System

Abstract

To provide a system capable of always providing a new interior experience.SOLUTION: Recognizing a voice input of a user, converting the voice input into text data, extracting a request of the user by analyzing the text data, generating an image based on the extracted request, transmitting the generated image data to a high-definition display, displaying the transmitted image data on the high-definition display, learning a preference of the user by analyzing a previously generated image and a request history of the user, automatically generating a new image generation request based on the preference of the user, transmitting an image generated based on the new image generation request to a terminal, and automatically updating display content.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] Frequently replacing interior items such as calendars, paintings, and posters is difficult for many homes because it requires purchasing physical materials and effort. Furthermore, there are limited ways to easily obtain interior items that are individually customized to the user's taste. As a result, the current situation makes it difficult to meet the need to frequently and easily change the atmosphere of an interior. [Means for solving the problem]

[0005] The present invention provides a system including: means for recognizing a user's voice input and converting the voice input into text data; means for analyzing the text data to extract a user's request; means for generating an image based on the extracted request; means for transmitting the generated image data to a high-definition display; means for displaying the transmitted image data on the high-definition display; means for analyzing past generated images and the user's request history to learn the user's preferences; means for automatically generating a new image generation request based on the user's preferences; and means for transmitting an image generated based on the new image generation request to a terminal and automatically updating the display content. This system allows users to effortlessly incorporate completely original paintings and posters tailored to their preferences into their interiors, and because new images are automatically generated and updated periodically based on past preferences, it is possible to provide a constantly new interior experience.

[0006] A "means for recognizing user voice input" is a device or software that receives voice from a user using a voice input device such as a microphone and converts the voice into digital voice data.

[0007] A "means for converting voice input into text data" is software or algorithms that use voice recognition technology to analyze voice data and convert the content into text format.

[0008] "Means of analyzing text data to extract user requirements" refers to natural language processing technology that analyzes keywords and important phrases within text data to clarify the user's intentions and requirements.

[0009] "Means for generating images based on extracted requests" refers to image generation algorithms or AI technologies for generating images with specific themes or content in response to user requests.

[0010] The "means for transmitting the generated image data to the high-definition display" refers to a communication protocol or software for transferring the generated image data to the high-definition display via a network.

[0011] The "means for displaying the transmitted image data on a high-definition display" refers to display control software or hardware for displaying the received image data on a high-definition display.

[0012] The "means for learning user preferences by analyzing previously generated images and user request history" is a machine learning algorithm that analyzes previously generated image data and user request history to learn user preferences.

[0013] "Means for automatically generating new image generation requests based on user preferences" means software or algorithms for periodically creating new image generation requests based on learned user preferences.

[0014] "Means for sending an image generated based on a new image generation request to a terminal and automatically updating the display content" refers to software or hardware for sending image data generated in response to a new image generation request to a terminal and automatically updating the display content on the terminal. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

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

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The system recognizes user voice input, converts the voice input into text data, analyzes the user's requests, and generates images based on the text. It also transmits the generated images to a high-definition display for display, learns the user's past request history, and automatically generates new image generation requests based on the user's preferences, periodically updating the displayed content.

[0037] Program processing

[0038] 1. Acquiring and Recognizing Voice Input

[0039] When a user speaks into the device, the device uses voice recognition technology to convert this into text data.

[0040] For example, if a user says, "I like ocean scenery. I'd like to see pictures of sunsets too," the device converts this voice data into text data saying, "I like ocean scenery. I'd like to see pictures of sunsets too."

[0041] 2. Analyzing text data and extracting requirements

[0042] The terminal transmits the text data to the server.

[0043] The server analyzes the text data and extracts the user's request (e.g., "seascape," "sunset").

[0044] 3. Image Generation

[0045] The server sends a request to the image generation AI based on the extracted requirements.

[0046] Based on the request, the image generation AI generates images of seascapes and sunsets and returns the data to the server.

[0047] 4. Image data transmission and display

[0048] The server transmits the generated image data to the terminal, which then displays the image on a high-definition display.

[0049] 5. Learning your preferences

[0050] The server analyzes past generated images and the user's request history to learn the user's preferences.

[0051] 6. Automatically generate and update new images

[0052] The server automatically creates a new image generation request based on the user's preferences and sends it to the image generation AI.

[0053] The new image generated is sent to the terminal, which automatically updates the display on the high-definition display.

[0054] Specific examples

[0055] For example, suppose the user first says, "I want to display a painting that suits my room, and I like paintings of flowers." This voice input is converted into text data and sent to the server. The server extracts the request, "I like paintings of flowers," from the text data and sends a request to the image generation AI to generate a painting of a flower. The generated image of the flower is sent from the server to the device and displayed on the device's high-definition display.

[0056] The server then learns from this request history and recognizes that the user's preference is flower images. After a few weeks, the server sends a request to the AI ​​to automatically generate new flower images based on the user's preferences. The generated new flower images are then sent to the device, automatically updating the content on the high-definition display. This process allows the user to enjoy their new interior without any hassle.

[0057] This system allows users to easily change the atmosphere of their interior by displaying paintings and posters that suit their tastes on a high-definition display. It also learns from past requests and automatically generates and updates new images, providing a fresh and appealing interior experience for users.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The user speaks to the device, for example, "I like seascapes. I'd like to see pictures of sunsets too."

[0061] Step 2:

[0062] The device picks up the user's voice through a microphone and uses voice recognition software to convert the voice data into text data. Specifically, the speech "I like seascapes. I'd like to see pictures of sunsets, too" is converted into text data "I like seascapes. I'd like to see pictures of sunsets, too."

[0063] Step 3:

[0064] The terminal sends the converted text data to the server. Using a communication protocol, the text data is sent to the server via the network.

[0065] Step 4:

[0066] The server analyzes the received text data and extracts the user's request. For example, it extracts keywords such as "seascape" and "sunset" from the text data.

[0067] Step 5:

[0068] The server sends image generation requests to the image generation AI based on the extracted keywords. Specifically, it sends requests such as "generate an image of a seascape" and "generate an image of a sunset."

[0069] Step 6:

[0070] The image generation AI generates an image based on the specified keywords, for example, a beautiful seascape or sunset image, and returns the image data to the server.

[0071] Step 7:

[0072] The server receives the generated image data and sends it to the terminal via a communication protocol over the network.

[0073] Step 8:

[0074] The image data received by the terminal is displayed on a high-definition display. The terminal's display control software processes the image data and displays it on the display.

[0075] Step 9:

[0076] The server analyzes previously generated images and the user's request history to learn the user's preferences, for example, that they like "seascapes" and "sunsets."

[0077] Step 10:

[0078] The server automatically generates new image generation requests based on the user's preferences. For example, it creates a new "seascape" or "sunset" image generation request and sends it to the image generation AI.

[0079] Step 11:

[0080] The image generation AI generates a new image and returns the image data to the server, which then sends the new image data it receives to the device.

[0081] Step 12:

[0082] New image data received by the device is automatically updated and displayed on the high-definition display, allowing users to enjoy constantly updated interior designs.

[0083] Example 1

[0084] 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."

[0085] In conventional image generation systems, users must manually input image generation requests each time, and they lack a mechanism for automatically considering user preferences and past request history. As a result, it takes a lot of effort for users to continuously enjoy new images, resulting in a lack of usability. In addition, the displayed content of generated images is not regularly updated, which can lead to user boredom.

[0086] 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.

[0087] In this invention, the server includes means for recognizing a user's voice input, means for converting the voice input into text data, means for analyzing the text data to extract a user's request, means for sending a request to input an image to a generative AI model based on the extracted request, means for receiving image data generated from the generative AI model, means for sending the received image data to a high-definition display, means for displaying the sent image data on the high-definition display, means for analyzing past generated images and the user's request history to learn the user's preferences, means for automatically generating a new image generation request based on the user's preferences, and means for sending an image generated based on the new image generation request to the terminal and automatically updating the display content. This allows the user to continuously enjoy new images that suit their preferences without any hassle.

[0088] "User" refers to an individual who utilizes the system to provide voice input and view the resulting image generation and display.

[0089] "Means for recognizing voice input" refers to technical devices or software that capture and interpret the voice uttered by the user as a digital signal.

[0090] "Means for converting speech input into text data" refers to digital processing technology or software that converts recognized speech into written form.

[0091] "Means for analyzing text data to extract user requirements" refers to processing technology or software that analyzes text data and finds out the user's intended requirements or wishes from within it.

[0092] "Means for sending a request to input an image into a generative AI model" refers to a technical device or software that sends a request to an artificial intelligence model that generates an image based on the extracted request.

[0093] "Means for receiving image data generated from a generative AI model" refers to a processing technology or device that receives image data generated by an image-generating AI model.

[0094] "High-definition display" refers to a display device that can display detailed images and videos at high resolution.

[0095] "Means for displaying the transmitted image data on a high definition display" refers to technical devices or software that transmit and display the generated image data on a high definition display.

[0096] "Means for learning user preferences by analyzing past generated images and user request history" refers to technical devices or software that analyze past image generation history and user request history to learn user preferences and tendencies.

[0097] "Means for automatically generating new image generation requests" refers to technical devices or software that automatically generate requests for new image generation based on learned user preferences.

[0098] "Means for automatically updating the display content" refers to technical devices or software that periodically or automatically update the display content of a high-definition display with newly generated images.

[0099] This invention is a system that recognizes and analyzes a user's voice input, and generates and displays an image based on the analysis results. This system specifically uses the following technical means.

[0100] First, the user speaks to the device. For example, if the user says, "I want to see a picture of a flower," the device receives the voice input through the built-in microphone. The device uses voice recognition software, such as the Google Cloud Speech-to-Text API, to convert the captured voice data into text data.

[0101] The device then sends the generated text data to the server, which then uses natural language processing tools (e.g., spaCy or NLTK) to analyze the user's request. Based on this analysis, the server extracts the user's specific request (e.g., "flower picture").

[0102] Based on the extracted requirements, the server sends an image generation request to an image generation AI (e.g., OpenAI's DALL·E or Stability AI's Stable Diffusion). Specific examples of prompts include "Generate a picture of a flower" or "Generate a new flower picture that matches the user's preferences."

[0103] The image data generated by the image generation AI is sent back to the server, which then receives the data and sends it to the device, which then displays it on a high-definition display.

[0104] Furthermore, the server stores the past generated images and request history in a database and analyzes them using machine learning algorithms (e.g., K-Nearest Neighbors and Decision Trees) to learn the user's preferences. Based on the learning results, new image generation requests are automatically generated periodically, and the server again sends these to the image generation AI. The newly generated images are sent to the device, which automatically updates the display on the high-definition display.

[0105] As an example, when a user first voice-inputs "I want to see summer scenery," this voice is converted into text data and sent to the server. The server extracts the request "summer scenery" from the text data and requests the image generation AI to generate "summer scenery." The generated image of the summer scenery is sent from the server to the device, which then displays it on a high-definition display.

[0106] The server also learns user trends by analyzing past request data. For example, if a user frequently requests "cherry blossom photos," the server will automatically create requests to periodically generate "new cherry blossom photos" and send them to the image generation AI. These new cherry blossom photos are sent to the device and automatically updated as content on the high-definition display. This allows users to constantly enjoy new images seamlessly.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] The user inputs voice into the device. For example, if the user says, "I want to see pictures of seascapes," the device picks up this voice through the built-in microphone and saves it as voice data. The input of this step is the user's voice, and the output is voice data.

[0110] Step 2:

[0111] The device inputs the voice data into voice recognition software (e.g., a general voice recognition API) and converts it into text data. This conversion analyzes the sound wave signal as digital text and generates the string "I want to see pictures of seascapes." The input of this step is voice data, and the output is text data.

[0112] Step 3:

[0113] The terminal sends the generated text data to the server. The server receives this text data and analyzes it using a natural language processing tool (e.g., a general natural language processing library). In this analysis, the request "seascape" is extracted from the text data. The input of this step is the text data, and the output is the analyzed request data.

[0114] Step 4:

[0115] Based on the parsed request, the server sends an image generation request to an image generation AI (e.g., a general image generation model). Specifically, it sends a prompt to the generative AI model saying, "Please generate an image of a seascape." The input of this step is the parsed request data, and the output is a request to the generative AI.

[0116] Step 5:

[0117] The image generation AI generates an image based on the received prompt and sends the generated image data back to the server. The input to this step is the request to the generation AI, and the output is the image data.

[0118] Step 6:

[0119] The server receives the generated image data and sends it to the terminal. In this step, data is transferred over the network. The input is the image data, and the output is the transmission of the image data to the terminal.

[0120] Step 7:

[0121] The terminal displays the image data received from the server on a high-definition display. In this display process, the image data is passed to the display driver and displayed in a form that is visible to the user. The input of this step is the image data, and the output is the image displayed on the display.

[0122] Step 8:

[0123] The server stores the user's past requests and the history of generated images in a database and analyzes them using a machine learning algorithm. This analysis learns the user's preferences and automatically generates prompts for new image generation requests. The input of this step is the past request and image history data, and the output is the learned user preferences and new requests.

[0124] Step 9:

[0125] The server again sends an automatically generated new image generation request to the image generation AI, and the generated new image is sent to the terminal. The terminal receives this and periodically updates the content of the high-definition display. The input of this step is the automatically generated request and the generated image data, and the output is the updated display content on the display.

[0126] (Application example 1)

[0127] 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."

[0128] Conventional interior design systems require users to manually select images and display them on a screen, making it difficult to frequently update the atmosphere of a physical store. Additionally, there is a lack of technology to automatically generate and display appropriate images continuously based on user preferences.

[0129] 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.

[0130] In this invention, the server includes means for recognizing a user's voice input, means for converting the voice input into text data, means for analyzing the text data to extract a user's request, means for generating an image based on the extracted request, means for transmitting the generated image data to a high-definition display, means for displaying the transmitted image data on the high-definition display, means for analyzing past generated images and the user's request history to learn the user's preferences, means for automatically generating a new image generation request based on the user's preferences, means for transmitting an image generated based on the new image generation request to a terminal and automatically updating the display content, and means for displaying the generated image on a terminal with a high-definition display to provide customers of a physical store with a visual interior experience. This enables users to automatically generate and display interior designs that suit their preferences using only voice input, thereby continuously maintaining the atmosphere of the physical store fresh.

[0131] "User voice input" means verbal instructions or requests made by a User.

[0132] "Means for converting speech input into text data" refers to technology or devices that analyze speech signals and convert them into corresponding text.

[0133] "Text data" refers to character string data converted from speech.

[0134] "Means for extracting user requirements" refers to techniques and methods for identifying user intent and requests from converted text data.

[0135] "Means for generating images" refers to techniques or devices that create images by computer based on a user's request.

[0136] "Image data" refers to the digital data of the generated image.

[0137] "High definition display" refers to a display device capable of displaying images at high resolution.

[0138] "User request history" refers to a record of requests and instructions that a user has previously entered into the system.

[0139] "Means for learning user preferences" refers to technologies and methods for analyzing user preferences and trends based on past request history.

[0140] "Means for automatically generating new image generation requests" refers to techniques or methods by which the system automatically generates new image generation instructions based on user preferences.

[0141] A "physical store" refers to a commercial facility or service location that has a specific physical space.

[0142] "Interior experience" refers to the experience of the visual design and decoration of an indoor space.

[0143] This invention is a system that recognizes a user's voice input, converts it into text data, and analyzes the user's requests. Specifically, this system generates images based on the user's preferences and displays them on a high-definition display. It also learns from past request history, automatically makes new image generation requests, and periodically updates the displayed content.

[0144] System configuration and programs

[0145] Hardware:

[0146] Microphone: A device that captures the user's voice input.

[0147] High-definition display: A device that displays the generated images.

[0148] Edge device: A device that performs some of the processing for voice recognition and image generation.

[0149] software:

[0150] Speech recognition technology (speech_recognition library): A library for converting voice input into text data.

[0151] Image generation AI (access API using the requests library): An AI model for generating images based on text data.

[0152] Image processing library (Pillow): A library for processing and displaying acquired image data.

[0153] History database: A database to store past requests and generated images and learn user preferences.

[0154] Processing Details

[0155] When a user speaks into the microphone, the server captures the voice and converts it into text data using voice recognition technology. For example, if a user says, "I want to display summer scenery, but I like pictures of the beach," the voice data is converted into text data saying, "I want to display summer scenery, but I like pictures of the beach."

[0156] The server then analyzes this text data and extracts user requests such as "summer scenery" or "beach photos." Once the request is extracted, the server sends a prompt to the image generation AI. An example of this prompt is "Please generate an image of a summer beach scenery that matches the interior of a cafe."

[0157] The image generation AI generates an appropriate image based on this prompt and returns the image data to the server. The server then sends the received image data to a high-definition display, where the image is displayed on the physical store's terminal. By analyzing past generated images and the user's request history, the AI ​​learns the user's preferences and automatically makes new image generation requests. The newly generated images are also displayed on the high-definition display, allowing the store's atmosphere to be constantly updated.

[0158] For example, if a cafe owner says, "I want to display a summer scene, but I like beach photos," the system will send a prompt to the generative AI model based on that request, and the generated beach image will be displayed on the cafe's high-definition display. An example of this prompt would be, "Please generate a summer beach scene image that matches the cafe's interior." This saves users the trouble of manually selecting an image, allowing them to easily change the atmosphere of their store.

[0159] As a whole, the system allows users to use voice input to automatically generate interior designs that suit their preferences, providing a visual interior experience in a physical store.

[0160] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0161] Step 1:

[0162] The user provides voice input. The user speaks into the microphone and inputs a request such as, "I want to display a painting that matches my room, and I like paintings of flowers."

[0163] Input: User's voice.

[0164] Output: Audio data.

[0165] Step 2:

[0166] The server receives audio data from the microphone and converts it into text using speech recognition technology. Specifically, it uses the speech_recognition library.

[0167] Input: Audio data.

[0168] Output: Text data (e.g. "I want to display paintings that suit my room, and I like paintings of flowers.").

[0169] Step 3:

[0170] The server analyzes the text data and extracts the user's request using natural language processing to identify the request.

[0171] Input: Text data.

[0172] Output: Request data (e.g. "A painting that suits the room", "A painting of flowers").

[0173] Step 4:

[0174] Based on the extracted request, the server creates a prompt and sends it to the image generation AI model. Example prompt: "Please generate a painting of a flower."

[0175] Input: Request data.

[0176] Output: A prompt statement (e.g., "Generate a painting of a flower.").

[0177] Step 5:

[0178] The image generation AI model generates an image based on the prompt text. The server sends a request to the image generation API and receives the generated image data.

[0179] Input: Prompt statement.

[0180] Output: Image data.

[0181] Step 6:

[0182] The server transmits the received image data to the high-definition display. Specifically, the image data is transferred through the interface of the display device.

[0183] Input: Image data.

[0184] Output: Preparing image data for display.

