System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving two-dimensional data from a user terminal; means for analyzing the received two-dimensional data to extract feature information; means for generating a three-dimensional model by a generative AI based on the extracted feature information; means for transmitting the generated three-dimensional model to the user terminal; and means for displaying the three-dimensional model received by the user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Existing 2D data, especially information on weather, news, maps, etc., has visual limitations that make it difficult for users to understand intuitively. As augmented reality (AR) devices become more widespread, simply displaying 2D data reduces usability. Furthermore, creating 3D models typically requires manual modeling, which is time-consuming and resource-intensive. It is necessary to solve this problem by efficiently and automatically generating 3D models that can be easily used with devices such as AR glasses. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: a system including means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, means for generating a 3D model using a generation AI based on the extracted feature information, means for transmitting the generated 3D model to the user terminal, and means for displaying the received 3D model on the user terminal. This system automatically generates a 3D model based on 2D data, allowing users to use information in a visually easy-to-understand manner using an AR device, etc. Furthermore, manual modeling is no longer necessary, saving time and resources.

[0006] A "user terminal" is an electronic device that a user operates to input and receive information.

[0007] "Two-dimensional data" is a flat data format that includes information such as weather, news, and maps.

[0008] "Receiving" is the process of getting data from another device or system.

[0009] "Analysis" is the process of examining and evaluating acquired data in detail to extract necessary information.

[0010] "Feature information" is information that has a particular meaning or importance and is extracted from the analyzed data.

[0011] "Generative AI" is a system that uses artificial intelligence technology to generate new models and information from input data.

[0012] A "3D model" is a three-dimensional data model expressed in three-dimensional space.

[0013] "Transmitting" is the process of transferring data to another device or system.

[0014] "Optimization" is the process of improving and adjusting generated or analyzed data or models to make them suitable for a specific purpose.

[0015] "Display" is the process of presenting data or models visually to a user. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] To implement this invention, a system using a user terminal, a server, a generation AI, and the Internet is required. Below, the processing of the programs that make up this system will be explained in detail in natural language.

[0038] Overall system configuration

[0039] 1. User Device

[0040] The device operated by the user (smartphone, tablet, AR glasses, etc.) uses a dedicated application to acquire 2D data and send it to the server. The specific data input by the user includes information such as weather, news, and maps.

[0041] Example: A user opens a smartphone application and taps the "Get Weather Information" button to get weather information.

[0042] 2. Server

[0043] The server receives the 2D data sent from the user's device, analyzes it, and extracts the necessary feature information. It then inputs the extracted feature information into a generation AI, which automatically generates a 3D model. The generated 3D model is then further optimized and converted into a format suitable for the user's device. The generated 3D model is then sent to the user's device.

[0044] Example: A server receives weather information sent from a smartphone app, analyzes and extracts data such as temperature, humidity, and wind speed, and inputs that data into a generative AI to generate a 3D weather forecast model.

[0045] 3. Generation AI

[0046] Generative AI is responsible for generating 3D models based on datasets provided by the server. For example, it generates 3D models that visually represent cloud movement and temperature distribution based on weather data.

[0047] Example: Generative AI takes temperature, humidity, and wind speed data as input and generates a 3D model to visualize real-time weather forecasts.

[0048] 4. Distribution and display on devices

[0049] The server optimizes the generated 3D model, converts it into an appropriate format, and sends it to the user's device, where it displays the received 3D model, allowing the user to view it in real time.

[0050] Example: The optimized 3D weather model is sent to the AR glasses, allowing users to see the real-time weather forecast in 3D through the glasses.

[0051] Specific examples

[0052] 3D model generation for weather forecasts

[0053] 1. The user taps the "Get Weather Information" button on the smartphone app.

[0054] 2. The device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server.

[0055] 3. The server receives the JSON data and analyzes and extracts the necessary weather information (temperature, humidity, wind speed, precipitation probability, etc.).

[0056] 4. Based on the weather information extracted by the server, a dataset is created to be input into the generation AI and sent to the generation AI.

[0057] 5. The generative AI generates a 3D model of the weather forecast based on the input dataset and returns the results to the server.

[0058] 6. The server converts the received 3D model into GLTF format and sends it to the device (such as AR glasses).

[0059] 7. The device renders the received 3D model and visually displays it to the user, allowing the user to see a real-time weather forecast in 3D.

[0060] The system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI, manual model creation is no longer necessary, enabling fast and efficient information visualization.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user opens the dedicated application, selects the type of 2D data they want to acquire, and taps the "Get Weather Information" button.

[0064] Step 2:

[0065] The device accesses the weather information API and sends a request to the server, which includes location information, the current time, and other information.

[0066] Step 3:

[0067] The server receives 2D data from a weather information API, usually in JSON format, including information such as temperature, humidity, wind speed, and chance of precipitation.

[0068] Step 4:

[0069] The server analyzes the received JSON data and extracts the necessary characteristic information (temperature, humidity, wind speed, probability of precipitation, etc.).

[0070] Step 5:

[0071] The server creates a dataset based on the extracted feature information to be input into the generative AI. The dataset contains each element of weather information.

[0072] Step 6:

[0073] The server sends the dataset to the generation AI, which then starts the process of generating a 3D model. The generation AI generates a 3D weather forecast model based on the input weather data.

[0074] Step 7:

[0075] The generation AI returns the generated 3D model to the server, which then optimizes the received 3D model and converts it into a display format (e.g., GLTF format).

[0076] Step 8:

[0077] The server sends the optimized 3D model to the device.

[0078] Step 9:

[0079] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Through the AR glasses, the user can check the real-time weather forecast in 3D.

[0080] Step 10:

[0081] If necessary, the user can interact with the displayed 3D model, for example, by moving the time forward or backward to check future or past weather information.

[0082] Example 1

[0083] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0084] In today's information society, there is a growing need for a more intuitive and visual understanding of real-time information such as weather forecasts, news, and map information. However, traditional 2D data often makes it difficult to understand the information, and there is a need for technology to provide information in a format that is easy for users to understand. In particular, there is a lack of technology to efficiently generate 3D models and provide them in a format suitable for the device used by the user. To solve this issue, it is necessary to utilize more advanced data analysis and generative AI technology to quickly and effectively provide 3D models compatible with user devices.

[0085] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0086] In this invention, the server includes means for receiving 2D data from a user terminal, means for the user terminal to acquire 2D data from an external database and transmit it to the server, means for analyzing the received 2D data and extracting feature information, means for generating a 3D model using a generation AI based on the extracted feature information, means for the server to optimize the generated 3D model, convert it into a display format, and transmit it to the user terminal, and means for displaying the received 3D model on the user terminal. This allows information to be understood intuitively and visually, and makes it possible to efficiently generate and optimize 3D models and provide them in a form suitable for the user terminal.

[0087] A "user terminal" is a terminal operated by a user, and includes devices such as smartphones, tablets, and AR glasses.

[0088] "Two-dimensional data" is data that includes information such as weather, news, and maps, and is a data format that users acquire and send.

[0089] An "external database" is a repository of data that can be accessed via the Internet, such as a weather API or news API.

[0090] The "server" is a central processing unit that receives and analyzes data sent from the user terminal and provides the data to the generation AI.

[0091] "Feature information" is specific information such as temperature, humidity, and wind speed that is extracted by analyzing the two-dimensional data sent from the user terminal.

[0092] "Generative AI" is an artificial intelligence technology for generating 3D models based on feature information provided by a server.

[0093] A "3D model" is visually represented three-dimensional information generated based on 2D data and feature information.

[0094] A "display format" is a data format for appropriately displaying a 3D model on a user terminal, and includes the GLTF format.

[0095] "Optimization" is the process of streamlining the data volume and structure of the generated 3D model and converting it into a form suitable for the user's device.

[0096] "Rendering" is a process for visually displaying a 3D model received by a user terminal.

[0097] MODE FOR CARRYING OUT THE INVENTION

[0098] To implement this invention, a system using a user terminal, a server, a generation AI, and the Internet is required. Below, the processing of the programs that make up this system will be explained in detail in natural language.

[0099] Overall system configuration

[0100] User terminal

[0101] A dedicated application is installed on the user's device (smartphone, tablet, AR glasses, etc.). This application acquires 2D data from the user and sends it to the server. Specifically, when the user taps the "Get Weather Information" button, a request is sent to the weather API, current weather information is acquired, and it is sent to the server.

[0102] server

[0103] The server receives and analyzes the 2D data sent from the user's device. During the analysis, feature information such as temperature, humidity, and wind speed is extracted. The analysis is performed using the Python pandas library. A dataset is then created based on the extracted feature information and sent to the generation AI.

[0104] Generation AI

[0105] The generative AI generates a 3D model based on the dataset provided by the server. This generation process uses deep learning libraries such as TENSORFLOW (registered trademark) and PyTorch. The generated 3D model visually represents, for example, cloud movement and temperature distribution.

[0106] Distribution and display on terminals

[0107] The server optimizes the generated 3D model and converts it into a format suitable for the user device (e.g., GLTF format). The server then sends the optimized model to the user device. The user device then renders and displays the received 3D model. This allows the user to intuitively and visually confirm real-time information.

[0108] Specific examples

[0109] 3D model generation for weather forecasts

[0110] When a user taps the "Get Weather Information" button on a smartphone app, the device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server. The server receives the JSON data, analyzes and extracts weather information such as temperature, humidity, and wind speed. The server then creates a dataset based on the extracted weather information and sends it to the generation AI. The generation AI generates a 3D model of the weather forecast based on the dataset and returns the result to the server. The server converts the received 3D model into GLTF format and sends it to the device. The device renders the received 3D model, allowing the user to view the real-time weather forecast in 3D.

[0111] Example prompt:

[0112] By tapping the "Get Weather Information" button, the device sends a request to the weather API to obtain current weather information. The data sent to the server is then analyzed to create a dataset to input into the generation AI. The generation AI generates a 3D model based on the dataset and sends the optimized model to the device. The device then renders the 3D model and displays it to the user.

[0113] This system allows users to intuitively and visually understand information such as weather, news, maps, etc. By utilizing generative AI, manual model creation is no longer necessary, enabling fast and efficient information visualization.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] The user initiates an action

[0117] A user opens a smartphone application and taps the "Get Weather Information" button. This initiates an operation. The input is the user's action, and the output is a request to get weather information.

[0118] Step 2:

[0119] The device retrieves weather data

[0120] The device sends a request to the weather API to obtain current weather information. For example, access "https: / / api.weather.com / v3 / wx / conditions / current?apiKey=YOUR_API_KEY&format=json". The input is the API request, and the output is JSON data containing weather data such as temperature, humidity, and wind speed. The device sends this data to the server.

[0121] Step 3:

[0122] The server receives and analyzes the data

[0123] The server receives JSON data sent from the device. It analyzes the received data and extracts feature information such as temperature, humidity, and wind speed. The Python pandas library is used for analysis. The input is JSON data, and the output is the extracted feature information.

[0124] Step 4:

[0125] The server sends the data to the generated AI.

[0126] The server creates a dataset based on the extracted feature information and sends the dataset to the generation AI. The data is then formatted into the format required by the generation AI and sent. The input is the feature information and dataset, and the output is data sent to the generation AI.

[0127] Step 5:

[0128] Generative AI generates 3D models

[0129] The generative AI generates a 3D model based on a dataset provided by the server. The generation process uses deep learning libraries such as TensorFlow and PyTorch. The input is the dataset, and the output is the generated 3D model.

[0130] Step 6:

[0131] The server optimizes the 3D model

[0132] The server optimizes the generated 3D model and converts it into a format suitable for the user's device (e.g., GLTF format) using an appropriate optimization algorithm. The input is the generated 3D model, and the output is the optimized 3D model.

[0133] Step 7:

[0134] Display the optimized model for your device

[0135] The user device receives the optimized 3D model, renders it, and displays it. Rendering is performed in real time using a game engine such as Unity. The input is the optimized 3D model, and the output is a visual display of the rendered 3D model.

[0136] (Application example 1)

[0137] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0138] Conventional factory monitoring systems mainly display two-dimensional data, making it difficult to intuitively grasp the overall status of the factory in real time. In addition, it was necessary to monitor various sensor data individually, which made it difficult to manage efficiently.

[0139] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0140] In this invention, the server includes means for collecting various sensor data in the factory and converting it into a 3D model in real time for monitoring, means for optimizing the generated 3D model and transmitting it to a user terminal, and means for displaying the received 3D model on the user terminal, thereby enabling the status in the factory to be intuitively and visually grasped in real time using the 3D model.

[0141] A "user terminal" is a device operated by a user, and includes devices such as smartphones, tablets, and AR glasses.

[0142] "Two-dimensional data" refers to data that is written in a two-dimensional format, such as weather information, news, and map information.

[0143] "Feature information" is information with specific attributes or patterns extracted from analyzed two-dimensional data.

[0144] "Generative AI" is an artificial intelligence system that automatically generates 3D models based on an input dataset.

[0145] A "3D model" is three-dimensional visual data created by generative AI and displayed in a way that users can intuitively understand.

[0146] "Sensor data" is data collected from sensors that measure temperature, humidity, machine operating status, etc. within the factory.

[0147] "Real-time" means the immediacy in time that data is collected, processed and displayed at approximately the same time.

[0148] "Monitoring" is the process of continuously observing conditions within a factory to detect abnormalities or changes.

[0149] "Optimization" is the process of adjusting and converting the generated 3D model so that it can be displayed efficiently on the user's device.

[0150] This invention is a system for monitoring the status of a factory in real time as a 3D model. This system mainly uses user terminals, a server, a generating AI, and the Internet.

[0151] Overall system configuration

[0152] 1. User Device:

[0153] The user terminal is a device such as a smartphone or smart glasses. The user terminal collects various sensor data within the factory and transmits the data to a server, allowing the status within the factory to be monitored in real time.

[0154] 2. Server:

[0155] The server receives and analyzes the sensor data sent from the user device, extracts feature information, and then uses generative AI to generate a 3D model based on the extracted feature information. The generated model is then optimized and sent to the user device.

[0156] 3. Generation AI:

[0157] The generative AI uses data sets provided by the server to generate 3D models, such as those based on sensor data on temperature, humidity, and machine operation status, to generate 3D models that visually represent the real-time situation inside a factory.

[0158] 4. Distribution and display on devices:

[0159] The 3D model sent from the server is displayed on the user's device, allowing the user to check the real-time situation inside the factory using smart glasses or a smartphone.

[0160] Hardware and software used

[0161] User devices: smartphones, smart glasses

[0162] Server: High performance server

[0163] Generative AI: High-performance generative AI systems (e.g., OpenAI®)

[0164] Communication technologies: Internet, HTTP requests

[0165] Data processing flow

[0166] User devices collect sensor data such as temperature, humidity, and machine operation status within the factory. This data is sent to the server using HTTP requests. The server analyzes the received data and extracts feature information. The extracted information is input into a generative AI, which generates a 3D model in real time. The generated model is optimized and then sent to the user's device, where the user can visually view it.

[0167] Specific examples

[0168] If the factory temperature exceeds 50 degrees, a red warning area will be displayed in the generated 3D model. Also, if a specific machine is stopped, an icon indicating this will be displayed on the factory map. This makes it possible to immediately detect and deal with abnormal conditions within the factory.

[0169] Prompt Sentence Examples

[0170] "The temperature has risen to 55 degrees and the humidity is at 40%. Machine_A is running, but Machine_B is stopped."

[0171] By inputting this prompt, the generative AI will generate a detailed 3D model like this:

[0172] "Generated 3D model with areas marked in red for high temperature and icons indicating machine statuses"

[0173] The system and process of this invention allows for intuitive understanding of conditions within a factory in real time, enabling efficient management and anomaly detection.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] Data collection from user devices

[0177] The user terminal collects various sensor data from within the factory (temperature, humidity, machine operation status, etc.) The data obtained from the sensors is collected in real time and handled as a single data set.

[0178] Input: Various sensor data

[0179] Output: Collected dataset

[0180] Step 2:

[0181] Sending data from the user device to the server

[0182] The user device sends the collected data set to the server using an HTTP request, which includes information such as temperature, humidity, and machine operation status.

[0183] Input: Collected dataset

[0184] Output: Request to send data to the server

[0185] Step 3:

[0186] Data analysis by server

[0187] The server receives the data set and analyzes it, extracting temperature and humidity data, as well as machine operating status. This analyzed data is then formatted into specific feature information.

[0188] Input: Dataset

[0189] Output: Feature information

[0190] Step 4:

[0191] Input to AI for generating feature information

[0192] The server sends the extracted feature information as a dataset to the generation AI, which then generates prompt sentences in a specific format and inputs them to the AI.

[0193] Input: feature information

[0194] Output: prompt statement

[0195] Step 5:

[0196] Generating 3D models using generative AI

[0197] The generative AI generates a 3D model based on the received prompt text. This model visually represents the factory status and provides an intuitive understanding of abnormal conditions and functions.

[0198] Input: prompt statement

[0199] Output: 3D model data

[0200] Step 6:

[0201] 3D model optimization by server

[0202] The generated 3D model is optimized by the server. The optimized 3D model is then adjusted so that it can be displayed efficiently on the user's device. This optimization process involves converting the file format and reducing the file size.

[0203] Input: 3D model data

[0204] Output: Optimized 3D model data

[0205] Step 7:

[0206] Sending the optimized 3D model to the user device

[0207] The server sends the optimized 3D model to the user's device using an HTTP POST request, which then displays the data appropriately on the user's device.

[0208] Input: Optimized 3D model data

[0209] Output: Request to send data to the user terminal

[0210] Step 8:

[0211] Display of 3D models on user devices

[0212] The user device displays the received 3D model, and the real-time situation inside the factory is visualized in 3D on the display of smart glasses or a smartphone, allowing the user to check it.

[0213] Input: Optimized 3D model data

[0214] Output: A representation of the 3D model as seen by the user

[0215] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0216] To implement this invention, a system using a user terminal, a server, a generation AI, an emotion engine, and the Internet is required. Below, the processing of the programs that make up this system will be explained in natural language.

[0217] Overall system configuration

[0218] 1. User Device

[0219] The device operated by the user (smartphone, tablet, AR glasses, etc.) uses a dedicated application to acquire 2D data and send it to a server. It also has an emotion engine that recognizes the user's emotions in real time. Specific data input by the user includes information such as weather, news, and maps.

[0220] Explaining program processing in natural language

[0221] 1. Enter and submit data

[0222] The user opens the smartphone application and selects the type of 2D data they want to acquire. For example, they select weather information and tap the "Get Weather Information" button. The device accesses the weather information API and sends the acquired data to the server.

[0223] 2. Data Receipt and Analysis

[0224] The server receives two-dimensional data from the weather information API, analyzes it, and extracts the necessary characteristic information (temperature, humidity, wind speed, probability of precipitation, etc.).

[0225] 3. Emotion recognition

[0226] The emotion engine installed on the device analyzes the user's facial expressions and voice in real time to recognize the user's emotions, and this recognition result is also sent to the server.

[0227] 4. 3D model generation using generative AI

[0228] The server creates a dataset for the generation AI based on the analyzed data and emotion recognition results, and inputs it into the generation AI, which then generates a 3D model that reflects the user's emotions in the weather information data.

[0229] 5. Optimize and submit the model

[0230] The generation AI returns the generated 3D model to the server, which then optimizes the received 3D model and converts it into a display format (e.g., GLTF format), after which it sends the optimized 3D model to the device.

