system

Abstract

We provide the system. [Solution] A means of collecting information about users' interests and location, A means of generating an original disaster prevention story based on the collected information, A means of providing the generated story along with audio and video, A means of branching the story based on user choices and realizing an interactive experience, A means to track the user's learning progress and reflect it in the next content generation, A system that includes this.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional disaster prevention education often focuses on general information provision and has difficulty sustaining the interest of children who are the recipients. In addition, with uniform content, it is difficult to fully convey specific disaster prevention measures according to individual regional characteristics, and there is a problem that the effect of linking to actual actions is limited. Furthermore, there is a need to provide a mechanism that enables the learned content to be remembered in the long term and leads to actions.

Means for Solving the Problems

[0005] This invention solves the above problems by providing a system that collects information on users' interests and local areas and generates personalized disaster prevention stories based on that data. The generated stories are provided as audio and video content, enabling an interactive experience that includes branching based on user choices. This allows children to continuously maintain their interest while learning specific disaster prevention actions that take local characteristics into account. Furthermore, by tracking the user's learning progress and feeding this information back into the next content generation, it further enhances individual learning motivation and promotes long-term knowledge retention.

[0006] "User information" refers to data collected from users regarding their interests, personality, and regional characteristics.

[0007] An "original story" is a personalized narrative generated based on collected user information.

[0008] A "disaster prevention story" is a narrative intended for learning purposes, including knowledge and actions related to disaster prevention.

[0009] "Audio content" refers to audio data that can be played back using speech synthesis to tell a story.

[0010] "Video content" refers to image or video data that visually represents scenes from a story.

[0011] An "interactive experience" is an experience in which the story branches according to the user's choices, enabling participatory learning.

[0012] "Tracking learning progress" means recording the user's learning activities and understanding their progress.

[0013] "Data-driven optimization" is a technology that analyzes collected data to optimize the content provided in future deliveries.

[0014] Augmented reality technology is a technology that overlays digital information onto the real world. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine.

Embodiments for Carrying Out the Invention

[0016] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system that generates and provides disaster prevention education content that takes into account the user's interests and regional characteristics. The user uses a terminal and selects their interests and preferred story genres through an interview screen, which initiates the generation of a personalized disaster prevention story. The terminal transmits the user's interest information and automatically acquired regional characteristics data to the server.

[0037] Based on this information, the server utilizes a generative AI model to generate original disaster prevention stories. These stories incorporate specific countermeasures and preventative measures for particular disasters based on the collected data, and are optimized for individual users. The generated story text is converted into audio content using speech synthesis technology, and an image generation AI creates related visual content. Augmented reality technology is used as needed to enhance the visual experience of the story.

[0038] This system incorporates interactive elements into the story delivered via the device, where the narrative branches based on the user's choices. The mechanism, which changes disaster prevention actions according to the user's choices, aims to reinforce learning. As the user progresses through the story, their learning progress and choice data are recorded by the device and sent to the server. This data is used to optimize the next content provided, generating content that continuously engages the user.

[0039] For example, if a user selects the themes "earthquake" and "adventure," the server will generate an adventure story in which the user cooperates with family and friends to evacuate during an earthquake. In this story, the user can make choices such as "take refuge in the basement" or "search for emergency supplies," and the story dynamically changes based on the user's choices, with audio and video playing in real time based on the results. Users can learn disaster preparedness actions based on a real-life scenario through experience, improving their ability to respond in real life.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user uses the device to answer questions about their interests and preferred story genres. The device collects the user's input information and obtains regional characteristics data using the device's location services. This information is temporarily stored in a local database.

[0043] Step 2:

[0044] The device creates a request to send the collected interest and location information to the server and transmits it over the network. This request also includes the user ID and selected themes.

[0045] Step 3:

[0046] The server analyzes the received user information and activates a generation AI model. The AI ​​model generates an original disaster prevention story based on the user's interests and regional characteristics. This is where the story outline and event sequence are constructed.

[0047] Step 4:

[0048] The server generates audio content from the generated story using text-to-speech technology. Simultaneously, an image generation AI creates visual content of scenes and characters within the story. The generated content is stored in a content database.

[0049] Step 5:

[0050] The server creates interaction points within the story to provide to the user and builds branching logic based on the user's choices. This creates a mechanism where the story dynamically changes according to the user's choices.

[0051] Step 6:

[0052] The server sends a package containing the generated audio and video content and interaction data to the terminal.

[0053] Step 7:

[0054] The device decodes the content received from the server and plays it for the user. The device plays audio and video simultaneously, and the user can participate in the story through interactive choices.

[0055] Step 8:

[0056] As the user progresses through the story, the device records the user's choices and collects learning progress data. The device periodically uploads this data to the server, which analyzes and uses it to generate future content.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] Disaster prevention education is an important field in modern society, but the content generally provided is uniform and does not adequately reflect the interests of individual users or the characteristics of their region. This makes it difficult for users to effectively learn disaster prevention knowledge. Furthermore, general teaching materials lack interactivity, making it difficult to maintain interest.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for collecting data on users' interests and local area, means for generating novel disaster prevention narratives using a generative AI model based on the collected data, and means for presenting the generated narratives together with speech synthesis and image generation technologies. This makes it possible to provide personalized disaster prevention education content tailored to the user's interests and local characteristics.

[0062] "Users" refers to individuals who experience and learn from disaster prevention education content.

[0063] "Interests" refers to the specific interests and preferences of the user.

[0064] "Local data" refers to information about the user's place of residence and the unique characteristics of that region.

[0065] A "generative AI model" refers to artificial intelligence technology used to create new disaster prevention narratives based on collected data.

[0066] "Disaster prevention stories" refer to educational materials in the form of stories that are provided as disaster prevention education content.

[0067] "Speech synthesis" refers to a technology that uses text data to reproduce its content as speech.

[0068] "Image generation technology" refers to the technology of creating visual images based on the content of a story.

[0069] This invention relates to a system for providing personalized disaster prevention education content. Specific embodiments for carrying out the invention are described below.

[0070] Users select their interests and preferred story genres through an interview screen using a device such as a computer or mobile device. The device collects this information, along with automatically acquired data on regional characteristics, and sends it to the server.

[0071] The server uses a generative AI model to generate an original disaster prevention story based on the information it receives. This generative AI model uses the collected data as prompts to construct optimal content tailored to the user's interests and local characteristics. The generated story text is converted into audio content using speech synthesis technology, and related visual content is created using image generation technology. Augmented reality technology is applied as needed to make the user experience more immersive.

[0072] The system includes interactive elements and presents a story to the user through their device. The user progresses through the story based on the choices displayed. The story branches according to the user's choices, and audio and video are played in real time based on the results.

[0073] For example, if a user selects the themes "earthquake" and "adventure," the server will generate an adventure story about "what to do when an earthquake occurs." This story will include options such as "take refuge in the basement" and "gather emergency supplies," allowing the user to learn disaster preparedness actions based on a real-world scenario. An example of a prompt would be, "Generate an earthquake adventure story that the user will find interesting."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] To reflect their interests, users select genres of stories and disaster prevention-related themes on the device's interview screen. Input includes disaster types such as "earthquake" or "flood," and genre selections such as "adventure" or "drama." The device collects this user input as data and prepares it for further processing.

[0077] Step 2:

[0078] The device automatically acquires regional data such as the user's current location and residential characteristics, along with collected user interest data. Specifically, it uses GPS data and registered address information. This information is integrated to form a dataset for transmission to the server. The output is a complete dataset of user interests and location.

[0079] Step 3:

[0080] The server receives the dataset sent from the terminal and runs a generative AI model based on prompts. This generates personalized disaster prevention stories. Data processing involves extracting the narrative elements best suited to the user's interests and regional characteristics, and combining them to construct a unique story. The output is the constructed story text.

[0081] Step 4:

[0082] The server inputs the generated story text into speech synthesis technology to produce audio content. It also uses image generation technology to create visual content related to the story. Specifically, the text data is converted into audio clips, and visual scenes are drawn. The output includes both audio and image data.

[0083] Step 5:

[0084] The device presents the user with audio and visual content received from the server. The user interacts with the story based on choices presented as the story progresses, determining the direction of the narrative. Specifically, the user makes choices such as "climb the mountain" or "descend the valley." This provides the user with a dynamic and interactive experience.

[0085] Step 6:

[0086] The device records user selections and analyzes the user's learning patterns and progress based on them. The analyzed data is sent to a server and used to optimize future disaster prevention content. Specifically, the selection data is analyzed to enable the provision of more detailed disaster prevention measures and new scenarios. The output includes the user's selection history and learning progress data.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Disaster prevention education content is generally provided in a standardized format, lacking personalization based on individual user interests and regional characteristics. As a result, it is difficult to capture users' attention, leading to problems with insufficient learning and retention of disaster prevention actions. Furthermore, existing educational methods have limited visual experiences, which may not be effective in improving response capabilities during actual disasters.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for collecting information on the user's interests and region, means for generating an original disaster prevention story based on the collected information, and means for providing the generated story along with audio and video on a three-dimensional display device. This generates personalized disaster prevention education content tailored to the user's interests and regional characteristics, enabling learning through an interactive and visually impactful experience, and allowing for the understanding and acquisition of disaster prevention actions.

[0092] A "user" is an individual who receives disaster prevention education content using an information processing system.

[0093] "Interest" refers to the user's interest in the content and themes of the disaster prevention stories they select.

[0094] "Regional information" refers to data about the characteristics of the user's location and disaster risks.

[0095] A "three-dimensional display device" is a device that presents visual content to the user in a three-dimensional format.

[0096] "Branching the story based on choices" means changing the progression of the narrative based on user input.

[0097] An "interactive experience" is an experience in which the user actively participates and the response changes based on their actions.

[0098] "Learning progress" refers to the level of disaster prevention knowledge that a user has acquired through the system.

[0099] "Information generation" is the process of creating new content based on user choices and interests.

[0100] Augmented reality technology is a technique that overlays virtual visual information onto the real world.

[0101] "Data-driven optimization" is a method of optimizing content by analyzing data collected from users.

[0102] The embodiment of the invention involves constructing a specific system for users to receive personalized disaster prevention education content. The terminal collects data from the user regarding their interests and regional characteristics. This is achieved by allowing the user to select the genre and theme of stories they are interested in through a user interface. Furthermore, the terminal can automatically acquire the user's regional information using GPS sensors, etc.

[0103] The server receives user interest information and regional information transmitted from the terminal and uses a generative AI model to generate original stories based on disaster prevention themes. These stories incorporate specific countermeasures and preventative measures for particular disasters and are personalized according to the characteristics of each user. The generated stories are converted from text to speech using a speech synthesis engine. In addition, related visual content is generated by an image generation engine and provided on a 3D display device.

[0104] By using augmented reality technology, the visual experience of the story is enhanced, allowing users to learn interactive disaster preparedness actions based on real-world scenarios. When users make choices within the story, their selections are recorded as data and reflected in future content generation. This data-driven optimization enables more effective learning.

[0105] For example, if a user selects the themes "typhoon" and "mystery solving," the server generates an adventure story in which the user explores evacuation procedures while preparing for an approaching typhoon. In this scenario, the user is presented with options such as gathering evacuation equipment and checking the safety of their evacuation route, and the story dynamically changes depending on their choices. Furthermore, an immersive experience is achieved through the combination of audio guidance and visual content.

[0106] Examples of prompt messages include, "Generate a story about preparing for a typhoon where the user solves puzzles to ensure safety."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The device collects interest information from the user. The user selects the genre of stories they are interested in through the provided interface. This input information is then compiled into request data for the server.

[0110] Step 2:

[0111] The device automatically acquires the user's current location using a GPS sensor and collects characteristic data about the region. This information is sent to a server for region-specific disaster risk analysis.

[0112] Step 3:

[0113] The server integrates user interest information and local information sent from the terminal. This information is then input into a generative AI model as prompts to generate an original disaster prevention story tailored to the user's interests.

[0114] Step 4:

[0115] The server outputs the generated story as text data and converts it into audio data using a speech synthesis engine. This audio data is then provided to the user as auditory content.

[0116] Step 5:

[0117] The server uses an image generation engine to create visual content based on the generated story. Visual effects are added to this content, and it is then sent to the terminal in a format suitable for a 3D display device.

[0118] Step 6:

[0119] The device provides visual and audio data to the user through a three-dimensional display device. The user gains an interactive and immersive disaster prevention experience through augmented reality technology.

[0120] Step 7:

[0121] The device records the story's progression based on the user's choices and sends this selection data to the server. The server uses this data to optimize the next story to the user's interests.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention is a disaster prevention education system that combines an emotion engine that recognizes user emotions. This system has the function of generating personalized disaster prevention stories based on information about the user's interests and local area, and providing them as audio and video content. Furthermore, by recognizing the user's emotions in real time and dynamically adjusting the story and delivery method based on the results, it realizes a more personalized learning experience.