[0185] Step 7:

[0186] The terminal displays the image on a high-definition display. The display device receives the image data and displays it for the user to visually confirm.

[0187] Input: Image data to be displayed on the display.

[0188] Output: Image displayed on a high definition display.

[0189] Step 8:

[0190] The server analyzes past generated images and user request history to learn user preferences. It identifies user preferences using data stored in a history database.

[0191] Input: Previously generated images, user request history.

[0192] Output: Data about user preferences.

[0193] Step 9:

[0194] The server automatically generates new image generation requests based on the user's preferences, which are sent to the generation AI as prompts that are periodically updated.

[0195] Input: Data about the user's preferences.

[0196] Output: A new image generation request (e.g. "Flower Painting").

[0197] Step 10:

[0198] The server then sends the image generated based on the new image generation request to the high-definition display again, automatically updating the display content.

[0199] Input: Image data generated based on a new image generation request.

[0200] Output: Updated display content.

[0201] 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.

[0202] This system recognizes user voice input, converts the voice into text data, and extracts and recognizes the user's requests through analysis. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it has the ability to generate and select images based on the user's emotions. This allows for a more personalized user experience.

[0203] Program processing

[0204] 1. Acquiring and Recognizing Voice Input

[0205] The user speaks into the device, and the device uses voice recognition software to convert the voice data into text data. For example, if the user says, "I'm feeling sad today," the device converts this into text data: "I'm feeling sad today."

[0206] 2. Analyzing text data and extracting requirements

[0207] The terminal transmits the converted text data to the server.

[0208] The server analyzes the text data and extracts the user's request (e.g., "feeling sad").

[0209] 3. Emotional Recognition

[0210] The server uses an emotion engine to recognize emotions from the user's voice. For example, if the text data is analyzed as "feeling sad," the server recognizes the user's emotion as "sad."

[0211] 4. Select or generate an image

[0212] Based on the recognized emotion, the server sends a request to an image generation AI or selects an appropriate image from an existing image database. For example, if the user is in a sad mood, it will generate or select a calm and soothing image.

[0213] 5. Image data transmission and display

[0214] The server transmits the generated or selected image data to the terminal, which displays the image on a high-definition display.

[0215] 6. Learning user preferences and emotional patterns

[0216] The server analyzes past generated images, user request history, and recognized emotional patterns to learn the user's preferences and emotional patterns, thereby understanding which images tend to be preferred when the user is in a particular emotional state.

[0217] 7. Automatically generate and update new image generation requests

[0218] The server automatically generates new image generation requests based on the user's preferences and emotional patterns. For example, if a user has previously preferred a particular type of image that has a soothing effect when they felt sad, the server will create a request to automatically generate that type of image.

[0219] 8. Create and send a new image

[0220] The image generation AI generates a new image and returns the image data to the server. The server then sends the new image data to the device, which then automatically updates the content displayed on the high-definition display.

[0221] Specific examples

[0222] For example, if a user says, "I want to display a painting that suits my room, but I'm feeling down today," the device converts the voice data into text data saying, "I want to display a painting that suits my room, but I'm feeling down today," and sends it to the server. The server analyzes this and extracts the emotion "down." The emotion engine recognizes this as a "depressed mood" and sends a request to the image generation AI to generate an image with a soothing theme. The generated image is sent from the server to the device, which then displays it on a high-definition display.

[0223] The server then learns from this request history, generated images, and recognized emotions to understand the image preferences of users when they are in a particular emotional state. From then on, the next time the user is in a similar emotional state, the server can automatically generate and display the image the user prefers, providing a more personalized user experience.

[0224] The processing flow will be explained below.

[0225] Step 1:

[0226] The user speaks into the device, for example, saying, "I'm feeling sad today. I want to see pictures that will lift my spirits."

[0227] Step 2:

[0228] The device picks up the user's voice through a microphone and uses voice recognition software to convert the voice data into text data. Specifically, the speech "I'm feeling sad today. I want to see pictures that will lift my spirits" is converted into text data "I'm feeling sad today. I want to see pictures that will lift my spirits."

[0229] Step 3:

[0230] The terminal sends the converted text data to the server via a network using a communication protocol.

[0231] Step 4:

[0232] The server analyzes the received text data and extracts the user's request, for example, extracting keywords such as "sad mood" and "pictures that lift your spirits."

[0233] Step 5:

[0234] The server uses an emotion engine to recognize emotions from the user's voice. For example, if the text data is analyzed as "feeling sad," the server recognizes the user's emotion as "sad."

[0235] Step 6:

[0236] The server sends an image generation request to the image generation AI based on the extracted keywords and the recognized emotions. Specifically, it sends a request to "generate a soothing image to lift the mood."

[0237] Step 7:

[0238] The image generation AI generates an image based on the specified request, for example, generating a vivid and uplifting image of a flower, and returns the image data to the server.

[0239] Step 8:

[0240] The server receives the generated image data and sends it to the terminal via the network using a communication protocol.

[0241] Step 9:

[0242] The image data received by the terminal is displayed on a high-definition display. The terminal's display control software processes the image data and displays it on the display.

[0243] Step 10:

[0244] The server analyzes previously generated images, user request history, and recognized emotional patterns to learn user preferences and emotional patterns, thereby understanding which images users tend to like for specific emotional states.

[0245] Step 11:

[0246] The server automatically generates new image generation requests based on the user's preferences and emotional patterns it has learned. For example, if a user has previously preferred a particular type of image that has a soothing effect when they felt sad, it will send a request to the image generation AI to automatically generate that type of image.

[0247] Step 12:

[0248] The image generation AI generates a new image and returns the image data to the server, which then sends the new image data it receives to the device.

[0249] Step 13:

[0250] New image data received by the device is automatically updated and displayed on the high-definition display, allowing users to enjoy constantly updated interior designs.

[0251] Example 2

[0252] 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."

[0253] Conventional voice recognition systems only convert a user's voice input into text data, making it difficult to generate appropriate responses based on the user's emotions or specific requests. Furthermore, there is no system that dynamically generates or selects and displays images based on the user's emotions, limiting the user experience. This invention aims to provide a more personalized user experience by focusing on user emotion recognition and image generation based on those emotions.

[0254] 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.

[0255] In this invention, the server includes a means for recognizing user emotions from text data, a means for generating images based on an image generation artificial intelligence model, and a means for analyzing past generated images and the user's request history to learn the user's preferences, thereby enabling the server to generate, select, and provide appropriate and personalized images based on the emotions and requests extracted from the user's voice input.

[0256] "User" refers to any person or entity that uses this system.

[0257] "Voice input" refers to voice data uttered by a user.

[0258] "Text data" refers to data converted from voice input into a string of characters.

[0259] "Emotion" refers to information that indicates the user's internal emotional state.

[0260] "Image" refers to digital data containing visual information.

[0261] "Generation" refers to the act of the system creating new data.

[0262] "Display" refers to the act of projecting a generated or selected image onto a terminal display.

[0263] "High-definition display" refers to a device that displays images and information in high resolution.

[0264] "Server" refers to a central computer system that processes and stores data.

[0265] "Terminal" refers to a device that is directly operated by a user.

[0266] "Requests" refer to the wishes and requirements that users have for the system.

[0267] "Image generation artificial intelligence model" refers to algorithms and programs that generate images using AI technology.

[0268] "Recognition" refers to the act of a system understanding and making sense of data.

[0269] "Analysis" refers to the process of examining data in detail and extracting meaning.

[0270] "Learning" refers to the process of extracting trends and patterns from past data and using them to predict and respond to the future.

[0271] "Transmitting" refers to the act of transferring data from one point to another.

[0272] The present invention provides a system that recognizes a user's voice input, converts it into text data, analyzes it, and extracts emotions and requests. This system generates or selects and displays images according to the user's emotions, thereby achieving a highly personalized user experience. Specific embodiments are described below.

[0273] Acquiring and recognizing voice input

[0274] The user speaks into the device, and the device uses the built-in microphone to capture the voice and collects the voice data, which is then converted into text data using speech recognition software (e.g., Google's speech recognition API).

[0275] Analyzing text data and extracting requirements

[0276] The device transmits the converted text data to the server, which then uses a natural language processing engine (e.g., spaCy) to analyze the text data and extract the user's request and emotion. For example, from the text data "I'm feeling sad today," it identifies the emotion "sad" and the request "I'm feeling bad."

[0277] Emotion recognition

[0278] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's text data. In this way, the server specifically grasps the user's internal emotional state (e.g., "sad," "happy," etc.).

[0279] Select or generate an image

[0280] Based on the recognized emotion, the server generates an image using an image generation artificial intelligence model (e.g., OpenAI's DALL-E) or selects an appropriate image from an existing image database (e.g., Pexels or Unsplash). For example, when the user is in a "sad" mood, it provides calming and soothing images.

[0281] Image data transmission and display

[0282] The server sends the generated or selected image data to the device, which then displays the received image data on a high-definition display, allowing the user to view an image that matches their emotions.

[0283] Learning user preferences and emotional patterns

[0284] The server analyzes past generated images, the user's request history, and recognized emotional patterns. It uses machine learning algorithms (e.g., TensorFlow) to learn the user's preferences and emotional patterns. This allows it to generate or select the most appropriate image for similar emotional states in the future.

[0285] Automatically generate and update new image generation requests

[0286] The server automatically generates new image generation requests based on the user's preferences and emotional patterns. For example, it generates new prompts from specific types of image data that the user prefers when feeling sad. This ensures that images that match the user's emotions are always provided.

[0287] Specific examples

[0288] For example, consider the case where a user says to the device, "I want to display a painting that suits my room, but I'm feeling down today." The device converts this speech into text data using a speech recognition API and sends it to the server. The server extracts the emotion "down" and uses its emotion engine to recognize it as "depressed mood." Based on this emotion, it sends a prompt to the image generation AI model to "generate an image with a soothing theme." The generated image is sent from the server to the device and displayed on the device's high-definition display. The next time the user expresses a similar emotion, the system will provide the most appropriate image based on its past learning results.

[0289] This system enables dynamic image generation and display according to the user's emotions, providing a personalized, high-quality user experience.

[0290] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0291] Step 1:

[0292] Acquiring and recognizing voice input

[0293] The user inputs voice into the terminal.

[0294] Example: "I feel sad today."

[0295] The device captures voice data through the microphone and converts this voice data into text data using voice recognition software (for example, Google's voice recognition API).

[0296] Input: Audio data

[0297] Data processing: Speech-to-text conversion using speech recognition API

[0298] Output: Text data "I feel sad today"

[0299] Specific operation: recognizer.recognize_google(audio_data)

[0300] Step 2:

[0301] Analyzing text data and extracting requirements

[0302] The terminal transmits the text data to the server.

[0303] Input: Text data

[0304] Output: Sends text data to the server

[0305] Specific behavior: requests.post(server_url, json={"text": "I'm feeling sad today"})

[0306] The server analyzes the received text data using a natural language processing engine (e.g., spaCy) to extract the user's requests and sentiments.

[0307] Input: Text data

[0308] Data Calculation: Analysis and request extraction using a natural language processing engine

[0309] Output: Request "I feel bad" and emotion "Sad"

[0310] Specific behavior: nlp = spacy.load("ja_core_news_sm"), doc = nlp("I'm feeling sad today")

[0311] Step 3:

[0312] Emotion recognition

[0313] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion from the text data.

[0314] Input: Extracted text data

[0315] Data Computation: Emotion Recognition with Emotion Engine

[0316] Output: Recognized emotion "sad"

[0317] Specific behavior: tone_analyzer.tone({"text": "I'm feeling sad today"}, content_type="application / json")

[0318] Step 4:

[0319] Select or generate an image

[0320] Based on the recognized emotion, the server requests an image generation AI model (e.g., OpenAI's DALL-E) to generate an image, or selects an appropriate image from an existing image database (e.g., Pexels or Unsplash).

[0321] Input: Recognized emotion "sad"

[0322] Data operation: Image generation request or image selection

[0323] Output: Generated or selected image

[0324] Specific behavior: response = openai.Image.create(prompt="calming scenery", num_images=1) or search_results = pexels_api.search("calming scenery")

[0325] Step 5:

[0326] Image data transmission and display

[0327] The server transmits the generated or selected image data to the terminal.

[0328] Input: Image data

[0329] Output: Send image data to the device

[0330] Specific behavior: requests.post(client_url, json={"image_url": image_url})

[0331] The terminal displays the received image on a high-definition display.

[0332] Input: Received image data

[0333] Output: Display images on a high-definition display

[0334] Specific behavior: display_image(image_url)

[0335] Step 6:

[0336] Learning user preferences and emotional patterns

[0337] The server analyzes past generated images, the user's request history, and recognized emotional patterns to learn the user's preferences and emotional patterns.

[0338] Input: Previously generated images, request history, emotion patterns

[0339] Data Computing: Analysis and learning using machine learning algorithms

[0340] Output: Updated user preferences and sentiment patterns

[0341] Specific behavior: user_preferences.update({"mood": "sad", "liked_images": [image_url]}), model.fit(history_data, preferences_data)

[0342] Step 7:

[0343] Automatically generate and update new image generation requests

[0344] The server automatically generates new image generation requests based on learned user preferences and emotional patterns.

[0345] Input: Learned user preferences and emotional patterns

[0346] Data Calculation: New Prompt Generation

[0347] Output: Auto-generated image request

[0348] Specific behavior: auto_prompt = generate_prompt(user_preferences)

[0349] Step 8:

[0350] Generate and send a new image

[0351] The image generation artificial intelligence model generates a new image and returns the image data to the server.

[0352] Input: A new image generation request

[0353] Data computation: Image generation using generative AI models

[0354] Output: New image data

[0355] Specific behavior: response = openai.Image.create(prompt=auto_prompt, num_images=1)

[0356] The server transmits the received new image data to the terminal.

[0357] Input: New image data

[0358] Output: Send image data to the device

[0359] Specific behavior: requests.post(client_url, json={"image_url": new_image_url})

[0360] The device will display new images on its high-definition display and automatically refresh the display.

[0361] Input: New image data

[0362] Output: Display images on a high-definition display

[0363] Specific operation: display_image(new_image_url)

[0364] (Application example 2)

[0365] 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."

[0366] Conventional voice input systems often simply analyze user requests as text data and provide static responses. This makes it difficult to provide a truly personalized experience because they do not reflect the user's emotional state. Furthermore, they lack the ability to learn user preferences and automatically provide optimal content. In many settings, particularly brick-and-mortar stores, where information provision based on user emotions and preferences is required, there is a demand for improved customer satisfaction.

[0367] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing a user's emotion, means for selecting or generating an image based on the extracted request and emotion, and means for transmitting the generated image data to a high-definition display. This makes it possible to provide personalized images and information based on the user's emotion, thereby improving the user experience and increasing customer satisfaction.

[0368] "Voice input" refers to voice data emitted by the user, and this data is used by the system to detect operations and requests.

[0369] "Text data" refers to data of character information obtained by analyzing voice input.

[0370] "User requests" are specific requests or instructions given by users to the system.

[0371] "Emotions" represent the user's psychology and mental state, and are analyzed and recognized by the system.

[0372] "Selecting or generating an image" refers to choosing an appropriate image from an existing image database or generating a new image based on the user's requirements or emotions.

[0373] "High definition display" means a display device having a high resolution that presents a generated or selected image to a user.

[0374] "User preferences" refers to the user's individual tendencies and likes learned through past generated images and request history.

[0375] "Image Generation Request" means instructions or commands for generating a new image based on the user's needs or emotions.

[0376] A "terminal" is a device used by a user, typically hardware such as a smartphone or smart glasses.

[0377] "Automatic updating" means that the system replaces the displayed content with new content based on user input and history, without manual intervention.

[0378] This invention comprises a system that utilizes a user's voice input, analyzes the user's requests and emotions based on the voice input, and generates or selects appropriate images. A specific method for realizing this system is described below.

[0379] First, the user speaks into a device such as a smartphone or smart glasses. The voice input is picked up through the device's microphone and converted into text data using speech recognition software. This process is performed using a library called SpeechRecognition, for example.

[0380] The converted text data is then sent to a server, which analyzes the text data and extracts the user's request and emotion. This analysis uses natural language processing techniques such as the Transformers library. Emotion recognition uses an emotion engine to analyze the user's mental state.

[0381] Based on the extracted needs and emotions, the server then sends a generation request to an image generation AI model or selects an appropriate image from an existing image database, such as DALL-E or Midjourney.

[0382] The generated or selected image data is sent from the server to the device and displayed on the device's high-definition display. This image data is then automatically generated based on the user's preferences and request history. By learning the user's preferences, more appropriate and personalized images are provided when a similar request occurs again.

[0383] Specific examples

[0384] For example, if a user says to their smartphone, "I'm a little tired today, so I'm looking for a product that will help me relax," the device converts this speech into text data, "I'm a little tired today, so I'm looking for a product that will help me relax," and sends it to the server. The server analyzes this text data and recognizes the user's emotion as "fatigue." Next, based on the emotion, it generates or selects a product image that has a relaxing effect. In this case, the prompt text used is "relaxation, fatigue."

[0385] Finally, the selected or generated image data is displayed on the smartphone's high-definition display, and appropriate products are presented according to the user's request.

[0386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0387] Step 1:

[0388] A user speaks into a device such as a smartphone or smart glasses. Specifically, the voice data is acquired through a microphone. The input is the user's voice, and the output is the acquired voice data.

[0389] Step 2:

[0390] The device receives the voice data and converts it into text data using voice recognition software, such as a library called SpeechRecognition, which takes voice data as input and outputs text data as the result.

[0391] Step 3:

[0392] The terminal sends the converted text data to the server. The input is the text data, and the output is a transmission completion notification to the server.

[0393] Step 4:

[0394] The server analyzes the received text data and extracts the user's requests and emotions. This analysis uses natural language processing techniques such as the Transformers library. The input is text data, and the output is the analyzed user's requests and emotions.

[0395] Step 5:

[0396] The server performs emotion recognition and analyzes the user's emotional state using an emotion engine. For example, emotions such as fatigue and joy are recognized. The input is text data, and the output is the recognized emotion.

[0397] Step 6:

[0398] Based on the extracted request and emotion, the server sends a generation request to an image generation AI model or selects an appropriate image from an existing image database. Examples of image generation AI models used include DALL-E and Midjourney. The input is request and emotion data, and the output is the generated or selected image data.

[0399] Step 7:

[0400] The generated or selected image data is sent from the server to the terminal. The input is the image data, and the output is a notification that the image data has been sent.

[0401] Step 8:

[0402] The terminal receives the transmitted image data and displays it on a high-definition display. The input is the image data, and the output is the image displayed on the display.

[0403] Step 9:

[0404] The server analyzes the past generated images and the user's request history and executes a process to learn the user's preferences. The input is the past generated images and the request history, and the output is the learned user preference data.

