone that the user uses to read the story. The device is equipped with sensors such as a camera and a fingerprint sensor (for measuring pulse) to measure the user's physiological responses.

[0552] 3. User: The individual who actually reads the story, and their reaction data is fed back to the server.

[0553] Program processing overview

[0554] Server Processing

[0555] The server first stores a story template in a database (e.g., MongoDB). This template is used when the user selects the first pattern of the story. When the user operates the device to select a pattern of the story, the information is sent to the server. The server then uses generative AI to dynamically generate a story and sends the text to the device.

[0556] The server also analyzes sensor data (facial expressions, pulse rate, sweat rate, etc.) sent from the device in real time. Based on the analysis results, it sends new instructions to the generation AI and adjusts the direction of the story. The generated story and analysis data are stored in a database for later use.

[0557] Terminal handling

[0558] The device sends the initial story pattern selected by the user to the server and receives the generated story text. While displaying the story, the device captures the user's facial expressions with a camera and measures their pulse with a pulse sensor. These data are sent to the server in real time.

[0559] User Roles

[0560] The user operates the device to select a story pattern. While the story is displayed, the user's natural reactions are measured as sensor data. The user's reaction data is reflected in the customization of the story, providing an individually optimized reading experience.

[0561] Examples of concrete examples and prompts

[0562] For example, if the user selects the "Adventure" pattern, the server generates the following story:

[0563] "The boy sensed the beginning of an adventure and stepped into the unknown..."

[0564] If the user's heart rate increases and their facial expression shows surprise, the following prompt is fed to the generative AI model:

[0565] Q: The user selected "Adventure" as the beginning of the story. The current storyline has lowered the user's excitement level, so a more exciting scene is needed. Add a monster encounter or treasure hunt element.

[0566] A:

[0567] Based on these prompts, the generative AI model adds new adventures and surprises to the story, and adjusts the direction of the story based on its analysis.

[0568] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0569] Step 1:

[0570] The server stores story templates in a database, which are used when a user selects the first pattern of a story. The input data is a prepared story template, which is saved in the database. The output is the saved template data.

[0571] Step 2:

[0572] The user operates the terminal to select the first pattern of the story. The terminal collects the user's selection data and sends it to the server. The input data is the pattern of the story selected by the user, and the output is a request sent to the server.

[0573] Step 3:

[0574] The server generates the initial part of the story using a generative AI model based on the received request. The input data is the story pattern selected by the user, which is input to the generative AI model as a prompt sentence. The output is the initial text of the generated story.

[0575] Step 4:

[0576] The device displays the initial text of the generated story to the user. It uses a built-in camera and biometric sensors to measure the user's facial expressions, pulse rate, sweat rate, and other physiological responses. The input data is the generated story text and the measured physiological data, and the output is the displayed story text and the collected physiological data.

[0577] Step 5:

[0578] The terminal transmits the collected physiological data to the server, where the input data is the measured physiological data and the output is the transmitted data to the server.

[0579] Step 6:

[0580] The server analyzes the received sensor data and evaluates the user's interest and emotions. Using analytical means, it analyzes data such as facial expressions and pulse rate to quantify the user's excitement and interest. The input data is the measurement data, and the output is the evaluation result.

[0581] Step 7:

[0582] Based on the evaluation results, the server sends new instructions to the generative AI model to adjust the direction of the story. For example, if the user's excitement level is evaluated as low, the server instructs the model to add a new episode to the story. In this case, the following prompt sentence is input to the generative AI model:

[0583] Q: The user selected "Adventure" as the opening part of the story. The current story flow has lowered the user's excitement level, so a more exciting scene is needed. Please add a monster encounter or treasure hunt element. A:

[0584] The input data are the evaluation results and instructions for the generative AI model, and the output is the tailored narrative text.

[0585] Step 8:

[0586] The server sends the adjusted story text to the terminal. The input data is the adjusted story text, and the output is the data sent to the terminal.

[0587] Step 9:

[0588] The terminal then displays the newly generated story text back to the user. The input data is the adjusted story text, and the output is the new text of the displayed story.

[0589] Step 10:

[0590] As the user continues to read the story, the device and server repeat the above steps, dynamically adjusting the story based on the user's responses to continuously optimize the reading experience. Finally, the generated story and analysis data are stored on the server and used for the next story generation.

[0591] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0592] The present invention is a system incorporating an emotion engine that recognizes the user's emotions, which dynamically generates stories based on the user's interests and emotions, optimizing the reading experience for each individual.

[0593] System configuration

[0594] The system consists of the following main components:

[0595] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[0596] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses.

[0597] 3. Emotion engine: This engine recognizes the user's emotions, analyzes their state, and reflects them in the story generation.

[0598] 4. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[0599] Initial Setup

[0600] The server first stores the story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generation AI, preparing to generate the story.

[0601] Beginning of story generation

[0602] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into the generation AI to generate the initial section of the story. The generated text is then sent to the device.

[0603] Displaying a story and measuring user responses

[0604] The device displays the generated story to the user, while sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmit this data to the server in real time.

[0605] Emotion Recognition and Analysis

[0606] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generation AI.

[0607] Story Updates

[0608] Once the story direction is determined, the server uses generative AI to generate the next section of the story, for example, by adding new adventures or suspense elements to the story if it determines that the user's excitement level is low.

[0609] End of story and data saving

[0610] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[0611] Specific examples

[0612] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read this story, the device continuously measures the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the user's level of excitement is deemed low, the server instructs the generation AI to develop a new plot development, such as "The grandmother reveals that she was once a witch."

[0613] In this way, our invention can dynamically generate and adjust the story according to the user's emotional state, optimizing the reading experience for each individual. By flexibly changing and updating the direction of the story based on detailed sensor data and the analysis results of the emotion engine, it is possible to provide a consistently engaging reading experience for the user.

[0614] The processing flow will be explained below.

[0615] Step 1:

[0616] The server initially stores some initial story patterns in a database.

[0617] Specific behavior:

[0618] 1. The server loads the story template from the configuration file.

[0619] 2. Insert the loaded template data into the database.

[0620] 3. Set the API key and authentication information for the generated AI and initialize the AI.

[0621] Step 2:

[0622] The user selects one from a list of story templates displayed on the terminal, and the terminal transmits the information to the server.

[0623] Specific behavior:

[0624] 1. The terminal displays a list of story templates to the user.

[0625] 2. The user selects the desired template and presses the Select button.

[0626] 3. The device sends a request including the selected template ID to the server.

[0627] Step 3:

[0628] Based on the received request, the server passes the selected template content to the generation AI to generate the first part of the story, and the generated text is sent to the device.

[0629] Specific behavior:

[0630] 1. The server analyzes the received template ID and retrieves the corresponding template content from the database.

[0631] 2. The acquired template content is input into the generation AI to generate the initial section of the story.

[0632] 3. Send the generated text to the terminal.

[0633] Step 4:

[0634] The device displays the initial section of the story to the user, while sensors begin measuring the user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate).

[0635] Specific behavior:

[0636] 1. The device displays the received story text on the screen.

[0637] 2. The user begins reading the story.

[0638] 3. Sensors on the device measure the user's physiological responses in real time.

[0639] 4. The measured data is periodically sent to the server.

[0640] Step 5:

[0641] The server inputs the received user reaction data into the emotion engine, recognizes and evaluates the user's emotional state, and instructs the generation AI to generate the next section based on the evaluation results.

[0642] Specific behavior:

[0643] 1. The server inputs the received sensor data into the emotion engine.

[0644] 2. The emotion engine analyzes and scores the user's emotional state.

[0645] 3. Determine the direction of the story based on the score.

[0646] 4. The server sends new instructions to the generation AI to generate the next section.

[0647] 5. Send the next generated section to the terminal.

[0648] Step 6:

[0649] The device then displays the next generated section to the user, and the sensors again measure the user's response, repeating this process until the user has finished reading the story.

[0650] Specific behavior:

[0651] 1. Your device will display a new story section on the screen.

[0652] 2. The user reads the story.

[0653] 3. The device's sensors again measure the user's reaction and send it to the server.

[0654] Step 7:

[0655] Once the story is finished, the server stores all user response data and the generated story, and uses this data the next time a story is generated.

[0656] Specific behavior:

[0657] 1. The server generates the ending of the story.

[0658] 2. Upon completion of the story, all response data and the generated story are stored in a database.

[0659] 3. The stored data is used as training data for generative AI and emotion engines.

[0660] Example 2

[0661] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0662] Conventional story generation systems have had difficulty dynamically generating and adjusting a story based on the user's emotions and interests. Furthermore, there has been a lack of technology that can evaluate the user's physiological responses in real time and flexibly change the direction of the story based on those responses. As a result, it has been difficult for users to obtain an individually optimized reading experience.

[0663] 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.

[0664] In this invention, the server includes database means for storing initial story patterns, generation means for dynamically generating generated stories, sensor means for measuring the user's facial expressions, eye brightness, pulse rate, and sweat rate, analysis means for analyzing the measured data to evaluate the user's excitement level and interest, control means for adjusting the direction of the story based on the evaluation results, storage means for saving the generated story and analysis data, display means for displaying the generated story, selection means for the user to select a story template, and generation means for generating story sections using a generative AI model. This enables dynamic story generation according to the user's emotional state and individual optimization of the reading experience based on the generated story.

[0665] A "narrative" refers to a series of stories or texts presented to a user.

[0666] "Pattern" refers to the basic structure or template of a story.

[0667] A "database" refers to a system or repository for storing data such as initial story patterns.

[0668] "Generative means" refers to means for dynamically creating narrative sections or stories using generative AI models.

[0669] "Sensor" refers to a device used to measure a user's facial expressions and physiological responses.

[0670] "Analysis means" refers to a means for analyzing sensor data to assess the user's excitement level and interest.

[0671] "Control measures" refer to means for adjusting the direction of the story based on the analysis results.

[0672] "Storage means" refers to means for storing generated stories and user response data.

[0673] "Display means" refers to a means for visually presenting the generated story to the user.

[0674] "Selection means" refers to the interface or mechanism by which a user selects a story template.

[0675] "Generative AI Model" refers to the artificial intelligence model used to generate a section of a story.

[0676] The present invention is a system that utilizes an emotion engine that recognizes the user's emotions to dynamically generate stories based on the user's interests and emotions, providing an individually optimized reading experience.

[0677] System configuration

[0678] The system consists of the following main components:

[0679] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[0680] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses.

[0681] 3. Emotion engine: This engine recognizes the user's emotions, analyzes their state, and reflects them in the story generation.

[0682] 4. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[0683] Initial Setup

[0684] The server first stores story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generative AI model (e.g., a general generative AI model) to prepare for story generation.

[0685] Story Generation

[0686] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into a generative AI model to generate the initial section of the story. The generated text is then sent to the device.

[0687] Displaying a story and measuring user responses

[0688] The device displays the generated story to the user, while sensors on the device measure the user's physiological responses, such as facial expressions, eye brightness, pulse rate, and sweat rate, and transmits this data to a server in real time.

[0689] Emotion Recognition and Analysis

[0690] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generative AI model.

[0691] Story Updates

[0692] Once the story direction is determined, the server uses a generative AI model to generate the next section of the story, for example, by adding new adventures or suspense elements to the story if it determines that the user's excitement level is low.

[0693] End of story and data saving

[0694] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[0695] Specific examples

[0696] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read the story, the device continuously monitors the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the server determines that the user's level of excitement is low, it instructs the generative AI model to develop a new plot, such as "The grandmother reveals that she was once a witch."

[0697] In this way, the present invention can dynamically generate and adjust the story according to the user's emotional state, thereby optimizing the reading experience for each individual. By flexibly changing and updating the direction of the story based on detailed sensor data and the analysis results of the emotion engine, the present invention provides a constantly engaging reading experience for the user.

[0698] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0699] Step 1:

[0700] Initial Setup

[0701] Input: story template, generative AI model

[0702] The server stores templates in a database containing initial patterns of stories, and this information is used by the user when selecting a story.