[0231] 6. Displaying the 3D model

[0232] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Through the AR glasses, the user can check the real-time weather forecast in 3D. The display content is also adjusted based on the user's emotion recognition results.

[0233] Specific examples

[0234] 3D model generation for weather forecasts

[0235] 1. The user taps the "Get Weather Information" button on the smartphone app.

[0236] 2. The device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server.

[0237] 3. The server receives the JSON data and analyzes and extracts the necessary weather information (temperature, humidity, wind speed, precipitation probability, etc.).

[0238] 4. The emotion engine installed on the device analyzes the user's facial expressions and voice to recognize their emotions. The recognition results are sent to the server.

[0239] 5. Based on the weather information and emotion recognition results extracted by the server, a dataset is created to be input into the generation AI and sent to the generation AI.

[0240] 6. The generative AI generates a 3D model of the weather forecast based on the input dataset and emotion recognition results, and returns the result to the server.

[0241] 7. The server converts the received 3D model into GLTF format and sends it to the device (such as AR glasses).

[0242] 8. The device renders the received 3D model and visually displays it to the user, allowing the user to see a real-time weather forecast in 3D. Furthermore, the information is adjusted based on the user's emotions, allowing the user to receive more personalized information.

[0243] The system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI and an emotion engine, manual model creation is eliminated, enabling fast and efficient information visualization and personalization.

[0244] The processing flow will be explained below.

[0245] Step 1:

[0246] A user opens a smartphone application and selects the type of 2D data they want to obtain. For example, the user selects weather information and taps the "Get Weather Information" button.

[0247] Step 2:

[0248] The device accesses the weather information API and requests weather data based on the specified location and time, and obtains two-dimensional data such as temperature, humidity, wind speed, and precipitation probability from the API.

[0249] Step 3:

[0250] The device sends the acquired 2D data to the server, usually using HTTP or HTTPS.

[0251] Step 4:

[0252] The server receives the 2D data sent from the device, analyzes the data format (e.g., JSON), and extracts necessary characteristic information (temperature, humidity, wind speed, precipitation probability, etc.) from the analyzed data.

[0253] Step 5:

[0254] The device's emotion engine collects the user's facial and voice data, recognizes the user's emotions in real time, and generates emotion recognition results (e.g., joy, sadness, surprise, etc.) and sends them to the server.

[0255] Step 6:

[0256] The server receives the emotion recognition results and combines them with the previously extracted feature information to create a dataset, which contains the user's emotion information along with their mood information.

[0257] Step 7:

[0258] The server sends the dataset to the generation AI for input, which analyzes the dataset and begins generating a 3D model based on the user's emotions.

[0259] Step 8:

[0260] The generative AI generates a 3D weather forecast model that reflects the user's emotions based on weather information and emotion recognition results. The generated 3D model is adjusted to have a realistic visual effect.

[0261] Step 9:

[0262] The AI ​​generates a 3D model and returns it to the server, which then optimizes it and converts it into a display format (e.g., GLTF).

[0263] Step 10:

[0264] The server sends the optimized 3D model to the device using fast and efficient data transmission technologies (e.g., HTTP, WebSocket).

[0265] Step 11:

[0266] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Users can check the real-time weather forecast in 3D through the AR glasses. Emotion-based customization allows users to receive personalized information.

[0267] Step 12:

[0268] Users can interact with the displayed 3D model, for example, by moving forward or backward in time to see future or past weather information, and can also select different emotions from the interface to change the displayed content.

[0269] Example 2

[0270] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0271] In today's digital information society, users acquire a wide variety of information, and the amount of information is enormous. Weather information, news, and map information, in particular, change daily, and users need to be able to instantly understand that information. However, traditional two-dimensional data displays often make it difficult to intuitively grasp information. Furthermore, information display does not take into account the user's emotional state, resulting in insufficient personalization. The present invention aims to solve these problems and provide efficient and personalized information.

[0272] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0273] In this invention, the server includes means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, means for receiving and analyzing emotion data from the user terminal, means for generating a 3D model using a generation AI based on the extracted feature information and emotion data, means for optimizing the generated 3D model, converting it into a display format, and transmitting it to the user terminal, and means for displaying the received 3D model on the user terminal. This allows users to easily understand information using intuitive and visual 3D models, and further enables personalized information display based on the user's emotions.

[0274] A "user terminal" is a device operated by a user, and is a general term for devices such as smartphones, tablets, and AR glasses.

[0275] "Two-dimensional data" refers to information data that is spread out on a single plane, and refers to data groups in the form of weather information, news articles, map information, etc.

[0276] "Server" means a computer system that transmits, receives, analyzes, stores, and processes data over a network.

[0277] "Feature information" refers to specific information components such as temperature, humidity, wind speed, and precipitation probability extracted from two-dimensional data.

[0278] "Emotion data" is data that indicates the emotional state of the user, obtained by analyzing the user's facial expressions and voice.

[0279] "Generative AI" refers to artificial intelligence technology that generates new data and models based on input data, and is particularly responsible for generating images and 3D models.

[0280] A "3D model" refers to a three-dimensional digital object used to visually represent weather, map information, etc.

[0281] "Display format" refers to a data format for properly displaying a 3D model on a user terminal, and examples include the GLTF format.

[0282] MODE FOR CARRYING OUT THE INVENTION

[0283] To implement this invention, a user terminal, a server, a generating AI, an emotion engine, and a system that utilizes the Internet are required.

[0284] Hardware and software used

[0285] User devices: Smartphones, tablets, AR glasses, etc. These devices are equipped with internet connectivity, cameras, and microphones. A dedicated application is installed, and an emotion engine is also installed to acquire 2D data and analyze emotion data.

[0286] Server: A high-performance computer system that receives data, analyzes it, creates generative AI models, optimizes them, and transmits them. It includes a database system, an analysis engine, generative AI (e.g., OpenAI's DALL-E), and optimization tools.

[0287] Internet: A communications network for transmitting data between user terminals and servers.

[0288] System operation procedure

[0289] The user device acquires 2D data (e.g., weather information) through user operation and sends it to the server. The server analyzes the received data and extracts feature information such as weather information. At the same time, the user device uses an emotion engine to analyze the user's emotions and sends the results to the server. The server combines the extracted feature information and emotion data to create a dataset to input into the generative AI. The generative AI generates a 3D model based on the input data and returns it to the server. The server optimizes the generated 3D model, converts it into a display format (e.g., GLTF format), and sends it to the user device. Finally, the user device renders the received 3D model and displays it on the user's display device.

[0290] Detailed processing example

[0291] When a user taps the "Get Weather Information" button on a smartphone app, the device sends a request to a weather information API (e.g., OpenWeatherMap API), obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server. The server receives the JSON data, analyzes and extracts the necessary weather information (e.g., temperature, humidity, wind speed, probability of precipitation, etc.). At the same time, the device's built-in emotion engine analyzes the user's facial expressions and voice to recognize the user's emotions. The recognition results are then sent to the server.

[0292] The server creates a dataset to be input into the generation AI based on the extracted weather information and emotion recognition results, and sends it to the generation AI. The generation AI generates a 3D model of the weather forecast corresponding to the emotion based on the input dataset and emotion recognition results, and sends it back to the server. The server optimizes the generated 3D model, converts it to GLTF format, and sends it to the device. The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses).

[0293] Prompt Sentence Examples

[0294] Input: Temperature 25°C, humidity 60%, wind speed 5 m / s, user emotion is happiness

[0295] Output: A 3D model of a sunny weather forecast with a rainbow that reflects happiness

[0296] This system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI and an emotion engine, it eliminates the need for manual model creation, enabling fast and efficient visualization and personalization of information. This system is a powerful tool for aiding information understanding.

[0297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0298] Step 1:

[0299] Entering data

[0300] The user taps the "Get Weather Information" button on the smartphone app.

[0301] Specific actions

[0302] The user interacts with the app and taps a button to get weather information.

[0303] input

[0304] Input from user actions.

[0305] output

[0306] Weather information request.

[0307] Data processing / calculation

[0308] A request is created and sent to the weather information API.

[0309] Step 2:

[0310] Acquiring and Sending Data

[0311] The device sends a request to the weather information API and sends the retrieved weather data in JSON format to the server.

[0312] Specific actions

[0313] The device accesses the weather information API via the network and obtains current weather information (e.g., temperature, humidity, wind speed).

[0314] Send the obtained JSON data to the server.

[0315] input

[0316] Weather information request

[0317] Weather information API response data (JSON format).

[0318] output

[0319] Obtained weather data.

[0320] Data processing / calculation

[0321] Receives JSON format data and temporarily saves it.

[0322] Convert it into a format to send to the server.

[0323] Step 3:

[0324] Data reception and analysis

[0325] The server analyzes the JSON-formatted weather data it receives and extracts the necessary feature information.

[0326] Specific actions

[0327] The server receives the JSON data.

[0328] Use a data analytics engine to extract key data such as temperature, humidity, and wind speed.

[0329] input

[0330] Weather data in JSON format sent from the device.

[0331] output

[0332] Extracted feature information (e.g., temperature 25°C, humidity 60%, wind speed 5m / s).

[0333] Data processing / calculation

[0334] Analyze the JSON data and extract the necessary items (temperature, humidity, wind speed, etc.).

[0335] The extracted information is stored in an internal database.

[0336] Step 4:

[0337] emotion recognition

[0338] The emotion engine installed in the device analyzes the user's facial expressions and voice to recognize the user's emotional state.

[0339] Specific actions

[0340] The device uses a camera and microphone to capture the user's facial expressions and voice.

[0341] The emotion engine analyzes the user's emotions in real time.

[0342] Send the results to the server.

[0343] input

[0344] User facial and voice data.

[0345] output

[0346] Recognized emotion data (e.g., happiness).

[0347] Data processing / calculation

[0348] Facial expressions and voice are analyzed using analytical algorithms.

[0349] Determine the emotional state and output the results as data.

[0350] Step 5:

[0351] Creating and generating datasets and inputting them into AI

[0352] The server creates a dataset to be input into the generative AI based on the extracted feature information and emotion data.

[0353] Specific actions

[0354] The server combines weather information and emotion data to create a dataset.

[0355] Input this as a prompt to the generation AI.

[0356] input

[0357] Feature information and emotion data.

[0358] output

[0359] Datasets for generative AI.

[0360] Data processing / calculation

[0361] The extracted feature information and emotion data are integrated and converted into a format suitable for generative AI.

[0362] Input this as a prompt to the generation AI.

[0363] Step 6:

[0364] Generating 3D models using generative AI

[0365] The generative AI generates a 3D model based on the input dataset and sends it back to the server.

[0366] Specific actions

[0367] Generative AI generates a 3D model based on the dataset.

[0368] The generated 3D model is sent back to the server.

[0369] input

[0370] Datasets for generative AI.

[0371] output

[0372] Generated 3D model

[0373] Data processing / calculation

[0374] Run an algorithm that analyzes the dataset and generates a 3D model.

[0375] Step 7:

[0376] Optimize and submit the model

[0377] The server optimizes the generated 3D model, converts it into a display format (GLTF format), and then sends it to the user's terminal.

[0378] Specific actions

[0379] The 3D model is made lighter by adjusting the number of polygons, etc.

[0380] Convert to GLTF format.

[0381] The converted model is sent to the user terminal.

[0382] input

[0383] Generated 3D model.

[0384] output

[0385] Optimized 3D model in GLTF format.

[0386] Data processing / calculation

[0387] Optimize the model to improve display efficiency.

[0388] Convert the format to GLTF.

[0389] Step 8:

[0390] 3D model display

[0391] The terminal renders the received 3D model and displays it on the user's display device.

[0392] Specific actions

[0393] The device uses a graphics engine to render the received 3D model.

[0394] The rendered model is displayed on a display device such as AR glasses.

[0395] input

[0396] 3D model in GLTF format sent from the server.

[0397] output

[0398] The 3D model displayed on the user's display device.

[0399] Data processing / calculation

[0400] Render a 3D model.

[0401] Visualize in a format suitable for the display device.

[0402] (Application example 2)

[0403] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0404] Conventional information provision systems have difficulty providing users with personalized real-time information, and are unable to provide information that reflects the user's emotions or current location, particularly in the case of shopping in physical stores. As a result, users are unable to efficiently obtain the information they need, making it difficult to improve their shopping experience.

[0405] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, and means for combining the extracted feature information with the emotion recognition result of the emotion engine and generating a 3D model using a generation AI. This makes it possible to provide personalized real-time information that reflects the user's emotions and current location information.

[0406] A "user terminal" is a device operated by a user and is part of a system that includes smart glasses, smartphones, tablets, etc.

[0407] "Two-dimensional data" refers to information such as weather information, news, and map information expressed in two-dimensional format.

[0408] "Feature information" is important information extracted from two-dimensional data, and refers to specific numerical values ​​and data such as temperature, humidity, price, and inventory quantity.

[0409] The "emotion engine" is a software component that analyzes emotions from the user's facial expressions and voice in real time.

[0410] "Generative AI" is an artificial intelligence system that generates 3D models based on input data, and has the ability to learn features from datasets and generate models.

[0411] A "3D model" is three-dimensional visual information created by the generative AI based on feature information and emotion recognition results, and is visually displayed to the user.

[0412] The "server" is a computer system that receives and analyzes data sent from the user's device, generates a 3D model using generative AI, optimizes it, and sends it to the user's device.

[0413] "Optimization" is a process of converting the generated 3D model into a display format to ensure smooth display on the user's device.

[0414] "Display format" refers to a data format for displaying a 3D model on a user terminal, such as the GLTF format.

[0415] "Emotion recognition result" is data indicating the emotional state analyzed by the emotion engine from the user's facial expressions and voice.

[0416] "Location Sensor" means a hardware component that detects a user's current location, including GPS and other location technologies.

[0417] "Sale information" is data related to discounts and sales on products in stores, and includes information such as price, number of items in stock, and sale end time.

[0418] The system for implementing this invention utilizes a user terminal, a server, a generating AI, an emotion engine, and the Internet. The detailed program processing of the system will be explained below.

[0419] Overall system configuration

[0420] 1. User Device

[0421] A device operated by the user, such as smart glasses, smartphones, or tablets, has a dedicated application installed on the user's device, which recognizes location information and emotions in real time and sends 2D data to a server. It also uses an emotion engine to analyze emotions in real time from the user's facial expressions and voice.

[0422] 2. Server

[0423] The server receives 2D data and emotion recognition results sent from the user device. It analyzes the data and extracts feature information. Based on the extracted feature information and emotion recognition results, it uses generative AI to generate and optimize a 3D model. The optimized 3D model is converted into a display format (e.g., GLTF format) and sent to the user device.

[0424] What the program does

[0425] 1. Enter and submit data

[0426] When a user wears smart glasses with a location sensor and stands in front of a specific location (for example, a sale section in a physical store), the location sensor and camera detect the location. Based on the detected location information, the user's device accesses the API of the inventory management system, obtains real-time data such as sale information, and sends it to the server.

[0427] 2. Data Receipt and Analysis

[0428] The server analyzes the received real-time data and extracts important information such as price, stock quantity, and sale end time.

[0429] 3. Emotion recognition

[0430] The emotion engine installed in the user device analyzes the user's facial expressions and voice to recognize their emotional state, such as interest or surprise, and this recognition result is also sent to the server.

[0431] 4. 3D model generation using generative AI

[0432] The server creates a dataset for the generation AI based on the extracted feature information and emotion recognition results, and inputs this data into the generation AI. The generation AI then generates a 3D model of the sale information, taking into account the emotion recognition results, and returns the result to the server.

[0433] 5. Optimize and submit the model

[0434] The server optimizes the generated 3D model, converts it into a display format such as GLTF format, and then sends it to the user's terminal.

[0435] 6. Displaying the 3D model

[0436] The user device renders the received 3D model and visually displays it to the user through the smart glasses. Based on the user's emotion recognition results, the display content is adjusted, for example, enhancing color when the user is interested, or adding animation when the user is surprised.

[0437] Specific examples

[0438] Displaying special sales information in physical stores

[0439] 1. A user puts on smart glasses and stands in the bargain section of a supermarket.

[0440] 2. The user device uses a sensor to detect its location within the sale section, sends a request to the inventory management system API, and obtains current sale information (price, number of items in stock, sale end time).

[0441] 3. The server analyzes the received inventory information and extracts important information such as price and stock quantity.

[0442] 4. The emotion engine installed on the user device analyzes the user's facial expressions and voice in real time to recognize the user's emotions (e.g., interest or surprise). The recognition results are sent to the server.

[0443] 5. Based on the extracted sale information and emotion recognition results, the server creates a dataset for the generation AI and inputs it. The generation AI generates a 3D model of the sale information according to the emotion and returns the result to the server.

[0444] 6. The server converts the received 3D model into GLTF format and sends it to the user's device.

[0445] 7. The user device renders the received 3D model, and through the smart glasses, the user can check real-time inventory information and sales information corresponding to the sale section in 3D. Furthermore, the display content is adjusted based on the user's emotions.

[0446] Example prompts to input to the generative AI model

[0447] "Generate emotionally relevant 3D models of your sale section's inventory. Use vibrant colors to emphasize interest and add animations for surprise."

[0448] The system allows users to visually view personalized sales information based on their emotions, enhancing the intuitive shopping experience.

[0449] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0450] Step 1:

[0451] A user puts on smart glasses and stands at a specific location in a store. The location sensor and camera on the smart glasses detect this location and capture its location information. The location information becomes input data, which is then sent to a server by an application on the user's device.

[0452] Step 2:

[0453] The server receives location information sent from the user's device. Based on the received location information, the server accesses the inventory management system API and obtains sale information (price, stock quantity, sale end time) related to a specific location in the store. This sale information is analyzed by the server, and characteristic information such as price and stock quantity is extracted.

[0454] Step 3:

[0455] After processing the feature information, the emotion engine installed in the user device analyzes the user's facial expressions and voice in real time. This analysis recognizes the user's emotional state (e.g., interest, surprise). The recognized emotion data is sent from the user device to the server.

[0456] Step 4:

[0457] The server receives the emotion recognition results. The received feature information and the emotion recognition results are combined to create a dataset to be input into the generation AI. This dataset is prompt data that the generation AI uses to generate a 3D model that reflects the user's emotions in the sale information.

[0458] Step 5:

[0459] The generative AI receives the created dataset as input and generates a 3D model based on the sale information. The generated 3D model reflects the user's emotions and visually emphasizes the sale information, and is sent back to the server.

[0460] Step 6:

[0461] The server optimizes the 3D model returned by the AI ​​generator and converts it into an appropriate display format (e.g., GLTF format). The converted 3D model is then sent to the user's device.

[0462] Step 7:

[0463] The user device renders the 3D model received from the server and displays it visually to the user through the smart glasses. Special sale information is displayed in real time as a 3D model, and color enhancement and animation are added based on the user's emotion recognition results. This allows the user to understand the special sale information more intuitively.

[0464] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0465] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0466] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0467] [Second embodiment]

[0468] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0469] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0470] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0471] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0472] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0473] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0474] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0475] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0476] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0477] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0478] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0479] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0480] To implement this invention, a system using a user terminal, a server, a generation AI, and the Internet is required. Below, the processing of the programs that make up this system will be explained in detail in natural language.