[0124] Users use their devices to select their interests and preferred story genres and input information. The device sends this information, along with regional characteristics information obtained based on location data, to a server. The server uses a generative AI model to generate disaster prevention stories based on this information. The generated stories are enhanced with audio and image content that aligns with their content, and visual effects are further enhanced using augmented reality technology.

[0125] Meanwhile, the emotion engine analyzes the user's voice and facial expression data to recognize their emotional state in real time. Based on this emotional data, the server adjusts the story's progression and presentation, ensuring the optimal experience for the user. For example, if the system detects that the user is experiencing fear or anxiety, it will adjust the story to alleviate the tension.

[0126] The story branches based on user choices and includes interactive elements. Throughout the user experience, the device records selection data and emotional changes, and the server analyzes this data to improve future content creation. This ensures that learning content is always tailored to the user's interests, fostering a continuous desire to learn.

[0127] For example, if a user selects the genres "flood" and "drama," the server will provide an evacuation story for when a flood occurs. If the emotion engine recognizes the user's surprise or confusion, the server will soften the tone of the narration and adjust the pace of the story to make the user feel more at ease, enabling more effective disaster preparedness learning.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The user uses their device to select themes and story genres that interest them. The device collects regional data based on the information entered and the device's location. The collected information is stored locally and prepared to be sent to the server.

[0131] Step 2:

[0132] The device sends the collected user information to the server. The data sent includes user ID, interests, story genre, and location information. The server receives this information and records it in its database.

[0133] Step 3:

[0134] Based on the received user information, the server uses a generation AI model to generate customized disaster prevention stories. A story outline is created, and scenarios tailored to the user's interests and local area are designed.

[0135] Step 4:

[0136] The server converts the generated stories into audio and video content using text-to-speech technology and image generation AI. The generated content is stored in a story management database, and visual effects may be added using augmented reality technology.

[0137] Step 5:

[0138] The server sets up the interactive content and determines how the story branches based on user choices. This interaction element includes user choices and their corresponding story paths.

[0139] Step 6:

[0140] The emotion engine analyzes the user's voice and facial expression data to recognize their emotional state. This data is sent from the device to the server and used to adjust the story.

[0141] Step 7:

[0142] The server adjusts the story content and delivery method in real time based on sentiment data. If negative emotions are detected, it adjusts the tone of the story and takes measures to make the user experience more comfortable.

[0143] Step 8:

[0144] The device plays pre-arranged story content received from the server. The user accesses the story, learns as they progress through the narrative by making choices.

[0145] Step 9:

[0146] As users experience the story, their devices record their choices and emotional changes. This recorded data is uploaded to a server and used to generate future content, providing a more personalized learning experience.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0149] Traditional disaster prevention education systems have a problem in that they cannot provide content that is tailored to the individual interests and emotions of users. Because education is based on general scenarios and templates, it often fails to provide an appropriate learning experience for users. In addition, because content is not adjusted in real time to take into account changes in emotions, there are challenges such as decreased motivation to learn and hindering effective learning.

[0150] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0151] In this invention, the server includes means for collecting information about the user's interests and location, means for generating disaster prevention stories using a generative AI model, and means for analyzing the user's voice and facial expression data, recognizing their emotional state, and adjusting the story accordingly. This makes it possible to provide a personalized disaster prevention learning experience that is tailored to the user's individual interests and emotions.

[0152] A "user" is an individual person who uses the system to experience a disaster prevention story.

[0153] "Interest and geographical information" refers to data that users provide to the system, relating to their preferences and interests, as well as data indicating their geographical characteristics.

[0154] A "generative AI model" is a machine learning-based algorithm that generates new content based on data received from users.

[0155] A "disaster prevention story" is an educational narrative that simulates actions and countermeasures to take during a disaster.

[0156] "Audio and video content" refers to multimedia materials used to convey the content of disaster prevention stories visually and aurally.

[0157] "User voice and facial expression data" refers to data that records the tone of a user's voice and facial movements, and is used to determine the person's emotional state.

[0158] "Recognizing emotional states and adjusting the story" refers to the process of analyzing user emotional data and modifying the story's content and presentation to elicit appropriate emotional responses.

[0159] An "interactive experience" is a learning activity in which the story changes based on the choices and actions taken by the user, resulting in a participatory and immersive experience.

[0160] Augmented reality technology is a technique that uses computer technology to overlay digital information onto the real world environment, thereby enhancing visual effects.

[0161] This invention is a system that provides users with a personalized learning experience by generating disaster prevention stories based on their interests and local information, and dynamically adjusting the content by recognizing their emotions. The configuration and operation of this system will be described in detail below.

[0162] First, the user enters their interests and preferred genres from their device. During this process, templates for disaster prevention events and stories that appeal to the user are selected and sent to the server along with their location information. Based on this information, the server uses a generative AI model to generate a disaster prevention story. The generated story is then accompanied by audio and video content and provided to the user.

[0163] The server uses a generation AI model to create a new disaster prevention story based on a prompt. An example of a prompt is input to the AI ​​model such as, "Generate a story that includes safe evacuation methods during a flood." The generated story is then accompanied by appropriate voice narration and visually engaging images.

[0164] Furthermore, the device uses an emotion engine to acquire the user's voice and facial expression data in real time. This data is used to analyze the user's emotional state, and the results are sent to the server. The server uses this emotional information to adjust the story's progression in real time. For example, if the user expresses anxiety during the story, the narration tone is softened, and the flow of the story is adjusted to be more nuanced.

[0165] Users can participate in the story through interactive elements. The device records the history of choices and emotional changes, and the server analyzes this data to improve future content creation. This feedback loop enables the delivery of disaster prevention education content optimized for the user.

[0166] Specific examples of prompts could include phrases like, "Based on your interests and local information, please suggest the next disaster prevention scenario," or "Adjust the story progression when the user expresses surprise." This allows for a more personalized learning experience for the user.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] Users use their devices to select disaster prevention events and story genres that interest them, and input this information along with local information. This input causes the device to send data about the user's interests and location to a server. The collected data is then organized and used as foundational data for story generation on the server side. Specifically, the device saves the input information in real time, encrypts it, and securely transmits it to the server.

[0170] Step 2:

[0171] The server generates disaster prevention stories using a generative AI model based on the received user data. The input user information is used to generate prompt statements set in the generative AI model. These prompts may take the form of, for example, "Please generate a story that includes an evacuation plan in preparation for an earthquake." The generative AI model processes these prompt statements and outputs a disaster prevention story that reflects the user's individual interests.

[0172] Step 3:

[0173] The generated story is enhanced with audio and video content by the server. The story content is enriched in a multimedia format that includes visual and auditory elements, such as recorded narration and animation. The server processes this and sends it to the device as rich content.

[0174] Step 4:

[0175] The device displays received content to the user using augmented reality technology. This enhances the visual effects of the story and provides an immersive experience. Users can, for example, access parts of the story while searching for an evacuation route or participate in simulations. The device utilizes AR tools to overlay virtual objects onto a view of the real world.

[0176] Step 5:

[0177] The user's voice and facial expression data are acquired by the device and sent to the emotion engine in real time. The emotion engine analyzes this data to identify the user's emotional state. Specifically, it uses voice tone analysis and facial expression recognition algorithms to make judgments. The results of this analysis are sent from the device to the server.

[0178] Step 6:

[0179] The server dynamically adjusts the story based on feedback from the emotion engine. For example, if the user shows anxiety or tension, the server changes the tone of the story and softens the narration to reassure the user. This optimizes the user experience and provides more personalized content.

[0180] Step 7:

[0181] The device records user selection data and emotional changes and sends them to the server. This data is analyzed on the server and used to generate future content. This continuously provides a learning experience tailored to the user and improves the system's personalization capabilities. The server uses this analysis to improve settings and prompts in future story generation.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] Traditional disaster prevention education systems often provide standardized content, which is problematic because they cannot offer learning experiences tailored to the individual interests and emotional states of each user. Furthermore, virtual stores face the challenge of not being able to promote purchasing behavior because it is difficult to suggest products based on customer emotions and preferences.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for acquiring information about the user's interests and location, means for generating a personalized disaster prevention story based on the acquired information, and means for recognizing the user's emotional state in real time and dynamically adjusting the experience content. This enables personalized learning and product recommendations that are tailored to the user's individual interests and emotional state.

[0187] "Means of obtaining information on user interests and location" refers to data collection devices and related programs for understanding users' interests and geographical characteristics.

[0188] "Means for generating personalized disaster prevention stories" refers to a generation program that creates disaster prevention narrative content tailored to individual users based on collected user information.

[0189] "Means of providing audio and visual content" refers to means of visually presenting the generated story via an audio output device and a display.

[0190] "Means of providing interactive experiences" refers to a system or program that provides an interactive experience in which the story and content change based on the user's individual choices.

[0191] "Means of recognizing the user's emotional state in real time and dynamically adjusting the experience" refers to algorithms that analyze emotional indicators such as the user's facial expressions and voiceprints, and adjust the development of the content and story being provided accordingly.

[0192] "Means of presenting relevant information and making customized product suggestions" refers to a program that provides relevant product information and individually tailored purchase suggestions based on the user's interests and sentiment data.

[0193] To implement this invention, a server capable of communicating with a terminal equipped with emotion recognition capabilities is required. First, the user inputs information about their interests and location via the terminal, and this information is collected. This information is transmitted from the terminal to the server, which uses a generative AI model to generate a personalized disaster prevention story based on this information. The generated story is provided to the user terminal as audio and visual content.

[0194] Users receive this content using mobile devices such as smart glasses. Audio and visual information is presented via augmented reality technology, and interactive choices are offered. As the user progresses through the story, their emotional state is analyzed in real time based on audio and facial data collected by the camera and microphone. This analysis utilizes Azure® Emotion API, among others. Emotional data is sent to a server, and the story content and progression are continuously and dynamically adjusted to provide the user with the optimal experience.

[0195] For example, when a user wears smart glasses and experiences an interactive story for disaster preparedness education, if the user experiences anxiety based on emotion recognition, feedback is provided such as the narration becoming gentler or the content being changed to something more reassuring. Also, in a virtual store shopping experience, if the user's interest or curiosity is detected, detailed product information and personalized suggestions are displayed.

[0196] An example of a prompt message could be a request sent to the AI ​​model such as, "Look at what the user is currently looking forward to, determine whether their emotion is interest or question, and provide appropriate guidance or suggestions." This invention allows users to enjoy a more personalized and memorable learning and purchasing experience.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server collects information about the user's interests and location from their device.

[0200] The system receives user-generated information about their interests and location from their device. This information is provided as text and location data.

[0201] As part of data processing, the input information is formatted and prepared for storage in the database.

[0202] The output generates structured user profile information.

[0203] Step 2:

[0204] The server uses an AI model to generate personalized disaster prevention stories based on collected user information.

[0205] The system receives user profile information as input.

[0206] As a data processing step, a generative AI model algorithmically constructs stories tailored to the user's interests and regional characteristics. Specific story content is then output using prompts from the generative AI.

[0207] The output generates story data that can be used as audio and visual content.

[0208] Step 3:

[0209] The device provides the generated story to the user as audio and visual content.

[0210] The input is story data sent from the server.

[0211] As part of the data processing, the story data is converted into a format suitable for the user and then passed to the speech synthesis software and display.

[0212] The output presents audio and visual information in a format that the user can see and hear.

[0213] Step 4:

[0214] The device uses emotion recognition to analyze the user's emotions in real time and sends the data to the server.

[0215] The system acquires user facial expression data and voice data from the camera and microphone as input.

[0216] For data processing, we will use the Azure Emotion API to analyze emotional states.

[0217] The output is the user's sentiment data, which is sent to the server.

[0218] Step 5:

[0219] The server dynamically adjusts the story content and presentation method based on the emotional data it receives.

[0220] The system receives user sentiment data as input.

[0221] As part of the data processing, emotional data and generative AI models are reused to adjust the story progression and narration tone.

[0222] As output, the adjusted story data is sent to the device to improve the user experience.

[0223] Step 6:

[0224] The updated device story is presented again, offering users interactive options.

[0225] The input is the adjusted story data received from the server.

[0226] As a data processing step, interactive choices are presented to the user, and the selection results are used to determine the next story branch.

[0227] The final output will be a story updated based on the user's choices.