[0703] The server configures and initializes the generative AI model, including parameter setting and initialization processing for the generative model.

[0704] Output: Templates stored in a database, an initialized generative AI model

[0705] Step 2:

[0706] Beginning of story generation

[0707] Input: User-selected story template

[0708] The user operates the terminal to select a story template.

[0709] The terminal transmits the selected template information to the server.

[0710] The server inputs prompts into the generative AI model based on the received template information to generate the initial section of the story, for example, "A 17-year-old boy living in the city hears an old folktale from his grandmother in the countryside."

[0711] Output: The initial section of the generated story

[0712] Step 3:

[0713] Displaying a story and measuring user responses

[0714] Input: The initial section of the generated story

[0715] The device displays the generated story to the user, who then reads the story on the screen.

[0716] At the same time, sensors installed in the device measure the user's facial expressions, eye brightness, pulse rate, sweat rate, etc. in real time, collecting physiological response data.

[0717] Output: User's physiological response data (facial expression, pulse rate, amount of sweat, etc.)

[0718] Step 4:

[0719] Emotion Recognition and Analysis

[0720] Input: User's physiological response data

[0721] The server inputs the received sensor data into the emotion engine.

[0722] The emotion engine analyzes the user's physiological response data to evaluate the user's level of excitement and interest. For example, if the user's pulse rate increases or their eyes sparkle above a certain level, it will evaluate the user's level of excitement as high.

[0723] Output: Evaluation results of excitement and interest

[0724] Step 5:

[0725] Determining and updating the story direction

[0726] Input: Excitement and interest evaluation results

[0727] The server decides the direction of the story based on the evaluation results obtained from the emotion engine. For example, if the excitement level is low, it adds new adventures or suspense elements.

[0728] Based on the evaluation results, the server re-enters the prompt into the generative AI model, generating a new section, such as "The old woman reveals that she was once a witch."

[0729] Output: Updated narrative section

[0730] Step 6:

[0731] Narrative display and data feedback

[0732] Input: Updated story section

[0733] The device displays the updated story to the user, who then proceeds to read the next section of the story.

[0734] The server then repeats the process of collecting and evaluating new physiological response data from the user.

[0735] Output: Continuously updated narrative, additional physiological response data

[0736] Step 7:

[0737] End of story and data saving

[0738] Input: All generated story sections, all physiological response data of the user

[0739] Once the story is finished, the server stores all user reaction data and the generated story.

[0740] The saved data will be used the next time a story is generated and will be used as learning data to make the generation process more suitable.

[0741] Output: Stored story and user response data

[0742] (Application example 2)

[0743] 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."

[0744] Current reading experiences are static, with the story content set once and not changing based on the user's reactions. This makes it difficult to provide a personalized reading experience that reflects the user's interests and emotions. Furthermore, no system effectively utilizes user emotional data to dynamically adjust the direction of the story. As a result, users tend to lose interest while reading, which leads to issues with the quality of the reading experience.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a database that stores initial story patterns, a generation means that dynamically generates a generated story, sensors that measure the user's facial expression, eye brightness, pulse rate, and sweat rate, an analysis means that analyzes the measured data and evaluates the user's emotions, a control means that adjusts the direction of the story based on the evaluation results, a storage means that saves the generated story and analysis data, a generative AI model that dynamically changes the content of the story depending on the user's state, and an input means for a prompt sentence that generates a new section of the story based on the user's emotions. This enables dynamic story generation according to the user's emotional state, making it possible to provide an individually optimized reading experience.

[0746] The "initial story pattern" is initial setting information including the opening part and basic structure of the story, and is a template that can be selected by the user.

[0747] "Generation means" refers to algorithms or software that dynamically generate a story from input information.

[0748] A "sensor" is a device for measuring a user's physiological responses (facial expression, eye brightness, pulse rate, amount of sweat, etc.).

[0749] "Analysis means" refers to methods and software for assessing the user's state of emotions and interests based on data obtained from sensors.

[0750] "Control means" refers to algorithms or programs that adjust the direction of the story based on the evaluation results of the analysis means.

[0751] "Storage means" refers to a system including a storage device and software for storing the generated story and user response data.

[0752] A "generative AI model" is an artificial intelligence model that takes a user's emotional state as input and generates new sections of a story based on it.

[0753] "Means for inputting prompt sentences" refers to the interface and method for inputting specific instructions to a generative AI model.

[0754] In order to implement this invention, it is necessary to build a system in which a server, terminal, sensor, generative AI model, and prompt sentence input means work in cooperation with each other.

[0755] System configuration

[0756] The system consists of the following main components:

[0757] 1. Server: This is the central component responsible for story generation, database management, analysis, control, and storage. It uses the generative AI model and a means of inputting prompts to generate the next section of the story.

[0758] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses. Specific examples include smartphones and smart glasses.

[0759] 3. Sensor: A device that measures the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmits this data to a server in real time.

[0760] 4. Generative AI model: An artificial intelligence model that analyzes the user's emotional state and generates new sections of the story based on the results.

[0761] 5. Prompt sentence input means: An interface for inputting specific instructions to the generative AI model.

[0762] Initial Setup

[0763] The server first stores the story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generation AI, preparing to generate the story.

[0764] Beginning of story generation

[0765] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into a generative AI model to generate the initial section of the story. The generated text is then sent to the device.

[0766] Displaying a story and measuring user responses

[0767] The device displays the generated story to the user, while sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmit this data to the server in real time.

[0768] Emotion Recognition and Analysis

[0769] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generative AI model.

[0770] Story Updates

[0771] Once the story direction is determined, the server uses a generative AI model to generate the next section of the story, for example, designing it to add new adventures or suspense elements if it determines that the user's excitement level is low.

[0772] End of story and data saving

[0773] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[0774] Specific examples

[0775] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read the story, the device continuously monitors the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the server determines that the user's level of excitement is low, it instructs the generative AI model to develop a new plot, such as "The grandmother reveals that she was once a witch."

[0776] Example prompts to input to the generative AI model:

[0777] "We've determined that users are bored, so add an element of surprise to your story."

[0778] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0779] Step 1:

[0780] Initial Setup

[0781] The server prepares a database to store the initial story patterns, and configures and initializes the generative AI model and the prompt sentence input method. At this stage, the server saves the available story templates in the database.

[0782] Input: Story template information

[0783] Output: Initialized generative AI model and database

[0784] Specific operation: The server stores the story template in a database and initializes the parameters of the generative AI model.

[0785] Step 2:

[0786] Choosing the first pattern of the story

[0787] The user selects the first pattern of the story through the terminal, and once the selection is complete, the terminal sends the information to the server.

[0788] Input: User selection of story patterns

[0789] Output: Sends the selection information to the server

[0790] Specific operation: The user operates the device screen to select a story template from the list.

[0791] Step 3:

[0792] Generating the initial section of the story

[0793] The server inputs the received pattern information into a generative AI model to generate the initial section of the story, and the generated text is sent to the device.

[0794] Input: Selected story pattern information

[0795] Output: The initial section of the generated story

[0796] Specific operation: The generative AI model generates an initial section based on the selected template and sends it to the terminal.

[0797] Step 4:

[0798] Displaying a story and measuring user responses

[0799] The device displays the generated story to the user, while sensors on the device measure the user's facial expression, eye brightness, pulse rate, and sweat rate, and transmit this data to a server in real time.

[0800] Input: The initial section of the generated story and the user's physiological response data

[0801] Output: Sending sensor data to the server

[0802] Specific operation: The device displays the story text to the user, and the built-in sensors begin measuring the user's reactions.

[0803] Step 5:

[0804] Emotion Recognition and Analysis

[0805] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine analyzes the user's excitement level and interest.

[0806] Input: User's physiological response data

[0807] Output: User's emotional state evaluation result

[0808] Specific operation: The emotion engine analyzes the received data and evaluates the user's emotions in real time.

[0809] Step 6:

[0810] Adjusting the direction of the story

[0811] The server inputs prompt sentences into the generative AI model to determine the direction of the story based on the evaluation results.

[0812] Input: User's emotional state assessment results

[0813] Output: Instructions and prompts that generate the following sections:

[0814] Specific operation: The server instructs the generative AI model, "It has been determined that the user is bored, so please add an element of surprise to the story."

[0815] Step 7:

[0816] Story Updates and Display

[0817] The server uses the generative AI model to generate the next section of the story, which is then sent back to the device and displayed to the user.

[0818] Input: A prompt sentence entered into the generative AI model

[0819] Output: Updated narrative section

[0820] How it works: The generative AI model generates a new section, and the server sends it to the device for display.

[0821] Step 8:

[0822] End of story and data saving

[0823] When the story is finished, the server stores all user reaction data and the generated story data in a storage means, so that this data can be used the next time a story is generated.

[0824] Input: All user response data and generated story data

[0825] Output: Saved data

[0826] Specific operation: The server saves the data in a memory device and uses it as a reference for future story generation.

[0827] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0828] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0829] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0830] [Third embodiment]

[0831] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0832] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0833] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0834] 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.

[0835] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0836] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0837] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0838] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0839] 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.

[0840] 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.

[0841] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0842] 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."

[0843] This invention is a system in which a user selects an initial story pattern, a generation AI dynamically generates a story based on that selection, and measures and analyzes the user's response in real time. This system customizes the story according to the user's interests and emotions, optimizing the reading experience for each individual.

[0844] System configuration

[0845] The system consists of the following main components:

[0846] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[0847] 2. Terminal: A device that the user uses to read the story and is equipped with sensors to measure the user's physiological responses.

[0848] 3. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[0849] Initial Setup

[0850] The server first stores a story template (for example, "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside") in a database. This prepares the database for when the user selects the first pattern of the story. The server also simultaneously prepares for story generation by configuring and initializing the generation AI.

[0851] Beginning of story generation

[0852] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends a request to the server. Based on the received request, the server passes the selected template to the generation AI, which generates the first part of the story. The generated story text is then sent to the device.

[0853] Displaying a story and measuring user responses

[0854] The device displays the generated story to the user. At the same time, sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate. This data is sent to the server in real time. For example, the sensors measure whether the user's heart rate or facial expression changes when an exciting scene is displayed.

[0855] Analyzing user responses and updating the story

[0856] The server analyzes the received sensor data and evaluates the user's level of excitement and interest. Based on the analysis results, it sends new instructions to the generation AI to adjust the direction of the story. For example, if the analysis results indicate that the user's level of excitement is low, it instructs the generation AI to add new adventures or surprise elements to the story.

[0857] End of story and data saving

[0858] After the story is finished, the server stores the user's reaction data and the generated story in a database, allowing the server to utilize this data the next time the story is generated to provide a more engaging story.

[0859] Specific examples

[0860] For example, a story starts based on the template "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside." After the user makes a selection, the server generates the following opening: "The boy visits his grandmother's house in the countryside during summer vacation." If the user's heart rate and facial expression data indicate a low level of excitement, the server adds a scene in which it is revealed that the grandmother is a witch, making the story more interesting.

[0861] In this way, the present invention aims to enhance the reading experience by dynamically generating and adjusting stories according to the user's interests and emotions.

[0862] The processing flow will be explained below.

[0863] Step 1:

[0864] As an initial setting, the server stores some initial story patterns in the database, which prepares template data to be used in subsequent story generation.

[0865] Specific behavior:

[0866] 1. The server loads a story template (e.g., "A 17-year-old city boy hears an old folktale from his country grandmother") from a configuration file.

[0867] 2. Insert the loaded template data into the database.

[0868] 3. Set the API key and authentication information for the generated AI and initialize the AI.

[0869] Step 2:

[0870] The user selects one from a list of story templates displayed on the terminal, and once the selection is complete, the terminal sends the information to the server.

[0871] Specific behavior:

[0872] 1. The terminal displays a list of story templates to the user.

[0873] 2. The user selects the desired template (for example, "A 17-year-old boy living in the city hears an old story from a country grandmother") and presses the select button.

[0874] 3. The device sends a request including the selected template ID to the server.