[0405] Step 10:

[0406] The server automatically generates new image generation requests based on the learned user preferences and recognized emotions. The input is preference data and emotion data, and the output is a new image generation request.

[0407] Step 11:

[0408] The image data generated based on the new image generation request is sent to the terminal again, and the display content is automatically updated. The input is the new image data, and the output is the updated display.

[0409] This series of processes realizes a system that provides a personalized experience according to the user's emotions.

[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 (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.

[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] The system recognizes user voice input, converts the voice input into text data, analyzes the user's requests, and generates images based on the text. It also transmits the generated images to a high-definition display for display, learns the user's past request history, and automatically generates new image generation requests based on the user's preferences, periodically updating the displayed content.

[0427] Program processing

[0428] 1. Acquiring and Recognizing Voice Input

[0429] When a user speaks into the device, the device uses voice recognition technology to convert this into text data.

[0430] For example, if a user says, "I like ocean scenery. I'd like to see pictures of sunsets too," the device converts this voice data into text data saying, "I like ocean scenery. I'd like to see pictures of sunsets too."

[0431] 2. Analyzing text data and extracting requirements

[0432] The terminal transmits the text data to the server.

[0433] The server analyzes the text data and extracts the user's request (e.g., "seascape," "sunset").

[0434] 3. Image Generation

[0435] The server sends a request to the image generation AI based on the extracted requirements.

[0436] Based on the request, the image generation AI generates images of seascapes and sunsets and returns the data to the server.

[0437] 4. Image data transmission and display

[0438] The server transmits the generated image data to the terminal, which then displays the image on a high-definition display.

[0439] 5. Learning your preferences

[0440] The server analyzes past generated images and the user's request history to learn the user's preferences.

[0441] 6. Automatically generate and update new images

[0442] The server automatically creates a new image generation request based on the user's preferences and sends it to the image generation AI.

[0443] The new image generated is sent to the terminal, which automatically updates the display on the high-definition display.

[0444] Specific examples

[0445] For example, suppose the user first says, "I want to display a painting that suits my room, and I like paintings of flowers." This voice input is converted into text data and sent to the server. The server extracts the request, "I like paintings of flowers," from the text data and sends a request to the image generation AI to generate a painting of a flower. The generated image of the flower is sent from the server to the device and displayed on the device's high-definition display.

[0446] The server then learns from this request history and recognizes that the user's preference is flower images. After a few weeks, the server sends a request to the AI ​​to automatically generate new flower images based on the user's preferences. The generated new flower images are then sent to the device, automatically updating the content on the high-definition display. This process allows the user to enjoy their new interior without any hassle.

[0447] This system allows users to easily change the atmosphere of their interior by displaying paintings and posters that suit their tastes on a high-definition display. It also learns from past requests and automatically generates and updates new images, providing a fresh and appealing interior experience for users.

[0448] The processing flow will be explained below.

[0449] Step 1:

[0450] The user speaks to the device, for example, "I like seascapes. I'd like to see pictures of sunsets too."

[0451] Step 2:

[0452] The device picks up the user's voice through a microphone and uses voice recognition software to convert the voice data into text data. Specifically, the speech "I like seascapes. I'd like to see pictures of sunsets, too" is converted into text data "I like seascapes. I'd like to see pictures of sunsets, too."

[0453] Step 3:

[0454] The terminal sends the converted text data to the server. Using a communication protocol, the text data is sent to the server via the network.

[0455] Step 4:

[0456] The server analyzes the received text data and extracts the user's request. For example, it extracts keywords such as "seascape" and "sunset" from the text data.

[0457] Step 5:

[0458] The server sends image generation requests to the image generation AI based on the extracted keywords. Specifically, it sends requests such as "generate an image of a seascape" and "generate an image of a sunset."

[0459] Step 6:

[0460] The image generation AI generates an image based on the specified keywords, for example, a beautiful seascape or sunset image, and returns the image data to the server.

[0461] Step 7:

[0462] The server receives the generated image data and sends it to the terminal via a communication protocol over the network.

[0463] Step 8:

[0464] The image data received by the terminal is displayed on a high-definition display. The terminal's display control software processes the image data and displays it on the display.

[0465] Step 9:

[0466] The server analyzes previously generated images and the user's request history to learn the user's preferences, for example, that they like "seascapes" and "sunsets."

[0467] Step 10:

[0468] The server automatically generates new image generation requests based on the user's preferences. For example, it creates a new "seascape" or "sunset" image generation request and sends it to the image generation AI.

[0469] Step 11:

[0470] The image generation AI generates a new image and returns the image data to the server, which then sends the new image data it receives to the device.

[0471] Step 12:

[0472] New image data received by the device is automatically updated and displayed on the high-definition display, allowing users to enjoy constantly updated interior designs.

[0473] Example 1

[0474] 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."

[0475] In conventional image generation systems, users must manually input image generation requests each time, and they lack a mechanism for automatically considering user preferences and past request history. As a result, it takes a lot of effort for users to continuously enjoy new images, resulting in a lack of usability. In addition, the displayed content of generated images is not regularly updated, which can lead to user boredom.

[0476] 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.

[0477] In this invention, the server includes means for recognizing a user's voice input, means for converting the voice input into text data, means for analyzing the text data to extract a user's request, means for sending a request to input an image to a generative AI model based on the extracted request, means for receiving image data generated from the generative AI model, means for sending the received image data to a high-definition display, means for displaying the sent image data on the high-definition display, means for analyzing past generated images and the user's request history to learn the user's preferences, means for automatically generating a new image generation request based on the user's preferences, and means for sending an image generated based on the new image generation request to the terminal and automatically updating the display content. This allows the user to continuously enjoy new images that suit their preferences without any hassle.

[0478] "User" refers to an individual who utilizes the system to provide voice input and view the resulting image generation and display.

[0479] "Means for recognizing voice input" refers to technical devices or software that capture and interpret the voice uttered by the user as a digital signal.

[0480] "Means for converting speech input into text data" refers to digital processing technology or software that converts recognized speech into written form.

[0481] "Means for analyzing text data to extract user requirements" refers to processing technology or software that analyzes text data and finds out the user's intended requirements or wishes from within it.

[0482] "Means for sending a request to input an image into a generative AI model" refers to a technical device or software that sends a request to an artificial intelligence model that generates an image based on the extracted request.

[0483] "Means for receiving image data generated from a generative AI model" refers to a processing technology or device that receives image data generated by an image-generating AI model.

[0484] "High-definition display" refers to a display device that can display detailed images and videos at high resolution.

[0485] "Means for displaying the transmitted image data on a high definition display" refers to technical devices or software that transmit and display the generated image data on a high definition display.

[0486] "Means for learning user preferences by analyzing past generated images and user request history" refers to technical devices or software that analyze past image generation history and user request history to learn user preferences and tendencies.

[0487] "Means for automatically generating new image generation requests" refers to technical devices or software that automatically generate requests for new image generation based on learned user preferences.

[0488] "Means for automatically updating the display content" refers to technical devices or software that periodically or automatically update the display content of a high-definition display with newly generated images.

[0489] This invention is a system that recognizes and analyzes a user's voice input, and generates and displays an image based on the analysis results. This system specifically uses the following technical means.

[0490] First, the user speaks to the device. For example, if the user says, "I want to see a picture of a flower," the device receives the voice input through the built-in microphone. The device uses voice recognition software, such as the Google Cloud Speech-to-Text API, to convert the captured voice data into text data.

[0491] The device then sends the generated text data to the server, which then uses natural language processing tools (e.g., spaCy or NLTK) to analyze the user's request. Based on this analysis, the server extracts the user's specific request (e.g., "flower picture").

[0492] Based on the extracted requirements, the server sends an image generation request to an image generation AI (e.g., OpenAI's DALL·E or Stability AI's Stable Diffusion). Specific examples of prompts include "Generate a picture of a flower" or "Generate a new flower picture that matches the user's preferences."

[0493] The image data generated by the image generation AI is sent back to the server, which then receives the data and sends it to the device, which then displays it on a high-definition display.

[0494] Furthermore, the server stores the past generated images and request history in a database and analyzes them using machine learning algorithms (e.g., K-Nearest Neighbors and Decision Trees) to learn the user's preferences. Based on the learning results, new image generation requests are automatically generated periodically, and the server again sends these to the image generation AI. The newly generated images are sent to the device, which automatically updates the display on the high-definition display.

[0495] As an example, when a user first voice-inputs "I want to see summer scenery," this voice is converted into text data and sent to the server. The server extracts the request "summer scenery" from the text data and requests the image generation AI to generate "summer scenery." The generated image of the summer scenery is sent from the server to the device, which then displays it on a high-definition display.

[0496] The server also learns user trends by analyzing past request data. For example, if a user frequently requests "cherry blossom photos," the server will automatically create requests to periodically generate "new cherry blossom photos" and send them to the image generation AI. These new cherry blossom photos are sent to the device and automatically updated as content on the high-definition display. This allows users to constantly enjoy new images seamlessly.

[0497] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0498] Step 1:

[0499] The user inputs voice into the device. For example, if the user says, "I want to see pictures of seascapes," the device picks up this voice through the built-in microphone and saves it as voice data. The input of this step is the user's voice, and the output is voice data.

[0500] Step 2:

[0501] The device inputs the voice data into voice recognition software (e.g., a general voice recognition API) and converts it into text data. This conversion analyzes the sound wave signal as digital text and generates the string "I want to see pictures of seascapes." The input of this step is voice data, and the output is text data.

[0502] Step 3:

[0503] The terminal sends the generated text data to the server. The server receives this text data and analyzes it using a natural language processing tool (e.g., a general natural language processing library). In this analysis, the request "seascape" is extracted from the text data. The input of this step is the text data, and the output is the analyzed request data.

[0504] Step 4:

[0505] Based on the parsed request, the server sends an image generation request to an image generation AI (e.g., a general image generation model). Specifically, it sends a prompt to the generative AI model saying, "Please generate an image of a seascape." The input of this step is the parsed request data, and the output is a request to the generative AI.

[0506] Step 5:

[0507] The image generation AI generates an image based on the received prompt and sends the generated image data back to the server. The input to this step is the request to the generation AI, and the output is the image data.

[0508] Step 6:

[0509] The server receives the generated image data and sends it to the terminal. In this step, data is transferred over the network. The input is the image data, and the output is the transmission of the image data to the terminal.

[0510] Step 7:

[0511] The terminal displays the image data received from the server on a high-definition display. In this display process, the image data is passed to the display driver and displayed in a form that is visible to the user. The input of this step is the image data, and the output is the image displayed on the display.

[0512] Step 8:

[0513] The server stores the user's past requests and the history of generated images in a database and analyzes them using a machine learning algorithm. This analysis learns the user's preferences and automatically generates prompts for new image generation requests. The input of this step is the past request and image history data, and the output is the learned user preferences and new requests.

[0514] Step 9:

[0515] The server again sends an automatically generated new image generation request to the image generation AI, and the generated new image is sent to the terminal. The terminal receives this and periodically updates the content of the high-definition display. The input of this step is the automatically generated request and the generated image data, and the output is the updated display content on the display.

[0516] (Application example 1)

[0517] 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."

[0518] Conventional interior design systems require users to manually select images and display them on a screen, making it difficult to frequently update the atmosphere of a physical store. Additionally, there is a lack of technology to automatically generate and display appropriate images continuously based on user preferences.

[0519] 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.

[0520] In this invention, the server includes means for recognizing a user's voice input, means for converting the voice input into text data, means for analyzing the text data to extract a user's request, means for generating an image based on the extracted request, means for transmitting the generated image data to a high-definition display, means for displaying the transmitted image data on the high-definition display, means for analyzing past generated images and the user's request history to learn the user's preferences, means for automatically generating a new image generation request based on the user's preferences, means for transmitting an image generated based on the new image generation request to a terminal and automatically updating the display content, and means for displaying the generated image on a terminal with a high-definition display to provide customers of a physical store with a visual interior experience. This enables users to automatically generate and display interior designs that suit their preferences using only voice input, thereby continuously maintaining the atmosphere of the physical store fresh.

[0521] "User voice input" means verbal instructions or requests made by a User.

[0522] "Means for converting speech input into text data" refers to technology or devices that analyze speech signals and convert them into corresponding text.

[0523] "Text data" refers to character string data converted from speech.

[0524] "Means for extracting user requirements" refers to techniques and methods for identifying user intent and requests from converted text data.

[0525] "Means for generating images" refers to techniques or devices that create images by computer based on a user's request.

[0526] "Image data" refers to the digital data of the generated image.

[0527] "High definition display" refers to a display device capable of displaying images at high resolution.

[0528] "User request history" refers to a record of requests and instructions that a user has previously entered into the system.

[0529] "Means for learning user preferences" refers to technologies and methods for analyzing user preferences and trends based on past request history.

[0530] "Means for automatically generating new image generation requests" refers to techniques or methods by which the system automatically generates new image generation instructions based on user preferences.

[0531] A "physical store" refers to a commercial facility or service location that has a specific physical space.

[0532] "Interior experience" refers to the experience of the visual design and decoration of an indoor space.

[0533] This invention is a system that recognizes a user's voice input, converts it into text data, and analyzes the user's requests. Specifically, this system generates images based on the user's preferences and displays them on a high-definition display. It also learns from past request history, automatically makes new image generation requests, and periodically updates the displayed content.

[0534] System configuration and programs

[0535] Hardware:

[0536] Microphone: A device that captures the user's voice input.

[0537] High-definition display: A device that displays the generated images.

[0538] Edge device: A device that performs some of the processing for voice recognition and image generation.

[0539] software:

[0540] Speech recognition technology (speech_recognition library): A library for converting voice input into text data.

[0541] Image generation AI (access API using the requests library): An AI model for generating images based on text data.

[0542] Image processing library (Pillow): A library for processing and displaying acquired image data.

[0543] History database: A database to store past requests and generated images and learn user preferences.

[0544] Processing Details

[0545] When a user speaks into the microphone, the server captures the voice and converts it into text data using voice recognition technology. For example, if a user says, "I want to display summer scenery, but I like pictures of the beach," the voice data is converted into text data saying, "I want to display summer scenery, but I like pictures of the beach."

[0546] The server then analyzes this text data and extracts user requests such as "summer scenery" or "beach photos." Once the request is extracted, the server sends a prompt to the image generation AI. An example of this prompt is "Please generate an image of a summer beach scenery that matches the interior of a cafe."

[0547] The image generation AI generates an appropriate image based on this prompt and returns the image data to the server. The server then sends the received image data to a high-definition display, where the image is displayed on the physical store's terminal. By analyzing past generated images and the user's request history, the AI ​​learns the user's preferences and automatically makes new image generation requests. The newly generated images are also displayed on the high-definition display, allowing the store's atmosphere to be constantly updated.

[0548] For example, if a cafe owner says, "I want to display a summer scene, but I like beach photos," the system will send a prompt to the generative AI model based on that request, and the generated beach image will be displayed on the cafe's high-definition display. An example of this prompt would be, "Please generate a summer beach scene image that matches the cafe's interior." This saves users the trouble of manually selecting an image, allowing them to easily change the atmosphere of their store.

[0549] As a whole, the system allows users to use voice input to automatically generate interior designs that suit their preferences, providing a visual interior experience in a physical store.

[0550] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0551] Step 1:

[0552] The user provides voice input. The user speaks into the microphone and inputs a request such as, "I want to display a painting that matches my room, and I like paintings of flowers."

[0553] Input: User's voice.

[0554] Output: Audio data.

[0555] Step 2:

[0556] The server receives audio data from the microphone and converts it into text using speech recognition technology. Specifically, it uses the speech_recognition library.

[0557] Input: Audio data.

[0558] Output: Text data (e.g. "I want to display paintings that suit my room, and I like paintings of flowers.").

[0559] Step 3:

[0560] The server analyzes the text data and extracts the user's request using natural language processing to identify the request.

[0561] Input: Text data.

[0562] Output: Request data (e.g. "A painting that suits the room", "A painting of flowers").

[0563] Step 4:

[0564] Based on the extracted request, the server creates a prompt and sends it to the image generation AI model. Example prompt: "Please generate a painting of a flower."

[0565] Input: Request data.

[0566] Output: A prompt statement (e.g., "Generate a painting of a flower.").

[0567] Step 5:

[0568] The image generation AI model generates an image based on the prompt text. The server sends a request to the image generation API and receives the generated image data.

[0569] Input: Prompt statement.

[0570] Output: Image data.

[0571] Step 6:

[0572] The server transmits the received image data to the high-definition display. Specifically, the image data is transferred through the interface of the display device.

[0573] Input: Image data.

[0574] Output: Preparing image data for display.

[0575] Step 7:

[0576] The terminal displays the image on a high-definition display. The display device receives the image data and displays it for the user to visually confirm.

[0577] Input: Image data to be displayed on the display.

[0578] Output: Image displayed on a high definition display.

[0579] Step 8:

[0580] The server analyzes past generated images and user request history to learn user preferences. It identifies user preferences using data stored in a history database.

[0581] Input: Previously generated images, user request history.

[0582] Output: Data about user preferences.

[0583] Step 9:

[0584] The server automatically generates new image generation requests based on the user's preferences, which are sent to the generation AI as prompts that are periodically updated.

[0585] Input: Data about the user's preferences.

[0586] Output: A new image generation request (e.g. "Flower Painting").

[0587] Step 10:

[0588] The server then sends the image generated based on the new image generation request to the high-definition display again, automatically updating the display content.

[0589] Input: Image data generated based on a new image generation request.

[0590] Output: Updated display content.

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

[0592] This system recognizes user voice input, converts the voice into text data, and extracts and recognizes the user's requests through analysis. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it has the ability to generate and select images based on the user's emotions. This allows for a more personalized user experience.

[0593] Program processing

[0594] 1. Acquiring and Recognizing Voice Input

[0595] The user speaks into the device, and the device uses voice recognition software to convert the voice data into text data. For example, if the user says, "I'm feeling sad today," the device converts this into text data: "I'm feeling sad today."

[0596] 2. Analyzing text data and extracting requirements

[0597] The terminal transmits the converted text data to the server.

[0598] The server analyzes the text data and extracts the user's request (e.g., "feeling sad").

[0599] 3. Emotional Recognition

[0600] The server uses an emotion engine to recognize emotions from the user's voice. For example, if the text data is analyzed as "feeling sad," the server recognizes the user's emotion as "sad."

[0601] 4. Select or generate an image

[0602] Based on the recognized emotion, the server sends a request to an image generation AI or selects an appropriate image from an existing image database. For example, if the user is in a sad mood, it will generate or select a calm and soothing image.

[0603] 5. Image data transmission and display

[0604] The server transmits the generated or selected image data to the terminal, which displays the image on a high-definition display.

[0605] 6. Learning user preferences and emotional patterns

[0606] The server analyzes past generated images, user request history, and recognized emotional patterns to learn the user's preferences and emotional patterns, thereby understanding which images tend to be preferred when the user is in a particular emotional state.

