System

Abstract

A system is provided.SOLUTION: A system comprising means for collecting behavioral data of a user, means for analyzing the collected behavioral data to generate and update a user profile, means for receiving a user request, means for instructing a generative AI to generate content based on the received request and the user profile, means for receiving the generated content and delivering it to an IoT device, and means for adjusting an environment based on the content received by the IoT device.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] Many people today seek individually optimized environments that allow them to relax and concentrate in their busy daily lives. However, manually adjusting such environments is cumbersome. Furthermore, it is difficult to instantly provide an environment tailored to individual preferences and requirements. Conventional technologies lack the means to flexibly and dynamically configure environments according to user needs. [Means for solving the problem]

[0005] This invention provides a means for collecting user behavior data, analyzing it, and generating and updating a user profile. It also includes a means for receiving requests from the user and instructing the generation AI to generate content based on those requests. The generated content is delivered to the IoT device, which provides a means for the device to automatically adjust the environment, thereby providing an optimal environment according to the user's requests. Furthermore, by including a means for collecting user feedback and updating the profile based on that, it is possible to achieve highly accurate environment settings with each repeated use.

[0006] "User behavior data" refers to various data generated when a user uses the system, such as the user's application usage history, music playback history, video viewing history, and language usage patterns.

[0007] A "user profile" is a collection of information that represents a user's preferences and behavioral patterns, generated by analyzing the user's behavioral data.

[0008] A "user request" is an input from a user to the system requesting adjustments to the environment or provision of a particular service, and may take the form of a voice command, text input, or the like.

[0009] "Generative AI" is an artificial intelligence system that generates content such as music, video, or text based on specified requirements.

[0010] "Content" refers to information such as music files, video files, and text data generated by generative AI.

[0011] An "IoT device" is a smart device that is connected to the Internet and can be remotely controlled and monitored, including smart speakers, smart displays, and smart lights.

[0012] "Feedback" refers to the user's evaluations and impressions of their usage experience provided to the system, as well as data obtained from environmental sensors.

[0013] "Means for adjusting the environment" refers to methods or means for controlling IoT devices to change the physical environment, such as lighting, music playback, and video display, in response to user requests. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

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

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

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

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

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

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

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

[0035] This invention relates to a system that analyzes user behavior data and provides an optimal environment according to individual requests. This system provides an optimal real-time environment for users by adjusting the environment through collaboration with a server that collects user behavior data and generates and updates profiles, a terminal that receives user requests, content generation using generative AI, and IoT devices.

[0036] Program processing

[0037] Creating a User Profile

[0038] The server collects user behavioral data, including application usage history, music playback history, video viewing history, language usage patterns, etc. The server then applies this data to machine learning algorithms to identify user preferences and behavioral patterns and generate and update user profiles.

[0039] Receiving user requests

[0040] The device provides an interface for receiving requests from the user, for example, a request such as "create a relaxing environment" input through a smartphone app or voice assistant, and sends the request to the server.

[0041] Content Generation Instructions

[0042] The server issues appropriate instructions to the generation AI based on the received user request and the generated profile. For example, it may ask the music generation AI to generate "music to create a relaxing environment." Similarly, it sends instructions to the video generation AI and language generation AI to generate "relaxing images" and "relaxing text."

[0043] Content Delivery

[0044] The server that receives the content generated by the generative AI distributes it to the appropriate IoT device: for example, music files to a smart speaker, video files to a smart display, and text data to an e-book reader.

[0045] Adjusting the environment

[0046] The terminals (each IoT device) adjust their settings based on the content received from the server. Smart speakers play music, smart displays show images, and smart lights adjust the color and brightness of lighting. This allows users to experience a relaxing environment.

[0047] Specific Examples

[0048] Example 1: Relaxed environment

[0049] The user enters "I want to relax" through the app.

[0050] The terminal sends the request to the server.

[0051] Based on the user's profile and requests, the server instructs the generative AI to generate "relaxing music," "landscape footage," and "relaxing essays."

[0052] The generative AI generates appropriate music, video, and text and sends them to the server.

[0053] The server distributes this data to smart speakers, smart displays, and e-readers.

[0054] The terminal plays music, displays videos, and displays essays.

[0055] Example 2: In an environment where you can concentrate

[0056] Users input "I want to concentrate" through the app.

[0057] The terminal sends the request to the server.

[0058] Based on the user's profile and requests, the server instructs the generative AI to generate "music that improves concentration," "images with moderate movement," and "text that improves concentration."

[0059] The generation AI generates appropriate content and sends it to the server.

[0060] The server distributes this data to smart speakers, smart displays, and e-readers.

[0061] The terminal plays music, displays video, and displays text.

[0062] This system provides an optimal environment based on user behavior data and real-time requests. It also continuously updates the user profile through feedback, enabling even more accurate environment settings for subsequent uses.

[0063] The processing flow will be explained below.

[0064] Step 1: Collect user behavior data

[0065] The server periodically collects users' application usage history, music playback history, video viewing history, language usage patterns, etc. This includes data sent from IoT devices such as smartphones, smart speakers, and smart displays.

[0066] Step 2: Analyze behavioral data

[0067] The server then applies machine learning algorithms to analyze the collected behavioral data, for example, identifying preferred genres from a user's music playback history and determining the types of videos they like from their video viewing history.

[0068] Step 3: Update your user profile

[0069] The server generates or updates a user profile based on the analysis results, reflecting the user's preferences and behavioral patterns. The updated profile includes the user's preferred music genres, video types, language styles, etc.

[0070] Step 4: Receive user requests

[0071] The device receives requests from the user through an interface, for example, a request to "create a relaxing environment" via a smartphone app or voice assistant.

[0072] Step 5: Submitting the request

[0073] The device sends the user's request as structured data (e.g., JSON format) to the server. The server receives it and starts the next process.

[0074] Step 6: Content Generation Instructions

[0075] The server compares the user's request with the updated profile and issues appropriate instructions to each AI generator. For example, to create a "relaxing environment," the server might instruct the music generator AI to "generate calming music" and the video generator AI to "generate landscape images."

[0076] Step 7: Run content generation

[0077] Generative AI (music generation AI, video generation AI, language generation AI) generates content based on their respective instructions. For example, music generation AI generates relaxing music, video generation AI generates landscape images, and language generation AI generates relaxing essays.

[0078] Step 8: Receive your content

[0079] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[0080] Step 9: Deliver your content

[0081] The server then sends the generated content to the appropriate IoT device: music files to a smart speaker, video files to a smart display, text data to an e-reader, and so on.

[0082] Step 10: Adjusting the environment

[0083] The terminals (each IoT device) use the received content to automatically adjust the environment: for example, a smart speaker plays relaxing music, a smart display shows a landscape image, and smart lights adjust the color and brightness of the lighting to a relaxing mode.

[0084] Step 11: Gather feedback

[0085] The device collects user feedback, including voice input, tap gestures, and even data from environmental sensors, which is sent to a server and used to further update the user profile.

[0086] Example 1

[0087] 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."

[0088] Many modern systems only collect user behavior data, but are unable to provide an appropriate environment based on that data. Furthermore, they are limited in their ability to respond to user requests in real time, automatically generate content, and integrate with IoT devices, making it difficult to provide an optimal experience for users.

[0089] 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.

[0090] In this invention, the server includes means for collecting user behavioral data, means for analyzing the collected behavioral data using a machine learning algorithm to generate and update a user profile, interface means for receiving user requests, means for instructing content generation by sending appropriate prompts to a generation AI based on the received request and the user profile, means for receiving the generated content and distributing it to an IoT device via a network, and means for the IoT device to adjust its settings based on the received content to optimize the environment, thereby making it possible to provide an optimal environment based on the user's behavioral data and real-time requests.

[0091] "User behavioral data" refers to general information about user behavior and choices, such as application usage history, music playback history, video viewing history, and text message exchanges.

[0092] "Machine learning algorithm" is a general term for algorithms that automatically learn patterns based on large amounts of data and make predictions and classifications, and is used in this system to generate and update user profiles.

[0093] A "user profile" is a collection of data that represents characteristics such as a user's preferences and behavioral patterns, generated from collected user behavioral data and analysis results based on that data.

[0094] "Interface means" refers to a window or device through which a user inputs requests or information, such as a smartphone app or voice assistant.

[0095] "Generative AI" refers to artificial intelligence that automatically generates content such as text, music, and images based on user requests.

[0096] A "prompt" refers to an input sentence, such as an instruction or question, given to the generation AI, which determines the content to be generated.

[0097] "Means for distribution over a network" refers to a method or apparatus for transmitting generated content to IoT devices using the Internet or other communications networks.

[0098] An "IoT device" refers to a device that is connected to the Internet and can send and receive data and perform specific functions, such as a smart speaker, smart display, or smart light.

[0099] "Means for optimizing the environment" refers to IoT devices automatically adjusting their settings based on the content they receive, providing the optimal environment for the user.

[0100] The present invention relates to a system for collecting user behavior data, generating and updating profiles, and providing an optimal environment according to user requests. This system includes the following elements:

[0101] 1. Collecting user behavior data

[0102] The server collects behavioral data from various applications that users use on a daily basis. This behavioral data includes application usage history, music playback history, video viewing history, language usage patterns, etc. To do this, the server uses the Google Analytics API and other general data collection tools.

[0103] 2. Creating and updating user profiles

[0104] The server analyzes the collected behavioral data using machine learning algorithms based on Python's Scikit-learn library. This analysis identifies user preferences and behavioral patterns, and generates and updates user profiles. For example, K-means clustering can be used to classify user interests and create profiles based on those.

[0105] 3. Receiving user requests

[0106] The device provides an interface to receive requests from the user, which can be done through a smartphone app or a voice assistant (e.g., Amazon Alexa or Google Assistant). When the user types a request, such as "create a relaxing environment," the device sends the request to the server.

[0107] 4. Content Generation Instructions

[0108] The server sends appropriate prompts to the AI ​​based on the user's request and the generated profile to instruct it to generate content. For example, for text generation, OpenAI's GPT-4 (registered trademark) is used, and the server sends a prompt such as "Generate relaxing music."

[0109] Example prompt: "Create soothing music that's perfect for someone who wants to relax."

[0110] 5. Content Delivery

[0111] The content generated by the generative AI model is returned to the server, which then distributes it to the appropriate IoT device: for example, music files to a smart speaker (commonly known as a smart speaker), video files to a smart display (commonly known as a smart display), and text data to an e-reader (commonly known as an e-reader).

[0112] 6. Adjusting the environment

[0113] Each IoT device (e.g., smart speaker, smart display, smart light, etc.) automatically adjusts its settings based on the content received from the server, allowing users to experience a relaxing or focused environment.

[0114] Example: When a user enters "I want to relax" into an app, the server sends instructions to the AI ​​generator based on the user profile. The AI ​​generator generates music and video, which are then distributed to a smart speaker and a smart display, respectively, and the smart light is set to warm colors.

[0115] In this way, the system can provide an optimal environment based on the user's behavioral data and real-time requirements. Furthermore, by continuously updating the user profile through feedback, the system can achieve even more accurate environment settings for subsequent uses.

[0116] This system allows users to easily obtain the optimal environment that meets their individual needs, improving their quality of life.

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

[0118] Step 1: Collect user behavior data

[0119] The server collects data on the user's behavior in various applications. Specifically, it collects app usage history on smartphones and PCs, music playback history, video viewing history, text message exchanges, etc. It receives data from various APIs (e.g., Google Analytics API, Spotify API) as input and stores that data in an internal database as output.

[0120] Specific behavior:

[0121] The server calls the Google Analytics API to obtain app usage history.

[0122] The server uses the Spotify API to collect the user's music playback history.

[0123] Save the retrieved data in the database.

[0124] Step 2: Create and update user profiles

[0125] The server runs the collected behavioral data through a machine learning algorithm (e.g., Scikit-learn's K-means clustering). Using the data collected in the previous step as input, it analyzes the user's preferences and behavioral patterns, and generates and updates a user profile as output.

[0126] Specific behavior:

[0127] The server preprocesses the acquired behavioral data and converts it into numerical data.

[0128] The server inputs the preprocessed data into the K-means clustering algorithm.

[0129] A user profile is generated based on the analysis results and stored in a database.

[0130] Step 3: Receiving the user request

[0131] The device provides an interface (such as a smartphone app or a voice assistant) to receive requests from the user. It receives the user's request (e.g., "I want to relax") as input and sends the request to the server as output.

[0132] Specific behavior:

[0133] The user types "I want to relax" into a text field on the smartphone app.

[0134] The terminal sends this request to the server as an HTTP request.

[0135] Step 4: Directing content generation

[0136] The server sends appropriate prompts to the generation AI based on the user's request and the generated profile, instructing it to generate content. Using the user's request and profile data as input, the server creates prompts to send to the generation AI as output. The generation AI receives instructions in advance via an API or other means.

[0137] Specific behavior:

[0138] The server extracts features of the content for relaxation from the user profile.

[0139] The server calls the API of the generative AI model and sends a prompt to generate relaxing music.

[0140] Step 5: Deliver your content

[0141] After the content generated by the generative AI model is returned to the server, it is distributed to the appropriate IoT devices (smart speakers, smart displays, e-readers, etc.) It receives the generated content as input and sends data to each IoT device as output.

[0142] Specific behavior:

[0143] The server receives the music file returned by the generation AI.

[0144] The server sends the music file to the smart speaker as an HTTP request.

[0145] Step 6: Adjusting the environment

[0146] Each IoT device automatically adjusts its settings based on the content it receives from the server. It receives content as input and adjusts its behavior as output. For example, a smart speaker plays music, and a smart display displays video.

[0147] Specific behavior:

[0148] The smart speaker plays the music files received from the server.

[0149] The smart display plays the video file received from the server.

[0150] The smart light changes the color of the light to a warmer color based on instructions from the server.

[0151] This processing step allows for providing an optimal environment based on the user's behavioral data and real-time requirements.

[0152] (Application example 1)

[0153] 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."

[0154] Conventional autonomous vehicles have had difficulty providing an environment that appropriately reflects passengers' specific needs, such as relaxation and concentration, while on board. Furthermore, the generation of profiles based on passenger behavior data and the use of such profiles to generate content and automatically adjust the environment were insufficient, resulting in a lack of a means to provide an optimal environment for each individual user.

[0155] 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.

[0156] In this invention, the server includes a means for collecting user behavioral data, a means for analyzing the collected behavioral data to generate and update a user profile, and a means for receiving user requests. This allows the server to instruct a generation AI to generate content based on the received request and user profile, receive the generated content, and distribute it to the in-vehicle system. Furthermore, the in-vehicle system can control at least one of lighting, music playback, and video display based on the received content, providing an environment tailored to the user's requests in real time. This system allows the server to provide an optimal riding environment for each user, ensuring a comfortable driving experience.

[0157] "User behavioral data" refers to data such as operation history, browsing history, and playback history when a user uses an application or device, which makes it possible to analyze the preferences and behavioral patterns of individual users.

[0158] A "user profile" is a collection of information generated based on collected user behavior data, and specifically indicates the user's preferences, behavioral patterns, and characteristics according to their requirements.

[0159] "Generative AI" refers to artificial intelligence technology that generates content such as music, video, and text based on user profiles and requests. For example, it can automatically generate music and videos for relaxation.

[0160] "In-vehicle system" includes information processing devices and entertainment systems installed in autonomous vehicles, and has the function of playing and displaying content in response to user requests and adjusting the in-vehicle environment.

[0161] "Means for adjusting the environment" refers to the ability of the in-vehicle system to control environmental elements such as lighting, music playback, and video display in real time based on the generated content, such as playing relaxation music or adjusting the color and brightness of lighting.

[0162] This invention is a system for collecting and analyzing user behavior data in an autonomous vehicle, and providing an environment that is optimal for individual needs based on that data. This system is composed of the following elements: a server, a user terminal, and an in-vehicle system.

[0163] System Configuration

[0164] server

[0165] The server collects user behavioral data (e.g., application usage history, music playback history, video viewing history), analyzes the data, and generates and updates user profiles. A RESTful API is used to collect the behavioral data, and PostgreSQL is used as the database. A machine learning algorithm is used for the analysis to identify user behavioral patterns and preferences.

[0166] The server also provides an interface for receiving requests from users (e.g., "I want to relax" or "I want to concentrate"). Based on these requests, it issues instructions to a generative AI model (e.g., OpenAI's GPT-4) to generate appropriate content. The instructions are generated as prompt sentences and sent to the generative AI.

[0167] The content (e.g., music, video, text) returned by the generative AI is sent back to the server, converted into an appropriate format, and delivered to the in-car system.

[0168] User terminal

[0169] The user terminal (e.g., a smartphone) provides an application for inputting user requests. Through this application, the user inputs requests such as "I want to relax" or "I want to concentrate," and the input data is sent to the server.

[0170] In-vehicle systems

[0171] The in-vehicle system adjusts the environment based on the generated content received from the server. Specifically, it plays music through the in-vehicle speakers, displays images on the in-vehicle display, adjusts the color and brightness of the smart lights, etc. The in-vehicle system automates these operations using an information processing device such as ANDROID (registered trademark) Auto.

[0172] Processing flow

[0173] 1. User behavior data collection: The server collects user usage and playback history.

[0174] 2. User profile generation and update: The collected data is analyzed using machine learning algorithms to generate and update user profiles.

[0175] 3. Receiving a user request: The user enters a request into the smartphone app and the server receives it.

[0176] 4. Content generation by generative AI: The server sends a prompt to the generative AI to generate appropriate content. For example, "Generate relaxing music. The user's profile is as follows: [specific data]."

[0177] 5. Content distribution: The server distributes the generated content to the in-vehicle system.

[0178] 6. Environmental adjustment: Based on the content received by the in-vehicle system, it plays music, displays images, adjusts lighting, etc.

[0179] Specific examples

[0180] If a user requests "I want to relax," the server instructs the generation AI to generate "relaxing music" based on the user profile. The music file returned by the generation AI is converted into the appropriate format on the server and distributed to the car's speakers. Relaxation videos are displayed on the car display, and the smart lights are adjusted to a soft, warm light. This series of actions allows the user to enjoy a relaxing environment in the car.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] The server collects user behavior data.

[0184] Input: User's application usage history, music playback history, video viewing history

[0185] Data processing: Save to database via API

[0186] Output: A database of accumulated behavioral data

[0187] Step 2:

[0188] The server analyzes the collected data and generates and updates the user profile.

[0189] Input: Behavioral data stored in a database

[0190] Data Computing: Using machine learning algorithms to identify user behavior patterns and preferences

[0191] Output: Updated user profile

[0192] Step 3:

[0193] The user inputs a request through a terminal.

[0194] Input: User request (e.g., "I want to relax" or "I want to concentrate")

[0195] Data processing: Sending user requests to the server

[0196] Output: Request data is sent to the server

[0197] Step 4:

[0198] The server instructs the generation AI to generate content based on the received request and user profile.

[0199] Input: User request, updated user profile

[0200] Data calculation: Generate prompts for the generation AI and instruct it to specify the request. Example: "Generate relaxing music. The user's profile is as follows: [specific data]."

[0201] Output: Prompt sent to the generation AI

[0202] Step 5:

[0203] The generation AI generates the content and sends it to the server.

[0204] Input: Prompt sent to the generation AI

[0205] Data processing: Generative AI generates content based on prompts (e.g., music files, video files, text)

[0206] Output: The generated content is sent to the server

[0207] Step 6:

[0208] The server receives the generated content and distributes it to the in-vehicle system.

[0209] Input: Content received from the generation AI

[0210] Data processing: Converting content into the appropriate format and delivering it to the in-vehicle system

[0211] Output: Content delivered to the in-car system

[0212] Step 7:

[0213] The in-vehicle system adjusts the environment based on the content it receives.

[0214] Input: Content delivered from the server (music files, video files, text, etc.)

[0215] Data calculation and processing: Set up the environment for music playback, video display, lighting adjustment, etc.

[0216] Output: Optimal in-car environment according to user demands

[0217] 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.

[0218] This invention relates to a system that analyzes user behavioral and emotional data and provides an optimal environment in response to user requests. In particular, this invention incorporates an emotion engine that recognizes user emotions in real time and utilizes that data to adjust the environment. This system provides an optimal environment by collecting and analyzing user behavioral and emotional data, creating and updating profiles on a server, receiving user requests from a terminal, generating content using a generative AI, and linking with IoT devices.

[0219] Program processing

[0220] Creating a User Profile

[0221] The server collects user behavioral and emotional data. Behavioral data includes application usage history, music playback history, video viewing history, and language usage patterns, while emotional data includes facial expressions and voice tone captured through cameras and microphones. The server analyzes this data using machine learning algorithms to identify user preferences and behavioral patterns. At the same time, the emotion engine also analyzes user emotions in real time and sends the results to the server.