[0875] Step 3:

[0876] Based on the received request, the server passes the selected template content to the generation AI to generate the first part of the story, and the generated text is sent to the device.

[0877] Specific behavior:

[0878] 1. The server analyzes the received template ID and retrieves the corresponding template content from the database.

[0879] 2. The obtained template content is input into the generation AI to generate the initial section of the story (for example, "The boy visited his grandmother's house in the countryside during his summer vacation").

[0880] 3. Send the generated text to the terminal.

[0881] Step 4:

[0882] The device displays the initial section of the story to the user, while sensors begin measuring the user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate).

[0883] Specific behavior:

[0884] 1. The device displays the received story text on the screen.

[0885] 2. The user begins reading the story.

[0886] 3. Sensors on the device measure the user's physiological responses in real time.

[0887] 4. The measured data is periodically sent to the server.

[0888] Step 5:

[0889] The server analyzes the received user response data and evaluates the user's level of excitement and interest. Based on the evaluation results, it instructs the generation AI to generate the next section.

[0890] Specific behavior:

[0891] 1. The server inputs the received sensor data into the machine learning model.

[0892] 2. The model analyzes and scores the user's emotion and interest level (e.g., excitement is rated as low).

[0893] 3. Decide on the direction of the story based on the score (e.g., add an adventure element to the story).

[0894] 4. The server sends new instructions to the generation AI to generate the next section (e.g., "The old woman claims to have once been a witch").

[0895] 5. Send the next generated section to the terminal.

[0896] Step 6:

[0897] Once the story is finished, the server saves all user response data and the generated story, allowing it to be used the next time a story is generated.

[0898] Specific behavior:

[0899] 1. The server generates the story's ending (e.g., "The boy accompanied his grandmother on a magical adventure, reaffirming his precious family bond").

[0900] 2. When the story is completed, all response data and the generated story are saved in a database.

[0901] 3. The saved data is used as training data for the generative AI.

[0902] Example 1

[0903] 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."

[0904] Conventional story generation systems have the problem of being unable to customize the story according to the user's interests and emotions, resulting in a uniform experience. Furthermore, because they were unable to dynamically adjust the story based on the user's real-time reactions, it was difficult to provide an optimal reading experience for each individual user. As a result, there were issues with lower satisfaction with the reading experience and lower continuity of use.

[0905] 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.

[0906] In this invention, the server includes a database means for storing the initial pattern of the story, a generation means for dynamically generating a generated story, a sensor means for measuring the user's facial expression, eye brightness, pulse rate, and amount of sweat, an analysis means for analyzing the measured data and evaluating the user's interests and emotions, a control means for adjusting the direction of the story based on the evaluation results, a means for passing the initial pattern of the story to a generative AI model based on user selection information and presenting a newly generated story, and a storage means for saving the generated story and analysis data. This makes it possible to dynamically customize the story according to the user's real-time reactions and provide an individually optimized reading experience.

[0907] "The initial pattern of the story" refers to the initial setting or beginning scenario of the story that the user can select.

[0908] "Database" refers to a system for structuring and storing information such as initial story patterns, generated stories, and user response data.

[0909] "Generation means" refers to AI systems or software that dynamically generate stories based on user selection information.

[0910] "Sensor" refers to a hardware device that measures a user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate, etc.).

[0911] "Analysis means" refers to the algorithms and software used to process and analyze data acquired by sensors and evaluate user interests and emotions.

[0912] "Control measures" refer to systems or software that adjust the direction of the story based on the results of the analytical measures.

[0913] "Generative AI model" refers to a model of artificial intelligence (e.g., generative AI) used to generate a story.

[0914] "Storage means" refers to a storage system or database for storing generated stories and analytical data.

[0915] "Selection means" refers to an interface or system that allows the user to select the initial pattern of the story.

[0916] "Stopping means" refers to a system or software that stops the generation of a story if the user's response exceeds a certain threshold.

[0917] This system allows users to select an initial story pattern, and then a generative AI model dynamically generates a story based on that selection, and then measures and analyzes the user's response in real time. The system consists of the following main components: a server, a terminal, and a user.

[0918] First, the server has a database that stores story templates. This database stores multiple initial story patterns for users to choose from. For example, a template such as "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside" is provided. The server also uses a generative AI model (e.g., generative AI) and is responsible for the initial setup and operation of this AI model. A cloud server (e.g., AWS) is typically used.

[0919] The user can select the first pattern of the story by operating a device (e.g., a smartphone or tablet). The device is equipped with sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat volume. Specific sensors used include a camera (for facial expression detection), a heart rate sensor (e.g., Polar H10), and a sweat sensor. The information selected by the user is sent from the device to the server, which then passes this information to the generative AI model as a prompt. The following prompts are used:

[0920] Start your story with the theme "A 17-year-old city boy hears old stories from his country grandmother." The story begins with the boy visiting his country grandmother's house during summer vacation. Add a scene where it turns out the grandmother is a witch.

[0921] The generative AI model generates the first part of the story based on this prompt, and the server sends that text to the device. The device displays the generated story to the user while measuring the user's physiological responses in real time with sensors and sending the data to the server. For example, it measures whether the user's heart rate or facial expression changes when an exciting scene is displayed.

[0922] The server analyzes the received sensor data using analytical methods (e.g., machine learning models) to assess the user's level of excitement and interest. Based on the results of this analysis, the server sends new instructions to the generative AI model, instructing it to adjust the direction of the story. For example, if the server determines that the user's level of excitement is low, it will instruct the model to add new adventures or surprises to the story.

[0923] After the story is finished, the server stores the user's reaction data and the generated story in a database. This allows the server to utilize this data the next time the story is generated, thereby providing a more engaging story.

[0924] This invention dynamically changes the content according to the user's reactions as they read the story, providing an individually optimized reading experience. As a specific example, a story may be generated based on a template of "a 17-year-old boy living in the city hears an old folktale from his grandmother in the countryside," and if the user is not excited by the displayed content, a scene in which it is revealed that the grandmother is a witch may be added.

[0925] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0926] Step 1:

[0927] The server stores story templates in a database. This includes templates such as "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside." This template data is stored in a database (e.g., MySQL) using an INSERT statement. The server also performs initial setup of the generative AI model (e.g., the generative AI). Specifically, it sets the API key and prepares the initial prompt. The input data is the story template and the configuration data for the generative AI model, and the output is the registration of the template in the database and the initialization of the generative AI model.

[0928] Step 2:

[0929] The user operates the device to select the first pattern for the story. A list of templates is displayed through the device's UI, and the user selects one from the list. The selected template ID is sent from the device to the server as a request. Specifically, the user clicks on a template and presses the "Send" button. The input data is the user's selection information, and the output is a request sent to the server.

[0930] Step 3:

[0931] Based on the received request, the server passes the selected template ID to the generative AI model as a prompt sentence. Based on this prompt sentence, the generative AI model generates the first part of the story. The generated story text is sent from the server to the device. The input data is the selected template ID, and the output is the generated story text. Specifically, the server sends a request to the generative AI model's API to obtain the generated text. It then returns the text in JSON format to the device as a response.

[0932] Step 4:

[0933] The device displays the generated story to the user. At the same time, sensors installed on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate in real time. These data are periodically sent to the server. The input data is the generated story text and the user's physiological response data, and the output is displaying the story to the user and sending sensor data to the server. Specifically, the device displays the story on the screen, obtains data collected from the camera and heart rate sensor via Bluetooth, and sends it to the server using an HTTP POST request.

[0934] Step 5:

[0935] The server analyzes the received sensor data and evaluates the user's excitement and interest. It uses an analysis algorithm (e.g., a machine learning model) to quantify the sensor data and evaluate the user's emotional state. Based on the analysis results, the server sends new instructions to the generative AI model and adjusts the direction of the story. The input data is the user's sensor data, and the output is the user's emotional evaluation result and new instructions to the generative AI model. Specifically, the server executes the analysis algorithm and sends the analysis results to the generative AI model as a new prompt.

[0936] Step 6:

[0937] After the story is finished, the server saves the user's reaction data and the generated story in a database. By utilizing this data in the next story generation, the aim is to provide a more compelling story. The input data is the user's reaction data and the generated story text, and the output is saving to the database. Specifically, the server executes the SQL statement for saving and stores the data in the database.

[0938] (Application example 1)

[0939] 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."

[0940] Conventional story generation systems struggle to reflect a user's interests and emotional responses in real time, making it difficult to optimize an individual reading experience. Furthermore, there is a lack of technology that can effectively measure a user's physiological responses and dynamically adjust the story content based on them. This makes it difficult to maintain a user's interest and provide an engaging story experience.

[0941] 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.

[0942] In this invention, the server includes a database that stores initial story patterns, a generation unit that dynamically generates a generated story, sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, an analysis unit that analyzes the measured data to evaluate the user's interests and emotions, a control unit that adjusts the direction of the story based on the evaluation results, a storage unit that saves the generated story and analysis data, and a terminal that operates a smartphone to display the story and measure the user's reaction. This enables individually optimized dynamic story generation and customization based on the user's physiological reaction.

[0943] "Story start patterns" are templates of different themes and settings that users can choose from at the start of a story.

[0944] A "database" is an information storage system for storing story patterns, generated stories, and user response data.

[0945] "Generation means" refers to algorithms or software that dynamically generate a story based on the story pattern selected by the user.

[0946] "Sensor" refers to a device that measures physiological data such as a user's facial expression, eye brightness, pulse rate, and sweat rate.

[0947] "Analysis means" refers to algorithms or software that analyze the user's physiological data collected by the sensors and evaluate the user's interests and emotions.

[0948] "Control means" refers to algorithms or software that adjust the direction of the story based on the evaluation results obtained by the analysis means.

[0949] "Memory means" refers to a recording device or storage for saving the generated stories and analyzed data.

[0950] A "terminal" is a device such as a smartphone that a user uses to measure physiological responses while reading a story.

[0951] This invention is a system in which a user selects the initial pattern of a story, a generation AI dynamically generates a story based on that, and measures and analyzes the user's reaction in real time. Specific embodiments are described below.

[0952] System configuration

[0953] The system consists of the following major components:

[0954] 1. Server: This is the central component responsible for story generation, database management, analysis, control, and storage. A Transformer-based generative AI model (e.g., GPT-4) is used to generate stories.

[0955] 2. Device: A device such as a smartphone that the user uses to read the story. The device is equipped with sensors such as a camera and a fingerprint sensor (for measuring pulse) to measure the user's physiological responses.

[0956] 3. User: The individual who actually reads the story, and their reaction data is fed back to the server.

[0957] Program processing overview

[0958] Server Processing

[0959] The server first stores a story template in a database (e.g., MongoDB). This template is used when the user selects the first pattern of the story. When the user operates the device to select a pattern of the story, the information is sent to the server. The server then uses generative AI to dynamically generate a story and sends the text to the device.

[0960] The server also analyzes sensor data (facial expressions, pulse rate, sweat rate, etc.) sent from the device in real time. Based on the analysis results, it sends new instructions to the generation AI and adjusts the direction of the story. The generated story and analysis data are stored in a database for later use.

[0961] Terminal handling

[0962] The device sends the initial story pattern selected by the user to the server and receives the generated story text. While displaying the story, the device captures the user's facial expressions with a camera and measures their pulse with a pulse sensor. These data are sent to the server in real time.

[0963] User Roles

[0964] The user operates the device to select a story pattern. While the story is displayed, the user's natural reactions are measured as sensor data. The user's reaction data is reflected in the customization of the story, providing an individually optimized reading experience.

[0965] Examples of concrete examples and prompts

[0966] For example, if the user selects the "Adventure" pattern, the server generates the following story:

[0967] "The boy sensed the beginning of an adventure and stepped into the unknown..."

[0968] If the user's heart rate increases and their facial expression shows surprise, the following prompt is fed to the generative AI model:

[0969] Q: The user selected "Adventure" as the beginning of the story. The current storyline has lowered the user's excitement level, so a more exciting scene is needed. Add a monster encounter or treasure hunt element.