[0481] Overall system configuration

[0482] 1. User Device

[0483] The device operated by the user (smartphone, tablet, AR glasses, etc.) uses a dedicated application to acquire 2D data and send it to the server. The specific data input by the user includes information such as weather, news, and maps.

[0484] Example: A user opens a smartphone application and taps the "Get Weather Information" button to get weather information.

[0485] 2. Server

[0486] The server receives the 2D data sent from the user's device, analyzes it, and extracts the necessary feature information. It then inputs the extracted feature information into a generation AI, which automatically generates a 3D model. The generated 3D model is then further optimized and converted into a format suitable for the user's device. The generated 3D model is then sent to the user's device.

[0487] Example: A server receives weather information sent from a smartphone app, analyzes and extracts data such as temperature, humidity, and wind speed, and inputs that data into a generative AI to generate a 3D weather forecast model.

[0488] 3. Generation AI

[0489] Generative AI is responsible for generating 3D models based on datasets provided by the server. For example, it generates 3D models that visually represent cloud movement and temperature distribution based on weather data.

[0490] Example: Generative AI takes temperature, humidity, and wind speed data as input and generates a 3D model to visualize real-time weather forecasts.

[0491] 4. Distribution and display on devices

[0492] The server optimizes the generated 3D model, converts it into an appropriate format, and sends it to the user's device, where it displays the received 3D model, allowing the user to view it in real time.

[0493] Example: The optimized 3D weather model is sent to the AR glasses, allowing users to see the real-time weather forecast in 3D through the glasses.

[0494] Specific examples

[0495] 3D model generation for weather forecasts

[0496] 1. The user taps the "Get Weather Information" button on the smartphone app.

[0497] 2. The device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server.

[0498] 3. The server receives the JSON data and analyzes and extracts the necessary weather information (temperature, humidity, wind speed, precipitation probability, etc.).

[0499] 4. Based on the weather information extracted by the server, a dataset is created to be input into the generation AI and sent to the generation AI.

[0500] 5. The generative AI generates a 3D model of the weather forecast based on the input dataset and returns the results to the server.

[0501] 6. The server converts the received 3D model into GLTF format and sends it to the device (such as AR glasses).

[0502] 7. The device renders the received 3D model and visually displays it to the user, allowing the user to see a real-time weather forecast in 3D.

[0503] The system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI, manual model creation is no longer necessary, enabling fast and efficient information visualization.

[0504] The processing flow will be explained below.

[0505] Step 1:

[0506] The user opens the dedicated application, selects the type of 2D data they want to acquire, and taps the "Get Weather Information" button.

[0507] Step 2:

[0508] The device accesses the weather information API and sends a request to the server, which includes location information, the current time, and other information.

[0509] Step 3:

[0510] The server receives 2D data from a weather information API, usually in JSON format, including information such as temperature, humidity, wind speed, and chance of precipitation.

[0511] Step 4:

[0512] The server analyzes the received JSON data and extracts the necessary characteristic information (temperature, humidity, wind speed, probability of precipitation, etc.).

[0513] Step 5:

[0514] The server creates a dataset based on the extracted feature information to be input into the generative AI. The dataset contains each element of weather information.

[0515] Step 6:

[0516] The server sends the dataset to the generation AI, which then starts the process of generating a 3D model. The generation AI generates a 3D weather forecast model based on the input weather data.

[0517] Step 7:

[0518] The generation AI returns the generated 3D model to the server, which then optimizes the received 3D model and converts it into a display format (e.g., GLTF format).

[0519] Step 8:

[0520] The server sends the optimized 3D model to the device.

[0521] Step 9:

[0522] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Through the AR glasses, the user can check the real-time weather forecast in 3D.

[0523] Step 10:

[0524] If necessary, the user can interact with the displayed 3D model, for example, by moving the time forward or backward to check future or past weather information.

[0525] Example 1

[0526] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0527] In today's information society, there is a growing need for a more intuitive and visual understanding of real-time information such as weather forecasts, news, and map information. However, traditional 2D data often makes it difficult to understand the information, and there is a need for technology to provide information in a format that is easy for users to understand. In particular, there is a lack of technology to efficiently generate 3D models and provide them in a format suitable for the device used by the user. To solve this issue, it is necessary to utilize more advanced data analysis and generative AI technology to quickly and effectively provide 3D models compatible with user devices.

[0528] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0529] In this invention, the server includes means for receiving 2D data from a user terminal, means for the user terminal to acquire 2D data from an external database and transmit it to the server, means for analyzing the received 2D data and extracting feature information, means for generating a 3D model using a generation AI based on the extracted feature information, means for the server to optimize the generated 3D model, convert it into a display format, and transmit it to the user terminal, and means for displaying the received 3D model on the user terminal. This allows information to be understood intuitively and visually, and makes it possible to efficiently generate and optimize 3D models and provide them in a form suitable for the user terminal.

[0530] A "user terminal" is a terminal operated by a user, and includes devices such as smartphones, tablets, and AR glasses.

[0531] "Two-dimensional data" is data that includes information such as weather, news, and maps, and is a data format that users acquire and send.

[0532] An "external database" is a repository of data that can be accessed via the Internet, such as a weather API or news API.

[0533] The "server" is a central processing unit that receives and analyzes data sent from the user terminal and provides the data to the generation AI.

[0534] "Feature information" is specific information such as temperature, humidity, and wind speed that is extracted by analyzing the two-dimensional data sent from the user terminal.

[0535] "Generative AI" is an artificial intelligence technology for generating 3D models based on feature information provided by a server.

[0536] A "3D model" is visually represented three-dimensional information generated based on 2D data and feature information.

[0537] A "display format" is a data format for appropriately displaying a 3D model on a user terminal, and includes the GLTF format.

[0538] "Optimization" is the process of streamlining the data volume and structure of the generated 3D model and converting it into a form suitable for the user's device.

[0539] "Rendering" is a process for visually displaying a 3D model received by a user terminal.

[0540] MODE FOR CARRYING OUT THE INVENTION

[0541] To implement this invention, a system using a user terminal, a server, a generation AI, and the Internet is required. Below, the processing of the programs that make up this system will be explained in detail in natural language.

[0542] Overall system configuration

[0543] User terminal

[0544] A dedicated application is installed on the user's device (smartphone, tablet, AR glasses, etc.). This application acquires 2D data from the user and sends it to the server. Specifically, when the user taps the "Get Weather Information" button, a request is sent to the weather API, current weather information is acquired, and it is sent to the server.

[0545] server

[0546] The server receives and analyzes the 2D data sent from the user's device. During the analysis, feature information such as temperature, humidity, and wind speed is extracted. The analysis is performed using the Python pandas library. A dataset is then created based on the extracted feature information and sent to the generation AI.

[0547] Generation AI

[0548] The generative AI generates a 3D model based on the dataset provided by the server. This generation process uses deep learning libraries such as TensorFlow and PyTorch. The generated 3D model visually represents, for example, cloud movement and temperature distribution.

[0549] Distribution and display on terminals

[0550] The server optimizes the generated 3D model and converts it into a format suitable for the user device (e.g., GLTF format). The server then sends the optimized model to the user device. The user device then renders and displays the received 3D model. This allows the user to intuitively and visually confirm real-time information.

[0551] Specific examples

[0552] 3D model generation for weather forecasts

[0553] When a user taps the "Get Weather Information" button on a smartphone app, the device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server. The server receives the JSON data, analyzes and extracts weather information such as temperature, humidity, and wind speed. The server then creates a dataset based on the extracted weather information and sends it to the generation AI. The generation AI generates a 3D model of the weather forecast based on the dataset and returns the result to the server. The server converts the received 3D model into GLTF format and sends it to the device. The device renders the received 3D model, allowing the user to view the real-time weather forecast in 3D.

[0554] Example prompt:

[0555] By tapping the "Get Weather Information" button, the device sends a request to the weather API to obtain current weather information. The data sent to the server is then analyzed to create a dataset to input into the generation AI. The generation AI generates a 3D model based on the dataset and sends the optimized model to the device. The device then renders the 3D model and displays it to the user.

[0556] This system allows users to intuitively and visually understand information such as weather, news, maps, etc. By utilizing generative AI, manual model creation is no longer necessary, enabling fast and efficient information visualization.

[0557] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0558] Step 1:

[0559] The user initiates an action

[0560] A user opens a smartphone application and taps the "Get Weather Information" button. This initiates an operation. The input is the user's action, and the output is a request to get weather information.

[0561] Step 2:

[0562] The device retrieves weather data

[0563] The device sends a request to the weather API to obtain current weather information. For example, access "https: / / api.weather.com / v3 / wx / conditions / current?apiKey=YOUR_API_KEY&format=json". The input is the API request, and the output is JSON data containing weather data such as temperature, humidity, and wind speed. The device sends this data to the server.

[0564] Step 3:

[0565] The server receives and analyzes the data

[0566] The server receives JSON data sent from the device. It analyzes the received data and extracts feature information such as temperature, humidity, and wind speed. The Python pandas library is used for analysis. The input is JSON data, and the output is the extracted feature information.

[0567] Step 4:

[0568] The server sends the data to the generated AI.

[0569] The server creates a dataset based on the extracted feature information and sends the dataset to the generation AI. The data is then formatted into the format required by the generation AI and sent. The input is the feature information and dataset, and the output is data sent to the generation AI.

[0570] Step 5:

[0571] Generative AI generates 3D models

[0572] The generative AI generates a 3D model based on a dataset provided by the server. The generation process uses deep learning libraries such as TensorFlow and PyTorch. The input is the dataset, and the output is the generated 3D model.

[0573] Step 6:

[0574] The server optimizes the 3D model

[0575] The server optimizes the generated 3D model and converts it into a format suitable for the user's device (e.g., GLTF format) using an appropriate optimization algorithm. The input is the generated 3D model, and the output is the optimized 3D model.

[0576] Step 7:

[0577] Display the optimized model for your device

[0578] The user device receives the optimized 3D model, renders it, and displays it. Rendering is performed in real time using a game engine such as Unity. The input is the optimized 3D model, and the output is a visual display of the rendered 3D model.

[0579] (Application example 1)

[0580] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0581] Conventional factory monitoring systems mainly display two-dimensional data, making it difficult to intuitively grasp the overall status of the factory in real time. In addition, it was necessary to monitor various sensor data individually, which made it difficult to manage efficiently.

[0582] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0583] In this invention, the server includes means for collecting various sensor data in the factory and converting it into a 3D model in real time for monitoring, means for optimizing the generated 3D model and transmitting it to a user terminal, and means for displaying the received 3D model on the user terminal, thereby enabling the status in the factory to be intuitively and visually grasped in real time using the 3D model.

[0584] A "user terminal" is a device operated by a user, and includes devices such as smartphones, tablets, and AR glasses.

[0585] "Two-dimensional data" refers to data that is written in a two-dimensional format, such as weather information, news, and map information.

[0586] "Feature information" is information with specific attributes or patterns extracted from analyzed two-dimensional data.

[0587] "Generative AI" is an artificial intelligence system that automatically generates 3D models based on an input dataset.

[0588] A "3D model" is three-dimensional visual data created by generative AI and displayed in a way that users can intuitively understand.

[0589] "Sensor data" is data collected from sensors that measure temperature, humidity, machine operating status, etc. within the factory.

[0590] "Real-time" means the immediacy in time that data is collected, processed and displayed at approximately the same time.

[0591] "Monitoring" is the process of continuously observing conditions within a factory to detect abnormalities or changes.

[0592] "Optimization" is the process of adjusting and converting the generated 3D model so that it can be displayed efficiently on the user's device.

[0593] This invention is a system for monitoring the status of a factory in real time as a 3D model. This system mainly uses user terminals, a server, a generating AI, and the Internet.

[0594] Overall system configuration

[0595] 1. User Device:

[0596] The user terminal is a device such as a smartphone or smart glasses. The user terminal collects various sensor data within the factory and transmits the data to a server, allowing the status within the factory to be monitored in real time.

[0597] 2. Server:

[0598] The server receives and analyzes the sensor data sent from the user device, extracts feature information, and then uses generative AI to generate a 3D model based on the extracted feature information. The generated model is then optimized and sent to the user device.

[0599] 3. Generation AI:

[0600] The generative AI uses data sets provided by the server to generate 3D models, such as those based on sensor data on temperature, humidity, and machine operation status, to generate 3D models that visually represent the real-time situation inside a factory.

[0601] 4. Distribution and display on devices:

[0602] The 3D model sent from the server is displayed on the user's device, allowing the user to check the real-time situation inside the factory using smart glasses or a smartphone.

[0603] Hardware and software used

[0604] User devices: smartphones, smart glasses

[0605] Server: High performance server

[0606] Generative AI: High-performance generative AI systems (e.g., OpenAI)

[0607] Communication technologies: Internet, HTTP requests

[0608] Data processing flow

[0609] User devices collect sensor data such as temperature, humidity, and machine operation status within the factory. This data is sent to the server using HTTP requests. The server analyzes the received data and extracts feature information. The extracted information is input into a generative AI, which generates a 3D model in real time. The generated model is optimized and then sent to the user's device, where the user can visually view it.

[0610] Specific examples

[0611] If the factory temperature exceeds 50 degrees, a red warning area will be displayed in the generated 3D model. Also, if a specific machine is stopped, an icon indicating this will be displayed on the factory map. This makes it possible to immediately detect and deal with abnormal conditions within the factory.

[0612] Prompt Sentence Examples

[0613] "The temperature has risen to 55 degrees and the humidity is at 40%. Machine_A is running, but Machine_B is stopped."

[0614] By inputting this prompt, the generative AI will generate a detailed 3D model like this:

[0615] "Generated 3D model with areas marked in red for high temperature and icons indicating machine statuses"

[0616] The system and process of this invention allows for intuitive understanding of conditions within a factory in real time, enabling efficient management and anomaly detection.

[0617] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0618] Step 1:

[0619] Data collection from user devices

[0620] The user terminal collects various sensor data from within the factory (temperature, humidity, machine operation status, etc.) The data obtained from the sensors is collected in real time and handled as a single data set.

[0621] Input: Various sensor data

[0622] Output: Collected dataset

[0623] Step 2:

[0624] Sending data from the user device to the server

[0625] The user device sends the collected data set to the server using an HTTP request, which includes information such as temperature, humidity, and machine operation status.

[0626] Input: Collected dataset

[0627] Output: Request to send data to the server

[0628] Step 3:

[0629] Data analysis by server

[0630] The server receives the data set and analyzes it, extracting temperature and humidity data, as well as machine operating status. This analyzed data is then formatted into specific feature information.

[0631] Input: Dataset

[0632] Output: Feature information

[0633] Step 4:

[0634] Input to AI for generating feature information

[0635] The server sends the extracted feature information as a dataset to the generation AI, which then generates prompt sentences in a specific format and inputs them to the AI.

[0636] Input: feature information

[0637] Output: prompt statement

[0638] Step 5:

[0639] Generating 3D models using generative AI

[0640] The generative AI generates a 3D model based on the received prompt text. This model visually represents the factory status and provides an intuitive understanding of abnormal conditions and functions.

[0641] Input: prompt statement

[0642] Output: 3D model data

[0643] Step 6:

[0644] 3D model optimization by server

[0645] The generated 3D model is optimized by the server. The optimized 3D model is then adjusted so that it can be displayed efficiently on the user's device. This optimization process involves converting the file format and reducing the file size.

[0646] Input: 3D model data

[0647] Output: Optimized 3D model data

[0648] Step 7:

[0649] Sending the optimized 3D model to the user device

[0650] The server sends the optimized 3D model to the user's device using an HTTP POST request, which then displays the data appropriately on the user's device.

[0651] Input: Optimized 3D model data

[0652] Output: Request to send data to the user terminal

[0653] Step 8:

[0654] Display of 3D models on user devices

[0655] The user device displays the received 3D model, and the real-time situation inside the factory is visualized in 3D on the display of smart glasses or a smartphone, allowing the user to check it.

[0656] Input: Optimized 3D model data

[0657] Output: A representation of the 3D model as seen by the user

[0658] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0659] To implement this invention, a system using a user terminal, a server, a generation AI, an emotion engine, and the Internet is required. Below, the processing of the programs that make up this system will be explained in natural language.

[0660] Overall system configuration

[0661] 1. User Device

[0662] The device operated by the user (smartphone, tablet, AR glasses, etc.) uses a dedicated application to acquire 2D data and send it to a server. It also has an emotion engine that recognizes the user's emotions in real time. Specific data input by the user includes information such as weather, news, and maps.

[0663] Explaining program processing in natural language

[0664] 1. Enter and submit data

[0665] The user opens the smartphone application and selects the type of 2D data they want to acquire. For example, they select weather information and tap the "Get Weather Information" button. The device accesses the weather information API and sends the acquired data to the server.

[0666] 2. Data Receipt and Analysis

[0667] The server receives two-dimensional data from the weather information API, analyzes it, and extracts the necessary characteristic information (temperature, humidity, wind speed, probability of precipitation, etc.).

[0668] 3. Emotion recognition

[0669] The emotion engine installed on the device analyzes the user's facial expressions and voice in real time to recognize the user's emotions, and this recognition result is also sent to the server.

[0670] 4. 3D model generation using generative AI

[0671] The server creates a dataset for the generation AI based on the analyzed data and emotion recognition results, and inputs it into the generation AI, which then generates a 3D model that reflects the user's emotions in the weather information data.

[0672] 5. Optimize and submit the model

[0673] The generation AI returns the generated 3D model to the server, which then optimizes the received 3D model and converts it into a display format (e.g., GLTF format), after which it sends the optimized 3D model to the device.

[0674] 6. Displaying the 3D model

[0675] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Through the AR glasses, the user can check the real-time weather forecast in 3D. The display content is also adjusted based on the user's emotion recognition results.

[0676] Specific examples

[0677] 3D model generation for weather forecasts

[0678] 1. The user taps the "Get Weather Information" button on the smartphone app.

[0679] 2. The device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server.

[0680] 3. The server receives the JSON data and analyzes and extracts the necessary weather information (temperature, humidity, wind speed, precipitation probability, etc.).

[0681] 4. The emotion engine installed on the device analyzes the user's facial expressions and voice to recognize their emotions. The recognition results are sent to the server.

[0682] 5. Based on the weather information and emotion recognition results extracted by the server, a dataset is created to be input into the generation AI and sent to the generation AI.

[0683] 6. The generative AI generates a 3D model of the weather forecast based on the input dataset and emotion recognition results, and returns the result to the server.

[0684] 7. The server converts the received 3D model into GLTF format and sends it to the device (such as AR glasses).

[0685] 8. The device renders the received 3D model and visually displays it to the user, allowing the user to see a real-time weather forecast in 3D. Furthermore, the information is adjusted based on the user's emotions, allowing the user to receive more personalized information.

[0686] The system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI and an emotion engine, manual model creation is eliminated, enabling fast and efficient information visualization and personalization.

[0687] The processing flow will be explained below.

[0688] Step 1:

[0689] A user opens a smartphone application and selects the type of 2D data they want to obtain. For example, the user selects weather information and taps the "Get Weather Information" button.

[0690] Step 2:

[0691] The device accesses the weather information API and requests weather data based on the specified location and time, and obtains two-dimensional data such as temperature, humidity, wind speed, and precipitation probability from the API.