[0222] Update your user profile

[0223] The server generates or updates a user profile based on the analysis results and data from the emotion engine, including the user's preferred music genres, video types, and preferences for content that corresponds to specific emotional states.

[0224] Receiving user requests

[0225] The device receives requests from the user through the interface. For example, the user may say, "Create a relaxing environment" through a smartphone app or voice assistant. If the emotion engine already recognizes an emotion, such as "stress," that information is also sent to the server along with the request.

[0226] Submitting a request

[0227] The device structures the user's request and emotion data and sends them to the server, which receives them and starts the next process.

[0228] Content generation instructions

[0229] The server compares the user's request, updated profile, and emotion engine data and issues appropriate instructions to each AI generator. For example, to create a "relaxing environment," the server instructs the music generator AI to "generate calming music" and the video generator AI to "generate landscape images."

[0230] Content generation execution

[0231] The generative AIs (music generation AI, video generation AI, and language generation AI) generate content based on their respective instructions. The music generation AI generates relaxing music, the video generation AI generates landscape images, and the language generation AI generates relaxing essays.

[0232] Receiving content

[0233] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[0234] Content Delivery

[0235] The server then sends the generated content to the appropriate IoT device: music files to a smart speaker, video files to a smart display, text data to an e-reader, and so on.

[0236] Adjusting the environment

[0237] The terminals (each IoT device) automatically adjust their environment based on the content they receive: for example, a smart speaker plays relaxing music, a smart display shows a landscape image, and smart lights adjust the color and brightness of the lights to a relaxing mode.

[0238] Collecting feedback

[0239] The device collects user feedback, including voice input, tap gestures, and even data from environmental sensors, along with an emotion engine, to analyze the user's current emotional state, which is then sent to the server for further updates to the user profile.

[0240] Specific Examples

[0241] Example 1: Relaxed environment

[0242] The user inputs "I want to relax" through the app, and at the same time, the emotion engine recognizes that the user is feeling stressed.

[0243] The terminal transmits the request and the emotion data to the server.

[0244] Based on the user's profile and emotional data, the server instructs the generative AI to generate "relaxing music," "landscape footage," and "relaxing essays."

[0245] The generative AI generates appropriate music, video, and text and sends them to the server.

[0246] The server distributes this data to smart speakers, smart displays, and e-readers.

[0247] The device plays music, displays videos, and displays essays, while an emotion engine continuously monitors the effects of the environment.

[0248] Example 2: In an environment where you can concentrate

[0249] The user inputs "I want to concentrate" through the app, and at the same time the emotion engine recognizes that the user is slightly tired.

[0250] The terminal transmits the request and the emotion data to the server.

[0251] Based on the user's profile and emotional data, the server instructs the generative AI to generate "music that improves concentration," "images with moderate movement," and "text that improves concentration."

[0252] The generation AI generates appropriate content and sends it to the server.

[0253] The server distributes this data to smart speakers, smart displays, and e-readers.

[0254] The device plays music, displays video, and displays text, while an emotion engine continuously monitors the user's emotional state and fine-tunes the environment as needed.

[0255] The system utilizes user behavioral data and real-time emotional data to provide an environment that is optimally tailored to the user's needs. Through feedback, the system continuously updates the user profile, achieving more accurate environment settings with each repeated use.

[0256] The processing flow will be explained below.

[0257] Step 1: Collect behavioral and emotional data

[0258] The server periodically collects user behavioral data such as application usage history, music playback history, video viewing history, and language usage patterns. The emotion engine also analyzes the user's facial expressions and voice tone in real time through cameras and microphones to obtain emotion data.

[0259] Step 2: Analyze behavioral and emotional data

[0260] The server analyzes the collected behavioral data using machine learning algorithms. For example, it identifies preferences based on the genres of music the user has listened to or the types of videos they have watched. The emotion engine analyzes the acquired emotion data and identifies the user's current emotional state (e.g., stress, relaxation, lack of concentration, etc.).

[0261] Step 3: Update your user profile

[0262] The server generates or updates a user profile based on the analysis of the behavioral and emotional data, including the user's preferred music genres, video types, and content preferences that correspond to specific emotional states.

[0263] Step 4: Receive user requests

[0264] The device receives a request from the user through the interface. For example, the user may input "Create a relaxing environment" through a smartphone app or voice assistant. The current emotional state recognized by the emotion engine is also sent to the server along with the request.

[0265] Step 5: Sending request and emotion data

[0266] The device structures the user's request and emotion data and sends it to the server in a standard format such as JSON.

[0267] Step 6: Content Generation Instructions

[0268] The server compares the user's request, updated profile, and emotion engine data, and issues appropriate instructions to each generation AI. For example, to create a "relaxing environment," the server instructs the music generation AI to "generate calming music" and the video generation AI to "generate relaxing videos."

[0269] Step 7: Run content generation

[0270] The generative AIs (music generation AI, video generation AI, and language generation AI) generate content based on their respective instructions. The music generation AI generates relaxing music, the video generation AI generates natural landscape footage, and the language generation AI generates relaxing essays.

[0271] Step 8: Receive your content

[0272] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[0273] Step 9: Deliver your content

[0274] The server then sends the generated content to IoT devices, for example, music files to smart speakers, video files to smart displays, and text data to e-readers.

[0275] Step 10: Adjusting the environment

[0276] The terminals (each IoT device) automatically adjust their environment based on the content they receive: for example, a smart speaker plays relaxing music, a smart display shows natural scenery, and smart lights adjust the color and brightness of the lights to a relaxing mode.

[0277] Step 11: Gather feedback

[0278] The device collects user feedback, including voice input, tap gestures, and data from environmental sensors. The emotion engine also continuously monitors the user's emotional state and sends it to the server for further updates to the user profile.

[0279] Example 2

[0280] 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."

[0281] In modern daily life, it is difficult to provide an optimal environment for users by utilizing their behavioral and emotional data. Specifically, there is a lack of technology that can respond to diverse user requests in real time and appropriately adjust the environment while monitoring the effects. This poses a challenge, making it difficult to provide a comfortable, relaxing, and focused environment for users.

[0282] 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.

[0283] In this invention, the server includes means for collecting user behavioral data and emotional data, means for analyzing the collected behavioral data and emotional data to generate and update a user profile, means for receiving a user request, means for instructing a generative AI model to generate content based on the received request and the user profile, means for receiving the generated content and delivering it to an IoT device, and means for adjusting an environment based on the content received by the IoT device, thereby making it possible to provide an optimal environment for the user and adjust the environment based on the user's behavioral data and real-time emotional state.

[0284] "User behavior data" is information that indicates user behavior, such as the user's history of using various applications, music and video playback history, and language usage patterns.

[0285] "Emotion data" is information that indicates the user's emotional state, such as the user's facial expression or tone of voice, and is acquired through a camera or microphone.

[0286] A "user profile" is information that indicates content preferences that correspond to a user's preferences, behavioral patterns, and emotional state based on collected behavioral and emotional data.

[0287] A "generative AI model" is an artificial intelligence algorithm or system that generates content such as music, video, or text based on user requests and profiles.

[0288] An "IoT device" is an internet-connected device that adjusts its environment based on the content delivered to it, and examples include smart speakers and smart displays.

[0289] "Means for adjusting the environment" refers to mechanisms that include the ability to play music from a smart speaker, display images on a smart display, and change the lighting settings of smart lights.

[0290] "Feedback" is information used to evaluate system performance and the user's emotional state through user-provided opinions, impressions, and data obtained from environmental sensors.

[0291] The present invention relates to a system that analyzes user behavioral and emotional data to provide an optimal environment in response to user requests. In particular, it incorporates an emotion engine, recognizes user emotions in real time, and uses that data to adjust the environment.

[0292] Specific hardware and software configurations

[0293] The system consists of the following main components:

[0294] Server: Collects data, analyzes, creates profiles, instructs content generation, and distributes content. The server has installed software libraries (e.g., Scikit-learn, TENSORFLOW®) for running machine learning algorithms.

[0295] Device: The part of the system that receives user requests and transmits the request and emotion data to the server. Devices include smartphones, voice assistants, and smart displays.

[0296] Emotion engine: Recognizes the user's facial expressions and tone of voice and analyzes the resulting emotional data. Emotion engines include commonly used facial recognition and voice analysis APIs (e.g., Amazon Rekognition, Google Cloud Vision API, Microsoft® Azure® Cognitive Services).

[0297] IoT devices: These are devices that automatically adjust their environment based on the content they generate. Examples include smart speakers, smart displays, smart lights, and e-readers.

[0298] Data processing and calculation methods

[0299] The server collects user behavioral and emotional data. This data includes application usage history, music playback history, video viewing history, language usage patterns, and facial expressions and tone of voice captured through cameras and microphones. The server then analyzes this data using machine learning algorithms to identify user preferences and behavioral patterns. For example, it uses clustering algorithms and sentiment analysis models. Meanwhile, the emotion engine analyzes user emotions in real time and sends the results to the server.

[0300] Creating and updating user profiles

[0301] Based on the analysis and data from the emotion engine, the server generates or updates a user profile, including the user's preferred music genres, video types, and content preferences that correspond to particular emotional states.

[0302] Receiving and processing user requests

[0303] The device receives user requests through an interface (smartphone app or voice assistant). For example, the user might say, "Create a relaxing environment." If the emotion engine recognizes the user's emotional state (e.g., "I'm feeling stressed"), that information is also sent to the server. The device then structures this data and sends it to the server.

[0304] Directing and generating content

[0305] The server compares the received user request, updated profile, and emotion engine data, and issues appropriate instructions to each generative AI model. For example, to create a "relaxing environment," it issues specific instructions such as "generate calming music" to the music generation AI model and "generate a landscape video" to the video generation AI model. Examples of prompt sentences are "create a relaxing environment" and "generate calming music."

[0306] Content Generation and Delivery

[0307] Each generative AI model (music generation AI, video generation AI, language generation AI) generates content based on a specified prompt. The music generation AI generates quiet, slow-tempo music, the video generation AI generates videos of tranquil landscapes, and the language generation AI generates relaxing essays. The generated content is sent to a server and distributed to appropriate IoT devices (smart speakers, smart displays, e-book readers, etc.).

[0308] Tuning the environment and gathering feedback

[0309] IoT devices automatically adjust the environment based on the received content. For example, a smart speaker can play relaxing music, a smart display can display landscape images, and smart lights can set the lights in a relaxing mode. Furthermore, the emotion engine can analyze the user's current emotional state by collecting user feedback (voice input, tap gestures, environmental sensor data, etc.). This feedback is sent to the server and used to update the user profile.

[0310] The system utilizes user behavioral data and real-time emotional data to provide an optimal environment tailored to the user's needs, and continuously updates the user profile through feedback, ensuring accurate environment settings with each use.

[0311] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0312] Step 1: Data collection

[0313] The server collects user behavioral and emotional data.

[0314] Specifically, it collects application usage history, music playback history, video viewing history, and language usage patterns from smartphone and PC applications (e.g., music player apps, video streaming apps).

[0315] In addition, facial expression and voice data is acquired through the device's camera and microphone, and this is analyzed by the emotion engine.

[0316] The input is "various user usage data" and the output is "collected behavioral data and emotional data."

[0317] Step 2: Analyze the data and generate a profile

[0318] The server analyzes the collected behavioral and emotional data using machine learning algorithms (e.g., Scikit-learn, TensorFlow).

[0319] Machine learning algorithms are used to run clustering algorithms and sentiment analysis models to identify user preferences and behavioral patterns.

[0320] The input is "collected data" and the output is "a profile showing the user's preferences and behavioral patterns."

[0321] Specifically, the data is preprocessed (scaling, interpolation, etc.), input into the model, and calculations are performed.

[0322] Step 3: Receiving the user request

[0323] The terminal receives user requests through an interface (e.g., smartphone app, voice assistant).

[0324] Specifically, when a user verbally commands "create a relaxing environment," the voice input system converts this into text and registers the request.

[0325] The input is "user request" and the output is "structured request data."

[0326] Step 4: Sending the request to the server

[0327] The terminal structures the user's request and real-time emotion data and transmits them to the server.

[0328] As a specific operation, the robot requests a prompt such as "Create a relaxing environment" and sends emotional data such as "I feel stressed" to the server.

[0329] The input is "structured request data and emotion data" and the output is "data sent to the server."

[0330] Step 5: Directing content generation

[0331] The server compares the received request, updated profile, and emotion engine data and issues appropriate instructions to each generative AI model.

[0332] As a specific operation, specific commands are sent as prompts to the music generation AI model, such as "Generate calming music," and to the video generation AI model, such as "Generate a landscape video."

[0333] The input is "request data, profile, and emotional data," and the output is "instructions to the generative AI model."

[0334] Step 6: Generate content

[0335] The generative AI model generates content based on instructions from the server.

[0336] Specifically, the music generation AI generates relaxing music with little noise, the video generation AI generates images of tranquil landscapes, and the language generation AI generates relaxing essays.

[0337] The input is "instructions from the server" and the output is "generated music files, video files, and text data."

[0338] Step 7: Receiving generated content

[0339] The server receives the content generated by the generative AI model and stores and manages it appropriately.

[0340] Specifically, it saves music files in the appropriate format (e.g., MP3, WAV) and converts video files for streaming.

[0341] The input is the "generated content" and the output is the "stored content."

[0342] Step 8: Deliver your content

[0343] The server distributes the generated content to the appropriate IoT devices.

[0344] Specifically, it sends music files to a smart speaker, streams video files to a smart display, and sends text data to an e-book reader.

[0345] The input is "stored content" and the output is "delivered content."

[0346] Step 9: Adjust your environment

[0347] Each IoT device automatically adjusts its environment based on the content it receives.

[0348] Specifically, the smart speaker will play relaxing music, the smart display will show a landscape image, and the smart light will adjust the color and brightness of the lighting.

[0349] The input is the "distributed content" and the output is the "conditioned environment."

[0350] Step 10: Gather feedback

[0351] The terminal collects the user's feedback and sends it to the server.

[0352] Specifically, it collects voice input, tap gestures, and environmental sensor data, analyzes it with an emotion engine, and sends the current emotional state to the server.

[0353] The input is "user feedback and emotion data" and the output is "updated user profile and system feedback."

[0354] In this way, the system utilizes user behavioral data and real-time emotional data to provide an optimal environment that meets the user's needs.

[0355] (Application example 2)

[0356] 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."

[0357] In modern society, there is a demand for effective utilization of user behavioral and emotional data to provide optimal content and environments in real time. However, conventional systems have had difficulty recognizing user emotions in real time and generating and delivering optimal content that meets specific requests. They also face challenges in appropriately collecting and incorporating user feedback and maintaining highly accurate user profiles. As a result, they have not been able to provide an environment that adequately enhances user satisfaction.

[0358] The identification processing 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 collecting user behavioral data and emotional data, means for analyzing the collected behavioral data and emotional data to generate and update a user profile, means for receiving a user request, means for generating a prompt sentence for a generative AI model based on the received request and user profile, means for instructing the generative AI model to generate content using the generated prompt sentence, means for receiving the generated content and delivering it to an environment adjustment device, and means for adjusting the environment based on the content received by the environment adjustment device. This makes it possible to comprehensively analyze the user's behavioral data and emotional data and provide optimal content and an environment that meets the user's requests in real time.

[0359] "User behavior data" refers to data related to a series of operations and activities performed by a user, such as application usage history, music playback history, and video viewing history.

[0360] "Emotion data" is data that indicates the user's emotional state, such as facial expressions and tone of voice captured through a camera or microphone.

[0361] A "user profile" is a data set that compiles information about a user's preferences, behavioral patterns, and emotions.

[0362] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate content such as music, video, and text in response to user requests.

[0363] A "prompt sentence" is a text sentence generated to give specific instructions to a generative AI model.

[0364] An "environmental adjustment device" is a device that adjusts the environment based on specified content, such as a smart speaker, smart display, or lighting device.

[0365] "Feedback" refers to opinions and reactions provided by users, or emotional state data collected automatically by the system.

[0366] A "server" is an information processing device that collects and analyzes user behavioral and emotional data, and generates and updates user profiles.

[0367] This invention is a system that collects and analyzes user behavioral and emotional data in real time and provides an optimal environment according to the user's requests. This system is realized by linking a server that generates and updates user profiles, a terminal that receives requests, content generation by generative AI, and an environment adjustment device.

[0368] First, the server collects user behavioral and emotional data. Behavioral data includes application usage history and music and video playback history, while emotional data includes facial expressions and voice tone captured through cameras and microphones. The collected data is analyzed using machine learning algorithms such as GOOGLE TENSOR® Flow. This analysis identifies user preferences and behavioral patterns, and a user profile is created and updated.

[0369] Next, the device receives the user's request through the interface. For example, a user might input "I want to relax" into a smartphone app. At the same time, an emotion recognition engine (Microsoft Azure Cognitive Services) recognizes the user's emotional state in real time, and this data is also sent to the server.

[0370] When the server receives this request, it generates a specific prompt for the generative AI model based on the user profile and emotional data. This prompt is used to instruct the generative AI model to generate content. For example, an instruction such as "Generate relaxing music" is sent to the generative AI model.

[0371] Generative AI models (e.g., Jukedeck, Runway, OpenAI GPT) receive instructions and generate their respective content. A music generation AI model generates relaxing music, a video generation AI model generates relaxing landscape footage, and a language generation AI model generates soothing essays. The generated content is sent back to the server, which distributes it to the environment adjustment device.

[0372] The environmental adjustment devices include smart speakers, smart displays, and lighting fixtures. These devices adjust the environment based on the content they receive: a smart speaker plays relaxing music, a smart display shows a video of a relaxing scene, and lighting fixtures are adjusted to a relaxing mode.

[0373] Finally, user feedback is collected through voice input and tap gestures, and an emotion recognition engine also continuously monitors the user's emotional state. The collected feedback and emotion data are sent back to the server for further updating of the user profile.

[0374] For example, if a user inputs "I want to concentrate" and the emotion engine detects that the user is slightly tired, the server will send prompts to the generative AI model such as "Please generate music that will help me concentrate" or "Please generate a video with moderate movement." The generated music and video will then be distributed to smart speakers and smart displays, providing the user with an environment in which they can concentrate.

[0375] An example of a prompt is as follows:

[0376] "Generate relaxing music."

[0377] "The current video generation task is to create a video of a relaxing scene. Please create an appropriate video."

[0378] "Generate soothing essays. Users want to relax through reading."

[0379] This system makes it possible to comprehensively utilize user behavioral and emotional data to provide optimal content and environments in real time that meet the user's needs.

[0380] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0381] Step 1:

[0382] A user inputs a request using a smartphone app. At the same time, the user's emotional data is collected. The emotional data consists of facial expressions and voice tone captured through the smartphone's camera and microphone. This input data is sent from the device to the server.

[0383] Input: User request (e.g., "I want to relax"), emotional data (facial expression, tone of voice)

[0384] Output: A request containing the user's request and emotion data

[0385] Step 2:

[0386] The server analyzes the user's request and emotional data received from the device. The collected emotional data is analyzed using an emotion recognition engine (Microsoft Azure Cognitive Services). The analysis results are integrated with the existing user profile to understand the request.

[0387] Input: User requests, emotion data

[0388] Output: Parsed emotion information, updated request data

[0389] Step 3:

[0390] The server generates specific prompts for the generative AI model based on the analyzed emotional information and the user profile. These prompts are necessary to instruct the generative AI model to generate appropriate content.

[0391] Input: Analyzed emotion information, user profile

[0392] Output: The generated prompt (e.g., "Generate some relaxing music.")

[0393] Step 4:

[0394] The server uses the generated prompts to send instructions for generating content to each generative AI model, which then generates music, video, text, etc.

[0395] Input: Generated prompt text

[0396] Output: Content generated by the generative AI model (music files, video files, text data)

[0397] Step 5:

[0398] The server receives the content obtained from the generative AI model and distributes it to the environment conditioning device.

[0399] Input: Generated content

[0400] Output: Content delivery request to each environmental adjustment device

[0401] Step 6:

[0402] The environmental adjustment devices (smart speakers, smart displays, lighting devices) adjust the environment based on the received content: the smart speaker plays relaxing music, the smart display shows a video of a relaxing scene, and the lighting devices are set to relaxation mode.

[0403] Input: Received content

[0404] Output: Controlled environment (music playback, video display, lighting settings)

[0405] Step 7:

[0406] Users provide feedback on the environment and content provided. Feedback is collected through voice input and tap gestures, and an emotion recognition engine analyzes their current emotional state. This feedback data is then sent back to the server and used to update the user profile.

