system

Abstract

We provide the system. [Solution] Means for collecting image data, A method for training a machine learning model based on collected image data, A means for generating images from different viewpoints and heights based on user requests, A means of delivering the generated images to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional online tours and street views can only observe tourist attractions and exhibits from fixed viewpoints and heights, and there are limitations in providing users with an experience close to the real thing. In particular, for users with different viewpoints such as children and wheelchair users, these limitations are even more prominent, and it is difficult to reproduce the real vision. As a result, users cannot enjoy tourist attractions from the viewpoints that originally attract their interest, and there is a problem of reduced satisfaction.

Means for Solving the Problems

[0005] This invention provides a system that collects image data and uses a machine learning model based on it to generate images from a user's requested viewpoint and height. This enables users with various viewpoints, such as children and wheelchair users, to experience tourist destinations from their specific viewpoint. Furthermore, the generated images are delivered to the user, allowing them to enjoy a realistic visual experience through their device. In addition, by using three-dimensional model reconstruction technology, the system provides customized viewpoint options based on the user's location information, offering users a new way to enjoy their experiences.

[0006] "Image data" refers to data recorded as visual information, and includes a variety of scenes, such as tourist destinations and exhibits.

[0007] A "machine learning model" is an artificial intelligence technology that learns specific patterns and rules based on large amounts of data, and then uses that knowledge to make predictions and classifications from new data.

[0008] "User requirements" refer to specific requests that users make regarding the viewpoint and height they desire from the system.

[0009] "Different perspectives" refer to views from various angles and heights, unlike the conventional fixed viewpoint.

[0010] A "three-dimensional model" is a form of computer graphics that represents physical space or objects in three dimensions.

[0011] "Reconstruction" is the process of generating new perspectives and models based on existing data.

[0012] "Viewpoint options" refer to different viewpoint settings that users can choose from, providing a way to customize their specific visual experience.

[0013] A "device" is an electronic device used by a user to receive information and obtain a visual experience. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0017] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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.

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

[0019] In the following embodiments, the labeled 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, etc.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system for highly personalizing online experiences of tourist destinations and exhibits, and consists of processes including image data collection, utilization of machine learning models, and generation and distribution of images based on user requests.

[0036] The server first collects image data taken from tourist destinations at various viewpoints and heights. This data is stored in a database and used to train a machine learning model. The model is optimized to enhance its ability to simulate different viewpoints and heights. This makes it possible to provide high-quality images when users select their desired viewpoint and height.

[0037] The device receives requests from the user regarding the selection of tourist destinations and types of viewpoints. This request information is sent to the server, where the corresponding image data is processed. The server uses a trained machine learning model to generate native images based on the specific viewpoint and height. The generated content is delivered to the device, allowing the user to explore tourist destinations online while changing the viewpoint and height to suit their preferences.

[0038] For example, if a user wants to enjoy an online tour with their child, they can select "child's perspective" on their device. Based on the relevant data, the server generates images from a lower viewpoint, providing a new visual experience for the family. In this way, the system is designed to meet diverse user needs, allowing individual users to obtain a customized experience according to their situation and purpose.

[0039] By implementing this invention, users can enjoy a more realistic and personalized experience compared to conventional online tourism experiences. This provides a visual breadth that transcends the limitations of tourist destinations, and serves as a new solution for providing a rich tourism experience even to users who find it difficult to actually visit.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects image data of tourist attractions and exhibits taken from multiple viewpoints and various heights. This data is stored in a database and used to train models.

[0043] Step 2:

[0044] The server uses the collected image data to train a machine learning model. This model is optimized using deep learning techniques to generate views based on different viewpoints and heights.

[0045] Step 3:

[0046] Users select tourist destinations via their devices and make requests regarding specific viewpoints or heights. This includes options such as a child's eye level or a wheelchair user's eye level.

[0047] Step 4:

[0048] The terminal sends user request information to the server and requests processing. The server reads the corresponding image data from the database.

[0049] Step 5:

[0050] The server uses a trained model to generate images from new viewpoints that meet the user's requested viewpoint and height conditions. This utilizes three-dimensional reconstruction technology to create a continuous visual experience.

[0051] Step 6:

[0052] The generated image data is delivered to the user's device. The device displays this data through an interactive user interface, allowing the user to explore while adjusting their viewpoint and height.

[0053] Step 7:

[0054] Users can enjoy the provided visual experience and make further requests based on their interests and preferences. They can also provide feedback based on their experience through their device.

[0055] (Example 1)

[0056] 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."

[0057] In traditional online tourism experiences, users were limited to images from fixed viewpoints or altitudes, resulting in a restricted visual experience. Furthermore, it was difficult to fully meet the individual needs of users, leading to a uniform user experience.

[0058] 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.

[0059] In this invention, the server includes means for collecting image information, means for training an automated learning model based on the collected image information, and means for creating visual representations from different viewpoints and heights based on user requests. This makes it possible for users to obtain customized visual experiences from various viewpoints and heights.

[0060] "Methods for collecting image information" refer to techniques for photographing tourist destinations and exhibits from diverse viewpoints and heights, and collecting that data.

[0061] "Methods for training automated learning models" refer to techniques for optimizing machine learning models to improve their ability to simulate different viewpoints and heights based on collected image information.

[0062] "A means of creating visual representations from different viewpoints and heights based on user requests" refers to a technology that generates high-quality images using a pre-trained machine learning model in response to user requests.

[0063] "Means of providing created visual representations to users" refers to technologies that quickly and efficiently deliver generated content to users' devices.

[0064] A "terminal that receives requests from users" is a device that allows users to input their selection of tourist destinations and types of viewpoints, and then sends that information to a server.

[0065] "Means for processing prompt statements" refers to techniques for generating appropriate visual representations by converting user requests into a specific format and inputting them into a model.

[0066] This invention is a system that highly personalizes online experiences of tourist destinations and exhibits. Its main components are a server and a terminal, and it provides high-quality visual representations tailored to user requests, thereby realizing an experience suited to each individual user.

[0067] The server first collects image information from tourist attractions and exhibits. To do this, it uses cameras and drones to capture images from various viewpoints and heights. The collected image information is then stored in a database.

[0068] Next, the server trains an automated learning model. The model is trained using collected image data to improve its ability to simulate different viewpoints and heights. Machine learning frameworks (e.g., Tensorflow® or PyTorch) are used for this purpose.

[0069] A terminal is a device that receives requests from users. Mobile and web applications are provided to allow users to specify tourist destinations and viewpoint types. This information is sent to the server.

[0070] Users experience customized visual representations provided by the server based on their requests. Specifically, users input prompts such as "I want to see the Eiffel Tower from a child's perspective" into their terminal, and the server uses a model to generate appropriate images and delivers them to the user. This allows users to visually explore tourist destinations from a perspective that suits their preferences.

[0071] As a result, this system enables users to have a personalized and realistic online sightseeing experience that goes beyond simply providing images. This technology also provides a means of offering new experiences to users who are in situations where visiting in person is difficult.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server collects image information from tourist attractions and exhibits. The input is raw data captured using cameras and drones, and the output is unprocessed image information stored in a database. This process ensures information diversity by collecting images from various viewpoints and altitudes.

[0075] Step 2:

[0076] The server preprocesses the collected image information. The input here is raw image information stored in a database, and the output is training data suitable for machine learning models. In this step, the quality of the data is improved by adjusting the image resolution and denoising.

[0077] Step 3:

[0078] The server trains an automated learning model using preprocessed data. The input here is the preprocessed training data, and the output is a machine learning model capable of simulating viewpoints and altitude. This process utilizes machine learning frameworks (e.g., TensorFlow and PyTorch) to efficiently build and optimize the model.

[0079] Step 4:

[0080] The terminal receives requests from the user. The input here is the user's request regarding tourist destinations or viewpoints, and the output is the specific request data sent to the server. This operation utilizes the interfaces of mobile or web applications.

[0081] Step 5:

[0082] The server processes prompt messages based on user requests and generates appropriate visual representations. The input here is request data sent from the terminal and the corresponding prompt messages, while the output is a high-quality image corresponding to the user's request. This step utilizes a trained machine learning model to generate images at specified viewpoints and altitudes.

[0083] Step 6:

[0084] The server delivers the generated visual representation to the terminal. The input here is the generated high-quality image, and the output is the visual content the user receives in real time. This delivery utilizes efficient streaming technologies and CDN services to ensure a smooth user experience.

[0085] Step 7:

[0086] The user experiences a visual representation delivered via their device. The input here is the visual content delivered from the server, and the output is the user's satisfaction with the visual experience. In this final step, the user can freely select various viewpoints and altitudes to virtually explore the tourist destination.

[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] Traditional online shopping systems have the drawback of making it difficult for users to view products in detail from multiple angles, and the limited visual information makes product selection more challenging compared to the in-store shopping experience. Furthermore, there is a lack of systems capable of real-time display that reflects user movements and perspectives.

[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 image data, means for training a machine learning model based on the collected image data, and means for tracking the user's movements with a motion sensor and updating the viewpoint image in real time based on the transmitted motion data. This allows the user to observe products in detail from various angles in a virtual store, as if walking around the store.

[0092] "Methods for collecting image data" refer to methods of photographing tourist destinations or products within virtual stores from various viewpoints and heights, and then accumulating that information.

[0093] "Methods for training machine learning models" refer to the process of using collected image data to teach a computer about changes in viewpoint and height.

[0094] "A means of generating images from different viewpoints and heights based on user requests" refers to a technology that uses a machine learning model to create images from new viewpoints and heights according to user specifications.

[0095] "Means of delivering generated images to users" refers to a system that sends the created images to the user's device and provides a visual experience.

[0096] A "mobility tracking sensor for users" is a device that senses a user's movements and location and collects that information in real time.

[0097] "A means of updating the viewpoint image in real time based on transmitted motion data" refers to a technology that dynamically switches images in response to the user's movements.

[0098] The system that realizes this application provides users with a personalized visual experience in tourist destinations and virtual stores. The server first collects image data of products in tourist destinations and stores, taken from various viewpoints and heights. This collection is done using multiple cameras and sensors from different angles, and the obtained data is stored in a database.

[0099] The server then uses this image data to train a machine learning model. The software used leverages machine learning frameworks such as TensorFlow. The trained model will have improved capabilities to simulate various viewpoints and heights, enabling it to meet diverse requirements.

[0100] The user uses a device, such as smart glasses, to request a specific viewpoint or height. This request is entered through the device's user interface and sent to the server. The server then uses a trained machine learning model to generate an image from the new viewpoint.

[0101] This system includes motion sensors to track user behavior in real time. These sensors are gyroscopes and accelerometers built into smart glasses, and this data is sent to a server, updating the image in real time. Switching viewpoints is also smooth, providing users with an experience like walking around a virtual store from the comfort of their home.

[0102] To give a concrete example, imagine a user browsing new clothing in a virtual store. In this case, smart glasses would allow the user to view the clothing from bottom to top, and also check the design from the side. The user can easily change their viewpoint and check the details of the product.

[0103] An example of a prompt to the generating AI model is as follows: "Generate images of the new fall collection in a virtual store, viewed from a low perspective. The movement will change based on sensor information from smart glasses." In this way, the system of the present invention provides the user with a distinctive and personalized shopping experience.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server collects image data from tourist destinations and virtual stores. It uses cameras and sensors to capture images from various viewpoints and heights. The input for this step is product images from the tourist destination or store, and the output is a dataset of images from multiple angles and heights. The server stores this data in a database for later training.

[0107] Step 2:

[0108] The server trains a machine learning model based on the collected image data. It uses a machine learning framework such as TensorFlow. The input data is the image data obtained in the previous step, and the output is a trained model capable of generating images from different viewpoints and heights. Through training, the server obtains a model capable of generating images according to user requests.