[0692] Step 3:

[0693] The device sends the acquired 2D data to the server, usually using HTTP or HTTPS.

[0694] Step 4:

[0695] The server receives the 2D data sent from the device, analyzes the data format (e.g., JSON), and extracts necessary characteristic information (temperature, humidity, wind speed, precipitation probability, etc.) from the analyzed data.

[0696] Step 5:

[0697] The device's emotion engine collects the user's facial and voice data, recognizes the user's emotions in real time, and generates emotion recognition results (e.g., joy, sadness, surprise, etc.) and sends them to the server.

[0698] Step 6:

[0699] The server receives the emotion recognition results and combines them with the previously extracted feature information to create a dataset, which contains the user's emotion information along with their mood information.

[0700] Step 7:

[0701] The server sends the dataset to the generation AI for input, which analyzes the dataset and begins generating a 3D model based on the user's emotions.

[0702] Step 8:

[0703] The generative AI generates a 3D weather forecast model that reflects the user's emotions based on weather information and emotion recognition results. The generated 3D model is adjusted to have a realistic visual effect.

[0704] Step 9:

[0705] The AI ​​generates a 3D model and returns it to the server, which then optimizes it and converts it into a display format (e.g., GLTF).

[0706] Step 10:

[0707] The server sends the optimized 3D model to the device using fast and efficient data transmission technologies (e.g., HTTP, WebSocket).

[0708] Step 11:

[0709] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Users can check the real-time weather forecast in 3D through the AR glasses. Emotion-based customization allows users to receive personalized information.

[0710] Step 12:

[0711] Users can interact with the displayed 3D model, for example, by moving forward or backward in time to see future or past weather information, and can also select different emotions from the interface to change the displayed content.

[0712] Example 2

[0713] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0714] In today's digital information society, users acquire a wide variety of information, and the amount of information is enormous. Weather information, news, and map information, in particular, change daily, and users need to be able to instantly understand that information. However, traditional two-dimensional data displays often make it difficult to intuitively grasp information. Furthermore, information display does not take into account the user's emotional state, resulting in insufficient personalization. The present invention aims to solve these problems and provide efficient and personalized information.

[0715] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0716] In this invention, the server includes means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, means for receiving and analyzing emotion data from the user terminal, means for generating a 3D model using a generation AI based on the extracted feature information and emotion data, means for optimizing the generated 3D model, converting it into a display format, and transmitting it to the user terminal, and means for displaying the received 3D model on the user terminal. This allows users to easily understand information using intuitive and visual 3D models, and further enables personalized information display based on the user's emotions.

[0717] A "user terminal" is a device operated by a user, and is a general term for devices such as smartphones, tablets, and AR glasses.

[0718] "Two-dimensional data" refers to information data that is spread out on a single plane, and refers to data groups in the form of weather information, news articles, map information, etc.

[0719] "Server" means a computer system that transmits, receives, analyzes, stores, and processes data over a network.

[0720] "Feature information" refers to specific information components such as temperature, humidity, wind speed, and precipitation probability extracted from two-dimensional data.

[0721] "Emotion data" is data that indicates the emotional state of the user, obtained by analyzing the user's facial expressions and voice.

[0722] "Generative AI" refers to artificial intelligence technology that generates new data and models based on input data, and is particularly responsible for generating images and 3D models.

[0723] A "3D model" refers to a three-dimensional digital object used to visually represent weather, map information, etc.

[0724] "Display format" refers to a data format for properly displaying a 3D model on a user terminal, and examples include the GLTF format.

[0725] MODE FOR CARRYING OUT THE INVENTION

[0726] To implement this invention, a user terminal, a server, a generating AI, an emotion engine, and a system that utilizes the Internet are required.

[0727] Hardware and software used

[0728] User devices: Smartphones, tablets, AR glasses, etc. These devices are equipped with internet connectivity, cameras, and microphones. A dedicated application is installed, and an emotion engine is also installed to acquire 2D data and analyze emotion data.

[0729] Server: A high-performance computer system that receives data, analyzes it, creates generative AI models, optimizes them, and transmits them. It includes a database system, an analysis engine, generative AI (e.g., OpenAI's DALL-E), and optimization tools.

[0730] Internet: A communications network for transmitting data between user terminals and servers.

[0731] System operation procedure

[0732] The user device acquires 2D data (e.g., weather information) through user operation and sends it to the server. The server analyzes the received data and extracts feature information such as weather information. At the same time, the user device uses an emotion engine to analyze the user's emotions and sends the results to the server. The server combines the extracted feature information and emotion data to create a dataset to input into the generative AI. The generative AI generates a 3D model based on the input data and returns it to the server. The server optimizes the generated 3D model, converts it into a display format (e.g., GLTF format), and sends it to the user device. Finally, the user device renders the received 3D model and displays it on the user's display device.

[0733] Detailed processing example

[0734] When a user taps the "Get Weather Information" button on a smartphone app, the device sends a request to a weather information API (e.g., OpenWeatherMap API), obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server. The server receives the JSON data, analyzes and extracts the necessary weather information (e.g., temperature, humidity, wind speed, probability of precipitation, etc.). At the same time, the device's built-in emotion engine analyzes the user's facial expressions and voice to recognize the user's emotions. The recognition results are then sent to the server.

[0735] The server creates a dataset to be input into the generation AI based on the extracted weather information and emotion recognition results, and sends it to the generation AI. The generation AI generates a 3D model of the weather forecast corresponding to the emotion based on the input dataset and emotion recognition results, and sends it back to the server. The server optimizes the generated 3D model, converts it to GLTF format, and sends it to the device. The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses).

[0736] Prompt Sentence Examples

[0737] Input: Temperature 25°C, humidity 60%, wind speed 5 m / s, user emotion is happiness

[0738] Output: A 3D model of a sunny weather forecast with a rainbow that reflects happiness

[0739] This system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI and an emotion engine, it eliminates the need for manual model creation, enabling fast and efficient visualization and personalization of information. This system is a powerful tool for aiding information understanding.

[0740] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0741] Step 1:

[0742] Entering data

[0743] The user taps the "Get Weather Information" button on the smartphone app.

[0744] Specific actions

[0745] The user interacts with the app and taps a button to get weather information.

[0746] input

[0747] Input from user actions.

[0748] output

[0749] Weather information request.

[0750] Data processing / calculation

[0751] A request is created and sent to the weather information API.

[0752] Step 2:

[0753] Acquiring and Sending Data

[0754] The device sends a request to the weather information API and sends the retrieved weather data in JSON format to the server.

[0755] Specific actions

[0756] The device accesses the weather information API via the network and obtains current weather information (e.g., temperature, humidity, wind speed).

[0757] Send the obtained JSON data to the server.

[0758] input

[0759] Weather information request

[0760] Weather information API response data (JSON format).

[0761] output

[0762] Obtained weather data.

[0763] Data processing / calculation

[0764] Receives JSON format data and temporarily saves it.

[0765] Convert it into a format to send to the server.

[0766] Step 3:

[0767] Data reception and analysis

[0768] The server analyzes the JSON-formatted weather data it receives and extracts the necessary feature information.

[0769] Specific actions

[0770] The server receives the JSON data.

[0771] Use a data analytics engine to extract key data such as temperature, humidity, and wind speed.

[0772] input

[0773] Weather data in JSON format sent from the device.

[0774] output

[0775] Extracted feature information (e.g., temperature 25°C, humidity 60%, wind speed 5m / s).

[0776] Data processing / calculation

[0777] Analyze the JSON data and extract the necessary items (temperature, humidity, wind speed, etc.).

[0778] The extracted information is stored in an internal database.

[0779] Step 4:

[0780] emotion recognition

[0781] The emotion engine installed in the device analyzes the user's facial expressions and voice to recognize the user's emotional state.

[0782] Specific actions

[0783] The device uses a camera and microphone to capture the user's facial expressions and voice.

[0784] The emotion engine analyzes the user's emotions in real time.

[0785] Send the results to the server.

[0786] input

[0787] User facial and voice data.

[0788] output

[0789] Recognized emotion data (e.g., happiness).

[0790] Data processing / calculation

[0791] Facial expressions and voice are analyzed using analytical algorithms.

[0792] Determine the emotional state and output the results as data.

[0793] Step 5:

[0794] Creating and generating datasets and inputting them into AI

[0795] The server creates a dataset to be input into the generative AI based on the extracted feature information and emotion data.

[0796] Specific actions

[0797] The server combines weather information and emotion data to create a dataset.

[0798] Input this as a prompt to the generation AI.

[0799] input

[0800] Feature information and emotion data.

[0801] output

[0802] Datasets for generative AI.

[0803] Data processing / calculation

[0804] The extracted feature information and emotion data are integrated and converted into a format suitable for generative AI.

[0805] Input this as a prompt to the generation AI.

[0806] Step 6:

[0807] Generating 3D models using generative AI

[0808] The generative AI generates a 3D model based on the input dataset and sends it back to the server.

[0809] Specific actions

[0810] Generative AI generates a 3D model based on the dataset.

[0811] The generated 3D model is sent back to the server.

[0812] input

[0813] Datasets for generative AI.

[0814] output

[0815] Generated 3D model

[0816] Data processing / calculation

[0817] Run an algorithm that analyzes the dataset and generates a 3D model.

[0818] Step 7:

[0819] Optimize and submit the model

[0820] The server optimizes the generated 3D model, converts it into a display format (GLTF format), and then sends it to the user's terminal.

[0821] Specific actions

[0822] The 3D model is made lighter by adjusting the number of polygons, etc.

[0823] Convert to GLTF format.

[0824] The converted model is sent to the user terminal.

[0825] input

[0826] Generated 3D model.

[0827] output

[0828] Optimized 3D model in GLTF format.

[0829] Data processing / calculation

[0830] Optimize the model to improve display efficiency.

[0831] Convert the format to GLTF.

[0832] Step 8:

[0833] 3D model display

[0834] The terminal renders the received 3D model and displays it on the user's display device.

[0835] Specific actions

[0836] The device uses a graphics engine to render the received 3D model.

[0837] The rendered model is displayed on a display device such as AR glasses.

[0838] input

[0839] 3D model in GLTF format sent from the server.

[0840] output

[0841] The 3D model displayed on the user's display device.

[0842] Data processing / calculation

[0843] Render a 3D model.

[0844] Visualize in a format suitable for the display device.

[0845] (Application example 2)

[0846] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0847] Conventional information provision systems have difficulty providing users with personalized real-time information, and are unable to provide information that reflects the user's emotions or current location, particularly in the case of shopping in physical stores. As a result, users are unable to efficiently obtain the information they need, making it difficult to improve their shopping experience.

[0848] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, and means for combining the extracted feature information with the emotion recognition result of the emotion engine and generating a 3D model using a generation AI. This makes it possible to provide personalized real-time information that reflects the user's emotions and current location information.

[0849] A "user terminal" is a device operated by a user and is part of a system that includes smart glasses, smartphones, tablets, etc.

[0850] "Two-dimensional data" refers to information such as weather information, news, and map information expressed in two-dimensional format.

[0851] "Feature information" is important information extracted from two-dimensional data, and refers to specific numerical values ​​and data such as temperature, humidity, price, and inventory quantity.

[0852] The "emotion engine" is a software component that analyzes emotions from the user's facial expressions and voice in real time.

[0853] "Generative AI" is an artificial intelligence system that generates 3D models based on input data, and has the ability to learn features from datasets and generate models.

[0854] A "3D model" is three-dimensional visual information created by the generative AI based on feature information and emotion recognition results, and is visually displayed to the user.

[0855] The "server" is a computer system that receives and analyzes data sent from the user's device, generates a 3D model using generative AI, optimizes it, and sends it to the user's device.

[0856] "Optimization" is a process of converting the generated 3D model into a display format to ensure smooth display on the user's device.

[0857] "Display format" refers to a data format for displaying a 3D model on a user terminal, such as the GLTF format.

[0858] "Emotion recognition result" is data indicating the emotional state analyzed by the emotion engine from the user's facial expressions and voice.

[0859] "Location Sensor" means a hardware component that detects a user's current location, including GPS and other location technologies.

[0860] "Sale information" is data related to discounts and sales on products in stores, and includes information such as price, number of items in stock, and sale end time.

[0861] The system for implementing this invention utilizes a user terminal, a server, a generating AI, an emotion engine, and the Internet. The detailed program processing of the system will be explained below.

[0862] Overall system configuration

[0863] 1. User Device

[0864] A device operated by the user, such as smart glasses, smartphones, or tablets, has a dedicated application installed on the user's device, which recognizes location information and emotions in real time and sends 2D data to a server. It also uses an emotion engine to analyze emotions in real time from the user's facial expressions and voice.

[0865] 2. Server

[0866] The server receives 2D data and emotion recognition results sent from the user device. It analyzes the data and extracts feature information. Based on the extracted feature information and emotion recognition results, it uses generative AI to generate and optimize a 3D model. The optimized 3D model is converted into a display format (e.g., GLTF format) and sent to the user device.

[0867] What the program does

[0868] 1. Enter and submit data

[0869] When a user wears smart glasses with a location sensor and stands in front of a specific location (for example, a sale section in a physical store), the location sensor and camera detect the location. Based on the detected location information, the user's device accesses the API of the inventory management system, obtains real-time data such as sale information, and sends it to the server.

[0870] 2. Data Receipt and Analysis

[0871] The server analyzes the received real-time data and extracts important information such as price, stock quantity, and sale end time.

[0872] 3. Emotion recognition

[0873] The emotion engine installed in the user device analyzes the user's facial expressions and voice to recognize their emotional state, such as interest or surprise, and this recognition result is also sent to the server.

[0874] 4. 3D model generation using generative AI

[0875] The server creates a dataset for the generation AI based on the extracted feature information and emotion recognition results, and inputs this data into the generation AI. The generation AI then generates a 3D model of the sale information, taking into account the emotion recognition results, and returns the result to the server.

[0876] 5. Optimize and submit the model

[0877] The server optimizes the generated 3D model, converts it into a display format such as GLTF format, and then sends it to the user's terminal.

[0878] 6. Displaying the 3D model

[0879] The user device renders the received 3D model and visually displays it to the user through the smart glasses. Based on the user's emotion recognition results, the display content is adjusted, for example, enhancing color when the user is interested, or adding animation when the user is surprised.

[0880] Specific examples

[0881] Displaying special sales information in physical stores

[0882] 1. A user puts on smart glasses and stands in the bargain section of a supermarket.

[0883] 2. The user device uses a sensor to detect its location within the sale section, sends a request to the inventory management system API, and obtains current sale information (price, number of items in stock, sale end time).

[0884] 3. The server analyzes the received inventory information and extracts important information such as price and stock quantity.

[0885] 4. The emotion engine installed on the user device analyzes the user's facial expressions and voice in real time to recognize the user's emotions (e.g., interest or surprise). The recognition results are sent to the server.

[0886] 5. Based on the extracted sale information and emotion recognition results, the server creates a dataset for the generation AI and inputs it. The generation AI generates a 3D model of the sale information according to the emotion and returns the result to the server.

[0887] 6. The server converts the received 3D model into GLTF format and sends it to the user's device.

[0888] 7. The user device renders the received 3D model, and through the smart glasses, the user can check real-time inventory information and sales information corresponding to the sale section in 3D. Furthermore, the display content is adjusted based on the user's emotions.

[0889] Example prompts to input to the generative AI model

[0890] "Generate emotionally relevant 3D models of your sale section's inventory. Use vibrant colors to emphasize interest and add animations for surprise."

[0891] The system allows users to visually view personalized sales information based on their emotions, enhancing the intuitive shopping experience.

[0892] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0893] Step 1:

[0894] A user puts on smart glasses and stands at a specific location in a store. The location sensor and camera on the smart glasses detect this location and capture its location information. The location information becomes input data, which is then sent to a server by an application on the user's device.

[0895] Step 2:

[0896] The server receives location information sent from the user's device. Based on the received location information, the server accesses the inventory management system API and obtains sale information (price, stock quantity, sale end time) related to a specific location in the store. This sale information is analyzed by the server, and characteristic information such as price and stock quantity is extracted.

[0897] Step 3:

[0898] After processing the feature information, the emotion engine installed in the user device analyzes the user's facial expressions and voice in real time. This analysis recognizes the user's emotional state (e.g., interest, surprise). The recognized emotion data is sent from the user device to the server.

[0899] Step 4:

[0900] The server receives the emotion recognition results. The received feature information and the emotion recognition results are combined to create a dataset to be input into the generation AI. This dataset is prompt data that the generation AI uses to generate a 3D model that reflects the user's emotions in the sale information.

[0901] Step 5:

[0902] The generative AI receives the created dataset as input and generates a 3D model based on the sale information. The generated 3D model reflects the user's emotions and visually emphasizes the sale information, and is sent back to the server.

[0903] Step 6:

[0904] The server optimizes the 3D model returned by the AI ​​generator and converts it into an appropriate display format (e.g., GLTF format). The converted 3D model is then sent to the user's device.

[0905] Step 7:

[0906] The user device renders the 3D model received from the server and displays it visually to the user through the smart glasses. Special sale information is displayed in real time as a 3D model, and color enhancement and animation are added based on the user's emotion recognition results. This allows the user to understand the special sale information more intuitively.

[0907] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0908] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0909] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0910] [Third embodiment]

[0911] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0912] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0913] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0914] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0915] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0916] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0917] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0918] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0919] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0920] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0921] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0922] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0923] To implement this invention, a system using a user terminal, a server, a generation AI, and the Internet is required. Below, the processing of the programs that make up this system will be explained in detail in natural language.

[0924] Overall system configuration

[0925] 1. User Device

[0926] The device operated by the user (smartphone, tablet, AR glasses, etc.) uses a dedicated application to acquire 2D data and send it to the server. The specific data input by the user includes information such as weather, news, and maps.

[0927] Example: A user opens a smartphone application and taps the "Get Weather Information" button to get weather information.

[0928] 2. Server

[0929] The server receives the 2D data sent from the user's device, analyzes it, and extracts the necessary feature information. It then inputs the extracted feature information into a generation AI, which automatically generates a 3D model. The generated 3D model is then further optimized and converted into a format suitable for the user's device. The generated 3D model is then sent to the user's device.

[0930] Example: A server receives weather information sent from a smartphone app, analyzes and extracts data such as temperature, humidity, and wind speed, and inputs that data into a generative AI to generate a 3D weather forecast model.

[0931] 3. Generation AI

[0932] Generative AI is responsible for generating 3D models based on datasets provided by the server. For example, it generates 3D models that visually represent cloud movement and temperature distribution based on weather data.

[0933] Example: Generative AI takes temperature, humidity, and wind speed data as input and generates a 3D model to visualize real-time weather forecasts.

[0934] 4. Distribution and display on devices

[0935] The server optimizes the generated 3D model, converts it into an appropriate format, and sends it to the user's device, where it displays the received 3D model, allowing the user to view it in real time.

[0936] Example: The optimized 3D weather model is sent to the AR glasses, allowing users to see the real-time weather forecast in 3D through the glasses.

[0937] Specific examples

[0938] 3D model generation for weather forecasts

[0939] 1. The user taps the "Get Weather Information" button on the smartphone app.

[0940] 2. The device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server.

[0941] 3. The server receives the JSON data and analyzes and extracts the necessary weather information (temperature, humidity, wind speed, precipitation probability, etc.).