[0407] Input: User feedback, real-time sentiment data

[0408] Output: Feedback data sent to server, updated user profile

[0409] This series of steps makes it possible to comprehensively utilize user behavioral and emotional data to provide optimal content and environments in real time that meet the user's needs.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] [Second embodiment]

[0414] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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).

[0420] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0425] 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."

[0426] This invention relates to a system that analyzes user behavior data and provides an optimal environment according to individual requests. This system provides an optimal real-time environment for users by adjusting the environment through collaboration with a server that collects user behavior data and generates and updates profiles, a terminal that receives user requests, content generation using generative AI, and IoT devices.

[0427] Program processing

[0428] Creating a User Profile

[0429] The server collects user behavioral data, including application usage history, music playback history, video viewing history, language usage patterns, etc. The server then applies this data to machine learning algorithms to identify user preferences and behavioral patterns and generate and update user profiles.

[0430] Receiving user requests

[0431] The device provides an interface for receiving requests from the user, for example, a request such as "create a relaxing environment" input through a smartphone app or voice assistant, and sends the request to the server.

[0432] Content Generation Instructions

[0433] The server issues appropriate instructions to the generation AI based on the received user request and the generated profile. For example, it may ask the music generation AI to generate "music to create a relaxing environment." Similarly, it sends instructions to the video generation AI and language generation AI to generate "relaxing images" and "relaxing text."

[0434] Content Delivery

[0435] The server that receives the content generated by the generative AI distributes it to the appropriate IoT device: for example, music files to a smart speaker, video files to a smart display, and text data to an e-book reader.

[0436] Adjusting the environment

[0437] The terminals (each IoT device) adjust their settings based on the content received from the server. Smart speakers play music, smart displays show images, and smart lights adjust the color and brightness of lighting. This allows users to experience a relaxing environment.

[0438] Specific Examples

[0439] Example 1: Relaxed environment

[0440] The user enters "I want to relax" through the app.

[0441] The terminal sends the request to the server.

[0442] Based on the user's profile and requests, the server instructs the generative AI to generate "relaxing music," "landscape footage," and "relaxing essays."

[0443] The generative AI generates appropriate music, video, and text and sends them to the server.

[0444] The server distributes this data to smart speakers, smart displays, and e-readers.

[0445] The terminal plays music, displays videos, and displays essays.

[0446] Example 2: In an environment where you can concentrate

[0447] Users input "I want to concentrate" through the app.

[0448] The terminal sends the request to the server.

[0449] Based on the user's profile and requests, the server instructs the generative AI to generate "music that improves concentration," "images with moderate movement," and "text that improves concentration."

[0450] The generation AI generates appropriate content and sends it to the server.

[0451] The server distributes this data to smart speakers, smart displays, and e-readers.

[0452] The terminal plays music, displays video, and displays text.

[0453] This system provides an optimal environment based on user behavior data and real-time requests. It also continuously updates the user profile through feedback, enabling even more accurate environment settings for subsequent uses.

[0454] The processing flow will be explained below.

[0455] Step 1: Collect user behavior data

[0456] The server periodically collects users' application usage history, music playback history, video viewing history, language usage patterns, etc. This includes data sent from IoT devices such as smartphones, smart speakers, and smart displays.

[0457] Step 2: Analyze behavioral data

[0458] The server then applies machine learning algorithms to analyze the collected behavioral data, for example, identifying preferred genres from a user's music playback history and determining the types of videos they like from their video viewing history.

[0459] Step 3: Update your user profile

[0460] The server generates or updates a user profile based on the analysis results, reflecting the user's preferences and behavioral patterns. The updated profile includes the user's preferred music genres, video types, language styles, etc.

[0461] Step 4: Receive user requests

[0462] The device receives requests from the user through an interface, for example, a request to "create a relaxing environment" via a smartphone app or voice assistant.

[0463] Step 5: Submitting the request

[0464] The device sends the user's request as structured data (e.g., JSON format) to the server. The server receives it and starts the next process.

[0465] Step 6: Content Generation Instructions

[0466] The server compares the user's request with the updated profile and issues appropriate instructions to each AI generator. For example, to create a "relaxing environment," the server might instruct the music generator AI to "generate calming music" and the video generator AI to "generate landscape images."

[0467] Step 7: Run content generation

[0468] Generative AI (music generation AI, video generation AI, language generation AI) generates content based on their respective instructions. For example, music generation AI generates relaxing music, video generation AI generates landscape images, and language generation AI generates relaxing essays.

[0469] Step 8: Receive your content

[0470] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[0471] Step 9: Deliver your content

[0472] The server then sends the generated content to the appropriate IoT device: music files to a smart speaker, video files to a smart display, text data to an e-reader, and so on.

[0473] Step 10: Adjusting the environment

[0474] The terminals (each IoT device) use the received content to automatically adjust the environment: for example, a smart speaker plays relaxing music, a smart display shows a landscape image, and smart lights adjust the color and brightness of the lighting to a relaxing mode.

[0475] Step 11: Gather feedback

[0476] The device collects user feedback, including voice input, tap gestures, and even data from environmental sensors, which is sent to a server and used to further update the user profile.

[0477] Example 1

[0478] 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."

[0479] Many modern systems only collect user behavior data, but are unable to provide an appropriate environment based on that data. Furthermore, they are limited in their ability to respond to user requests in real time, automatically generate content, and integrate with IoT devices, making it difficult to provide an optimal experience for users.

[0480] 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.

[0481] In this invention, the server includes means for collecting user behavioral data, means for analyzing the collected behavioral data using a machine learning algorithm to generate and update a user profile, interface means for receiving user requests, means for instructing content generation by sending appropriate prompts to a generation AI based on the received request and the user profile, means for receiving the generated content and distributing it to an IoT device via a network, and means for the IoT device to adjust its settings based on the received content to optimize the environment, thereby making it possible to provide an optimal environment based on the user's behavioral data and real-time requests.

[0482] "User behavioral data" refers to general information about user behavior and choices, such as application usage history, music playback history, video viewing history, and text message exchanges.

[0483] "Machine learning algorithm" is a general term for algorithms that automatically learn patterns based on large amounts of data and make predictions and classifications, and is used in this system to generate and update user profiles.

[0484] A "user profile" is a collection of data that represents characteristics such as a user's preferences and behavioral patterns, generated from collected user behavioral data and analysis results based on that data.

[0485] "Interface means" refers to a window or device through which a user inputs requests or information, such as a smartphone app or voice assistant.

[0486] "Generative AI" refers to artificial intelligence that automatically generates content such as text, music, and images based on user requests.

[0487] A "prompt" refers to an input sentence, such as an instruction or question, given to the generation AI, which determines the content to be generated.

[0488] "Means for distribution over a network" refers to a method or apparatus for transmitting generated content to IoT devices using the Internet or other communications networks.

[0489] An "IoT device" refers to a device that is connected to the Internet and can send and receive data and perform specific functions, such as a smart speaker, smart display, or smart light.

[0490] "Means for optimizing the environment" refers to IoT devices automatically adjusting their settings based on the content they receive, providing the optimal environment for the user.

[0491] The present invention relates to a system for collecting user behavior data, generating and updating profiles, and providing an optimal environment according to user requests. This system includes the following elements:

[0492] 1. Collecting user behavior data

[0493] The server collects behavioral data from various applications that users use on a daily basis, including application usage history, music playback history, video viewing history, language usage patterns, etc. To do this, it uses the Google Analytics API and general data collection tools.

[0494] 2. Creating and updating user profiles

[0495] The server analyzes the collected behavioral data using machine learning algorithms based on Python's Scikit-learn library. This analysis identifies user preferences and behavioral patterns, and generates and updates user profiles. For example, K-means clustering can be used to classify user interests and create profiles based on those.

[0496] 3. Receiving user requests

[0497] The device provides an interface to receive requests from the user, which can be done through a smartphone app or a voice assistant (e.g., Amazon Alexa or Google Assistant). When the user types a request, such as "create a relaxing environment," the device sends the request to the server.

[0498] 4. Content Generation Instructions

[0499] The server sends appropriate prompts to the AI ​​based on the user's request and the generated profile to instruct it to generate content. For example, for text generation, OpenAI's GPT-4 is used, sending a prompt such as "Generate relaxing music."

[0500] Example prompt: "Create soothing music that's perfect for someone who wants to relax."

[0501] 5. Content Delivery

[0502] The content generated by the generative AI model is returned to the server, which then distributes it to the appropriate IoT device: for example, music files to a smart speaker (commonly known as a smart speaker), video files to a smart display (commonly known as a smart display), and text data to an e-reader (commonly known as an e-reader).

[0503] 6. Adjusting the environment

[0504] Each IoT device (e.g., smart speaker, smart display, smart light, etc.) automatically adjusts its settings based on the content received from the server, allowing users to experience a relaxing or focused environment.

[0505] Example: When a user enters "I want to relax" into an app, the server sends instructions to the AI ​​generator based on the user profile. The AI ​​generator generates music and video, which are then distributed to a smart speaker and a smart display, respectively, and the smart light is set to warm colors.

[0506] In this way, the system can provide an optimal environment based on the user's behavioral data and real-time requirements. Furthermore, by continuously updating the user profile through feedback, the system can achieve even more accurate environment settings for subsequent uses.

[0507] This system allows users to easily obtain the optimal environment that meets their individual needs, improving their quality of life.

[0508] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0509] Step 1: Collect user behavior data

[0510] The server collects data on the user's behavior in various applications. Specifically, it collects app usage history on smartphones and PCs, music playback history, video viewing history, text message exchanges, etc. It receives data from various APIs (e.g., Google Analytics API, Spotify API) as input and stores that data in an internal database as output.

[0511] Specific behavior:

[0512] The server calls the Google Analytics API to obtain app usage history.

[0513] The server uses the Spotify API to collect the user's music playback history.

[0514] Save the retrieved data in the database.

[0515] Step 2: Create and update user profiles

[0516] The server runs the collected behavioral data through a machine learning algorithm (e.g., Scikit-learn's K-means clustering). Using the data collected in the previous step as input, it analyzes the user's preferences and behavioral patterns, and generates and updates a user profile as output.

[0517] Specific behavior:

[0518] The server preprocesses the acquired behavioral data and converts it into numerical data.

[0519] The server inputs the preprocessed data into the K-means clustering algorithm.

[0520] A user profile is generated based on the analysis results and stored in a database.

[0521] Step 3: Receiving the user request

[0522] The device provides an interface (such as a smartphone app or a voice assistant) to receive requests from the user. It receives the user's request (e.g., "I want to relax") as input and sends the request to the server as output.

[0523] Specific behavior:

[0524] The user types "I want to relax" into a text field on the smartphone app.

[0525] The terminal sends this request to the server as an HTTP request.

[0526] Step 4: Directing content generation

[0527] The server sends appropriate prompts to the generation AI based on the user's request and the generated profile, instructing it to generate content. Using the user's request and profile data as input, the server creates prompts to send to the generation AI as output. The generation AI receives instructions in advance via an API or other means.

[0528] Specific behavior:

[0529] The server extracts features of the content for relaxation from the user profile.

[0530] The server calls the API of the generative AI model and sends a prompt to generate relaxing music.

[0531] Step 5: Deliver your content

[0532] After the content generated by the generative AI model is returned to the server, it is distributed to the appropriate IoT devices (smart speakers, smart displays, e-readers, etc.) It receives the generated content as input and sends data to each IoT device as output.

[0533] Specific behavior:

[0534] The server receives the music file returned by the generation AI.

[0535] The server sends the music file to the smart speaker as an HTTP request.

[0536] Step 6: Adjusting the environment

[0537] Each IoT device automatically adjusts its settings based on the content it receives from the server. It receives content as input and adjusts its behavior as output. For example, a smart speaker plays music, and a smart display displays video.

[0538] Specific behavior:

[0539] The smart speaker plays the music files received from the server.

[0540] The smart display plays the video file received from the server.

[0541] The smart light changes the color of the light to a warmer color based on instructions from the server.

[0542] This processing step allows for providing an optimal environment based on the user's behavioral data and real-time requirements.

[0543] (Application example 1)

[0544] 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."

[0545] Conventional autonomous vehicles have had difficulty providing an environment that appropriately reflects passengers' specific needs, such as relaxation and concentration, while on board. Furthermore, the generation of profiles based on passenger behavior data and the use of such profiles to generate content and automatically adjust the environment were insufficient, resulting in a lack of a means to provide an optimal environment for each individual user.

[0546] 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.

[0547] In this invention, the server includes a means for collecting user behavioral data, a means for analyzing the collected behavioral data to generate and update a user profile, and a means for receiving user requests. This allows the server to instruct a generation AI to generate content based on the received request and user profile, receive the generated content, and distribute it to the in-vehicle system. Furthermore, the in-vehicle system can control at least one of lighting, music playback, and video display based on the received content, providing an environment tailored to the user's requests in real time. This system allows the server to provide an optimal riding environment for each user, ensuring a comfortable driving experience.

[0548] "User behavioral data" refers to data such as operation history, browsing history, and playback history when a user uses an application or device, which makes it possible to analyze the preferences and behavioral patterns of individual users.

[0549] A "user profile" is a collection of information generated based on collected user behavior data, and specifically indicates the user's preferences, behavioral patterns, and characteristics according to their requirements.

[0550] "Generative AI" refers to artificial intelligence technology that generates content such as music, video, and text based on user profiles and requests. For example, it can automatically generate music and videos for relaxation.

[0551] "In-vehicle system" includes information processing devices and entertainment systems installed in autonomous vehicles, and has the function of playing and displaying content in response to user requests and adjusting the in-vehicle environment.

[0552] "Means for adjusting the environment" refers to the ability of the in-vehicle system to control environmental elements such as lighting, music playback, and video display in real time based on the generated content, such as playing relaxation music or adjusting the color and brightness of lighting.

[0553] This invention is a system for collecting and analyzing user behavior data in an autonomous vehicle, and providing an environment that is optimal for individual needs based on that data. This system is composed of the following elements: a server, a user terminal, and an in-vehicle system.

[0554] System Configuration

[0555] server

[0556] The server collects user behavioral data (e.g., application usage history, music playback history, video viewing history), analyzes the data, and generates and updates user profiles. A RESTful API is used to collect the behavioral data, and PostgreSQL is used as the database. A machine learning algorithm is used for the analysis to identify user behavioral patterns and preferences.

[0557] The server also provides an interface for receiving requests from users (e.g., "I want to relax" or "I want to concentrate"). Based on these requests, it issues instructions to a generative AI model (e.g., OpenAI's GPT-4) to generate appropriate content. The instructions are generated as prompt sentences and sent to the generative AI.

[0558] The content (e.g., music, video, text) returned by the generative AI is sent back to the server, converted into an appropriate format, and delivered to the in-car system.

[0559] User terminal

[0560] The user terminal (e.g., a smartphone) provides an application for inputting user requests. Through this application, the user inputs requests such as "I want to relax" or "I want to concentrate," and the input data is sent to the server.

[0561] In-vehicle systems

[0562] The in-vehicle system adjusts the environment based on the generated content received from the server. Specifically, it plays music through the in-vehicle speakers, displays images on the in-vehicle display, adjusts the color and brightness of the smart lights, etc. The in-vehicle system automates these operations using information processing devices such as Android Auto.

[0563] Processing flow

[0564] 1. User behavior data collection: The server collects user usage and playback history.

[0565] 2. User profile generation and update: The collected data is analyzed using machine learning algorithms to generate and update user profiles.

[0566] 3. Receiving a user request: The user enters a request into the smartphone app and the server receives it.

[0567] 4. Content generation by generative AI: The server sends a prompt to the generative AI to generate appropriate content. For example, "Generate relaxing music. The user's profile is as follows: [specific data]."

[0568] 5. Content distribution: The server distributes the generated content to the in-vehicle system.

[0569] 6. Environmental adjustment: Based on the content received by the in-vehicle system, it plays music, displays images, adjusts lighting, etc.

[0570] Specific examples

[0571] If a user requests "I want to relax," the server instructs the generation AI to generate "relaxing music" based on the user profile. The music file returned by the generation AI is converted into the appropriate format on the server and distributed to the car's speakers. Relaxation videos are displayed on the car display, and the smart lights are adjusted to a soft, warm light. This series of actions allows the user to enjoy a relaxing environment in the car.

[0572] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0573] Step 1:

[0574] The server collects user behavior data.

[0575] Input: User's application usage history, music playback history, video viewing history

[0576] Data processing: Save to database via API

[0577] Output: A database of accumulated behavioral data

[0578] Step 2:

[0579] The server analyzes the collected data and generates and updates the user profile.

[0580] Input: Behavioral data stored in a database

[0581] Data Computing: Using machine learning algorithms to identify user behavior patterns and preferences

[0582] Output: Updated user profile

[0583] Step 3:

[0584] The user inputs a request through a terminal.

[0585] Input: User request (e.g., "I want to relax" or "I want to concentrate")

[0586] Data processing: Sending user requests to the server

[0587] Output: Request data is sent to the server

[0588] Step 4:

[0589] The server instructs the generation AI to generate content based on the received request and user profile.

[0590] Input: User request, updated user profile

[0591] Data calculation: Generate prompts for the generation AI and instruct it to specify the request. Example: "Generate relaxing music. The user's profile is as follows: [specific data]."

[0592] Output: Prompt sent to the generation AI

[0593] Step 5:

[0594] The generation AI generates the content and sends it to the server.

[0595] Input: Prompt sent to the generation AI

[0596] Data processing: Generative AI generates content based on prompts (e.g., music files, video files, text)

[0597] Output: The generated content is sent to the server

[0598] Step 6:

[0599] The server receives the generated content and distributes it to the in-vehicle system.

[0600] Input: Content received from the generation AI

[0601] Data processing: Converting content into the appropriate format and delivering it to the in-vehicle system

[0602] Output: Content delivered to the in-car system

[0603] Step 7:

[0604] The in-vehicle system adjusts the environment based on the content it receives.

[0605] Input: Content delivered from the server (music files, video files, text, etc.)

[0606] Data calculation and processing: Set up the environment for music playback, video display, lighting adjustment, etc.

[0607] Output: Optimal in-car environment according to user demands

[0608] 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.

[0609] This invention relates to a system that analyzes user behavioral and emotional data and provides an optimal environment in response to user requests. In particular, this invention incorporates an emotion engine that recognizes user emotions in real time and utilizes that data to adjust the environment. This system provides an optimal environment by collecting and analyzing user behavioral and emotional data, creating and updating profiles on a server, receiving user requests from a terminal, generating content using a generative AI, and linking with IoT devices.

[0610] Program processing

[0611] Creating a User Profile

[0612] The server collects user behavioral and emotional data. Behavioral data includes application usage history, music playback history, video viewing history, and language usage patterns, while emotional data includes facial expressions and voice tone captured through cameras and microphones. The server analyzes this data using machine learning algorithms to identify user preferences and behavioral patterns. At the same time, the emotion engine also analyzes user emotions in real time and sends the results to the server.

[0613] Update your user profile

[0614] The server generates or updates a user profile based on the analysis results and data from the emotion engine, including the user's preferred music genres, video types, and preferences for content that corresponds to specific emotional states.

[0615] Receiving user requests

[0616] The device receives requests from the user through the interface. For example, the user may say, "Create a relaxing environment" through a smartphone app or voice assistant. If the emotion engine already recognizes an emotion, such as "stress," that information is also sent to the server along with the request.

[0617] Submitting a request

[0618] The device structures the user's request and emotion data and sends them to the server, which receives them and starts the next process.

[0619] Content generation instructions

[0620] The server compares the user's request, updated profile, and emotion engine data and issues appropriate instructions to each AI generator. For example, to create a "relaxing environment," the server instructs the music generator AI to "generate calming music" and the video generator AI to "generate landscape images."

[0621] Content generation execution

[0622] The generative AIs (music generation AI, video generation AI, and language generation AI) generate content based on their respective instructions. The music generation AI generates relaxing music, the video generation AI generates landscape images, and the language generation AI generates relaxing essays.

[0623] Receiving content

[0624] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[0625] Content Delivery

[0626] The server then sends the generated content to the appropriate IoT device: music files to a smart speaker, video files to a smart display, text data to an e-reader, and so on.

[0627] Adjusting the environment

[0628] The terminals (each IoT device) automatically adjust their environment based on the content they receive: for example, a smart speaker plays relaxing music, a smart display shows a landscape image, and smart lights adjust the color and brightness of the lights to a relaxing mode.

[0629] Collecting feedback

[0630] The device collects user feedback, including voice input, tap gestures, and even data from environmental sensors, along with an emotion engine, to analyze the user's current emotional state, which is then sent to the server for further updates to the user profile.