[0607] 7. Automatically generate and update new image generation requests

[0608] The server automatically generates new image generation requests based on the user's preferences and emotional patterns. For example, if a user has previously preferred a particular type of image that has a soothing effect when they felt sad, the server will create a request to automatically generate that type of image.

[0609] 8. Create and send a new image

[0610] The image generation AI generates a new image and returns the image data to the server. The server then sends the new image data to the device, which then automatically updates the content displayed on the high-definition display.

[0611] Specific examples

[0612] For example, if a user says, "I want to display a painting that suits my room, but I'm feeling down today," the device converts the voice data into text data saying, "I want to display a painting that suits my room, but I'm feeling down today," and sends it to the server. The server analyzes this and extracts the emotion "down." The emotion engine recognizes this as a "depressed mood" and sends a request to the image generation AI to generate an image with a soothing theme. The generated image is sent from the server to the device, which then displays it on a high-definition display.

[0613] The server then learns from this request history, generated images, and recognized emotions to understand the image preferences of users when they are in a particular emotional state. From then on, the next time the user is in a similar emotional state, the server can automatically generate and display the image the user prefers, providing a more personalized user experience.

[0614] The processing flow will be explained below.

[0615] Step 1:

[0616] The user speaks into the device, for example, saying, "I'm feeling sad today. I want to see pictures that will lift my spirits."

[0617] Step 2:

[0618] The device picks up the user's voice through a microphone and uses voice recognition software to convert the voice data into text data. Specifically, the speech "I'm feeling sad today. I want to see pictures that will lift my spirits" is converted into text data "I'm feeling sad today. I want to see pictures that will lift my spirits."

[0619] Step 3:

[0620] The terminal sends the converted text data to the server via a network using a communication protocol.

[0621] Step 4:

[0622] The server analyzes the received text data and extracts the user's request, for example, extracting keywords such as "sad mood" and "pictures that lift your spirits."

[0623] Step 5:

[0624] The server uses an emotion engine to recognize emotions from the user's voice. For example, if the text data is analyzed as "feeling sad," the server recognizes the user's emotion as "sad."

[0625] Step 6:

[0626] The server sends an image generation request to the image generation AI based on the extracted keywords and the recognized emotions. Specifically, it sends a request to "generate a soothing image to lift the mood."

[0627] Step 7:

[0628] The image generation AI generates an image based on the specified request, for example, generating a vivid and uplifting image of a flower, and returns the image data to the server.

[0629] Step 8:

[0630] The server receives the generated image data and sends it to the terminal via the network using a communication protocol.

[0631] Step 9:

[0632] The image data received by the terminal is displayed on a high-definition display. The terminal's display control software processes the image data and displays it on the display.

[0633] Step 10:

[0634] The server analyzes previously generated images, user request history, and recognized emotional patterns to learn user preferences and emotional patterns, thereby understanding which images users tend to like for specific emotional states.

[0635] Step 11:

[0636] The server automatically generates new image generation requests based on the user's preferences and emotional patterns it has learned. For example, if a user has previously preferred a particular type of image that has a soothing effect when they felt sad, it will send a request to the image generation AI to automatically generate that type of image.

[0637] Step 12:

[0638] The image generation AI generates a new image and returns the image data to the server, which then sends the new image data it receives to the device.

[0639] Step 13:

[0640] New image data received by the device is automatically updated and displayed on the high-definition display, allowing users to enjoy constantly updated interior designs.

[0641] Example 2

[0642] 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."

[0643] Conventional voice recognition systems only convert a user's voice input into text data, making it difficult to generate appropriate responses based on the user's emotions or specific requests. Furthermore, there is no system that dynamically generates or selects and displays images based on the user's emotions, limiting the user experience. This invention aims to provide a more personalized user experience by focusing on user emotion recognition and image generation based on those emotions.

[0644] 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.

[0645] In this invention, the server includes a means for recognizing user emotions from text data, a means for generating images based on an image generation artificial intelligence model, and a means for analyzing past generated images and the user's request history to learn the user's preferences, thereby enabling the server to generate, select, and provide appropriate and personalized images based on the emotions and requests extracted from the user's voice input.

[0646] "User" refers to any person or entity that uses this system.

[0647] "Voice input" refers to voice data uttered by a user.

[0648] "Text data" refers to data converted from voice input into a string of characters.

[0649] "Emotion" refers to information that indicates the user's internal emotional state.

[0650] "Image" refers to digital data containing visual information.

[0651] "Generation" refers to the act of the system creating new data.

[0652] "Display" refers to the act of projecting a generated or selected image onto a terminal display.

[0653] "High-definition display" refers to a device that displays images and information in high resolution.

[0654] "Server" refers to a central computer system that processes and stores data.

[0655] "Terminal" refers to a device that is directly operated by a user.

[0656] "Requests" refer to the wishes and requirements that users have for the system.

[0657] "Image generation artificial intelligence model" refers to algorithms and programs that generate images using AI technology.

[0658] "Recognition" refers to the act of a system understanding and making sense of data.

[0659] "Analysis" refers to the process of examining data in detail and extracting meaning.

[0660] "Learning" refers to the process of extracting trends and patterns from past data and using them to predict and respond to the future.

[0661] "Transmitting" refers to the act of transferring data from one point to another.

[0662] The present invention provides a system that recognizes a user's voice input, converts it into text data, analyzes it, and extracts emotions and requests. This system generates or selects and displays images according to the user's emotions, thereby achieving a highly personalized user experience. Specific embodiments are described below.

[0663] Acquiring and recognizing voice input

[0664] The user speaks into the device, and the device uses the built-in microphone to capture the voice and collects the voice data, which is then converted into text data using speech recognition software (e.g., Google's speech recognition API).

[0665] Analyzing text data and extracting requirements

[0666] The device transmits the converted text data to the server, which then uses a natural language processing engine (e.g., spaCy) to analyze the text data and extract the user's request and emotion. For example, from the text data "I'm feeling sad today," it identifies the emotion "sad" and the request "I'm feeling bad."

[0667] Emotion recognition

[0668] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's text data. In this way, the server specifically grasps the user's internal emotional state (e.g., "sad," "happy," etc.).

[0669] Select or generate an image

[0670] Based on the recognized emotion, the server generates an image using an image generation artificial intelligence model (e.g., OpenAI's DALL-E) or selects an appropriate image from an existing image database (e.g., Pexels or Unsplash). For example, when the user is in a "sad" mood, it provides calming and soothing images.

[0671] Image data transmission and display

[0672] The server sends the generated or selected image data to the device, which then displays the received image data on a high-definition display, allowing the user to view an image that matches their emotions.

[0673] Learning user preferences and emotional patterns

[0674] The server analyzes past generated images, the user's request history, and recognized emotional patterns. It uses machine learning algorithms (e.g., TensorFlow) to learn the user's preferences and emotional patterns. This allows it to generate or select the most appropriate image for similar emotional states in the future.

[0675] Automatically generate and update new image generation requests

[0676] The server automatically generates new image generation requests based on the user's preferences and emotional patterns. For example, it generates new prompts from specific types of image data that the user prefers when feeling sad. This ensures that images that match the user's emotions are always provided.

[0677] Specific examples

[0678] For example, consider the case where a user says to the device, "I want to display a painting that suits my room, but I'm feeling down today." The device converts this speech into text data using a speech recognition API and sends it to the server. The server extracts the emotion "down" and uses its emotion engine to recognize it as "depressed mood." Based on this emotion, it sends a prompt to the image generation AI model to "generate an image with a soothing theme." The generated image is sent from the server to the device and displayed on the device's high-definition display. The next time the user expresses a similar emotion, the system will provide the most appropriate image based on its past learning results.

[0679] This system enables dynamic image generation and display according to the user's emotions, providing a personalized, high-quality user experience.

[0680] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0681] Step 1:

[0682] Acquiring and recognizing voice input

[0683] The user inputs voice into the terminal.

[0684] Example: "I feel sad today."

[0685] The device captures voice data through the microphone and converts this voice data into text data using voice recognition software (for example, Google's voice recognition API).

[0686] Input: Audio data

[0687] Data processing: Speech-to-text conversion using speech recognition API

[0688] Output: Text data "I feel sad today"

[0689] Specific operation: recognizer.recognize_google(audio_data)

[0690] Step 2:

[0691] Analyzing text data and extracting requirements

[0692] The terminal transmits the text data to the server.

[0693] Input: Text data

[0694] Output: Sends text data to the server

[0695] Specific behavior: requests.post(server_url, json={"text": "I'm feeling sad today"})

[0696] The server analyzes the received text data using a natural language processing engine (e.g., spaCy) to extract the user's requests and sentiments.

[0697] Input: Text data

[0698] Data Calculation: Analysis and request extraction using a natural language processing engine

[0699] Output: Request "I feel bad" and emotion "Sad"

[0700] Specific behavior: nlp = spacy.load("ja_core_news_sm"), doc = nlp("I'm feeling sad today")

[0701] Step 3:

[0702] Emotion recognition

[0703] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion from the text data.

[0704] Input: Extracted text data

[0705] Data Computation: Emotion Recognition with Emotion Engine

[0706] Output: Recognized emotion "sad"

[0707] Specific behavior: tone_analyzer.tone({"text": "I'm feeling sad today"}, content_type="application / json")

[0708] Step 4:

[0709] Select or generate an image

[0710] Based on the recognized emotion, the server requests an image generation AI model (e.g., OpenAI's DALL-E) to generate an image, or selects an appropriate image from an existing image database (e.g., Pexels or Unsplash).

[0711] Input: Recognized emotion "sad"

[0712] Data operation: Image generation request or image selection

[0713] Output: Generated or selected image

[0714] Specific behavior: response = openai.Image.create(prompt="calming scenery", num_images=1) or search_results = pexels_api.search("calming scenery")

[0715] Step 5:

[0716] Image data transmission and display

[0717] The server transmits the generated or selected image data to the terminal.

[0718] Input: Image data

[0719] Output: Send image data to the device

[0720] Specific behavior: requests.post(client_url, json={"image_url": image_url})

[0721] The terminal displays the received image on a high-definition display.

[0722] Input: Received image data

[0723] Output: Display images on a high-definition display

[0724] Specific behavior: display_image(image_url)

[0725] Step 6:

[0726] Learning user preferences and emotional patterns

[0727] The server analyzes past generated images, the user's request history, and recognized emotional patterns to learn the user's preferences and emotional patterns.

[0728] Input: Previously generated images, request history, emotion patterns

[0729] Data Computing: Analysis and learning using machine learning algorithms

[0730] Output: Updated user preferences and sentiment patterns

[0731] Specific behavior: user_preferences.update({"mood": "sad", "liked_images": [image_url]}), model.fit(history_data, preferences_data)

[0732] Step 7:

[0733] Automatically generate and update new image generation requests

[0734] The server automatically generates new image generation requests based on learned user preferences and emotional patterns.

[0735] Input: Learned user preferences and emotional patterns

[0736] Data Calculation: New Prompt Generation

[0737] Output: Auto-generated image request

[0738] Specific behavior: auto_prompt = generate_prompt(user_preferences)

[0739] Step 8:

[0740] Generate and send a new image

[0741] The image generation artificial intelligence model generates a new image and returns the image data to the server.

[0742] Input: A new image generation request

[0743] Data computation: Image generation using generative AI models

[0744] Output: New image data

[0745] Specific behavior: response = openai.Image.create(prompt=auto_prompt, num_images=1)

[0746] The server transmits the received new image data to the terminal.

[0747] Input: New image data

[0748] Output: Send image data to the device

[0749] Specific behavior: requests.post(client_url, json={"image_url": new_image_url})

[0750] The device will display new images on its high-definition display and automatically refresh the display.

[0751] Input: New image data

[0752] Output: Display images on a high-definition display

[0753] Specific operation: display_image(new_image_url)

[0754] (Application example 2)

[0755] 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."

[0756] Conventional voice input systems often simply analyze user requests as text data and provide static responses. This makes it difficult to provide a truly personalized experience because they do not reflect the user's emotional state. Furthermore, they lack the ability to learn user preferences and automatically provide optimal content. In many settings, particularly brick-and-mortar stores, where information provision based on user emotions and preferences is required, there is a demand for improved customer satisfaction.

[0757] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing a user's emotion, means for selecting or generating an image based on the extracted request and emotion, and means for transmitting the generated image data to a high-definition display. This makes it possible to provide personalized images and information based on the user's emotion, thereby improving the user experience and increasing customer satisfaction.

[0758] "Voice input" refers to voice data emitted by the user, and this data is used by the system to detect operations and requests.

[0759] "Text data" refers to data of character information obtained by analyzing voice input.

[0760] "User requests" are specific requests or instructions given by users to the system.

[0761] "Emotions" represent the user's psychology and mental state, and are analyzed and recognized by the system.

[0762] "Selecting or generating an image" refers to choosing an appropriate image from an existing image database or generating a new image based on the user's requirements or emotions.

[0763] "High definition display" means a display device having a high resolution that presents a generated or selected image to a user.

[0764] "User preferences" refers to the user's individual tendencies and likes learned through past generated images and request history.

[0765] "Image Generation Request" means instructions or commands for generating a new image based on the user's needs or emotions.

[0766] A "terminal" is a device used by a user, typically hardware such as a smartphone or smart glasses.

[0767] "Automatic updating" means that the system replaces the displayed content with new content based on user input and history, without manual intervention.

[0768] This invention comprises a system that utilizes a user's voice input, analyzes the user's requests and emotions based on the voice input, and generates or selects appropriate images. A specific method for realizing this system is described below.

[0769] First, the user speaks into a device such as a smartphone or smart glasses. The voice input is picked up through the device's microphone and converted into text data using speech recognition software. This process is performed using a library called SpeechRecognition, for example.

[0770] The converted text data is then sent to a server, which analyzes the text data and extracts the user's request and emotion. This analysis uses natural language processing techniques such as the Transformers library. Emotion recognition uses an emotion engine to analyze the user's mental state.

[0771] Based on the extracted needs and emotions, the server then sends a generation request to an image generation AI model or selects an appropriate image from an existing image database, such as DALL-E or Midjourney.

[0772] The generated or selected image data is sent from the server to the device and displayed on the device's high-definition display. This image data is then automatically generated based on the user's preferences and request history. By learning the user's preferences, more appropriate and personalized images are provided when a similar request occurs again.

[0773] Specific examples

[0774] For example, if a user says to their smartphone, "I'm a little tired today, so I'm looking for a product that will help me relax," the device converts this speech into text data, "I'm a little tired today, so I'm looking for a product that will help me relax," and sends it to the server. The server analyzes this text data and recognizes the user's emotion as "fatigue." Next, based on the emotion, it generates or selects a product image that has a relaxing effect. In this case, the prompt text used is "relaxation, fatigue."

[0775] Finally, the selected or generated image data is displayed on the smartphone's high-definition display, and appropriate products are presented according to the user's request.

[0776] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0777] Step 1:

[0778] A user speaks into a device such as a smartphone or smart glasses. Specifically, the voice data is acquired through a microphone. The input is the user's voice, and the output is the acquired voice data.

[0779] Step 2:

[0780] The device receives the voice data and converts it into text data using voice recognition software, such as a library called SpeechRecognition, which takes voice data as input and outputs text data as the result.

[0781] Step 3:

[0782] The terminal sends the converted text data to the server. The input is the text data, and the output is a transmission completion notification to the server.

[0783] Step 4:

[0784] The server analyzes the received text data and extracts the user's requests and emotions. This analysis uses natural language processing techniques such as the Transformers library. The input is text data, and the output is the analyzed user's requests and emotions.

[0785] Step 5:

[0786] The server performs emotion recognition and analyzes the user's emotional state using an emotion engine. For example, emotions such as fatigue and joy are recognized. The input is text data, and the output is the recognized emotion.

[0787] Step 6:

[0788] Based on the extracted request and emotion, the server sends a generation request to an image generation AI model or selects an appropriate image from an existing image database. Examples of image generation AI models used include DALL-E and Midjourney. The input is request and emotion data, and the output is the generated or selected image data.

[0789] Step 7:

[0790] The generated or selected image data is sent from the server to the terminal. The input is the image data, and the output is a notification that the image data has been sent.

[0791] Step 8:

[0792] The terminal receives the transmitted image data and displays it on a high-definition display. The input is the image data, and the output is the image displayed on the display.

[0793] Step 9:

[0794] The server analyzes the past generated images and the user's request history and executes a process to learn the user's preferences. The input is the past generated images and the request history, and the output is the learned user preference data.

[0795] Step 10:

[0796] The server automatically generates new image generation requests based on the learned user preferences and recognized emotions. The input is preference data and emotion data, and the output is a new image generation request.

[0797] Step 11:

[0798] The image data generated based on the new image generation request is sent to the terminal again, and the display content is automatically updated. The input is the new image data, and the output is the updated display.

[0799] This series of processes realizes a system that provides a personalized experience according to the user's emotions.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] [Third embodiment]

[0804] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0805] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0806] 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).

[0807] 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.

[0808] 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.

[0809] 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).

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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."

[0816] The system recognizes user voice input, converts the voice input into text data, analyzes the user's requests, and generates images based on the text. It also transmits the generated images to a high-definition display for display, learns the user's past request history, and automatically generates new image generation requests based on the user's preferences, periodically updating the displayed content.

[0817] Program processing

[0818] 1. Acquiring and Recognizing Voice Input

[0819] When a user speaks into the device, the device uses voice recognition technology to convert this into text data.

[0820] For example, if a user says, "I like ocean scenery. I'd like to see pictures of sunsets too," the device converts this voice data into text data saying, "I like ocean scenery. I'd like to see pictures of sunsets too."

[0821] 2. Analyzing text data and extracting requirements

[0822] The terminal transmits the text data to the server.

[0823] The server analyzes the text data and extracts the user's request (e.g., "seascape," "sunset").

[0824] 3. Image Generation

[0825] The server sends a request to the image generation AI based on the extracted requirements.

[0826] Based on the request, the image generation AI generates images of seascapes and sunsets and returns the data to the server.

[0827] 4. Image data transmission and display

[0828] The server transmits the generated image data to the terminal, which then displays the image on a high-definition display.

[0829] 5. Learning your preferences

[0830] The server analyzes past generated images and the user's request history to learn the user's preferences.

[0831] 6. Automatically generate and update new images

[0832] The server automatically creates a new image generation request based on the user's preferences and sends it to the image generation AI.

[0833] The new image generated is sent to the terminal, which automatically updates the display on the high-definition display.

[0834] Specific examples

[0835] For example, suppose the user first says, "I want to display a painting that suits my room, and I like paintings of flowers." This voice input is converted into text data and sent to the server. The server extracts the request, "I like paintings of flowers," from the text data and sends a request to the image generation AI to generate a painting of a flower. The generated image of the flower is sent from the server to the device and displayed on the device's high-definition display.