[0228] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0229] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0230] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0231] [Second Embodiment]

[0232] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0233] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0234] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0235] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0236] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0237] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0238] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0239] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0240] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0241] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0242] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0243] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0244] This invention is a system that generates and provides disaster prevention education content that takes into account the user's interests and regional characteristics. The user uses a terminal and selects their interests and preferred story genres through an interview screen, which initiates the generation of a personalized disaster prevention story. The terminal transmits the user's interest information and automatically acquired regional characteristics data to the server.

[0245] Based on this information, the server utilizes a generative AI model to generate original disaster prevention stories. These stories incorporate specific countermeasures and preventative measures for particular disasters based on the collected data, and are optimized for individual users. The generated story text is converted into audio content using speech synthesis technology, and an image generation AI creates related visual content. Augmented reality technology is used as needed to enhance the visual experience of the story.

[0246] This system incorporates interactive elements into the story delivered via the device, where the narrative branches based on the user's choices. The mechanism, which changes disaster prevention actions according to the user's choices, aims to reinforce learning. As the user progresses through the story, their learning progress and choice data are recorded by the device and sent to the server. This data is used to optimize the next content provided, generating content that continuously engages the user.

[0247] For example, if a user selects the themes "earthquake" and "adventure," the server will generate an adventure story in which the user cooperates with family and friends to evacuate during an earthquake. In this story, the user can make choices such as "take refuge in the basement" or "search for emergency supplies," and the story dynamically changes based on the user's choices, with audio and video playing in real time based on the results. Users can learn disaster preparedness actions based on a real-life scenario through experience, improving their ability to respond in real life.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] The user uses the device to answer questions about their interests and preferred story genres. The device collects the user's input information and obtains regional characteristics data using the device's location services. This information is temporarily stored in a local database.

[0251] Step 2:

[0252] The device creates a request to send the collected interest and location information to the server and transmits it over the network. This request also includes the user ID and selected themes.

[0253] Step 3:

[0254] The server analyzes the received user information and activates a generation AI model. The AI ​​model generates an original disaster prevention story based on the user's interests and regional characteristics. This is where the story outline and event sequence are constructed.

[0255] Step 4:

[0256] The server generates audio content from the generated story using text-to-speech technology. Simultaneously, an image generation AI creates visual content of scenes and characters within the story. The generated content is stored in a content database.

[0257] Step 5:

[0258] The server creates interaction points within the story to provide to the user and builds branching logic based on the user's choices. This creates a mechanism where the story dynamically changes according to the user's choices.

[0259] Step 6:

[0260] The server sends a package containing the generated audio and video content and interaction data to the terminal.

[0261] Step 7:

[0262] The device decodes the content received from the server and plays it for the user. The device plays audio and video simultaneously, and the user can participate in the story through interactive choices.

[0263] Step 8:

[0264] As the user progresses through the story, the device records the user's choices and collects learning progress data. The device periodically uploads this data to the server, which analyzes and uses it to generate future content.

[0265] (Example 1)

[0266] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0267] Disaster prevention education is an important field in modern society, but the content generally provided is uniform and does not adequately reflect the interests of individual users or the characteristics of their region. This makes it difficult for users to effectively learn disaster prevention knowledge. Furthermore, general teaching materials lack interactivity, making it difficult to maintain interest.

[0268] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0269] In this invention, the server includes means for collecting data on users' interests and local area, means for generating novel disaster prevention narratives using a generative AI model based on the collected data, and means for presenting the generated narratives together with speech synthesis and image generation technologies. This makes it possible to provide personalized disaster prevention education content tailored to the user's interests and local characteristics.

[0270] "Users" refers to individuals who experience and learn from disaster prevention education content.

[0271] "Interests" refers to the specific interests and preferences of the user.

[0272] "Local data" refers to information about the user's place of residence and the unique characteristics of that region.

[0273] A "generative AI model" refers to artificial intelligence technology used to create new disaster prevention narratives based on collected data.

[0274] "Disaster prevention stories" refer to educational materials in the form of stories that are provided as disaster prevention education content.

[0275] "Speech synthesis" refers to a technology that uses text data to reproduce its content as speech.

[0276] "Image generation technology" refers to the technology of creating visual images based on the content of a story.

[0277] This invention relates to a system for providing personalized disaster prevention education content. Specific embodiments for carrying out the invention are described below.

[0278] Users select their interests and preferred story genres through an interview screen using a device such as a computer or mobile device. The device collects this information, along with automatically acquired data on regional characteristics, and sends it to the server.

[0279] The server uses a generative AI model to generate an original disaster prevention story based on the information it receives. This generative AI model uses the collected data as prompts to construct optimal content tailored to the user's interests and local characteristics. The generated story text is converted into audio content using speech synthesis technology, and related visual content is created using image generation technology. Augmented reality technology is applied as needed to make the user experience more immersive.

[0280] The system includes interactive elements and presents a story to the user through a terminal. The user advances the story based on the displayed options. The story branches according to the user's choices, and audio and video are played in real time based on the results.

[0281] As a specific example, when the user selects themes such as "earthquake" and "adventure", the server generates an adventure story about "what to do when an earthquake occurs". In this story, options such as "take shelter in the basement" and "collect emergency supplies" are provided, and the user can learn disaster prevention actions along the actual scenario. An example of a prompt sentence is "Please generate an adventure story about earthquakes that the user is interested in".

[0282] The flow of the specific process in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] To reflect their own interests, the user selects a genre of interesting stories or a disaster prevention-related theme on the interview screen of the terminal. The inputs include disaster types such as "earthquake" and "flood", and genre selections such as "adventure" and "drama". The terminal collects these user inputs as data and prepares them for the next process.

[0285] Step 2:

[0286] The terminal automatically acquires regional data such as the user's current location and residential characteristics together with the collected user interest data. Specifically, GPS data and registered address information are used. These pieces of information are integrated to form a dataset for transmission to the server. As an output, a complete dataset regarding the user's interests and region is obtained.

[0287] Step 3:

[0288] The server receives the dataset sent from the terminal and runs a generative AI model based on prompts. This generates personalized disaster prevention stories. Data processing involves extracting the narrative elements best suited to the user's interests and regional characteristics, and combining them to construct a unique story. The output is the constructed story text.

[0289] Step 4:

[0290] The server inputs the generated story text into speech synthesis technology to produce audio content. It also uses image generation technology to create visual content related to the story. Specifically, the text data is converted into audio clips, and visual scenes are drawn. The output includes both audio and image data.

[0291] Step 5:

[0292] The device presents the user with audio and visual content received from the server. The user interacts with the story based on choices presented as the story progresses, determining the direction of the narrative. Specifically, the user makes choices such as "climb the mountain" or "descend the valley." This provides the user with a dynamic and interactive experience.

[0293] Step 6:

[0294] The device records user selections and analyzes the user's learning patterns and progress based on them. The analyzed data is sent to a server and used to optimize future disaster prevention content. Specifically, the selection data is analyzed to enable the provision of more detailed disaster prevention measures and new scenarios. The output includes the user's selection history and learning progress data.

[0295] (Application Example 1)

[0296] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0297] Disaster prevention education content is generally provided in a standardized format, lacking personalization based on individual user interests and regional characteristics. As a result, it is difficult to capture users' attention, leading to problems with insufficient learning and retention of disaster prevention actions. Furthermore, existing educational methods have limited visual experiences, which may not be effective in improving response capabilities during actual disasters.

[0298] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0299] In this invention, the server includes means for collecting information on the user's interests and region, means for generating an original disaster prevention story based on the collected information, and means for providing the generated story along with audio and video on a three-dimensional display device. This generates personalized disaster prevention education content tailored to the user's interests and regional characteristics, enabling learning through an interactive and visually impactful experience, and allowing for the understanding and acquisition of disaster prevention actions.

[0300] A "user" is an individual who receives disaster prevention education content using an information processing system.

[0301] "Interest" refers to the user's interest in the content and themes of the disaster prevention stories they select.

[0302] "Regional information" refers to data about the characteristics of the user's location and disaster risks.

[0303] A "three-dimensional display device" is a device that presents visual content to the user in a three-dimensional format.

[0304] "Branching the story based on choices" means changing the progression of the narrative based on user input.

[0305] "An 'interactive experience' is an experience where the user actively participates and the reaction changes by operation."

[0306] "The 'learning progress' is the situation of the disaster prevention knowledge acquired by the user through the same system."

[0307] " 'Information generation' is a process of creating new content according to the user's selection and interests."

[0308] " 'Augmented reality technology' is a technology that overlays virtual visual information on the real environment."

[0309] " 'Data-driven optimization' is a method of optimizing content by analyzing data collected from users."

[0310] The form for implementing the invention is to construct a specific system for the user to receive disaster prevention education content in a personalized form. The terminal collects information about the user's interests and data about regional characteristics. This is realized by the user selecting the genre or theme of the story they are interested in via the user interface. Also, using a GPS sensor or the like, the terminal can automatically obtain the user's regional information.

[0311] The server receives the user's interest information and information about the region transmitted from the terminal, and utilizes a generation AI model to generate an original story based on a disaster prevention theme. This story incorporates specific countermeasures and preventive measures for specific disasters, and is personalized according to the characteristics of individual users. The generated story is converted from text to voice using a voice synthesis engine. Also, related visual content is generated by an image generation engine and provided on a three-dimensional display device.

[0312] By using augmented reality technology, the visual experience of the story is enhanced, allowing users to learn interactive disaster preparedness actions based on real-world scenarios. When users make choices within the story, their selections are recorded as data and reflected in future content generation. This data-driven optimization enables more effective learning.

[0313] For example, if a user selects the themes "typhoon" and "mystery solving," the server generates an adventure story in which the user explores evacuation procedures while preparing for an approaching typhoon. In this scenario, the user is presented with options such as gathering evacuation equipment and checking the safety of their evacuation route, and the story dynamically changes depending on their choices. Furthermore, an immersive experience is achieved through the combination of audio guidance and visual content.

[0314] Examples of prompt messages include, "Generate a story about preparing for a typhoon where the user solves puzzles to ensure safety."

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The device collects interest information from the user. The user selects the genre of stories they are interested in through the provided interface. This input information is then compiled into request data for the server.

[0318] Step 2:

[0319] The device automatically acquires the user's current location using a GPS sensor and collects characteristic data about the region. This information is sent to a server for region-specific disaster risk analysis.

[0320] Step 3:

[0321] The server integrates user interest information and local information sent from the terminal. This information is then input into a generative AI model as prompts to generate an original disaster prevention story tailored to the user's interests.

[0322] Step 4:

[0323] The server outputs the generated story as text data and converts it into audio data using a speech synthesis engine. This audio data is then provided to the user as auditory content.

[0324] Step 5:

[0325] The server uses an image generation engine to create visual content based on the generated story. Visual effects are added to this content, and it is then sent to the terminal in a format suitable for a 3D display device.

[0326] Step 6:

[0327] The device provides visual and audio data to the user through a three-dimensional display device. The user gains an interactive and immersive disaster prevention experience through augmented reality technology.

[0328] Step 7:

[0329] The device records the story's progression based on the user's choices and sends this selection data to the server. The server uses this data to optimize the next story to the user's interests.

[0330] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0331] This invention is a disaster prevention education system that combines an emotion engine that recognizes user emotions. This system has the function of generating personalized disaster prevention stories based on information about the user's interests and local area, and providing them as audio and video content. Furthermore, by recognizing the user's emotions in real time and dynamically adjusting the story and delivery method based on the results, it realizes a more personalized learning experience.

[0332] Users use their devices to select their interests and preferred story genres and input information. The device sends this information, along with regional characteristics information obtained based on location data, to a server. The server uses a generative AI model to generate disaster prevention stories based on this information. The generated stories are enhanced with audio and image content that aligns with their content, and visual effects are further enhanced using augmented reality technology.

[0333] Meanwhile, the emotion engine analyzes the user's voice and facial expression data to recognize their emotional state in real time. Based on this emotional data, the server adjusts the story's progression and presentation, ensuring the optimal experience for the user. For example, if the system detects that the user is experiencing fear or anxiety, it will adjust the story to alleviate the tension.

[0334] The story branches based on user choices and includes interactive elements. Throughout the user experience, the device records selection data and emotional changes, and the server analyzes this data to improve future content creation. This ensures that learning content is always tailored to the user's interests, fostering a continuous desire to learn.

[0335] For example, if a user selects the genres "flood" and "drama," the server will provide an evacuation story for when a flood occurs. If the emotion engine recognizes the user's surprise or confusion, the server will soften the tone of the narration and adjust the pace of the story to make the user feel more at ease, enabling more effective disaster preparedness learning.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] The user uses their device to select themes and story genres that interest them. The device collects regional data based on the information entered and the device's location. The collected information is stored locally and prepared to be sent to the server.