[0631] Specific Examples

[0632] Example 1: Relaxed environment

[0633] The user inputs "I want to relax" through the app, and at the same time, the emotion engine recognizes that the user is feeling stressed.

[0634] The terminal transmits the request and the emotion data to the server.

[0635] Based on the user's profile and emotional data, the server instructs the generative AI to generate "relaxing music," "landscape footage," and "relaxing essays."

[0636] The generative AI generates appropriate music, video, and text and sends them to the server.

[0637] The server distributes this data to smart speakers, smart displays, and e-readers.

[0638] The device plays music, displays videos, and displays essays, while an emotion engine continuously monitors the effects of the environment.

[0639] Example 2: In an environment where you can concentrate

[0640] The user inputs "I want to concentrate" through the app, and at the same time the emotion engine recognizes that the user is slightly tired.

[0641] The terminal transmits the request and the emotion data to the server.

[0642] Based on the user's profile and emotional data, the server instructs the generative AI to generate "music that improves concentration," "images with moderate movement," and "text that improves concentration."

[0643] The generation AI generates appropriate content and sends it to the server.

[0644] The server distributes this data to smart speakers, smart displays, and e-readers.

[0645] The device plays music, displays video, and displays text, while an emotion engine continuously monitors the user's emotional state and fine-tunes the environment as needed.

[0646] The system utilizes user behavioral data and real-time emotional data to provide an environment that is optimally tailored to the user's needs. Through feedback, the system continuously updates the user profile, achieving more accurate environment settings with each repeated use.

[0647] The processing flow will be explained below.

[0648] Step 1: Collect behavioral and emotional data

[0649] The server periodically collects user behavioral data such as application usage history, music playback history, video viewing history, and language usage patterns. The emotion engine also analyzes the user's facial expressions and voice tone in real time through cameras and microphones to obtain emotion data.

[0650] Step 2: Analyze behavioral and emotional data

[0651] The server analyzes the collected behavioral data using machine learning algorithms. For example, it identifies preferences based on the genres of music the user has listened to or the types of videos they have watched. The emotion engine analyzes the acquired emotion data and identifies the user's current emotional state (e.g., stress, relaxation, lack of concentration, etc.).

[0652] Step 3: Update your user profile

[0653] The server generates or updates a user profile based on the analysis of the behavioral and emotional data, including the user's preferred music genres, video types, and content preferences that correspond to specific emotional states.

[0654] Step 4: Receive user requests

[0655] The device receives a request from the user through the interface. For example, the user may input "Create a relaxing environment" through a smartphone app or voice assistant. The current emotional state recognized by the emotion engine is also sent to the server along with the request.

[0656] Step 5: Sending request and emotion data

[0657] The device structures the user's request and emotion data and sends it to the server in a standard format such as JSON.

[0658] Step 6: Content Generation Instructions

[0659] The server compares the user's request, updated profile, and emotion engine data, and issues appropriate instructions to each generation AI. For example, to create a "relaxing environment," the server instructs the music generation AI to "generate calming music" and the video generation AI to "generate relaxing videos."

[0660] Step 7: Run content generation

[0661] The generative AIs (music generation AI, video generation AI, and language generation AI) generate content based on their respective instructions. The music generation AI generates relaxing music, the video generation AI generates natural landscape footage, and the language generation AI generates relaxing essays.

[0662] Step 8: Receive your content

[0663] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[0664] Step 9: Deliver your content

[0665] The server then sends the generated content to IoT devices, for example, music files to smart speakers, video files to smart displays, and text data to e-readers.

[0666] Step 10: Adjusting the environment

[0667] The terminals (each IoT device) automatically adjust their environment based on the content they receive: for example, a smart speaker plays relaxing music, a smart display shows natural scenery, and smart lights adjust the color and brightness of the lights to a relaxing mode.

[0668] Step 11: Gather feedback

[0669] The device collects user feedback, including voice input, tap gestures, and data from environmental sensors. The emotion engine also continuously monitors the user's emotional state and sends it to the server for further updates to the user profile.

[0670] Example 2

[0671] 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."

[0672] In modern daily life, it is difficult to provide an optimal environment for users by utilizing their behavioral and emotional data. Specifically, there is a lack of technology that can respond to diverse user requests in real time and appropriately adjust the environment while monitoring the effects. This poses a challenge, making it difficult to provide a comfortable, relaxing, and focused environment for users.

[0673] 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.

[0674] In this invention, the server includes means for collecting user behavioral data and emotional data, means for analyzing the collected behavioral data and emotional data to generate and update a user profile, means for receiving a user request, means for instructing a generative AI model to generate content based on the received request and the user profile, means for receiving the generated content and delivering it to an IoT device, and means for adjusting an environment based on the content received by the IoT device, thereby making it possible to provide an optimal environment for the user and adjust the environment based on the user's behavioral data and real-time emotional state.

[0675] "User behavior data" is information that indicates user behavior, such as the user's history of using various applications, music and video playback history, and language usage patterns.

[0676] "Emotion data" is information that indicates the user's emotional state, such as the user's facial expression or tone of voice, and is acquired through a camera or microphone.

[0677] A "user profile" is information that indicates content preferences that correspond to a user's preferences, behavioral patterns, and emotional state based on collected behavioral and emotional data.

[0678] A "generative AI model" is an artificial intelligence algorithm or system that generates content such as music, video, or text based on user requests and profiles.

[0679] An "IoT device" is an internet-connected device that adjusts its environment based on the content delivered to it, and examples include smart speakers and smart displays.

[0680] "Means for adjusting the environment" refers to mechanisms that include the ability to play music from a smart speaker, display images on a smart display, and change the lighting settings of smart lights.

[0681] "Feedback" is information used to evaluate system performance and the user's emotional state through user-provided opinions, impressions, and data obtained from environmental sensors.

[0682] The present invention relates to a system that analyzes user behavioral and emotional data to provide an optimal environment in response to user requests. In particular, it incorporates an emotion engine, recognizes user emotions in real time, and uses that data to adjust the environment.

[0683] Specific hardware and software configurations

[0684] The system consists of the following main components:

[0685] Server: Collects data, analyzes it, generates profiles, directs content generation, and distributes it. The server has software libraries (e.g., Scikit-learn, TensorFlow) installed to run machine learning algorithms.

[0686] Device: The part of the system that receives user requests and transmits the request and emotion data to the server. Devices include smartphones, voice assistants, and smart displays.

[0687] Emotion engine: Recognizes the user's facial expressions and tone of voice and analyzes the resulting emotional data. Emotion engines include commonly used facial recognition and voice analysis APIs (e.g., Amazon Rekognition, Google Cloud Vision API, Microsoft Azure Cognitive Services).

[0688] IoT devices: These are devices that automatically adjust their environment based on the content they generate. Examples include smart speakers, smart displays, smart lights, and e-readers.

[0689] Data processing and calculation methods

[0690] The server collects user behavioral and emotional data. This data includes application usage history, music playback history, video viewing history, language usage patterns, and facial expressions and tone of voice captured through cameras and microphones. The server then analyzes this data using machine learning algorithms to identify user preferences and behavioral patterns. For example, it uses clustering algorithms and sentiment analysis models. Meanwhile, the emotion engine analyzes user emotions in real time and sends the results to the server.

[0691] Creating and updating user profiles

[0692] Based on the analysis and data from the emotion engine, the server generates or updates a user profile, including the user's preferred music genres, video types, and content preferences that correspond to particular emotional states.

[0693] Receiving and processing user requests

[0694] The device receives user requests through an interface (smartphone app or voice assistant). For example, the user might say, "Create a relaxing environment." If the emotion engine recognizes the user's emotional state (e.g., "I'm feeling stressed"), that information is also sent to the server. The device then structures this data and sends it to the server.

[0695] Directing and generating content

[0696] The server compares the received user request, updated profile, and emotion engine data, and issues appropriate instructions to each generative AI model. For example, to create a "relaxing environment," it issues specific instructions such as "generate calming music" to the music generation AI model and "generate a landscape video" to the video generation AI model. Examples of prompt sentences are "create a relaxing environment" and "generate calming music."

[0697] Content Generation and Delivery

[0698] Each generative AI model (music generation AI, video generation AI, language generation AI) generates content based on a specified prompt. The music generation AI generates quiet, slow-tempo music, the video generation AI generates videos of tranquil landscapes, and the language generation AI generates relaxing essays. The generated content is sent to a server and distributed to appropriate IoT devices (smart speakers, smart displays, e-book readers, etc.).

[0699] Tuning the environment and gathering feedback

[0700] IoT devices automatically adjust the environment based on the received content. For example, a smart speaker can play relaxing music, a smart display can display landscape images, and smart lights can set the lights in a relaxing mode. Furthermore, the emotion engine can analyze the user's current emotional state by collecting user feedback (voice input, tap gestures, environmental sensor data, etc.). This feedback is sent to the server and used to update the user profile.

[0701] The system utilizes user behavioral data and real-time emotional data to provide an optimal environment tailored to the user's needs, and continuously updates the user profile through feedback, ensuring accurate environment settings with each use.

[0702] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0703] Step 1: Data collection

[0704] The server collects user behavioral and emotional data.

[0705] Specifically, it collects application usage history, music playback history, video viewing history, and language usage patterns from smartphone and PC applications (e.g., music player apps, video streaming apps).

[0706] In addition, facial expression and voice data is acquired through the device's camera and microphone, and this is analyzed by the emotion engine.

[0707] The input is "various user usage data" and the output is "collected behavioral data and emotional data."

[0708] Step 2: Analyze the data and generate a profile

[0709] The server analyzes the collected behavioral and emotional data using machine learning algorithms (e.g., Scikit-learn, TensorFlow).

[0710] Machine learning algorithms are used to run clustering algorithms and sentiment analysis models to identify user preferences and behavioral patterns.

[0711] The input is "collected data" and the output is "a profile showing the user's preferences and behavioral patterns."

[0712] Specifically, the data is preprocessed (scaling, interpolation, etc.), input into the model, and calculations are performed.

[0713] Step 3: Receiving the user request

[0714] The terminal receives user requests through an interface (e.g., smartphone app, voice assistant).

[0715] Specifically, when a user verbally commands "create a relaxing environment," the voice input system converts this into text and registers the request.

[0716] The input is "user request" and the output is "structured request data."

[0717] Step 4: Sending the request to the server

[0718] The terminal structures the user's request and real-time emotion data and transmits them to the server.

[0719] As a specific operation, the robot requests a prompt such as "Create a relaxing environment" and sends emotional data such as "I feel stressed" to the server.

[0720] The input is "structured request data and emotion data" and the output is "data sent to the server."

[0721] Step 5: Directing content generation

[0722] The server compares the received request, updated profile, and emotion engine data and issues appropriate instructions to each generative AI model.

[0723] As a specific operation, specific commands are sent as prompts to the music generation AI model, such as "Generate calming music," and to the video generation AI model, such as "Generate a landscape video."

[0724] The input is "request data, profile, and emotional data," and the output is "instructions to the generative AI model."

[0725] Step 6: Generate content

[0726] The generative AI model generates content based on instructions from the server.

[0727] Specifically, the music generation AI generates relaxing music with little noise, the video generation AI generates images of tranquil landscapes, and the language generation AI generates relaxing essays.

[0728] The input is "instructions from the server" and the output is "generated music files, video files, and text data."

[0729] Step 7: Receiving generated content

[0730] The server receives the content generated by the generative AI model and stores and manages it appropriately.

[0731] Specifically, it saves music files in the appropriate format (e.g., MP3, WAV) and converts video files for streaming.

[0732] The input is the "generated content" and the output is the "stored content."

[0733] Step 8: Deliver your content

[0734] The server distributes the generated content to the appropriate IoT devices.

[0735] Specifically, it sends music files to a smart speaker, streams video files to a smart display, and sends text data to an e-book reader.

[0736] The input is "stored content" and the output is "delivered content."

[0737] Step 9: Adjust your environment

[0738] Each IoT device automatically adjusts its environment based on the content it receives.

[0739] Specifically, the smart speaker will play relaxing music, the smart display will show a landscape image, and the smart light will adjust the color and brightness of the lighting.

[0740] The input is the "distributed content" and the output is the "conditioned environment."

[0741] Step 10: Gather feedback

[0742] The terminal collects the user's feedback and sends it to the server.

[0743] Specifically, it collects voice input, tap gestures, and environmental sensor data, analyzes it with an emotion engine, and sends the current emotional state to the server.

[0744] The input is "user feedback and emotion data" and the output is "updated user profile and system feedback."

[0745] In this way, the system utilizes user behavioral data and real-time emotional data to provide an optimal environment that meets the user's needs.

[0746] (Application example 2)

[0747] 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."

[0748] In modern society, there is a demand for effective utilization of user behavioral and emotional data to provide optimal content and environments in real time. However, conventional systems have had difficulty recognizing user emotions in real time and generating and delivering optimal content that meets specific requests. They also face challenges in appropriately collecting and incorporating user feedback and maintaining highly accurate user profiles. As a result, they have not been able to provide an environment that adequately enhances user satisfaction.

[0749] The identification processing 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 collecting user behavioral data and emotional data, means for analyzing the collected behavioral data and emotional data to generate and update a user profile, means for receiving a user request, means for generating a prompt sentence for a generative AI model based on the received request and user profile, means for instructing the generative AI model to generate content using the generated prompt sentence, means for receiving the generated content and delivering it to an environment adjustment device, and means for adjusting the environment based on the content received by the environment adjustment device. This makes it possible to comprehensively analyze the user's behavioral data and emotional data and provide optimal content and an environment that meets the user's requests in real time.

[0750] "User behavior data" refers to data related to a series of operations and activities performed by a user, such as application usage history, music playback history, and video viewing history.

[0751] "Emotion data" is data that indicates the user's emotional state, such as facial expressions and tone of voice captured through a camera or microphone.

[0752] A "user profile" is a data set that compiles information about a user's preferences, behavioral patterns, and emotions.

[0753] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate content such as music, video, and text in response to user requests.

[0754] A "prompt sentence" is a text sentence generated to give specific instructions to a generative AI model.

[0755] An "environmental adjustment device" is a device that adjusts the environment based on specified content, such as a smart speaker, smart display, or lighting device.

[0756] "Feedback" refers to opinions and reactions provided by users, or emotional state data collected automatically by the system.

[0757] A "server" is an information processing device that collects and analyzes user behavioral and emotional data, and generates and updates user profiles.

[0758] This invention is a system that collects and analyzes user behavioral and emotional data in real time and provides an optimal environment according to the user's requests. This system is realized by linking a server that generates and updates user profiles, a terminal that receives requests, content generation by generative AI, and an environment adjustment device.

[0759] First, the server collects user behavioral and emotional data. Behavioral data includes application usage history and music and video playback history, while emotional data includes facial expressions and voice tone captured through cameras and microphones. The collected data is analyzed using machine learning algorithms such as Google TensorFlow. This analysis identifies user preferences and behavioral patterns, and a user profile is created and updated.

[0760] Next, the device receives the user's request through the interface. For example, a user might input "I want to relax" into a smartphone app. At the same time, an emotion recognition engine (Microsoft Azure Cognitive Services) recognizes the user's emotional state in real time, and this data is also sent to the server.

[0761] When the server receives this request, it generates a specific prompt for the generative AI model based on the user profile and emotional data. This prompt is used to instruct the generative AI model to generate content. For example, an instruction such as "Generate relaxing music" is sent to the generative AI model.

[0762] Generative AI models (e.g., Jukedeck, Runway, OpenAI GPT) receive instructions and generate their respective content. A music generation AI model generates relaxing music, a video generation AI model generates relaxing landscape footage, and a language generation AI model generates soothing essays. The generated content is sent back to the server, which distributes it to the environment adjustment device.

[0763] The environmental adjustment devices include smart speakers, smart displays, and lighting fixtures. These devices adjust the environment based on the content they receive: a smart speaker plays relaxing music, a smart display shows a video of a relaxing scene, and lighting fixtures are adjusted to a relaxing mode.

[0764] Finally, user feedback is collected through voice input and tap gestures, and an emotion recognition engine also continuously monitors the user's emotional state. The collected feedback and emotion data are sent back to the server for further updating of the user profile.

[0765] For example, if a user inputs "I want to concentrate" and the emotion engine detects that the user is slightly tired, the server will send prompts to the generative AI model such as "Please generate music that will help me concentrate" or "Please generate a video with moderate movement." The generated music and video will then be distributed to smart speakers and smart displays, providing the user with an environment in which they can concentrate.

[0766] An example of a prompt is as follows:

[0767] "Generate relaxing music."

[0768] "The current video generation task is to create a video of a relaxing scene. Please create an appropriate video."

[0769] "Generate soothing essays. Users want to relax through reading."

[0770] This system makes it possible to comprehensively utilize user behavioral and emotional data to provide optimal content and environments in real time that meet the user's needs.

[0771] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0772] Step 1:

[0773] A user inputs a request using a smartphone app. At the same time, the user's emotional data is collected. The emotional data consists of facial expressions and voice tone captured through the smartphone's camera and microphone. This input data is sent from the device to the server.

[0774] Input: User request (e.g., "I want to relax"), emotional data (facial expression, tone of voice)

[0775] Output: A request containing the user's request and emotion data

[0776] Step 2:

[0777] The server analyzes the user's request and emotional data received from the device. The collected emotional data is analyzed using an emotion recognition engine (Microsoft Azure Cognitive Services). The analysis results are integrated with the existing user profile to understand the request.

[0778] Input: User requests, emotion data

[0779] Output: Parsed emotion information, updated request data

[0780] Step 3:

[0781] The server generates specific prompts for the generative AI model based on the analyzed emotional information and the user profile. These prompts are necessary to instruct the generative AI model to generate appropriate content.

[0782] Input: Analyzed emotion information, user profile

[0783] Output: The generated prompt (e.g., "Generate some relaxing music.")

[0784] Step 4:

[0785] The server uses the generated prompts to send instructions for generating content to each generative AI model, which then generates music, video, text, etc.

[0786] Input: Generated prompt text

[0787] Output: Content generated by the generative AI model (music files, video files, text data)

[0788] Step 5:

[0789] The server receives the content obtained from the generative AI model and distributes it to the environment conditioning device.

[0790] Input: Generated content

[0791] Output: Content delivery request to each environmental adjustment device

[0792] Step 6:

[0793] The environmental adjustment devices (smart speakers, smart displays, lighting devices) adjust the environment based on the received content: the smart speaker plays relaxing music, the smart display shows a video of a relaxing scene, and the lighting devices are set to relaxation mode.

[0794] Input: Received content

[0795] Output: Controlled environment (music playback, video display, lighting settings)

[0796] Step 7:

[0797] Users provide feedback on the environment and content provided. Feedback is collected through voice input and tap gestures, and an emotion recognition engine analyzes their current emotional state. This feedback data is then sent back to the server and used to update the user profile.

[0798] Input: User feedback, real-time sentiment data

[0799] Output: Feedback data sent to server, updated user profile

[0800] This series of steps makes it possible to comprehensively utilize user behavioral and emotional data to provide optimal content and environments in real time that meet the user's needs.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] [Third embodiment]

[0805] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0806] 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.

[0807] 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).

[0808] 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.

[0809] 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.

[0810] 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).

[0811] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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."

[0817] This invention relates to a system that analyzes user behavior data and provides an optimal environment according to individual requests. This system provides an optimal real-time environment for users by adjusting the environment through collaboration with a server that collects user behavior data and generates and updates profiles, a terminal that receives user requests, content generation using generative AI, and IoT devices.

[0818] Program processing

[0819] Creating a User Profile

[0820] The server collects user behavioral data, including application usage history, music playback history, video viewing history, language usage patterns, etc. The server then applies this data to machine learning algorithms to identify user preferences and behavioral patterns and generate and update user profiles.

[0821] Receiving user requests

[0822] The device provides an interface for receiving requests from the user, for example, a request such as "create a relaxing environment" input through a smartphone app or voice assistant, and sends the request to the server.

[0823] Content Generation Instructions

[0824] The server issues appropriate instructions to the generation AI based on the received user request and the generated profile. For example, it may ask the music generation AI to generate "music to create a relaxing environment." Similarly, it sends instructions to the video generation AI and language generation AI to generate "relaxing images" and "relaxing text."

[0825] Content Delivery

[0826] The server that receives the content generated by the generative AI distributes it to the appropriate IoT device: for example, music files to a smart speaker, video files to a smart display, and text data to an e-book reader.

[0827] Adjusting the environment

[0828] The terminals (each IoT device) adjust their settings based on the content received from the server. Smart speakers play music, smart displays show images, and smart lights adjust the color and brightness of lighting. This allows users to experience a relaxing environment.