[0109] Step 3:

[0110] The user requests image display from a specific viewpoint and height through their smart glasses. The input is request data regarding the viewpoint and height selected by the user, and the output is the request information sent to the server.

[0111] Step 4:

[0112] Based on the received request information, the server uses a trained machine learning model to generate an image based on the user's selected viewpoint and height. The input is the request data and the trained model, and the output is the generated image from the new viewpoint.

[0113] Step 5:

[0114] The server delivers the generated images to the user's device. The input is an image from a new perspective, and the output is visual data displayed on the user's smart glasses. This allows the user to examine products and scenery in detail from a perspective that suits their preferences.

[0115] Step 6:

[0116] To track user behavior in real time, the device's motion sensors are used. The gyroscope and accelerometer of smart glasses serve as inputs, and the output is motion data sent to the server.

[0117] Step 7:

[0118] The server updates the viewpoint image in real time based on the user's movement data. The input is the user's movement data, and the output is the updated viewpoint image. Through the image, which quickly reflects the changed viewpoint, the user can have an experience as if they were actually walking around the store.

[0119] 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.

[0120] This invention provides a highly personalized online tourism experience, enabling customization that takes into account not only the user's viewpoint selection but also their emotional state. This system begins with image data collection and combines it with real-time emotion analysis using an emotion engine to deliver a new level of experiential value.

[0121] The server collects image data of tourist attractions and exhibits, and uses this data to train a machine learning model. The model can generate images based on specific viewpoints and heights, and a sentiment engine can dynamically adjust the viewpoint according to the user's emotional state. The sentiment engine recognizes emotions from the user's facial expressions and voice, and analyzes the data in real time based on user feedback.

[0122] The device plays a role in receiving information from the user regarding the selection of tourist destinations, viewpoints, and emotional states. If the user wishes to consider their emotional state, they provide that information through the device. The device sends this information to the server, which then generates customized visual content based on that information.

[0123] For example, if a user is experiencing fear, the emotion engine can detect this and instruct the server to provide a calming and reassuring viewpoint. For instance, if the user is visiting a high place, the viewpoint can be lowered to provide a view from a safer position. Similarly, if a user is expressing excitement or joy, the emotion engine can select a correspondingly stimulating viewpoint to further enhance the user's experience.

[0124] In this way, the present invention can make online experiences of sightseeing and exhibits more engaging and personalized by providing a flexible visual experience that responds to the user's emotional state. This system allows users to experience a special journey that is tailored to their emotions at any given moment.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The server collects diverse image data of tourist attractions and exhibits and stores this data in a database. This allows for the accumulation of information necessary for generating images from various viewpoints and heights.

[0128] Step 2:

[0129] The server uses the collected data to train a machine learning model. This model has the ability to generate images based on specified viewpoints and heights, and is further prepared to dynamically adjust viewpoints using an emotion engine.

[0130] Step 3:

[0131] The device receives requests from the user regarding the selection of tourist destinations and the type of viewpoint. It also collects emotional information through the user's facial expressions and voice. This information is used to customize the tourist experience.

[0132] Step 4:

[0133] The terminal sends the user's tourist destination selection, viewpoint requests, and sentiment data to the server. The server receives this data and begins the necessary processing.

[0134] Step 5:

[0135] The server uses an emotion engine to analyze the user's emotional information. The emotion engine determines the user's emotional state (e.g., joy, surprise, fear) in real time and adjusts the viewpoint based on that information.

[0136] Step 6:

[0137] The server generates images from appropriate viewpoints and heights based on the emotion engine's output. For example, if the user desires a relaxed atmosphere, it will process the image to select a calm landscape.

[0138] Step 7:

[0139] The generated image data is delivered to the device and provided to the user. The user can then interactively enjoy a visual experience that matches their emotions through the device.

[0140] Step 8:

[0141] Users can enjoy the experience and provide more detailed emotional feedback as needed. The device sends this information to the server to help improve future experiences.

[0142] (Example 2)

[0143] 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".

[0144] Conventional online sightseeing experience systems have struggled to provide flexible perspectives and highly personalized experiences that respond to users' emotional states. The limited selection of specific viewpoints and heights, along with the lack of real-time viewpoint adjustments that consider the user's emotional state, have prevented them from providing the optimal experience for each user.

[0145] 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.

[0146] In this invention, the server includes means for collecting image information, means for training a learning model based on the collected image information, and means for generating images from different viewpoints and heights based on the user's emotional state. This enables the analysis of the user's emotional information and dynamic adjustment of the individualized viewpoint.

[0147] "Image information" refers to information that includes visual data, and includes visual representations related to subjects such as tourist destinations and exhibits.

[0148] A "learning model" refers to an algorithm that learns patterns and features based on collected data and can perform inference and prediction.

[0149] "Users" refer to individuals who use the system to experience online tourism.

[0150] "Emotional state" refers to the psychological and emotional condition of a user at any given time, which can be analyzed from their facial expressions and voice.

[0151] "Perspective" refers to a specific angle or direction from which an image or experience is visually perceived.

[0152] "Height" refers to the vertical position related to the viewpoint and is an element that influences how images appear during the visual experience.

[0153] "Generating" means creating new visual content using a learning model.

[0154] "Analyzing" means investigating data in detail to understand it and extract relevant information.

[0155] This invention provides a system that highly personalizes online tourism experiences. Through the interaction of a server, a terminal, and a user, this system delivers a visual experience tailored to the user's emotional state.

[0156] The server is responsible for collecting image information of tourist attractions and exhibits. This image information is used to train a machine learning model. Specifically, it preprocesses the images and uses them to train a generative AI model. This model enables image generation based on specific viewpoints and heights. It also utilizes an emotion engine to analyze the user's emotional state and dynamically adjust the viewpoint.

[0157] The device is used to collect information from the user regarding the selection of tourist destinations, viewpoints, and emotions. The user provides their emotional state through the device, and this information is sent to the server. This allows the server to generate customized visual content based on the user's emotions.

[0158] This system allows users to have a personalized sightseeing experience tailored to their emotional state. For example, if a user is feeling fear, the system can sense this and suggest a calming and reassuring viewpoint. Specifically, when visiting high places, the system can lower the viewpoint to provide a safer perspective. Furthermore, if a user is expressing excitement or joy, the emotion engine selects a correspondingly stimulating viewpoint to enhance the experience.

[0159] A concrete example of a prompt might be text like, "Provide a quiet museum experience to enhance the user's sense of relaxation." This is used as an instruction for the generative AI model to provide a visual experience that aligns with the user's emotions.

[0160] Through this system, the present invention can provide a flexible and engaging visual experience that responds to the user's emotions, making online sightseeing and exhibition experiences even more personalized.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The server collects image information related to tourist attractions and exhibits from online sources. The collected data is preprocessed by resizing and denoising the images and converted into a format suitable for training a learning model. It takes raw image data as input and generates preprocessed image data as output.

[0164] Step 2:

[0165] The server trains a learning model based on pre-processed image data. During this training phase, a large amount of data is used to improve the generative AI model's ability to generate images based on specified viewpoints and heights. The input is pre-processed image data, and the output is a trained learning model.

[0166] Step 3:

[0167] The device acquires information from the user regarding the selection of tourist destinations, viewpoints, and emotions. The user provides their emotional state through the device's camera and microphone. The input consists of visual and audio data from the user, and the output consists of the user's selection information and analyzed emotion data.

[0168] Step 4:

[0169] The server analyzes the user's emotional information transmitted from the terminal. The emotion engine identifies emotions from the user's facial expressions and voice, and dynamically adjusts the viewpoint based on that. The input is the user's emotional data, and the output is information about the adjusted viewpoint. Specifically, for example, if the user is in a relaxed state, the server will be instructed to select a calm and reassuring viewpoint.

[0170] Step 5:

[0171] Based on the analysis results, the server uses a generative AI model to generate visual content optimized for the user's emotional state. An example prompt is, "Provide a quiet museum experience to enhance the user's sense of relaxation." The input consists of adjusted viewpoint information and a prompt, and the output is customized image data.

[0172] Step 6:

[0173] The device presents the generated visual content to the user. Through this content, the user can obtain a personalized sightseeing experience. Specifically, the device's display shows generated visual information, which the user then views. The input is generated image data from the server, and the output is the user's visual experience.

[0174] (Application Example 2)

[0175] 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".

[0176] Traditional online tourism experience systems have struggled to personalize experiences based on users' emotional states, limiting the quality of the experience. Furthermore, they lacked dynamic adjustments of visual content based on user emotions, failing to provide a deeper level of satisfaction. This made it difficult to meet the diverse needs of users.

[0177] 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.

[0178] In this invention, the server includes means for collecting image data, means for training a machine learning model based on the collected image data, means for analyzing the user's emotional state, means for generating images from different viewpoints and heights based on the emotional state and the user's requests, and means for delivering the generated images to the user. This makes it possible to take the user's emotional state into consideration and highly customize the online sightseeing experience.

[0179] "Image data" refers to a collection of visual information stored in digital format, used to generate visual content from diverse viewpoints and heights.

[0180] A "machine learning model" is a computational algorithm that learns patterns from data and performs predictions or classifications for specific tasks.

[0181] "User emotional state" refers to the state of the user's psychological and emotional responses, which is determined in real time from facial expressions, voice, and other factors.

[0182] "Means for generating images from different viewpoints and heights" refers to a system or technology for creating visual content from diverse angles and positions based on user requirements.

[0183] "Means of distribution to users" refers to methods or devices for transferring and displaying generated visual content on a user's device.

[0184] A "three-dimensional model" is a three-dimensional digital structure that geometrically represents actual space and objects.

[0185] "User characteristics" refer to attribute information and preference data about users, which are used to provide personalized experiences.

[0186] This invention is a technology for personalizing online tourism experiences and provides a system that enables advanced customization that takes into account the user's emotional state. This system mainly consists of a server and a user terminal.

[0187] The server collects image data of tourist attractions or exhibits and uses it to train a machine learning model. The machine learning model is built using deep learning frameworks such as TensorFlow or PyTorch and has the ability to generate images from different viewpoints and heights. It also utilizes facial recognition and speech recognition technologies, and an emotion engine analyzes the user's emotional state in real time. Image processing libraries such as OpenCV can be used for emotion analysis.

[0188] The user's device, such as smart glasses or a smartphone, is responsible for capturing the user's facial expressions and voice. These devices transmit the collected data to a server, which then analyzes it to provide a customized visual experience tailored to the user's emotional state.

[0189] For example, if a user expresses fear, the server, based on the analysis of the emotion engine, generates and provides a calmer perspective that provides a greater sense of security. Conversely, if a user expresses joy, it selects a stimulating perspective that promotes excitement. This allows users to have the optimal experience according to their emotions at that moment.

[0190] Examples of prompts include, "Please suggest travel items that would be suitable for a user who is relaxed." By using such prompts, generative AI models can provide excellent suggestions tailored to the user's emotional state.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The device collects the user's facial expressions and voice data. This data is acquired using the built-in camera and microphone. This provides the input data necessary for emotion analysis.

[0194] Step 2:

[0195] The device transmits collected facial expression and voice data to the server. The data is transferred in real time via a secure protocol and used for analysis by the server's emotion engine.

[0196] Step 3:

[0197] The server uses the received data to analyze the user's emotional state using an emotion engine. In this process, facial features are extracted using the OpenCV library, and a machine learning model estimates the emotion. For example, if the facial feature obtained as a feature is recognized as a "smile," the emotion is determined to be "joy."

[0198] Step 4:

[0199] The server generates appropriate visual content based on the sentiment analysis results. This process uses machine learning models to create images from specific viewpoints and heights that correspond to the user's emotional state.

[0200] Step 5:

[0201] The server delivers the generated, customized visual content to the device. The visual content is optimized and displayed for the device the user is using.