[0836] The server then learns from this request history and recognizes that the user's preference is flower images. After a few weeks, the server sends a request to the AI ​​to automatically generate new flower images based on the user's preferences. The generated new flower images are then sent to the device, automatically updating the content on the high-definition display. This process allows the user to enjoy their new interior without any hassle.

[0837] This system allows users to easily change the atmosphere of their interior by displaying paintings and posters that suit their tastes on a high-definition display. It also learns from past requests and automatically generates and updates new images, providing a fresh and appealing interior experience for users.

[0838] The processing flow will be explained below.

[0839] Step 1:

[0840] The user speaks to the device, for example, "I like seascapes. I'd like to see pictures of sunsets too."

[0841] Step 2:

[0842] The device picks up the user's voice through a microphone and uses voice recognition software to convert the voice data into text data. Specifically, the speech "I like seascapes. I'd like to see pictures of sunsets, too" is converted into text data "I like seascapes. I'd like to see pictures of sunsets, too."

[0843] Step 3:

[0844] The terminal sends the converted text data to the server. Using a communication protocol, the text data is sent to the server via the network.

[0845] Step 4:

[0846] The server analyzes the received text data and extracts the user's request. For example, it extracts keywords such as "seascape" and "sunset" from the text data.

[0847] Step 5:

[0848] The server sends image generation requests to the image generation AI based on the extracted keywords. Specifically, it sends requests such as "generate an image of a seascape" and "generate an image of a sunset."

[0849] Step 6:

[0850] The image generation AI generates an image based on the specified keywords, for example, a beautiful seascape or sunset image, and returns the image data to the server.

[0851] Step 7:

[0852] The server receives the generated image data and sends it to the terminal via a communication protocol over the network.

[0853] Step 8:

[0854] The image data received by the terminal is displayed on a high-definition display. The terminal's display control software processes the image data and displays it on the display.

[0855] Step 9:

[0856] The server analyzes previously generated images and the user's request history to learn the user's preferences, for example, that they like "seascapes" and "sunsets."

[0857] Step 10:

[0858] The server automatically generates new image generation requests based on the user's preferences. For example, it creates a new "seascape" or "sunset" image generation request and sends it to the image generation AI.

[0859] Step 11:

[0860] The image generation AI generates a new image and returns the image data to the server, which then sends the new image data it receives to the device.

[0861] Step 12:

[0862] New image data received by the device is automatically updated and displayed on the high-definition display, allowing users to enjoy constantly updated interior designs.

[0863] Example 1

[0864] 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."

[0865] In conventional image generation systems, users must manually input image generation requests each time, and they lack a mechanism for automatically considering user preferences and past request history. As a result, it takes a lot of effort for users to continuously enjoy new images, resulting in a lack of usability. In addition, the displayed content of generated images is not regularly updated, which can lead to user boredom.

[0866] 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.

[0867] In this invention, the server includes means for recognizing a user's voice input, means for converting the voice input into text data, means for analyzing the text data to extract a user's request, means for sending a request to input an image to a generative AI model based on the extracted request, means for receiving image data generated from the generative AI model, means for sending the received image data to a high-definition display, means for displaying the sent image data on the high-definition display, means for analyzing past generated images and the user's request history to learn the user's preferences, means for automatically generating a new image generation request based on the user's preferences, and means for sending an image generated based on the new image generation request to the terminal and automatically updating the display content. This allows the user to continuously enjoy new images that suit their preferences without any hassle.

[0868] "User" refers to an individual who utilizes the system to provide voice input and view the resulting image generation and display.

[0869] "Means for recognizing voice input" refers to technical devices or software that capture and interpret the voice uttered by the user as a digital signal.

[0870] "Means for converting speech input into text data" refers to digital processing technology or software that converts recognized speech into written form.

[0871] "Means for analyzing text data to extract user requirements" refers to processing technology or software that analyzes text data and finds out the user's intended requirements or wishes from within it.

[0872] "Means for sending a request to input an image into a generative AI model" refers to a technical device or software that sends a request to an artificial intelligence model that generates an image based on the extracted request.

[0873] "Means for receiving image data generated from a generative AI model" refers to a processing technology or device that receives image data generated by an image-generating AI model.

[0874] "High-definition display" refers to a display device that can display detailed images and videos at high resolution.

[0875] "Means for displaying the transmitted image data on a high definition display" refers to technical devices or software that transmit and display the generated image data on a high definition display.

[0876] "Means for learning user preferences by analyzing past generated images and user request history" refers to technical devices or software that analyze past image generation history and user request history to learn user preferences and tendencies.

[0877] "Means for automatically generating new image generation requests" refers to technical devices or software that automatically generate requests for new image generation based on learned user preferences.

[0878] "Means for automatically updating the display content" refers to technical devices or software that periodically or automatically update the display content of a high-definition display with newly generated images.

[0879] This invention is a system that recognizes and analyzes a user's voice input, and generates and displays an image based on the analysis results. This system specifically uses the following technical means.

[0880] First, the user speaks to the device. For example, if the user says, "I want to see a picture of a flower," the device receives the voice input through the built-in microphone. The device uses voice recognition software, such as the Google Cloud Speech-to-Text API, to convert the captured voice data into text data.

[0881] The device then sends the generated text data to the server, which then uses natural language processing tools (e.g., spaCy or NLTK) to analyze the user's request. Based on this analysis, the server extracts the user's specific request (e.g., "flower picture").

[0882] Based on the extracted requirements, the server sends an image generation request to an image generation AI (e.g., OpenAI's DALL·E or Stability AI's Stable Diffusion). Specific examples of prompts include "Generate a picture of a flower" or "Generate a new flower picture that matches the user's preferences."

[0883] The image data generated by the image generation AI is sent back to the server, which then receives the data and sends it to the device, which then displays it on a high-definition display.

[0884] Furthermore, the server stores the past generated images and request history in a database and analyzes them using machine learning algorithms (e.g., K-Nearest Neighbors and Decision Trees) to learn the user's preferences. Based on the learning results, new image generation requests are automatically generated periodically, and the server again sends these to the image generation AI. The newly generated images are sent to the device, which automatically updates the display on the high-definition display.

[0885] As an example, when a user first voice-inputs "I want to see summer scenery," this voice is converted into text data and sent to the server. The server extracts the request "summer scenery" from the text data and requests the image generation AI to generate "summer scenery." The generated image of the summer scenery is sent from the server to the device, which then displays it on a high-definition display.

[0886] The server also learns user trends by analyzing past request data. For example, if a user frequently requests "cherry blossom photos," the server will automatically create requests to periodically generate "new cherry blossom photos" and send them to the image generation AI. These new cherry blossom photos are sent to the device and automatically updated as content on the high-definition display. This allows users to constantly enjoy new images seamlessly.

[0887] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0888] Step 1:

[0889] The user inputs voice into the device. For example, if the user says, "I want to see pictures of seascapes," the device picks up this voice through the built-in microphone and saves it as voice data. The input of this step is the user's voice, and the output is voice data.

[0890] Step 2:

[0891] The device inputs the voice data into voice recognition software (e.g., a general voice recognition API) and converts it into text data. This conversion analyzes the sound wave signal as digital text and generates the string "I want to see pictures of seascapes." The input of this step is voice data, and the output is text data.

[0892] Step 3:

[0893] The terminal sends the generated text data to the server. The server receives this text data and analyzes it using a natural language processing tool (e.g., a general natural language processing library). In this analysis, the request "seascape" is extracted from the text data. The input of this step is the text data, and the output is the analyzed request data.

[0894] Step 4:

[0895] Based on the parsed request, the server sends an image generation request to an image generation AI (e.g., a general image generation model). Specifically, it sends a prompt to the generative AI model saying, "Please generate an image of a seascape." The input of this step is the parsed request data, and the output is a request to the generative AI.

[0896] Step 5:

[0897] The image generation AI generates an image based on the received prompt and sends the generated image data back to the server. The input to this step is the request to the generation AI, and the output is the image data.

[0898] Step 6:

[0899] The server receives the generated image data and sends it to the terminal. In this step, data is transferred over the network. The input is the image data, and the output is the transmission of the image data to the terminal.

[0900] Step 7:

[0901] The terminal displays the image data received from the server on a high-definition display. In this display process, the image data is passed to the display driver and displayed in a form that is visible to the user. The input of this step is the image data, and the output is the image displayed on the display.

[0902] Step 8:

[0903] The server stores the user's past requests and the history of generated images in a database and analyzes them using a machine learning algorithm. This analysis learns the user's preferences and automatically generates prompts for new image generation requests. The input of this step is the past request and image history data, and the output is the learned user preferences and new requests.

[0904] Step 9:

[0905] The server again sends an automatically generated new image generation request to the image generation AI, and the generated new image is sent to the terminal. The terminal receives this and periodically updates the content of the high-definition display. The input of this step is the automatically generated request and the generated image data, and the output is the updated display content on the display.

[0906] (Application example 1)

[0907] 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."

[0908] Conventional interior design systems require users to manually select images and display them on a screen, making it difficult to frequently update the atmosphere of a physical store. Additionally, there is a lack of technology to automatically generate and display appropriate images continuously based on user preferences.

[0909] 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.

[0910] In this invention, the server includes means for recognizing a user's voice input, means for converting the voice input into text data, means for analyzing the text data to extract a user's request, means for generating an image based on the extracted request, means for transmitting the generated image data to a high-definition display, means for displaying the transmitted image data on the high-definition display, means for analyzing past generated images and the user's request history to learn the user's preferences, means for automatically generating a new image generation request based on the user's preferences, means for transmitting an image generated based on the new image generation request to a terminal and automatically updating the display content, and means for displaying the generated image on a terminal with a high-definition display to provide customers of a physical store with a visual interior experience. This enables users to automatically generate and display interior designs that suit their preferences using only voice input, thereby continuously maintaining the atmosphere of the physical store fresh.

[0911] "User voice input" means verbal instructions or requests made by a User.

[0912] "Means for converting speech input into text data" refers to technology or devices that analyze speech signals and convert them into corresponding text.

[0913] "Text data" refers to character string data converted from speech.

[0914] "Means for extracting user requirements" refers to techniques and methods for identifying user intent and requests from converted text data.

[0915] "Means for generating images" refers to techniques or devices that create images by computer based on a user's request.

[0916] "Image data" refers to the digital data of the generated image.

[0917] "High definition display" refers to a display device capable of displaying images at high resolution.

[0918] "User request history" refers to a record of requests and instructions that a user has previously entered into the system.

[0919] "Means for learning user preferences" refers to technologies and methods for analyzing user preferences and trends based on past request history.

[0920] "Means for automatically generating new image generation requests" refers to techniques or methods by which the system automatically generates new image generation instructions based on user preferences.

[0921] A "physical store" refers to a commercial facility or service location that has a specific physical space.

[0922] "Interior experience" refers to the experience of the visual design and decoration of an indoor space.

[0923] This invention is a system that recognizes a user's voice input, converts it into text data, and analyzes the user's requests. Specifically, this system generates images based on the user's preferences and displays them on a high-definition display. It also learns from past request history, automatically makes new image generation requests, and periodically updates the displayed content.

[0924] System configuration and programs

[0925] Hardware:

[0926] Microphone: A device that captures the user's voice input.

[0927] High-definition display: A device that displays the generated images.

[0928] Edge device: A device that performs some of the processing for voice recognition and image generation.

[0929] software:

[0930] Speech recognition technology (speech_recognition library): A library for converting voice input into text data.

[0931] Image generation AI (access API using the requests library): An AI model for generating images based on text data.

[0932] Image processing library (Pillow): A library for processing and displaying acquired image data.

[0933] History database: A database to store past requests and generated images and learn user preferences.

[0934] Processing Details

[0935] When a user speaks into the microphone, the server captures the voice and converts it into text data using voice recognition technology. For example, if a user says, "I want to display summer scenery, but I like pictures of the beach," the voice data is converted into text data saying, "I want to display summer scenery, but I like pictures of the beach."

[0936] The server then analyzes this text data and extracts user requests such as "summer scenery" or "beach photos." Once the request is extracted, the server sends a prompt to the image generation AI. An example of this prompt is "Please generate an image of a summer beach scenery that matches the interior of a cafe."

[0937] The image generation AI generates an appropriate image based on this prompt and returns the image data to the server. The server then sends the received image data to a high-definition display, where the image is displayed on the physical store's terminal. By analyzing past generated images and the user's request history, the AI ​​learns the user's preferences and automatically makes new image generation requests. The newly generated images are also displayed on the high-definition display, allowing the store's atmosphere to be constantly updated.

[0938] For example, if a cafe owner says, "I want to display a summer scene, but I like beach photos," the system will send a prompt to the generative AI model based on that request, and the generated beach image will be displayed on the cafe's high-definition display. An example of this prompt would be, "Please generate a summer beach scene image that matches the cafe's interior." This saves users the trouble of manually selecting an image, allowing them to easily change the atmosphere of their store.

[0939] As a whole, the system allows users to use voice input to automatically generate interior designs that suit their preferences, providing a visual interior experience in a physical store.

[0940] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0941] Step 1:

[0942] The user provides voice input. The user speaks into the microphone and inputs a request such as, "I want to display a painting that matches my room, and I like paintings of flowers."

[0943] Input: User's voice.

[0944] Output: Audio data.

[0945] Step 2:

[0946] The server receives audio data from the microphone and converts it into text using speech recognition technology. Specifically, it uses the speech_recognition library.

[0947] Input: Audio data.

[0948] Output: Text data (e.g. "I want to display paintings that suit my room, and I like paintings of flowers.").

[0949] Step 3:

[0950] The server analyzes the text data and extracts the user's request using natural language processing to identify the request.

[0951] Input: Text data.

[0952] Output: Request data (e.g. "A painting that suits the room", "A painting of flowers").

[0953] Step 4:

[0954] Based on the extracted request, the server creates a prompt and sends it to the image generation AI model. Example prompt: "Please generate a painting of a flower."

[0955] Input: Request data.

[0956] Output: A prompt statement (e.g., "Generate a painting of a flower.").

[0957] Step 5:

[0958] The image generation AI model generates an image based on the prompt text. The server sends a request to the image generation API and receives the generated image data.

[0959] Input: Prompt statement.

[0960] Output: Image data.

[0961] Step 6:

[0962] The server transmits the received image data to the high-definition display. Specifically, the image data is transferred through the interface of the display device.

[0963] Input: Image data.

[0964] Output: Preparing image data for display.

[0965] Step 7:

[0966] The terminal displays the image on a high-definition display. The display device receives the image data and displays it for the user to visually confirm.

[0967] Input: Image data to be displayed on the display.

[0968] Output: Image displayed on a high definition display.

[0969] Step 8:

[0970] The server analyzes past generated images and user request history to learn user preferences. It identifies user preferences using data stored in a history database.

[0971] Input: Previously generated images, user request history.

[0972] Output: Data about user preferences.

[0973] Step 9:

[0974] The server automatically generates new image generation requests based on the user's preferences, which are sent to the generation AI as prompts that are periodically updated.

[0975] Input: Data about the user's preferences.

[0976] Output: A new image generation request (e.g. "Flower Painting").

[0977] Step 10:

[0978] The server then sends the image generated based on the new image generation request to the high-definition display again, automatically updating the display content.

[0979] Input: Image data generated based on a new image generation request.

[0980] Output: Updated display content.

[0981] 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.

[0982] This system recognizes user voice input, converts the voice into text data, and extracts and recognizes the user's requests through analysis. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it has the ability to generate and select images based on the user's emotions. This allows for a more personalized user experience.

[0983] Program processing

[0984] 1. Acquiring and Recognizing Voice Input

[0985] The user speaks into the device, and the device uses voice recognition software to convert the voice data into text data. For example, if the user says, "I'm feeling sad today," the device converts this into text data: "I'm feeling sad today."

[0986] 2. Analyzing text data and extracting requirements

[0987] The terminal transmits the converted text data to the server.

[0988] The server analyzes the text data and extracts the user's request (e.g., "feeling sad").

[0989] 3. Emotional Recognition

[0990] The server uses an emotion engine to recognize emotions from the user's voice. For example, if the text data is analyzed as "feeling sad," the server recognizes the user's emotion as "sad."

[0991] 4. Select or generate an image

[0992] Based on the recognized emotion, the server sends a request to an image generation AI or selects an appropriate image from an existing image database. For example, if the user is in a sad mood, it will generate or select a calm and soothing image.

[0993] 5. Image data transmission and display

[0994] The server transmits the generated or selected image data to the terminal, which displays the image on a high-definition display.

[0995] 6. Learning user preferences and emotional patterns

[0996] The server analyzes past generated images, user request history, and recognized emotional patterns to learn the user's preferences and emotional patterns, thereby understanding which images tend to be preferred when the user is in a particular emotional state.

[0997] 7. Automatically generate and update new image generation requests

[0998] The server automatically generates new image generation requests based on the user's preferences and emotional patterns. For example, if a user has previously preferred a particular type of image that has a soothing effect when they felt sad, the server will create a request to automatically generate that type of image.

[0999] 8. Create and send a new image

[1000] The image generation AI generates a new image and returns the image data to the server. The server then sends the new image data to the device, which then automatically updates the content displayed on the high-definition display.

[1001] Specific examples

[1002] For example, if a user says, "I want to display a painting that suits my room, but I'm feeling down today," the device converts the voice data into text data saying, "I want to display a painting that suits my room, but I'm feeling down today," and sends it to the server. The server analyzes this and extracts the emotion "down." The emotion engine recognizes this as a "depressed mood" and sends a request to the image generation AI to generate an image with a soothing theme. The generated image is sent from the server to the device, which then displays it on a high-definition display.

[1003] The server then learns from this request history, generated images, and recognized emotions to understand the image preferences of users when they are in a particular emotional state. From then on, the next time the user is in a similar emotional state, the server can automatically generate and display the image the user prefers, providing a more personalized user experience.

[1004] The processing flow will be explained below.

[1005] Step 1:

[1006] The user speaks into the device, for example, saying, "I'm feeling sad today. I want to see pictures that will lift my spirits."

[1007] Step 2:

[1008] The device picks up the user's voice through a microphone and uses voice recognition software to convert the voice data into text data. Specifically, the speech "I'm feeling sad today. I want to see pictures that will lift my spirits" is converted into text data "I'm feeling sad today. I want to see pictures that will lift my spirits."

[1009] Step 3:

[1010] The terminal sends the converted text data to the server via a network using a communication protocol.

[1011] Step 4:

[1012] The server analyzes the received text data and extracts the user's request, for example, extracting keywords such as "sad mood" and "pictures that lift your spirits."

[1013] Step 5:

[1014] The server uses an emotion engine to recognize emotions from the user's voice. For example, if the text data is analyzed as "feeling sad," the server recognizes the user's emotion as "sad."