[0829] Specific Examples

[0830] Example 1: Relaxed environment

[0831] The user enters "I want to relax" through the app.

[0832] The terminal sends the request to the server.

[0833] Based on the user's profile and requests, the server instructs the generative AI to generate "relaxing music," "landscape footage," and "relaxing essays."

[0834] The generative AI generates appropriate music, video, and text and sends them to the server.

[0835] The server distributes this data to smart speakers, smart displays, and e-readers.

[0836] The terminal plays music, displays videos, and displays essays.

[0837] Example 2: In an environment where you can concentrate

[0838] Users input "I want to concentrate" through the app.

[0839] The terminal sends the request to the server.

[0840] Based on the user's profile and requests, the server instructs the generative AI to generate "music that improves concentration," "images with moderate movement," and "text that improves concentration."

[0841] The generation AI generates appropriate content and sends it to the server.

[0842] The server distributes this data to smart speakers, smart displays, and e-readers.

[0843] The terminal plays music, displays video, and displays text.

[0844] This system provides an optimal environment based on user behavior data and real-time requests. It also continuously updates the user profile through feedback, enabling even more accurate environment settings for subsequent uses.

[0845] The processing flow will be explained below.

[0846] Step 1: Collect user behavior data

[0847] The server periodically collects users' application usage history, music playback history, video viewing history, language usage patterns, etc. This includes data sent from IoT devices such as smartphones, smart speakers, and smart displays.

[0848] Step 2: Analyze behavioral data

[0849] The server then applies machine learning algorithms to analyze the collected behavioral data, for example, identifying preferred genres from a user's music playback history and determining the types of videos they like from their video viewing history.

[0850] Step 3: Update your user profile

[0851] The server generates or updates a user profile based on the analysis results, reflecting the user's preferences and behavioral patterns. The updated profile includes the user's preferred music genres, video types, language styles, etc.

[0852] Step 4: Receive user requests

[0853] The device receives requests from the user through an interface, for example, a request to "create a relaxing environment" via a smartphone app or voice assistant.

[0854] Step 5: Submitting the request

[0855] The device sends the user's request as structured data (e.g., JSON format) to the server. The server receives it and starts the next process.

[0856] Step 6: Content Generation Instructions

[0857] The server compares the user's request with the updated profile and issues appropriate instructions to each AI generator. For example, to create a "relaxing environment," the server might instruct the music generator AI to "generate calming music" and the video generator AI to "generate landscape images."

[0858] Step 7: Run content generation

[0859] Generative AI (music generation AI, video generation AI, language generation AI) generates content based on their respective instructions. For example, music generation AI generates relaxing music, video generation AI generates landscape images, and language generation AI generates relaxing essays.

[0860] Step 8: Receive your content

[0861] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[0862] Step 9: Deliver your content

[0863] The server then sends the generated content to the appropriate IoT device: music files to a smart speaker, video files to a smart display, text data to an e-reader, and so on.

[0864] Step 10: Adjusting the environment

[0865] The terminals (each IoT device) use the received content to automatically adjust the environment: for example, a smart speaker plays relaxing music, a smart display shows a landscape image, and smart lights adjust the color and brightness of the lighting to a relaxing mode.

[0866] Step 11: Gather feedback

[0867] The device collects user feedback, including voice input, tap gestures, and even data from environmental sensors, which is sent to a server and used to further update the user profile.

[0868] Example 1

[0869] 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."

[0870] Many modern systems only collect user behavior data, but are unable to provide an appropriate environment based on that data. Furthermore, they are limited in their ability to respond to user requests in real time, automatically generate content, and integrate with IoT devices, making it difficult to provide an optimal experience for users.

[0871] 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.

[0872] In this invention, the server includes means for collecting user behavioral data, means for analyzing the collected behavioral data using a machine learning algorithm to generate and update a user profile, interface means for receiving user requests, means for instructing content generation by sending appropriate prompts to a generation AI based on the received request and the user profile, means for receiving the generated content and distributing it to an IoT device via a network, and means for the IoT device to adjust its settings based on the received content to optimize the environment, thereby making it possible to provide an optimal environment based on the user's behavioral data and real-time requests.

[0873] "User behavioral data" refers to general information about user behavior and choices, such as application usage history, music playback history, video viewing history, and text message exchanges.

[0874] "Machine learning algorithm" is a general term for algorithms that automatically learn patterns based on large amounts of data and make predictions and classifications, and is used in this system to generate and update user profiles.

[0875] A "user profile" is a collection of data that represents characteristics such as a user's preferences and behavioral patterns, generated from collected user behavioral data and analysis results based on that data.

[0876] "Interface means" refers to a window or device through which a user inputs requests or information, such as a smartphone app or voice assistant.

[0877] "Generative AI" refers to artificial intelligence that automatically generates content such as text, music, and images based on user requests.

[0878] A "prompt" refers to an input sentence, such as an instruction or question, given to the generation AI, which determines the content to be generated.

[0879] "Means for distribution over a network" refers to a method or apparatus for transmitting generated content to IoT devices using the Internet or other communications networks.

[0880] An "IoT device" refers to a device that is connected to the Internet and can send and receive data and perform specific functions, such as a smart speaker, smart display, or smart light.

[0881] "Means for optimizing the environment" refers to IoT devices automatically adjusting their settings based on the content they receive, providing the optimal environment for the user.

[0882] The present invention relates to a system for collecting user behavior data, generating and updating profiles, and providing an optimal environment according to user requests. This system includes the following elements:

[0883] 1. Collecting user behavior data

[0884] The server collects behavioral data from various applications that users use on a daily basis, including application usage history, music playback history, video viewing history, language usage patterns, etc. To do this, it uses the Google Analytics API and general data collection tools.

[0885] 2. Creating and updating user profiles

[0886] The server analyzes the collected behavioral data using machine learning algorithms based on Python's Scikit-learn library. This analysis identifies user preferences and behavioral patterns, and generates and updates user profiles. For example, K-means clustering can be used to classify user interests and create profiles based on those.

[0887] 3. Receiving user requests

[0888] The device provides an interface to receive requests from the user, which can be done through a smartphone app or a voice assistant (e.g., Amazon Alexa or Google Assistant). When the user types a request, such as "create a relaxing environment," the device sends the request to the server.

[0889] 4. Content Generation Instructions

[0890] The server sends appropriate prompts to the AI ​​based on the user's request and the generated profile to instruct it to generate content. For example, for text generation, OpenAI's GPT-4 is used, sending a prompt such as "Generate relaxing music."

[0891] Example prompt: "Create soothing music that's perfect for someone who wants to relax."

[0892] 5. Content Delivery

[0893] The content generated by the generative AI model is returned to the server, which then distributes it to the appropriate IoT device: for example, music files to a smart speaker (commonly known as a smart speaker), video files to a smart display (commonly known as a smart display), and text data to an e-reader (commonly known as an e-reader).

[0894] 6. Adjusting the environment

[0895] Each IoT device (e.g., smart speaker, smart display, smart light, etc.) automatically adjusts its settings based on the content received from the server, allowing users to experience a relaxing or focused environment.

[0896] Example: When a user enters "I want to relax" into an app, the server sends instructions to the AI ​​generator based on the user profile. The AI ​​generator generates music and video, which are then distributed to a smart speaker and a smart display, respectively, and the smart light is set to warm colors.

[0897] In this way, the system can provide an optimal environment based on the user's behavioral data and real-time requirements. Furthermore, by continuously updating the user profile through feedback, the system can achieve even more accurate environment settings for subsequent uses.

[0898] This system allows users to easily obtain the optimal environment that meets their individual needs, improving their quality of life.

[0899] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0900] Step 1: Collect user behavior data

[0901] The server collects data on the user's behavior in various applications. Specifically, it collects app usage history on smartphones and PCs, music playback history, video viewing history, text message exchanges, etc. It receives data from various APIs (e.g., Google Analytics API, Spotify API) as input and stores that data in an internal database as output.

[0902] Specific behavior:

[0903] The server calls the Google Analytics API to obtain app usage history.

[0904] The server uses the Spotify API to collect the user's music playback history.

[0905] Save the retrieved data in the database.

[0906] Step 2: Create and update user profiles

[0907] The server runs the collected behavioral data through a machine learning algorithm (e.g., Scikit-learn's K-means clustering). Using the data collected in the previous step as input, it analyzes the user's preferences and behavioral patterns, and generates and updates a user profile as output.

[0908] Specific behavior:

[0909] The server preprocesses the acquired behavioral data and converts it into numerical data.

[0910] The server inputs the preprocessed data into the K-means clustering algorithm.

[0911] A user profile is generated based on the analysis results and stored in a database.

[0912] Step 3: Receiving the user request

[0913] The device provides an interface (such as a smartphone app or a voice assistant) to receive requests from the user. It receives the user's request (e.g., "I want to relax") as input and sends the request to the server as output.

[0914] Specific behavior:

[0915] The user types "I want to relax" into a text field on the smartphone app.

[0916] The terminal sends this request to the server as an HTTP request.

[0917] Step 4: Directing content generation

[0918] The server sends appropriate prompts to the generation AI based on the user's request and the generated profile, instructing it to generate content. Using the user's request and profile data as input, the server creates prompts to send to the generation AI as output. The generation AI receives instructions in advance via an API or other means.

[0919] Specific behavior:

[0920] The server extracts features of the content for relaxation from the user profile.

[0921] The server calls the API of the generative AI model and sends a prompt to generate relaxing music.

[0922] Step 5: Deliver your content

[0923] After the content generated by the generative AI model is returned to the server, it is distributed to the appropriate IoT devices (smart speakers, smart displays, e-readers, etc.) It receives the generated content as input and sends data to each IoT device as output.

[0924] Specific behavior:

[0925] The server receives the music file returned by the generation AI.

[0926] The server sends the music file to the smart speaker as an HTTP request.

[0927] Step 6: Adjusting the environment

[0928] Each IoT device automatically adjusts its settings based on the content it receives from the server. It receives content as input and adjusts its behavior as output. For example, a smart speaker plays music, and a smart display displays video.

[0929] Specific behavior:

[0930] The smart speaker plays the music files received from the server.

[0931] The smart display plays the video file received from the server.

[0932] The smart light changes the color of the light to a warmer color based on instructions from the server.

[0933] This processing step allows for providing an optimal environment based on the user's behavioral data and real-time requirements.

[0934] (Application example 1)

[0935] 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."

[0936] Conventional autonomous vehicles have had difficulty providing an environment that appropriately reflects passengers' specific needs, such as relaxation and concentration, while on board. Furthermore, the generation of profiles based on passenger behavior data and the use of such profiles to generate content and automatically adjust the environment were insufficient, resulting in a lack of a means to provide an optimal environment for each individual user.

[0937] 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.

[0938] In this invention, the server includes a means for collecting user behavioral data, a means for analyzing the collected behavioral data to generate and update a user profile, and a means for receiving user requests. This allows the server to instruct a generation AI to generate content based on the received request and user profile, receive the generated content, and distribute it to the in-vehicle system. Furthermore, the in-vehicle system can control at least one of lighting, music playback, and video display based on the received content, providing an environment tailored to the user's requests in real time. This system allows the server to provide an optimal riding environment for each user, ensuring a comfortable driving experience.

[0939] "User behavioral data" refers to data such as operation history, browsing history, and playback history when a user uses an application or device, which makes it possible to analyze the preferences and behavioral patterns of individual users.

[0940] A "user profile" is a collection of information generated based on collected user behavior data, and specifically indicates the user's preferences, behavioral patterns, and characteristics according to their requirements.

[0941] "Generative AI" refers to artificial intelligence technology that generates content such as music, video, and text based on user profiles and requests. For example, it can automatically generate music and videos for relaxation.

[0942] "In-vehicle system" includes information processing devices and entertainment systems installed in autonomous vehicles, and has the function of playing and displaying content in response to user requests and adjusting the in-vehicle environment.

[0943] "Means for adjusting the environment" refers to the ability of the in-vehicle system to control environmental elements such as lighting, music playback, and video display in real time based on the generated content, such as playing relaxation music or adjusting the color and brightness of lighting.

[0944] This invention is a system for collecting and analyzing user behavior data in an autonomous vehicle, and providing an environment that is optimal for individual needs based on that data. This system is composed of the following elements: a server, a user terminal, and an in-vehicle system.

[0945] System Configuration

[0946] server

[0947] The server collects user behavioral data (e.g., application usage history, music playback history, video viewing history), analyzes the data, and generates and updates user profiles. A RESTful API is used to collect the behavioral data, and PostgreSQL is used as the database. A machine learning algorithm is used for the analysis to identify user behavioral patterns and preferences.

[0948] The server also provides an interface for receiving requests from users (e.g., "I want to relax" or "I want to concentrate"). Based on these requests, it issues instructions to a generative AI model (e.g., OpenAI's GPT-4) to generate appropriate content. The instructions are generated as prompt sentences and sent to the generative AI.

[0949] The content (e.g., music, video, text) returned by the generative AI is sent back to the server, converted into an appropriate format, and delivered to the in-car system.

[0950] User terminal

[0951] The user terminal (e.g., a smartphone) provides an application for inputting user requests. Through this application, the user inputs requests such as "I want to relax" or "I want to concentrate," and the input data is sent to the server.

[0952] In-vehicle systems

[0953] The in-vehicle system adjusts the environment based on the generated content received from the server. Specifically, it plays music through the in-vehicle speakers, displays images on the in-vehicle display, adjusts the color and brightness of the smart lights, etc. The in-vehicle system automates these operations using information processing devices such as Android Auto.

[0954] Processing flow

[0955] 1. User behavior data collection: The server collects user usage and playback history.

[0956] 2. User profile generation and update: The collected data is analyzed using machine learning algorithms to generate and update user profiles.

[0957] 3. Receiving a user request: The user enters a request into the smartphone app and the server receives it.

[0958] 4. Content generation by generative AI: The server sends a prompt to the generative AI to generate appropriate content. For example, "Generate relaxing music. The user's profile is as follows: [specific data]."

[0959] 5. Content distribution: The server distributes the generated content to the in-vehicle system.

[0960] 6. Environmental adjustment: Based on the content received by the in-vehicle system, it plays music, displays images, adjusts lighting, etc.

[0961] Specific examples

[0962] If a user requests "I want to relax," the server instructs the generation AI to generate "relaxing music" based on the user profile. The music file returned by the generation AI is converted into the appropriate format on the server and distributed to the car's speakers. Relaxation videos are displayed on the car display, and the smart lights are adjusted to a soft, warm light. This series of actions allows the user to enjoy a relaxing environment in the car.

[0963] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0964] Step 1:

[0965] The server collects user behavior data.

[0966] Input: User's application usage history, music playback history, video viewing history

[0967] Data processing: Save to database via API

[0968] Output: A database of accumulated behavioral data

[0969] Step 2:

[0970] The server analyzes the collected data and generates and updates the user profile.

[0971] Input: Behavioral data stored in a database

[0972] Data Computing: Using machine learning algorithms to identify user behavior patterns and preferences

[0973] Output: Updated user profile

[0974] Step 3:

[0975] The user inputs a request through a terminal.

[0976] Input: User request (e.g., "I want to relax" or "I want to concentrate")

[0977] Data processing: Sending user requests to the server

[0978] Output: Request data is sent to the server

[0979] Step 4:

[0980] The server instructs the generation AI to generate content based on the received request and user profile.

[0981] Input: User request, updated user profile

[0982] Data calculation: Generate prompts for the generation AI and instruct it to specify the request. Example: "Generate relaxing music. The user's profile is as follows: [specific data]."

[0983] Output: Prompt sent to the generation AI

[0984] Step 5:

[0985] The generation AI generates the content and sends it to the server.

[0986] Input: Prompt sent to the generation AI

[0987] Data processing: Generative AI generates content based on prompts (e.g., music files, video files, text)

[0988] Output: The generated content is sent to the server

[0989] Step 6:

[0990] The server receives the generated content and distributes it to the in-vehicle system.

[0991] Input: Content received from the generation AI

[0992] Data processing: Converting content into the appropriate format and delivering it to the in-vehicle system

[0993] Output: Content delivered to the in-car system

[0994] Step 7:

[0995] The in-vehicle system adjusts the environment based on the content it receives.

[0996] Input: Content delivered from the server (music files, video files, text, etc.)

[0997] Data calculation and processing: Set up the environment for music playback, video display, lighting adjustment, etc.

[0998] Output: Optimal in-car environment according to user demands

[0999] 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.

[1000] This invention relates to a system that analyzes user behavioral and emotional data and provides an optimal environment in response to user requests. In particular, this invention incorporates an emotion engine that recognizes user emotions in real time and utilizes that data to adjust the environment. This system provides an optimal environment by collecting and analyzing user behavioral and emotional data, creating and updating profiles on a server, receiving user requests from a terminal, generating content using a generative AI, and linking with IoT devices.

[1001] Program processing

[1002] Creating a User Profile

[1003] The server collects user behavioral and emotional data. Behavioral data includes application usage history, music playback history, video viewing history, and language usage patterns, while emotional data includes facial expressions and voice tone captured through cameras and microphones. The server analyzes this data using machine learning algorithms to identify user preferences and behavioral patterns. At the same time, the emotion engine also analyzes user emotions in real time and sends the results to the server.

[1004] Update your user profile

[1005] The server generates or updates a user profile based on the analysis results and data from the emotion engine, including the user's preferred music genres, video types, and preferences for content that corresponds to specific emotional states.

[1006] Receiving user requests

[1007] The device receives requests from the user through the interface. For example, the user may say, "Create a relaxing environment" through a smartphone app or voice assistant. If the emotion engine already recognizes an emotion, such as "stress," that information is also sent to the server along with the request.

[1008] Submitting a request

[1009] The device structures the user's request and emotion data and sends them to the server, which receives them and starts the next process.

[1010] Content generation instructions

[1011] The server compares the user's request, updated profile, and emotion engine data and issues appropriate instructions to each AI generator. For example, to create a "relaxing environment," the server instructs the music generator AI to "generate calming music" and the video generator AI to "generate landscape images."

[1012] Content generation execution

[1013] The generative AIs (music generation AI, video generation AI, and language generation AI) generate content based on their respective instructions. The music generation AI generates relaxing music, the video generation AI generates landscape images, and the language generation AI generates relaxing essays.

[1014] Receiving content

[1015] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[1016] Content Delivery

[1017] The server then sends the generated content to the appropriate IoT device: music files to a smart speaker, video files to a smart display, text data to an e-reader, and so on.

[1018] Adjusting the environment

[1019] The terminals (each IoT device) automatically adjust their environment based on the content they receive: for example, a smart speaker plays relaxing music, a smart display shows a landscape image, and smart lights adjust the color and brightness of the lights to a relaxing mode.

[1020] Collecting feedback

[1021] The device collects user feedback, including voice input, tap gestures, and even data from environmental sensors, along with an emotion engine, to analyze the user's current emotional state, which is then sent to the server for further updates to the user profile.

[1022] Specific Examples

[1023] Example 1: Relaxed environment

[1024] The user inputs "I want to relax" through the app, and at the same time, the emotion engine recognizes that the user is feeling stressed.

[1025] The terminal transmits the request and the emotion data to the server.

[1026] Based on the user's profile and emotional data, the server instructs the generative AI to generate "relaxing music," "landscape footage," and "relaxing essays."

[1027] The generative AI generates appropriate music, video, and text and sends them to the server.

[1028] The server distributes this data to smart speakers, smart displays, and e-readers.

[1029] The device plays music, displays videos, and displays essays, while an emotion engine continuously monitors the effects of the environment.

[1030] Example 2: In an environment where you can concentrate

[1031] The user inputs "I want to concentrate" through the app, and at the same time the emotion engine recognizes that the user is slightly tired.

[1032] The terminal transmits the request and the emotion data to the server.

[1033] Based on the user's profile and emotional data, the server instructs the generative AI to generate "music that improves concentration," "images with moderate movement," and "text that improves concentration."

[1034] The generation AI generates appropriate content and sends it to the server.

[1035] The server distributes this data to smart speakers, smart displays, and e-readers.

[1036] The device plays music, displays video, and displays text, while an emotion engine continuously monitors the user's emotional state and fine-tunes the environment as needed.

[1037] The system utilizes user behavioral data and real-time emotional data to provide an environment that is optimally tailored to the user's needs. Through feedback, the system continuously updates the user profile, achieving more accurate environment settings with each repeated use.

[1038] The processing flow will be explained below.

[1039] Step 1: Collect behavioral and emotional data

[1040] The server periodically collects user behavioral data such as application usage history, music playback history, video viewing history, and language usage patterns. The emotion engine also analyzes the user's facial expressions and voice tone in real time through cameras and microphones to obtain emotion data.