[0202] Step 6:

[0203] Users experience visual content delivered through their devices. During this stage, users can continuously provide emotional information to their devices, and the server further adjusts the content based on this new data. This enables a dynamically personalized tourism experience.

[0204] 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.

[0205] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0206] 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.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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".

[0220] This invention is a system for highly personalizing online experiences of tourist destinations and exhibits, and consists of processes including image data collection, utilization of machine learning models, and generation and distribution of images based on user requests.

[0221] The server first collects image data taken from tourist destinations at various viewpoints and heights. This data is stored in a database and used to train a machine learning model. The model is optimized to enhance its ability to simulate different viewpoints and heights. This makes it possible to provide high-quality images when users select their desired viewpoint and height.

[0222] The device receives requests from the user regarding the selection of tourist destinations and types of viewpoints. This request information is sent to the server, where the corresponding image data is processed. The server uses a trained machine learning model to generate native images based on the specific viewpoint and height. The generated content is delivered to the device, allowing the user to explore tourist destinations online while changing the viewpoint and height to suit their preferences.

[0223] For example, if a user wants to enjoy an online tour with their child, they can select "child's perspective" on their device. Based on the relevant data, the server generates images from a lower viewpoint, providing a new visual experience for the family. In this way, the system is designed to meet diverse user needs, allowing individual users to obtain a customized experience according to their situation and purpose.

[0224] By implementing this invention, users can enjoy a more realistic and personalized experience compared to conventional online tourism experiences. This provides a visual breadth that transcends the limitations of tourist destinations, and serves as a new solution for providing a rich tourism experience even to users who find it difficult to actually visit.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server collects image data of tourist attractions and exhibits taken from multiple viewpoints and various heights. This data is stored in a database and used to train models.

[0228] Step 2:

[0229] The server uses the collected image data to train a machine learning model. This model is optimized using deep learning techniques to generate views based on different viewpoints and heights.

[0230] Step 3:

[0231] Users select tourist destinations via their devices and make requests regarding specific viewpoints or heights. This includes options such as a child's eye level or a wheelchair user's eye level.

[0232] Step 4:

[0233] The terminal sends user request information to the server and requests processing. The server reads the corresponding image data from the database.

[0234] Step 5:

[0235] The server uses a trained model to generate images from new viewpoints that meet the user's requested viewpoint and height conditions. This utilizes three-dimensional reconstruction technology to create a continuous visual experience.

[0236] Step 6:

[0237] The generated image data is delivered to the user's device. The device displays this data through an interactive user interface, allowing the user to explore while adjusting their viewpoint and height.

[0238] Step 7:

[0239] Users can enjoy the provided visual experience and make further requests based on their interests and preferences. They can also provide feedback based on their experience through their device.

[0240] (Example 1)

[0241] 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."

[0242] In traditional online tourism experiences, users were limited to images from fixed viewpoints or altitudes, resulting in a restricted visual experience. Furthermore, it was difficult to fully meet the individual needs of users, leading to a uniform user experience.

[0243] 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.

[0244] In this invention, the server includes means for collecting image information, means for training an automated learning model based on the collected image information, and means for creating visual representations from different viewpoints and heights based on user requests. This makes it possible for users to obtain customized visual experiences from various viewpoints and heights.

[0245] "Methods for collecting image information" refer to techniques for photographing tourist destinations and exhibits from diverse viewpoints and heights, and collecting that data.

[0246] "Methods for training automated learning models" refer to techniques for optimizing machine learning models to improve their ability to simulate different viewpoints and heights based on collected image information.

[0247] "A means of creating visual representations from different viewpoints and heights based on user requests" refers to a technology that generates high-quality images using a pre-trained machine learning model in response to user requests.

[0248] "Means of providing created visual representations to users" refers to technologies that quickly and efficiently deliver generated content to users' devices.

[0249] A "terminal that receives requests from users" is a device that allows users to input their selection of tourist destinations and types of viewpoints, and then sends that information to a server.

[0250] "Means for processing prompt statements" refers to techniques for generating appropriate visual representations by converting user requests into a specific format and inputting them into a model.

[0251] This invention is a system that highly personalizes online experiences of tourist destinations and exhibits. Its main components are a server and a terminal, and it provides high-quality visual representations tailored to user requests, thereby realizing an experience suited to each individual user.

[0252] The server first collects image information from tourist attractions and exhibits. To do this, it uses cameras and drones to capture images from various viewpoints and heights. The collected image information is then stored in a database.

[0253] Next, the server trains an automated learning model. The model is trained using collected image data to improve its ability to simulate different viewpoints and heights. A machine learning framework (e.g., TensorFlow or PyTorch) is used for this.

[0254] A terminal is a device that receives requests from users. Mobile and web applications are provided to allow users to specify tourist destinations and viewpoint types. This information is sent to the server.

[0255] Users experience customized visual representations provided by the server based on their requests. Specifically, users input prompts such as "I want to see the Eiffel Tower from a child's perspective" into their terminal, and the server uses a model to generate appropriate images and delivers them to the user. This allows users to visually explore tourist destinations from a perspective that suits their preferences.

[0256] As a result, this system enables users to have a personalized and realistic online sightseeing experience that goes beyond simply providing images. This technology also provides a means of offering new experiences to users who are in situations where visiting in person is difficult.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The server collects image information from tourist attractions and exhibits. The input is raw data captured using cameras and drones, and the output is unprocessed image information stored in a database. This process ensures information diversity by collecting images from various viewpoints and altitudes.

[0260] Step 2:

[0261] The server preprocesses the collected image information. The input here is raw image information stored in a database, and the output is training data suitable for machine learning models. In this step, the quality of the data is improved by adjusting the image resolution and denoising.

[0262] Step 3:

[0263] The server trains an automated learning model using preprocessed data. The input here is the preprocessed training data, and the output is a machine learning model capable of simulating viewpoints and altitude. This process utilizes machine learning frameworks (e.g., TensorFlow and PyTorch) to efficiently build and optimize the model.

[0264] Step 4:

[0265] The terminal receives requests from the user. The input here is the user's request regarding tourist destinations or viewpoints, and the output is the specific request data sent to the server. This operation utilizes the interfaces of mobile or web applications.

[0266] Step 5:

[0267] The server processes prompt messages based on user requests and generates appropriate visual representations. The input here is request data sent from the terminal and the corresponding prompt messages, while the output is a high-quality image corresponding to the user's request. This step utilizes a trained machine learning model to generate images at specified viewpoints and altitudes.

[0268] Step 6:

[0269] The server delivers the generated visual representation to the terminal. The input here is the generated high-quality image, and the output is the visual content the user receives in real time. This delivery utilizes efficient streaming technologies and CDN services to ensure a smooth user experience.

[0270] Step 7:

[0271] The user experiences a visual representation delivered via their device. The input here is the visual content delivered from the server, and the output is the user's satisfaction with the visual experience. In this final step, the user can freely select various viewpoints and altitudes to virtually explore the tourist destination.

[0272] (Application Example 1)

[0273] 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."

[0274] Traditional online shopping systems have the drawback of making it difficult for users to view products in detail from multiple angles, and the limited visual information makes product selection more challenging compared to the in-store shopping experience. Furthermore, there is a lack of systems capable of real-time display that reflects user movements and perspectives.

[0275] 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.

[0276] In this invention, the server includes means for collecting image data, means for training a machine learning model based on the collected image data, and means for tracking the user's movements with a motion sensor and updating the viewpoint image in real time based on the transmitted motion data. This allows the user to observe products in detail from various angles in a virtual store, as if walking around the store.

[0277] "Methods for collecting image data" refer to methods of photographing tourist destinations or products within virtual stores from various viewpoints and heights, and then accumulating that information.

[0278] "Methods for training machine learning models" refer to the process of using collected image data to teach a computer about changes in viewpoint and height.

[0279] "A means of generating images from different viewpoints and heights based on user requests" refers to a technology that uses a machine learning model to create images from new viewpoints and heights according to user specifications.

[0280] "Means of delivering generated images to users" refers to a system that sends the created images to the user's device and provides a visual experience.

[0281] A "mobility tracking sensor for users" is a device that senses a user's movements and location and collects that information in real time.

[0282] "A means of updating the viewpoint image in real time based on transmitted motion data" refers to a technology that dynamically switches images in response to the user's movements.

[0283] The system that realizes this application example provides a personalized visual experience for users in tourist attractions and virtual stores. First, the server collects image data of the products in tourist attractions or stores photographed from various viewpoints and heights. This collection is carried out from different angles using multiple cameras and sensors, and the obtained data is stored in a database.

[0284] Next, the server uses this image data to train a machine learning model. Machine learning frameworks such as TensorFlow are utilized in the software used. The trained model improves the ability to simulate various viewpoints and heights and can meet various requirements.

[0285] The user uses a terminal, such as smart glasses, to make requests for specific viewpoints and heights. This request is input through the user interface of the terminal and sent to the server. The server uses the trained machine learning model based on this to generate an image of a new viewpoint.

[0286] This system includes a mobile device sensor for tracking the user's actions in real time. This sensor is a gyroscope and an accelerometer installed in the smart glasses, and this data is sent to the server, and the image is updated in real time. The switching of viewpoints also proceeds smoothly, providing the user with an experience of walking around a virtual store while staying at home.

[0287] For a specific example, suppose the user is looking at new clothes in a virtual store. In this case, through the smart glasses, the user can look at the clothes from bottom to top, and can also check the design from the side. The user can easily change the viewpoint and can check the details of the product.

[0288] An example of a prompt to the generating AI model is as follows: "Generate images of the new fall collection in a virtual store, viewed from a low perspective. The movement will change based on sensor information from smart glasses." In this way, the system of the present invention provides the user with a distinctive and personalized shopping experience.

[0289] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0290] Step 1:

[0291] The server collects image data from tourist destinations and virtual stores. It uses cameras and sensors to capture images from various viewpoints and heights. The input for this step is product images from the tourist destination or store, and the output is a dataset of images from multiple angles and heights. The server stores this data in a database for later training.

[0292] Step 2:

[0293] The server trains a machine learning model based on the collected image data. It uses a machine learning framework such as TensorFlow. The input data is the image data obtained in the previous step, and the output is a trained model capable of generating images from different viewpoints and heights. Through training, the server obtains a model capable of generating images according to user requests.

[0294] Step 3:

[0295] The user requests image display from a specific viewpoint and height through their smart glasses. The input is request data regarding the viewpoint and height selected by the user, and the output is the request information sent to the server.

[0296] Step 4:

[0297] Based on the received request information, the server uses a trained machine learning model to generate an image based on the user's selected viewpoint and height. The input is the request data and the trained model, and the output is the generated image from the new viewpoint.

[0298] Step 5:

[0299] The server delivers the generated images to the user's device. The input is an image from a new perspective, and the output is visual data displayed on the user's smart glasses. This allows the user to examine products and scenery in detail from a perspective that suits their preferences.

[0300] Step 6:

[0301] To track user behavior in real time, the device's motion sensors are used. The gyroscope and accelerometer of smart glasses serve as inputs, and the output is motion data sent to the server.

[0302] Step 7:

[0303] The server updates the viewpoint image in real time based on the user's movement data. The input is the user's movement data, and the output is the updated viewpoint image. Through the image, which quickly reflects the changed viewpoint, the user can have an experience as if they were actually walking around the store.

[0304] 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.

[0305] This invention provides a highly personalized online tourism experience, enabling customization that takes into account not only the user's viewpoint selection but also their emotional state. This system begins with image data collection and combines it with real-time emotion analysis using an emotion engine to deliver a new level of experiential value.

[0306] The server collects image data of tourist attractions and exhibits, and trains a machine learning model based on this data. The model can generate images based on specific viewpoints and heights, and can also dynamically adjust the viewpoint according to the user's emotional state by means of an emotion engine. The emotion engine recognizes emotions from the user's facial expressions and voices, and analyzes the data in real time upon receiving the user's feedback.