[0970] A:

[0971] Based on these prompts, the generative AI model adds new adventures and surprises to the story, and adjusts the direction of the story based on its analysis.

[0972] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0973] Step 1:

[0974] The server stores story templates in a database, which are used when a user selects the first pattern of a story. The input data is a prepared story template, which is saved in the database. The output is the saved template data.

[0975] Step 2:

[0976] The user operates the terminal to select the first pattern of the story. The terminal collects the user's selection data and sends it to the server. The input data is the pattern of the story selected by the user, and the output is a request sent to the server.

[0977] Step 3:

[0978] The server generates the initial part of the story using a generative AI model based on the received request. The input data is the story pattern selected by the user, which is input to the generative AI model as a prompt sentence. The output is the initial text of the generated story.

[0979] Step 4:

[0980] The device displays the initial text of the generated story to the user. It uses a built-in camera and biometric sensors to measure the user's facial expressions, pulse rate, sweat rate, and other physiological responses. The input data is the generated story text and the measured physiological data, and the output is the displayed story text and the collected physiological data.

[0981] Step 5:

[0982] The terminal transmits the collected physiological data to the server, where the input data is the measured physiological data and the output is the transmitted data to the server.

[0983] Step 6:

[0984] The server analyzes the received sensor data and evaluates the user's interest and emotions. Using analytical means, it analyzes data such as facial expressions and pulse rate to quantify the user's excitement and interest. The input data is the measurement data, and the output is the evaluation result.

[0985] Step 7:

[0986] Based on the evaluation results, the server sends new instructions to the generative AI model to adjust the direction of the story. For example, if the user's excitement level is evaluated as low, the server instructs the model to add a new episode to the story. In this case, the following prompt sentence is input to the generative AI model:

[0987] Q: The user selected "Adventure" as the opening part of the story. The current story flow has lowered the user's excitement level, so a more exciting scene is needed. Please add a monster encounter or treasure hunt element. A:

[0988] The input data are the evaluation results and instructions for the generative AI model, and the output is the tailored narrative text.

[0989] Step 8:

[0990] The server sends the adjusted story text to the terminal. The input data is the adjusted story text, and the output is the data sent to the terminal.

[0991] Step 9:

[0992] The terminal then displays the newly generated story text back to the user. The input data is the adjusted story text, and the output is the new text of the displayed story.

[0993] Step 10:

[0994] As the user continues to read the story, the device and server repeat the above steps, dynamically adjusting the story based on the user's responses to continuously optimize the reading experience. Finally, the generated story and analysis data are stored on the server and used for the next story generation.

[0995] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0996] The present invention is a system incorporating an emotion engine that recognizes the user's emotions, which dynamically generates stories based on the user's interests and emotions, optimizing the reading experience for each individual.

[0997] System configuration

[0998] The system consists of the following main components:

[0999] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[1000] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses.

[1001] 3. Emotion engine: This engine recognizes the user's emotions, analyzes their state, and reflects them in the story generation.

[1002] 4. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[1003] Initial Setup

[1004] The server first stores the story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generation AI, preparing to generate the story.

[1005] Beginning of story generation

[1006] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into the generation AI to generate the initial section of the story. The generated text is then sent to the device.

[1007] Displaying a story and measuring user responses

[1008] The device displays the generated story to the user, while sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmit this data to the server in real time.

[1009] Emotion Recognition and Analysis

[1010] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generation AI.

[1011] Story Updates

[1012] Once the story direction is determined, the server uses generative AI to generate the next section of the story, for example, by adding new adventures or suspense elements to the story if it determines that the user's excitement level is low.

[1013] End of story and data saving

[1014] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[1015] Specific examples

[1016] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read this story, the device continuously measures the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the user's level of excitement is deemed low, the server instructs the generation AI to develop a new plot development, such as "The grandmother reveals that she was once a witch."

[1017] In this way, our invention can dynamically generate and adjust the story according to the user's emotional state, optimizing the reading experience for each individual. By flexibly changing and updating the direction of the story based on detailed sensor data and the analysis results of the emotion engine, it is possible to provide a consistently engaging reading experience for the user.

[1018] The processing flow will be explained below.

[1019] Step 1:

[1020] The server initially stores some initial story patterns in a database.

[1021] Specific behavior:

[1022] 1. The server loads the story template from the configuration file.

[1023] 2. Insert the loaded template data into the database.

[1024] 3. Set the API key and authentication information for the generated AI and initialize the AI.

[1025] Step 2:

[1026] The user selects one from a list of story templates displayed on the terminal, and the terminal transmits the information to the server.

[1027] Specific behavior:

[1028] 1. The terminal displays a list of story templates to the user.

[1029] 2. The user selects the desired template and presses the Select button.

[1030] 3. The device sends a request including the selected template ID to the server.

[1031] Step 3:

[1032] Based on the received request, the server passes the selected template content to the generation AI to generate the first part of the story, and the generated text is sent to the device.

[1033] Specific behavior:

[1034] 1. The server analyzes the received template ID and retrieves the corresponding template content from the database.

[1035] 2. The acquired template content is input into the generation AI to generate the initial section of the story.

[1036] 3. Send the generated text to the terminal.

[1037] Step 4:

[1038] The device displays the initial section of the story to the user, while sensors begin measuring the user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate).

[1039] Specific behavior:

[1040] 1. The device displays the received story text on the screen.

[1041] 2. The user begins reading the story.

[1042] 3. Sensors on the device measure the user's physiological responses in real time.

[1043] 4. The measured data is periodically sent to the server.

[1044] Step 5:

[1045] The server inputs the received user reaction data into the emotion engine, recognizes and evaluates the user's emotional state, and instructs the generation AI to generate the next section based on the evaluation results.

[1046] Specific behavior:

[1047] 1. The server inputs the received sensor data into the emotion engine.

[1048] 2. The emotion engine analyzes and scores the user's emotional state.

[1049] 3. Determine the direction of the story based on the score.

[1050] 4. The server sends new instructions to the generation AI to generate the next section.

[1051] 5. Send the next generated section to the terminal.

[1052] Step 6:

[1053] The device then displays the next generated section to the user, and the sensors again measure the user's response, repeating this process until the user has finished reading the story.

[1054] Specific behavior:

[1055] 1. Your device will display a new story section on the screen.

[1056] 2. The user reads the story.

[1057] 3. The device's sensors again measure the user's reaction and send it to the server.

[1058] Step 7:

[1059] Once the story is finished, the server stores all user response data and the generated story, and uses this data the next time a story is generated.

[1060] Specific behavior:

[1061] 1. The server generates the ending of the story.

[1062] 2. Upon completion of the story, all response data and the generated story are stored in a database.

[1063] 3. The stored data is used as training data for generative AI and emotion engines.

[1064] Example 2

[1065] 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."

[1066] Conventional story generation systems have had difficulty dynamically generating and adjusting a story based on the user's emotions and interests. Furthermore, there has been a lack of technology that can evaluate the user's physiological responses in real time and flexibly change the direction of the story based on those responses. As a result, it has been difficult for users to obtain an individually optimized reading experience.

[1067] 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.

[1068] In this invention, the server includes database means for storing initial story patterns, generation means for dynamically generating generated stories, sensor means for measuring the user's facial expressions, eye brightness, pulse rate, and sweat rate, analysis means for analyzing the measured data to evaluate the user's excitement level and interest, control means for adjusting the direction of the story based on the evaluation results, storage means for saving the generated story and analysis data, display means for displaying the generated story, selection means for the user to select a story template, and generation means for generating story sections using a generative AI model. This enables dynamic story generation according to the user's emotional state and individual optimization of the reading experience based on the generated story.

[1069] A "narrative" refers to a series of stories or texts presented to a user.

[1070] "Pattern" refers to the basic structure or template of a story.

[1071] A "database" refers to a system or repository for storing data such as initial story patterns.

[1072] "Generative means" refers to means for dynamically creating narrative sections or stories using generative AI models.

[1073] "Sensor" refers to a device used to measure a user's facial expressions and physiological responses.

[1074] "Analysis means" refers to a means for analyzing sensor data to assess the user's excitement level and interest.

[1075] "Control measures" refer to means for adjusting the direction of the story based on the analysis results.

[1076] "Storage means" refers to means for storing generated stories and user response data.

[1077] "Display means" refers to a means for visually presenting the generated story to the user.

[1078] "Selection means" refers to the interface or mechanism by which a user selects a story template.

[1079] "Generative AI Model" refers to the artificial intelligence model used to generate a section of a story.

[1080] The present invention is a system that utilizes an emotion engine that recognizes the user's emotions to dynamically generate stories based on the user's interests and emotions, providing an individually optimized reading experience.

[1081] System configuration

[1082] The system consists of the following main components:

[1083] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[1084] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses.

[1085] 3. Emotion engine: This engine recognizes the user's emotions, analyzes their state, and reflects them in the story generation.

[1086] 4. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[1087] Initial Setup

[1088] The server first stores story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generative AI model (e.g., a general generative AI model) to prepare for story generation.

[1089] Story Generation

[1090] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into a generative AI model to generate the initial section of the story. The generated text is then sent to the device.

[1091] Displaying a story and measuring user responses

[1092] The device displays the generated story to the user, while sensors on the device measure the user's physiological responses, such as facial expressions, eye brightness, pulse rate, and sweat rate, and transmits this data to a server in real time.

[1093] Emotion Recognition and Analysis

[1094] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generative AI model.

[1095] Story Updates

[1096] Once the story direction is determined, the server uses a generative AI model to generate the next section of the story, for example, by adding new adventures or suspense elements to the story if it determines that the user's excitement level is low.

[1097] End of story and data saving

[1098] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[1099] Specific examples

[1100] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read the story, the device continuously monitors the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the server determines that the user's level of excitement is low, it instructs the generative AI model to develop a new plot, such as "The grandmother reveals that she was once a witch."

[1101] In this way, the present invention can dynamically generate and adjust the story according to the user's emotional state, thereby optimizing the reading experience for each individual. By flexibly changing and updating the direction of the story based on detailed sensor data and the analysis results of the emotion engine, the present invention provides a constantly engaging reading experience for the user.

[1102] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1103] Step 1:

[1104] Initial Setup

[1105] Input: story template, generative AI model

[1106] The server stores templates in a database containing initial patterns of stories, and this information is used by the user when selecting a story.

[1107] The server configures and initializes the generative AI model, including parameter setting and initialization processing for the generative model.

[1108] Output: Templates stored in a database, an initialized generative AI model

[1109] Step 2:

[1110] Beginning of story generation

[1111] Input: User-selected story template

[1112] The user operates the terminal to select a story template.

[1113] The terminal transmits the selected template information to the server.

[1114] The server inputs prompts into the generative AI model based on the received template information to generate the initial section of the story, for example, "A 17-year-old boy living in the city hears an old folktale from his grandmother in the countryside."

[1115] Output: The initial section of the generated story

[1116] Step 3:

[1117] Displaying a story and measuring user responses

[1118] Input: The initial section of the generated story

[1119] The device displays the generated story to the user, who then reads the story on the screen.

[1120] At the same time, sensors installed in the device measure the user's facial expressions, eye brightness, pulse rate, sweat rate, etc. in real time, collecting physiological response data.

[1121] Output: User's physiological response data (facial expression, pulse rate, amount of sweat, etc.)

[1122] Step 4:

[1123] Emotion Recognition and Analysis

[1124] Input: User's physiological response data

[1125] The server inputs the received sensor data into the emotion engine.

[1126] The emotion engine analyzes the user's physiological response data to evaluate the user's level of excitement and interest. For example, if the user's pulse rate increases or their eyes sparkle above a certain level, it will evaluate the user's level of excitement as high.

[1127] Output: Evaluation results of excitement and interest

[1128] Step 5:

[1129] Determining and updating the story direction

[1130] Input: Excitement and interest evaluation results

[1131] The server decides the direction of the story based on the evaluation results obtained from the emotion engine. For example, if the excitement level is low, it adds new adventures or suspense elements.