[1041] Step 2: Analyze behavioral and emotional data

[1042] The server analyzes the collected behavioral data using machine learning algorithms. For example, it identifies preferences based on the genres of music the user has listened to or the types of videos they have watched. The emotion engine analyzes the acquired emotion data and identifies the user's current emotional state (e.g., stress, relaxation, lack of concentration, etc.).

[1043] Step 3: Update your user profile

[1044] The server generates or updates a user profile based on the analysis of the behavioral and emotional data, including the user's preferred music genres, video types, and content preferences that correspond to specific emotional states.

[1045] Step 4: Receive user requests

[1046] The device receives a request from the user through the interface. For example, the user may input "Create a relaxing environment" through a smartphone app or voice assistant. The current emotional state recognized by the emotion engine is also sent to the server along with the request.

[1047] Step 5: Sending request and emotion data

[1048] The device structures the user's request and emotion data and sends it to the server in a standard format such as JSON.

[1049] Step 6: Content Generation Instructions

[1050] The server compares the user's request, updated profile, and emotion engine data, and issues appropriate instructions to each generation AI. For example, to create a "relaxing environment," the server instructs the music generation AI to "generate calming music" and the video generation AI to "generate relaxing videos."

[1051] Step 7: Run content generation

[1052] The generative AIs (music generation AI, video generation AI, and language generation AI) generate content based on their respective instructions. The music generation AI generates relaxing music, the video generation AI generates natural landscape footage, and the language generation AI generates relaxing essays.

[1053] Step 8: Receive your content

[1054] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[1055] Step 9: Deliver your content

[1056] The server then sends the generated content to IoT devices, for example, music files to smart speakers, video files to smart displays, and text data to e-readers.

[1057] Step 10: Adjusting the environment

[1058] The terminals (each IoT device) automatically adjust their environment based on the content they receive: for example, a smart speaker plays relaxing music, a smart display shows natural scenery, and smart lights adjust the color and brightness of the lights to a relaxing mode.

[1059] Step 11: Gather feedback

[1060] The device collects user feedback, including voice input, tap gestures, and data from environmental sensors. The emotion engine also continuously monitors the user's emotional state and sends it to the server for further updates to the user profile.

[1061] Example 2

[1062] 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."

[1063] In modern daily life, it is difficult to provide an optimal environment for users by utilizing their behavioral and emotional data. Specifically, there is a lack of technology that can respond to diverse user requests in real time and appropriately adjust the environment while monitoring the effects. This poses a challenge, making it difficult to provide a comfortable, relaxing, and focused environment for users.

[1064] 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.

[1065] In this invention, the server includes means for collecting user behavioral data and emotional data, means for analyzing the collected behavioral data and emotional data to generate and update a user profile, means for receiving a user request, means for instructing a generative AI model to generate content based on the received request and the user profile, means for receiving the generated content and delivering it to an IoT device, and means for adjusting an environment based on the content received by the IoT device, thereby making it possible to provide an optimal environment for the user and adjust the environment based on the user's behavioral data and real-time emotional state.

[1066] "User behavior data" is information that indicates user behavior, such as the user's history of using various applications, music and video playback history, and language usage patterns.

[1067] "Emotion data" is information that indicates the user's emotional state, such as the user's facial expression or tone of voice, and is acquired through a camera or microphone.

[1068] A "user profile" is information that indicates content preferences that correspond to a user's preferences, behavioral patterns, and emotional state based on collected behavioral and emotional data.

[1069] A "generative AI model" is an artificial intelligence algorithm or system that generates content such as music, video, or text based on user requests and profiles.

[1070] An "IoT device" is an internet-connected device that adjusts its environment based on the content delivered to it, and examples include smart speakers and smart displays.

[1071] "Means for adjusting the environment" refers to mechanisms that include the ability to play music from a smart speaker, display images on a smart display, and change the lighting settings of smart lights.

[1072] "Feedback" is information used to evaluate system performance and the user's emotional state through user-provided opinions, impressions, and data obtained from environmental sensors.

[1073] The present invention relates to a system that analyzes user behavioral and emotional data to provide an optimal environment in response to user requests. In particular, it incorporates an emotion engine, recognizes user emotions in real time, and uses that data to adjust the environment.

[1074] Specific hardware and software configurations

[1075] The system consists of the following main components:

[1076] Server: Collects data, analyzes it, generates profiles, directs content generation, and distributes it. The server has software libraries (e.g., Scikit-learn, TensorFlow) installed to run machine learning algorithms.

[1077] Device: The part of the system that receives user requests and transmits the request and emotion data to the server. Devices include smartphones, voice assistants, and smart displays.

[1078] Emotion engine: Recognizes the user's facial expressions and tone of voice and analyzes the resulting emotional data. Emotion engines include commonly used facial recognition and voice analysis APIs (e.g., Amazon Rekognition, Google Cloud Vision API, Microsoft Azure Cognitive Services).

[1079] IoT devices: These are devices that automatically adjust their environment based on the content they generate. Examples include smart speakers, smart displays, smart lights, and e-readers.

[1080] Data processing and calculation methods

[1081] The server collects user behavioral and emotional data. This data includes application usage history, music playback history, video viewing history, language usage patterns, and facial expressions and tone of voice captured through cameras and microphones. The server then analyzes this data using machine learning algorithms to identify user preferences and behavioral patterns. For example, it uses clustering algorithms and sentiment analysis models. Meanwhile, the emotion engine analyzes user emotions in real time and sends the results to the server.

[1082] Creating and updating user profiles

[1083] Based on the analysis and data from the emotion engine, the server generates or updates a user profile, including the user's preferred music genres, video types, and content preferences that correspond to particular emotional states.

[1084] Receiving and processing user requests

[1085] The device receives user requests through an interface (smartphone app or voice assistant). For example, the user might say, "Create a relaxing environment." If the emotion engine recognizes the user's emotional state (e.g., "I'm feeling stressed"), that information is also sent to the server. The device then structures this data and sends it to the server.

[1086] Directing and generating content

[1087] The server compares the received user request, updated profile, and emotion engine data, and issues appropriate instructions to each generative AI model. For example, to create a "relaxing environment," it issues specific instructions such as "generate calming music" to the music generation AI model and "generate a landscape video" to the video generation AI model. Examples of prompt sentences are "create a relaxing environment" and "generate calming music."

[1088] Content Generation and Delivery

[1089] Each generative AI model (music generation AI, video generation AI, language generation AI) generates content based on a specified prompt. The music generation AI generates quiet, slow-tempo music, the video generation AI generates videos of tranquil landscapes, and the language generation AI generates relaxing essays. The generated content is sent to a server and distributed to appropriate IoT devices (smart speakers, smart displays, e-book readers, etc.).

[1090] Tuning the environment and gathering feedback

[1091] IoT devices automatically adjust the environment based on the received content. For example, a smart speaker can play relaxing music, a smart display can display landscape images, and smart lights can set the lights in a relaxing mode. Furthermore, the emotion engine can analyze the user's current emotional state by collecting user feedback (voice input, tap gestures, environmental sensor data, etc.). This feedback is sent to the server and used to update the user profile.

[1092] The system utilizes user behavioral data and real-time emotional data to provide an optimal environment tailored to the user's needs, and continuously updates the user profile through feedback, ensuring accurate environment settings with each use.

[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1094] Step 1: Data collection

[1095] The server collects user behavioral and emotional data.

[1096] Specifically, it collects application usage history, music playback history, video viewing history, and language usage patterns from smartphone and PC applications (e.g., music player apps, video streaming apps).

[1097] In addition, facial expression and voice data is acquired through the device's camera and microphone, and this is analyzed by the emotion engine.

[1098] The input is "various user usage data" and the output is "collected behavioral data and emotional data."

[1099] Step 2: Analyze the data and generate a profile

[1100] The server analyzes the collected behavioral and emotional data using machine learning algorithms (e.g., Scikit-learn, TensorFlow).

[1101] Machine learning algorithms are used to run clustering algorithms and sentiment analysis models to identify user preferences and behavioral patterns.

[1102] The input is "collected data" and the output is "a profile showing the user's preferences and behavioral patterns."

[1103] Specifically, the data is preprocessed (scaling, interpolation, etc.), input into the model, and calculations are performed.

[1104] Step 3: Receiving the user request

[1105] The terminal receives user requests through an interface (e.g., smartphone app, voice assistant).

[1106] Specifically, when a user verbally commands "create a relaxing environment," the voice input system converts this into text and registers the request.

[1107] The input is "user request" and the output is "structured request data."

[1108] Step 4: Sending the request to the server

[1109] The terminal structures the user's request and real-time emotion data and transmits them to the server.

[1110] As a specific operation, the robot requests a prompt such as "Create a relaxing environment" and sends emotional data such as "I feel stressed" to the server.

[1111] The input is "structured request data and emotion data" and the output is "data sent to the server."

[1112] Step 5: Directing content generation

[1113] The server compares the received request, updated profile, and emotion engine data and issues appropriate instructions to each generative AI model.

[1114] As a specific operation, specific commands are sent as prompts to the music generation AI model, such as "Generate calming music," and to the video generation AI model, such as "Generate a landscape video."

[1115] The input is "request data, profile, and emotional data," and the output is "instructions to the generative AI model."

[1116] Step 6: Generate content

[1117] The generative AI model generates content based on instructions from the server.

[1118] Specifically, the music generation AI generates relaxing music with little noise, the video generation AI generates images of tranquil landscapes, and the language generation AI generates relaxing essays.

[1119] The input is "instructions from the server" and the output is "generated music files, video files, and text data."

[1120] Step 7: Receiving generated content

[1121] The server receives the content generated by the generative AI model and stores and manages it appropriately.

[1122] Specifically, it saves music files in the appropriate format (e.g., MP3, WAV) and converts video files for streaming.

[1123] The input is the "generated content" and the output is the "stored content."

[1124] Step 8: Deliver your content

[1125] The server distributes the generated content to the appropriate IoT devices.

[1126] Specifically, it sends music files to a smart speaker, streams video files to a smart display, and sends text data to an e-book reader.

[1127] The input is "stored content" and the output is "delivered content."

[1128] Step 9: Adjust your environment

[1129] Each IoT device automatically adjusts its environment based on the content it receives.

[1130] Specifically, the smart speaker will play relaxing music, the smart display will show a landscape image, and the smart light will adjust the color and brightness of the lighting.

[1131] The input is the "distributed content" and the output is the "conditioned environment."

[1132] Step 10: Gather feedback

[1133] The terminal collects the user's feedback and sends it to the server.

[1134] Specifically, it collects voice input, tap gestures, and environmental sensor data, analyzes it with an emotion engine, and sends the current emotional state to the server.

[1135] The input is "user feedback and emotion data" and the output is "updated user profile and system feedback."

[1136] In this way, the system utilizes user behavioral data and real-time emotional data to provide an optimal environment that meets the user's needs.

[1137] (Application example 2)

[1138] 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."

[1139] In modern society, there is a demand for effective utilization of user behavioral and emotional data to provide optimal content and environments in real time. However, conventional systems have had difficulty recognizing user emotions in real time and generating and delivering optimal content that meets specific requests. They also face challenges in appropriately collecting and incorporating user feedback and maintaining highly accurate user profiles. As a result, they have not been able to provide an environment that adequately enhances user satisfaction.

[1140] The identification processing 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 collecting user behavioral data and emotional data, means for analyzing the collected behavioral data and emotional data to generate and update a user profile, means for receiving a user request, means for generating a prompt sentence for a generative AI model based on the received request and user profile, means for instructing the generative AI model to generate content using the generated prompt sentence, means for receiving the generated content and delivering it to an environment adjustment device, and means for adjusting the environment based on the content received by the environment adjustment device. This makes it possible to comprehensively analyze the user's behavioral data and emotional data and provide optimal content and an environment that meets the user's requests in real time.

[1141] "User behavior data" refers to data related to a series of operations and activities performed by a user, such as application usage history, music playback history, and video viewing history.

[1142] "Emotion data" is data that indicates the user's emotional state, such as facial expressions and tone of voice captured through a camera or microphone.

[1143] A "user profile" is a data set that compiles information about a user's preferences, behavioral patterns, and emotions.

[1144] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate content such as music, video, and text in response to user requests.

[1145] A "prompt sentence" is a text sentence generated to give specific instructions to a generative AI model.

[1146] An "environmental adjustment device" is a device that adjusts the environment based on specified content, such as a smart speaker, smart display, or lighting device.

[1147] "Feedback" refers to opinions and reactions provided by users, or emotional state data collected automatically by the system.

[1148] A "server" is an information processing device that collects and analyzes user behavioral and emotional data, and generates and updates user profiles.

[1149] This invention is a system that collects and analyzes user behavioral and emotional data in real time and provides an optimal environment according to the user's requests. This system is realized by linking a server that generates and updates user profiles, a terminal that receives requests, content generation by generative AI, and an environment adjustment device.

[1150] First, the server collects user behavioral and emotional data. Behavioral data includes application usage history and music and video playback history, while emotional data includes facial expressions and voice tone captured through cameras and microphones. The collected data is analyzed using machine learning algorithms such as Google TensorFlow. This analysis identifies user preferences and behavioral patterns, and a user profile is created and updated.

[1151] Next, the device receives the user's request through the interface. For example, a user might input "I want to relax" into a smartphone app. At the same time, an emotion recognition engine (Microsoft Azure Cognitive Services) recognizes the user's emotional state in real time, and this data is also sent to the server.

[1152] When the server receives this request, it generates a specific prompt for the generative AI model based on the user profile and emotional data. This prompt is used to instruct the generative AI model to generate content. For example, an instruction such as "Generate relaxing music" is sent to the generative AI model.

[1153] Generative AI models (e.g., Jukedeck, Runway, OpenAI GPT) receive instructions and generate their respective content. A music generation AI model generates relaxing music, a video generation AI model generates relaxing landscape footage, and a language generation AI model generates soothing essays. The generated content is sent back to the server, which distributes it to the environment adjustment device.

[1154] The environmental adjustment devices include smart speakers, smart displays, and lighting fixtures. These devices adjust the environment based on the content they receive: a smart speaker plays relaxing music, a smart display shows a video of a relaxing scene, and lighting fixtures are adjusted to a relaxing mode.

[1155] Finally, user feedback is collected through voice input and tap gestures, and an emotion recognition engine also continuously monitors the user's emotional state. The collected feedback and emotion data are sent back to the server for further updating of the user profile.

[1156] For example, if a user inputs "I want to concentrate" and the emotion engine detects that the user is slightly tired, the server will send prompts to the generative AI model such as "Please generate music that will help me concentrate" or "Please generate a video with moderate movement." The generated music and video will then be distributed to smart speakers and smart displays, providing the user with an environment in which they can concentrate.

[1157] An example of a prompt is as follows:

[1158] "Generate relaxing music."

[1159] "The current video generation task is to create a video of a relaxing scene. Please create an appropriate video."

[1160] "Generate soothing essays. Users want to relax through reading."

[1161] This system makes it possible to comprehensively utilize user behavioral and emotional data to provide optimal content and environments in real time that meet the user's needs.

[1162] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1163] Step 1:

[1164] A user inputs a request using a smartphone app. At the same time, the user's emotional data is collected. The emotional data consists of facial expressions and voice tone captured through the smartphone's camera and microphone. This input data is sent from the device to the server.

[1165] Input: User request (e.g., "I want to relax"), emotional data (facial expression, tone of voice)

[1166] Output: A request containing the user's request and emotion data

[1167] Step 2:

[1168] The server analyzes the user's request and emotional data received from the device. The collected emotional data is analyzed using an emotion recognition engine (Microsoft Azure Cognitive Services). The analysis results are integrated with the existing user profile to understand the request.

[1169] Input: User requests, emotion data

[1170] Output: Parsed emotion information, updated request data

[1171] Step 3:

[1172] The server generates specific prompts for the generative AI model based on the analyzed emotional information and the user profile. These prompts are necessary to instruct the generative AI model to generate appropriate content.

[1173] Input: Analyzed emotion information, user profile

[1174] Output: The generated prompt (e.g., "Generate some relaxing music.")

[1175] Step 4:

[1176] The server uses the generated prompts to send instructions for generating content to each generative AI model, which then generates music, video, text, etc.

[1177] Input: Generated prompt text

[1178] Output: Content generated by the generative AI model (music files, video files, text data)

[1179] Step 5:

[1180] The server receives the content obtained from the generative AI model and distributes it to the environment conditioning device.

[1181] Input: Generated content

[1182] Output: Content delivery request to each environmental adjustment device

[1183] Step 6:

[1184] The environmental adjustment devices (smart speakers, smart displays, lighting devices) adjust the environment based on the received content: the smart speaker plays relaxing music, the smart display shows a video of a relaxing scene, and the lighting devices are set to relaxation mode.

[1185] Input: Received content

[1186] Output: Controlled environment (music playback, video display, lighting settings)

[1187] Step 7:

[1188] Users provide feedback on the environment and content provided. Feedback is collected through voice input and tap gestures, and an emotion recognition engine analyzes their current emotional state. This feedback data is then sent back to the server and used to update the user profile.

[1189] Input: User feedback, real-time sentiment data

[1190] Output: Feedback data sent to server, updated user profile

[1191] This series of steps makes it possible to comprehensively utilize user behavioral and emotional data to provide optimal content and environments in real time that meet the user's needs.

[1192] 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.

[1193] 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.

[1194] 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.

[1195] [Fourth embodiment]

[1196] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1197] 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.

[1198] 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).

[1199] 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.

[1200] 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.

[1201] 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).

[1202] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1203] 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.

[1204] 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.

[1205] 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.

[1206] 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.

[1207] 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.

[1208] 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."

[1209] This invention relates to a system that analyzes user behavior data and provides an optimal environment according to individual requests. This system provides an optimal real-time environment for users by adjusting the environment through collaboration with a server that collects user behavior data and generates and updates profiles, a terminal that receives user requests, content generation using generative AI, and IoT devices.

[1210] Program processing

[1211] Creating a User Profile

[1212] The server collects user behavioral data, including application usage history, music playback history, video viewing history, language usage patterns, etc. The server then applies this data to machine learning algorithms to identify user preferences and behavioral patterns and generate and update user profiles.

[1213] Receiving user requests

[1214] The device provides an interface for receiving requests from the user, for example, a request such as "create a relaxing environment" input through a smartphone app or voice assistant, and sends the request to the server.

[1215] Content Generation Instructions

[1216] The server issues appropriate instructions to the generation AI based on the received user request and the generated profile. For example, it may ask the music generation AI to generate "music to create a relaxing environment." Similarly, it sends instructions to the video generation AI and language generation AI to generate "relaxing images" and "relaxing text."

[1217] Content Delivery

[1218] The server that receives the content generated by the generative AI distributes it to the appropriate IoT device: for example, music files to a smart speaker, video files to a smart display, and text data to an e-book reader.

[1219] Adjusting the environment

[1220] The terminals (each IoT device) adjust their settings based on the content received from the server. Smart speakers play music, smart displays show images, and smart lights adjust the color and brightness of lighting. This allows users to experience a relaxing environment.

[1221] Specific Examples

[1222] Example 1: Relaxed environment

[1223] The user enters "I want to relax" through the app.

[1224] The terminal sends the request to the server.

[1225] Based on the user's profile and requests, the server instructs the generative AI to generate "relaxing music," "landscape footage," and "relaxing essays."

[1226] The generative AI generates appropriate music, video, and text and sends them to the server.

[1227] The server distributes this data to smart speakers, smart displays, and e-readers.

[1228] The terminal plays music, displays videos, and displays essays.

[1229] Example 2: In an environment where you can concentrate

[1230] Users input "I want to concentrate" through the app.

[1231] The terminal sends the request to the server.

[1232] Based on the user's profile and requests, the server instructs the generative AI to generate "music that improves concentration," "images with moderate movement," and "text that improves concentration."

[1233] The generation AI generates appropriate content and sends it to the server.

[1234] The server distributes this data to smart speakers, smart displays, and e-readers.

[1235] The terminal plays music, displays video, and displays text.

[1236] This system provides an optimal environment based on user behavior data and real-time requests. It also continuously updates the user profile through feedback, enabling even more accurate environment settings for subsequent uses.

[1237] The processing flow will be explained below.

[1238] Step 1: Collect user behavior data

[1239] The server periodically collects users' application usage history, music playback history, video viewing history, language usage patterns, etc. This includes data sent from IoT devices such as smartphones, smart speakers, and smart displays.

[1240] Step 2: Analyze behavioral data

[1241] The server then applies machine learning algorithms to analyze the collected behavioral data, for example, identifying preferred genres from a user's music playback history and determining the types of videos they like from their video viewing history.