[0942] 4. Based on the weather information extracted by the server, a dataset is created to be input into the generation AI and sent to the generation AI.

[0943] 5. The generative AI generates a 3D model of the weather forecast based on the input dataset and returns the results to the server.

[0944] 6. The server converts the received 3D model into GLTF format and sends it to the device (such as AR glasses).

[0945] 7. The device renders the received 3D model and visually displays it to the user, allowing the user to see a real-time weather forecast in 3D.

[0946] The system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI, manual model creation is no longer necessary, enabling fast and efficient information visualization.

[0947] The processing flow will be explained below.

[0948] Step 1:

[0949] The user opens the dedicated application, selects the type of 2D data they want to acquire, and taps the "Get Weather Information" button.

[0950] Step 2:

[0951] The device accesses the weather information API and sends a request to the server, which includes location information, the current time, and other information.

[0952] Step 3:

[0953] The server receives 2D data from a weather information API, usually in JSON format, including information such as temperature, humidity, wind speed, and chance of precipitation.

[0954] Step 4:

[0955] The server analyzes the received JSON data and extracts the necessary characteristic information (temperature, humidity, wind speed, probability of precipitation, etc.).

[0956] Step 5:

[0957] The server creates a dataset based on the extracted feature information to be input into the generative AI. The dataset contains each element of weather information.

[0958] Step 6:

[0959] The server sends the dataset to the generation AI, which then starts the process of generating a 3D model. The generation AI generates a 3D weather forecast model based on the input weather data.

[0960] Step 7:

[0961] The generation AI returns the generated 3D model to the server, which then optimizes the received 3D model and converts it into a display format (e.g., GLTF format).

[0962] Step 8:

[0963] The server sends the optimized 3D model to the device.

[0964] Step 9:

[0965] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Through the AR glasses, the user can check the real-time weather forecast in 3D.

[0966] Step 10:

[0967] If necessary, the user can interact with the displayed 3D model, for example, by moving the time forward or backward to check future or past weather information.

[0968] Example 1

[0969] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0970] In today's information society, there is a growing need for a more intuitive and visual understanding of real-time information such as weather forecasts, news, and map information. However, traditional 2D data often makes it difficult to understand the information, and there is a need for technology to provide information in a format that is easy for users to understand. In particular, there is a lack of technology to efficiently generate 3D models and provide them in a format suitable for the device used by the user. To solve this issue, it is necessary to utilize more advanced data analysis and generative AI technology to quickly and effectively provide 3D models compatible with user devices.

[0971] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0972] In this invention, the server includes means for receiving 2D data from a user terminal, means for the user terminal to acquire 2D data from an external database and transmit it to the server, means for analyzing the received 2D data and extracting feature information, means for generating a 3D model using a generation AI based on the extracted feature information, means for the server to optimize the generated 3D model, convert it into a display format, and transmit it to the user terminal, and means for displaying the received 3D model on the user terminal. This allows information to be understood intuitively and visually, and makes it possible to efficiently generate and optimize 3D models and provide them in a form suitable for the user terminal.

[0973] A "user terminal" is a terminal operated by a user, and includes devices such as smartphones, tablets, and AR glasses.

[0974] "Two-dimensional data" is data that includes information such as weather, news, and maps, and is a data format that users acquire and send.

[0975] An "external database" is a repository of data that can be accessed via the Internet, such as a weather API or news API.

[0976] The "server" is a central processing unit that receives and analyzes data sent from the user terminal and provides the data to the generation AI.

[0977] "Feature information" is specific information such as temperature, humidity, and wind speed that is extracted by analyzing the two-dimensional data sent from the user terminal.

[0978] "Generative AI" is an artificial intelligence technology for generating 3D models based on feature information provided by a server.

[0979] A "3D model" is visually represented three-dimensional information generated based on 2D data and feature information.

[0980] A "display format" is a data format for appropriately displaying a 3D model on a user terminal, and includes the GLTF format.

[0981] "Optimization" is the process of streamlining the data volume and structure of the generated 3D model and converting it into a form suitable for the user's device.

[0982] "Rendering" is a process for visually displaying a 3D model received by a user terminal.

[0983] MODE FOR CARRYING OUT THE INVENTION

[0984] To implement this invention, a system using a user terminal, a server, a generation AI, and the Internet is required. Below, the processing of the programs that make up this system will be explained in detail in natural language.

[0985] Overall system configuration

[0986] User terminal

[0987] A dedicated application is installed on the user's device (smartphone, tablet, AR glasses, etc.). This application acquires 2D data from the user and sends it to the server. Specifically, when the user taps the "Get Weather Information" button, a request is sent to the weather API, current weather information is acquired, and it is sent to the server.

[0988] server

[0989] The server receives and analyzes the 2D data sent from the user's device. During the analysis, feature information such as temperature, humidity, and wind speed is extracted. The analysis is performed using the Python pandas library. A dataset is then created based on the extracted feature information and sent to the generation AI.

[0990] Generation AI

[0991] The generative AI generates a 3D model based on the dataset provided by the server. This generation process uses deep learning libraries such as TensorFlow and PyTorch. The generated 3D model visually represents, for example, cloud movement and temperature distribution.

[0992] Distribution and display on terminals

[0993] The server optimizes the generated 3D model and converts it into a format suitable for the user device (e.g., GLTF format). The server then sends the optimized model to the user device. The user device then renders and displays the received 3D model. This allows the user to intuitively and visually confirm real-time information.

[0994] Specific examples

[0995] 3D model generation for weather forecasts

[0996] When a user taps the "Get Weather Information" button on a smartphone app, the device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server. The server receives the JSON data, analyzes and extracts weather information such as temperature, humidity, and wind speed. The server then creates a dataset based on the extracted weather information and sends it to the generation AI. The generation AI generates a 3D model of the weather forecast based on the dataset and returns the result to the server. The server converts the received 3D model into GLTF format and sends it to the device. The device renders the received 3D model, allowing the user to view the real-time weather forecast in 3D.

[0997] Example prompt:

[0998] By tapping the "Get Weather Information" button, the device sends a request to the weather API to obtain current weather information. The data sent to the server is then analyzed to create a dataset to input into the generation AI. The generation AI generates a 3D model based on the dataset and sends the optimized model to the device. The device then renders the 3D model and displays it to the user.

[0999] This system allows users to intuitively and visually understand information such as weather, news, maps, etc. By utilizing generative AI, manual model creation is no longer necessary, enabling fast and efficient information visualization.

[1000] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1001] Step 1:

[1002] The user initiates an action

[1003] A user opens a smartphone application and taps the "Get Weather Information" button. This initiates an operation. The input is the user's action, and the output is a request to get weather information.

[1004] Step 2:

[1005] The device retrieves weather data

[1006] The device sends a request to the weather API to obtain current weather information. For example, access "https: / / api.weather.com / v3 / wx / conditions / current?apiKey=YOUR_API_KEY&format=json". The input is the API request, and the output is JSON data containing weather data such as temperature, humidity, and wind speed. The device sends this data to the server.

[1007] Step 3:

[1008] The server receives and analyzes the data

[1009] The server receives JSON data sent from the device. It analyzes the received data and extracts feature information such as temperature, humidity, and wind speed. The Python pandas library is used for analysis. The input is JSON data, and the output is the extracted feature information.

[1010] Step 4:

[1011] The server sends the data to the generated AI.

[1012] The server creates a dataset based on the extracted feature information and sends the dataset to the generation AI. The data is then formatted into the format required by the generation AI and sent. The input is the feature information and dataset, and the output is data sent to the generation AI.

[1013] Step 5:

[1014] Generative AI generates 3D models

[1015] The generative AI generates a 3D model based on a dataset provided by the server. The generation process uses deep learning libraries such as TensorFlow and PyTorch. The input is the dataset, and the output is the generated 3D model.

[1016] Step 6:

[1017] The server optimizes the 3D model

[1018] The server optimizes the generated 3D model and converts it into a format suitable for the user's device (e.g., GLTF format) using an appropriate optimization algorithm. The input is the generated 3D model, and the output is the optimized 3D model.

[1019] Step 7:

[1020] Display the optimized model for your device

[1021] The user device receives the optimized 3D model, renders it, and displays it. Rendering is performed in real time using a game engine such as Unity. The input is the optimized 3D model, and the output is a visual display of the rendered 3D model.

[1022] (Application example 1)

[1023] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1024] Conventional factory monitoring systems mainly display two-dimensional data, making it difficult to intuitively grasp the overall status of the factory in real time. In addition, it was necessary to monitor various sensor data individually, which made it difficult to manage efficiently.

[1025] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1026] In this invention, the server includes means for collecting various sensor data in the factory and converting it into a 3D model in real time for monitoring, means for optimizing the generated 3D model and transmitting it to a user terminal, and means for displaying the received 3D model on the user terminal, thereby enabling the status in the factory to be intuitively and visually grasped in real time using the 3D model.

[1027] A "user terminal" is a device operated by a user, and includes devices such as smartphones, tablets, and AR glasses.

[1028] "Two-dimensional data" refers to data that is written in a two-dimensional format, such as weather information, news, and map information.

[1029] "Feature information" is information with specific attributes or patterns extracted from analyzed two-dimensional data.

[1030] "Generative AI" is an artificial intelligence system that automatically generates 3D models based on an input dataset.

[1031] A "3D model" is three-dimensional visual data created by generative AI and displayed in a way that users can intuitively understand.

[1032] "Sensor data" is data collected from sensors that measure temperature, humidity, machine operating status, etc. within the factory.

[1033] "Real-time" means the immediacy in time that data is collected, processed and displayed at approximately the same time.

[1034] "Monitoring" is the process of continuously observing conditions within a factory to detect abnormalities or changes.

[1035] "Optimization" is the process of adjusting and converting the generated 3D model so that it can be displayed efficiently on the user's device.

[1036] This invention is a system for monitoring the status of a factory in real time as a 3D model. This system mainly uses user terminals, a server, a generating AI, and the Internet.

[1037] Overall system configuration

[1038] 1. User Device:

[1039] The user terminal is a device such as a smartphone or smart glasses. The user terminal collects various sensor data within the factory and transmits the data to a server, allowing the status within the factory to be monitored in real time.

[1040] 2. Server:

[1041] The server receives and analyzes the sensor data sent from the user device, extracts feature information, and then uses generative AI to generate a 3D model based on the extracted feature information. The generated model is then optimized and sent to the user device.

[1042] 3. Generation AI:

[1043] The generative AI uses data sets provided by the server to generate 3D models, such as those based on sensor data on temperature, humidity, and machine operation status, to generate 3D models that visually represent the real-time situation inside a factory.

[1044] 4. Distribution and display on devices:

[1045] The 3D model sent from the server is displayed on the user's device, allowing the user to check the real-time situation inside the factory using smart glasses or a smartphone.

[1046] Hardware and software used

[1047] User devices: smartphones, smart glasses

[1048] Server: High performance server

[1049] Generative AI: High-performance generative AI systems (e.g., OpenAI)

[1050] Communication technologies: Internet, HTTP requests

[1051] Data processing flow

[1052] User devices collect sensor data such as temperature, humidity, and machine operation status within the factory. This data is sent to the server using HTTP requests. The server analyzes the received data and extracts feature information. The extracted information is input into a generative AI, which generates a 3D model in real time. The generated model is optimized and then sent to the user's device, where the user can visually view it.

[1053] Specific examples

[1054] If the factory temperature exceeds 50 degrees, a red warning area will be displayed in the generated 3D model. Also, if a specific machine is stopped, an icon indicating this will be displayed on the factory map. This makes it possible to immediately detect and deal with abnormal conditions within the factory.

[1055] Prompt Sentence Examples

[1056] "The temperature has risen to 55 degrees and the humidity is at 40%. Machine_A is running, but Machine_B is stopped."

[1057] By inputting this prompt, the generative AI will generate a detailed 3D model like this:

[1058] "Generated 3D model with areas marked in red for high temperature and icons indicating machine statuses"

[1059] The system and process of this invention allows for intuitive understanding of conditions within a factory in real time, enabling efficient management and anomaly detection.

[1060] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1061] Step 1:

[1062] Data collection from user devices

[1063] The user terminal collects various sensor data from within the factory (temperature, humidity, machine operation status, etc.) The data obtained from the sensors is collected in real time and handled as a single data set.

[1064] Input: Various sensor data

[1065] Output: Collected dataset

[1066] Step 2:

[1067] Sending data from the user device to the server

[1068] The user device sends the collected data set to the server using an HTTP request, which includes information such as temperature, humidity, and machine operation status.

[1069] Input: Collected dataset

[1070] Output: Request to send data to the server

[1071] Step 3:

[1072] Data analysis by server

[1073] The server receives the data set and analyzes it, extracting temperature and humidity data, as well as machine operating status. This analyzed data is then formatted into specific feature information.

[1074] Input: Dataset

[1075] Output: Feature information

[1076] Step 4:

[1077] Input to AI for generating feature information

[1078] The server sends the extracted feature information as a dataset to the generation AI, which then generates prompt sentences in a specific format and inputs them to the AI.

[1079] Input: feature information

[1080] Output: prompt statement

[1081] Step 5:

[1082] Generating 3D models using generative AI

[1083] The generative AI generates a 3D model based on the received prompt text. This model visually represents the factory status and provides an intuitive understanding of abnormal conditions and functions.

[1084] Input: prompt statement

[1085] Output: 3D model data

[1086] Step 6:

[1087] 3D model optimization by server

[1088] The generated 3D model is optimized by the server. The optimized 3D model is then adjusted so that it can be displayed efficiently on the user's device. This optimization process involves converting the file format and reducing the file size.

[1089] Input: 3D model data

[1090] Output: Optimized 3D model data

[1091] Step 7:

[1092] Sending the optimized 3D model to the user device

[1093] The server sends the optimized 3D model to the user's device using an HTTP POST request, which then displays the data appropriately on the user's device.

[1094] Input: Optimized 3D model data

[1095] Output: Request to send data to the user terminal

[1096] Step 8:

[1097] Display of 3D models on user devices

[1098] The user device displays the received 3D model, and the real-time situation inside the factory is visualized in 3D on the display of smart glasses or a smartphone, allowing the user to check it.

[1099] Input: Optimized 3D model data

[1100] Output: A representation of the 3D model as seen by the user

[1101] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1102] To implement this invention, a system using a user terminal, a server, a generation AI, an emotion engine, and the Internet is required. Below, the processing of the programs that make up this system will be explained in natural language.

[1103] Overall system configuration

[1104] 1. User Device

[1105] The device operated by the user (smartphone, tablet, AR glasses, etc.) uses a dedicated application to acquire 2D data and send it to a server. It also has an emotion engine that recognizes the user's emotions in real time. Specific data input by the user includes information such as weather, news, and maps.

[1106] Explaining program processing in natural language

[1107] 1. Enter and submit data

[1108] The user opens the smartphone application and selects the type of 2D data they want to acquire. For example, they select weather information and tap the "Get Weather Information" button. The device accesses the weather information API and sends the acquired data to the server.

[1109] 2. Data Receipt and Analysis

[1110] The server receives two-dimensional data from the weather information API, analyzes it, and extracts the necessary characteristic information (temperature, humidity, wind speed, probability of precipitation, etc.).

[1111] 3. Emotion recognition

[1112] The emotion engine installed on the device analyzes the user's facial expressions and voice in real time to recognize the user's emotions, and this recognition result is also sent to the server.

[1113] 4. 3D model generation using generative AI

[1114] The server creates a dataset for the generation AI based on the analyzed data and emotion recognition results, and inputs it into the generation AI, which then generates a 3D model that reflects the user's emotions in the weather information data.

[1115] 5. Optimize and submit the model

[1116] The generation AI returns the generated 3D model to the server, which then optimizes the received 3D model and converts it into a display format (e.g., GLTF format), after which it sends the optimized 3D model to the device.

[1117] 6. Displaying the 3D model

[1118] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Through the AR glasses, the user can check the real-time weather forecast in 3D. The display content is also adjusted based on the user's emotion recognition results.

[1119] Specific examples

[1120] 3D model generation for weather forecasts

[1121] 1. The user taps the "Get Weather Information" button on the smartphone app.

[1122] 2. The device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server.

[1123] 3. The server receives the JSON data and analyzes and extracts the necessary weather information (temperature, humidity, wind speed, precipitation probability, etc.).

[1124] 4. The emotion engine installed on the device analyzes the user's facial expressions and voice to recognize their emotions. The recognition results are sent to the server.

[1125] 5. Based on the weather information and emotion recognition results extracted by the server, a dataset is created to be input into the generation AI and sent to the generation AI.

[1126] 6. The generative AI generates a 3D model of the weather forecast based on the input dataset and emotion recognition results, and returns the result to the server.

[1127] 7. The server converts the received 3D model into GLTF format and sends it to the device (such as AR glasses).

[1128] 8. The device renders the received 3D model and visually displays it to the user, allowing the user to see a real-time weather forecast in 3D. Furthermore, the information is adjusted based on the user's emotions, allowing the user to receive more personalized information.

[1129] The system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI and an emotion engine, manual model creation is eliminated, enabling fast and efficient information visualization and personalization.

[1130] The processing flow will be explained below.

[1131] Step 1:

[1132] A user opens a smartphone application and selects the type of 2D data they want to obtain. For example, the user selects weather information and taps the "Get Weather Information" button.

[1133] Step 2:

[1134] The device accesses the weather information API and requests weather data based on the specified location and time, and obtains two-dimensional data such as temperature, humidity, wind speed, and precipitation probability from the API.

[1135] Step 3:

[1136] The device sends the acquired 2D data to the server, usually using HTTP or HTTPS.

[1137] Step 4:

[1138] The server receives the 2D data sent from the device, analyzes the data format (e.g., JSON), and extracts necessary characteristic information (temperature, humidity, wind speed, precipitation probability, etc.) from the analyzed data.

[1139] Step 5:

[1140] The device's emotion engine collects the user's facial and voice data, recognizes the user's emotions in real time, and generates emotion recognition results (e.g., joy, sadness, surprise, etc.) and sends them to the server.

[1141] Step 6:

[1142] The server receives the emotion recognition results and combines them with the previously extracted feature information to create a dataset, which contains the user's emotion information along with their mood information.

[1143] Step 7:

[1144] The server sends the dataset to the generation AI for input, which analyzes the dataset and begins generating a 3D model based on the user's emotions.

[1145] Step 8:

[1146] The generative AI generates a 3D weather forecast model that reflects the user's emotions based on weather information and emotion recognition results. The generated 3D model is adjusted to have a realistic visual effect.

[1147] Step 9:

[1148] The AI ​​generates a 3D model and returns it to the server, which then optimizes it and converts it into a display format (e.g., GLTF).

[1149] Step 10:

[1150] The server sends the optimized 3D model to the device using fast and efficient data transmission technologies (e.g., HTTP, WebSocket).

[1151] Step 11:

[1152] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Users can check the real-time weather forecast in 3D through the AR glasses. Emotion-based customization allows users to receive personalized information.

[1153] Step 12:

[1154] Users can interact with the displayed 3D model, for example, by moving forward or backward in time to see future or past weather information, and can also select different emotions from the interface to change the displayed content.