[0307] The terminal serves to receive from the user the selection of a tourist attraction, the selection of a viewpoint, and emotional information. When the user wants to consider their emotional state, they provide such information via the terminal. The terminal sends this information to the server, and the server generates customized visual content based on this information.

[0308] As a specific example, when the user is feeling scared, the emotion engine senses this and instructs the server to provide a viewpoint that is gentle and gives a sense of security. For example, when visiting a high place, the viewpoint can be lowered to provide a view from a safer position. Also, when the user is showing excitement or joy, the emotion engine selects a stimulating viewpoint accordingly, which can further enhance the user's experience.

[0309] In this way, the present invention can make the online experience of tourism and exhibits more attractive and personalized by providing a flexible visual experience according to the user's emotional state. With this system, the user can experience a special journey that suits their emotions at each moment.

[0310] The following describes the processing flow.

[0311] Step 1:

[0312] The server collects diverse image data of tourist attractions and exhibits, and stores this data in a database. Thereby, the information necessary for generating images of various viewpoints and heights is accumulated.

[0313] Step 2:

[0314] The server uses the collected data to train a machine learning model. This model has the ability to generate images based on specified viewpoints and heights, and is further prepared to dynamically adjust viewpoints using an emotion engine.

[0315] Step 3:

[0316] The device receives requests from the user regarding the selection of tourist destinations and the type of viewpoint. It also collects emotional information through the user's facial expressions and voice. This information is used to customize the tourist experience.

[0317] Step 4:

[0318] The terminal sends the user's tourist destination selection, viewpoint requests, and sentiment data to the server. The server receives this data and begins the necessary processing.

[0319] Step 5:

[0320] The server uses an emotion engine to analyze the user's emotional information. The emotion engine determines the user's emotional state (e.g., joy, surprise, fear) in real time and adjusts the viewpoint based on that information.

[0321] Step 6:

[0322] The server generates images from appropriate viewpoints and heights based on the emotion engine's output. For example, if the user desires a relaxed atmosphere, it will process the image to select a calm landscape.

[0323] Step 7:

[0324] The generated image data is delivered to the device and provided to the user. The user can then interactively enjoy a visual experience that matches their emotions through the device.

[0325] Step 8:

[0326] Users can enjoy the experience and provide more detailed emotional feedback as needed. The device sends this information to the server to help improve future experiences.

[0327] (Example 2)

[0328] 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".

[0329] Conventional online sightseeing experience systems have struggled to provide flexible perspectives and highly personalized experiences that respond to users' emotional states. The limited selection of specific viewpoints and heights, along with the lack of real-time viewpoint adjustments that consider the user's emotional state, have prevented them from providing the optimal experience for each user.

[0330] 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.

[0331] In this invention, the server includes means for collecting image information, means for training a learning model based on the collected image information, and means for generating images from different viewpoints and heights based on the user's emotional state. This enables the analysis of the user's emotional information and dynamic adjustment of the individualized viewpoint.

[0332] "Image information" refers to information that includes visual data, and includes visual representations related to subjects such as tourist destinations and exhibits.

[0333] A "learning model" refers to an algorithm that learns patterns and features based on collected data and can perform inference and prediction.

[0334] "Users" refer to individuals who use the system to experience online tourism.

[0335] "Emotional state" refers to the psychological and emotional condition of a user at any given time, which can be analyzed from their facial expressions and voice.

[0336] "Perspective" refers to a specific angle or direction from which an image or experience is visually perceived.

[0337] "Height" refers to the vertical position related to the viewpoint and is an element that influences how images appear during the visual experience.

[0338] "Generating" means creating new visual content using a learning model.

[0339] "Analyzing" means investigating data in detail to understand it and extract relevant information.

[0340] This invention provides a system that highly personalizes online tourism experiences. Through the interaction of a server, a terminal, and a user, this system delivers a visual experience tailored to the user's emotional state.

[0341] The server is responsible for collecting image information of tourist attractions and exhibits. This image information is used to train a machine learning model. Specifically, it preprocesses the images and uses them to train a generative AI model. This model enables image generation based on specific viewpoints and heights. It also utilizes an emotion engine to analyze the user's emotional state and dynamically adjust the viewpoint.

[0342] The device is used to collect information from the user regarding the selection of tourist destinations, viewpoints, and emotions. The user provides their emotional state through the device, and this information is sent to the server. This allows the server to generate customized visual content based on the user's emotions.

[0343] This system allows users to have a personalized sightseeing experience tailored to their emotional state. For example, if a user is feeling fear, the system can sense this and suggest a calming and reassuring viewpoint. Specifically, when visiting high places, the system can lower the viewpoint to provide a safer perspective. Furthermore, if a user is expressing excitement or joy, the emotion engine selects a correspondingly stimulating viewpoint to enhance the experience.

[0344] A concrete example of a prompt might be text like, "Provide a quiet museum experience to enhance the user's sense of relaxation." This is used as an instruction for the generative AI model to provide a visual experience that aligns with the user's emotions.

[0345] Through this system, the present invention can provide a flexible and engaging visual experience that responds to the user's emotions, making online sightseeing and exhibition experiences even more personalized.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] The server collects image information related to tourist attractions and exhibits from online sources. The collected data is preprocessed by resizing and denoising the images and converted into a format suitable for training a learning model. It takes raw image data as input and generates preprocessed image data as output.

[0349] Step 2:

[0350] The server trains a learning model based on pre-processed image data. During this training phase, a large amount of data is used to improve the generative AI model's ability to generate images based on specified viewpoints and heights. The input is pre-processed image data, and the output is a trained learning model.

[0351] Step 3:

[0352] The device acquires information from the user regarding the selection of tourist destinations, viewpoints, and emotions. The user provides their emotional state through the device's camera and microphone. The input consists of visual and audio data from the user, and the output consists of the user's selection information and analyzed emotion data.

[0353] Step 4:

[0354] The server analyzes the user's emotional information transmitted from the terminal. The emotion engine identifies emotions from the user's facial expressions and voice, and dynamically adjusts the viewpoint based on that. The input is the user's emotional data, and the output is information about the adjusted viewpoint. Specifically, for example, if the user is in a relaxed state, the server will be instructed to select a calm and reassuring viewpoint.

[0355] Step 5:

[0356] Based on the analysis results, the server uses a generative AI model to generate visual content optimized for the user's emotional state. An example prompt is, "Provide a quiet museum experience to enhance the user's sense of relaxation." The input consists of adjusted viewpoint information and a prompt, and the output is customized image data.

[0357] Step 6:

[0358] The device presents the generated visual content to the user. Through this content, the user can obtain a personalized sightseeing experience. Specifically, the device's display shows generated visual information, which the user then views. The input is generated image data from the server, and the output is the user's visual experience.

[0359] (Application Example 2)

[0360] 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."

[0361] Traditional online tourism experience systems have struggled to personalize experiences based on users' emotional states, limiting the quality of the experience. Furthermore, they lacked dynamic adjustments of visual content based on user emotions, failing to provide a deeper level of satisfaction. This made it difficult to meet the diverse needs of users.

[0362] 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.

[0363] In this invention, the server includes means for collecting image data, means for training a machine learning model based on the collected image data, means for analyzing the user's emotional state, means for generating images from different viewpoints and heights based on the emotional state and the user's requests, and means for delivering the generated images to the user. This makes it possible to take the user's emotional state into consideration and highly customize the online sightseeing experience.

[0364] "Image data" refers to a collection of visual information stored in digital format, used to generate visual content from diverse viewpoints and heights.

[0365] A "machine learning model" is a computational algorithm that learns patterns from data and performs predictions or classifications for specific tasks.

[0366] "User emotional state" refers to the state of the user's psychological and emotional responses, which is determined in real time from facial expressions, voice, and other factors.

[0367] "Means for generating images from different viewpoints and heights" refers to a system or technology for creating visual content from diverse angles and positions based on user requirements.

[0368] "Means of distribution to users" refers to methods or devices for transferring and displaying generated visual content on a user's device.

[0369] A "three-dimensional model" is a three-dimensional digital structure that geometrically represents actual space and objects.

[0370] "User characteristics" refer to attribute information and preference data about users, which are used to provide personalized experiences.

[0371] This invention is a technology for personalizing online tourism experiences and provides a system that enables advanced customization that takes into account the user's emotional state. This system mainly consists of a server and a user terminal.

[0372] The server collects image data of tourist attractions or exhibits and uses it to train a machine learning model. The machine learning model is built using deep learning frameworks such as TensorFlow or PyTorch and has the ability to generate images from different viewpoints and heights. It also utilizes facial recognition and speech recognition technologies, and an emotion engine analyzes the user's emotional state in real time. Image processing libraries such as OpenCV can be used for emotion analysis.

[0373] The user's device, such as smart glasses or a smartphone, is responsible for capturing the user's facial expressions and voice. These devices transmit the collected data to a server, which then analyzes it to provide a customized visual experience tailored to the user's emotional state.

[0374] For example, if a user expresses fear, the server, based on the analysis of the emotion engine, generates and provides a calmer perspective that provides a greater sense of security. Conversely, if a user expresses joy, it selects a stimulating perspective that promotes excitement. This allows users to have the optimal experience according to their emotions at that moment.

[0375] Examples of prompts include, "Please suggest travel items that would be suitable for a user who is relaxed." By using such prompts, generative AI models can provide excellent suggestions tailored to the user's emotional state.

[0376] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0377] Step 1:

[0378] The device collects the user's facial expressions and voice data. This data is acquired using the built-in camera and microphone. This provides the input data necessary for emotion analysis.

[0379] Step 2:

[0380] The device transmits collected facial expression and voice data to the server. The data is transferred in real time via a secure protocol and used for analysis by the server's emotion engine.

[0381] Step 3:

[0382] The server uses the received data to analyze the user's emotional state using an emotion engine. In this process, facial features are extracted using the OpenCV library, and a machine learning model estimates the emotion. For example, if the facial feature obtained as a feature is recognized as a "smile," the emotion is determined to be "joy."

[0383] Step 4:

[0384] The server generates appropriate visual content based on the sentiment analysis results. This process uses machine learning models to create images from specific viewpoints and heights that correspond to the user's emotional state.

[0385] Step 5:

[0386] The server delivers the generated, customized visual content to the device. The visual content is optimized and displayed for the device the user is using.

[0387] Step 6:

[0388] Users experience visual content delivered through their devices. During this stage, users can continuously provide emotional information to their devices, and the server further adjusts the content based on this new data. This enables a dynamically personalized tourism experience.

[0389] 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.

[0390] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0391] 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.

[0392] [Third Embodiment]

[0393] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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).

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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".

[0405] This invention is a system for highly personalizing online experiences of tourist destinations and exhibits, and consists of processes including image data collection, utilization of machine learning models, and generation and distribution of images based on user requests.

[0406] The server first collects image data taken from tourist destinations at various viewpoints and heights. This data is stored in a database and used to train a machine learning model. The model is optimized to enhance its ability to simulate different viewpoints and heights. This makes it possible to provide high-quality images when users select their desired viewpoint and height.

[0407] The device receives requests from the user regarding the selection of tourist destinations and types of viewpoints. This request information is sent to the server, where the corresponding image data is processed. The server uses a trained machine learning model to generate native images based on the specific viewpoint and height. The generated content is delivered to the device, allowing the user to explore tourist destinations online while changing the viewpoint and height to suit their preferences.

[0408] For example, if a user wants to enjoy an online tour with their child, they can select "child's perspective" on their device. Based on the relevant data, the server generates images from a lower viewpoint, providing a new visual experience for the family. In this way, the system is designed to meet diverse user needs, allowing individual users to obtain a customized experience according to their situation and purpose.