[1015] Step 6:

[1016] The server sends an image generation request to the image generation AI based on the extracted keywords and the recognized emotions. Specifically, it sends a request to "generate a soothing image to lift the mood."

[1017] Step 7:

[1018] The image generation AI generates an image based on the specified request, for example, generating a vivid and uplifting image of a flower, and returns the image data to the server.

[1019] Step 8:

[1020] The server receives the generated image data and sends it to the terminal via the network using a communication protocol.

[1021] Step 9:

[1022] The image data received by the terminal is displayed on a high-definition display. The terminal's display control software processes the image data and displays it on the display.

[1023] Step 10:

[1024] The server analyzes previously generated images, user request history, and recognized emotional patterns to learn user preferences and emotional patterns, thereby understanding which images users tend to like for specific emotional states.

[1025] Step 11:

[1026] The server automatically generates new image generation requests based on the user's preferences and emotional patterns it has learned. For example, if a user has previously preferred a particular type of image that has a soothing effect when they felt sad, it will send a request to the image generation AI to automatically generate that type of image.

[1027] Step 12:

[1028] The image generation AI generates a new image and returns the image data to the server, which then sends the new image data it receives to the device.

[1029] Step 13:

[1030] New image data received by the device is automatically updated and displayed on the high-definition display, allowing users to enjoy constantly updated interior designs.

[1031] Example 2

[1032] 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."

[1033] Conventional voice recognition systems only convert a user's voice input into text data, making it difficult to generate appropriate responses based on the user's emotions or specific requests. Furthermore, there is no system that dynamically generates or selects and displays images based on the user's emotions, limiting the user experience. This invention aims to provide a more personalized user experience by focusing on user emotion recognition and image generation based on those emotions.

[1034] 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.

[1035] In this invention, the server includes a means for recognizing user emotions from text data, a means for generating images based on an image generation artificial intelligence model, and a means for analyzing past generated images and the user's request history to learn the user's preferences, thereby enabling the server to generate, select, and provide appropriate and personalized images based on the emotions and requests extracted from the user's voice input.

[1036] "User" refers to any person or entity that uses this system.

[1037] "Voice input" refers to voice data uttered by a user.

[1038] "Text data" refers to data converted from voice input into a string of characters.

[1039] "Emotion" refers to information that indicates the user's internal emotional state.

[1040] "Image" refers to digital data containing visual information.

[1041] "Generation" refers to the act of the system creating new data.

[1042] "Display" refers to the act of projecting a generated or selected image onto a terminal display.

[1043] "High-definition display" refers to a device that displays images and information in high resolution.

[1044] "Server" refers to a central computer system that processes and stores data.

[1045] "Terminal" refers to a device that is directly operated by a user.

[1046] "Requests" refer to the wishes and requirements that users have for the system.

[1047] "Image generation artificial intelligence model" refers to algorithms and programs that generate images using AI technology.

[1048] "Recognition" refers to the act of a system understanding and making sense of data.

[1049] "Analysis" refers to the process of examining data in detail and extracting meaning.

[1050] "Learning" refers to the process of extracting trends and patterns from past data and using them to predict and respond to the future.

[1051] "Transmitting" refers to the act of transferring data from one point to another.

[1052] The present invention provides a system that recognizes a user's voice input, converts it into text data, analyzes it, and extracts emotions and requests. This system generates or selects and displays images according to the user's emotions, thereby achieving a highly personalized user experience. Specific embodiments are described below.

[1053] Acquiring and recognizing voice input

[1054] The user speaks into the device, and the device uses the built-in microphone to capture the voice and collects the voice data, which is then converted into text data using speech recognition software (e.g., Google's speech recognition API).

[1055] Analyzing text data and extracting requirements

[1056] The device transmits the converted text data to the server, which then uses a natural language processing engine (e.g., spaCy) to analyze the text data and extract the user's request and emotion. For example, from the text data "I'm feeling sad today," it identifies the emotion "sad" and the request "I'm feeling bad."

[1057] Emotion recognition

[1058] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's text data. In this way, the server specifically grasps the user's internal emotional state (e.g., "sad," "happy," etc.).

[1059] Select or generate an image

[1060] Based on the recognized emotion, the server generates an image using an image generation artificial intelligence model (e.g., OpenAI's DALL-E) or selects an appropriate image from an existing image database (e.g., Pexels or Unsplash). For example, when the user is in a "sad" mood, it provides calming and soothing images.

[1061] Image data transmission and display

[1062] The server sends the generated or selected image data to the device, which then displays the received image data on a high-definition display, allowing the user to view an image that matches their emotions.

[1063] Learning user preferences and emotional patterns

[1064] The server analyzes past generated images, the user's request history, and recognized emotional patterns. It uses machine learning algorithms (e.g., TensorFlow) to learn the user's preferences and emotional patterns. This allows it to generate or select the most appropriate image for similar emotional states in the future.

[1065] Automatically generate and update new image generation requests

[1066] The server automatically generates new image generation requests based on the user's preferences and emotional patterns. For example, it generates new prompts from specific types of image data that the user prefers when feeling sad. This ensures that images that match the user's emotions are always provided.

[1067] Specific examples

[1068] For example, consider the case where a user says to the device, "I want to display a painting that suits my room, but I'm feeling down today." The device converts this speech into text data using a speech recognition API and sends it to the server. The server extracts the emotion "down" and uses its emotion engine to recognize it as "depressed mood." Based on this emotion, it sends a prompt to the image generation AI model to "generate an image with a soothing theme." The generated image is sent from the server to the device and displayed on the device's high-definition display. The next time the user expresses a similar emotion, the system will provide the most appropriate image based on its past learning results.

[1069] This system enables dynamic image generation and display according to the user's emotions, providing a personalized, high-quality user experience.

[1070] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1071] Step 1:

[1072] Acquiring and recognizing voice input

[1073] The user inputs voice into the terminal.

[1074] Example: "I feel sad today."

[1075] The device captures voice data through the microphone and converts this voice data into text data using voice recognition software (for example, Google's voice recognition API).

[1076] Input: Audio data

[1077] Data processing: Speech-to-text conversion using speech recognition API

[1078] Output: Text data "I feel sad today"

[1079] Specific operation: recognizer.recognize_google(audio_data)

[1080] Step 2:

[1081] Analyzing text data and extracting requirements

[1082] The terminal transmits the text data to the server.

[1083] Input: Text data

[1084] Output: Sends text data to the server

[1085] Specific behavior: requests.post(server_url, json={"text": "I'm feeling sad today"})

[1086] The server analyzes the received text data using a natural language processing engine (e.g., spaCy) to extract the user's requests and sentiments.

[1087] Input: Text data

[1088] Data Calculation: Analysis and request extraction using a natural language processing engine

[1089] Output: Request "I feel bad" and emotion "Sad"

[1090] Specific behavior: nlp = spacy.load("ja_core_news_sm"), doc = nlp("I'm feeling sad today")

[1091] Step 3:

[1092] Emotion recognition

[1093] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion from the text data.

[1094] Input: Extracted text data

[1095] Data Computation: Emotion Recognition with Emotion Engine

[1096] Output: Recognized emotion "sad"

[1097] Specific behavior: tone_analyzer.tone({"text": "I'm feeling sad today"}, content_type="application / json")

[1098] Step 4:

[1099] Select or generate an image

[1100] Based on the recognized emotion, the server requests an image generation AI model (e.g., OpenAI's DALL-E) to generate an image, or selects an appropriate image from an existing image database (e.g., Pexels or Unsplash).

[1101] Input: Recognized emotion "sad"

[1102] Data operation: Image generation request or image selection

[1103] Output: Generated or selected image

[1104] Specific behavior: response = openai.Image.create(prompt="calming scenery", num_images=1) or search_results = pexels_api.search("calming scenery")

[1105] Step 5:

[1106] Image data transmission and display

[1107] The server transmits the generated or selected image data to the terminal.

[1108] Input: Image data

[1109] Output: Send image data to the device

[1110] Specific behavior: requests.post(client_url, json={"image_url": image_url})

[1111] The terminal displays the received image on a high-definition display.

[1112] Input: Received image data

[1113] Output: Display images on a high-definition display

[1114] Specific behavior: display_image(image_url)

[1115] Step 6:

[1116] Learning user preferences and emotional patterns

[1117] The server analyzes past generated images, the user's request history, and recognized emotional patterns to learn the user's preferences and emotional patterns.

[1118] Input: Previously generated images, request history, emotion patterns

[1119] Data Computing: Analysis and learning using machine learning algorithms

[1120] Output: Updated user preferences and sentiment patterns

[1121] Specific behavior: user_preferences.update({"mood": "sad", "liked_images": [image_url]}), model.fit(history_data, preferences_data)

[1122] Step 7:

[1123] Automatically generate and update new image generation requests

[1124] The server automatically generates new image generation requests based on learned user preferences and emotional patterns.

[1125] Input: Learned user preferences and emotional patterns

[1126] Data Calculation: New Prompt Generation

[1127] Output: Auto-generated image request

[1128] Specific behavior: auto_prompt = generate_prompt(user_preferences)

[1129] Step 8:

[1130] Generate and send a new image

[1131] The image generation artificial intelligence model generates a new image and returns the image data to the server.

[1132] Input: A new image generation request

[1133] Data computation: Image generation using generative AI models

[1134] Output: New image data

[1135] Specific behavior: response = openai.Image.create(prompt=auto_prompt, num_images=1)

[1136] The server transmits the received new image data to the terminal.

[1137] Input: New image data

[1138] Output: Send image data to the device

[1139] Specific behavior: requests.post(client_url, json={"image_url": new_image_url})

[1140] The device will display new images on its high-definition display and automatically refresh the display.

[1141] Input: New image data

[1142] Output: Display images on a high-definition display

[1143] Specific operation: display_image(new_image_url)

[1144] (Application example 2)

[1145] 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."

[1146] Conventional voice input systems often simply analyze user requests as text data and provide static responses. This makes it difficult to provide a truly personalized experience because they do not reflect the user's emotional state. Furthermore, they lack the ability to learn user preferences and automatically provide optimal content. In many settings, particularly brick-and-mortar stores, where information provision based on user emotions and preferences is required, there is a demand for improved customer satisfaction.

[1147] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing a user's emotion, means for selecting or generating an image based on the extracted request and emotion, and means for transmitting the generated image data to a high-definition display. This makes it possible to provide personalized images and information based on the user's emotion, thereby improving the user experience and increasing customer satisfaction.

[1148] "Voice input" refers to voice data emitted by the user, and this data is used by the system to detect operations and requests.

[1149] "Text data" refers to data of character information obtained by analyzing voice input.

[1150] "User requests" are specific requests or instructions given by users to the system.

[1151] "Emotions" represent the user's psychology and mental state, and are analyzed and recognized by the system.

[1152] "Selecting or generating an image" refers to choosing an appropriate image from an existing image database or generating a new image based on the user's requirements or emotions.

[1153] "High definition display" means a display device having a high resolution that presents a generated or selected image to a user.

[1154] "User preferences" refers to the user's individual tendencies and likes learned through past generated images and request history.

[1155] "Image Generation Request" means instructions or commands for generating a new image based on the user's needs or emotions.

[1156] A "terminal" is a device used by a user, typically hardware such as a smartphone or smart glasses.

[1157] "Automatic updating" means that the system replaces the displayed content with new content based on user input and history, without manual intervention.

[1158] This invention comprises a system that utilizes a user's voice input, analyzes the user's requests and emotions based on the voice input, and generates or selects appropriate images. A specific method for realizing this system is described below.

[1159] First, the user speaks into a device such as a smartphone or smart glasses. The voice input is picked up through the device's microphone and converted into text data using speech recognition software. This process is performed using a library called SpeechRecognition, for example.

[1160] The converted text data is then sent to a server, which analyzes the text data and extracts the user's request and emotion. This analysis uses natural language processing techniques such as the Transformers library. Emotion recognition uses an emotion engine to analyze the user's mental state.

[1161] Based on the extracted needs and emotions, the server then sends a generation request to an image generation AI model or selects an appropriate image from an existing image database, such as DALL-E or Midjourney.

[1162] The generated or selected image data is sent from the server to the device and displayed on the device's high-definition display. This image data is then automatically generated based on the user's preferences and request history. By learning the user's preferences, more appropriate and personalized images are provided when a similar request occurs again.

[1163] Specific examples

[1164] For example, if a user says to their smartphone, "I'm a little tired today, so I'm looking for a product that will help me relax," the device converts this speech into text data, "I'm a little tired today, so I'm looking for a product that will help me relax," and sends it to the server. The server analyzes this text data and recognizes the user's emotion as "fatigue." Next, based on the emotion, it generates or selects a product image that has a relaxing effect. In this case, the prompt text used is "relaxation, fatigue."

[1165] Finally, the selected or generated image data is displayed on the smartphone's high-definition display, and appropriate products are presented according to the user's request.

[1166] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1167] Step 1:

[1168] A user speaks into a device such as a smartphone or smart glasses. Specifically, the voice data is acquired through a microphone. The input is the user's voice, and the output is the acquired voice data.

[1169] Step 2:

[1170] The device receives the voice data and converts it into text data using voice recognition software, such as a library called SpeechRecognition, which takes voice data as input and outputs text data as the result.

[1171] Step 3:

[1172] The terminal sends the converted text data to the server. The input is the text data, and the output is a transmission completion notification to the server.

[1173] Step 4:

[1174] The server analyzes the received text data and extracts the user's requests and emotions. This analysis uses natural language processing techniques such as the Transformers library. The input is text data, and the output is the analyzed user's requests and emotions.

[1175] Step 5:

[1176] The server performs emotion recognition and analyzes the user's emotional state using an emotion engine. For example, emotions such as fatigue and joy are recognized. The input is text data, and the output is the recognized emotion.

[1177] Step 6:

[1178] Based on the extracted request and emotion, the server sends a generation request to an image generation AI model or selects an appropriate image from an existing image database. Examples of image generation AI models used include DALL-E and Midjourney. The input is request and emotion data, and the output is the generated or selected image data.

[1179] Step 7:

[1180] The generated or selected image data is sent from the server to the terminal. The input is the image data, and the output is a notification that the image data has been sent.

[1181] Step 8:

[1182] The terminal receives the transmitted image data and displays it on a high-definition display. The input is the image data, and the output is the image displayed on the display.

[1183] Step 9:

[1184] The server analyzes the past generated images and the user's request history and executes a process to learn the user's preferences. The input is the past generated images and the request history, and the output is the learned user preference data.

[1185] Step 10:

[1186] The server automatically generates new image generation requests based on the learned user preferences and recognized emotions. The input is preference data and emotion data, and the output is a new image generation request.

[1187] Step 11:

[1188] The image data generated based on the new image generation request is sent to the terminal again, and the display content is automatically updated. The input is the new image data, and the output is the updated display.

[1189] This series of processes realizes a system that provides a personalized experience according to the user's emotions.

[1190] 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.

[1191] 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.

[1192] 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.

[1193] [Fourth embodiment]

[1194] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1195] 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.

[1196] 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).

[1197] 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.

[1198] 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.

[1199] 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).

[1200] 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.

[1201] 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.

[1202] 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.

[1203] 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.

[1204] 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.

[1205] 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.

[1206] 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."

[1207] The system recognizes user voice input, converts the voice input into text data, analyzes the user's requests, and generates images based on the text. It also transmits the generated images to a high-definition display for display, learns the user's past request history, and automatically generates new image generation requests based on the user's preferences, periodically updating the displayed content.

[1208] Program processing

[1209] 1. Acquiring and Recognizing Voice Input

[1210] When a user speaks into the device, the device uses voice recognition technology to convert this into text data.

[1211] For example, if a user says, "I like ocean scenery. I'd like to see pictures of sunsets too," the device converts this voice data into text data saying, "I like ocean scenery. I'd like to see pictures of sunsets too."

[1212] 2. Analyzing text data and extracting requirements

[1213] The terminal transmits the text data to the server.

[1214] The server analyzes the text data and extracts the user's request (e.g., "seascape," "sunset").

[1215] 3. Image Generation

[1216] The server sends a request to the image generation AI based on the extracted requirements.

[1217] Based on the request, the image generation AI generates images of seascapes and sunsets and returns the data to the server.

[1218] 4. Image data transmission and display

[1219] The server transmits the generated image data to the terminal, which then displays the image on a high-definition display.

[1220] 5. Learning your preferences

[1221] The server analyzes past generated images and the user's request history to learn the user's preferences.

[1222] 6. Automatically generate and update new images

[1223] The server automatically creates a new image generation request based on the user's preferences and sends it to the image generation AI.

[1224] The new image generated is sent to the terminal, which automatically updates the display on the high-definition display.

[1225] Specific examples

[1226] For example, suppose the user first says, "I want to display a painting that suits my room, and I like paintings of flowers." This voice input is converted into text data and sent to the server. The server extracts the request, "I like paintings of flowers," from the text data and sends a request to the image generation AI to generate a painting of a flower. The generated image of the flower is sent from the server to the device and displayed on the device's high-definition display.

[1227] The server then learns from this request history and recognizes that the user's preference is flower images. After a few weeks, the server sends a request to the AI ​​to automatically generate new flower images based on the user's preferences. The generated new flower images are then sent to the device, automatically updating the content on the high-definition display. This process allows the user to enjoy their new interior without any hassle.

[1228] This system allows users to easily change the atmosphere of their interior by displaying paintings and posters that suit their tastes on a high-definition display. It also learns from past requests and automatically generates and updates new images, providing a fresh and appealing interior experience for users.

[1229] The processing flow will be explained below.

[1230] Step 1:

[1231] The user speaks to the device, for example, "I like seascapes. I'd like to see pictures of sunsets too."

[1232] Step 2:

[1233] The device picks up the user's voice through a microphone and uses voice recognition software to convert the voice data into text data. Specifically, the speech "I like seascapes. I'd like to see pictures of sunsets, too" is converted into text data "I like seascapes. I'd like to see pictures of sunsets, too."

[1234] Step 3:

[1235] The terminal sends the converted text data to the server. Using a communication protocol, the text data is sent to the server via the network.

[1236] Step 4:

[1237] The server analyzes the received text data and extracts the user's request. For example, it extracts keywords such as "seascape" and "sunset" from the text data.

[1238] Step 5:

[1239] The server sends image generation requests to the image generation AI based on the extracted keywords. Specifically, it sends requests such as "generate an image of a seascape" and "generate an image of a sunset."

[1240] Step 6:

[1241] The image generation AI generates an image based on the specified keywords, for example, a beautiful seascape or sunset image, and returns the image data to the server.

[1242] Step 7:

[1243] The server receives the generated image data and sends it to the terminal via a communication protocol over the network.

[1244] Step 8:

[1245] The image data received by the terminal is displayed on a high-definition display. The terminal's display control software processes the image data and displays it on the display.

[1246] Step 9:

[1247] The server analyzes previously generated images and the user's request history to learn the user's preferences, for example, that they like "seascapes" and "sunsets."