[0339] Step 2:

[0340] The device sends the collected user information to the server. The data sent includes user ID, interests, story genre, and location information. The server receives this information and records it in its database.

[0341] Step 3:

[0342] Based on the received user information, the server uses a generation AI model to generate customized disaster prevention stories. A story outline is created, and scenarios tailored to the user's interests and local area are designed.

[0343] Step 4:

[0344] The server converts the generated stories into audio and video content using text-to-speech technology and image generation AI. The generated content is stored in a story management database, and visual effects may be added using augmented reality technology.

[0345] Step 5:

[0346] The server sets up the interactive content and determines how the story branches based on user choices. This interaction element includes user choices and their corresponding story paths.

[0347] Step 6:

[0348] The emotion engine analyzes the user's voice and facial expression data to recognize their emotional state. This data is sent from the device to the server and used to adjust the story.

[0349] Step 7:

[0350] The server adjusts the story content and delivery method in real time based on sentiment data. If negative emotions are detected, it adjusts the tone of the story and takes measures to make the user experience more comfortable.

[0351] Step 8:

[0352] The device plays pre-arranged story content received from the server. The user accesses the story, learns as they progress through the narrative by making choices.

[0353] Step 9:

[0354] As users experience the story, their devices record their choices and emotional changes. This recorded data is uploaded to a server and used to generate future content, providing a more personalized learning experience.

[0355] (Example 2)

[0356] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0357] Traditional disaster prevention education systems have a problem in that they cannot provide content that is tailored to the individual interests and emotions of users. Because education is based on general scenarios and templates, it often fails to provide an appropriate learning experience for users. In addition, because content is not adjusted in real time to take into account changes in emotions, there are challenges such as decreased motivation to learn and hindering effective learning.

[0358] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0359] In this invention, the server includes means for collecting information about the user's interests and location, means for generating disaster prevention stories using a generative AI model, and means for analyzing the user's voice and facial expression data, recognizing their emotional state, and adjusting the story accordingly. This makes it possible to provide a personalized disaster prevention learning experience that is tailored to the user's individual interests and emotions.

[0360] A "user" is an individual person who uses the system to experience a disaster prevention story.

[0361] "Interest and geographical information" refers to data that users provide to the system, relating to their preferences and interests, as well as data indicating their geographical characteristics.

[0362] A "generative AI model" is a machine learning-based algorithm that generates new content based on data received from users.

[0363] A "disaster prevention story" is an educational narrative that simulates actions and countermeasures to take during a disaster.

[0364] "Audio and video content" refers to multimedia materials used to convey the content of disaster prevention stories visually and aurally.

[0365] "User voice and facial expression data" refers to data that records the tone of a user's voice and facial movements, and is used to determine the person's emotional state.

[0366] "Recognizing emotional states and adjusting the story" refers to the process of analyzing user emotional data and modifying the story's content and presentation to elicit appropriate emotional responses.

[0367] An "interactive experience" is a learning activity in which the story changes based on the choices and actions taken by the user, resulting in a participatory and immersive experience.

[0368] Augmented reality technology is a technique that uses computer technology to overlay digital information onto the real world environment, thereby enhancing visual effects.

[0369] This invention is a system that provides users with a personalized learning experience by generating disaster prevention stories based on their interests and local information, and dynamically adjusting the content by recognizing their emotions. The configuration and operation of this system will be described in detail below.

[0370] First, the user enters their interests and preferred genres from their device. During this process, templates for disaster prevention events and stories that appeal to the user are selected and sent to the server along with their location information. Based on this information, the server uses a generative AI model to generate a disaster prevention story. The generated story is then accompanied by audio and video content and provided to the user.

[0371] The server uses a generation AI model to create a new disaster prevention story based on a prompt. An example of a prompt is input to the AI ​​model such as, "Generate a story that includes safe evacuation methods during a flood." The generated story is then accompanied by appropriate voice narration and visually engaging images.

[0372] Furthermore, the device uses an emotion engine to acquire the user's voice and facial expression data in real time. This data is used to analyze the user's emotional state, and the results are sent to the server. The server uses this emotional information to adjust the story's progression in real time. For example, if the user expresses anxiety during the story, the narration tone is softened, and the flow of the story is adjusted to be more nuanced.

[0373] Users can participate in the story through interactive elements. The device records the history of choices and emotional changes, and the server analyzes this data to improve future content creation. This feedback loop enables the delivery of disaster prevention education content optimized for the user.

[0374] Specific examples of prompts could include phrases like, "Based on your interests and local information, please suggest the next disaster prevention scenario," or "Adjust the story progression when the user expresses surprise." This allows for a more personalized learning experience for the user.

[0375] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0376] Step 1:

[0377] Users use their devices to select disaster prevention events and story genres that interest them, and input this information along with local information. This input causes the device to send data about the user's interests and location to a server. The collected data is then organized and used as foundational data for story generation on the server side. Specifically, the device saves the input information in real time, encrypts it, and securely transmits it to the server.

[0378] Step 2:

[0379] The server generates disaster prevention stories using a generative AI model based on the received user data. The input user information is used to generate prompt statements set in the generative AI model. These prompts may take the form of, for example, "Please generate a story that includes an evacuation plan in preparation for an earthquake." The generative AI model processes these prompt statements and outputs a disaster prevention story that reflects the user's individual interests.

[0380] Step 3:

[0381] The generated story is enhanced with audio and video content by the server. The story content is enriched in a multimedia format that includes visual and auditory elements, such as recorded narration and animation. The server processes this and sends it to the device as rich content.

[0382] Step 4:

[0383] The device displays received content to the user using augmented reality technology. This enhances the visual effects of the story and provides an immersive experience. Users can, for example, access parts of the story while searching for an evacuation route or participate in simulations. The device utilizes AR tools to overlay virtual objects onto a view of the real world.

[0384] Step 5:

[0385] The user's voice and facial expression data are acquired by the device and sent to the emotion engine in real time. The emotion engine analyzes this data to identify the user's emotional state. Specifically, it uses voice tone analysis and facial expression recognition algorithms to make judgments. The results of this analysis are sent from the device to the server.

[0386] Step 6:

[0387] The server dynamically adjusts the story based on feedback from the emotion engine. For example, if the user shows anxiety or tension, the server changes the tone of the story and softens the narration to reassure the user. This optimizes the user experience and provides more personalized content.

[0388] Step 7:

[0389] The device records user selection data and emotional changes and sends them to the server. This data is analyzed on the server and used to generate future content. This continuously provides a learning experience tailored to the user and improves the system's personalization capabilities. The server uses this analysis to improve settings and prompts in future story generation.

[0390] (Application Example 2)

[0391] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0392] Traditional disaster prevention education systems often provide standardized content, which is problematic because they cannot offer learning experiences tailored to the individual interests and emotional states of each user. Furthermore, virtual stores face the challenge of not being able to promote purchasing behavior because it is difficult to suggest products based on customer emotions and preferences.

[0393] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0394] In this invention, the server includes means for acquiring information about the user's interests and location, means for generating a personalized disaster prevention story based on the acquired information, and means for recognizing the user's emotional state in real time and dynamically adjusting the experience content. This enables personalized learning and product recommendations that are tailored to the user's individual interests and emotional state.

[0395] "Means of obtaining information on user interests and location" refers to data collection devices and related programs for understanding users' interests and geographical characteristics.

[0396] "Means for generating personalized disaster prevention stories" refers to a generation program that creates disaster prevention narrative content tailored to individual users based on collected user information.

[0397] "Means of providing audio and visual content" refers to means of visually presenting the generated story via an audio output device and a display.

[0398] "Means of providing interactive experiences" refers to a system or program that provides an interactive experience in which the story and content change based on the user's individual choices.

[0399] "Means of recognizing the user's emotional state in real time and dynamically adjusting the experience" refers to algorithms that analyze emotional indicators such as the user's facial expressions and voiceprints, and adjust the development of the content and story being provided accordingly.

[0400] "Means of presenting relevant information and making customized product suggestions" refers to a program that provides relevant product information and individually tailored purchase suggestions based on the user's interests and sentiment data.

[0401] To implement this invention, a server capable of communicating with a terminal equipped with emotion recognition capabilities is required. First, the user inputs information about their interests and location via the terminal, and this information is collected. This information is transmitted from the terminal to the server, which uses a generative AI model to generate a personalized disaster prevention story based on this information. The generated story is provided to the user terminal as audio and visual content.

[0402] Users receive this content using mobile devices such as smart glasses. Audio and visual information is presented via augmented reality technology, and interactive choices are offered. As the user progresses through the story, their emotional state is analyzed in real time based on audio and facial data collected by the camera and microphone. This analysis uses Azure's Emotion API, among others. Emotional data is sent to a server, and the story content and progression are continuously and dynamically adjusted to provide the user with the best possible experience.

[0403] For example, when a user wears smart glasses and experiences an interactive story for disaster preparedness education, if the user experiences anxiety based on emotion recognition, feedback is provided such as the narration becoming gentler or the content being changed to something more reassuring. Also, in a virtual store shopping experience, if the user's interest or curiosity is detected, detailed product information and personalized suggestions are displayed.

[0404] An example of a prompt message could be a request sent to the AI ​​model such as, "Look at what the user is currently looking forward to, determine whether their emotion is interest or question, and provide appropriate guidance or suggestions." This invention allows users to enjoy a more personalized and memorable learning and purchasing experience.

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The server collects information about the user's interests and location from their device.

[0408] The system receives user-generated information about their interests and location from their device. This information is provided as text and location data.

[0409] As part of data processing, the input information is formatted and prepared for storage in the database.

[0410] The output generates structured user profile information.

[0411] Step 2:

[0412] The server uses an AI model to generate personalized disaster prevention stories based on collected user information.

[0413] The system receives user profile information as input.

[0414] As a data processing step, a generative AI model algorithmically constructs stories tailored to the user's interests and regional characteristics. Specific story content is then output using prompts from the generative AI.

[0415] The output generates story data that can be used as audio and visual content.

[0416] Step 3:

[0417] The device provides the generated story to the user as audio and visual content.

[0418] The input is story data sent from the server.

[0419] As part of the data processing, the story data is converted into a format suitable for the user and then passed to the speech synthesis software and display.

[0420] The output presents audio and visual information in a format that the user can see and hear.

[0421] Step 4:

[0422] The device uses emotion recognition to analyze the user's emotions in real time and sends the data to the server.

[0423] The system acquires user facial expression data and voice data from the camera and microphone as input.

[0424] For data processing, we will use the Azure Emotion API to analyze emotional states.

[0425] The output is the user's sentiment data, which is sent to the server.

[0426] Step 5:

[0427] The server dynamically adjusts the story content and presentation method based on the emotional data it receives.

[0428] The system receives user sentiment data as input.

[0429] As part of the data processing, emotional data and generative AI models are reused to adjust the story progression and narration tone.

[0430] As output, the adjusted story data is sent to the device to improve the user experience.

[0431] Step 6:

[0432] The updated device story is presented again, offering users interactive options.

[0433] The input is the adjusted story data received from the server.

[0434] As a data processing step, interactive choices are presented to the user, and the selection results are used to determine the next story branch.

[0435] The final output will be a story updated based on the user's choices.

[0436] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0437] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0438] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0439] [Third Embodiment]

[0440] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0441] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0442] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0443] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0444] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0445] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0446] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0447] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0448] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0449] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0450] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0451] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0452] This invention is a system that generates and provides disaster prevention education content that takes into account the user's interests and regional characteristics. The user uses a terminal and selects their interests and preferred story genres through an interview screen, which initiates the generation of a personalized disaster prevention story. The terminal transmits the user's interest information and automatically acquired regional characteristics data to the server.

[0453] Based on this information, the server utilizes a generative AI model to generate original disaster prevention stories. These stories incorporate specific countermeasures and preventative measures for particular disasters based on the collected data, and are optimized for individual users. The generated story text is converted into audio content using speech synthesis technology, and an image generation AI creates related visual content. Augmented reality technology is used as needed to enhance the visual experience of the story.

[0454] This system incorporates interactive elements into the story delivered via the device, where the narrative branches based on the user's choices. The mechanism, which changes disaster prevention actions according to the user's choices, aims to reinforce learning. As the user progresses through the story, their learning progress and choice data are recorded by the device and sent to the server. This data is used to optimize the next content provided, generating content that continuously engages the user.

[0455] For example, if a user selects the themes "earthquake" and "adventure," the server will generate an adventure story in which the user cooperates with family and friends to evacuate during an earthquake. In this story, the user can make choices such as "take refuge in the basement" or "search for emergency supplies," and the story dynamically changes based on the user's choices, with audio and video playing in real time based on the results. Users can learn disaster preparedness actions based on a real-life scenario through experience, improving their ability to respond in real life.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The user uses the device to answer questions about their interests and preferred story genres. The device collects the user's input information and obtains regional characteristics data using the device's location services. This information is temporarily stored in a local database.