[1132] Based on the evaluation results, the server re-enters the prompt into the generative AI model, generating a new section, such as "The old woman reveals that she was once a witch."

[1133] Output: Updated narrative section

[1134] Step 6:

[1135] Narrative display and data feedback

[1136] Input: Updated story section

[1137] The device displays the updated story to the user, who then proceeds to read the next section of the story.

[1138] The server then repeats the process of collecting and evaluating new physiological response data from the user.

[1139] Output: Continuously updated narrative, additional physiological response data

[1140] Step 7:

[1141] End of story and data saving

[1142] Input: All generated story sections, all physiological response data of the user

[1143] Once the story is finished, the server stores all user reaction data and the generated story.

[1144] The saved data will be used the next time a story is generated and will be used as learning data to make the generation process more suitable.

[1145] Output: Stored story and user response data

[1146] (Application example 2)

[1147] 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."

[1148] Current reading experiences are static, with the story content set once and not changing based on the user's reactions. This makes it difficult to provide a personalized reading experience that reflects the user's interests and emotions. Furthermore, no system effectively utilizes user emotional data to dynamically adjust the direction of the story. As a result, users tend to lose interest while reading, which leads to issues with the quality of the reading experience.

[1149] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a database that stores initial story patterns, a generation means that dynamically generates a generated story, sensors that measure the user's facial expression, eye brightness, pulse rate, and sweat rate, an analysis means that analyzes the measured data and evaluates the user's emotions, a control means that adjusts the direction of the story based on the evaluation results, a storage means that saves the generated story and analysis data, a generative AI model that dynamically changes the content of the story depending on the user's state, and an input means for a prompt sentence that generates a new section of the story based on the user's emotions. This enables dynamic story generation according to the user's emotional state, making it possible to provide an individually optimized reading experience.

[1150] The "initial story pattern" is initial setting information including the opening part and basic structure of the story, and is a template that can be selected by the user.

[1151] "Generation means" refers to algorithms or software that dynamically generate a story from input information.

[1152] A "sensor" is a device for measuring a user's physiological responses (facial expression, eye brightness, pulse rate, amount of sweat, etc.).

[1153] "Analysis means" refers to methods and software for assessing the user's state of emotions and interests based on data obtained from sensors.

[1154] "Control means" refers to algorithms or programs that adjust the direction of the story based on the evaluation results of the analysis means.

[1155] "Storage means" refers to a system including a storage device and software for storing the generated story and user response data.

[1156] A "generative AI model" is an artificial intelligence model that takes a user's emotional state as input and generates new sections of a story based on it.

[1157] "Means for inputting prompt sentences" refers to the interface and method for inputting specific instructions to a generative AI model.

[1158] In order to implement this invention, it is necessary to build a system in which a server, terminal, sensor, generative AI model, and prompt sentence input means work in cooperation with each other.

[1159] System configuration

[1160] The system consists of the following main components:

[1161] 1. Server: This is the central component responsible for story generation, database management, analysis, control, and storage. It uses the generative AI model and a means of inputting prompts to generate the next section of the story.

[1162] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses. Specific examples include smartphones and smart glasses.

[1163] 3. Sensor: A device that measures the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmits this data to a server in real time.

[1164] 4. Generative AI model: An artificial intelligence model that analyzes the user's emotional state and generates new sections of the story based on the results.

[1165] 5. Prompt sentence input means: An interface for inputting specific instructions to the generative AI model.

[1166] Initial Setup

[1167] The server first stores the story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generation AI, preparing to generate the story.

[1168] Beginning of story generation

[1169] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into a generative AI model to generate the initial section of the story. The generated text is then sent to the device.

[1170] Displaying a story and measuring user responses

[1171] The device displays the generated story to the user, while sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmit this data to the server in real time.

[1172] Emotion Recognition and Analysis

[1173] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generative AI model.

[1174] Story Updates

[1175] Once the story direction is determined, the server uses a generative AI model to generate the next section of the story, for example, designing it to add new adventures or suspense elements if it determines that the user's excitement level is low.

[1176] End of story and data saving

[1177] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[1178] Specific examples

[1179] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read the story, the device continuously monitors the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the server determines that the user's level of excitement is low, it instructs the generative AI model to develop a new plot, such as "The grandmother reveals that she was once a witch."

[1180] Example prompts to input to the generative AI model:

[1181] "We've determined that users are bored, so add an element of surprise to your story."

[1182] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1183] Step 1:

[1184] Initial Setup

[1185] The server prepares a database to store the initial story patterns, and configures and initializes the generative AI model and the prompt sentence input method. At this stage, the server saves the available story templates in the database.

[1186] Input: Story template information

[1187] Output: Initialized generative AI model and database

[1188] Specific operation: The server stores the story template in a database and initializes the parameters of the generative AI model.

[1189] Step 2:

[1190] Choosing the first pattern of the story

[1191] The user selects the first pattern of the story through the terminal, and once the selection is complete, the terminal sends the information to the server.

[1192] Input: User selection of story patterns

[1193] Output: Sends the selection information to the server

[1194] Specific operation: The user operates the device screen to select a story template from the list.

[1195] Step 3:

[1196] Generating the initial section of the story

[1197] The server inputs the received pattern information into a generative AI model to generate the initial section of the story, and the generated text is sent to the device.

[1198] Input: Selected story pattern information

[1199] Output: The initial section of the generated story

[1200] Specific operation: The generative AI model generates an initial section based on the selected template and sends it to the terminal.

[1201] Step 4:

[1202] Displaying a story and measuring user responses

[1203] The device displays the generated story to the user, while sensors on the device measure the user's facial expression, eye brightness, pulse rate, and sweat rate, and transmit this data to a server in real time.

[1204] Input: The initial section of the generated story and the user's physiological response data

[1205] Output: Sending sensor data to the server

[1206] Specific operation: The device displays the story text to the user, and the built-in sensors begin measuring the user's reactions.

[1207] Step 5:

[1208] Emotion Recognition and Analysis

[1209] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine analyzes the user's excitement level and interest.

[1210] Input: User's physiological response data

[1211] Output: User's emotional state evaluation result

[1212] Specific operation: The emotion engine analyzes the received data and evaluates the user's emotions in real time.

[1213] Step 6:

[1214] Adjusting the direction of the story

[1215] The server inputs prompt sentences into the generative AI model to determine the direction of the story based on the evaluation results.

[1216] Input: User's emotional state assessment results

[1217] Output: Instructions and prompts that generate the following sections:

[1218] Specific operation: The server instructs the generative AI model, "It has been determined that the user is bored, so please add an element of surprise to the story."

[1219] Step 7:

[1220] Story Updates and Display

[1221] The server uses the generative AI model to generate the next section of the story, which is then sent back to the device and displayed to the user.

[1222] Input: A prompt sentence entered into the generative AI model

[1223] Output: Updated narrative section

[1224] How it works: The generative AI model generates a new section, and the server sends it to the device for display.

[1225] Step 8:

[1226] End of story and data saving

[1227] When the story is finished, the server stores all user reaction data and the generated story data in a storage means, so that this data can be used the next time a story is generated.

[1228] Input: All user response data and generated story data

[1229] Output: Saved data

[1230] Specific operation: The server saves the data in a memory device and uses it as a reference for future story generation.

[1231] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1232] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1233] 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.

[1234] [Fourth embodiment]

[1235] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1236] 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.

[1237] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1238] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1239] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1240] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1241] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1242] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1243] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1244] 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.

[1245] 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.

[1246] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1247] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1248] This invention is a system in which a user selects an initial story pattern, a generation AI dynamically generates a story based on that selection, and measures and analyzes the user's response in real time. This system customizes the story according to the user's interests and emotions, optimizing the reading experience for each individual.

[1249] System configuration

[1250] The system consists of the following main components:

[1251] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[1252] 2. Terminal: A device that the user uses to read the story and is equipped with sensors to measure the user's physiological responses.

[1253] 3. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[1254] Initial Setup

[1255] The server first stores a story template (for example, "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside") in a database. This prepares the database for when the user selects the first pattern of the story. The server also simultaneously prepares for story generation by configuring and initializing the generation AI.

[1256] Beginning of story generation

[1257] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends a request to the server. Based on the received request, the server passes the selected template to the generation AI, which generates the first part of the story. The generated story text is then sent to the device.

[1258] Displaying a story and measuring user responses

[1259] The device displays the generated story to the user. At the same time, sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate. This data is sent to the server in real time. For example, the sensors measure whether the user's heart rate or facial expression changes when an exciting scene is displayed.

[1260] Analyzing user responses and updating the story

[1261] The server analyzes the received sensor data and evaluates the user's level of excitement and interest. Based on the analysis results, it sends new instructions to the generation AI to adjust the direction of the story. For example, if the analysis results indicate that the user's level of excitement is low, it instructs the generation AI to add new adventures or surprise elements to the story.

[1262] End of story and data saving

[1263] After the story is finished, the server stores the user's reaction data and the generated story in a database, allowing the server to utilize this data the next time the story is generated to provide a more engaging story.

[1264] Specific examples

[1265] For example, a story starts based on the template "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside." After the user makes a selection, the server generates the following opening: "The boy visits his grandmother's house in the countryside during summer vacation." If the user's heart rate and facial expression data indicate a low level of excitement, the server adds a scene in which it is revealed that the grandmother is a witch, making the story more interesting.

[1266] In this way, the present invention aims to enhance the reading experience by dynamically generating and adjusting stories according to the user's interests and emotions.

[1267] The processing flow will be explained below.

[1268] Step 1:

[1269] As an initial setting, the server stores some initial story patterns in the database, which prepares template data to be used in subsequent story generation.

[1270] Specific behavior:

[1271] 1. The server loads a story template (e.g., "A 17-year-old city boy hears an old folktale from his country grandmother") from a configuration file.

[1272] 2. Insert the loaded template data into the database.

[1273] 3. Set the API key and authentication information for the generated AI and initialize the AI.

[1274] Step 2:

[1275] The user selects one from a list of story templates displayed on the terminal, and once the selection is complete, the terminal sends the information to the server.

[1276] Specific behavior:

[1277] 1. The terminal displays a list of story templates to the user.

[1278] 2. The user selects the desired template (for example, "A 17-year-old boy living in the city hears an old story from a country grandmother") and presses the select button.

[1279] 3. The device sends a request including the selected template ID to the server.

[1280] Step 3:

[1281] Based on the received request, the server passes the selected template content to the generation AI to generate the first part of the story, and the generated text is sent to the device.

[1282] Specific behavior:

[1283] 1. The server analyzes the received template ID and retrieves the corresponding template content from the database.

[1284] 2. The obtained template content is input into the generation AI to generate the initial section of the story (for example, "The boy visited his grandmother's house in the countryside during his summer vacation").

[1285] 3. Send the generated text to the terminal.

[1286] Step 4:

[1287] The device displays the initial section of the story to the user, while sensors begin measuring the user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate).

[1288] Specific behavior:

[1289] 1. The device displays the received story text on the screen.

[1290] 2. The user begins reading the story.

[1291] 3. Sensors on the device measure the user's physiological responses in real time.

[1292] 4. The measured data is periodically sent to the server.

[1293] Step 5:

[1294] The server analyzes the received user response data and evaluates the user's level of excitement and interest. Based on the evaluation results, it instructs the generation AI to generate the next section.

[1295] Specific behavior:

[1296] 1. The server inputs the received sensor data into the machine learning model.

[1297] 2. The model analyzes and scores the user's emotion and interest level (e.g., excitement is rated as low).

[1298] 3. Decide on the direction of the story based on the score (e.g., add an adventure element to the story).

[1299] 4. The server sends new instructions to the generation AI to generate the next section (e.g., "The old woman claims to have once been a witch").

[1300] 5. Send the next generated section to the terminal.

[1301] Step 6:

[1302] Once the story is finished, the server saves all user response data and the generated story, allowing it to be used the next time a story is generated.