[1248] Step 10:

[1249] The server automatically generates new image generation requests based on the user's preferences. For example, it creates a new "seascape" or "sunset" image generation request and sends it to the image generation AI.

[1250] Step 11:

[1251] The image generation AI generates a new image and returns the image data to the server, which then sends the new image data it receives to the device.

[1252] Step 12:

[1253] New image data received by the device is automatically updated and displayed on the high-definition display, allowing users to enjoy constantly updated interior designs.

[1254] Example 1

[1255] 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."

[1256] In conventional image generation systems, users must manually input image generation requests each time, and they lack a mechanism for automatically considering user preferences and past request history. As a result, it takes a lot of effort for users to continuously enjoy new images, resulting in a lack of usability. In addition, the displayed content of generated images is not regularly updated, which can lead to user boredom.

[1257] 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.

[1258] In this invention, the server includes means for recognizing a user's voice input, means for converting the voice input into text data, means for analyzing the text data to extract a user's request, means for sending a request to input an image to a generative AI model based on the extracted request, means for receiving image data generated from the generative AI model, means for sending the received image data to a high-definition display, means for displaying the sent image data on the high-definition display, means for analyzing past generated images and the user's request history to learn the user's preferences, means for automatically generating a new image generation request based on the user's preferences, and means for sending an image generated based on the new image generation request to the terminal and automatically updating the display content. This allows the user to continuously enjoy new images that suit their preferences without any hassle.

[1259] "User" refers to an individual who utilizes the system to provide voice input and view the resulting image generation and display.

[1260] "Means for recognizing voice input" refers to technical devices or software that capture and interpret the voice uttered by the user as a digital signal.

[1261] "Means for converting speech input into text data" refers to digital processing technology or software that converts recognized speech into written form.

[1262] "Means for analyzing text data to extract user requirements" refers to processing technology or software that analyzes text data and finds out the user's intended requirements or wishes from within it.

[1263] "Means for sending a request to input an image into a generative AI model" refers to a technical device or software that sends a request to an artificial intelligence model that generates an image based on the extracted request.

[1264] "Means for receiving image data generated from a generative AI model" refers to a processing technology or device that receives image data generated by an image-generating AI model.

[1265] "High-definition display" refers to a display device that can display detailed images and videos at high resolution.

[1266] "Means for displaying the transmitted image data on a high definition display" refers to technical devices or software that transmit and display the generated image data on a high definition display.

[1267] "Means for learning user preferences by analyzing past generated images and user request history" refers to technical devices or software that analyze past image generation history and user request history to learn user preferences and tendencies.

[1268] "Means for automatically generating new image generation requests" refers to technical devices or software that automatically generate requests for new image generation based on learned user preferences.

[1269] "Means for automatically updating the display content" refers to technical devices or software that periodically or automatically update the display content of a high-definition display with newly generated images.

[1270] This invention is a system that recognizes and analyzes a user's voice input, and generates and displays an image based on the analysis results. This system specifically uses the following technical means.

[1271] First, the user speaks to the device. For example, if the user says, "I want to see a picture of a flower," the device receives the voice input through the built-in microphone. The device uses voice recognition software, such as the Google Cloud Speech-to-Text API, to convert the captured voice data into text data.

[1272] The device then sends the generated text data to the server, which then uses natural language processing tools (e.g., spaCy or NLTK) to analyze the user's request. Based on this analysis, the server extracts the user's specific request (e.g., "flower picture").

[1273] Based on the extracted requirements, the server sends an image generation request to an image generation AI (e.g., OpenAI's DALL·E or Stability AI's Stable Diffusion). Specific examples of prompts include "Generate a picture of a flower" or "Generate a new flower picture that matches the user's preferences."

[1274] The image data generated by the image generation AI is sent back to the server, which then receives the data and sends it to the device, which then displays it on a high-definition display.

[1275] Furthermore, the server stores the past generated images and request history in a database and analyzes them using machine learning algorithms (e.g., K-Nearest Neighbors and Decision Trees) to learn the user's preferences. Based on the learning results, new image generation requests are automatically generated periodically, and the server again sends these to the image generation AI. The newly generated images are sent to the device, which automatically updates the display on the high-definition display.

[1276] As an example, when a user first voice-inputs "I want to see summer scenery," this voice is converted into text data and sent to the server. The server extracts the request "summer scenery" from the text data and requests the image generation AI to generate "summer scenery." The generated image of the summer scenery is sent from the server to the device, which then displays it on a high-definition display.

[1277] The server also learns user trends by analyzing past request data. For example, if a user frequently requests "cherry blossom photos," the server will automatically create requests to periodically generate "new cherry blossom photos" and send them to the image generation AI. These new cherry blossom photos are sent to the device and automatically updated as content on the high-definition display. This allows users to constantly enjoy new images seamlessly.

[1278] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1279] Step 1:

[1280] The user inputs voice into the device. For example, if the user says, "I want to see pictures of seascapes," the device picks up this voice through the built-in microphone and saves it as voice data. The input of this step is the user's voice, and the output is voice data.

[1281] Step 2:

[1282] The device inputs the voice data into voice recognition software (e.g., a general voice recognition API) and converts it into text data. This conversion analyzes the sound wave signal as digital text and generates the string "I want to see pictures of seascapes." The input of this step is voice data, and the output is text data.

[1283] Step 3:

[1284] The terminal sends the generated text data to the server. The server receives this text data and analyzes it using a natural language processing tool (e.g., a general natural language processing library). In this analysis, the request "seascape" is extracted from the text data. The input of this step is the text data, and the output is the analyzed request data.

[1285] Step 4:

[1286] Based on the parsed request, the server sends an image generation request to an image generation AI (e.g., a general image generation model). Specifically, it sends a prompt to the generative AI model saying, "Please generate an image of a seascape." The input of this step is the parsed request data, and the output is a request to the generative AI.

[1287] Step 5:

[1288] The image generation AI generates an image based on the received prompt and sends the generated image data back to the server. The input to this step is the request to the generation AI, and the output is the image data.

[1289] Step 6:

[1290] The server receives the generated image data and sends it to the terminal. In this step, data is transferred over the network. The input is the image data, and the output is the transmission of the image data to the terminal.

[1291] Step 7:

[1292] The terminal displays the image data received from the server on a high-definition display. In this display process, the image data is passed to the display driver and displayed in a form that is visible to the user. The input of this step is the image data, and the output is the image displayed on the display.

[1293] Step 8:

[1294] The server stores the user's past requests and the history of generated images in a database and analyzes them using a machine learning algorithm. This analysis learns the user's preferences and automatically generates prompts for new image generation requests. The input of this step is the past request and image history data, and the output is the learned user preferences and new requests.

[1295] Step 9:

[1296] The server again sends an automatically generated new image generation request to the image generation AI, and the generated new image is sent to the terminal. The terminal receives this and periodically updates the content of the high-definition display. The input of this step is the automatically generated request and the generated image data, and the output is the updated display content on the display.

[1297] (Application example 1)

[1298] 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."

[1299] Conventional interior design systems require users to manually select images and display them on a screen, making it difficult to frequently update the atmosphere of a physical store. Additionally, there is a lack of technology to automatically generate and display appropriate images continuously based on user preferences.

[1300] 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.

[1301] In this invention, the server includes means for recognizing a user's voice input, means for converting the voice input into text data, means for analyzing the text data to extract a user's request, means for generating an image based on the extracted request, means for transmitting the generated image data to a high-definition display, means for displaying the transmitted image data on the high-definition display, means for analyzing past generated images and the user's request history to learn the user's preferences, means for automatically generating a new image generation request based on the user's preferences, means for transmitting an image generated based on the new image generation request to a terminal and automatically updating the display content, and means for displaying the generated image on a terminal with a high-definition display to provide customers of a physical store with a visual interior experience. This enables users to automatically generate and display interior designs that suit their preferences using only voice input, thereby continuously maintaining the atmosphere of the physical store fresh.

[1302] "User voice input" means verbal instructions or requests made by a User.

[1303] "Means for converting speech input into text data" refers to technology or devices that analyze speech signals and convert them into corresponding text.

[1304] "Text data" refers to character string data converted from speech.

[1305] "Means for extracting user requirements" refers to techniques and methods for identifying user intent and requests from converted text data.

[1306] "Means for generating images" refers to techniques or devices that create images by computer based on a user's request.

[1307] "Image data" refers to the digital data of the generated image.

[1308] "High definition display" refers to a display device capable of displaying images at high resolution.

[1309] "User request history" refers to a record of requests and instructions that a user has previously entered into the system.

[1310] "Means for learning user preferences" refers to technologies and methods for analyzing user preferences and trends based on past request history.

[1311] "Means for automatically generating new image generation requests" refers to techniques or methods by which the system automatically generates new image generation instructions based on user preferences.

[1312] A "physical store" refers to a commercial facility or service location that has a specific physical space.

[1313] "Interior experience" refers to the experience of the visual design and decoration of an indoor space.

[1314] This invention is a system that recognizes a user's voice input, converts it into text data, and analyzes the user's requests. Specifically, this system generates images based on the user's preferences and displays them on a high-definition display. It also learns from past request history, automatically makes new image generation requests, and periodically updates the displayed content.

[1315] System configuration and programs

[1316] Hardware:

[1317] Microphone: A device that captures the user's voice input.

[1318] High-definition display: A device that displays the generated images.

[1319] Edge device: A device that performs some of the processing for voice recognition and image generation.

[1320] software:

[1321] Speech recognition technology (speech_recognition library): A library for converting voice input into text data.

[1322] Image generation AI (access API using the requests library): An AI model for generating images based on text data.

[1323] Image processing library (Pillow): A library for processing and displaying acquired image data.

[1324] History database: A database to store past requests and generated images and learn user preferences.

[1325] Processing Details

[1326] When a user speaks into the microphone, the server captures the voice and converts it into text data using voice recognition technology. For example, if a user says, "I want to display summer scenery, but I like pictures of the beach," the voice data is converted into text data saying, "I want to display summer scenery, but I like pictures of the beach."

[1327] The server then analyzes this text data and extracts user requests such as "summer scenery" or "beach photos." Once the request is extracted, the server sends a prompt to the image generation AI. An example of this prompt is "Please generate an image of a summer beach scenery that matches the interior of a cafe."

[1328] The image generation AI generates an appropriate image based on this prompt and returns the image data to the server. The server then sends the received image data to a high-definition display, where the image is displayed on the physical store's terminal. By analyzing past generated images and the user's request history, the AI ​​learns the user's preferences and automatically makes new image generation requests. The newly generated images are also displayed on the high-definition display, allowing the store's atmosphere to be constantly updated.

[1329] For example, if a cafe owner says, "I want to display a summer scene, but I like beach photos," the system will send a prompt to the generative AI model based on that request, and the generated beach image will be displayed on the cafe's high-definition display. An example of this prompt would be, "Please generate a summer beach scene image that matches the cafe's interior." This saves users the trouble of manually selecting an image, allowing them to easily change the atmosphere of their store.

[1330] As a whole, the system allows users to use voice input to automatically generate interior designs that suit their preferences, providing a visual interior experience in a physical store.

[1331] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1332] Step 1:

[1333] The user provides voice input. The user speaks into the microphone and inputs a request such as, "I want to display a painting that matches my room, and I like paintings of flowers."

[1334] Input: User's voice.

[1335] Output: Audio data.

[1336] Step 2:

[1337] The server receives audio data from the microphone and converts it into text using speech recognition technology. Specifically, it uses the speech_recognition library.

[1338] Input: Audio data.

[1339] Output: Text data (e.g. "I want to display paintings that suit my room, and I like paintings of flowers.").

[1340] Step 3:

[1341] The server analyzes the text data and extracts the user's request using natural language processing to identify the request.

[1342] Input: Text data.

[1343] Output: Request data (e.g. "A painting that suits the room", "A painting of flowers").

[1344] Step 4:

[1345] Based on the extracted request, the server creates a prompt and sends it to the image generation AI model. Example prompt: "Please generate a painting of a flower."

[1346] Input: Request data.

[1347] Output: A prompt statement (e.g., "Generate a painting of a flower.").

[1348] Step 5:

[1349] The image generation AI model generates an image based on the prompt text. The server sends a request to the image generation API and receives the generated image data.

[1350] Input: Prompt statement.

[1351] Output: Image data.

[1352] Step 6:

[1353] The server transmits the received image data to the high-definition display. Specifically, the image data is transferred through the interface of the display device.

[1354] Input: Image data.

[1355] Output: Preparing image data for display.

[1356] Step 7:

[1357] The terminal displays the image on a high-definition display. The display device receives the image data and displays it for the user to visually confirm.

[1358] Input: Image data to be displayed on the display.

[1359] Output: Image displayed on a high definition display.

[1360] Step 8:

[1361] The server analyzes past generated images and user request history to learn user preferences. It identifies user preferences using data stored in a history database.

[1362] Input: Previously generated images, user request history.

[1363] Output: Data about user preferences.

[1364] Step 9:

[1365] The server automatically generates new image generation requests based on the user's preferences, which are sent to the generation AI as prompts that are periodically updated.

[1366] Input: Data about the user's preferences.

[1367] Output: A new image generation request (e.g. "Flower Painting").

[1368] Step 10:

[1369] The server then sends the image generated based on the new image generation request to the high-definition display again, automatically updating the display content.

[1370] Input: Image data generated based on a new image generation request.

[1371] Output: Updated display content.

[1372] 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.

[1373] This system recognizes user voice input, converts the voice into text data, and extracts and recognizes the user's requests through analysis. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it has the ability to generate and select images based on the user's emotions. This allows for a more personalized user experience.

[1374] Program processing

[1375] 1. Acquiring and Recognizing Voice Input

[1376] The user speaks into the device, and the device uses voice recognition software to convert the voice data into text data. For example, if the user says, "I'm feeling sad today," the device converts this into text data: "I'm feeling sad today."

[1377] 2. Analyzing text data and extracting requirements

[1378] The terminal transmits the converted text data to the server.

[1379] The server analyzes the text data and extracts the user's request (e.g., "feeling sad").

[1380] 3. Emotional Recognition

[1381] The server uses an emotion engine to recognize emotions from the user's voice. For example, if the text data is analyzed as "feeling sad," the server recognizes the user's emotion as "sad."

[1382] 4. Select or generate an image

[1383] Based on the recognized emotion, the server sends a request to an image generation AI or selects an appropriate image from an existing image database. For example, if the user is in a sad mood, it will generate or select a calm and soothing image.

[1384] 5. Image data transmission and display

[1385] The server transmits the generated or selected image data to the terminal, which displays the image on a high-definition display.

[1386] 6. Learning user preferences and emotional patterns

[1387] The server analyzes past generated images, user request history, and recognized emotional patterns to learn the user's preferences and emotional patterns, thereby understanding which images tend to be preferred when the user is in a particular emotional state.

[1388] 7. Automatically generate and update new image generation requests

[1389] The server automatically generates new image generation requests based on the user's preferences and emotional patterns. For example, if a user has previously preferred a particular type of image that has a soothing effect when they felt sad, the server will create a request to automatically generate that type of image.

[1390] 8. Create and send a new image

[1391] The image generation AI generates a new image and returns the image data to the server. The server then sends the new image data to the device, which then automatically updates the content displayed on the high-definition display.

[1392] Specific examples

[1393] For example, if a user says, "I want to display a painting that suits my room, but I'm feeling down today," the device converts the voice data into text data saying, "I want to display a painting that suits my room, but I'm feeling down today," and sends it to the server. The server analyzes this and extracts the emotion "down." The emotion engine recognizes this as a "depressed mood" and sends a request to the image generation AI to generate an image with a soothing theme. The generated image is sent from the server to the device, which then displays it on a high-definition display.

[1394] The server then learns from this request history, generated images, and recognized emotions to understand the image preferences of users when they are in a particular emotional state. From then on, the next time the user is in a similar emotional state, the server can automatically generate and display the image the user prefers, providing a more personalized user experience.

[1395] The processing flow will be explained below.

[1396] Step 1:

[1397] The user speaks into the device, for example, saying, "I'm feeling sad today. I want to see pictures that will lift my spirits."

[1398] Step 2:

[1399] The device picks up the user's voice through a microphone and uses voice recognition software to convert the voice data into text data. Specifically, the speech "I'm feeling sad today. I want to see pictures that will lift my spirits" is converted into text data "I'm feeling sad today. I want to see pictures that will lift my spirits."

[1400] Step 3:

[1401] The terminal sends the converted text data to the server via a network using a communication protocol.

[1402] Step 4:

[1403] The server analyzes the received text data and extracts the user's request, for example, extracting keywords such as "sad mood" and "pictures that lift your spirits."

[1404] Step 5:

[1405] The server uses an emotion engine to recognize emotions from the user's voice. For example, if the text data is analyzed as "feeling sad," the server recognizes the user's emotion as "sad."

[1406] Step 6:

[1407] The server sends an image generation request to the image generation AI based on the extracted keywords and the recognized emotions. Specifically, it sends a request to "generate a soothing image to lift the mood."

[1408] Step 7:

[1409] The image generation AI generates an image based on the specified request, for example, generating a vivid and uplifting image of a flower, and returns the image data to the server.

[1410] Step 8:

[1411] The server receives the generated image data and sends it to the terminal via the network using a communication protocol.

[1412] Step 9:

[1413] The image data received by the terminal is displayed on a high-definition display. The terminal's display control software processes the image data and displays it on the display.

[1414] Step 10:

[1415] The server analyzes previously generated images, user request history, and recognized emotional patterns to learn user preferences and emotional patterns, thereby understanding which images users tend to like for specific emotional states.

[1416] Step 11:

[1417] The server automatically generates new image generation requests based on the user's preferences and emotional patterns it has learned. For example, if a user has previously preferred a particular type of image that has a soothing effect when they felt sad, it will send a request to the image generation AI to automatically generate that type of image.

[1418] Step 12:

[1419] The image generation AI generates a new image and returns the image data to the server, which then sends the new image data it receives to the device.

[1420] Step 13:

[1421] New image data received by the device is automatically updated and displayed on the high-definition display, allowing users to enjoy constantly updated interior designs.

[1422] Example 2

[1423] 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."

[1424] Conventional voice recognition systems only convert a user's voice input into text data, making it difficult to generate appropriate responses based on the user's emotions or specific requests. Furthermore, there is no system that dynamically generates or selects and displays images based on the user's emotions, limiting the user experience. This invention aims to provide a more personalized user experience by focusing on user emotion recognition and image generation based on those emotions.

[1425] 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.

[1426] In this invention, the server includes a means for recognizing user emotions from text data, a means for generating images based on an image generation artificial intelligence model, and a means for analyzing past generated images and the user's request history to learn the user's preferences, thereby enabling the server to generate, select, and provide appropriate and personalized images based on the emotions and requests extracted from the user's voice input.