[1242] Step 3: Update your user profile

[1243] The server generates or updates a user profile based on the analysis results, reflecting the user's preferences and behavioral patterns. The updated profile includes the user's preferred music genres, video types, language styles, etc.

[1244] Step 4: Receive user requests

[1245] The device receives requests from the user through an interface, for example, a request to "create a relaxing environment" via a smartphone app or voice assistant.

[1246] Step 5: Submitting the request

[1247] The device sends the user's request as structured data (e.g., JSON format) to the server. The server receives it and starts the next process.

[1248] Step 6: Content Generation Instructions

[1249] The server compares the user's request with the updated profile and issues appropriate instructions to each AI generator. For example, to create a "relaxing environment," the server might instruct the music generator AI to "generate calming music" and the video generator AI to "generate landscape images."

[1250] Step 7: Run content generation

[1251] Generative AI (music generation AI, video generation AI, language generation AI) generates content based on their respective instructions. For example, music generation AI generates relaxing music, video generation AI generates landscape images, and language generation AI generates relaxing essays.

[1252] Step 8: Receive your content

[1253] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[1254] Step 9: Deliver your content

[1255] The server then sends the generated content to the appropriate IoT device: music files to a smart speaker, video files to a smart display, text data to an e-reader, and so on.

[1256] Step 10: Adjusting the environment

[1257] The terminals (each IoT device) use the received content to automatically adjust the environment: for example, a smart speaker plays relaxing music, a smart display shows a landscape image, and smart lights adjust the color and brightness of the lighting to a relaxing mode.

[1258] Step 11: Gather feedback

[1259] The device collects user feedback, including voice input, tap gestures, and even data from environmental sensors, which is sent to a server and used to further update the user profile.

[1260] Example 1

[1261] 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."

[1262] Many modern systems only collect user behavior data, but are unable to provide an appropriate environment based on that data. Furthermore, they are limited in their ability to respond to user requests in real time, automatically generate content, and integrate with IoT devices, making it difficult to provide an optimal experience for users.

[1263] 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.

[1264] In this invention, the server includes means for collecting user behavioral data, means for analyzing the collected behavioral data using a machine learning algorithm to generate and update a user profile, interface means for receiving user requests, means for instructing content generation by sending appropriate prompts to a generation AI based on the received request and the user profile, means for receiving the generated content and distributing it to an IoT device via a network, and means for the IoT device to adjust its settings based on the received content to optimize the environment, thereby making it possible to provide an optimal environment based on the user's behavioral data and real-time requests.

[1265] "User behavioral data" refers to general information about user behavior and choices, such as application usage history, music playback history, video viewing history, and text message exchanges.

[1266] "Machine learning algorithm" is a general term for algorithms that automatically learn patterns based on large amounts of data and make predictions and classifications, and is used in this system to generate and update user profiles.

[1267] A "user profile" is a collection of data that represents characteristics such as a user's preferences and behavioral patterns, generated from collected user behavioral data and analysis results based on that data.

[1268] "Interface means" refers to a window or device through which a user inputs requests or information, such as a smartphone app or voice assistant.

[1269] "Generative AI" refers to artificial intelligence that automatically generates content such as text, music, and images based on user requests.

[1270] A "prompt" refers to an input sentence, such as an instruction or question, given to the generation AI, which determines the content to be generated.

[1271] "Means for distribution over a network" refers to a method or apparatus for transmitting generated content to IoT devices using the Internet or other communications networks.

[1272] An "IoT device" refers to a device that is connected to the Internet and can send and receive data and perform specific functions, such as a smart speaker, smart display, or smart light.

[1273] "Means for optimizing the environment" refers to IoT devices automatically adjusting their settings based on the content they receive, providing the optimal environment for the user.

[1274] The present invention relates to a system for collecting user behavior data, generating and updating profiles, and providing an optimal environment according to user requests. This system includes the following elements:

[1275] 1. Collecting user behavior data

[1276] The server collects behavioral data from various applications that users use on a daily basis, including application usage history, music playback history, video viewing history, language usage patterns, etc. To do this, it uses the Google Analytics API and general data collection tools.

[1277] 2. Creating and updating user profiles

[1278] The server analyzes the collected behavioral data using machine learning algorithms based on Python's Scikit-learn library. This analysis identifies user preferences and behavioral patterns, and generates and updates user profiles. For example, K-means clustering can be used to classify user interests and create profiles based on those.

[1279] 3. Receiving user requests

[1280] The device provides an interface to receive requests from the user, which can be done through a smartphone app or a voice assistant (e.g., Amazon Alexa or Google Assistant). When the user types a request, such as "create a relaxing environment," the device sends the request to the server.

[1281] 4. Content Generation Instructions

[1282] The server sends appropriate prompts to the AI ​​based on the user's request and the generated profile to instruct it to generate content. For example, for text generation, OpenAI's GPT-4 is used, sending a prompt such as "Generate relaxing music."

[1283] Example prompt: "Create soothing music that's perfect for someone who wants to relax."

[1284] 5. Content Delivery

[1285] The content generated by the generative AI model is returned to the server, which then distributes it to the appropriate IoT device: for example, music files to a smart speaker (commonly known as a smart speaker), video files to a smart display (commonly known as a smart display), and text data to an e-reader (commonly known as an e-reader).

[1286] 6. Adjusting the environment

[1287] Each IoT device (e.g., smart speaker, smart display, smart light, etc.) automatically adjusts its settings based on the content received from the server, allowing users to experience a relaxing or focused environment.

[1288] Example: When a user enters "I want to relax" into an app, the server sends instructions to the AI ​​generator based on the user profile. The AI ​​generator generates music and video, which are then distributed to a smart speaker and a smart display, respectively, and the smart light is set to warm colors.

[1289] In this way, the system can provide an optimal environment based on the user's behavioral data and real-time requirements. Furthermore, by continuously updating the user profile through feedback, the system can achieve even more accurate environment settings for subsequent uses.

[1290] This system allows users to easily obtain the optimal environment that meets their individual needs, improving their quality of life.

[1291] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1292] Step 1: Collect user behavior data

[1293] The server collects data on the user's behavior in various applications. Specifically, it collects app usage history on smartphones and PCs, music playback history, video viewing history, text message exchanges, etc. It receives data from various APIs (e.g., Google Analytics API, Spotify API) as input and stores that data in an internal database as output.

[1294] Specific behavior:

[1295] The server calls the Google Analytics API to obtain app usage history.

[1296] The server uses the Spotify API to collect the user's music playback history.

[1297] Save the retrieved data in the database.

[1298] Step 2: Create and update user profiles

[1299] The server runs the collected behavioral data through a machine learning algorithm (e.g., Scikit-learn's K-means clustering). Using the data collected in the previous step as input, it analyzes the user's preferences and behavioral patterns, and generates and updates a user profile as output.

[1300] Specific behavior:

[1301] The server preprocesses the acquired behavioral data and converts it into numerical data.

[1302] The server inputs the preprocessed data into the K-means clustering algorithm.

[1303] A user profile is generated based on the analysis results and stored in a database.

[1304] Step 3: Receiving the user request

[1305] The device provides an interface (such as a smartphone app or a voice assistant) to receive requests from the user. It receives the user's request (e.g., "I want to relax") as input and sends the request to the server as output.

[1306] Specific behavior:

[1307] The user types "I want to relax" into a text field on the smartphone app.

[1308] The terminal sends this request to the server as an HTTP request.

[1309] Step 4: Directing content generation

[1310] The server sends appropriate prompts to the generation AI based on the user's request and the generated profile, instructing it to generate content. Using the user's request and profile data as input, the server creates prompts to send to the generation AI as output. The generation AI receives instructions in advance via an API or other means.

[1311] Specific behavior:

[1312] The server extracts features of the content for relaxation from the user profile.

[1313] The server calls the API of the generative AI model and sends a prompt to generate relaxing music.

[1314] Step 5: Deliver your content

[1315] After the content generated by the generative AI model is returned to the server, it is distributed to the appropriate IoT devices (smart speakers, smart displays, e-readers, etc.) It receives the generated content as input and sends data to each IoT device as output.

[1316] Specific behavior:

[1317] The server receives the music file returned by the generation AI.

[1318] The server sends the music file to the smart speaker as an HTTP request.

[1319] Step 6: Adjusting the environment

[1320] Each IoT device automatically adjusts its settings based on the content it receives from the server. It receives content as input and adjusts its behavior as output. For example, a smart speaker plays music, and a smart display displays video.

[1321] Specific behavior:

[1322] The smart speaker plays the music files received from the server.

[1323] The smart display plays the video file received from the server.

[1324] The smart light changes the color of the light to a warmer color based on instructions from the server.

[1325] This processing step allows for providing an optimal environment based on the user's behavioral data and real-time requirements.

[1326] (Application example 1)

[1327] 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."

[1328] Conventional autonomous vehicles have had difficulty providing an environment that appropriately reflects passengers' specific needs, such as relaxation and concentration, while on board. Furthermore, the generation of profiles based on passenger behavior data and the use of such profiles to generate content and automatically adjust the environment were insufficient, resulting in a lack of a means to provide an optimal environment for each individual user.

[1329] 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.

[1330] In this invention, the server includes a means for collecting user behavioral data, a means for analyzing the collected behavioral data to generate and update a user profile, and a means for receiving user requests. This allows the server to instruct a generation AI to generate content based on the received request and user profile, receive the generated content, and distribute it to the in-vehicle system. Furthermore, the in-vehicle system can control at least one of lighting, music playback, and video display based on the received content, providing an environment tailored to the user's requests in real time. This system allows the server to provide an optimal riding environment for each user, ensuring a comfortable driving experience.

[1331] "User behavioral data" refers to data such as operation history, browsing history, and playback history when a user uses an application or device, which makes it possible to analyze the preferences and behavioral patterns of individual users.

[1332] A "user profile" is a collection of information generated based on collected user behavior data, and specifically indicates the user's preferences, behavioral patterns, and characteristics according to their requirements.

[1333] "Generative AI" refers to artificial intelligence technology that generates content such as music, video, and text based on user profiles and requests. For example, it can automatically generate music and videos for relaxation.

[1334] "In-vehicle system" includes information processing devices and entertainment systems installed in autonomous vehicles, and has the function of playing and displaying content in response to user requests and adjusting the in-vehicle environment.

[1335] "Means for adjusting the environment" refers to the ability of the in-vehicle system to control environmental elements such as lighting, music playback, and video display in real time based on the generated content, such as playing relaxation music or adjusting the color and brightness of lighting.

[1336] This invention is a system for collecting and analyzing user behavior data in an autonomous vehicle, and providing an environment that is optimal for individual needs based on that data. This system is composed of the following elements: a server, a user terminal, and an in-vehicle system.

[1337] System Configuration

[1338] server

[1339] The server collects user behavioral data (e.g., application usage history, music playback history, video viewing history), analyzes the data, and generates and updates user profiles. A RESTful API is used to collect the behavioral data, and PostgreSQL is used as the database. A machine learning algorithm is used for the analysis to identify user behavioral patterns and preferences.

[1340] The server also provides an interface for receiving requests from users (e.g., "I want to relax" or "I want to concentrate"). Based on these requests, it issues instructions to a generative AI model (e.g., OpenAI's GPT-4) to generate appropriate content. The instructions are generated as prompt sentences and sent to the generative AI.

[1341] The content (e.g., music, video, text) returned by the generative AI is sent back to the server, converted into an appropriate format, and delivered to the in-car system.

[1342] User terminal

[1343] The user terminal (e.g., a smartphone) provides an application for inputting user requests. Through this application, the user inputs requests such as "I want to relax" or "I want to concentrate," and the input data is sent to the server.

[1344] In-vehicle systems

[1345] The in-vehicle system adjusts the environment based on the generated content received from the server. Specifically, it plays music through the in-vehicle speakers, displays images on the in-vehicle display, adjusts the color and brightness of the smart lights, etc. The in-vehicle system automates these operations using information processing devices such as Android Auto.

[1346] Processing flow

[1347] 1. User behavior data collection: The server collects user usage and playback history.

[1348] 2. User profile generation and update: The collected data is analyzed using machine learning algorithms to generate and update user profiles.

[1349] 3. Receiving a user request: The user enters a request into the smartphone app and the server receives it.

[1350] 4. Content generation by generative AI: The server sends a prompt to the generative AI to generate appropriate content. For example, "Generate relaxing music. The user's profile is as follows: [specific data]."

[1351] 5. Content distribution: The server distributes the generated content to the in-vehicle system.

[1352] 6. Environmental adjustment: Based on the content received by the in-vehicle system, it plays music, displays images, adjusts lighting, etc.

[1353] Specific examples

[1354] If a user requests "I want to relax," the server instructs the generation AI to generate "relaxing music" based on the user profile. The music file returned by the generation AI is converted into the appropriate format on the server and distributed to the car's speakers. Relaxation videos are displayed on the car display, and the smart lights are adjusted to a soft, warm light. This series of actions allows the user to enjoy a relaxing environment in the car.

[1355] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1356] Step 1:

[1357] The server collects user behavior data.

[1358] Input: User's application usage history, music playback history, video viewing history

[1359] Data processing: Save to database via API

[1360] Output: A database of accumulated behavioral data

[1361] Step 2:

[1362] The server analyzes the collected data and generates and updates the user profile.

[1363] Input: Behavioral data stored in a database

[1364] Data Computing: Using machine learning algorithms to identify user behavior patterns and preferences

[1365] Output: Updated user profile

[1366] Step 3:

[1367] The user inputs a request through a terminal.

[1368] Input: User request (e.g., "I want to relax" or "I want to concentrate")

[1369] Data processing: Sending user requests to the server

[1370] Output: Request data is sent to the server

[1371] Step 4:

[1372] The server instructs the generation AI to generate content based on the received request and user profile.

[1373] Input: User request, updated user profile

[1374] Data calculation: Generate prompts for the generation AI and instruct it to specify the request. Example: "Generate relaxing music. The user's profile is as follows: [specific data]."

[1375] Output: Prompt sent to the generation AI

[1376] Step 5:

[1377] The generation AI generates the content and sends it to the server.

[1378] Input: Prompt sent to the generation AI

[1379] Data processing: Generative AI generates content based on prompts (e.g., music files, video files, text)

[1380] Output: The generated content is sent to the server

[1381] Step 6:

[1382] The server receives the generated content and distributes it to the in-vehicle system.

[1383] Input: Content received from the generation AI

[1384] Data processing: Converting content into the appropriate format and delivering it to the in-vehicle system

[1385] Output: Content delivered to the in-car system

[1386] Step 7:

[1387] The in-vehicle system adjusts the environment based on the content it receives.

[1388] Input: Content delivered from the server (music files, video files, text, etc.)

[1389] Data calculation and processing: Set up the environment for music playback, video display, lighting adjustment, etc.

[1390] Output: Optimal in-car environment according to user demands

[1391] 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.

[1392] This invention relates to a system that analyzes user behavioral and emotional data and provides an optimal environment in response to user requests. In particular, this invention incorporates an emotion engine that recognizes user emotions in real time and utilizes that data to adjust the environment. This system provides an optimal environment by collecting and analyzing user behavioral and emotional data, creating and updating profiles on a server, receiving user requests from a terminal, generating content using a generative AI, and linking with IoT devices.

[1393] Program processing

[1394] Creating a User Profile

[1395] The server collects user behavioral and emotional data. Behavioral data includes application usage history, music playback history, video viewing history, and language usage patterns, while emotional data includes facial expressions and voice tone captured through cameras and microphones. The server analyzes this data using machine learning algorithms to identify user preferences and behavioral patterns. At the same time, the emotion engine also analyzes user emotions in real time and sends the results to the server.

[1396] Update your user profile

[1397] The server generates or updates a user profile based on the analysis results and data from the emotion engine, including the user's preferred music genres, video types, and preferences for content that corresponds to specific emotional states.

[1398] Receiving user requests

[1399] The device receives requests from the user through the interface. For example, the user may say, "Create a relaxing environment" through a smartphone app or voice assistant. If the emotion engine already recognizes an emotion, such as "stress," that information is also sent to the server along with the request.

[1400] Submitting a request

[1401] The device structures the user's request and emotion data and sends them to the server, which receives them and starts the next process.

[1402] Content generation instructions

[1403] The server compares the user's request, updated profile, and emotion engine data and issues appropriate instructions to each AI generator. For example, to create a "relaxing environment," the server instructs the music generator AI to "generate calming music" and the video generator AI to "generate landscape images."

[1404] Content generation execution

[1405] The generative AIs (music generation AI, video generation AI, and language generation AI) generate content based on their respective instructions. The music generation AI generates relaxing music, the video generation AI generates landscape images, and the language generation AI generates relaxing essays.

[1406] Receiving content

[1407] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[1408] Content Delivery

[1409] The server then sends the generated content to the appropriate IoT device: music files to a smart speaker, video files to a smart display, text data to an e-reader, and so on.

[1410] Adjusting the environment

[1411] The terminals (each IoT device) automatically adjust their environment based on the content they receive: for example, a smart speaker plays relaxing music, a smart display shows a landscape image, and smart lights adjust the color and brightness of the lights to a relaxing mode.

[1412] Collecting feedback

[1413] The device collects user feedback, including voice input, tap gestures, and even data from environmental sensors, along with an emotion engine, to analyze the user's current emotional state, which is then sent to the server for further updates to the user profile.

[1414] Specific Examples

[1415] Example 1: Relaxed environment

[1416] The user inputs "I want to relax" through the app, and at the same time, the emotion engine recognizes that the user is feeling stressed.

[1417] The terminal transmits the request and the emotion data to the server.

[1418] Based on the user's profile and emotional data, the server instructs the generative AI to generate "relaxing music," "landscape footage," and "relaxing essays."

[1419] The generative AI generates appropriate music, video, and text and sends them to the server.

[1420] The server distributes this data to smart speakers, smart displays, and e-readers.

[1421] The device plays music, displays videos, and displays essays, while an emotion engine continuously monitors the effects of the environment.

[1422] Example 2: In an environment where you can concentrate

[1423] The user inputs "I want to concentrate" through the app, and at the same time the emotion engine recognizes that the user is slightly tired.

[1424] The terminal transmits the request and the emotion data to the server.

[1425] Based on the user's profile and emotional data, the server instructs the generative AI to generate "music that improves concentration," "images with moderate movement," and "text that improves concentration."

[1426] The generation AI generates appropriate content and sends it to the server.

[1427] The server distributes this data to smart speakers, smart displays, and e-readers.

[1428] The device plays music, displays video, and displays text, while an emotion engine continuously monitors the user's emotional state and fine-tunes the environment as needed.

[1429] The system utilizes user behavioral data and real-time emotional data to provide an environment that is optimally tailored to the user's needs. Through feedback, the system continuously updates the user profile, achieving more accurate environment settings with each repeated use.

[1430] The processing flow will be explained below.

[1431] Step 1: Collect behavioral and emotional data

[1432] The server periodically collects user behavioral data such as application usage history, music playback history, video viewing history, and language usage patterns. The emotion engine also analyzes the user's facial expressions and voice tone in real time through cameras and microphones to obtain emotion data.

[1433] Step 2: Analyze behavioral and emotional data

[1434] The server analyzes the collected behavioral data using machine learning algorithms. For example, it identifies preferences based on the genres of music the user has listened to or the types of videos they have watched. The emotion engine analyzes the acquired emotion data and identifies the user's current emotional state (e.g., stress, relaxation, lack of concentration, etc.).

[1435] Step 3: Update your user profile

[1436] The server generates or updates a user profile based on the analysis of the behavioral and emotional data, including the user's preferred music genres, video types, and content preferences that correspond to specific emotional states.

[1437] Step 4: Receive user requests

[1438] The device receives a request from the user through the interface. For example, the user may input "Create a relaxing environment" through a smartphone app or voice assistant. The current emotional state recognized by the emotion engine is also sent to the server along with the request.

[1439] Step 5: Sending request and emotion data

[1440] The device structures the user's request and emotion data and sends it to the server in a standard format such as JSON.

[1441] Step 6: Content Generation Instructions

[1442] The server compares the user's request, updated profile, and emotion engine data, and issues appropriate instructions to each generation AI. For example, to create a "relaxing environment," the server instructs the music generation AI to "generate calming music" and the video generation AI to "generate relaxing videos."

[1443] Step 7: Run content generation

[1444] The generative AIs (music generation AI, video generation AI, and language generation AI) generate content based on their respective instructions. The music generation AI generates relaxing music, the video generation AI generates natural landscape footage, and the language generation AI generates relaxing essays.

[1445] Step 8: Receive your content

[1446] The server receives the content (music files, video files, text data) generated by the generation AI and stores them in an appropriate format.