[0409] By implementing this invention, users can enjoy a more realistic and personalized experience compared to conventional online tourism experiences. This provides a visual breadth that transcends the limitations of tourist destinations, and serves as a new solution for providing a rich tourism experience even to users who find it difficult to actually visit.

[0410] The following describes the processing flow.

[0411] Step 1:

[0412] The server collects image data of tourist attractions and exhibits taken from multiple viewpoints and various heights. This data is stored in a database and used to train models.

[0413] Step 2:

[0414] The server uses the collected image data to train a machine learning model. This model is optimized using deep learning techniques to generate views based on different viewpoints and heights.

[0415] Step 3:

[0416] Users select tourist destinations via their devices and make requests regarding specific viewpoints or heights. This includes options such as a child's eye level or a wheelchair user's eye level.

[0417] Step 4:

[0418] The terminal sends user request information to the server and requests processing. The server reads the corresponding image data from the database.

[0419] Step 5:

[0420] The server uses a trained model to generate images from new viewpoints that meet the user's requested viewpoint and height conditions. This utilizes three-dimensional reconstruction technology to create a continuous visual experience.

[0421] Step 6:

[0422] The generated image data is delivered to the user's device. The device displays this data through an interactive user interface, allowing the user to explore while adjusting their viewpoint and height.

[0423] Step 7:

[0424] Users can enjoy the provided visual experience and make further requests based on their interests and preferences. They can also provide feedback based on their experience through their device.

[0425] (Example 1)

[0426] 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."

[0427] In traditional online tourism experiences, users were limited to images from fixed viewpoints or altitudes, resulting in a restricted visual experience. Furthermore, it was difficult to fully meet the individual needs of users, leading to a uniform user experience.

[0428] 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.

[0429] In this invention, the server includes means for collecting image information, means for training an automated learning model based on the collected image information, and means for creating visual representations from different viewpoints and heights based on user requests. This makes it possible for users to obtain customized visual experiences from various viewpoints and heights.

[0430] "Methods for collecting image information" refer to techniques for photographing tourist destinations and exhibits from diverse viewpoints and heights, and collecting that data.

[0431] "Methods for training automated learning models" refer to techniques for optimizing machine learning models to improve their ability to simulate different viewpoints and heights based on collected image information.

[0432] "A means of creating visual representations from different viewpoints and heights based on user requests" refers to a technology that generates high-quality images using a pre-trained machine learning model in response to user requests.

[0433] "Means of providing created visual representations to users" refers to technologies that quickly and efficiently deliver generated content to users' devices.

[0434] A "terminal that receives requests from users" is a device that allows users to input their selection of tourist destinations and types of viewpoints, and then sends that information to a server.

[0435] "Means for processing prompt statements" refers to techniques for generating appropriate visual representations by converting user requests into a specific format and inputting them into a model.

[0436] This invention is a system that highly personalizes online experiences of tourist destinations and exhibits. Its main components are a server and a terminal, and it provides high-quality visual representations tailored to user requests, thereby realizing an experience suited to each individual user.

[0437] The server first collects image information from tourist attractions and exhibits. To do this, it uses cameras and drones to capture images from various viewpoints and heights. The collected image information is then stored in a database.

[0438] Next, the server trains an automated learning model. The model is trained using collected image data to improve its ability to simulate different viewpoints and heights. A machine learning framework (e.g., TensorFlow or PyTorch) is used for this.

[0439] A terminal is a device that receives requests from users. Mobile and web applications are provided to allow users to specify tourist destinations and viewpoint types. This information is sent to the server.

[0440] Users experience customized visual representations provided by the server based on their requests. Specifically, users input prompts such as "I want to see the Eiffel Tower from a child's perspective" into their terminal, and the server uses a model to generate appropriate images and delivers them to the user. This allows users to visually explore tourist destinations from a perspective that suits their preferences.

[0441] As a result, this system enables users to have a personalized and realistic online sightseeing experience that goes beyond simply providing images. This technology also provides a means of offering new experiences to users who are in situations where visiting in person is difficult.

[0442] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0443] Step 1:

[0444] The server collects image information from tourist attractions and exhibits. The input is raw data captured using cameras and drones, and the output is unprocessed image information stored in a database. This process ensures information diversity by collecting images from various viewpoints and altitudes.

[0445] Step 2:

[0446] The server preprocesses the collected image information. The input here is raw image information stored in a database, and the output is training data suitable for machine learning models. In this step, the quality of the data is improved by adjusting the image resolution and denoising.

[0447] Step 3:

[0448] The server trains an automated learning model using preprocessed data. The input here is the preprocessed training data, and the output is a machine learning model capable of simulating viewpoints and altitude. This process utilizes machine learning frameworks (e.g., TensorFlow and PyTorch) to efficiently build and optimize the model.

[0449] Step 4:

[0450] The terminal receives requests from the user. The input here is the user's request regarding tourist destinations or viewpoints, and the output is the specific request data sent to the server. This operation utilizes the interfaces of mobile or web applications.

[0451] Step 5:

[0452] The server processes prompt messages based on user requests and generates appropriate visual representations. The input here is request data sent from the terminal and the corresponding prompt messages, while the output is a high-quality image corresponding to the user's request. This step utilizes a trained machine learning model to generate images at specified viewpoints and altitudes.

[0453] Step 6:

[0454] The server delivers the generated visual representation to the terminal. The input here is the generated high-quality image, and the output is the visual content the user receives in real time. This delivery utilizes efficient streaming technologies and CDN services to ensure a smooth user experience.

[0455] Step 7:

[0456] The user experiences a visual representation delivered via their device. The input here is the visual content delivered from the server, and the output is the user's satisfaction with the visual experience. In this final step, the user can freely select various viewpoints and altitudes to virtually explore the tourist destination.

[0457] (Application Example 1)

[0458] 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."

[0459] Traditional online shopping systems have the drawback of making it difficult for users to view products in detail from multiple angles, and the limited visual information makes product selection more challenging compared to the in-store shopping experience. Furthermore, there is a lack of systems capable of real-time display that reflects user movements and perspectives.

[0460] 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.

[0461] In this invention, the server includes means for collecting image data, means for training a machine learning model based on the collected image data, and means for tracking the user's movements with a motion sensor and updating the viewpoint image in real time based on the transmitted motion data. This allows the user to observe products in detail from various angles in a virtual store, as if walking around the store.

[0462] "Methods for collecting image data" refer to methods of photographing tourist destinations or products within virtual stores from various viewpoints and heights, and then accumulating that information.

[0463] "Methods for training machine learning models" refer to the process of using collected image data to teach a computer about changes in viewpoint and height.

[0464] "A means of generating images from different viewpoints and heights based on user requests" refers to a technology that uses a machine learning model to create images from new viewpoints and heights according to user specifications.

[0465] "Means of delivering generated images to users" refers to a system that sends the created images to the user's device and provides a visual experience.

[0466] A "mobility tracking sensor for users" is a device that senses a user's movements and location and collects that information in real time.

[0467] "A means of updating the viewpoint image in real time based on transmitted motion data" refers to a technology that dynamically switches images in response to the user's movements.

[0468] The system that realizes this application provides users with a personalized visual experience in tourist destinations and virtual stores. The server first collects image data of products in tourist destinations and stores, taken from various viewpoints and heights. This collection is done using multiple cameras and sensors from different angles, and the obtained data is stored in a database.

[0469] The server then uses this image data to train a machine learning model. The software used leverages machine learning frameworks such as TensorFlow. The trained model will have improved capabilities to simulate various viewpoints and heights, enabling it to meet diverse requirements.

[0470] The user uses a device, such as smart glasses, to request a specific viewpoint or height. This request is entered through the device's user interface and sent to the server. The server then uses a trained machine learning model to generate an image from the new viewpoint.

[0471] This system includes motion sensors to track user behavior in real time. These sensors are gyroscopes and accelerometers built into smart glasses, and this data is sent to a server, updating the image in real time. Switching viewpoints is also smooth, providing users with an experience like walking around a virtual store from the comfort of their home.

[0472] To give a concrete example, imagine a user browsing new clothing in a virtual store. In this case, smart glasses would allow the user to view the clothing from bottom to top, and also check the design from the side. The user can easily change their viewpoint and check the details of the product.

[0473] An example of a prompt to the generating AI model is as follows: "Generate images of the new fall collection in a virtual store, viewed from a low perspective. The movement will change based on sensor information from smart glasses." In this way, the system of the present invention provides the user with a distinctive and personalized shopping experience.

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The server collects image data from tourist destinations and virtual stores. It uses cameras and sensors to capture images from various viewpoints and heights. The input for this step is product images from the tourist destination or store, and the output is a dataset of images from multiple angles and heights. The server stores this data in a database for later training.

[0477] Step 2:

[0478] The server trains a machine learning model based on the collected image data. It uses a machine learning framework such as TensorFlow. The input data is the image data obtained in the previous step, and the output is a trained model capable of generating images from different viewpoints and heights. Through training, the server obtains a model capable of generating images according to user requests.

[0479] Step 3:

[0480] The user requests image display from a specific viewpoint and height through their smart glasses. The input is request data regarding the viewpoint and height selected by the user, and the output is the request information sent to the server.

[0481] Step 4:

[0482] Based on the received request information, the server uses a trained machine learning model to generate an image based on the user's selected viewpoint and height. The input is the request data and the trained model, and the output is the generated image from the new viewpoint.

[0483] Step 5:

[0484] The server delivers the generated images to the user's device. The input is an image from a new perspective, and the output is visual data displayed on the user's smart glasses. This allows the user to examine products and scenery in detail from a perspective that suits their preferences.

[0485] Step 6:

[0486] To track user behavior in real time, the device's motion sensors are used. The gyroscope and accelerometer of smart glasses serve as inputs, and the output is motion data sent to the server.

[0487] Step 7:

[0488] The server updates the viewpoint image in real time based on the user's movement data. The input is the user's movement data, and the output is the updated viewpoint image. Through the image, which quickly reflects the changed viewpoint, the user can have an experience as if they were actually walking around the store.

[0489] 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.

[0490] This invention provides a highly personalized online tourism experience, enabling customization that takes into account not only the user's viewpoint selection but also their emotional state. This system begins with image data collection and combines it with real-time emotion analysis using an emotion engine to deliver a new level of experiential value.

[0491] The server collects image data of tourist attractions and exhibits, and uses this data to train a machine learning model. The model can generate images based on specific viewpoints and heights, and a sentiment engine can dynamically adjust the viewpoint according to the user's emotional state. The sentiment engine recognizes emotions from the user's facial expressions and voice, and analyzes the data in real time based on user feedback.

[0492] The device plays a role in receiving information from the user regarding the selection of tourist destinations, viewpoints, and emotional states. If the user wishes to consider their emotional state, they provide that information through the device. The device sends this information to the server, which then generates customized visual content based on that information.

[0493] For example, if a user is experiencing fear, the emotion engine can detect this and instruct the server to provide a calming and reassuring viewpoint. For instance, if the user is visiting a high place, the viewpoint can be lowered to provide a view from a safer position. Similarly, if a user is expressing excitement or joy, the emotion engine can select a correspondingly stimulating viewpoint to further enhance the user's experience.

[0494] In this way, the present invention can make online experiences of sightseeing and exhibits more engaging and personalized by providing a flexible visual experience that responds to the user's emotional state. This system allows users to experience a special journey that is tailored to their emotions at any given moment.

[0495] The following describes the processing flow.

[0496] Step 1:

[0497] The server collects diverse image data of tourist attractions and exhibits and stores this data in a database. This allows for the accumulation of information necessary for generating images from various viewpoints and heights.

[0498] Step 2:

[0499] The server uses the collected data to train a machine learning model. This model has the ability to generate images based on specified viewpoints and heights, and is further prepared to dynamically adjust viewpoints using an emotion engine.