[1427] "User" refers to any person or entity that uses this system.

[1428] "Voice input" refers to voice data uttered by a user.

[1429] "Text data" refers to data converted from voice input into a string of characters.

[1430] "Emotion" refers to information that indicates the user's internal emotional state.

[1431] "Image" refers to digital data containing visual information.

[1432] "Generation" refers to the act of the system creating new data.

[1433] "Display" refers to the act of projecting a generated or selected image onto a terminal display.

[1434] "High-definition display" refers to a device that displays images and information in high resolution.

[1435] "Server" refers to a central computer system that processes and stores data.

[1436] "Terminal" refers to a device that is directly operated by a user.

[1437] "Requests" refer to the wishes and requirements that users have for the system.

[1438] "Image generation artificial intelligence model" refers to algorithms and programs that generate images using AI technology.

[1439] "Recognition" refers to the act of a system understanding and making sense of data.

[1440] "Analysis" refers to the process of examining data in detail and extracting meaning.

[1441] "Learning" refers to the process of extracting trends and patterns from past data and using them to predict and respond to the future.

[1442] "Transmitting" refers to the act of transferring data from one point to another.

[1443] The present invention provides a system that recognizes a user's voice input, converts it into text data, analyzes it, and extracts emotions and requests. This system generates or selects and displays images according to the user's emotions, thereby achieving a highly personalized user experience. Specific embodiments are described below.

[1444] Acquiring and recognizing voice input

[1445] The user speaks into the device, and the device uses the built-in microphone to capture the voice and collects the voice data, which is then converted into text data using speech recognition software (e.g., Google's speech recognition API).

[1446] Analyzing text data and extracting requirements

[1447] The device transmits the converted text data to the server, which then uses a natural language processing engine (e.g., spaCy) to analyze the text data and extract the user's request and emotion. For example, from the text data "I'm feeling sad today," it identifies the emotion "sad" and the request "I'm feeling bad."

[1448] Emotion recognition

[1449] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's text data. In this way, the server specifically grasps the user's internal emotional state (e.g., "sad," "happy," etc.).

[1450] Select or generate an image

[1451] Based on the recognized emotion, the server generates an image using an image generation artificial intelligence model (e.g., OpenAI's DALL-E) or selects an appropriate image from an existing image database (e.g., Pexels or Unsplash). For example, when the user is in a "sad" mood, it provides calming and soothing images.

[1452] Image data transmission and display

[1453] The server sends the generated or selected image data to the device, which then displays the received image data on a high-definition display, allowing the user to view an image that matches their emotions.

[1454] Learning user preferences and emotional patterns

[1455] The server analyzes past generated images, the user's request history, and recognized emotional patterns. It uses machine learning algorithms (e.g., TensorFlow) to learn the user's preferences and emotional patterns. This allows it to generate or select the most appropriate image for similar emotional states in the future.

[1456] Automatically generate and update new image generation requests

[1457] The server automatically generates new image generation requests based on the user's preferences and emotional patterns. For example, it generates new prompts from specific types of image data that the user prefers when feeling sad. This ensures that images that match the user's emotions are always provided.

[1458] Specific examples

[1459] For example, consider the case where a user says to the device, "I want to display a painting that suits my room, but I'm feeling down today." The device converts this speech into text data using a speech recognition API and sends it to the server. The server extracts the emotion "down" and uses its emotion engine to recognize it as "depressed mood." Based on this emotion, it sends a prompt to the image generation AI model to "generate an image with a soothing theme." The generated image is sent from the server to the device and displayed on the device's high-definition display. The next time the user expresses a similar emotion, the system will provide the most appropriate image based on its past learning results.

[1460] This system enables dynamic image generation and display according to the user's emotions, providing a personalized, high-quality user experience.

[1461] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1462] Step 1:

[1463] Acquiring and recognizing voice input

[1464] The user inputs voice into the terminal.

[1465] Example: "I feel sad today."

[1466] The device captures voice data through the microphone and converts this voice data into text data using voice recognition software (for example, Google's voice recognition API).

[1467] Input: Audio data

[1468] Data processing: Speech-to-text conversion using speech recognition API

[1469] Output: Text data "I feel sad today"

[1470] Specific operation: recognizer.recognize_google(audio_data)

[1471] Step 2:

[1472] Analyzing text data and extracting requirements

[1473] The terminal transmits the text data to the server.

[1474] Input: Text data

[1475] Output: Sends text data to the server

[1476] Specific behavior: requests.post(server_url, json={"text": "I'm feeling sad today"})

[1477] The server analyzes the received text data using a natural language processing engine (e.g., spaCy) to extract the user's requests and sentiments.

[1478] Input: Text data

[1479] Data Calculation: Analysis and request extraction using a natural language processing engine

[1480] Output: Request "I feel bad" and emotion "Sad"

[1481] Specific behavior: nlp = spacy.load("ja_core_news_sm"), doc = nlp("I'm feeling sad today")

[1482] Step 3:

[1483] Emotion recognition

[1484] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion from the text data.

[1485] Input: Extracted text data

[1486] Data Computation: Emotion Recognition with Emotion Engine

[1487] Output: Recognized emotion "sad"

[1488] Specific behavior: tone_analyzer.tone({"text": "I'm feeling sad today"}, content_type="application / json")

[1489] Step 4:

[1490] Select or generate an image

[1491] Based on the recognized emotion, the server requests an image generation AI model (e.g., OpenAI's DALL-E) to generate an image, or selects an appropriate image from an existing image database (e.g., Pexels or Unsplash).

[1492] Input: Recognized emotion "sad"

[1493] Data operation: Image generation request or image selection

[1494] Output: Generated or selected image

[1495] Specific behavior: response = openai.Image.create(prompt="calming scenery", num_images=1) or search_results = pexels_api.search("calming scenery")

[1496] Step 5:

[1497] Image data transmission and display

[1498] The server transmits the generated or selected image data to the terminal.

[1499] Input: Image data

[1500] Output: Send image data to the device

[1501] Specific behavior: requests.post(client_url, json={"image_url": image_url})

[1502] The terminal displays the received image on a high-definition display.

[1503] Input: Received image data

[1504] Output: Display images on a high-definition display

[1505] Specific behavior: display_image(image_url)

[1506] Step 6:

[1507] Learning user preferences and emotional patterns

[1508] The server analyzes past generated images, the user's request history, and recognized emotional patterns to learn the user's preferences and emotional patterns.

[1509] Input: Previously generated images, request history, emotion patterns

[1510] Data Computing: Analysis and learning using machine learning algorithms

[1511] Output: Updated user preferences and sentiment patterns

[1512] Specific behavior: user_preferences.update({"mood": "sad", "liked_images": [image_url]}), model.fit(history_data, preferences_data)

[1513] Step 7:

[1514] Automatically generate and update new image generation requests

[1515] The server automatically generates new image generation requests based on learned user preferences and emotional patterns.

[1516] Input: Learned user preferences and emotional patterns

[1517] Data Calculation: New Prompt Generation

[1518] Output: Auto-generated image request

[1519] Specific behavior: auto_prompt = generate_prompt(user_preferences)

[1520] Step 8:

[1521] Generate and send a new image

[1522] The image generation artificial intelligence model generates a new image and returns the image data to the server.

[1523] Input: A new image generation request

[1524] Data computation: Image generation using generative AI models

[1525] Output: New image data

[1526] Specific behavior: response = openai.Image.create(prompt=auto_prompt, num_images=1)

[1527] The server transmits the received new image data to the terminal.

[1528] Input: New image data

[1529] Output: Send image data to the device

[1530] Specific behavior: requests.post(client_url, json={"image_url": new_image_url})

[1531] The device will display new images on its high-definition display and automatically refresh the display.

[1532] Input: New image data

[1533] Output: Display images on a high-definition display

[1534] Specific operation: display_image(new_image_url)

[1535] (Application example 2)

[1536] 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."

[1537] Conventional voice input systems often simply analyze user requests as text data and provide static responses. This makes it difficult to provide a truly personalized experience because they do not reflect the user's emotional state. Furthermore, they lack the ability to learn user preferences and automatically provide optimal content. In many settings, particularly brick-and-mortar stores, where information provision based on user emotions and preferences is required, there is a demand for improved customer satisfaction.

[1538] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing a user's emotion, means for selecting or generating an image based on the extracted request and emotion, and means for transmitting the generated image data to a high-definition display. This makes it possible to provide personalized images and information based on the user's emotion, thereby improving the user experience and increasing customer satisfaction.

[1539] "Voice input" refers to voice data emitted by the user, and this data is used by the system to detect operations and requests.

[1540] "Text data" refers to data of character information obtained by analyzing voice input.

[1541] "User requests" are specific requests or instructions given by users to the system.

[1542] "Emotions" represent the user's psychology and mental state, and are analyzed and recognized by the system.

[1543] "Selecting or generating an image" refers to choosing an appropriate image from an existing image database or generating a new image based on the user's requirements or emotions.

[1544] "High definition display" means a display device having a high resolution that presents a generated or selected image to a user.

[1545] "User preferences" refers to the user's individual tendencies and likes learned through past generated images and request history.

[1546] "Image Generation Request" means instructions or commands for generating a new image based on the user's needs or emotions.

[1547] A "terminal" is a device used by a user, typically hardware such as a smartphone or smart glasses.

[1548] "Automatic updating" means that the system replaces the displayed content with new content based on user input and history, without manual intervention.

[1549] This invention comprises a system that utilizes a user's voice input, analyzes the user's requests and emotions based on the voice input, and generates or selects appropriate images. A specific method for realizing this system is described below.

[1550] First, the user speaks into a device such as a smartphone or smart glasses. The voice input is picked up through the device's microphone and converted into text data using speech recognition software. This process is performed using a library called SpeechRecognition, for example.

[1551] The converted text data is then sent to a server, which analyzes the text data and extracts the user's request and emotion. This analysis uses natural language processing techniques such as the Transformers library. Emotion recognition uses an emotion engine to analyze the user's mental state.

[1552] Based on the extracted needs and emotions, the server then sends a generation request to an image generation AI model or selects an appropriate image from an existing image database, such as DALL-E or Midjourney.

[1553] The generated or selected image data is sent from the server to the device and displayed on the device's high-definition display. This image data is then automatically generated based on the user's preferences and request history. By learning the user's preferences, more appropriate and personalized images are provided when a similar request occurs again.

[1554] Specific examples

[1555] For example, if a user says to their smartphone, "I'm a little tired today, so I'm looking for a product that will help me relax," the device converts this speech into text data, "I'm a little tired today, so I'm looking for a product that will help me relax," and sends it to the server. The server analyzes this text data and recognizes the user's emotion as "fatigue." Next, based on the emotion, it generates or selects a product image that has a relaxing effect. In this case, the prompt text used is "relaxation, fatigue."

[1556] Finally, the selected or generated image data is displayed on the smartphone's high-definition display, and appropriate products are presented according to the user's request.

[1557] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1558] Step 1:

[1559] A user speaks into a device such as a smartphone or smart glasses. Specifically, the voice data is acquired through a microphone. The input is the user's voice, and the output is the acquired voice data.

[1560] Step 2:

[1561] The device receives the voice data and converts it into text data using voice recognition software, such as a library called SpeechRecognition, which takes voice data as input and outputs text data as the result.

[1562] Step 3:

[1563] The terminal sends the converted text data to the server. The input is the text data, and the output is a transmission completion notification to the server.

[1564] Step 4:

[1565] The server analyzes the received text data and extracts the user's requests and emotions. This analysis uses natural language processing techniques such as the Transformers library. The input is text data, and the output is the analyzed user's requests and emotions.

[1566] Step 5:

[1567] The server performs emotion recognition and analyzes the user's emotional state using an emotion engine. For example, emotions such as fatigue and joy are recognized. The input is text data, and the output is the recognized emotion.

[1568] Step 6:

[1569] Based on the extracted request and emotion, the server sends a generation request to an image generation AI model or selects an appropriate image from an existing image database. Examples of image generation AI models used include DALL-E and Midjourney. The input is request and emotion data, and the output is the generated or selected image data.

[1570] Step 7:

[1571] The generated or selected image data is sent from the server to the terminal. The input is the image data, and the output is a notification that the image data has been sent.

[1572] Step 8:

[1573] The terminal receives the transmitted image data and displays it on a high-definition display. The input is the image data, and the output is the image displayed on the display.

[1574] Step 9:

[1575] The server analyzes the past generated images and the user's request history and executes a process to learn the user's preferences. The input is the past generated images and the request history, and the output is the learned user preference data.

[1576] Step 10:

[1577] The server automatically generates new image generation requests based on the learned user preferences and recognized emotions. The input is preference data and emotion data, and the output is a new image generation request.

[1578] Step 11:

[1579] The image data generated based on the new image generation request is sent to the terminal again, and the display content is automatically updated. The input is the new image data, and the output is the updated display.

[1580] This series of processes realizes a system that provides a personalized experience according to the user's emotions.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] 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.

[1587] 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).

[1588] 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.

[1589] 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."

[1590] 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.

[1591] 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).

[1592] 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.

[1593] 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.

[1594] 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.

[1595] 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.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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.

[1602] The following is further disclosed regarding the above embodiment.

[1603] (Claim 1)

[1604] a means for recognizing a user's voice input;

[1605] means for converting voice input into text data;

[1606] A means for analyzing text data to extract user requirements;

[1607] means for generating an image based on the extracted request;

[1608] means for transmitting the generated image data to a high definition display;

[1609] means for displaying the transmitted image data on a high-definition display;

[1610] a means for learning user preferences by analyzing past generated images and user request history;

[1611] a means for automatically generating new image generation requests based on user preferences;

[1612] means for transmitting an image generated based on a new image generation request to the terminal and automatically updating the display content;

[1613] A system including:

[1614] (Claim 2)

[1615] 2. The system according to claim 1, further comprising means for transmitting an image generated based on a user's request from the server to the terminal.

[1616] (Claim 3)

[1617] 2. The system according to claim 1, further comprising means for transmitting image data generated based on an image generation request to the terminal and automatically updating the display content periodically.

[1618] "Example 1"

[1619] (Claim 1)

[1620] a means for recognizing a user's voice input;

[1621] means for converting voice input into text data;

[1622] A means for analyzing text data to extract user requirements;

[1623] means for sending a request to input an image to a generative AI model based on the extracted request;

[1624] means for receiving image data generated from the generative AI model;

[1625] means for transmitting the received image data to a high definition display;

[1626] means for displaying the transmitted image data on a high-definition display;

[1627] a means for learning user preferences by analyzing past generated images and user request history;

[1628] a means for automatically generating new image generation requests based on user preferences;

[1629] means for transmitting an image generated based on a new image generation request to the terminal and automatically updating the display content;

[1630] A system including:

[1631] (Claim 2)

[1632] 2. The system according to claim 1, further comprising means for transmitting an image generated based on a user's request from the server to the terminal.

[1633] (Claim 3)

[1634] 2. The system according to claim 1, further comprising means for transmitting image data generated based on an image generation request to the terminal and automatically updating the display content periodically.

[1635] "Application Example 1"

[1636] (Claim 1)

[1637] a means for recognizing a user's voice input;

[1638] means for converting voice input into text data;

[1639] A means for analyzing text data to extract user requirements;

[1640] means for generating an image based on the extracted request;

[1641] means for transmitting the generated image data to a high definition display;

[1642] means for displaying the transmitted image data on a high-definition display;

[1643] a means for learning user preferences by analyzing past generated images and user request history;

[1644] a means for automatically generating new image generation requests based on user preferences;

[1645] means for transmitting an image generated based on a new image generation request to the terminal and automatically updating the display content;

[1646] A means for displaying the generated image on a terminal with a high-definition display to provide customers in a physical store with a visual interior experience;

[1647] A system including:

[1648] (Claim 2)

[1649] The system according to claim 1, further comprising a means for transmitting an image generated based on a user's request from a server to a terminal, and a means for displaying the generated image on a high-definition display in a physical store.

[1650] (Claim 3)

[1651] The system according to claim 1, further comprising means for transmitting image data generated based on an image generation request to a terminal and automatically updating the display content of a physical store periodically.

[1652] "Example 2: Combining Emotion Engines"

[1653] (Claim 1)

[1654] a means for recognizing a user's voice input;

[1655] means for converting voice input into text data;

[1656] A means for analyzing text data to extract user requirements;

[1657] A means for recognizing user emotions from text data;

[1658] means for generating an image based on an image generation artificial intelligence model;

[1659] means for transmitting the generated image data to a high definition display;

[1660] means for displaying the transmitted image data on a high-definition display;

[1661] a means for learning user preferences by analyzing past generated images and user request history;

[1662] a means for automatically generating new image generation requests based on user preferences;

[1663] means for transmitting an image generated based on a new image generation request to the terminal and automatically updating the display content;

[1664] A system including:

[1665] (Claim 2)

[1666] 2. The system according to claim 1, further comprising means for transmitting an image generated based on the user's request and emotion from the server to the terminal.

[1667] (Claim 3)

[1668] 2. The system according to claim 1, further comprising means for transmitting image data generated based on an image generation request to the terminal and automatically updating the display content periodically.

[1669] "Application example 2 when combining emotion engines"

[1670] (Claim 1)

[1671] a means for recognizing a user's voice input;

[1672] means for converting voice input into text data;

[1673] A means for analyzing text data to extract user requirements;

[1674] a means of recognizing a user's emotions;

[1675] means for selecting or generating images based on the extracted desires and emotions;

[1676] means for transmitting the generated image data to a high definition display;

[1677] means for displaying the transmitted image data on a high-definition display;

[1678] means for learning user preferences by analyzing past generated images and user request history;

[1679] means for automatically generating new image generation requests based on user preferences and recognized emotions;

[1680] means for transmitting an image generated based on a new image generation request to the terminal and automatically updating the display content;

[1681] A system including:

[1682] (Claim 2)

[1683] 2. The system according to claim 1, further comprising means for transmitting an image generated or selected based on the user's request and emotion from the server to the terminal.

[1684] (Claim 3)

[1685] 2. The system according to claim 1, further comprising means for transmitting image data generated based on an image generation request to the terminal and automatically updating the display content periodically. [Explanation of symbols]

[1686] 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 recognizing a user's voice input; means for converting voice input into text data; A means for analyzing text data to extract user requirements; means for generating an image based on the extracted request; means for transmitting the generated image data to a high definition display; means for displaying the transmitted image data on a high-definition display; a means for learning user preferences by analyzing past generated images and user request history; a means for automatically generating new image generation requests based on user preferences; means for transmitting an image generated based on a new image generation request to the terminal and automatically updating the display content; A system including:

2. 2. The system according to claim 1, further comprising means for transmitting an image generated based on a user's request from the server to the terminal.

3. 2. The system according to claim 1, further comprising means for transmitting image data generated based on an image generation request to the terminal and automatically updating the display content periodically.

Images