[1303] Specific behavior:

[1304] 1. The server generates the story's ending (e.g., "The boy accompanied his grandmother on a magical adventure, reaffirming his precious family bond").

[1305] 2. When the story is completed, all response data and the generated story are saved in a database.

[1306] 3. The saved data is used as training data for the generative AI.

[1307] Example 1

[1308] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1309] Conventional story generation systems have the problem of being unable to customize the story according to the user's interests and emotions, resulting in a uniform experience. Furthermore, because they were unable to dynamically adjust the story based on the user's real-time reactions, it was difficult to provide an optimal reading experience for each individual user. As a result, there were issues with lower satisfaction with the reading experience and lower continuity of use.

[1310] 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.

[1311] In this invention, the server includes a database means for storing the initial pattern of the story, a generation means for dynamically generating a generated story, a sensor means for measuring the user's facial expression, eye brightness, pulse rate, and amount of sweat, an analysis means for analyzing the measured data and evaluating the user's interests and emotions, a control means for adjusting the direction of the story based on the evaluation results, a means for passing the initial pattern of the story to a generative AI model based on user selection information and presenting a newly generated story, and a storage means for saving the generated story and analysis data. This makes it possible to dynamically customize the story according to the user's real-time reactions and provide an individually optimized reading experience.

[1312] "The initial pattern of the story" refers to the initial setting or beginning scenario of the story that the user can select.

[1313] "Database" refers to a system for structuring and storing information such as initial story patterns, generated stories, and user response data.

[1314] "Generation means" refers to AI systems or software that dynamically generate stories based on user selection information.

[1315] "Sensor" refers to a hardware device that measures a user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate, etc.).

[1316] "Analysis means" refers to the algorithms and software used to process and analyze data acquired by sensors and evaluate user interests and emotions.

[1317] "Control measures" refer to systems or software that adjust the direction of the story based on the results of the analytical measures.

[1318] "Generative AI model" refers to a model of artificial intelligence (e.g., generative AI) used to generate a story.

[1319] "Storage means" refers to a storage system or database for storing generated stories and analytical data.

[1320] "Selection means" refers to an interface or system that allows the user to select the initial pattern of the story.

[1321] "Stopping means" refers to a system or software that stops the generation of a story if the user's response exceeds a certain threshold.

[1322] This system allows users to select an initial story pattern, and then a generative AI model dynamically generates a story based on that selection, and then measures and analyzes the user's response in real time. The system consists of the following main components: a server, a terminal, and a user.

[1323] First, the server has a database that stores story templates. This database stores multiple initial story patterns for users to choose from. For example, a template such as "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside" is provided. The server also uses a generative AI model (e.g., generative AI) and is responsible for the initial setup and operation of this AI model. A cloud server (e.g., AWS) is typically used.

[1324] The user can select the first pattern of the story by operating a device (e.g., a smartphone or tablet). The device is equipped with sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat volume. Specific sensors used include a camera (for facial expression detection), a heart rate sensor (e.g., Polar H10), and a sweat sensor. The information selected by the user is sent from the device to the server, which then passes this information to the generative AI model as a prompt. The following prompts are used:

[1325] Start your story with the theme "A 17-year-old city boy hears old stories from his country grandmother." The story begins with the boy visiting his country grandmother's house during summer vacation. Add a scene where it turns out the grandmother is a witch.

[1326] The generative AI model generates the first part of the story based on this prompt, and the server sends that text to the device. The device displays the generated story to the user while measuring the user's physiological responses in real time with sensors and sending the data to the server. For example, it measures whether the user's heart rate or facial expression changes when an exciting scene is displayed.

[1327] The server analyzes the received sensor data using analytical methods (e.g., machine learning models) to assess the user's level of excitement and interest. Based on the results of this analysis, the server sends new instructions to the generative AI model, instructing it to adjust the direction of the story. For example, if the server determines that the user's level of excitement is low, it will instruct the model to add new adventures or surprises to the story.

[1328] After the story is finished, the server stores the user's reaction data and the generated story in a database. This allows the server to utilize this data the next time the story is generated, thereby providing a more engaging story.

[1329] This invention dynamically changes the content according to the user's reactions as they read the story, providing an individually optimized reading experience. As a specific example, a story may be generated based on a template of "a 17-year-old boy living in the city hears an old folktale from his grandmother in the countryside," and if the user is not excited by the displayed content, a scene in which it is revealed that the grandmother is a witch may be added.

[1330] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1331] Step 1:

[1332] The server stores story templates in a database. This includes templates such as "A 17-year-old boy living in the city hears an old story from his grandmother in the countryside." This template data is stored in a database (e.g., MySQL) using an INSERT statement. The server also performs initial setup of the generative AI model (e.g., the generative AI). Specifically, it sets the API key and prepares the initial prompt. The input data is the story template and the configuration data for the generative AI model, and the output is the registration of the template in the database and the initialization of the generative AI model.

[1333] Step 2:

[1334] The user operates the device to select the first pattern for the story. A list of templates is displayed through the device's UI, and the user selects one from the list. The selected template ID is sent from the device to the server as a request. Specifically, the user clicks on a template and presses the "Send" button. The input data is the user's selection information, and the output is a request sent to the server.

[1335] Step 3:

[1336] Based on the received request, the server passes the selected template ID to the generative AI model as a prompt sentence. Based on this prompt sentence, the generative AI model generates the first part of the story. The generated story text is sent from the server to the device. The input data is the selected template ID, and the output is the generated story text. Specifically, the server sends a request to the generative AI model's API to obtain the generated text. It then returns the text in JSON format to the device as a response.

[1337] Step 4:

[1338] The device displays the generated story to the user. At the same time, sensors installed on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate in real time. These data are periodically sent to the server. The input data is the generated story text and the user's physiological response data, and the output is displaying the story to the user and sending sensor data to the server. Specifically, the device displays the story on the screen, obtains data collected from the camera and heart rate sensor via Bluetooth, and sends it to the server using an HTTP POST request.

[1339] Step 5:

[1340] The server analyzes the received sensor data and evaluates the user's excitement and interest. It uses an analysis algorithm (e.g., a machine learning model) to quantify the sensor data and evaluate the user's emotional state. Based on the analysis results, the server sends new instructions to the generative AI model and adjusts the direction of the story. The input data is the user's sensor data, and the output is the user's emotional evaluation result and new instructions to the generative AI model. Specifically, the server executes the analysis algorithm and sends the analysis results to the generative AI model as a new prompt.

[1341] Step 6:

[1342] After the story is finished, the server saves the user's reaction data and the generated story in a database. By utilizing this data in the next story generation, the aim is to provide a more compelling story. The input data is the user's reaction data and the generated story text, and the output is saving to the database. Specifically, the server executes the SQL statement for saving and stores the data in the database.

[1343] (Application example 1)

[1344] 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."

[1345] Conventional story generation systems struggle to reflect a user's interests and emotional responses in real time, making it difficult to optimize an individual reading experience. Furthermore, there is a lack of technology that can effectively measure a user's physiological responses and dynamically adjust the story content based on them. This makes it difficult to maintain a user's interest and provide an engaging story experience.

[1346] 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.

[1347] In this invention, the server includes a database that stores initial story patterns, a generation unit that dynamically generates a generated story, sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, an analysis unit that analyzes the measured data to evaluate the user's interests and emotions, a control unit that adjusts the direction of the story based on the evaluation results, a storage unit that saves the generated story and analysis data, and a terminal that operates a smartphone to display the story and measure the user's reaction. This enables individually optimized dynamic story generation and customization based on the user's physiological reaction.

[1348] "Story start patterns" are templates of different themes and settings that users can choose from at the start of a story.

[1349] A "database" is an information storage system for storing story patterns, generated stories, and user response data.

[1350] "Generation means" refers to algorithms or software that dynamically generate a story based on the story pattern selected by the user.

[1351] "Sensor" refers to a device that measures physiological data such as a user's facial expression, eye brightness, pulse rate, and sweat rate.

[1352] "Analysis means" refers to algorithms or software that analyze the user's physiological data collected by the sensors and evaluate the user's interests and emotions.

[1353] "Control means" refers to algorithms or software that adjust the direction of the story based on the evaluation results obtained by the analysis means.

[1354] "Memory means" refers to a recording device or storage for saving the generated stories and analyzed data.

[1355] A "terminal" is a device such as a smartphone that a user uses to measure physiological responses while reading a story.

[1356] This invention is a system in which a user selects the initial pattern of a story, a generation AI dynamically generates a story based on that, and measures and analyzes the user's reaction in real time. Specific embodiments are described below.

[1357] System configuration

[1358] The system consists of the following major components:

[1359] 1. Server: This is the central component responsible for story generation, database management, analysis, control, and storage. A Transformer-based generative AI model (e.g., GPT-4) is used to generate stories.

[1360] 2. Device: A device such as a smartphone that the user uses to read the story. The device is equipped with sensors such as a camera and a fingerprint sensor (for measuring pulse) to measure the user's physiological responses.

[1361] 3. User: The individual who actually reads the story, and their reaction data is fed back to the server.

[1362] Program processing overview

[1363] Server Processing

[1364] The server first stores a story template in a database (e.g., MongoDB). This template is used when the user selects the first pattern of the story. When the user operates the device to select a pattern of the story, the information is sent to the server. The server then uses generative AI to dynamically generate a story and sends the text to the device.

[1365] The server also analyzes sensor data (facial expressions, pulse rate, sweat rate, etc.) sent from the device in real time. Based on the analysis results, it sends new instructions to the generation AI and adjusts the direction of the story. The generated story and analysis data are stored in a database for later use.

[1366] Terminal handling

[1367] The device sends the initial story pattern selected by the user to the server and receives the generated story text. While displaying the story, the device captures the user's facial expressions with a camera and measures their pulse with a pulse sensor. These data are sent to the server in real time.

[1368] User Roles

[1369] The user operates the device to select a story pattern. While the story is displayed, the user's natural reactions are measured as sensor data. The user's reaction data is reflected in the customization of the story, providing an individually optimized reading experience.

[1370] Examples of concrete examples and prompts

[1371] For example, if the user selects the "Adventure" pattern, the server generates the following story:

[1372] "The boy sensed the beginning of an adventure and stepped into the unknown..."

[1373] If the user's heart rate increases and their facial expression shows surprise, the following prompt is fed to the generative AI model:

[1374] Q: The user selected "Adventure" as the beginning of the story. The current storyline has lowered the user's excitement level, so a more exciting scene is needed. Add a monster encounter or treasure hunt element.

[1375] A:

[1376] Based on these prompts, the generative AI model adds new adventures and surprises to the story, and adjusts the direction of the story based on its analysis.

[1377] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1378] Step 1:

[1379] The server stores story templates in a database, which are used when a user selects the first pattern of a story. The input data is a prepared story template, which is saved in the database. The output is the saved template data.

[1380] Step 2:

[1381] The user operates the terminal to select the first pattern of the story. The terminal collects the user's selection data and sends it to the server. The input data is the pattern of the story selected by the user, and the output is a request sent to the server.

[1382] Step 3:

[1383] The server generates the initial part of the story using a generative AI model based on the received request. The input data is the story pattern selected by the user, which is input to the generative AI model as a prompt sentence. The output is the initial text of the generated story.

[1384] Step 4:

[1385] The device displays the initial text of the generated story to the user. It uses a built-in camera and biometric sensors to measure the user's facial expressions, pulse rate, sweat rate, and other physiological responses. The input data is the generated story text and the measured physiological data, and the output is the displayed story text and the collected physiological data.

[1386] Step 5:

[1387] The terminal transmits the collected physiological data to the server, where the input data is the measured physiological data and the output is the transmitted data to the server.

[1388] Step 6:

[1389] The server analyzes the received sensor data and evaluates the user's interest and emotions. Using analytical means, it analyzes data such as facial expressions and pulse rate to quantify the user's excitement and interest. The input data is the measurement data, and the output is the evaluation result.