[0500] Step 3:

[0501] The device receives requests from the user regarding the selection of tourist destinations and the type of viewpoint. It also collects emotional information through the user's facial expressions and voice. This information is used to customize the tourist experience.

[0502] Step 4:

[0503] The terminal sends the user's tourist destination selection, viewpoint requests, and sentiment data to the server. The server receives this data and begins the necessary processing.

[0504] Step 5:

[0505] The server uses an emotion engine to analyze the user's emotional information. The emotion engine determines the user's emotional state (e.g., joy, surprise, fear) in real time and adjusts the viewpoint based on that information.

[0506] Step 6:

[0507] The server generates images from appropriate viewpoints and heights based on the emotion engine's output. For example, if the user desires a relaxed atmosphere, it will process the image to select a calm landscape.

[0508] Step 7:

[0509] The generated image data is delivered to the device and provided to the user. The user can then interactively enjoy a visual experience that matches their emotions through the device.

[0510] Step 8:

[0511] Users can enjoy the experience and provide more detailed emotional feedback as needed. The device sends this information to the server to help improve future experiences.

[0512] (Example 2)

[0513] 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."

[0514] Conventional online sightseeing experience systems have struggled to provide flexible perspectives and highly personalized experiences that respond to users' emotional states. The limited selection of specific viewpoints and heights, along with the lack of real-time viewpoint adjustments that consider the user's emotional state, have prevented them from providing the optimal experience for each user.

[0515] 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.

[0516] In this invention, the server includes means for collecting image information, means for training a learning model based on the collected image information, and means for generating images from different viewpoints and heights based on the user's emotional state. This enables the analysis of the user's emotional information and dynamic adjustment of the individualized viewpoint.

[0517] "Image information" refers to information that includes visual data, and includes visual representations related to subjects such as tourist destinations and exhibits.

[0518] A "learning model" refers to an algorithm that learns patterns and features based on collected data and can perform inference and prediction.

[0519] "Users" refer to individuals who use the system to experience online tourism.

[0520] "Emotional state" refers to the psychological and emotional condition of a user at any given time, which can be analyzed from their facial expressions and voice.

[0521] "Perspective" refers to a specific angle or direction from which an image or experience is visually perceived.

[0522] "Height" refers to the vertical position related to the viewpoint and is an element that influences how images appear during the visual experience.

[0523] "Generating" means creating new visual content using a learning model.

[0524] "Analyzing" means investigating data in detail to understand it and extract relevant information.

[0525] This invention provides a system that highly personalizes online tourism experiences. Through the interaction of a server, a terminal, and a user, this system delivers a visual experience tailored to the user's emotional state.

[0526] The server is responsible for collecting image information of tourist attractions and exhibits. This image information is used to train a machine learning model. Specifically, it preprocesses the images and uses them to train a generative AI model. This model enables image generation based on specific viewpoints and heights. It also utilizes an emotion engine to analyze the user's emotional state and dynamically adjust the viewpoint.

[0527] The device is used to collect information from the user regarding the selection of tourist destinations, viewpoints, and emotions. The user provides their emotional state through the device, and this information is sent to the server. This allows the server to generate customized visual content based on the user's emotions.

[0528] This system allows users to have a personalized sightseeing experience tailored to their emotional state. For example, if a user is feeling fear, the system can sense this and suggest a calming and reassuring viewpoint. Specifically, when visiting high places, the system can lower the viewpoint to provide a safer perspective. Furthermore, if a user is expressing excitement or joy, the emotion engine selects a correspondingly stimulating viewpoint to enhance the experience.

[0529] A concrete example of a prompt might be text like, "Provide a quiet museum experience to enhance the user's sense of relaxation." This is used as an instruction for the generative AI model to provide a visual experience that aligns with the user's emotions.

[0530] Through this system, the present invention can provide a flexible and engaging visual experience that responds to the user's emotions, making online sightseeing and exhibition experiences even more personalized.

[0531] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0532] Step 1:

[0533] The server collects image information related to tourist attractions and exhibits from online sources. The collected data is preprocessed by resizing and denoising the images and converted into a format suitable for training a learning model. It takes raw image data as input and generates preprocessed image data as output.

[0534] Step 2:

[0535] The server trains a learning model based on pre-processed image data. During this training phase, a large amount of data is used to improve the generative AI model's ability to generate images based on specified viewpoints and heights. The input is pre-processed image data, and the output is a trained learning model.

[0536] Step 3:

[0537] The device acquires information from the user regarding the selection of tourist destinations, viewpoints, and emotions. The user provides their emotional state through the device's camera and microphone. The input consists of visual and audio data from the user, and the output consists of the user's selection information and analyzed emotion data.

[0538] Step 4:

[0539] The server analyzes the user's emotional information transmitted from the terminal. The emotion engine identifies emotions from the user's facial expressions and voice, and dynamically adjusts the viewpoint based on that. The input is the user's emotional data, and the output is information about the adjusted viewpoint. Specifically, for example, if the user is in a relaxed state, the server will be instructed to select a calm and reassuring viewpoint.

[0540] Step 5:

[0541] Based on the analysis results, the server uses a generative AI model to generate visual content optimized for the user's emotional state. An example prompt is, "Provide a quiet museum experience to enhance the user's sense of relaxation." The input consists of adjusted viewpoint information and a prompt, and the output is customized image data.

[0542] Step 6:

[0543] The device presents the generated visual content to the user. Through this content, the user can obtain a personalized sightseeing experience. Specifically, the device's display shows generated visual information, which the user then views. The input is generated image data from the server, and the output is the user's visual experience.

[0544] (Application Example 2)

[0545] 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."

[0546] Traditional online tourism experience systems have struggled to personalize experiences based on users' emotional states, limiting the quality of the experience. Furthermore, they lacked dynamic adjustments of visual content based on user emotions, failing to provide a deeper level of satisfaction. This made it difficult to meet the diverse needs of users.

[0547] 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.

[0548] In this invention, the server includes means for collecting image data, means for training a machine learning model based on the collected image data, means for analyzing the user's emotional state, means for generating images from different viewpoints and heights based on the emotional state and the user's requests, and means for delivering the generated images to the user. This makes it possible to take the user's emotional state into consideration and highly customize the online sightseeing experience.

[0549] "Image data" refers to a collection of visual information stored in digital format, used to generate visual content from diverse viewpoints and heights.

[0550] A "machine learning model" is a computational algorithm that learns patterns from data and performs predictions or classifications for specific tasks.

[0551] "User emotional state" refers to the state of the user's psychological and emotional responses, which is determined in real time from facial expressions, voice, and other factors.

[0552] "Means for generating images from different viewpoints and heights" refers to a system or technology for creating visual content from diverse angles and positions based on user requirements.

[0553] "Means of distribution to users" refers to methods or devices for transferring and displaying generated visual content on a user's device.

[0554] A "three-dimensional model" is a three-dimensional digital structure that geometrically represents actual space and objects.

[0555] "User characteristics" refer to attribute information and preference data about users, which are used to provide personalized experiences.

[0556] This invention is a technology for personalizing online tourism experiences and provides a system that enables advanced customization that takes into account the user's emotional state. This system mainly consists of a server and a user terminal.

[0557] The server collects image data of tourist attractions or exhibits and uses it to train a machine learning model. The machine learning model is built using deep learning frameworks such as TensorFlow or PyTorch and has the ability to generate images from different viewpoints and heights. It also utilizes facial recognition and speech recognition technologies, and an emotion engine analyzes the user's emotional state in real time. Image processing libraries such as OpenCV can be used for emotion analysis.

[0558] The user's device, such as smart glasses or a smartphone, is responsible for capturing the user's facial expressions and voice. These devices transmit the collected data to a server, which then analyzes it to provide a customized visual experience tailored to the user's emotional state.

[0559] For example, if a user expresses fear, the server, based on the analysis of the emotion engine, generates and provides a calmer perspective that provides a greater sense of security. Conversely, if a user expresses joy, it selects a stimulating perspective that promotes excitement. This allows users to have the optimal experience according to their emotions at that moment.

[0560] Examples of prompts include, "Please suggest travel items that would be suitable for a user who is relaxed." By using such prompts, generative AI models can provide excellent suggestions tailored to the user's emotional state.

[0561] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0562] Step 1:

[0563] The device collects the user's facial expressions and voice data. This data is acquired using the built-in camera and microphone. This provides the input data necessary for emotion analysis.

[0564] Step 2:

[0565] The device transmits collected facial expression and voice data to the server. The data is transferred in real time via a secure protocol and used for analysis by the server's emotion engine.

[0566] Step 3:

[0567] The server uses the received data to analyze the user's emotional state using an emotion engine. In this process, facial features are extracted using the OpenCV library, and a machine learning model estimates the emotion. For example, if the facial feature obtained as a feature is recognized as a "smile," the emotion is determined to be "joy."

[0568] Step 4:

[0569] The server generates appropriate visual content based on the sentiment analysis results. This process uses machine learning models to create images from specific viewpoints and heights that correspond to the user's emotional state.

[0570] Step 5:

[0571] The server delivers the generated, customized visual content to the device. The visual content is optimized and displayed for the device the user is using.

[0572] Step 6:

[0573] Users experience visual content delivered through their devices. During this stage, users can continuously provide emotional information to their devices, and the server further adjusts the content based on this new data. This enables a dynamically personalized tourism experience.

[0574] 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.

[0575] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0576] 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.

[0577] [Fourth Embodiment]

[0578] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0579] 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.

[0580] 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).

[0581] 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.

[0582] 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.

[0583] 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).

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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".

[0591] This invention is a system for highly personalizing online experiences of tourist destinations and exhibits, and consists of processes including image data collection, utilization of machine learning models, and generation and distribution of images based on user requests.

[0592] The server first collects image data taken from tourist destinations at various viewpoints and heights. This data is stored in a database and used to train a machine learning model. The model is optimized to enhance its ability to simulate different viewpoints and heights. This makes it possible to provide high-quality images when users select their desired viewpoint and height.

[0593] The device receives requests from the user regarding the selection of tourist destinations and types of viewpoints. This request information is sent to the server, where the corresponding image data is processed. The server uses a trained machine learning model to generate native images based on the specific viewpoint and height. The generated content is delivered to the device, allowing the user to explore tourist destinations online while changing the viewpoint and height to suit their preferences.

[0594] For example, if a user wants to enjoy an online tour with their child, they can select "child's perspective" on their device. Based on the relevant data, the server generates images from a lower viewpoint, providing a new visual experience for the family. In this way, the system is designed to meet diverse user needs, allowing individual users to obtain a customized experience according to their situation and purpose.

[0595] By implementing this invention, users can enjoy a more realistic and personalized experience compared to conventional online tourism experiences. This provides a visual breadth that transcends the limitations of tourist destinations, and serves as a new solution for providing a rich tourism experience even to users who find it difficult to actually visit.

[0596] The following describes the processing flow.

[0597] Step 1:

[0598] The server collects image data of tourist attractions and exhibits taken from multiple viewpoints and various heights. This data is stored in a database and used to train models.

[0599] Step 2:

[0600] The server uses the collected image data to train a machine learning model. This model is optimized using deep learning techniques to generate views based on different viewpoints and heights.

[0601] Step 3:

[0602] Users select tourist destinations via their devices and make requests regarding specific viewpoints or heights. This includes options such as a child's eye level or a wheelchair user's eye level.

[0603] Step 4:

[0604] The terminal sends user request information to the server and requests processing. The server reads the corresponding image data from the database.

[0605] Step 5:

[0606] The server uses a trained model to generate images from new viewpoints that meet the user's requested viewpoint and height conditions. This utilizes three-dimensional reconstruction technology to create a continuous visual experience.

[0607] Step 6:

[0608] The generated image data is delivered to the user's device. The device displays this data through an interactive user interface, allowing the user to explore while adjusting their viewpoint and height.