[0459] Step 2:

[0460] The device creates a request to send the collected interest and location information to the server and transmits it over the network. This request also includes the user ID and selected themes.

[0461] Step 3:

[0462] The server analyzes the received user information and activates a generation AI model. The AI ​​model generates an original disaster prevention story based on the user's interests and regional characteristics. This is where the story outline and event sequence are constructed.

[0463] Step 4:

[0464] The server generates audio content from the generated story using text-to-speech technology. Simultaneously, an image generation AI creates visual content of scenes and characters within the story. The generated content is stored in a content database.

[0465] Step 5:

[0466] The server creates interaction points within the story to provide to the user and builds branching logic based on the user's choices. This creates a mechanism where the story dynamically changes according to the user's choices.

[0467] Step 6:

[0468] The server sends a package containing the generated audio and video content and interaction data to the terminal.

[0469] Step 7:

[0470] The device decodes the content received from the server and plays it for the user. The device plays audio and video simultaneously, and the user can participate in the story through interactive choices.

[0471] Step 8:

[0472] As the user progresses through the story, the device records the user's choices and collects learning progress data. The device periodically uploads this data to the server, which analyzes and uses it to generate future content.

[0473] (Example 1)

[0474] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0475] Disaster prevention education is an important field in modern society, but the content generally provided is uniform and does not adequately reflect the interests of individual users or the characteristics of their region. This makes it difficult for users to effectively learn disaster prevention knowledge. Furthermore, general teaching materials lack interactivity, making it difficult to maintain interest.

[0476] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0477] In this invention, the server includes means for collecting data on users' interests and local area, means for generating novel disaster prevention narratives using a generative AI model based on the collected data, and means for presenting the generated narratives together with speech synthesis and image generation technologies. This makes it possible to provide personalized disaster prevention education content tailored to the user's interests and local characteristics.

[0478] "Users" refers to individuals who experience and learn from disaster prevention education content.

[0479] "Interests" refers to the specific interests and preferences of the user.

[0480] "Local data" refers to information about the user's place of residence and the unique characteristics of that region.

[0481] A "generative AI model" refers to artificial intelligence technology used to create new disaster prevention narratives based on collected data.

[0482] "Disaster prevention stories" refer to educational materials in the form of stories that are provided as disaster prevention education content.

[0483] "Speech synthesis" refers to a technology that uses text data to reproduce its content as speech.

[0484] "Image generation technology" refers to the technology of creating visual images based on the content of a story.

[0485] This invention relates to a system for providing personalized disaster prevention education content. Specific embodiments for carrying out the invention are described below.

[0486] Users select their interests and preferred story genres through an interview screen using a device such as a computer or mobile device. The device collects this information, along with automatically acquired data on regional characteristics, and sends it to the server.

[0487] The server uses a generative AI model to generate an original disaster prevention story based on the information it receives. This generative AI model uses the collected data as prompts to construct optimal content tailored to the user's interests and local characteristics. The generated story text is converted into audio content using speech synthesis technology, and related visual content is created using image generation technology. Augmented reality technology is applied as needed to make the user experience more immersive.

[0488] The system includes interactive elements and presents a story to the user through their device. The user progresses through the story based on the choices displayed. The story branches according to the user's choices, and audio and video are played in real time based on the results.

[0489] For example, if a user selects the themes "earthquake" and "adventure," the server will generate an adventure story about "what to do when an earthquake occurs." This story will include options such as "take refuge in the basement" and "gather emergency supplies," allowing the user to learn disaster preparedness actions based on a real-world scenario. An example of a prompt would be, "Generate an earthquake adventure story that the user will find interesting."

[0490] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0491] Step 1:

[0492] To reflect their interests, users select genres of stories and disaster prevention-related themes on the device's interview screen. Input includes disaster types such as "earthquake" or "flood," and genre selections such as "adventure" or "drama." The device collects this user input as data and prepares it for further processing.

[0493] Step 2:

[0494] The device automatically acquires regional data such as the user's current location and residential characteristics, along with collected user interest data. Specifically, it uses GPS data and registered address information. This information is integrated to form a dataset for transmission to the server. The output is a complete dataset of user interests and location.

[0495] Step 3:

[0496] The server receives the dataset sent from the terminal and runs a generative AI model based on prompts. This generates personalized disaster prevention stories. Data processing involves extracting the narrative elements best suited to the user's interests and regional characteristics, and combining them to construct a unique story. The output is the constructed story text.

[0497] Step 4:

[0498] The server inputs the generated story text into speech synthesis technology to produce audio content. It also uses image generation technology to create visual content related to the story. Specifically, the text data is converted into audio clips, and visual scenes are drawn. The output includes both audio and image data.

[0499] Step 5:

[0500] The device presents the user with audio and visual content received from the server. The user interacts with the story based on choices presented as the story progresses, determining the direction of the narrative. Specifically, the user makes choices such as "climb the mountain" or "descend the valley." This provides the user with a dynamic and interactive experience.

[0501] Step 6:

[0502] The device records user selections and analyzes the user's learning patterns and progress based on them. The analyzed data is sent to a server and used to optimize future disaster prevention content. Specifically, the selection data is analyzed to enable the provision of more detailed disaster prevention measures and new scenarios. The output includes the user's selection history and learning progress data.

[0503] (Application Example 1)

[0504] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0505] Disaster prevention education content is generally provided in a standardized format, lacking personalization based on individual user interests and regional characteristics. As a result, it is difficult to capture users' attention, leading to problems with insufficient learning and retention of disaster prevention actions. Furthermore, existing educational methods have limited visual experiences, which may not be effective in improving response capabilities during actual disasters.

[0506] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0507] In this invention, the server includes means for collecting information on the user's interests and region, means for generating an original disaster prevention story based on the collected information, and means for providing the generated story along with audio and video on a three-dimensional display device. This generates personalized disaster prevention education content tailored to the user's interests and regional characteristics, enabling learning through an interactive and visually impactful experience, and allowing for the understanding and acquisition of disaster prevention actions.

[0508] A "user" is an individual who receives disaster prevention education content using an information processing system.

[0509] "Interest" refers to the user's interest in the content and themes of the disaster prevention stories they select.

[0510] "Regional information" refers to data about the characteristics of the user's location and disaster risks.

[0511] A "three-dimensional display device" is a device that presents visual content to the user in a three-dimensional format.

[0512] "Branching the story based on choices" means changing the progression of the narrative based on user input.

[0513] An "interactive experience" is an experience in which the user actively participates and the response changes based on their actions.

[0514] "Learning progress" refers to the level of disaster prevention knowledge that a user has acquired through the system.

[0515] "Information generation" is the process of creating new content based on user choices and interests.

[0516] Augmented reality technology is a technique that overlays virtual visual information onto the real world.

[0517] "Data-driven optimization" is a method of optimizing content by analyzing data collected from users.

[0518] The embodiment of the invention involves constructing a specific system for users to receive personalized disaster prevention education content. The terminal collects data from the user regarding their interests and regional characteristics. This is achieved by allowing the user to select the genre and theme of stories they are interested in through a user interface. Furthermore, the terminal can automatically acquire the user's regional information using GPS sensors, etc.

[0519] The server receives user interest information and regional information transmitted from the terminal and uses a generative AI model to generate original stories based on disaster prevention themes. These stories incorporate specific countermeasures and preventative measures for particular disasters and are personalized according to the characteristics of each user. The generated stories are converted from text to speech using a speech synthesis engine. In addition, related visual content is generated by an image generation engine and provided on a 3D display device.

[0520] By using augmented reality technology, the visual experience of the story is enhanced, allowing users to learn interactive disaster preparedness actions based on real-world scenarios. When users make choices within the story, their selections are recorded as data and reflected in future content generation. This data-driven optimization enables more effective learning.

[0521] For example, if a user selects the themes "typhoon" and "mystery solving," the server generates an adventure story in which the user explores evacuation procedures while preparing for an approaching typhoon. In this scenario, the user is presented with options such as gathering evacuation equipment and checking the safety of their evacuation route, and the story dynamically changes depending on their choices. Furthermore, an immersive experience is achieved through the combination of audio guidance and visual content.

[0522] Examples of prompt messages include, "Generate a story about preparing for a typhoon where the user solves puzzles to ensure safety."

[0523] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0524] Step 1:

[0525] The device collects interest information from the user. The user selects the genre of stories they are interested in through the provided interface. This input information is then compiled into request data for the server.

[0526] Step 2:

[0527] The device automatically acquires the user's current location using a GPS sensor and collects characteristic data about the region. This information is sent to a server for region-specific disaster risk analysis.

[0528] Step 3:

[0529] The server integrates user interest information and local information sent from the terminal. This information is then input into a generative AI model as prompts to generate an original disaster prevention story tailored to the user's interests.

[0530] Step 4:

[0531] The server outputs the generated story as text data and converts it into audio data using a speech synthesis engine. This audio data is then provided to the user as auditory content.

[0532] Step 5:

[0533] The server uses an image generation engine to create visual content based on the generated story. Visual effects are added to this content, and it is then sent to the terminal in a format suitable for a 3D display device.

[0534] Step 6:

[0535] The device provides visual and audio data to the user through a three-dimensional display device. The user gains an interactive and immersive disaster prevention experience through augmented reality technology.

[0536] Step 7:

[0537] The device records the story's progression based on the user's choices and sends this selection data to the server. The server uses this data to optimize the next story to the user's interests.

[0538] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0539] This invention is a disaster prevention education system that combines an emotion engine that recognizes user emotions. This system has the function of generating personalized disaster prevention stories based on information about the user's interests and local area, and providing them as audio and video content. Furthermore, by recognizing the user's emotions in real time and dynamically adjusting the story and delivery method based on the results, it realizes a more personalized learning experience.

[0540] Users use their devices to select their interests and preferred story genres and input information. The device sends this information, along with regional characteristics information obtained based on location data, to a server. The server uses a generative AI model to generate disaster prevention stories based on this information. The generated stories are enhanced with audio and image content that aligns with their content, and visual effects are further enhanced using augmented reality technology.

[0541] Meanwhile, the emotion engine analyzes the user's voice and facial expression data to recognize their emotional state in real time. Based on this emotional data, the server adjusts the story's progression and presentation, ensuring the optimal experience for the user. For example, if the system detects that the user is experiencing fear or anxiety, it will adjust the story to alleviate the tension.

[0542] The story branches based on user choices and includes interactive elements. Throughout the user experience, the device records selection data and emotional changes, and the server analyzes this data to improve future content creation. This ensures that learning content is always tailored to the user's interests, fostering a continuous desire to learn.

[0543] For example, if a user selects the genres "flood" and "drama," the server will provide an evacuation story for when a flood occurs. If the emotion engine recognizes the user's surprise or confusion, the server will soften the tone of the narration and adjust the pace of the story to make the user feel more at ease, enabling more effective disaster preparedness learning.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The user uses their device to select themes and story genres that interest them. The device collects regional data based on the information entered and the device's location. The collected information is stored locally and prepared to be sent to the server.

[0547] Step 2:

[0548] The device sends the collected user information to the server. The data sent includes user ID, interests, story genre, and location information. The server receives this information and records it in its database.

[0549] Step 3:

[0550] Based on the received user information, the server uses a generation AI model to generate customized disaster prevention stories. A story outline is created, and scenarios tailored to the user's interests and local area are designed.

[0551] Step 4:

[0552] The server converts the generated stories into audio and video content using text-to-speech technology and image generation AI. The generated content is stored in a story management database, and visual effects may be added using augmented reality technology.

[0553] Step 5:

[0554] The server sets up the interactive content and determines how the story branches based on user choices. This interaction element includes user choices and their corresponding story paths.

[0555] Step 6:

[0556] The emotion engine analyzes the user's voice and facial expression data to recognize their emotional state. This data is sent from the device to the server and used to adjust the story.

[0557] Step 7:

[0558] The server adjusts the story content and delivery method in real time based on sentiment data. If negative emotions are detected, it adjusts the tone of the story and takes measures to make the user experience more comfortable.

[0559] Step 8:

[0560] The device plays pre-arranged story content received from the server. The user accesses the story, learns as they progress through the narrative by making choices.

[0561] Step 9:

[0562] As users experience the story, their devices record their choices and emotional changes. This recorded data is uploaded to a server and used to generate future content, providing a more personalized learning experience.

[0563] (Example 2)

[0564] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0565] Traditional disaster prevention education systems have a problem in that they cannot provide content that is tailored to the individual interests and emotions of users. Because education is based on general scenarios and templates, it often fails to provide an appropriate learning experience for users. In addition, because content is not adjusted in real time to take into account changes in emotions, there are challenges such as decreased motivation to learn and hindering effective learning.