[1390] Step 7:

[1391] Based on the evaluation results, the server sends new instructions to the generative AI model to adjust the direction of the story. For example, if the user's excitement level is evaluated as low, the server instructs the model to add a new episode to the story. In this case, the following prompt sentence is input to the generative AI model:

[1392] Q: The user selected "Adventure" as the opening part of the story. The current story flow has lowered the user's excitement level, so a more exciting scene is needed. Please add a monster encounter or treasure hunt element. A:

[1393] The input data are the evaluation results and instructions for the generative AI model, and the output is the tailored narrative text.

[1394] Step 8:

[1395] The server sends the adjusted story text to the terminal. The input data is the adjusted story text, and the output is the data sent to the terminal.

[1396] Step 9:

[1397] The terminal then displays the newly generated story text back to the user. The input data is the adjusted story text, and the output is the new text of the displayed story.

[1398] Step 10:

[1399] As the user continues to read the story, the device and server repeat the above steps, dynamically adjusting the story based on the user's responses to continuously optimize the reading experience. Finally, the generated story and analysis data are stored on the server and used for the next story generation.

[1400] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1401] The present invention is a system incorporating an emotion engine that recognizes the user's emotions, which dynamically generates stories based on the user's interests and emotions, optimizing the reading experience for each individual.

[1402] System configuration

[1403] The system consists of the following main components:

[1404] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[1405] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses.

[1406] 3. Emotion engine: This engine recognizes the user's emotions, analyzes their state, and reflects them in the story generation.

[1407] 4. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[1408] Initial Setup

[1409] The server first stores the story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generation AI, preparing to generate the story.

[1410] Beginning of story generation

[1411] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into the generation AI to generate the initial section of the story. The generated text is then sent to the device.

[1412] Displaying a story and measuring user responses

[1413] The device displays the generated story to the user, while sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmit this data to the server in real time.

[1414] Emotion Recognition and Analysis

[1415] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generation AI.

[1416] Story Updates

[1417] Once the story direction is determined, the server uses generative AI to generate the next section of the story, for example, by adding new adventures or suspense elements to the story if it determines that the user's excitement level is low.

[1418] End of story and data saving

[1419] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[1420] Specific examples

[1421] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read this story, the device continuously measures the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the user's level of excitement is deemed low, the server instructs the generation AI to develop a new plot development, such as "The grandmother reveals that she was once a witch."

[1422] In this way, our invention can dynamically generate and adjust the story according to the user's emotional state, optimizing the reading experience for each individual. By flexibly changing and updating the direction of the story based on detailed sensor data and the analysis results of the emotion engine, it is possible to provide a consistently engaging reading experience for the user.

[1423] The processing flow will be explained below.

[1424] Step 1:

[1425] The server initially stores some initial story patterns in a database.

[1426] Specific behavior:

[1427] 1. The server loads the story template from the configuration file.

[1428] 2. Insert the loaded template data into the database.

[1429] 3. Set the API key and authentication information for the generated AI and initialize the AI.

[1430] Step 2:

[1431] The user selects one from a list of story templates displayed on the terminal, and the terminal transmits the information to the server.

[1432] Specific behavior:

[1433] 1. The terminal displays a list of story templates to the user.

[1434] 2. The user selects the desired template and presses the Select button.

[1435] 3. The device sends a request including the selected template ID to the server.

[1436] Step 3:

[1437] Based on the received request, the server passes the selected template content to the generation AI to generate the first part of the story, and the generated text is sent to the device.

[1438] Specific behavior:

[1439] 1. The server analyzes the received template ID and retrieves the corresponding template content from the database.

[1440] 2. The acquired template content is input into the generation AI to generate the initial section of the story.

[1441] 3. Send the generated text to the terminal.

[1442] Step 4:

[1443] The device displays the initial section of the story to the user, while sensors begin measuring the user's physiological responses (facial expression, eye brightness, pulse rate, sweat rate).

[1444] Specific behavior:

[1445] 1. The device displays the received story text on the screen.

[1446] 2. The user begins reading the story.

[1447] 3. Sensors on the device measure the user's physiological responses in real time.

[1448] 4. The measured data is periodically sent to the server.

[1449] Step 5:

[1450] The server inputs the received user reaction data into the emotion engine, recognizes and evaluates the user's emotional state, and instructs the generation AI to generate the next section based on the evaluation results.

[1451] Specific behavior:

[1452] 1. The server inputs the received sensor data into the emotion engine.

[1453] 2. The emotion engine analyzes and scores the user's emotional state.

[1454] 3. Determine the direction of the story based on the score.

[1455] 4. The server sends new instructions to the generation AI to generate the next section.

[1456] 5. Send the next generated section to the terminal.

[1457] Step 6:

[1458] The device then displays the next generated section to the user, and the sensors again measure the user's response, repeating this process until the user has finished reading the story.

[1459] Specific behavior:

[1460] 1. Your device will display a new story section on the screen.

[1461] 2. The user reads the story.

[1462] 3. The device's sensors again measure the user's reaction and send it to the server.

[1463] Step 7:

[1464] Once the story is finished, the server stores all user response data and the generated story, and uses this data the next time a story is generated.

[1465] Specific behavior:

[1466] 1. The server generates the ending of the story.

[1467] 2. Upon completion of the story, all response data and the generated story are stored in a database.

[1468] 3. The stored data is used as training data for generative AI and emotion engines.

[1469] Example 2

[1470] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1471] Conventional story generation systems have had difficulty dynamically generating and adjusting a story based on the user's emotions and interests. Furthermore, there has been a lack of technology that can evaluate the user's physiological responses in real time and flexibly change the direction of the story based on those responses. As a result, it has been difficult for users to obtain an individually optimized reading experience.

[1472] 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.

[1473] In this invention, the server includes database means for storing initial story patterns, generation means for dynamically generating generated stories, sensor means for measuring the user's facial expressions, eye brightness, pulse rate, and sweat rate, analysis means for analyzing the measured data to evaluate the user's excitement level and interest, control means for adjusting the direction of the story based on the evaluation results, storage means for saving the generated story and analysis data, display means for displaying the generated story, selection means for the user to select a story template, and generation means for generating story sections using a generative AI model. This enables dynamic story generation according to the user's emotional state and individual optimization of the reading experience based on the generated story.

[1474] A "narrative" refers to a series of stories or texts presented to a user.

[1475] "Pattern" refers to the basic structure or template of a story.

[1476] A "database" refers to a system or repository for storing data such as initial story patterns.

[1477] "Generative means" refers to means for dynamically creating narrative sections or stories using generative AI models.

[1478] "Sensor" refers to a device used to measure a user's facial expressions and physiological responses.

[1479] "Analysis means" refers to a means for analyzing sensor data to assess the user's excitement level and interest.

[1480] "Control measures" refer to means for adjusting the direction of the story based on the analysis results.

[1481] "Storage means" refers to means for storing generated stories and user response data.

[1482] "Display means" refers to a means for visually presenting the generated story to the user.

[1483] "Selection means" refers to the interface or mechanism by which a user selects a story template.

[1484] "Generative AI Model" refers to the artificial intelligence model used to generate a section of a story.

[1485] The present invention is a system that utilizes an emotion engine that recognizes the user's emotions to dynamically generate stories based on the user's interests and emotions, providing an individually optimized reading experience.

[1486] System configuration

[1487] The system consists of the following main components:

[1488] 1. Server: The central component responsible for story generation, database management, analysis, control, and storage.

[1489] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses.

[1490] 3. Emotion engine: This engine recognizes the user's emotions, analyzes their state, and reflects them in the story generation.

[1491] 4. User: An individual who actually reads the story, and their reaction data is fed back into the system.

[1492] Initial Setup

[1493] The server first stores story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generative AI model (e.g., a general generative AI model) to prepare for story generation.

[1494] Story Generation

[1495] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into a generative AI model to generate the initial section of the story. The generated text is then sent to the device.

[1496] Displaying a story and measuring user responses

[1497] The device displays the generated story to the user, while sensors on the device measure the user's physiological responses, such as facial expressions, eye brightness, pulse rate, and sweat rate, and transmits this data to a server in real time.

[1498] Emotion Recognition and Analysis

[1499] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generative AI model.

[1500] Story Updates

[1501] Once the story direction is determined, the server uses a generative AI model to generate the next section of the story, for example, by adding new adventures or suspense elements to the story if it determines that the user's excitement level is low.

[1502] End of story and data saving

[1503] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[1504] Specific examples

[1505] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read the story, the device continuously monitors the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the server determines that the user's level of excitement is low, it instructs the generative AI model to develop a new plot, such as "The grandmother reveals that she was once a witch."

[1506] In this way, the present invention can dynamically generate and adjust the story according to the user's emotional state, thereby optimizing the reading experience for each individual. By flexibly changing and updating the direction of the story based on detailed sensor data and the analysis results of the emotion engine, the present invention provides a constantly engaging reading experience for the user.

[1507] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1508] Step 1:

[1509] Initial Setup

[1510] Input: story template, generative AI model

[1511] The server stores templates in a database containing initial patterns of stories, and this information is used by the user when selecting a story.

[1512] The server configures and initializes the generative AI model, including parameter setting and initialization processing for the generative model.

[1513] Output: Templates stored in a database, an initialized generative AI model

[1514] Step 2:

[1515] Beginning of story generation

[1516] Input: User-selected story template

[1517] The user operates the terminal to select a story template.

[1518] The terminal transmits the selected template information to the server.

[1519] The server inputs prompts into the generative AI model based on the received template information to generate the initial section of the story, for example, "A 17-year-old boy living in the city hears an old folktale from his grandmother in the countryside."

[1520] Output: The initial section of the generated story

[1521] Step 3:

[1522] Displaying a story and measuring user responses

[1523] Input: The initial section of the generated story

[1524] The device displays the generated story to the user, who then reads the story on the screen.

[1525] At the same time, sensors installed in the device measure the user's facial expressions, eye brightness, pulse rate, sweat rate, etc. in real time, collecting physiological response data.

[1526] Output: User's physiological response data (facial expression, pulse rate, amount of sweat, etc.)

[1527] Step 4:

[1528] Emotion Recognition and Analysis

[1529] Input: User's physiological response data

[1530] The server inputs the received sensor data into the emotion engine.

[1531] The emotion engine analyzes the user's physiological response data to evaluate the user's level of excitement and interest. For example, if the user's pulse rate increases or their eyes sparkle above a certain level, it will evaluate the user's level of excitement as high.

[1532] Output: Evaluation results of excitement and interest

[1533] Step 5:

[1534] Determining and updating the story direction

[1535] Input: Excitement and interest evaluation results

[1536] The server decides the direction of the story based on the evaluation results obtained from the emotion engine. For example, if the excitement level is low, it adds new adventures or suspense elements.

[1537] Based on the evaluation results, the server re-enters the prompt into the generative AI model, generating a new section, such as "The old woman reveals that she was once a witch."

[1538] Output: Updated narrative section

[1539] Step 6:

[1540] Narrative display and data feedback

[1541] Input: Updated story section

[1542] The device displays the updated story to the user, who then proceeds to read the next section of the story.

[1543] The server then repeats the process of collecting and evaluating new physiological response data from the user.

[1544] Output: Continuously updated narrative, additional physiological response data

[1545] Step 7:

[1546] End of story and data saving

[1547] Input: All generated story sections, all physiological response data of the user

[1548] Once the story is finished, the server stores all user reaction data and the generated story.

[1549] The saved data will be used the next time a story is generated and will be used as learning data to make the generation process more suitable.

[1550] Output: Stored story and user response data

[1551] (Application example 2)

[1552] 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."

[1553] Current reading experiences are static, with the story content set once and not changing based on the user's reactions. This makes it difficult to provide a personalized reading experience that reflects the user's interests and emotions. Furthermore, no system effectively utilizes user emotional data to dynamically adjust the direction of the story. As a result, users tend to lose interest while reading, which leads to issues with the quality of the reading experience.