[0609] Step 7:

[0610] Users can enjoy the provided visual experience and make further requests based on their interests and preferences. They can also provide feedback based on their experience through their device.

[0611] (Example 1)

[0612] 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".

[0613] In traditional online tourism experiences, users were limited to images from fixed viewpoints or altitudes, resulting in a restricted visual experience. Furthermore, it was difficult to fully meet the individual needs of users, leading to a uniform user experience.

[0614] 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.

[0615] In this invention, the server includes means for collecting image information, means for training an automated learning model based on the collected image information, and means for creating visual representations from different viewpoints and heights based on user requests. This makes it possible for users to obtain customized visual experiences from various viewpoints and heights.

[0616] "Methods for collecting image information" refer to techniques for photographing tourist destinations and exhibits from diverse viewpoints and heights, and collecting that data.

[0617] "Methods for training automated learning models" refer to techniques for optimizing machine learning models to improve their ability to simulate different viewpoints and heights based on collected image information.

[0618] "A means of creating visual representations from different viewpoints and heights based on user requests" refers to a technology that generates high-quality images using a pre-trained machine learning model in response to user requests.

[0619] "Means of providing created visual representations to users" refers to technologies that quickly and efficiently deliver generated content to users' devices.

[0620] A "terminal that receives requests from users" is a device that allows users to input their selection of tourist destinations and types of viewpoints, and then sends that information to a server.

[0621] "Means for processing prompt statements" refers to techniques for generating appropriate visual representations by converting user requests into a specific format and inputting them into a model.

[0622] This invention is a system that highly personalizes online experiences of tourist destinations and exhibits. Its main components are a server and a terminal, and it provides high-quality visual representations tailored to user requests, thereby realizing an experience suited to each individual user.

[0623] The server first collects image information from tourist attractions and exhibits. To do this, it uses cameras and drones to capture images from various viewpoints and heights. The collected image information is then stored in a database.

[0624] Next, the server trains an automated learning model. The model is trained using collected image data to improve its ability to simulate different viewpoints and heights. A machine learning framework (e.g., TensorFlow or PyTorch) is used for this.

[0625] A terminal is a device that receives requests from users. Mobile and web applications are provided to allow users to specify tourist destinations and viewpoint types. This information is sent to the server.

[0626] Users experience customized visual representations provided by the server based on their requests. Specifically, users input prompts such as "I want to see the Eiffel Tower from a child's perspective" into their terminal, and the server uses a model to generate appropriate images and delivers them to the user. This allows users to visually explore tourist destinations from a perspective that suits their preferences.

[0627] As a result, this system enables users to have a personalized and realistic online sightseeing experience that goes beyond simply providing images. This technology also provides a means of offering new experiences to users who are in situations where visiting in person is difficult.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1:

[0630] The server collects image information from tourist attractions and exhibits. The input is raw data captured using cameras and drones, and the output is unprocessed image information stored in a database. This process ensures information diversity by collecting images from various viewpoints and altitudes.

[0631] Step 2:

[0632] The server preprocesses the collected image information. The input here is raw image information stored in a database, and the output is training data suitable for machine learning models. In this step, the quality of the data is improved by adjusting the image resolution and denoising.

[0633] Step 3:

[0634] The server trains an automated learning model using preprocessed data. The input here is the preprocessed training data, and the output is a machine learning model capable of simulating viewpoints and altitude. This process utilizes machine learning frameworks (e.g., TensorFlow and PyTorch) to efficiently build and optimize the model.

[0635] Step 4:

[0636] The terminal receives requests from the user. The input here is the user's request regarding tourist destinations or viewpoints, and the output is the specific request data sent to the server. This operation utilizes the interfaces of mobile or web applications.

[0637] Step 5:

[0638] The server processes prompt messages based on user requests and generates appropriate visual representations. The input here is request data sent from the terminal and the corresponding prompt messages, while the output is a high-quality image corresponding to the user's request. This step utilizes a trained machine learning model to generate images at specified viewpoints and altitudes.

[0639] Step 6:

[0640] The server delivers the generated visual representation to the terminal. The input here is the generated high-quality image, and the output is the visual content the user receives in real time. This delivery utilizes efficient streaming technologies and CDN services to ensure a smooth user experience.

[0641] Step 7:

[0642] The user experiences a visual representation delivered via their device. The input here is the visual content delivered from the server, and the output is the user's satisfaction with the visual experience. In this final step, the user can freely select various viewpoints and altitudes to virtually explore the tourist destination.

[0643] (Application Example 1)

[0644] 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".

[0645] Traditional online shopping systems have the drawback of making it difficult for users to view products in detail from multiple angles, and the limited visual information makes product selection more challenging compared to the in-store shopping experience. Furthermore, there is a lack of systems capable of real-time display that reflects user movements and perspectives.

[0646] 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.

[0647] In this invention, the server includes means for collecting image data, means for training a machine learning model based on the collected image data, and means for tracking the user's movements with a motion sensor and updating the viewpoint image in real time based on the transmitted motion data. This allows the user to observe products in detail from various angles in a virtual store, as if walking around the store.

[0648] "Methods for collecting image data" refer to methods of photographing tourist destinations or products within virtual stores from various viewpoints and heights, and then accumulating that information.

[0649] "Methods for training machine learning models" refer to the process of using collected image data to teach a computer about changes in viewpoint and height.

[0650] "A means of generating images from different viewpoints and heights based on user requests" refers to a technology that uses a machine learning model to create images from new viewpoints and heights according to user specifications.

[0651] "Means of delivering generated images to users" refers to a system that sends the created images to the user's device and provides a visual experience.

[0652] A "mobility tracking sensor for users" is a device that senses a user's movements and location and collects that information in real time.

[0653] "A means of updating the viewpoint image in real time based on transmitted motion data" refers to a technology that dynamically switches images in response to the user's movements.

[0654] The system that realizes this application provides users with a personalized visual experience in tourist destinations and virtual stores. The server first collects image data of products in tourist destinations and stores, taken from various viewpoints and heights. This collection is done using multiple cameras and sensors from different angles, and the obtained data is stored in a database.

[0655] The server then uses this image data to train a machine learning model. The software used leverages machine learning frameworks such as TensorFlow. The trained model will have improved capabilities to simulate various viewpoints and heights, enabling it to meet diverse requirements.

[0656] The user uses a device, such as smart glasses, to request a specific viewpoint or height. This request is entered through the device's user interface and sent to the server. The server then uses a trained machine learning model to generate an image from the new viewpoint.

[0657] This system includes motion sensors to track user behavior in real time. These sensors are gyroscopes and accelerometers built into smart glasses, and this data is sent to a server, updating the image in real time. Switching viewpoints is also smooth, providing users with an experience like walking around a virtual store from the comfort of their home.

[0658] To give a concrete example, imagine a user browsing new clothing in a virtual store. In this case, smart glasses would allow the user to view the clothing from bottom to top, and also check the design from the side. The user can easily change their viewpoint and check the details of the product.

[0659] An example of a prompt to the generating AI model is as follows: "Generate images of the new fall collection in a virtual store, viewed from a low perspective. The movement will change based on sensor information from smart glasses." In this way, the system of the present invention provides the user with a distinctive and personalized shopping experience.

[0660] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0661] Step 1:

[0662] The server collects image data from tourist destinations and virtual stores. It uses cameras and sensors to capture images from various viewpoints and heights. The input for this step is product images from the tourist destination or store, and the output is a dataset of images from multiple angles and heights. The server stores this data in a database for later training.

[0663] Step 2:

[0664] The server trains a machine learning model based on the collected image data. It uses a machine learning framework such as TensorFlow. The input data is the image data obtained in the previous step, and the output is a trained model capable of generating images from different viewpoints and heights. Through training, the server obtains a model capable of generating images according to user requests.

[0665] Step 3:

[0666] The user requests image display from a specific viewpoint and height through their smart glasses. The input is request data regarding the viewpoint and height selected by the user, and the output is the request information sent to the server.

[0667] Step 4:

[0668] Based on the received request information, the server uses a trained machine learning model to generate an image based on the user's selected viewpoint and height. The input is the request data and the trained model, and the output is the generated image from the new viewpoint.

[0669] Step 5:

[0670] The server delivers the generated images to the user's device. The input is an image from a new perspective, and the output is visual data displayed on the user's smart glasses. This allows the user to examine products and scenery in detail from a perspective that suits their preferences.

[0671] Step 6:

[0672] To track user behavior in real time, the device's motion sensors are used. The gyroscope and accelerometer of smart glasses serve as inputs, and the output is motion data sent to the server.

[0673] Step 7:

[0674] The server updates the viewpoint image in real time based on the user's movement data. The input is the user's movement data, and the output is the updated viewpoint image. Through the image, which quickly reflects the changed viewpoint, the user can have an experience as if they were actually walking around the store.

[0675] 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.

[0676] This invention provides a highly personalized online tourism experience, enabling customization that takes into account not only the user's viewpoint selection but also their emotional state. This system begins with image data collection and combines it with real-time emotion analysis using an emotion engine to deliver a new level of experiential value.

[0677] The server collects image data of tourist attractions and exhibits, and uses this data to train a machine learning model. The model can generate images based on specific viewpoints and heights, and a sentiment engine can dynamically adjust the viewpoint according to the user's emotional state. The sentiment engine recognizes emotions from the user's facial expressions and voice, and analyzes the data in real time based on user feedback.

[0678] The device plays a role in receiving information from the user regarding the selection of tourist destinations, viewpoints, and emotional states. If the user wishes to consider their emotional state, they provide that information through the device. The device sends this information to the server, which then generates customized visual content based on that information.

[0679] For example, if a user is experiencing fear, the emotion engine can detect this and instruct the server to provide a calming and reassuring viewpoint. For instance, if the user is visiting a high place, the viewpoint can be lowered to provide a view from a safer position. Similarly, if a user is expressing excitement or joy, the emotion engine can select a correspondingly stimulating viewpoint to further enhance the user's experience.

[0680] In this way, the present invention can make online experiences of sightseeing and exhibits more engaging and personalized by providing a flexible visual experience that responds to the user's emotional state. This system allows users to experience a special journey that is tailored to their emotions at any given moment.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] The server collects diverse image data of tourist attractions and exhibits and stores this data in a database. This allows for the accumulation of information necessary for generating images from various viewpoints and heights.

[0684] Step 2:

[0685] The server uses the collected data to train a machine learning model. This model has the ability to generate images based on specified viewpoints and heights, and is further prepared to dynamically adjust viewpoints using an emotion engine.

[0686] Step 3:

[0687] The device receives requests from the user regarding the selection of tourist destinations and the type of viewpoint. It also collects emotional information through the user's facial expressions and voice. This information is used to customize the tourist experience.

[0688] Step 4:

[0689] The terminal sends the user's tourist destination selection, viewpoint requests, and sentiment data to the server. The server receives this data and begins the necessary processing.

[0690] Step 5:

[0691] The server uses an emotion engine to analyze the user's emotional information. The emotion engine determines the user's emotional state (e.g., joy, surprise, fear) in real time and adjusts the viewpoint based on that information.

[0692] Step 6:

[0693] The server generates images from appropriate viewpoints and heights based on the emotion engine's output. For example, if the user desires a relaxed atmosphere, it will process the image to select a calm landscape.

[0694] Step 7:

[0695] The generated image data is delivered to the device and provided to the user. The user can then interactively enjoy a visual experience that matches their emotions through the device.

[0696] Step 8:

[0697] Users can enjoy the experience and provide more detailed emotional feedback as needed. The device sends this information to the server to help improve future experiences.

[0698] (Example 2)

[0699] 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".

[0700] Conventional online sightseeing experience systems have struggled to provide flexible perspectives and highly personalized experiences that respond to users' emotional states. The limited selection of specific viewpoints and heights, along with the lack of real-time viewpoint adjustments that consider the user's emotional state, have prevented them from providing the optimal experience for each user.