[1155] Example 2

[1156] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1157] In today's digital information society, users acquire a wide variety of information, and the amount of information is enormous. Weather information, news, and map information, in particular, change daily, and users need to be able to instantly understand that information. However, traditional two-dimensional data displays often make it difficult to intuitively grasp information. Furthermore, information display does not take into account the user's emotional state, resulting in insufficient personalization. The present invention aims to solve these problems and provide efficient and personalized information.

[1158] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1159] In this invention, the server includes means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, means for receiving and analyzing emotion data from the user terminal, means for generating a 3D model using a generation AI based on the extracted feature information and emotion data, means for optimizing the generated 3D model, converting it into a display format, and transmitting it to the user terminal, and means for displaying the received 3D model on the user terminal. This allows users to easily understand information using intuitive and visual 3D models, and further enables personalized information display based on the user's emotions.

[1160] A "user terminal" is a device operated by a user, and is a general term for devices such as smartphones, tablets, and AR glasses.

[1161] "Two-dimensional data" refers to information data that is spread out on a single plane, and refers to data groups in the form of weather information, news articles, map information, etc.

[1162] "Server" means a computer system that transmits, receives, analyzes, stores, and processes data over a network.

[1163] "Feature information" refers to specific information components such as temperature, humidity, wind speed, and precipitation probability extracted from two-dimensional data.

[1164] "Emotion data" is data that indicates the emotional state of the user, obtained by analyzing the user's facial expressions and voice.

[1165] "Generative AI" refers to artificial intelligence technology that generates new data and models based on input data, and is particularly responsible for generating images and 3D models.

[1166] A "3D model" refers to a three-dimensional digital object used to visually represent weather, map information, etc.

[1167] "Display format" refers to a data format for properly displaying a 3D model on a user terminal, and examples include the GLTF format.

[1168] MODE FOR CARRYING OUT THE INVENTION

[1169] To implement this invention, a user terminal, a server, a generating AI, an emotion engine, and a system that utilizes the Internet are required.

[1170] Hardware and software used

[1171] User devices: Smartphones, tablets, AR glasses, etc. These devices are equipped with internet connectivity, cameras, and microphones. A dedicated application is installed, and an emotion engine is also installed to acquire 2D data and analyze emotion data.

[1172] Server: A high-performance computer system that receives data, analyzes it, creates generative AI models, optimizes them, and transmits them. It includes a database system, an analysis engine, generative AI (e.g., OpenAI's DALL-E), and optimization tools.

[1173] Internet: A communications network for transmitting data between user terminals and servers.

[1174] System operation procedure

[1175] The user device acquires 2D data (e.g., weather information) through user operation and sends it to the server. The server analyzes the received data and extracts feature information such as weather information. At the same time, the user device uses an emotion engine to analyze the user's emotions and sends the results to the server. The server combines the extracted feature information and emotion data to create a dataset to input into the generative AI. The generative AI generates a 3D model based on the input data and returns it to the server. The server optimizes the generated 3D model, converts it into a display format (e.g., GLTF format), and sends it to the user device. Finally, the user device renders the received 3D model and displays it on the user's display device.

[1176] Detailed processing example

[1177] When a user taps the "Get Weather Information" button on a smartphone app, the device sends a request to a weather information API (e.g., OpenWeatherMap API), obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server. The server receives the JSON data, analyzes and extracts the necessary weather information (e.g., temperature, humidity, wind speed, probability of precipitation, etc.). At the same time, the device's built-in emotion engine analyzes the user's facial expressions and voice to recognize the user's emotions. The recognition results are then sent to the server.

[1178] The server creates a dataset to be input into the generation AI based on the extracted weather information and emotion recognition results, and sends it to the generation AI. The generation AI generates a 3D model of the weather forecast corresponding to the emotion based on the input dataset and emotion recognition results, and sends it back to the server. The server optimizes the generated 3D model, converts it to GLTF format, and sends it to the device. The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses).

[1179] Prompt Sentence Examples

[1180] Input: Temperature 25°C, humidity 60%, wind speed 5 m / s, user emotion is happiness

[1181] Output: A 3D model of a sunny weather forecast with a rainbow that reflects happiness

[1182] This system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI and an emotion engine, it eliminates the need for manual model creation, enabling fast and efficient visualization and personalization of information. This system is a powerful tool for aiding information understanding.

[1183] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1184] Step 1:

[1185] Entering data

[1186] The user taps the "Get Weather Information" button on the smartphone app.

[1187] Specific actions

[1188] The user interacts with the app and taps a button to get weather information.

[1189] input

[1190] Input from user actions.

[1191] output

[1192] Weather information request.

[1193] Data processing / calculation

[1194] A request is created and sent to the weather information API.

[1195] Step 2:

[1196] Acquiring and Sending Data

[1197] The device sends a request to the weather information API and sends the retrieved weather data in JSON format to the server.

[1198] Specific actions

[1199] The device accesses the weather information API via the network and obtains current weather information (e.g., temperature, humidity, wind speed).

[1200] Send the obtained JSON data to the server.

[1201] input

[1202] Weather information request

[1203] Weather information API response data (JSON format).

[1204] output

[1205] Obtained weather data.

[1206] Data processing / calculation

[1207] Receives JSON format data and temporarily saves it.

[1208] Convert it into a format to send to the server.

[1209] Step 3:

[1210] Data reception and analysis

[1211] The server analyzes the JSON-formatted weather data it receives and extracts the necessary feature information.

[1212] Specific actions

[1213] The server receives the JSON data.

[1214] Use a data analytics engine to extract key data such as temperature, humidity, and wind speed.

[1215] input

[1216] Weather data in JSON format sent from the device.

[1217] output

[1218] Extracted feature information (e.g., temperature 25°C, humidity 60%, wind speed 5m / s).

[1219] Data processing / calculation

[1220] Analyze the JSON data and extract the necessary items (temperature, humidity, wind speed, etc.).

[1221] The extracted information is stored in an internal database.

[1222] Step 4:

[1223] emotion recognition

[1224] The emotion engine installed in the device analyzes the user's facial expressions and voice to recognize the user's emotional state.

[1225] Specific actions

[1226] The device uses a camera and microphone to capture the user's facial expressions and voice.

[1227] The emotion engine analyzes the user's emotions in real time.

[1228] Send the results to the server.

[1229] input

[1230] User facial and voice data.

[1231] output

[1232] Recognized emotion data (e.g., happiness).

[1233] Data processing / calculation

[1234] Facial expressions and voice are analyzed using analytical algorithms.

[1235] Determine the emotional state and output the results as data.

[1236] Step 5:

[1237] Creating and generating datasets and inputting them into AI

[1238] The server creates a dataset to be input into the generative AI based on the extracted feature information and emotion data.

[1239] Specific actions

[1240] The server combines weather information and emotion data to create a dataset.

[1241] Input this as a prompt to the generation AI.

[1242] input

[1243] Feature information and emotion data.

[1244] output

[1245] Datasets for generative AI.

[1246] Data processing / calculation

[1247] The extracted feature information and emotion data are integrated and converted into a format suitable for generative AI.

[1248] Input this as a prompt to the generation AI.

[1249] Step 6:

[1250] Generating 3D models using generative AI

[1251] The generative AI generates a 3D model based on the input dataset and sends it back to the server.

[1252] Specific actions

[1253] Generative AI generates a 3D model based on the dataset.

[1254] The generated 3D model is sent back to the server.

[1255] input

[1256] Datasets for generative AI.

[1257] output

[1258] Generated 3D model

[1259] Data processing / calculation

[1260] Run an algorithm that analyzes the dataset and generates a 3D model.

[1261] Step 7:

[1262] Optimize and submit the model

[1263] The server optimizes the generated 3D model, converts it into a display format (GLTF format), and then sends it to the user's terminal.

[1264] Specific actions

[1265] The 3D model is made lighter by adjusting the number of polygons, etc.

[1266] Convert to GLTF format.

[1267] The converted model is sent to the user terminal.

[1268] input

[1269] Generated 3D model.

[1270] output

[1271] Optimized 3D model in GLTF format.

[1272] Data processing / calculation

[1273] Optimize the model to improve display efficiency.

[1274] Convert the format to GLTF.

[1275] Step 8:

[1276] 3D model display

[1277] The terminal renders the received 3D model and displays it on the user's display device.

[1278] Specific actions

[1279] The device uses a graphics engine to render the received 3D model.

[1280] The rendered model is displayed on a display device such as AR glasses.

[1281] input

[1282] 3D model in GLTF format sent from the server.

[1283] output

[1284] The 3D model displayed on the user's display device.

[1285] Data processing / calculation

[1286] Render a 3D model.

[1287] Visualize in a format suitable for the display device.

[1288] (Application example 2)

[1289] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1290] Conventional information provision systems have difficulty providing users with personalized real-time information, and are unable to provide information that reflects the user's emotions or current location, particularly in the case of shopping in physical stores. As a result, users are unable to efficiently obtain the information they need, making it difficult to improve their shopping experience.

[1291] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, and means for combining the extracted feature information with the emotion recognition result of the emotion engine and generating a 3D model using a generation AI. This makes it possible to provide personalized real-time information that reflects the user's emotions and current location information.

[1292] A "user terminal" is a device operated by a user and is part of a system that includes smart glasses, smartphones, tablets, etc.

[1293] "Two-dimensional data" refers to information such as weather information, news, and map information expressed in two-dimensional format.

[1294] "Feature information" is important information extracted from two-dimensional data, and refers to specific numerical values ​​and data such as temperature, humidity, price, and inventory quantity.

[1295] The "emotion engine" is a software component that analyzes emotions from the user's facial expressions and voice in real time.

[1296] "Generative AI" is an artificial intelligence system that generates 3D models based on input data, and has the ability to learn features from datasets and generate models.

[1297] A "3D model" is three-dimensional visual information created by the generative AI based on feature information and emotion recognition results, and is visually displayed to the user.

[1298] The "server" is a computer system that receives and analyzes data sent from the user's device, generates a 3D model using generative AI, optimizes it, and sends it to the user's device.

[1299] "Optimization" is a process of converting the generated 3D model into a display format to ensure smooth display on the user's device.

[1300] "Display format" refers to a data format for displaying a 3D model on a user terminal, such as the GLTF format.

[1301] "Emotion recognition result" is data indicating the emotional state analyzed by the emotion engine from the user's facial expressions and voice.

[1302] "Location Sensor" means a hardware component that detects a user's current location, including GPS and other location technologies.

[1303] "Sale information" is data related to discounts and sales on products in stores, and includes information such as price, number of items in stock, and sale end time.

[1304] The system for implementing this invention utilizes a user terminal, a server, a generating AI, an emotion engine, and the Internet. The detailed program processing of the system will be explained below.

[1305] Overall system configuration

[1306] 1. User Device

[1307] A device operated by the user, such as smart glasses, smartphones, or tablets, has a dedicated application installed on the user's device, which recognizes location information and emotions in real time and sends 2D data to a server. It also uses an emotion engine to analyze emotions in real time from the user's facial expressions and voice.

[1308] 2. Server

[1309] The server receives 2D data and emotion recognition results sent from the user device. It analyzes the data and extracts feature information. Based on the extracted feature information and emotion recognition results, it uses generative AI to generate and optimize a 3D model. The optimized 3D model is converted into a display format (e.g., GLTF format) and sent to the user device.

[1310] What the program does

[1311] 1. Enter and submit data

[1312] When a user wears smart glasses with a location sensor and stands in front of a specific location (for example, a sale section in a physical store), the location sensor and camera detect the location. Based on the detected location information, the user's device accesses the API of the inventory management system, obtains real-time data such as sale information, and sends it to the server.

[1313] 2. Data Receipt and Analysis

[1314] The server analyzes the received real-time data and extracts important information such as price, stock quantity, and sale end time.

[1315] 3. Emotion recognition

[1316] The emotion engine installed in the user device analyzes the user's facial expressions and voice to recognize their emotional state, such as interest or surprise, and this recognition result is also sent to the server.

[1317] 4. 3D model generation using generative AI

[1318] The server creates a dataset for the generation AI based on the extracted feature information and emotion recognition results, and inputs this data into the generation AI. The generation AI then generates a 3D model of the sale information, taking into account the emotion recognition results, and returns the result to the server.

[1319] 5. Optimize and submit the model

[1320] The server optimizes the generated 3D model, converts it into a display format such as GLTF format, and then sends it to the user's terminal.

[1321] 6. Displaying the 3D model

[1322] The user device renders the received 3D model and visually displays it to the user through the smart glasses. Based on the user's emotion recognition results, the display content is adjusted, for example, enhancing color when the user is interested, or adding animation when the user is surprised.

[1323] Specific examples

[1324] Displaying special sales information in physical stores

[1325] 1. A user puts on smart glasses and stands in the bargain section of a supermarket.

[1326] 2. The user device uses a sensor to detect its location within the sale section, sends a request to the inventory management system API, and obtains current sale information (price, number of items in stock, sale end time).

[1327] 3. The server analyzes the received inventory information and extracts important information such as price and stock quantity.

[1328] 4. The emotion engine installed on the user device analyzes the user's facial expressions and voice in real time to recognize the user's emotions (e.g., interest or surprise). The recognition results are sent to the server.

[1329] 5. Based on the extracted sale information and emotion recognition results, the server creates a dataset for the generation AI and inputs it. The generation AI generates a 3D model of the sale information according to the emotion and returns the result to the server.

[1330] 6. The server converts the received 3D model into GLTF format and sends it to the user's device.

[1331] 7. The user device renders the received 3D model, and through the smart glasses, the user can check real-time inventory information and sales information corresponding to the sale section in 3D. Furthermore, the display content is adjusted based on the user's emotions.

[1332] Example prompts to input to the generative AI model

[1333] "Generate emotionally relevant 3D models of your sale section's inventory. Use vibrant colors to emphasize interest and add animations for surprise."

[1334] The system allows users to visually view personalized sales information based on their emotions, enhancing the intuitive shopping experience.

[1335] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1336] Step 1:

[1337] A user puts on smart glasses and stands at a specific location in a store. The location sensor and camera on the smart glasses detect this location and capture its location information. The location information becomes input data, which is then sent to a server by an application on the user's device.

[1338] Step 2:

[1339] The server receives location information sent from the user's device. Based on the received location information, the server accesses the inventory management system API and obtains sale information (price, stock quantity, sale end time) related to a specific location in the store. This sale information is analyzed by the server, and characteristic information such as price and stock quantity is extracted.

[1340] Step 3:

[1341] After processing the feature information, the emotion engine installed in the user device analyzes the user's facial expressions and voice in real time. This analysis recognizes the user's emotional state (e.g., interest, surprise). The recognized emotion data is sent from the user device to the server.

[1342] Step 4:

[1343] The server receives the emotion recognition results. The received feature information and the emotion recognition results are combined to create a dataset to be input into the generation AI. This dataset is prompt data that the generation AI uses to generate a 3D model that reflects the user's emotions in the sale information.

[1344] Step 5:

[1345] The generative AI receives the created dataset as input and generates a 3D model based on the sale information. The generated 3D model reflects the user's emotions and visually emphasizes the sale information, and is sent back to the server.

[1346] Step 6:

[1347] The server optimizes the 3D model returned by the AI ​​generator and converts it into an appropriate display format (e.g., GLTF format). The converted 3D model is then sent to the user's device.

[1348] Step 7:

[1349] The user device renders the 3D model received from the server and displays it visually to the user through the smart glasses. Special sale information is displayed in real time as a 3D model, and color enhancement and animation are added based on the user's emotion recognition results. This allows the user to understand the special sale information more intuitively.

[1350] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1351] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1352] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1353] [Fourth embodiment]

[1354] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1355] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1356] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1357] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1358] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1359] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1360] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1361] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1362] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1363] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1364] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1365] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1366] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1367] To implement this invention, a system using a user terminal, a server, a generation AI, and the Internet is required. Below, the processing of the programs that make up this system will be explained in detail in natural language.

[1368] Overall system configuration

[1369] 1. User Device

[1370] The device operated by the user (smartphone, tablet, AR glasses, etc.) uses a dedicated application to acquire 2D data and send it to the server. The specific data input by the user includes information such as weather, news, and maps.

[1371] Example: A user opens a smartphone application and taps the "Get Weather Information" button to get weather information.

[1372] 2. Server

[1373] The server receives the 2D data sent from the user's device, analyzes it, and extracts the necessary feature information. It then inputs the extracted feature information into a generation AI, which automatically generates a 3D model. The generated 3D model is then further optimized and converted into a format suitable for the user's device. The generated 3D model is then sent to the user's device.

[1374] Example: A server receives weather information sent from a smartphone app, analyzes and extracts data such as temperature, humidity, and wind speed, and inputs that data into a generative AI to generate a 3D weather forecast model.

[1375] 3. Generation AI

[1376] Generative AI is responsible for generating 3D models based on datasets provided by the server. For example, it generates 3D models that visually represent cloud movement and temperature distribution based on weather data.

[1377] Example: Generative AI takes temperature, humidity, and wind speed data as input and generates a 3D model to visualize real-time weather forecasts.

[1378] 4. Distribution and display on devices

[1379] The server optimizes the generated 3D model, converts it into an appropriate format, and sends it to the user's device, where it displays the received 3D model, allowing the user to view it in real time.

[1380] Example: The optimized 3D weather model is sent to the AR glasses, allowing users to see the real-time weather forecast in 3D through the glasses.

[1381] Specific examples

[1382] 3D model generation for weather forecasts

[1383] 1. The user taps the "Get Weather Information" button on the smartphone app.

[1384] 2. The device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server.

[1385] 3. The server receives the JSON data and analyzes and extracts the necessary weather information (temperature, humidity, wind speed, precipitation probability, etc.).

[1386] 4. Based on the weather information extracted by the server, a dataset is created to be input into the generation AI and sent to the generation AI.

[1387] 5. The generative AI generates a 3D model of the weather forecast based on the input dataset and returns the results to the server.

[1388] 6. The server converts the received 3D model into GLTF format and sends it to the device (such as AR glasses).

[1389] 7. The device renders the received 3D model and visually displays it to the user, allowing the user to see a real-time weather forecast in 3D.

[1390] The system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI, manual model creation is no longer necessary, enabling fast and efficient information visualization.

[1391] The processing flow will be explained below.

[1392] Step 1:

[1393] The user opens the dedicated application, selects the type of 2D data they want to acquire, and taps the "Get Weather Information" button.

[1394] Step 2:

[1395] The device accesses the weather information API and sends a request to the server, which includes location information, the current time, and other information.

[1396] Step 3:

[1397] The server receives 2D data from a weather information API, usually in JSON format, including information such as temperature, humidity, wind speed, and chance of precipitation.

[1398] Step 4:

[1399] The server analyzes the received JSON data and extracts the necessary characteristic information (temperature, humidity, wind speed, probability of precipitation, etc.).

[1400] Step 5:

[1401] The server creates a dataset based on the extracted feature information to be input into the generative AI. The dataset contains each element of weather information.

[1402] Step 6:

[1403] The server sends the dataset to the generation AI, which then starts the process of generating a 3D model. The generation AI generates a 3D weather forecast model based on the input weather data.

[1404] Step 7:

[1405] The generation AI returns the generated 3D model to the server, which then optimizes the received 3D model and converts it into a display format (e.g., GLTF format).

[1406] Step 8:

[1407] The server sends the optimized 3D model to the device.

[1408] Step 9:

[1409] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Through the AR glasses, the user can check the real-time weather forecast in 3D.