[0566] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0567] In this invention, the server includes means for collecting information about the user's interests and location, means for generating disaster prevention stories using a generative AI model, and means for analyzing the user's voice and facial expression data, recognizing their emotional state, and adjusting the story accordingly. This makes it possible to provide a personalized disaster prevention learning experience that is tailored to the user's individual interests and emotions.

[0568] A "user" is an individual person who uses the system to experience a disaster prevention story.

[0569] "Interest and geographical information" refers to data that users provide to the system, relating to their preferences and interests, as well as data indicating their geographical characteristics.

[0570] A "generative AI model" is a machine learning-based algorithm that generates new content based on data received from users.

[0571] A "disaster prevention story" is an educational narrative that simulates actions and countermeasures to take during a disaster.

[0572] "Audio and video content" refers to multimedia materials used to convey the content of disaster prevention stories visually and aurally.

[0573] "User voice and facial expression data" refers to data that records the tone of a user's voice and facial movements, and is used to determine the person's emotional state.

[0574] "Recognizing emotional states and adjusting the story" refers to the process of analyzing user emotional data and modifying the story's content and presentation to elicit appropriate emotional responses.

[0575] An "interactive experience" is a learning activity in which the story changes based on the choices and actions taken by the user, resulting in a participatory and immersive experience.

[0576] Augmented reality technology is a technique that uses computer technology to overlay digital information onto the real world environment, thereby enhancing visual effects.

[0577] This invention is a system that provides users with a personalized learning experience by generating disaster prevention stories based on their interests and local information, and dynamically adjusting the content by recognizing their emotions. The configuration and operation of this system will be described in detail below.

[0578] First, the user enters their interests and preferred genres from their device. During this process, templates for disaster prevention events and stories that appeal to the user are selected and sent to the server along with their location information. Based on this information, the server uses a generative AI model to generate a disaster prevention story. The generated story is then accompanied by audio and video content and provided to the user.

[0579] The server uses a generation AI model to create a new disaster prevention story based on a prompt. An example of a prompt is input to the AI ​​model such as, "Generate a story that includes safe evacuation methods during a flood." The generated story is then accompanied by appropriate voice narration and visually engaging images.

[0580] Furthermore, the device uses an emotion engine to acquire the user's voice and facial expression data in real time. This data is used to analyze the user's emotional state, and the results are sent to the server. The server uses this emotional information to adjust the story's progression in real time. For example, if the user expresses anxiety during the story, the narration tone is softened, and the flow of the story is adjusted to be more nuanced.

[0581] Users can participate in the story through interactive elements. The device records the history of choices and emotional changes, and the server analyzes this data to improve future content creation. This feedback loop enables the delivery of disaster prevention education content optimized for the user.

[0582] Specific examples of prompts could include phrases like, "Based on your interests and local information, please suggest the next disaster prevention scenario," or "Adjust the story progression when the user expresses surprise." This allows for a more personalized learning experience for the user.

[0583] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0584] Step 1:

[0585] Users use their devices to select disaster prevention events and story genres that interest them, and input this information along with local information. This input causes the device to send data about the user's interests and location to a server. The collected data is then organized and used as foundational data for story generation on the server side. Specifically, the device saves the input information in real time, encrypts it, and securely transmits it to the server.

[0586] Step 2:

[0587] The server generates disaster prevention stories using a generative AI model based on the received user data. The input user information is used to generate prompt statements set in the generative AI model. These prompts may take the form of, for example, "Please generate a story that includes an evacuation plan in preparation for an earthquake." The generative AI model processes these prompt statements and outputs a disaster prevention story that reflects the user's individual interests.

[0588] Step 3:

[0589] The generated story is enhanced with audio and video content by the server. The story content is enriched in a multimedia format that includes visual and auditory elements, such as recorded narration and animation. The server processes this and sends it to the device as rich content.

[0590] Step 4:

[0591] The device displays received content to the user using augmented reality technology. This enhances the visual effects of the story and provides an immersive experience. Users can, for example, access parts of the story while searching for an evacuation route or participate in simulations. The device utilizes AR tools to overlay virtual objects onto a view of the real world.

[0592] Step 5:

[0593] The user's voice and facial expression data are acquired by the device and sent to the emotion engine in real time. The emotion engine analyzes this data to identify the user's emotional state. Specifically, it uses voice tone analysis and facial expression recognition algorithms to make judgments. The results of this analysis are sent from the device to the server.

[0594] Step 6:

[0595] The server dynamically adjusts the story based on feedback from the emotion engine. For example, if the user shows anxiety or tension, the server changes the tone of the story and softens the narration to reassure the user. This optimizes the user experience and provides more personalized content.

[0596] Step 7:

[0597] The device records user selection data and emotional changes and sends them to the server. This data is analyzed on the server and used to generate future content. This continuously provides a learning experience tailored to the user and improves the system's personalization capabilities. The server uses this analysis to improve settings and prompts in future story generation.

[0598] (Application Example 2)

[0599] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0600] Traditional disaster prevention education systems often provide standardized content, which is problematic because they cannot offer learning experiences tailored to the individual interests and emotional states of each user. Furthermore, virtual stores face the challenge of not being able to promote purchasing behavior because it is difficult to suggest products based on customer emotions and preferences.

[0601] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0602] In this invention, the server includes means for acquiring information about the user's interests and location, means for generating a personalized disaster prevention story based on the acquired information, and means for recognizing the user's emotional state in real time and dynamically adjusting the experience content. This enables personalized learning and product recommendations that are tailored to the user's individual interests and emotional state.

[0603] "Means of obtaining information on user interests and location" refers to data collection devices and related programs for understanding users' interests and geographical characteristics.

[0604] "Means for generating personalized disaster prevention stories" refers to a generation program that creates disaster prevention narrative content tailored to individual users based on collected user information.

[0605] "Means of providing audio and visual content" refers to means of visually presenting the generated story via an audio output device and a display.

[0606] "Means of providing interactive experiences" refers to a system or program that provides an interactive experience in which the story and content change based on the user's individual choices.

[0607] "Means of recognizing the user's emotional state in real time and dynamically adjusting the experience" refers to algorithms that analyze emotional indicators such as the user's facial expressions and voiceprints, and adjust the development of the content and story being provided accordingly.

[0608] "Means of presenting relevant information and making customized product suggestions" refers to a program that provides relevant product information and individually tailored purchase suggestions based on the user's interests and sentiment data.

[0609] To implement this invention, a server capable of communicating with a terminal equipped with emotion recognition capabilities is required. First, the user inputs information about their interests and location via the terminal, and this information is collected. This information is transmitted from the terminal to the server, which uses a generative AI model to generate a personalized disaster prevention story based on this information. The generated story is provided to the user terminal as audio and visual content.

[0610] Users receive this content using mobile devices such as smart glasses. Audio and visual information is presented via augmented reality technology, and interactive choices are offered. As the user progresses through the story, their emotional state is analyzed in real time based on audio and facial data collected by the camera and microphone. This analysis uses Azure's Emotion API, among others. Emotional data is sent to a server, and the story content and progression are continuously and dynamically adjusted to provide the user with the best possible experience.

[0611] For example, when a user wears smart glasses and experiences an interactive story for disaster preparedness education, if the user experiences anxiety based on emotion recognition, feedback is provided such as the narration becoming gentler or the content being changed to something more reassuring. Also, in a virtual store shopping experience, if the user's interest or curiosity is detected, detailed product information and personalized suggestions are displayed.

[0612] An example of a prompt message could be a request sent to the AI ​​model such as, "Look at what the user is currently looking forward to, determine whether their emotion is interest or question, and provide appropriate guidance or suggestions." This invention allows users to enjoy a more personalized and memorable learning and purchasing experience.

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] The server collects information about the user's interests and location from their device.

[0616] The system receives user-generated information about their interests and location from their device. This information is provided as text and location data.

[0617] As part of data processing, the input information is formatted and prepared for storage in the database.

[0618] The output generates structured user profile information.

[0619] Step 2:

[0620] The server uses an AI model to generate personalized disaster prevention stories based on collected user information.

[0621] The system receives user profile information as input.

[0622] As a data processing step, a generative AI model algorithmically constructs stories tailored to the user's interests and regional characteristics. Specific story content is then output using prompts from the generative AI.

[0623] The output generates story data that can be used as audio and visual content.

[0624] Step 3:

[0625] The device provides the generated story to the user as audio and visual content.

[0626] The input is story data sent from the server.

[0627] As part of the data processing, the story data is converted into a format suitable for the user and then passed to the speech synthesis software and display.

[0628] The output presents audio and visual information in a format that the user can see and hear.

[0629] Step 4:

[0630] The device uses emotion recognition to analyze the user's emotions in real time and sends the data to the server.

[0631] The system acquires user facial expression data and voice data from the camera and microphone as input.

[0632] For data processing, we will use the Azure Emotion API to analyze emotional states.

[0633] The output is the user's sentiment data, which is sent to the server.

[0634] Step 5:

[0635] The server dynamically adjusts the story content and presentation method based on the emotional data it receives.

[0636] The system receives user sentiment data as input.

[0637] As part of the data processing, emotional data and generative AI models are reused to adjust the story progression and narration tone.

[0638] As output, the adjusted story data is sent to the device to improve the user experience.

[0639] Step 6:

[0640] The updated device story is presented again, offering users interactive options.

[0641] The input is the adjusted story data received from the server.

[0642] As a data processing step, interactive choices are presented to the user, and the selection results are used to determine the next story branch.

[0643] The final output will be a story updated based on the user's choices.

[0644] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0645] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0646] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0647] [Fourth Embodiment]

[0648] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0649] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0650] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0651] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0652] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0653] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0654] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0655] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0656] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0657] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0658] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0659] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0660] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0661] This invention is a system that generates and provides disaster prevention education content that takes into account the user's interests and regional characteristics. The user uses a terminal and selects their interests and preferred story genres through an interview screen, which initiates the generation of a personalized disaster prevention story. The terminal transmits the user's interest information and automatically acquired regional characteristics data to the server.

[0662] Based on this information, the server utilizes a generative AI model to generate original disaster prevention stories. These stories incorporate specific countermeasures and preventative measures for particular disasters based on the collected data, and are optimized for individual users. The generated story text is converted into audio content using speech synthesis technology, and an image generation AI creates related visual content. Augmented reality technology is used as needed to enhance the visual experience of the story.

[0663] This system incorporates interactive elements into the story delivered via the device, where the narrative branches based on the user's choices. The mechanism, which changes disaster prevention actions according to the user's choices, aims to reinforce learning. As the user progresses through the story, their learning progress and choice data are recorded by the device and sent to the server. This data is used to optimize the next content provided, generating content that continuously engages the user.

[0664] For example, if a user selects the themes "earthquake" and "adventure," the server will generate an adventure story in which the user cooperates with family and friends to evacuate during an earthquake. In this story, the user can make choices such as "take refuge in the basement" or "search for emergency supplies," and the story dynamically changes based on the user's choices, with audio and video playing in real time based on the results. Users can learn disaster preparedness actions based on a real-life scenario through experience, improving their ability to respond in real life.

[0665] The following describes the processing flow.

[0666] Step 1:

[0667] The user uses the device to answer questions about their interests and preferred story genres. The device collects the user's input information and obtains regional characteristics data using the device's location services. This information is temporarily stored in a local database.

[0668] Step 2:

[0669] The device creates a request to send the collected interest and location information to the server and transmits it over the network. This request also includes the user ID and selected themes.

[0670] Step 3:

[0671] The server analyzes the received user information and activates a generation AI model. The AI ​​model generates an original disaster prevention story based on the user's interests and regional characteristics. This is where the story outline and event sequence are constructed.

[0672] Step 4:

[0673] The server generates audio content from the generated story using text-to-speech technology. Simultaneously, an image generation AI creates visual content of scenes and characters within the story. The generated content is stored in a content database.

[0674] Step 5:

[0675] The server creates interaction points within the story to provide to the user and builds branching logic based on the user's choices. This creates a mechanism where the story dynamically changes according to the user's choices.

[0676] Step 6:

[0677] The server sends a package containing the generated audio and video content and interaction data to the terminal.

[0678] Step 7:

[0679] The device decodes the content received from the server and plays it for the user. The device plays audio and video simultaneously, and the user can participate in the story through interactive choices.

[0680] Step 8:

[0681] As the user progresses through the story, the device records the user's choices and collects learning progress data. The device periodically uploads this data to the server, which analyzes and uses it to generate future content.