[0701] 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.

[0702] In this invention, the server includes means for collecting image information, means for training a learning model based on the collected image information, and means for generating images from different viewpoints and heights based on the user's emotional state. This enables the analysis of the user's emotional information and dynamic adjustment of the individualized viewpoint.

[0703] "Image information" refers to information that includes visual data, and includes visual representations related to subjects such as tourist destinations and exhibits.

[0704] A "learning model" refers to an algorithm that learns patterns and features based on collected data and can perform inference and prediction.

[0705] "Users" refer to individuals who use the system to experience online tourism.

[0706] "Emotional state" refers to the psychological and emotional condition of a user at any given time, which can be analyzed from their facial expressions and voice.

[0707] "Perspective" refers to a specific angle or direction from which an image or experience is visually perceived.

[0708] "Height" refers to the vertical position related to the viewpoint and is an element that influences how images appear during the visual experience.

[0709] "Generating" means creating new visual content using a learning model.

[0710] "Analyzing" means investigating data in detail to understand it and extract relevant information.

[0711] This invention provides a system that highly personalizes online tourism experiences. Through the interaction of a server, a terminal, and a user, this system delivers a visual experience tailored to the user's emotional state.

[0712] The server is responsible for collecting image information of tourist attractions and exhibits. This image information is used to train a machine learning model. Specifically, it preprocesses the images and uses them to train a generative AI model. This model enables image generation based on specific viewpoints and heights. It also utilizes an emotion engine to analyze the user's emotional state and dynamically adjust the viewpoint.

[0713] The device is used to collect information from the user regarding the selection of tourist destinations, viewpoints, and emotions. The user provides their emotional state through the device, and this information is sent to the server. This allows the server to generate customized visual content based on the user's emotions.

[0714] This system allows users to have a personalized sightseeing experience tailored to their emotional state. For example, if a user is feeling fear, the system can sense this and suggest a calming and reassuring viewpoint. Specifically, when visiting high places, the system can lower the viewpoint to provide a safer perspective. Furthermore, if a user is expressing excitement or joy, the emotion engine selects a correspondingly stimulating viewpoint to enhance the experience.

[0715] A concrete example of a prompt might be text like, "Provide a quiet museum experience to enhance the user's sense of relaxation." This is used as an instruction for the generative AI model to provide a visual experience that aligns with the user's emotions.

[0716] Through this system, the present invention can provide a flexible and engaging visual experience that responds to the user's emotions, making online sightseeing and exhibition experiences even more personalized.

[0717] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0718] Step 1:

[0719] The server collects image information related to tourist attractions and exhibits from online sources. The collected data is preprocessed by resizing and denoising the images and converted into a format suitable for training a learning model. It takes raw image data as input and generates preprocessed image data as output.

[0720] Step 2:

[0721] The server trains a learning model based on pre-processed image data. During this training phase, a large amount of data is used to improve the generative AI model's ability to generate images based on specified viewpoints and heights. The input is pre-processed image data, and the output is a trained learning model.

[0722] Step 3:

[0723] The device acquires information from the user regarding the selection of tourist destinations, viewpoints, and emotions. The user provides their emotional state through the device's camera and microphone. The input consists of visual and audio data from the user, and the output consists of the user's selection information and analyzed emotion data.

[0724] Step 4:

[0725] The server analyzes the user's emotional information transmitted from the terminal. The emotion engine identifies emotions from the user's facial expressions and voice, and dynamically adjusts the viewpoint based on that. The input is the user's emotional data, and the output is information about the adjusted viewpoint. Specifically, for example, if the user is in a relaxed state, the server will be instructed to select a calm and reassuring viewpoint.

[0726] Step 5:

[0727] Based on the analysis results, the server uses a generative AI model to generate visual content optimized for the user's emotional state. An example prompt is, "Provide a quiet museum experience to enhance the user's sense of relaxation." The input consists of adjusted viewpoint information and a prompt, and the output is customized image data.

[0728] Step 6:

[0729] The device presents the generated visual content to the user. Through this content, the user can obtain a personalized sightseeing experience. Specifically, the device's display shows generated visual information, which the user then views. The input is generated image data from the server, and the output is the user's visual experience.

[0730] (Application Example 2)

[0731] 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".

[0732] Traditional online tourism experience systems have struggled to personalize experiences based on users' emotional states, limiting the quality of the experience. Furthermore, they lacked dynamic adjustments of visual content based on user emotions, failing to provide a deeper level of satisfaction. This made it difficult to meet the diverse needs of users.

[0733] 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.

[0734] In this invention, the server includes means for collecting image data, means for training a machine learning model based on the collected image data, means for analyzing the user's emotional state, means for generating images from different viewpoints and heights based on the emotional state and the user's requests, and means for delivering the generated images to the user. This makes it possible to take the user's emotional state into consideration and highly customize the online sightseeing experience.

[0735] "Image data" refers to a collection of visual information stored in digital format, used to generate visual content from diverse viewpoints and heights.

[0736] A "machine learning model" is a computational algorithm that learns patterns from data and performs predictions or classifications for specific tasks.

[0737] "User emotional state" refers to the state of the user's psychological and emotional responses, which is determined in real time from facial expressions, voice, and other factors.

[0738] "Means for generating images from different viewpoints and heights" refers to a system or technology for creating visual content from diverse angles and positions based on user requirements.

[0739] "Means of distribution to users" refers to methods or devices for transferring and displaying generated visual content on a user's device.

[0740] A "three-dimensional model" is a three-dimensional digital structure that geometrically represents actual space and objects.

[0741] "User characteristics" refer to attribute information and preference data about users, which are used to provide personalized experiences.

[0742] This invention is a technology for personalizing online tourism experiences and provides a system that enables advanced customization that takes into account the user's emotional state. This system mainly consists of a server and a user terminal.

[0743] The server collects image data of tourist attractions or exhibits and uses it to train a machine learning model. The machine learning model is built using deep learning frameworks such as TensorFlow or PyTorch and has the ability to generate images from different viewpoints and heights. It also utilizes facial recognition and speech recognition technologies, and an emotion engine analyzes the user's emotional state in real time. Image processing libraries such as OpenCV can be used for emotion analysis.

[0744] The user's device, such as smart glasses or a smartphone, is responsible for capturing the user's facial expressions and voice. These devices transmit the collected data to a server, which then analyzes it to provide a customized visual experience tailored to the user's emotional state.

[0745] For example, if a user expresses fear, the server, based on the analysis of the emotion engine, generates and provides a calmer perspective that provides a greater sense of security. Conversely, if a user expresses joy, it selects a stimulating perspective that promotes excitement. This allows users to have the optimal experience according to their emotions at that moment.

[0746] Examples of prompts include, "Please suggest travel items that would be suitable for a user who is relaxed." By using such prompts, generative AI models can provide excellent suggestions tailored to the user's emotional state.

[0747] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0748] Step 1:

[0749] The device collects the user's facial expressions and voice data. This data is acquired using the built-in camera and microphone. This provides the input data necessary for emotion analysis.

[0750] Step 2:

[0751] The device transmits collected facial expression and voice data to the server. The data is transferred in real time via a secure protocol and used for analysis by the server's emotion engine.

[0752] Step 3:

[0753] The server uses the received data to analyze the user's emotional state using an emotion engine. In this process, facial features are extracted using the OpenCV library, and a machine learning model estimates the emotion. For example, if the facial feature obtained as a feature is recognized as a "smile," the emotion is determined to be "joy."

[0754] Step 4:

[0755] The server generates appropriate visual content based on the sentiment analysis results. This process uses machine learning models to create images from specific viewpoints and heights that correspond to the user's emotional state.

[0756] Step 5:

[0757] The server delivers the generated, customized visual content to the device. The visual content is optimized and displayed for the device the user is using.

[0758] Step 6:

[0759] Users experience visual content delivered through their devices. During this stage, users can continuously provide emotional information to their devices, and the server further adjusts the content based on this new data. This enables a dynamically personalized tourism experience.

[0760] 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.

[0761] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0762] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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 based, for example, 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.

[0768] 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."

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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 to be incorporated by reference.

[0781] The following is further disclosed regarding the embodiments described above.

[0782] (Claim 1)

[0783] Means for collecting image data,

[0784] A method for training a machine learning model based on collected image data,

[0785] A means for generating images from different viewpoints and heights based on user requests,

[0786] A means of delivering the generated images to the user,

[0787] A system that includes this.

[0788] (Claim 2)

[0789] The system according to claim 1, further comprising means for reconstructing a three-dimensional model of a tourist destination based on the user's location information and field of view requirements.

[0790] (Claim 3)

[0791] The system according to claim 1, further comprising means for providing multiple viewpoint options according to different user attributes in order to customize the user's viewpoint experience.

[0792] "Example 1"

[0793] (Claim 1)

[0794] Means of collecting image information,

[0795] A method for training an automated learning model based on collected image information,

[0796] A means of creating visual representations from different viewpoints and heights based on user requests,

[0797] Means for providing the created visual representation to users,

[0798] A terminal that receives requests from users,

[0799] A means for processing prompt statements to generate a visual representation based on a request,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, further comprising means for reconstructing the three-dimensional structure of a tourist destination based on the user's spatial information and field of view requirements.

[0803] (Claim 3)

[0804] The system according to claim 1, further comprising means for providing multiple viewpoint options according to different user attributes in order to adjust the user's viewpoint experience.

[0805] "Application Example 1"

[0806] (Claim 1)

[0807] Means for collecting image data,

[0808] A method for training a machine learning model based on collected image data,

[0809] A means for generating images from different viewpoints and heights based on user requests,

[0810] A means of delivering the generated images to the user,

[0811] A motion sensor that tracks the user's movements, and means for updating the viewpoint image in real time based on transmitted motion data,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, further comprising means for reconstructing a three-dimensional model of a tourist destination based on the user's location information and field of view requirements.

[0815] (Claim 3)

[0816] The system according to claim 1, further comprising means for providing multiple viewpoint options according to different user attributes in order to customize the user's viewpoint experience.

[0817] "Example 2 of combining an emotion engine"

[0818] (Claim 1)

[0819] Means for collecting image information,

[0820] A method for training a learning model based on collected image information,

[0821] A means for generating images from different viewpoints and heights based on the user's emotional state,

[0822] Means for providing the generated images to the user,

[0823] A means of dynamically adjusting the perspective by analyzing the user's emotional information,

[0824] A means of receiving user choices and emotional information from the device,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, further comprising means for reconstructing the three-dimensional structure of a tourist area based on the user's location information and field of view requirements.

[0828] (Claim 3)

[0829] The system according to claim 1, further comprising means for providing multiple viewpoint options according to different user characteristics in order to customize the user's viewpoint experience.

[0830] "Application example 2 when combining with an emotional engine"

[0831] (Claim 1)

[0832] Means for collecting image data,

[0833] A method for training a machine learning model based on collected image data,

[0834] A means of analyzing the emotional state of users,

[0835] A means for generating images from different viewpoints and heights based on emotional state and user requests,

[0836] A means of distributing the generated images to users,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, further comprising means for reconstructing a three-dimensional model of a tourist destination based on the user's location information and field of view requirements.

[0840] (Claim 3)

[0841] The system according to claim 1, further comprising means for adjusting the viewpoint according to the user's emotional state and providing multiple viewpoint options according to different user characteristics. [Explanation of Symbols]

[0842] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting image data, A method for training a machine learning model based on collected image data, A means for generating images from different viewpoints and heights based on user requests, A means of delivering the generated images to the user, A system that includes this.

2. The system according to claim 1, further comprising means for reconstructing a three-dimensional model of a tourist destination based on the user's location information and field of view requirements.

3. The system according to claim 1, further comprising means for providing multiple viewpoint options according to different user attributes in order to customize the user's viewpoint experience.

Images