[1410] Step 10:

[1411] If necessary, the user can interact with the displayed 3D model, for example, by moving the time forward or backward to check future or past weather information.

[1412] Example 1

[1413] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1414] In today's information society, there is a growing need for a more intuitive and visual understanding of real-time information such as weather forecasts, news, and map information. However, traditional 2D data often makes it difficult to understand the information, and there is a need for technology to provide information in a format that is easy for users to understand. In particular, there is a lack of technology to efficiently generate 3D models and provide them in a format suitable for the device used by the user. To solve this issue, it is necessary to utilize more advanced data analysis and generative AI technology to quickly and effectively provide 3D models compatible with user devices.

[1415] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1416] In this invention, the server includes means for receiving 2D data from a user terminal, means for the user terminal to acquire 2D data from an external database and transmit it to the server, means for analyzing the received 2D data and extracting feature information, means for generating a 3D model using a generation AI based on the extracted feature information, means for the server to optimize the generated 3D model, convert it into a display format, and transmit it to the user terminal, and means for displaying the received 3D model on the user terminal. This allows information to be understood intuitively and visually, and makes it possible to efficiently generate and optimize 3D models and provide them in a form suitable for the user terminal.

[1417] A "user terminal" is a terminal operated by a user, and includes devices such as smartphones, tablets, and AR glasses.

[1418] "Two-dimensional data" is data that includes information such as weather, news, and maps, and is a data format that users acquire and send.

[1419] An "external database" is a repository of data that can be accessed via the Internet, such as a weather API or news API.

[1420] The "server" is a central processing unit that receives and analyzes data sent from the user terminal and provides the data to the generation AI.

[1421] "Feature information" is specific information such as temperature, humidity, and wind speed that is extracted by analyzing the two-dimensional data sent from the user terminal.

[1422] "Generative AI" is an artificial intelligence technology for generating 3D models based on feature information provided by a server.

[1423] A "3D model" is visually represented three-dimensional information generated based on 2D data and feature information.

[1424] A "display format" is a data format for appropriately displaying a 3D model on a user terminal, and includes the GLTF format.

[1425] "Optimization" is the process of streamlining the data volume and structure of the generated 3D model and converting it into a form suitable for the user's device.

[1426] "Rendering" is a process for visually displaying a 3D model received by a user terminal.

[1427] MODE FOR CARRYING OUT THE INVENTION

[1428] To implement this invention, a system using a user terminal, a server, a generation AI, and the Internet is required. Below, the processing of the programs that make up this system will be explained in detail in natural language.

[1429] Overall system configuration

[1430] User terminal

[1431] A dedicated application is installed on the user's device (smartphone, tablet, AR glasses, etc.). This application acquires 2D data from the user and sends it to the server. Specifically, when the user taps the "Get Weather Information" button, a request is sent to the weather API, current weather information is acquired, and it is sent to the server.

[1432] server

[1433] The server receives and analyzes the 2D data sent from the user's device. During the analysis, feature information such as temperature, humidity, and wind speed is extracted. The analysis is performed using the Python pandas library. A dataset is then created based on the extracted feature information and sent to the generation AI.

[1434] Generation AI

[1435] The generative AI generates a 3D model based on the dataset provided by the server. This generation process uses deep learning libraries such as TensorFlow and PyTorch. The generated 3D model visually represents, for example, cloud movement and temperature distribution.

[1436] Distribution and display on terminals

[1437] The server optimizes the generated 3D model and converts it into a format suitable for the user device (e.g., GLTF format). The server then sends the optimized model to the user device. The user device then renders and displays the received 3D model. This allows the user to intuitively and visually confirm real-time information.

[1438] Specific examples

[1439] 3D model generation for weather forecasts

[1440] When a user taps the "Get Weather Information" button on a smartphone app, the device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server. The server receives the JSON data, analyzes and extracts weather information such as temperature, humidity, and wind speed. The server then creates a dataset based on the extracted weather information and sends it to the generation AI. The generation AI generates a 3D model of the weather forecast based on the dataset and returns the result to the server. The server converts the received 3D model into GLTF format and sends it to the device. The device renders the received 3D model, allowing the user to view the real-time weather forecast in 3D.

[1441] Example prompt:

[1442] By tapping the "Get Weather Information" button, the device sends a request to the weather API to obtain current weather information. The data sent to the server is then analyzed to create a dataset to input into the generation AI. The generation AI generates a 3D model based on the dataset and sends the optimized model to the device. The device then renders the 3D model and displays it to the user.

[1443] This system allows users to intuitively and visually understand information such as weather, news, maps, etc. By utilizing generative AI, manual model creation is no longer necessary, enabling fast and efficient information visualization.

[1444] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1445] Step 1:

[1446] The user initiates an action

[1447] A user opens a smartphone application and taps the "Get Weather Information" button. This initiates an operation. The input is the user's action, and the output is a request to get weather information.

[1448] Step 2:

[1449] The device retrieves weather data

[1450] The device sends a request to the weather API to obtain current weather information. For example, access "https: / / api.weather.com / v3 / wx / conditions / current?apiKey=YOUR_API_KEY&format=json". The input is the API request, and the output is JSON data containing weather data such as temperature, humidity, and wind speed. The device sends this data to the server.

[1451] Step 3:

[1452] The server receives and analyzes the data

[1453] The server receives JSON data sent from the device. It analyzes the received data and extracts feature information such as temperature, humidity, and wind speed. The Python pandas library is used for analysis. The input is JSON data, and the output is the extracted feature information.

[1454] Step 4:

[1455] The server sends the data to the generated AI.

[1456] The server creates a dataset based on the extracted feature information and sends the dataset to the generation AI. The data is then formatted into the format required by the generation AI and sent. The input is the feature information and dataset, and the output is data sent to the generation AI.

[1457] Step 5:

[1458] Generative AI generates 3D models

[1459] The generative AI generates a 3D model based on a dataset provided by the server. The generation process uses deep learning libraries such as TensorFlow and PyTorch. The input is the dataset, and the output is the generated 3D model.

[1460] Step 6:

[1461] The server optimizes the 3D model

[1462] The server optimizes the generated 3D model and converts it into a format suitable for the user's device (e.g., GLTF format) using an appropriate optimization algorithm. The input is the generated 3D model, and the output is the optimized 3D model.

[1463] Step 7:

[1464] Display the optimized model for your device

[1465] The user device receives the optimized 3D model, renders it, and displays it. Rendering is performed in real time using a game engine such as Unity. The input is the optimized 3D model, and the output is a visual display of the rendered 3D model.

[1466] (Application example 1)

[1467] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1468] Conventional factory monitoring systems mainly display two-dimensional data, making it difficult to intuitively grasp the overall status of the factory in real time. In addition, it was necessary to monitor various sensor data individually, which made it difficult to manage efficiently.

[1469] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1470] In this invention, the server includes means for collecting various sensor data in the factory and converting it into a 3D model in real time for monitoring, means for optimizing the generated 3D model and transmitting it to a user terminal, and means for displaying the received 3D model on the user terminal, thereby enabling the status in the factory to be intuitively and visually grasped in real time using the 3D model.

[1471] A "user terminal" is a device operated by a user, and includes devices such as smartphones, tablets, and AR glasses.

[1472] "Two-dimensional data" refers to data that is written in a two-dimensional format, such as weather information, news, and map information.

[1473] "Feature information" is information with specific attributes or patterns extracted from analyzed two-dimensional data.

[1474] "Generative AI" is an artificial intelligence system that automatically generates 3D models based on an input dataset.

[1475] A "3D model" is three-dimensional visual data created by generative AI and displayed in a way that users can intuitively understand.

[1476] "Sensor data" is data collected from sensors that measure temperature, humidity, machine operating status, etc. within the factory.

[1477] "Real-time" means the immediacy in time that data is collected, processed and displayed at approximately the same time.

[1478] "Monitoring" is the process of continuously observing conditions within a factory to detect abnormalities or changes.

[1479] "Optimization" is the process of adjusting and converting the generated 3D model so that it can be displayed efficiently on the user's device.

[1480] This invention is a system for monitoring the status of a factory in real time as a 3D model. This system mainly uses user terminals, a server, a generating AI, and the Internet.

[1481] Overall system configuration

[1482] 1. User Device:

[1483] The user terminal is a device such as a smartphone or smart glasses. The user terminal collects various sensor data within the factory and transmits the data to a server, allowing the status within the factory to be monitored in real time.

[1484] 2. Server:

[1485] The server receives and analyzes the sensor data sent from the user device, extracts feature information, and then uses generative AI to generate a 3D model based on the extracted feature information. The generated model is then optimized and sent to the user device.

[1486] 3. Generation AI:

[1487] The generative AI uses data sets provided by the server to generate 3D models, such as those based on sensor data on temperature, humidity, and machine operation status, to generate 3D models that visually represent the real-time situation inside a factory.

[1488] 4. Distribution and display on devices:

[1489] The 3D model sent from the server is displayed on the user's device, allowing the user to check the real-time situation inside the factory using smart glasses or a smartphone.

[1490] Hardware and software used

[1491] User devices: smartphones, smart glasses

[1492] Server: High performance server

[1493] Generative AI: High-performance generative AI systems (e.g., OpenAI)

[1494] Communication technologies: Internet, HTTP requests

[1495] Data processing flow

[1496] User devices collect sensor data such as temperature, humidity, and machine operation status within the factory. This data is sent to the server using HTTP requests. The server analyzes the received data and extracts feature information. The extracted information is input into a generative AI, which generates a 3D model in real time. The generated model is optimized and then sent to the user's device, where the user can visually view it.

[1497] Specific examples

[1498] If the factory temperature exceeds 50 degrees, a red warning area will be displayed in the generated 3D model. Also, if a specific machine is stopped, an icon indicating this will be displayed on the factory map. This makes it possible to immediately detect and deal with abnormal conditions within the factory.

[1499] Prompt Sentence Examples

[1500] "The temperature has risen to 55 degrees and the humidity is at 40%. Machine_A is running, but Machine_B is stopped."

[1501] By inputting this prompt, the generative AI will generate a detailed 3D model like this:

[1502] "Generated 3D model with areas marked in red for high temperature and icons indicating machine statuses"

[1503] The system and process of this invention allows for intuitive understanding of conditions within a factory in real time, enabling efficient management and anomaly detection.

[1504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1505] Step 1:

[1506] Data collection from user devices

[1507] The user terminal collects various sensor data from within the factory (temperature, humidity, machine operation status, etc.) The data obtained from the sensors is collected in real time and handled as a single data set.

[1508] Input: Various sensor data

[1509] Output: Collected dataset

[1510] Step 2:

[1511] Sending data from the user device to the server

[1512] The user device sends the collected data set to the server using an HTTP request, which includes information such as temperature, humidity, and machine operation status.

[1513] Input: Collected dataset

[1514] Output: Request to send data to the server

[1515] Step 3:

[1516] Data analysis by server

[1517] The server receives the data set and analyzes it, extracting temperature and humidity data, as well as machine operating status. This analyzed data is then formatted into specific feature information.

[1518] Input: Dataset

[1519] Output: Feature information

[1520] Step 4:

[1521] Input to AI for generating feature information

[1522] The server sends the extracted feature information as a dataset to the generation AI, which then generates prompt sentences in a specific format and inputs them to the AI.

[1523] Input: feature information

[1524] Output: prompt statement

[1525] Step 5:

[1526] Generating 3D models using generative AI

[1527] The generative AI generates a 3D model based on the received prompt text. This model visually represents the factory status and provides an intuitive understanding of abnormal conditions and functions.

[1528] Input: prompt statement

[1529] Output: 3D model data

[1530] Step 6:

[1531] 3D model optimization by server

[1532] The generated 3D model is optimized by the server. The optimized 3D model is then adjusted so that it can be displayed efficiently on the user's device. This optimization process involves converting the file format and reducing the file size.

[1533] Input: 3D model data

[1534] Output: Optimized 3D model data

[1535] Step 7:

[1536] Sending the optimized 3D model to the user device

[1537] The server sends the optimized 3D model to the user's device using an HTTP POST request, which then displays the data appropriately on the user's device.

[1538] Input: Optimized 3D model data

[1539] Output: Request to send data to the user terminal

[1540] Step 8:

[1541] Display of 3D models on user devices

[1542] The user device displays the received 3D model, and the real-time situation inside the factory is visualized in 3D on the display of smart glasses or a smartphone, allowing the user to check it.

[1543] Input: Optimized 3D model data

[1544] Output: A representation of the 3D model as seen by the user

[1545] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1546] To implement this invention, a system using a user terminal, a server, a generation AI, an emotion engine, and the Internet is required. Below, the processing of the programs that make up this system will be explained in natural language.

[1547] Overall system configuration

[1548] 1. User Device

[1549] The device operated by the user (smartphone, tablet, AR glasses, etc.) uses a dedicated application to acquire 2D data and send it to a server. It also has an emotion engine that recognizes the user's emotions in real time. Specific data input by the user includes information such as weather, news, and maps.

[1550] Explaining program processing in natural language

[1551] 1. Enter and submit data

[1552] The user opens the smartphone application and selects the type of 2D data they want to acquire. For example, they select weather information and tap the "Get Weather Information" button. The device accesses the weather information API and sends the acquired data to the server.

[1553] 2. Data Receipt and Analysis

[1554] The server receives two-dimensional data from the weather information API, analyzes it, and extracts the necessary characteristic information (temperature, humidity, wind speed, probability of precipitation, etc.).

[1555] 3. Emotion recognition

[1556] The emotion engine installed on the device analyzes the user's facial expressions and voice in real time to recognize the user's emotions, and this recognition result is also sent to the server.

[1557] 4. 3D model generation using generative AI

[1558] The server creates a dataset for the generation AI based on the analyzed data and emotion recognition results, and inputs it into the generation AI, which then generates a 3D model that reflects the user's emotions in the weather information data.

[1559] 5. Optimize and submit the model

[1560] The generation AI returns the generated 3D model to the server, which then optimizes the received 3D model and converts it into a display format (e.g., GLTF format), after which it sends the optimized 3D model to the device.

[1561] 6. Displaying the 3D model

[1562] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Through the AR glasses, the user can check the real-time weather forecast in 3D. The display content is also adjusted based on the user's emotion recognition results.

[1563] Specific examples

[1564] 3D model generation for weather forecasts

[1565] 1. The user taps the "Get Weather Information" button on the smartphone app.

[1566] 2. The device sends a request to the weather API, obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server.

[1567] 3. The server receives the JSON data and analyzes and extracts the necessary weather information (temperature, humidity, wind speed, precipitation probability, etc.).

[1568] 4. The emotion engine installed on the device analyzes the user's facial expressions and voice to recognize their emotions. The recognition results are sent to the server.

[1569] 5. Based on the weather information and emotion recognition results extracted by the server, a dataset is created to be input into the generation AI and sent to the generation AI.

[1570] 6. The generative AI generates a 3D model of the weather forecast based on the input dataset and emotion recognition results, and returns the result to the server.

[1571] 7. The server converts the received 3D model into GLTF format and sends it to the device (such as AR glasses).

[1572] 8. The device renders the received 3D model and visually displays it to the user, allowing the user to see a real-time weather forecast in 3D. Furthermore, the information is adjusted based on the user's emotions, allowing the user to receive more personalized information.

[1573] The system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI and an emotion engine, manual model creation is eliminated, enabling fast and efficient information visualization and personalization.

[1574] The processing flow will be explained below.

[1575] Step 1:

[1576] A user opens a smartphone application and selects the type of 2D data they want to obtain. For example, the user selects weather information and taps the "Get Weather Information" button.

[1577] Step 2:

[1578] The device accesses the weather information API and requests weather data based on the specified location and time, and obtains two-dimensional data such as temperature, humidity, wind speed, and precipitation probability from the API.

[1579] Step 3:

[1580] The device sends the acquired 2D data to the server, usually using HTTP or HTTPS.

[1581] Step 4:

[1582] The server receives the 2D data sent from the device, analyzes the data format (e.g., JSON), and extracts necessary characteristic information (temperature, humidity, wind speed, precipitation probability, etc.) from the analyzed data.

[1583] Step 5:

[1584] The device's emotion engine collects the user's facial and voice data, recognizes the user's emotions in real time, and generates emotion recognition results (e.g., joy, sadness, surprise, etc.) and sends them to the server.

[1585] Step 6:

[1586] The server receives the emotion recognition results and combines them with the previously extracted feature information to create a dataset, which contains the user's emotion information along with their mood information.

[1587] Step 7:

[1588] The server sends the dataset to the generation AI for input, which analyzes the dataset and begins generating a 3D model based on the user's emotions.

[1589] Step 8:

[1590] The generative AI generates a 3D weather forecast model that reflects the user's emotions based on weather information and emotion recognition results. The generated 3D model is adjusted to have a realistic visual effect.

[1591] Step 9:

[1592] The AI ​​generates a 3D model and returns it to the server, which then optimizes it and converts it into a display format (e.g., GLTF).

[1593] Step 10:

[1594] The server sends the optimized 3D model to the device using fast and efficient data transmission technologies (e.g., HTTP, WebSocket).

[1595] Step 11:

[1596] The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses). Users can check the real-time weather forecast in 3D through the AR glasses. Emotion-based customization allows users to receive personalized information.

[1597] Step 12:

[1598] Users can interact with the displayed 3D model, for example, by moving forward or backward in time to see future or past weather information, and can also select different emotions from the interface to change the displayed content.

[1599] Example 2

[1600] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1601] In today's digital information society, users acquire a wide variety of information, and the amount of information is enormous. Weather information, news, and map information, in particular, change daily, and users need to be able to instantly understand that information. However, traditional two-dimensional data displays often make it difficult to intuitively grasp information. Furthermore, information display does not take into account the user's emotional state, resulting in insufficient personalization. The present invention aims to solve these problems and provide efficient and personalized information.

[1602] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1603] In this invention, the server includes means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, means for receiving and analyzing emotion data from the user terminal, means for generating a 3D model using a generation AI based on the extracted feature information and emotion data, means for optimizing the generated 3D model, converting it into a display format, and transmitting it to the user terminal, and means for displaying the received 3D model on the user terminal. This allows users to easily understand information using intuitive and visual 3D models, and further enables personalized information display based on the user's emotions.

[1604] A "user terminal" is a device operated by a user, and is a general term for devices such as smartphones, tablets, and AR glasses.

[1605] "Two-dimensional data" refers to information data that is spread out on a single plane, and refers to data groups in the form of weather information, news articles, map information, etc.

[1606] "Server" means a computer system that transmits, receives, analyzes, stores, and processes data over a network.

[1607] "Feature information" refers to specific information components such as temperature, humidity, wind speed, and precipitation probability extracted from two-dimensional data.

[1608] "Emotion data" is data that indicates the emotional state of the user, obtained by analyzing the user's facial expressions and voice.

[1609] "Generative AI" refers to artificial intelligence technology that generates new data and models based on input data, and is particularly responsible for generating images and 3D models.

[1610] A "3D model" refers to a three-dimensional digital object used to visually represent weather, map information, etc.

[1611] "Display format" refers to a data format for properly displaying a 3D model on a user terminal, and examples include the GLTF format.

[1612] MODE FOR CARRYING OUT THE INVENTION

[1613] To implement this invention, a user terminal, a server, a generating AI, an emotion engine, and a system that utilizes the Internet are required.