[1447] Step 9: Deliver your content

[1448] The server then sends the generated content to IoT devices, for example, music files to smart speakers, video files to smart displays, and text data to e-readers.

[1449] Step 10: Adjusting the environment

[1450] The terminals (each IoT device) automatically adjust their environment based on the content they receive: for example, a smart speaker plays relaxing music, a smart display shows natural scenery, and smart lights adjust the color and brightness of the lights to a relaxing mode.

[1451] Step 11: Gather feedback

[1452] The device collects user feedback, including voice input, tap gestures, and data from environmental sensors. The emotion engine also continuously monitors the user's emotional state and sends it to the server for further updates to the user profile.

[1453] Example 2

[1454] 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."

[1455] In modern daily life, it is difficult to provide an optimal environment for users by utilizing their behavioral and emotional data. Specifically, there is a lack of technology that can respond to diverse user requests in real time and appropriately adjust the environment while monitoring the effects. This poses a challenge, making it difficult to provide a comfortable, relaxing, and focused environment for users.

[1456] 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.

[1457] In this invention, the server includes means for collecting user behavioral data and emotional data, means for analyzing the collected behavioral data and emotional data to generate and update a user profile, means for receiving a user request, means for instructing a generative AI model to generate content based on the received request and the user profile, means for receiving the generated content and delivering it to an IoT device, and means for adjusting an environment based on the content received by the IoT device, thereby making it possible to provide an optimal environment for the user and adjust the environment based on the user's behavioral data and real-time emotional state.

[1458] "User behavior data" is information that indicates user behavior, such as the user's history of using various applications, music and video playback history, and language usage patterns.

[1459] "Emotion data" is information that indicates the user's emotional state, such as the user's facial expression or tone of voice, and is acquired through a camera or microphone.

[1460] A "user profile" is information that indicates content preferences that correspond to a user's preferences, behavioral patterns, and emotional state based on collected behavioral and emotional data.

[1461] A "generative AI model" is an artificial intelligence algorithm or system that generates content such as music, video, or text based on user requests and profiles.

[1462] An "IoT device" is an internet-connected device that adjusts its environment based on the content delivered to it, and examples include smart speakers and smart displays.

[1463] "Means for adjusting the environment" refers to mechanisms that include the ability to play music from a smart speaker, display images on a smart display, and change the lighting settings of smart lights.

[1464] "Feedback" is information used to evaluate system performance and the user's emotional state through user-provided opinions, impressions, and data obtained from environmental sensors.

[1465] The present invention relates to a system that analyzes user behavioral and emotional data to provide an optimal environment in response to user requests. In particular, it incorporates an emotion engine, recognizes user emotions in real time, and uses that data to adjust the environment.

[1466] Specific hardware and software configurations

[1467] The system consists of the following main components:

[1468] Server: Collects data, analyzes it, generates profiles, directs content generation, and distributes it. The server has software libraries (e.g., Scikit-learn, TensorFlow) installed to run machine learning algorithms.

[1469] Device: The part of the system that receives user requests and transmits the request and emotion data to the server. Devices include smartphones, voice assistants, and smart displays.

[1470] Emotion engine: Recognizes the user's facial expressions and tone of voice and analyzes the resulting emotional data. Emotion engines include commonly used facial recognition and voice analysis APIs (e.g., Amazon Rekognition, Google Cloud Vision API, Microsoft Azure Cognitive Services).

[1471] IoT devices: These are devices that automatically adjust their environment based on the content they generate. Examples include smart speakers, smart displays, smart lights, and e-readers.

[1472] Data processing and calculation methods

[1473] The server collects user behavioral and emotional data. This data includes application usage history, music playback history, video viewing history, language usage patterns, and facial expressions and tone of voice captured through cameras and microphones. The server then analyzes this data using machine learning algorithms to identify user preferences and behavioral patterns. For example, it uses clustering algorithms and sentiment analysis models. Meanwhile, the emotion engine analyzes user emotions in real time and sends the results to the server.

[1474] Creating and updating user profiles

[1475] Based on the analysis and data from the emotion engine, the server generates or updates a user profile, including the user's preferred music genres, video types, and content preferences that correspond to particular emotional states.

[1476] Receiving and processing user requests

[1477] The device receives user requests through an interface (smartphone app or voice assistant). For example, the user might say, "Create a relaxing environment." If the emotion engine recognizes the user's emotional state (e.g., "I'm feeling stressed"), that information is also sent to the server. The device then structures this data and sends it to the server.

[1478] Directing and generating content

[1479] The server compares the received user request, updated profile, and emotion engine data, and issues appropriate instructions to each generative AI model. For example, to create a "relaxing environment," it issues specific instructions such as "generate calming music" to the music generation AI model and "generate a landscape video" to the video generation AI model. Examples of prompt sentences are "create a relaxing environment" and "generate calming music."

[1480] Content Generation and Delivery

[1481] Each generative AI model (music generation AI, video generation AI, language generation AI) generates content based on a specified prompt. The music generation AI generates quiet, slow-tempo music, the video generation AI generates videos of tranquil landscapes, and the language generation AI generates relaxing essays. The generated content is sent to a server and distributed to appropriate IoT devices (smart speakers, smart displays, e-book readers, etc.).

[1482] Tuning the environment and gathering feedback

[1483] IoT devices automatically adjust the environment based on the received content. For example, a smart speaker can play relaxing music, a smart display can display landscape images, and smart lights can set the lights in a relaxing mode. Furthermore, the emotion engine can analyze the user's current emotional state by collecting user feedback (voice input, tap gestures, environmental sensor data, etc.). This feedback is sent to the server and used to update the user profile.

[1484] The system utilizes user behavioral data and real-time emotional data to provide an optimal environment tailored to the user's needs, and continuously updates the user profile through feedback, ensuring accurate environment settings with each use.

[1485] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1486] Step 1: Data collection

[1487] The server collects user behavioral and emotional data.

[1488] Specifically, it collects application usage history, music playback history, video viewing history, and language usage patterns from smartphone and PC applications (e.g., music player apps, video streaming apps).

[1489] In addition, facial expression and voice data is acquired through the device's camera and microphone, and this is analyzed by the emotion engine.

[1490] The input is "various user usage data" and the output is "collected behavioral data and emotional data."

[1491] Step 2: Analyze the data and generate a profile

[1492] The server analyzes the collected behavioral and emotional data using machine learning algorithms (e.g., Scikit-learn, TensorFlow).

[1493] Machine learning algorithms are used to run clustering algorithms and sentiment analysis models to identify user preferences and behavioral patterns.

[1494] The input is "collected data" and the output is "a profile showing the user's preferences and behavioral patterns."

[1495] Specifically, the data is preprocessed (scaling, interpolation, etc.), input into the model, and calculations are performed.

[1496] Step 3: Receiving the user request

[1497] The terminal receives user requests through an interface (e.g., smartphone app, voice assistant).

[1498] Specifically, when a user verbally commands "create a relaxing environment," the voice input system converts this into text and registers the request.

[1499] The input is "user request" and the output is "structured request data."

[1500] Step 4: Sending the request to the server

[1501] The terminal structures the user's request and real-time emotion data and transmits them to the server.

[1502] As a specific operation, the robot requests a prompt such as "Create a relaxing environment" and sends emotional data such as "I feel stressed" to the server.

[1503] The input is "structured request data and emotion data" and the output is "data sent to the server."

[1504] Step 5: Directing content generation

[1505] The server compares the received request, updated profile, and emotion engine data and issues appropriate instructions to each generative AI model.

[1506] As a specific operation, specific commands are sent as prompts to the music generation AI model, such as "Generate calming music," and to the video generation AI model, such as "Generate a landscape video."

[1507] The input is "request data, profile, and emotional data," and the output is "instructions to the generative AI model."

[1508] Step 6: Generate content

[1509] The generative AI model generates content based on instructions from the server.

[1510] Specifically, the music generation AI generates relaxing music with little noise, the video generation AI generates images of tranquil landscapes, and the language generation AI generates relaxing essays.

[1511] The input is "instructions from the server" and the output is "generated music files, video files, and text data."

[1512] Step 7: Receiving generated content

[1513] The server receives the content generated by the generative AI model and stores and manages it appropriately.

[1514] Specifically, it saves music files in the appropriate format (e.g., MP3, WAV) and converts video files for streaming.

[1515] The input is the "generated content" and the output is the "stored content."

[1516] Step 8: Deliver your content

[1517] The server distributes the generated content to the appropriate IoT devices.

[1518] Specifically, it sends music files to a smart speaker, streams video files to a smart display, and sends text data to an e-book reader.

[1519] The input is "stored content" and the output is "delivered content."

[1520] Step 9: Adjust your environment

[1521] Each IoT device automatically adjusts its environment based on the content it receives.

[1522] Specifically, the smart speaker will play relaxing music, the smart display will show a landscape image, and the smart light will adjust the color and brightness of the lighting.

[1523] The input is the "distributed content" and the output is the "conditioned environment."

[1524] Step 10: Gather feedback

[1525] The terminal collects the user's feedback and sends it to the server.

[1526] Specifically, it collects voice input, tap gestures, and environmental sensor data, analyzes it with an emotion engine, and sends the current emotional state to the server.

[1527] The input is "user feedback and emotion data" and the output is "updated user profile and system feedback."

[1528] In this way, the system utilizes user behavioral data and real-time emotional data to provide an optimal environment that meets the user's needs.

[1529] (Application example 2)

[1530] 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."

[1531] In modern society, there is a demand for effective utilization of user behavioral and emotional data to provide optimal content and environments in real time. However, conventional systems have had difficulty recognizing user emotions in real time and generating and delivering optimal content that meets specific requests. They also face challenges in appropriately collecting and incorporating user feedback and maintaining highly accurate user profiles. As a result, they have not been able to provide an environment that adequately enhances user satisfaction.

[1532] The identification processing 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 collecting user behavioral data and emotional data, means for analyzing the collected behavioral data and emotional data to generate and update a user profile, means for receiving a user request, means for generating a prompt sentence for a generative AI model based on the received request and user profile, means for instructing the generative AI model to generate content using the generated prompt sentence, means for receiving the generated content and delivering it to an environment adjustment device, and means for adjusting the environment based on the content received by the environment adjustment device. This makes it possible to comprehensively analyze the user's behavioral data and emotional data and provide optimal content and an environment that meets the user's requests in real time.

[1533] "User behavior data" refers to data related to a series of operations and activities performed by a user, such as application usage history, music playback history, and video viewing history.

[1534] "Emotion data" is data that indicates the user's emotional state, such as facial expressions and tone of voice captured through a camera or microphone.

[1535] A "user profile" is a data set that compiles information about a user's preferences, behavioral patterns, and emotions.

[1536] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate content such as music, video, and text in response to user requests.

[1537] A "prompt sentence" is a text sentence generated to give specific instructions to a generative AI model.

[1538] An "environmental adjustment device" is a device that adjusts the environment based on specified content, such as a smart speaker, smart display, or lighting device.

[1539] "Feedback" refers to opinions and reactions provided by users, or emotional state data collected automatically by the system.

[1540] A "server" is an information processing device that collects and analyzes user behavioral and emotional data, and generates and updates user profiles.

[1541] This invention is a system that collects and analyzes user behavioral and emotional data in real time and provides an optimal environment according to the user's requests. This system is realized by linking a server that generates and updates user profiles, a terminal that receives requests, content generation by generative AI, and an environment adjustment device.

[1542] First, the server collects user behavioral and emotional data. Behavioral data includes application usage history and music and video playback history, while emotional data includes facial expressions and voice tone captured through cameras and microphones. The collected data is analyzed using machine learning algorithms such as Google TensorFlow. This analysis identifies user preferences and behavioral patterns, and a user profile is created and updated.

[1543] Next, the device receives the user's request through the interface. For example, a user might input "I want to relax" into a smartphone app. At the same time, an emotion recognition engine (Microsoft Azure Cognitive Services) recognizes the user's emotional state in real time, and this data is also sent to the server.

[1544] When the server receives this request, it generates a specific prompt for the generative AI model based on the user profile and emotional data. This prompt is used to instruct the generative AI model to generate content. For example, an instruction such as "Generate relaxing music" is sent to the generative AI model.

[1545] Generative AI models (e.g., Jukedeck, Runway, OpenAI GPT) receive instructions and generate their respective content. A music generation AI model generates relaxing music, a video generation AI model generates relaxing landscape footage, and a language generation AI model generates soothing essays. The generated content is sent back to the server, which distributes it to the environment adjustment device.

[1546] The environmental adjustment devices include smart speakers, smart displays, and lighting fixtures. These devices adjust the environment based on the content they receive: a smart speaker plays relaxing music, a smart display shows a video of a relaxing scene, and lighting fixtures are adjusted to a relaxing mode.

[1547] Finally, user feedback is collected through voice input and tap gestures, and an emotion recognition engine also continuously monitors the user's emotional state. The collected feedback and emotion data are sent back to the server for further updating of the user profile.

[1548] For example, if a user inputs "I want to concentrate" and the emotion engine detects that the user is slightly tired, the server will send prompts to the generative AI model such as "Please generate music that will help me concentrate" or "Please generate a video with moderate movement." The generated music and video will then be distributed to smart speakers and smart displays, providing the user with an environment in which they can concentrate.

[1549] An example of a prompt is as follows:

[1550] "Generate relaxing music."

[1551] "The current video generation task is to create a video of a relaxing scene. Please create an appropriate video."

[1552] "Generate soothing essays. Users want to relax through reading."

[1553] This system makes it possible to comprehensively utilize user behavioral and emotional data to provide optimal content and environments in real time that meet the user's needs.

[1554] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1555] Step 1:

[1556] A user inputs a request using a smartphone app. At the same time, the user's emotional data is collected. The emotional data consists of facial expressions and voice tone captured through the smartphone's camera and microphone. This input data is sent from the device to the server.

[1557] Input: User request (e.g., "I want to relax"), emotional data (facial expression, tone of voice)

[1558] Output: A request containing the user's request and emotion data

[1559] Step 2:

[1560] The server analyzes the user's request and emotional data received from the device. The collected emotional data is analyzed using an emotion recognition engine (Microsoft Azure Cognitive Services). The analysis results are integrated with the existing user profile to understand the request.

[1561] Input: User requests, emotion data

[1562] Output: Parsed emotion information, updated request data

[1563] Step 3:

[1564] The server generates specific prompts for the generative AI model based on the analyzed emotional information and the user profile. These prompts are necessary to instruct the generative AI model to generate appropriate content.

[1565] Input: Analyzed emotion information, user profile

[1566] Output: The generated prompt (e.g., "Generate some relaxing music.")

[1567] Step 4:

[1568] The server uses the generated prompts to send instructions for generating content to each generative AI model, which then generates music, video, text, etc.

[1569] Input: Generated prompt text

[1570] Output: Content generated by the generative AI model (music files, video files, text data)

[1571] Step 5:

[1572] The server receives the content obtained from the generative AI model and distributes it to the environment conditioning device.

[1573] Input: Generated content

[1574] Output: Content delivery request to each environmental adjustment device

[1575] Step 6:

[1576] The environmental adjustment devices (smart speakers, smart displays, lighting devices) adjust the environment based on the received content: the smart speaker plays relaxing music, the smart display shows a video of a relaxing scene, and the lighting devices are set to relaxation mode.

[1577] Input: Received content

[1578] Output: Controlled environment (music playback, video display, lighting settings)

[1579] Step 7:

[1580] Users provide feedback on the environment and content provided. Feedback is collected through voice input and tap gestures, and an emotion recognition engine analyzes their current emotional state. This feedback data is then sent back to the server and used to update the user profile.

[1581] Input: User feedback, real-time sentiment data

[1582] Output: Feedback data sent to server, updated user profile

[1583] This series of steps makes it possible to comprehensively utilize user behavioral and emotional data to provide optimal content and environments in real time that meet the user's needs.

[1584] 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.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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).

[1591] 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.

[1592] 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."

[1593] 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.

[1594] 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).

[1595] 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.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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.

[1602] 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.

[1603] 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.

[1604] 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.

[1605] The following is further disclosed regarding the above embodiment.

[1606] (Claim 1)

[1607] a means for collecting user behavior data;

[1608] a means for analyzing the collected behavioral data to generate and update a user profile;

[1609] means for receiving a user request;

[1610] A means for instructing a generation AI to generate content based on the received request and a user profile;

[1611] a means for receiving and delivering the generated content to IoT devices;

[1612] means for adjusting the environment based on the content received by the IoT device;

[1613] A system including:

[1614] (Claim 2)

[1615] 10. The system of claim 1, further comprising means for collecting feedback from users and updating user profiles based on the feedback.

[1616] (Claim 3)

[1617] The system of claim 1, further comprising means for controlling at least one of lighting, music playback, and video display by the IoT device to provide an environment according to the user's requests.

[1618] "Example 1"

[1619] (Claim 1)

[1620] a means for collecting user behavior data;

[1621] A means for analyzing the collected behavioral data using a machine learning algorithm to generate and update a user profile;

[1622] an interface means for receiving a user request;

[1623] means for sending appropriate prompts to the generation AI to instruct content generation based on the received request and the user profile;

[1624] means for receiving the generated content and distributing it to IoT devices over a network;

[1625] A means for the IoT device to adjust its settings and optimize the environment based on the content received; and

[1626] A system including:

[1627] (Claim 2)

[1628] 10. The system of claim 1, further comprising means for collecting feedback from users and updating user profiles based on the feedback.

[1629] (Claim 3)

[1630] The system of claim 1, further comprising means for controlling at least one of lighting, music playback, and video display by the IoT device to provide an environment according to the user's requests.

[1631] "Application Example 1"

[1632] (Claim 1)

[1633] a means for collecting user behavior data;

[1634] a means for analyzing the collected behavioral data to generate and update a user profile;

[1635] means for receiving a user request;

[1636] A means for instructing a generation AI to generate content based on the received request and a user profile;

[1637] means for receiving and delivering the generated content to an in-vehicle system;

[1638] means for adjusting the environment based on the content received by the in-vehicle system;

[1639] A system including:

[1640] (Claim 2)

[1641] 10. The system of claim 1, further comprising means for collecting feedback from users and updating user profiles based on the feedback.

[1642] (Claim 3)

[1643] 10. The system according to claim 1, wherein the in-vehicle system includes means for controlling at least one of lighting, music playback, and video display to provide an environment according to a user's request.

[1644] "Example 2: Combining Emotion Engines"

[1645] (Claim 1)

[1646] means for collecting user behavioral and emotional data;

[1647] means for analyzing the collected behavioral and emotional data to generate and update a user profile;

[1648] means for receiving a user request;

[1649] means for instructing a generative AI model to generate content based on the received request and a user profile;

[1650] a means for receiving and delivering the generated content to IoT devices;

[1651] means for adjusting the environment based on the content received by the IoT device;

[1652] A system including:

[1653] (Claim 2)

[1654] 10. The system of claim 1, further comprising means for collecting feedback from the user and updating the user profile based on the feedback and emotional state.

[1655] (Claim 3)

[1656] The system of claim 1, further comprising means for the IoT device to control at least one of lighting, music playback, and video display, and to provide an environment that meets the user's requests, taking into account data from environmental sensors.

[1657] "Application example 2 when combining emotion engines"

[1658] (Claim 1)

[1659] means for collecting user behavioral and emotional data;

[1660] means for analyzing the collected behavioral and emotional data to generate and update a user profile;

[1661] means for receiving a user request;

[1662] means for generating prompt sentences for the generative AI model based on the received request and a user profile;

[1663] a means for instructing a generative AI model to generate content using the generated prompt sentence;

[1664] means for receiving and delivering the generated content to an environment conditioning device;

[1665] means for adjusting an environment based on content received by the environment adjustment device;

[1666] A system including:

[1667] (Claim 2)

[1668] 10. The system of claim 1, further comprising means for collecting feedback from users and updating user profiles based on the feedback.

[1669] (Claim 3)

[1670] 2. The system according to claim 1, wherein the environmental adjustment device includes means for controlling at least one of lighting, music playback, and video display to provide an environment according to a user's request. [Explanation of symbols]

[1671] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting user behavior data; means for analyzing the collected behavioral data to generate and update a user profile; means for receiving a user request; A means for instructing a generation AI to generate content based on the received request and a user profile; a means for receiving and delivering the generated content to IoT devices; means for adjusting the environment based on content received by the IoT device; A system including:

2. 10. The system of claim 1, further comprising means for collecting feedback from users and updating user profiles based on the feedback.

3. The system of claim 1, further comprising means for controlling at least one of lighting, music playback, and video display by the IoT device to provide an environment according to a user's request.

Images