[1554] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a database that stores initial story patterns, a generation means that dynamically generates a generated story, sensors that measure the user's facial expression, eye brightness, pulse rate, and sweat rate, an analysis means that analyzes the measured data and evaluates the user's emotions, a control means that adjusts the direction of the story based on the evaluation results, a storage means that saves the generated story and analysis data, a generative AI model that dynamically changes the content of the story depending on the user's state, and an input means for a prompt sentence that generates a new section of the story based on the user's emotions. This enables dynamic story generation according to the user's emotional state, making it possible to provide an individually optimized reading experience.

[1555] The "initial story pattern" is initial setting information including the opening part and basic structure of the story, and is a template that can be selected by the user.

[1556] "Generation means" refers to algorithms or software that dynamically generate a story from input information.

[1557] A "sensor" is a device for measuring a user's physiological responses (facial expression, eye brightness, pulse rate, amount of sweat, etc.).

[1558] "Analysis means" refers to methods and software for assessing the user's state of emotions and interests based on data obtained from sensors.

[1559] "Control means" refers to algorithms or programs that adjust the direction of the story based on the evaluation results of the analysis means.

[1560] "Storage means" refers to a system including a storage device and software for storing the generated story and user response data.

[1561] A "generative AI model" is an artificial intelligence model that takes a user's emotional state as input and generates new sections of a story based on it.

[1562] "Means for inputting prompt sentences" refers to the interface and method for inputting specific instructions to a generative AI model.

[1563] In order to implement this invention, it is necessary to build a system in which a server, terminal, sensor, generative AI model, and prompt sentence input means work in cooperation with each other.

[1564] System configuration

[1565] The system consists of the following main components:

[1566] 1. Server: This is the central component responsible for story generation, database management, analysis, control, and storage. It uses the generative AI model and a means of inputting prompts to generate the next section of the story.

[1567] 2. Terminal: A device through which the user reads the story, equipped with sensors to measure the user's physiological responses. Specific examples include smartphones and smart glasses.

[1568] 3. Sensor: A device that measures the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmits this data to a server in real time.

[1569] 4. Generative AI model: An artificial intelligence model that analyzes the user's emotional state and generates new sections of the story based on the results.

[1570] 5. Prompt sentence input means: An interface for inputting specific instructions to the generative AI model.

[1571] Initial Setup

[1572] The server first stores the story templates in a database. This step prepares the database for when the user selects the first story pattern. It also configures and initializes the generation AI, preparing to generate the story.

[1573] Beginning of story generation

[1574] The user operates the device to select the first pattern of the story. Once the selection is complete, the device sends the information to the server. The server inputs the received template information into a generative AI model to generate the initial section of the story. The generated text is then sent to the device.

[1575] Displaying a story and measuring user responses

[1576] The device displays the generated story to the user, while sensors on the device measure the user's facial expressions, eye brightness, pulse rate, and sweat rate, and transmit this data to the server in real time.

[1577] Emotion Recognition and Analysis

[1578] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine works in conjunction with the analysis means to analyze the user's level of excitement and interest. Based on the results of this evaluation, it determines the direction of the story and issues instructions to the generative AI model.

[1579] Story Updates

[1580] Once the story direction is determined, the server uses a generative AI model to generate the next section of the story, for example, designing it to add new adventures or suspense elements if it determines that the user's excitement level is low.

[1581] End of story and data saving

[1582] Once the story is finished, the server stores all user response data and the generated story, so that it can use this data the next time a story is generated.

[1583] Specific examples

[1584] For example, if a user selects the template "A 17-year-old boy living in the city hears an old folktale from his country grandmother," the server generates the following opening: "The boy visits his country grandmother's house during summer vacation." As the user begins to read the story, the device continuously monitors the user's facial expressions and pulse rate. The sensor data is sent to the server in real time, and an emotion engine analyzes it to assess the user's level of excitement and interest. If the server determines that the user's level of excitement is low, it instructs the generative AI model to develop a new plot, such as "The grandmother reveals that she was once a witch."

[1585] Example prompts to input to the generative AI model:

[1586] "We've determined that users are bored, so add an element of surprise to your story."

[1587] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1588] Step 1:

[1589] Initial Setup

[1590] The server prepares a database to store the initial story patterns, and configures and initializes the generative AI model and the prompt sentence input method. At this stage, the server saves the available story templates in the database.

[1591] Input: Story template information

[1592] Output: Initialized generative AI model and database

[1593] Specific operation: The server stores the story template in a database and initializes the parameters of the generative AI model.

[1594] Step 2:

[1595] Choosing the first pattern of the story

[1596] The user selects the first pattern of the story through the terminal, and once the selection is complete, the terminal sends the information to the server.

[1597] Input: User selection of story patterns

[1598] Output: Sends the selection information to the server

[1599] Specific operation: The user operates the device screen to select a story template from the list.

[1600] Step 3:

[1601] Generating the initial section of the story

[1602] The server inputs the received pattern information into a generative AI model to generate the initial section of the story, and the generated text is sent to the device.

[1603] Input: Selected story pattern information

[1604] Output: The initial section of the generated story

[1605] Specific operation: The generative AI model generates an initial section based on the selected template and sends it to the terminal.

[1606] Step 4:

[1607] Displaying a story and measuring user responses

[1608] The device displays the generated story to the user, while sensors on the device measure the user's facial expression, eye brightness, pulse rate, and sweat rate, and transmit this data to a server in real time.

[1609] Input: The initial section of the generated story and the user's physiological response data

[1610] Output: Sending sensor data to the server

[1611] Specific operation: The device displays the story text to the user, and the built-in sensors begin measuring the user's reactions.

[1612] Step 5:

[1613] Emotion Recognition and Analysis

[1614] The server inputs the received sensor data into the emotion engine, which recognizes and evaluates the user's emotional state. The emotion engine analyzes the user's excitement level and interest.

[1615] Input: User's physiological response data

[1616] Output: User's emotional state evaluation result

[1617] Specific operation: The emotion engine analyzes the received data and evaluates the user's emotions in real time.

[1618] Step 6:

[1619] Adjusting the direction of the story

[1620] The server inputs prompt sentences into the generative AI model to determine the direction of the story based on the evaluation results.

[1621] Input: User's emotional state assessment results

[1622] Output: Instructions and prompts that generate the following sections:

[1623] Specific operation: The server instructs the generative AI model, "It has been determined that the user is bored, so please add an element of surprise to the story."

[1624] Step 7:

[1625] Story Updates and Display

[1626] The server uses the generative AI model to generate the next section of the story, which is then sent back to the device and displayed to the user.

[1627] Input: A prompt sentence entered into the generative AI model

[1628] Output: Updated narrative section

[1629] How it works: The generative AI model generates a new section, and the server sends it to the device for display.

[1630] Step 8:

[1631] End of story and data saving

[1632] When the story is finished, the server stores all user reaction data and the generated story data in a storage means, so that this data can be used the next time a story is generated.

[1633] Input: All user response data and generated story data

[1634] Output: Saved data

[1635] Specific operation: The server saves the data in a memory device and uses it as a reference for future story generation.

[1636] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1637] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1638] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1639] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1640] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1641] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1642] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1643] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1644] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1645] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1646] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1647] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1648] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1649] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1650] 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.

[1651] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1652] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1653] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1654] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1655] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1656] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1657] The following is further disclosed regarding the above embodiment.

[1658] (Claim 1)

[1659] A database that stores the initial patterns of the story,

[1660] a generating means for dynamically generating the generated story;

[1661] Sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate;

[1662] an analysis means for analyzing the measured data to evaluate the user's interests and emotions;

[1663] a control measure to adjust the direction of the story based on the evaluation results;

[1664] a storage means for storing the generated story and analysis data;

[1665] system.

[1666] (Claim 2)

[1667] The present invention further includes a selection means for allowing a user to select the initial pattern of the story.

[1668] 10. The system of claim 1.

[1669] (Claim 3)

[1670] The system further includes a stopping means for stopping the generation of the story when the user's response exceeds a certain standard.

[1671] 10. The system of claim 1.

[1672] "Example 1"

[1673] (Claim 1)

[1674] A database that stores the initial patterns of the story,

[1675] a generating means for dynamically generating the generated story;

[1676] Sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate;

[1677] an analysis means for analyzing the measured data to evaluate the user's interests and emotions;

[1678] a control measure to adjust the direction of the story based on the evaluation results;

[1679] A means for passing the initial pattern of the story to a generation AI model based on the user's selection information and presenting the newly generated story;

[1680] a storage means for storing the generated story and analysis data;

[1681] system.

[1682] (Claim 2)

[1683] The present invention further includes a selection means for allowing a user to select the initial pattern of the story.

[1684] 10. The system of claim 1.

[1685] (Claim 3)

[1686] The system further includes a stopping means for stopping the generation of the story when the user's response exceeds a certain standard.

[1687] 10. The system of claim 1.

[1688] "Application Example 1"

[1689] (Claim 1)

[1690] A database that stores the initial patterns of the story,

[1691] a generating means for dynamically generating the generated story;

[1692] Sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate;

[1693] an analysis means for analyzing the measured data to evaluate the user's interests and emotions;

[1694] a control measure to adjust the direction of the story based on the evaluation results;

[1695] a storage means for storing the generated story and analysis data;

[1696] It is equipped with a terminal that displays the story and measures user reactions by operating a smartphone.

[1697] system.

[1698] (Claim 2)

[1699] The present invention further includes a selection means for allowing a user to select the initial pattern of the story.

[1700] 10. The system of claim 1.

[1701] (Claim 3)

[1702] The system further includes a stopping means for stopping the generation of the story when the user's response exceeds a certain standard.

[1703] 10. The system of claim 1.

[1704] "Example 2: Combining Emotion Engines"

[1705] (Claim 1)

[1706] A database that stores the initial patterns of the story,

[1707] a generating means for dynamically generating the generated story;

[1708] Sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate;

[1709] an analysis means for analyzing the measured data to evaluate the user's excitement level and interest;

[1710] a control measure to adjust the direction of the story based on the evaluation results;

[1711] a storage means for storing the generated story and analysis data;

[1712] a display means for displaying the generated story;

[1713] a selection means for allowing a user to select a story template;

[1714] Includes a generator that uses a generative AI model to generate sections of a story

[1715] system.

[1716] (Claim 2)

[1717] The system further includes a transmitting means for transmitting the user's reaction data to the server in real time.

[1718] 10. The system of claim 1.

[1719] (Claim 3)

[1720] The system further includes a stopping means for stopping the generation of the story when the user's response exceeds a certain standard.

[1721] 10. The system of claim 1.

[1722] "Application example 2 when combining emotion engines"

[1723] (Claim 1)

[1724] A database that stores the initial patterns of the story,

[1725] a generating means for dynamically generating the generated story;

[1726] Sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate;

[1727] analysis means for analyzing the measured data and evaluating the user's emotions;

[1728] a control measure to adjust the direction of the story based on the evaluation results;

[1729] a storage means for storing the generated story and analysis data;

[1730] A generative AI model that dynamically changes the content of the story depending on the user's state,

[1731] A prompt sentence input method that generates a new section of the story based on the user's emotions.

[1732] A system including:

[1733] (Claim 2)

[1734] The present invention further includes a selection means for allowing a user to select the initial pattern of the story.

[1735] 10. The system of claim 1.

[1736] (Claim 3)

[1737] The system further includes a stopping means for stopping the generation of the story when the user's response exceeds a certain standard.

[1738] 10. The system of claim 1. [Explanation of symbols]

[1739] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A database that stores the initial patterns of the story, a generating means for dynamically generating the generated story; Sensors that measure the user's facial expressions, eye brightness, pulse rate, and sweat rate; an analysis means for analyzing the measured data to evaluate the user's interests and emotions; a control measure to adjust the direction of the story based on the evaluation results; a storage means for storing the generated story and analysis data; system.

2. The present invention further includes a selection means for allowing a user to select the initial pattern of the story. The system of claim 1 .

3. The system further includes a stopping means for stopping the generation of the story when the user's response exceeds a certain standard. The system of claim 1 .

Images