[0682] (Example 1)

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

[0684] Disaster prevention education is an important field in modern society, but the content generally provided is uniform and does not adequately reflect the interests of individual users or the characteristics of their region. This makes it difficult for users to effectively learn disaster prevention knowledge. Furthermore, general teaching materials lack interactivity, making it difficult to maintain interest.

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

[0686] In this invention, the server includes means for collecting data on users' interests and local area, means for generating novel disaster prevention narratives using a generative AI model based on the collected data, and means for presenting the generated narratives together with speech synthesis and image generation technologies. This makes it possible to provide personalized disaster prevention education content tailored to the user's interests and local characteristics.

[0687] "Users" refers to individuals who experience and learn from disaster prevention education content.

[0688] "Interests" refers to the specific interests and preferences of the user.

[0689] "Local data" refers to information about the user's place of residence and the unique characteristics of that region.

[0690] A "generative AI model" refers to artificial intelligence technology used to create new disaster prevention narratives based on collected data.

[0691] "Disaster prevention stories" refer to educational materials in the form of stories that are provided as disaster prevention education content.

[0692] "Speech synthesis" refers to a technology that uses text data to reproduce its content as speech.

[0693] "Image generation technology" refers to the technology of creating visual images based on the content of a story.

[0694] This invention relates to a system for providing personalized disaster prevention education content. Specific embodiments for carrying out the invention are described below.

[0695] Users select their interests and preferred story genres through an interview screen using a device such as a computer or mobile device. The device collects this information, along with automatically acquired data on regional characteristics, and sends it to the server.

[0696] The server uses a generative AI model to generate an original disaster prevention story based on the information it receives. This generative AI model uses the collected data as prompts to construct optimal content tailored to the user's interests and local characteristics. The generated story text is converted into audio content using speech synthesis technology, and related visual content is created using image generation technology. Augmented reality technology is applied as needed to make the user experience more immersive.

[0697] The system includes interactive elements and presents a story to the user through their device. The user progresses through the story based on the choices displayed. The story branches according to the user's choices, and audio and video are played in real time based on the results.

[0698] For example, if a user selects the themes "earthquake" and "adventure," the server will generate an adventure story about "what to do when an earthquake occurs." This story will include options such as "take refuge in the basement" and "gather emergency supplies," allowing the user to learn disaster preparedness actions based on a real-world scenario. An example of a prompt would be, "Generate an earthquake adventure story that the user will find interesting."

[0699] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0700] Step 1:

[0701] To reflect their interests, users select genres of stories and disaster prevention-related themes on the device's interview screen. Input includes disaster types such as "earthquake" or "flood," and genre selections such as "adventure" or "drama." The device collects this user input as data and prepares it for further processing.

[0702] Step 2:

[0703] The device automatically acquires regional data such as the user's current location and residential characteristics, along with collected user interest data. Specifically, it uses GPS data and registered address information. This information is integrated to form a dataset for transmission to the server. The output is a complete dataset of user interests and location.

[0704] Step 3:

[0705] The server receives the dataset sent from the terminal and runs a generative AI model based on prompts. This generates personalized disaster prevention stories. Data processing involves extracting the narrative elements best suited to the user's interests and regional characteristics, and combining them to construct a unique story. The output is the constructed story text.

[0706] Step 4:

[0707] The server inputs the generated story text into speech synthesis technology to produce audio content. It also uses image generation technology to create visual content related to the story. Specifically, the text data is converted into audio clips, and visual scenes are drawn. The output includes both audio and image data.

[0708] Step 5:

[0709] The device presents the user with audio and visual content received from the server. The user interacts with the story based on choices presented as the story progresses, determining the direction of the narrative. Specifically, the user makes choices such as "climb the mountain" or "descend the valley." This provides the user with a dynamic and interactive experience.

[0710] Step 6:

[0711] The device records user selections and analyzes the user's learning patterns and progress based on them. The analyzed data is sent to a server and used to optimize future disaster prevention content. Specifically, the selection data is analyzed to enable the provision of more detailed disaster prevention measures and new scenarios. The output includes the user's selection history and learning progress data.

[0712] (Application Example 1)

[0713] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0714] Disaster prevention education content is generally provided in a standardized format, lacking personalization based on individual user interests and regional characteristics. As a result, it is difficult to capture users' attention, leading to problems with insufficient learning and retention of disaster prevention actions. Furthermore, existing educational methods have limited visual experiences, which may not be effective in improving response capabilities during actual disasters.

[0715] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0716] In this invention, the server includes means for collecting information on the user's interests and region, means for generating an original disaster prevention story based on the collected information, and means for providing the generated story along with audio and video on a three-dimensional display device. This generates personalized disaster prevention education content tailored to the user's interests and regional characteristics, enabling learning through an interactive and visually impactful experience, and allowing for the understanding and acquisition of disaster prevention actions.

[0717] A "user" is an individual who receives disaster prevention education content using an information processing system.

[0718] "Interest" refers to the user's interest in the content and themes of the disaster prevention stories they select.

[0719] "Regional information" refers to data about the characteristics of the user's location and disaster risks.

[0720] A "three-dimensional display device" is a device that presents visual content to the user in a three-dimensional format.

[0721] "Branching the story based on choices" means changing the progression of the narrative based on user input.

[0722] An "interactive experience" is an experience in which the user actively participates and the response changes based on their actions.

[0723] "Learning progress" refers to the level of disaster prevention knowledge that a user has acquired through the system.

[0724] "Information generation" is the process of creating new content based on user choices and interests.

[0725] Augmented reality technology is a technique that overlays virtual visual information onto the real world.

[0726] "Data-driven optimization" is a method of optimizing content by analyzing data collected from users.

[0727] The embodiment of the invention involves constructing a specific system for users to receive personalized disaster prevention education content. The terminal collects data from the user regarding their interests and regional characteristics. This is achieved by allowing the user to select the genre and theme of stories they are interested in through a user interface. Furthermore, the terminal can automatically acquire the user's regional information using GPS sensors, etc.

[0728] The server receives user interest information and regional information transmitted from the terminal and uses a generative AI model to generate original stories based on disaster prevention themes. These stories incorporate specific countermeasures and preventative measures for particular disasters and are personalized according to the characteristics of each user. The generated stories are converted from text to speech using a speech synthesis engine. In addition, related visual content is generated by an image generation engine and provided on a 3D display device.

[0729] By using augmented reality technology, the visual experience of the story is enhanced, allowing users to learn interactive disaster preparedness actions based on real-world scenarios. When users make choices within the story, their selections are recorded as data and reflected in future content generation. This data-driven optimization enables more effective learning.

[0730] For example, if a user selects the themes "typhoon" and "mystery solving," the server generates an adventure story in which the user explores evacuation procedures while preparing for an approaching typhoon. In this scenario, the user is presented with options such as gathering evacuation equipment and checking the safety of their evacuation route, and the story dynamically changes depending on their choices. Furthermore, an immersive experience is achieved through the combination of audio guidance and visual content.

[0731] Examples of prompt messages include, "Generate a story about preparing for a typhoon where the user solves puzzles to ensure safety."

[0732] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0733] Step 1:

[0734] The device collects interest information from the user. The user selects the genre of stories they are interested in through the provided interface. This input information is then compiled into request data for the server.

[0735] Step 2:

[0736] The device automatically acquires the user's current location using a GPS sensor and collects characteristic data about the region. This information is sent to a server for region-specific disaster risk analysis.

[0737] Step 3:

[0738] The server integrates user interest information and local information sent from the terminal. This information is then input into a generative AI model as prompts to generate an original disaster prevention story tailored to the user's interests.

[0739] Step 4:

[0740] The server outputs the generated story as text data and converts it into audio data using a speech synthesis engine. This audio data is then provided to the user as auditory content.

[0741] Step 5:

[0742] The server uses an image generation engine to create visual content based on the generated story. Visual effects are added to this content, and it is then sent to the terminal in a format suitable for a 3D display device.

[0743] Step 6:

[0744] The device provides visual and audio data to the user through a three-dimensional display device. The user gains an interactive and immersive disaster prevention experience through augmented reality technology.

[0745] Step 7:

[0746] The device records the story's progression based on the user's choices and sends this selection data to the server. The server uses this data to optimize the next story to the user's interests.

[0747] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0748] This invention is a disaster prevention education system that combines an emotion engine that recognizes user emotions. This system has the function of generating personalized disaster prevention stories based on information about the user's interests and local area, and providing them as audio and video content. Furthermore, by recognizing the user's emotions in real time and dynamically adjusting the story and delivery method based on the results, it realizes a more personalized learning experience.

[0749] Users use their devices to select their interests and preferred story genres and input information. The device sends this information, along with regional characteristics information obtained based on location data, to a server. The server uses a generative AI model to generate disaster prevention stories based on this information. The generated stories are enhanced with audio and image content that aligns with their content, and visual effects are further enhanced using augmented reality technology.

[0750] Meanwhile, the emotion engine analyzes the user's voice and facial expression data to recognize their emotional state in real time. Based on this emotional data, the server adjusts the story's progression and presentation, ensuring the optimal experience for the user. For example, if the system detects that the user is experiencing fear or anxiety, it will adjust the story to alleviate the tension.

[0751] The story branches based on user choices and includes interactive elements. Throughout the user experience, the device records selection data and emotional changes, and the server analyzes this data to improve future content creation. This ensures that learning content is always tailored to the user's interests, fostering a continuous desire to learn.

[0752] For example, if a user selects the genres "flood" and "drama," the server will provide an evacuation story for when a flood occurs. If the emotion engine recognizes the user's surprise or confusion, the server will soften the tone of the narration and adjust the pace of the story to make the user feel more at ease, enabling more effective disaster preparedness learning.

[0753] The following describes the processing flow.

[0754] Step 1:

[0755] The user uses their device to select themes and story genres that interest them. The device collects regional data based on the information entered and the device's location. The collected information is stored locally and prepared to be sent to the server.

[0756] Step 2:

[0757] The device sends the collected user information to the server. The data sent includes user ID, interests, story genre, and location information. The server receives this information and records it in its database.

[0758] Step 3:

[0759] Based on the received user information, the server uses a generation AI model to generate customized disaster prevention stories. A story outline is created, and scenarios tailored to the user's interests and local area are designed.

[0760] Step 4:

[0761] The server converts the generated stories into audio and video content using text-to-speech technology and image generation AI. The generated content is stored in a story management database, and visual effects may be added using augmented reality technology.

[0762] Step 5:

[0763] The server sets up the interactive content and determines how the story branches based on user choices. This interaction element includes user choices and their corresponding story paths.

[0764] Step 6:

[0765] The emotion engine analyzes the user's voice and facial expression data to recognize their emotional state. This data is sent from the device to the server and used to adjust the story.

[0766] Step 7:

[0767] The server adjusts the story content and delivery method in real time based on sentiment data. If negative emotions are detected, it adjusts the tone of the story and takes measures to make the user experience more comfortable.

[0768] Step 8:

[0769] The device plays pre-arranged story content received from the server. The user accesses the story, learns as they progress through the narrative by making choices.

[0770] Step 9:

[0771] As users experience the story, their devices record their choices and emotional changes. This recorded data is uploaded to a server and used to generate future content, providing a more personalized learning experience.

[0772] (Example 2)

[0773] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0774] Traditional disaster prevention education systems have a problem in that they cannot provide content that is tailored to the individual interests and emotions of users. Because education is based on general scenarios and templates, it often fails to provide an appropriate learning experience for users. In addition, because content is not adjusted in real time to take into account changes in emotions, there are challenges such as decreased motivation to learn and hindering effective learning.

[0775] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0776] In this invention, the server includes means for collecting information about the user's interests and location, means for generating disaster prevention stories using a generative AI model, and means for analyzing the user's voice and facial expression data, recognizing their emotional state, and adjusting the story accordingly. This makes it possible to provide a personalized disaster prevention learning experience that is tailored to the user's individual interests and emotions.

[0777] A "user" is an individual person who uses the system to experience a disaster prevention story.

[0778] "Interest and geographical information" refers to data that users provide to the system, relating to their preferences and interests, as well as data indicating their geographical characteristics.

[0779] A "generative AI model" is a machine learning-based algorithm that generates new content based on data received from users.

[0780] A "disaster prevention story" is an educational narrative that simulates actions and countermeasures to take during a disaster.

[0781] "Audio and video content" refers to multimedia materials used to convey the content of disaster prevention stories visually and aurally.

[0782] "User voice and facial expression data" refers to data that records the tone of a user's voice and facial movements, and is used to determine the person's emotional state.

[0783] "Recognizing emotional states and adjusting the story" refers to the process of analyzing user emotional data and modifying the story's content and presentation to elicit appropriate emotional responses.