[1614] Hardware and software used

[1615] User devices: Smartphones, tablets, AR glasses, etc. These devices are equipped with internet connectivity, cameras, and microphones. A dedicated application is installed, and an emotion engine is also installed to acquire 2D data and analyze emotion data.

[1616] Server: A high-performance computer system that receives data, analyzes it, creates generative AI models, optimizes them, and transmits them. It includes a database system, an analysis engine, generative AI (e.g., OpenAI's DALL-E), and optimization tools.

[1617] Internet: A communications network for transmitting data between user terminals and servers.

[1618] System operation procedure

[1619] The user device acquires 2D data (e.g., weather information) through user operation and sends it to the server. The server analyzes the received data and extracts feature information such as weather information. At the same time, the user device uses an emotion engine to analyze the user's emotions and sends the results to the server. The server combines the extracted feature information and emotion data to create a dataset to input into the generative AI. The generative AI generates a 3D model based on the input data and returns it to the server. The server optimizes the generated 3D model, converts it into a display format (e.g., GLTF format), and sends it to the user device. Finally, the user device renders the received 3D model and displays it on the user's display device.

[1620] Detailed processing example

[1621] When a user taps the "Get Weather Information" button on a smartphone app, the device sends a request to a weather information API (e.g., OpenWeatherMap API), obtains JSON data of current weather information (temperature, humidity, wind speed, etc.), and sends it to the server. The server receives the JSON data, analyzes and extracts the necessary weather information (e.g., temperature, humidity, wind speed, probability of precipitation, etc.). At the same time, the device's built-in emotion engine analyzes the user's facial expressions and voice to recognize the user's emotions. The recognition results are then sent to the server.

[1622] The server creates a dataset to be input into the generation AI based on the extracted weather information and emotion recognition results, and sends it to the generation AI. The generation AI generates a 3D model of the weather forecast corresponding to the emotion based on the input dataset and emotion recognition results, and sends it back to the server. The server optimizes the generated 3D model, converts it to GLTF format, and sends it to the device. The device renders the received 3D model and displays it on the user's display device (e.g., AR glasses).

[1623] Prompt Sentence Examples

[1624] Input: Temperature 25°C, humidity 60%, wind speed 5 m / s, user emotion is happiness

[1625] Output: A 3D model of a sunny weather forecast with a rainbow that reflects happiness

[1626] This system allows users to easily understand information such as weather, news, and maps using intuitive, visual 3D models. By utilizing generative AI and an emotion engine, it eliminates the need for manual model creation, enabling fast and efficient visualization and personalization of information. This system is a powerful tool for aiding information understanding.

[1627] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1628] Step 1:

[1629] Entering data

[1630] The user taps the "Get Weather Information" button on the smartphone app.

[1631] Specific actions

[1632] The user interacts with the app and taps a button to get weather information.

[1633] input

[1634] Input from user actions.

[1635] output

[1636] Weather information request.

[1637] Data processing / calculation

[1638] A request is created and sent to the weather information API.

[1639] Step 2:

[1640] Acquiring and Sending Data

[1641] The device sends a request to the weather information API and sends the retrieved weather data in JSON format to the server.

[1642] Specific actions

[1643] The device accesses the weather information API via the network and obtains current weather information (e.g., temperature, humidity, wind speed).

[1644] Send the obtained JSON data to the server.

[1645] input

[1646] Weather information request

[1647] Weather information API response data (JSON format).

[1648] output

[1649] Obtained weather data.

[1650] Data processing / calculation

[1651] Receives JSON format data and temporarily saves it.

[1652] Convert it into a format to send to the server.

[1653] Step 3:

[1654] Data reception and analysis

[1655] The server analyzes the JSON-formatted weather data it receives and extracts the necessary feature information.

[1656] Specific actions

[1657] The server receives the JSON data.

[1658] Use a data analytics engine to extract key data such as temperature, humidity, and wind speed.

[1659] input

[1660] Weather data in JSON format sent from the device.

[1661] output

[1662] Extracted feature information (e.g., temperature 25°C, humidity 60%, wind speed 5m / s).

[1663] Data processing / calculation

[1664] Analyze the JSON data and extract the necessary items (temperature, humidity, wind speed, etc.).

[1665] The extracted information is stored in an internal database.

[1666] Step 4:

[1667] emotion recognition

[1668] The emotion engine installed in the device analyzes the user's facial expressions and voice to recognize the user's emotional state.

[1669] Specific actions

[1670] The device uses a camera and microphone to capture the user's facial expressions and voice.

[1671] The emotion engine analyzes the user's emotions in real time.

[1672] Send the results to the server.

[1673] input

[1674] User facial and voice data.

[1675] output

[1676] Recognized emotion data (e.g., happiness).

[1677] Data processing / calculation

[1678] Facial expressions and voice are analyzed using analytical algorithms.

[1679] Determine the emotional state and output the results as data.

[1680] Step 5:

[1681] Creating and generating datasets and inputting them into AI

[1682] The server creates a dataset to be input into the generative AI based on the extracted feature information and emotion data.

[1683] Specific actions

[1684] The server combines weather information and emotion data to create a dataset.

[1685] Input this as a prompt to the generation AI.

[1686] input

[1687] Feature information and emotion data.

[1688] output

[1689] Datasets for generative AI.

[1690] Data processing / calculation

[1691] The extracted feature information and emotion data are integrated and converted into a format suitable for generative AI.

[1692] Input this as a prompt to the generation AI.

[1693] Step 6:

[1694] Generating 3D models using generative AI

[1695] The generative AI generates a 3D model based on the input dataset and sends it back to the server.

[1696] Specific actions

[1697] Generative AI generates a 3D model based on the dataset.

[1698] The generated 3D model is sent back to the server.

[1699] input

[1700] Datasets for generative AI.

[1701] output

[1702] Generated 3D model

[1703] Data processing / calculation

[1704] Run an algorithm that analyzes the dataset and generates a 3D model.

[1705] Step 7:

[1706] Optimize and submit the model

[1707] The server optimizes the generated 3D model, converts it into a display format (GLTF format), and then sends it to the user's terminal.

[1708] Specific actions

[1709] The 3D model is made lighter by adjusting the number of polygons, etc.

[1710] Convert to GLTF format.

[1711] The converted model is sent to the user terminal.

[1712] input

[1713] Generated 3D model.

[1714] output

[1715] Optimized 3D model in GLTF format.

[1716] Data processing / calculation

[1717] Optimize the model to improve display efficiency.

[1718] Convert the format to GLTF.

[1719] Step 8:

[1720] 3D model display

[1721] The terminal renders the received 3D model and displays it on the user's display device.

[1722] Specific actions

[1723] The device uses a graphics engine to render the received 3D model.

[1724] The rendered model is displayed on a display device such as AR glasses.

[1725] input

[1726] 3D model in GLTF format sent from the server.

[1727] output

[1728] The 3D model displayed on the user's display device.

[1729] Data processing / calculation

[1730] Render a 3D model.

[1731] Visualize in a format suitable for the display device.

[1732] (Application example 2)

[1733] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1734] Conventional information provision systems have difficulty providing users with personalized real-time information, and are unable to provide information that reflects the user's emotions or current location, particularly in the case of shopping in physical stores. As a result, users are unable to efficiently obtain the information they need, making it difficult to improve their shopping experience.

[1735] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving 2D data from a user terminal, means for analyzing the received 2D data and extracting feature information, and means for combining the extracted feature information with the emotion recognition result of the emotion engine and generating a 3D model using a generation AI. This makes it possible to provide personalized real-time information that reflects the user's emotions and current location information.

[1736] A "user terminal" is a device operated by a user and is part of a system that includes smart glasses, smartphones, tablets, etc.

[1737] "Two-dimensional data" refers to information such as weather information, news, and map information expressed in two-dimensional format.

[1738] "Feature information" is important information extracted from two-dimensional data, and refers to specific numerical values ​​and data such as temperature, humidity, price, and inventory quantity.

[1739] The "emotion engine" is a software component that analyzes emotions from the user's facial expressions and voice in real time.

[1740] "Generative AI" is an artificial intelligence system that generates 3D models based on input data, and has the ability to learn features from datasets and generate models.

[1741] A "3D model" is three-dimensional visual information created by the generative AI based on feature information and emotion recognition results, and is visually displayed to the user.

[1742] The "server" is a computer system that receives and analyzes data sent from the user's device, generates a 3D model using generative AI, optimizes it, and sends it to the user's device.

[1743] "Optimization" is a process of converting the generated 3D model into a display format to ensure smooth display on the user's device.

[1744] "Display format" refers to a data format for displaying a 3D model on a user terminal, such as the GLTF format.

[1745] "Emotion recognition result" is data indicating the emotional state analyzed by the emotion engine from the user's facial expressions and voice.

[1746] "Location Sensor" means a hardware component that detects a user's current location, including GPS and other location technologies.

[1747] "Sale information" is data related to discounts and sales on products in stores, and includes information such as price, number of items in stock, and sale end time.

[1748] The system for implementing this invention utilizes a user terminal, a server, a generating AI, an emotion engine, and the Internet. The detailed program processing of the system will be explained below.

[1749] Overall system configuration

[1750] 1. User Device

[1751] A device operated by the user, such as smart glasses, smartphones, or tablets, has a dedicated application installed on the user's device, which recognizes location information and emotions in real time and sends 2D data to a server. It also uses an emotion engine to analyze emotions in real time from the user's facial expressions and voice.

[1752] 2. Server

[1753] The server receives 2D data and emotion recognition results sent from the user device. It analyzes the data and extracts feature information. Based on the extracted feature information and emotion recognition results, it uses generative AI to generate and optimize a 3D model. The optimized 3D model is converted into a display format (e.g., GLTF format) and sent to the user device.

[1754] What the program does

[1755] 1. Enter and submit data

[1756] When a user wears smart glasses with a location sensor and stands in front of a specific location (for example, a sale section in a physical store), the location sensor and camera detect the location. Based on the detected location information, the user's device accesses the API of the inventory management system, obtains real-time data such as sale information, and sends it to the server.

[1757] 2. Data Receipt and Analysis

[1758] The server analyzes the received real-time data and extracts important information such as price, stock quantity, and sale end time.

[1759] 3. Emotion recognition

[1760] The emotion engine installed in the user device analyzes the user's facial expressions and voice to recognize their emotional state, such as interest or surprise, and this recognition result is also sent to the server.

[1761] 4. 3D model generation using generative AI

[1762] The server creates a dataset for the generation AI based on the extracted feature information and emotion recognition results, and inputs this data into the generation AI. The generation AI then generates a 3D model of the sale information, taking into account the emotion recognition results, and returns the result to the server.

[1763] 5. Optimize and submit the model

[1764] The server optimizes the generated 3D model, converts it into a display format such as GLTF format, and then sends it to the user's terminal.

[1765] 6. Displaying the 3D model

[1766] The user device renders the received 3D model and visually displays it to the user through the smart glasses. Based on the user's emotion recognition results, the display content is adjusted, for example, enhancing color when the user is interested, or adding animation when the user is surprised.

[1767] Specific examples

[1768] Displaying special sales information in physical stores

[1769] 1. A user puts on smart glasses and stands in the bargain section of a supermarket.

[1770] 2. The user device uses a sensor to detect its location within the sale section, sends a request to the inventory management system API, and obtains current sale information (price, number of items in stock, sale end time).

[1771] 3. The server analyzes the received inventory information and extracts important information such as price and stock quantity.

[1772] 4. The emotion engine installed on the user device analyzes the user's facial expressions and voice in real time to recognize the user's emotions (e.g., interest or surprise). The recognition results are sent to the server.

[1773] 5. Based on the extracted sale information and emotion recognition results, the server creates a dataset for the generation AI and inputs it. The generation AI generates a 3D model of the sale information according to the emotion and returns the result to the server.

[1774] 6. The server converts the received 3D model into GLTF format and sends it to the user's device.

[1775] 7. The user device renders the received 3D model, and through the smart glasses, the user can check real-time inventory information and sales information corresponding to the sale section in 3D. Furthermore, the display content is adjusted based on the user's emotions.

[1776] Example prompts to input to the generative AI model

[1777] "Generate emotionally relevant 3D models of your sale section's inventory. Use vibrant colors to emphasize interest and add animations for surprise."

[1778] The system allows users to visually view personalized sales information based on their emotions, enhancing the intuitive shopping experience.

[1779] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1780] Step 1:

[1781] A user puts on smart glasses and stands at a specific location in a store. The location sensor and camera on the smart glasses detect this location and capture its location information. The location information becomes input data, which is then sent to a server by an application on the user's device.

[1782] Step 2:

[1783] The server receives location information sent from the user's device. Based on the received location information, the server accesses the inventory management system API and obtains sale information (price, stock quantity, sale end time) related to a specific location in the store. This sale information is analyzed by the server, and characteristic information such as price and stock quantity is extracted.

[1784] Step 3:

[1785] After processing the feature information, the emotion engine installed in the user device analyzes the user's facial expressions and voice in real time. This analysis recognizes the user's emotional state (e.g., interest, surprise). The recognized emotion data is sent from the user device to the server.

[1786] Step 4:

[1787] The server receives the emotion recognition results. The received feature information and the emotion recognition results are combined to create a dataset to be input into the generation AI. This dataset is prompt data that the generation AI uses to generate a 3D model that reflects the user's emotions in the sale information.

[1788] Step 5:

[1789] The generative AI receives the created dataset as input and generates a 3D model based on the sale information. The generated 3D model reflects the user's emotions and visually emphasizes the sale information, and is sent back to the server.

[1790] Step 6:

[1791] The server optimizes the 3D model returned by the AI ​​generator and converts it into an appropriate display format (e.g., GLTF format). The converted 3D model is then sent to the user's device.

[1792] Step 7:

[1793] The user device renders the 3D model received from the server and displays it visually to the user through the smart glasses. Special sale information is displayed in real time as a 3D model, and color enhancement and animation are added based on the user's emotion recognition results. This allows the user to understand the special sale information more intuitively.

[1794] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1795] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1796] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1797] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1798] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1799] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1800] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1801] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1802] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1803] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1804] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1805] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1806] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1807] 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.

[1808] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1809] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1810] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1811] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1812] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1813] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1814] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1815] The following is further disclosed regarding the above embodiment.

[1816] (Claim 1)

[1817] means for receiving two-dimensional data from a user terminal;

[1818] means for analyzing the received two-dimensional data and extracting feature information;

[1819] A means for generating a 3D model using a generative AI based on the extracted feature information;

[1820] means for transmitting the generated three-dimensional model to a user terminal;

[1821] means for displaying the received three-dimensional model at a user terminal;

[1822] A system including:

[1823] (Claim 2)

[1824] 2. The system according to claim 1, wherein the user terminal includes means for acquiring two-dimensional data from an external database and transmitting the data to the server.

[1825] (Claim 3)

[1826] 2. The system according to claim 1, further comprising means for optimizing the generated three-dimensional model, converting it into a display format, and transmitting it to a user terminal.

[1827] "Example 1"

[1828] (Claim 1)

[1829] means for receiving two-dimensional data from a user terminal;

[1830] A means for retrieving the received two-dimensional data from an external database and transmitting the data to a server;

[1831] means for analyzing the received two-dimensional data and extracting feature information;

[1832] A means for generating a 3D model using a generative AI based on the extracted feature information;

[1833] A means for the server to optimize the generated 3D model, convert it into a display format, and transmit it to a user terminal;

[1834] means for displaying the received three-dimensional model at a user terminal;

[1835] A system including:

[1836] (Claim 2)

[1837] 2. The system of claim 1, further comprising means for a user to initiate an action on a user terminal and send a request to an external data source, such as a weather API.

[1838] (Claim 3)

[1839] 2. The system according to claim 1, further comprising means for rendering and displaying the optimized three-dimensional model by a user terminal.

[1840] "Application Example 1"

[1841] (Claim 1)

[1842] means for receiving two-dimensional data from a user terminal;

[1843] means for analyzing the received two-dimensional data and extracting feature information;

[1844] A means for generating a 3D model using a generative AI based on the extracted feature information;

[1845] means for transmitting the generated three-dimensional model to a user terminal;

[1846] means for displaying the received three-dimensional model at a user terminal;

[1847] A means of collecting various sensor data within the factory and monitoring it in real time as a 3D model,

[1848] A system including:

[1849] (Claim 2)

[1850] 2. The system according to claim 1, wherein the user terminal includes means for acquiring two-dimensional data from an external database and transmitting the data to the server.

[1851] (Claim 3)

[1852] 2. The system according to claim 1, further comprising means for optimizing the generated three-dimensional model, converting it into a display format, and transmitting it to a user terminal.

[1853] "Example 2: Combining Emotion Engines"

[1854] (Claim 1)

[1855] means for receiving two-dimensional data from a user terminal;

[1856] means for analyzing the received two-dimensional data and extracting feature information;

[1857] means for receiving and analyzing emotion data from a user terminal;

[1858] A means for generating a 3D model using a generation AI based on the extracted feature information and emotion data;

[1859] means for optimizing the generated 3D model, converting it into a display format, and transmitting it to a user terminal;

[1860] means for displaying the received three-dimensional model at a user terminal;

[1861] A system including:

[1862] (Claim 2)

[1863] 2. The system according to claim 1, wherein the user terminal includes means for acquiring two-dimensional data from an external database and transmitting the data to the server.

[1864] (Claim 3)

[1865] 2. The system according to claim 1, further comprising means for optimizing the generated three-dimensional model, converting it into a display format, and transmitting it to a user terminal.

[1866] "Application example 2 when combining emotion engines"

[1867] (Claim 1)

[1868] means for receiving two-dimensional data from a user terminal;

[1869] means for analyzing the received two-dimensional data and extracting feature information;

[1870] A means for generating a 3D model using a generative AI by combining the extracted feature information and the emotion recognition results from the emotion engine;

[1871] means for transmitting the generated three-dimensional model to a user terminal;

[1872] means for displaying the received three-dimensional model at a user terminal;

[1873] A system including:

[1874] (Claim 2)

[1875] 2. The system according to claim 1, wherein the user terminal includes means for acquiring two-dimensional data from an external database and transmitting the data to the server.

[1876] (Claim 3)

[1877] 2. The system according to claim 1, further comprising means for optimizing the generated three-dimensional model, converting it into a display format, and transmitting it to a user terminal.

[1878] (Claim 4)

[1879] 2. The system of claim 1, wherein the user terminal includes means for detecting a specific location using a location sensor or a camera.

[1880] (Claim 5)

[1881] The system of claim 1, further comprising means for acquiring real-time information corresponding to the location detected by the smart device and transmitting the information to the generating AI.

[1882] (Claim 6)

[1883] The system of claim 1, characterized in that the generative AI includes means for generating a personalized 3D model based on real-time information and emotion recognition results. [Explanation of symbols]

[1884] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving two-dimensional data from a user terminal; means for analyzing the received two-dimensional data and extracting feature information; A means for generating a 3D model using a generative AI based on the extracted feature information; means for transmitting the generated three-dimensional model to a user terminal; means for displaying the received three-dimensional model at a user terminal; A system including:

2. 2. The system according to claim 1, wherein the user terminal includes means for acquiring two-dimensional data from an external database and transmitting the data to the server.

3. 2. The system according to claim 1, further comprising means for optimizing the generated three-dimensional model, converting it into a display format, and transmitting it to a user terminal.

Images