[0784] An "interactive experience" is a learning activity in which the story changes based on the choices and actions taken by the user, resulting in a participatory and immersive experience.

[0785] Augmented reality technology is a technique that uses computer technology to overlay digital information onto the real world environment, thereby enhancing visual effects.

[0786] This invention is a system that provides users with a personalized learning experience by generating disaster prevention stories based on their interests and local information, and dynamically adjusting the content by recognizing their emotions. The configuration and operation of this system will be described in detail below.

[0787] First, the user enters their interests and preferred genres from their device. During this process, templates for disaster prevention events and stories that appeal to the user are selected and sent to the server along with their location information. Based on this information, the server uses a generative AI model to generate a disaster prevention story. The generated story is then accompanied by audio and video content and provided to the user.

[0788] The server uses a generation AI model to create a new disaster prevention story based on a prompt. An example of a prompt is input to the AI ​​model such as, "Generate a story that includes safe evacuation methods during a flood." The generated story is then accompanied by appropriate voice narration and visually engaging images.

[0789] Furthermore, the device uses an emotion engine to acquire the user's voice and facial expression data in real time. This data is used to analyze the user's emotional state, and the results are sent to the server. The server uses this emotional information to adjust the story's progression in real time. For example, if the user expresses anxiety during the story, the narration tone is softened, and the flow of the story is adjusted to be more nuanced.

[0790] Users can participate in the story through interactive elements. The device records the history of choices and emotional changes, and the server analyzes this data to improve future content creation. This feedback loop enables the delivery of disaster prevention education content optimized for the user.

[0791] Specific examples of prompts could include phrases like, "Based on your interests and local information, please suggest the next disaster prevention scenario," or "Adjust the story progression when the user expresses surprise." This allows for a more personalized learning experience for the user.

[0792] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0793] Step 1:

[0794] Users use their devices to select disaster prevention events and story genres that interest them, and input this information along with local information. This input causes the device to send data about the user's interests and location to a server. The collected data is then organized and used as foundational data for story generation on the server side. Specifically, the device saves the input information in real time, encrypts it, and securely transmits it to the server.

[0795] Step 2:

[0796] The server generates disaster prevention stories using a generative AI model based on the received user data. The input user information is used to generate prompt statements set in the generative AI model. These prompts may take the form of, for example, "Please generate a story that includes an evacuation plan in preparation for an earthquake." The generative AI model processes these prompt statements and outputs a disaster prevention story that reflects the user's individual interests.

[0797] Step 3:

[0798] The generated story is enhanced with audio and video content by the server. The story content is enriched in a multimedia format that includes visual and auditory elements, such as recorded narration and animation. The server processes this and sends it to the device as rich content.

[0799] Step 4:

[0800] The device displays received content to the user using augmented reality technology. This enhances the visual effects of the story and provides an immersive experience. Users can, for example, access parts of the story while searching for an evacuation route or participate in simulations. The device utilizes AR tools to overlay virtual objects onto a view of the real world.

[0801] Step 5:

[0802] The user's voice and facial expression data are acquired by the device and sent to the emotion engine in real time. The emotion engine analyzes this data to identify the user's emotional state. Specifically, it uses voice tone analysis and facial expression recognition algorithms to make judgments. The results of this analysis are sent from the device to the server.

[0803] Step 6:

[0804] The server dynamically adjusts the story based on feedback from the emotion engine. For example, if the user shows anxiety or tension, the server changes the tone of the story and softens the narration to reassure the user. This optimizes the user experience and provides more personalized content.

[0805] Step 7:

[0806] The device records user selection data and emotional changes and sends them to the server. This data is analyzed on the server and used to generate future content. This continuously provides a learning experience tailored to the user and improves the system's personalization capabilities. The server uses this analysis to improve settings and prompts in future story generation.

[0807] (Application Example 2)

[0808] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0809] Traditional disaster prevention education systems often provide standardized content, which is problematic because they cannot offer learning experiences tailored to the individual interests and emotional states of each user. Furthermore, virtual stores face the challenge of not being able to promote purchasing behavior because it is difficult to suggest products based on customer emotions and preferences.

[0810] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0811] In this invention, the server includes means for acquiring information about the user's interests and location, means for generating a personalized disaster prevention story based on the acquired information, and means for recognizing the user's emotional state in real time and dynamically adjusting the experience content. This enables personalized learning and product recommendations that are tailored to the user's individual interests and emotional state.

[0812] "Means of obtaining information on user interests and location" refers to data collection devices and related programs for understanding users' interests and geographical characteristics.

[0813] "Means for generating personalized disaster prevention stories" refers to a generation program that creates disaster prevention narrative content tailored to individual users based on collected user information.

[0814] "Means of providing audio and visual content" refers to means of visually presenting the generated story via an audio output device and a display.

[0815] "Means of providing interactive experiences" refers to a system or program that provides an interactive experience in which the story and content change based on the user's individual choices.

[0816] "Means of recognizing the user's emotional state in real time and dynamically adjusting the experience" refers to algorithms that analyze emotional indicators such as the user's facial expressions and voiceprints, and adjust the development of the content and story being provided accordingly.

[0817] "Means of presenting relevant information and making customized product suggestions" refers to a program that provides relevant product information and individually tailored purchase suggestions based on the user's interests and sentiment data.

[0818] To implement this invention, a server capable of communicating with a terminal equipped with emotion recognition capabilities is required. First, the user inputs information about their interests and location via the terminal, and this information is collected. This information is transmitted from the terminal to the server, which uses a generative AI model to generate a personalized disaster prevention story based on this information. The generated story is provided to the user terminal as audio and visual content.

[0819] Users receive this content using mobile devices such as smart glasses. Audio and visual information is presented via augmented reality technology, and interactive choices are offered. As the user progresses through the story, their emotional state is analyzed in real time based on audio and facial data collected by the camera and microphone. This analysis uses Azure's Emotion API, among others. Emotional data is sent to a server, and the story content and progression are continuously and dynamically adjusted to provide the user with the best possible experience.

[0820] For example, when a user wears smart glasses and experiences an interactive story for disaster preparedness education, if the user experiences anxiety based on emotion recognition, feedback is provided such as the narration becoming gentler or the content being changed to something more reassuring. Also, in a virtual store shopping experience, if the user's interest or curiosity is detected, detailed product information and personalized suggestions are displayed.

[0821] An example of a prompt message could be a request sent to the AI ​​model such as, "Look at what the user is currently looking forward to, determine whether their emotion is interest or question, and provide appropriate guidance or suggestions." This invention allows users to enjoy a more personalized and memorable learning and purchasing experience.

[0822] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0823] Step 1:

[0824] The server collects information about the user's interests and location from their device.

[0825] The system receives user-generated information about their interests and location from their device. This information is provided as text and location data.

[0826] As part of data processing, the input information is formatted and prepared for storage in the database.

[0827] The output generates structured user profile information.

[0828] Step 2:

[0829] The server uses an AI model to generate personalized disaster prevention stories based on collected user information.

[0830] The system receives user profile information as input.

[0831] As a data processing step, a generative AI model algorithmically constructs stories tailored to the user's interests and regional characteristics. Specific story content is then output using prompts from the generative AI.

[0832] The output generates story data that can be used as audio and visual content.

[0833] Step 3:

[0834] The device provides the generated story to the user as audio and visual content.

[0835] The input is story data sent from the server.

[0836] As part of the data processing, the story data is converted into a format suitable for the user and then passed to the speech synthesis software and display.

[0837] The output presents audio and visual information in a format that the user can see and hear.

[0838] Step 4:

[0839] The device uses emotion recognition to analyze the user's emotions in real time and sends the data to the server.

[0840] The system acquires user facial expression data and voice data from the camera and microphone as input.

[0841] For data processing, we will use the Azure Emotion API to analyze emotional states.

[0842] The output is the user's sentiment data, which is sent to the server.

[0843] Step 5:

[0844] The server dynamically adjusts the story content and presentation method based on the emotional data it receives.

[0845] The system receives user sentiment data as input.

[0846] As part of the data processing, emotional data and generative AI models are reused to adjust the story progression and narration tone.

[0847] As output, the adjusted story data is sent to the device to improve the user experience.

[0848] Step 6:

[0849] The updated device story is presented again, offering users interactive options.

[0850] The input is the adjusted story data received from the server.

[0851] As a data processing step, interactive choices are presented to the user, and the selection results are used to determine the next story branch.

[0852] The final output will be a story updated based on the user's choices.

[0853] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0854] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0855] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0856] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0857] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0858] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0859] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0860] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0861] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0862] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0863] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0864] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0865] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0866] 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.

[0867] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0868] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0869] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0870] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0871] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0872] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0873] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0874] The following is further disclosed regarding the embodiments described above.

[0875] (Claim 1)

[0876] A means of collecting information about users' interests and location,

[0877] A means of generating an original disaster prevention story based on the collected information,

[0878] A means of providing the generated story along with audio and video,

[0879] A means of branching the story based on user choices and realizing an interactive experience,

[0880] A means to track the user's learning progress and reflect it in the next content generation,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, which uses augmented reality technology to enhance the visual effects of a story in the generated content.

[0884] (Claim 3)

[0885] The system according to claim 1, which analyzes user selection data and dynamically adjusts the next story to match the user's interests through data-driven optimization.

[0886] "Example 1"

[0887] (Claim 1)

[0888] A means of collecting data on users' interests and local area,

[0889] A means of generating new disaster prevention narratives using a generative AI model based on collected data,

[0890] A means of presenting the generated story together with speech synthesis and image generation techniques,

[0891] A means of enabling an interactive experience by branching the story according to the user's choices,

[0892] A means to track users' learning progress and reflect it in the creation of future digital content,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, which applies augmented reality technology to generated digital content to improve the visual effect of a story.

[0896] (Claim 3)

[0897] The system according to claim 1, which analyzes user selection data and dynamically adjusts the next story to suit the user's interests through data-driven optimization.

[0898] "Application Example 1"

[0899] (Claim 1)

[0900] A means of collecting information about users' interests and location,

[0901] A means of generating an original disaster prevention story based on the collected information,

[0902] A means of providing the generated story together with audio and video on a three-dimensional display device,

[0903] A means of branching the story based on user choices and realizing an interactive experience,

[0904] A means to track the user's learning progress and reflect it in the next information generation,

[0905] An information processing system that includes this.

[0906] (Claim 2)

[0907] The information processing system according to claim 1, which enhances the visual effects of a story using augmented reality technology on the generated visual information.

[0908] (Claim 3)

[0909] The information processing system according to claim 1, which analyzes user selection records and dynamically adjusts the next story to match the user's interests through data-driven optimization.

[0910] "Example 2 of combining an emotion engine"

[0911] (Claim 1)

[0912] A means of collecting information about users' interests and location,

[0913] A means of generating disaster prevention stories using a generative AI model based on collected information,

[0914] A means of adding audio and video content to a generated story and providing it,

[0915] A method for analyzing user voice and facial expression data to recognize emotional states and dynamically adjusting the story based on the results,

[0916] A means of branching the story based on user choices and realizing an interactive experience,

[0917] A means to track the user's learning progress and emotional changes and reflect them in the next content creation,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, which uses augmented reality technology to enhance the visual effects of a story in the generated content.

[0921] (Claim 3)

[0922] The system according to claim 1, which analyzes user selection data and emotional data, and dynamically adjusts the next story to match the user's interests and emotions through data-driven optimization.

[0923] "Application example 2 when combining with an emotional engine"

[0924] (Claim 1)

[0925] Means for obtaining information about users' interests and location,

[0926] A means of generating personalized disaster prevention stories based on acquired information,

[0927] A means of providing the generated story as audio and visual content,

[0928] A means of branching the plot according to the user's choices and providing an interactive experience,

[0929] A means of recognizing the user's emotional state in real time and dynamically adjusting the experience content,

[0930] A means of providing relevant information and customized product suggestions to support users' purchasing behavior,

[0931] A system that includes this.

[0932] (Claim 2)

[0933] The system according to claim 1, which utilizes augmented reality technology in the generated content to enhance the visual presentation of a story.

[0934] (Claim 3)

[0935] The system according to claim 1, which analyzes user selection data and dynamically adapts the next story that matches the user's interests through data-driven optimization. [Explanation of symbols]

[0936] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting information about users' interests and location, A means of generating an original disaster prevention story based on the collected information, A means of providing the generated story along with audio and video, A means of branching the story based on user choices and realizing an interactive experience, A means to track the user's learning progress and reflect it in the next content generation, A system that includes this.

2. The system according to claim 1, which uses augmented reality technology to enhance the visual effects of a story in the generated content.

3. The system according to claim 1, which analyzes user selection data and dynamically adjusts the next story to match the user's interests through data-driven optimization.

Images