System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring images of a plurality of rooms captured by a user terminal; server means for analyzing the acquired images to generate a three dimensional model of the rooms; server means for receiving an image of a budget or a design from a user in a natural language and analyzing the image; server means for searching for a suitable furniture avatar based on an analysis result and arranging the furniture avatar in the three dimensional model; and server means for transmitting the generated three dimensional model and arrangement information of furniture to the user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the conventional interior design and furniture purchasing process, it is difficult for users to visualize the product layout of the entire room, and selecting the optimal furniture takes a great deal of time and effort. Furthermore, there are limited ways to efficiently propose custom furniture designs or request manufacturing, making it difficult to quickly and accurately reflect the user's requests. There is a need for a system that solves these issues, allowing users to easily realize their ideal room design and smoothly purchase and manufacture furniture. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: means for acquiring multiple room images taken by a user terminal; server means for analyzing the acquired images to generate a 3D model of the room; server means for receiving budget and design ideas from the user in natural language and analyzing them; server means for searching for suitable furniture avatars based on the analysis results and placing them in the 3D model; and server means for transmitting the generated 3D model and furniture placement information to the user terminal. The system also includes server means for analyzing custom furniture design requests received from users and generating designs for the custom furniture, and server means for transmitting the generated design information to a manufacturing factory, thereby meeting the needs of custom furniture. Furthermore, the system includes means for converting room images sent from the user terminal into a dedicated format, means for transmitting the converted format to the server, and means for displaying the 3D model data received from the server, allowing users to easily use the system to visually design actual rooms.

[0006] "User terminal" refers to a device that a user uses as an interface, such as a smartphone, tablet, or computer.

[0007] "Server means" refers to a device or service that receives data from a user terminal via a network, processes and analyzes it, and returns the results.

[0008] A "room image" refers to a digital photograph containing visual information about the interior of a room, taken using a camera on a user terminal.

[0009] A "3D model" is digital data that represents rooms and furniture in three-dimensional space, enabling visual simulation in a virtual space.

[0010] "Receiving and analyzing natural language" refers to the technical process of understanding the text or voice input of the user and interpreting their requests or instructions based on that.

[0011] "Furniture avatars" are virtual furniture pieces that are digital versions of real furniture and can be placed within a 3D model.

[0012] "Means of transformation" refers to the process or technology that changes data from one format to another.

[0013] "Search methods" refers to the techniques and processes used to locate information or items that match specified criteria in a database or on the Internet.

[0014] "Custom Furniture Design" refers to a newly created digital blueprint of a piece of furniture based on a user's specific needs and requirements.

[0015] "Means for transmitting to a manufacturing plant" refers to the technology and process for transmitting the generated digital design data to a manufacturing plant via a network.

[0016] "Means of converting to a specific format" refers to techniques for organizing data into a specific format or structure.

[0017] "Displaying means" refers to the techniques and processes by which digital data and graphics are visually represented on the screen of a user's terminal. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention relates to a system that allows users to take photos of their rooms using devices such as smartphones or tablets, and then uses AI to generate a 3D model of the room. Furthermore, users can input their budget and design image using natural language, and digital avatars of real furniture are placed within the 3D model based on that input. This allows users to create a virtual space and specifically consider the design of their ideal room.

[0040] System Programming and Processing

[0041] 3D room model generation

[0042] The user takes photos of the room from multiple angles using their device. The device then converts the images into a dedicated format and uploads them to the server. The server receives the images, analyzes them using AI technology, and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the app.

[0043] Enter your image and budget

[0044] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then uses natural language processing technology to analyze the received data and understand the user's preferences and budget.

[0045] Furniture selection and placement

[0046] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The selected furniture avatars are then placed in the 3D model. The server then sends the placed 3D model back to the terminal, allowing the user to virtually check the room design.

[0047] Custom furniture design and ordering

[0048] If a user cannot find the furniture they want, they can input a custom-made furniture design request via text or voice. The device then sends the custom-made request data to the server. The server analyzes the request and uses generative AI to create a custom furniture design. The generated design is then sent to a partner manufacturing factory as order data.

[0049] Specific examples

[0050] Photographing the room and generating 3DCG

[0051] The user takes three photos of their living room from different angles. The device uploads these photos to the server, which then uses AI analysis to generate a 3D model of the living room. The generated 3D model is sent to the device, where the user can view it through the app.

[0052] Enter your image and budget

[0053] The user enters into the app, "I want a Scandinavian-style living room with a budget of 200,000 yen." The device sends this information to the server, which analyzes it. Based on the results, the app searches a list of Scandinavian-style furniture and selects an appropriate furniture avatar.

[0054] Furniture selection and placement

[0055] The server places furniture avatars such as sofas, tables, and rugs from the search results into the 3D model, and the placed 3D model is sent to the device, allowing the user to view the virtual living room on the app.

[0056] Custom furniture design and ordering

[0057] If a user wants a cabinet with specific dimensions and design, but there is no matching furniture in the system, they can enter a custom-order request into the app. The device sends the request to the server, which uses AI to create a custom cabinet design and sends the order data to a partner factory.

[0058] In this way, the present invention allows users to virtually design their own rooms and easily realize their ideal interior. In addition, by supporting custom-made furniture, it is possible to meet the diverse needs of users.

[0059] The processing flow will be explained below.

[0060] 3DCG generation of rooms

[0061] Step 1:

[0062] A user uses their smartphone to take photos of a room from multiple angles.

[0063] Step 2:

[0064] The device imports the photos taken into a dedicated application and converts the photo data into a format that is easy to analyze.

[0065] Step 3:

[0066] The device uploads the converted photo data to the server by sending an upload request, and the server receives the request and returns permission.

[0067] Step 4:

[0068] The server receives the photo data and analyzes it using AI technology (e.g., image recognition algorithms) to determine the dimensions of the room and the location of furniture.

[0069] Step 5:

[0070] The server generates a 3D model based on the identified information, which is a virtual reproduction of the user's room.

[0071] Step 6:

[0072] The server sends the generated 3D model to the device, which receives the data and displays the 3D model within the application.

[0073] Enter your image and budget

[0074] Step 1:

[0075] The user inputs the image and budget for the room design using text or voice within the dedicated application.

[0076] Step 2:

[0077] The terminal transmits the user's input data to the server.

[0078] Step 3:

[0079] The server receives the input data and analyzes it using natural language processing technology, understanding the design image and budget details and extracting related keywords.

[0080] Furniture selection and placement

[0081] Step 1:

[0082] The server searches a furniture database based on the user's desired design and budget.

[0083] Step 2:

[0084] Based on the search results, it generates a list of matching furniture avatars, including sofas, tables, chairs, etc.

[0085] Step 3:

[0086] The server places the selected furniture avatars in the 3D model, using an algorithm to calculate the optimal placement.

[0087] Step 4:

[0088] The server sends 3D model data with furniture arranged on it to the terminal.

[0089] Step 5:

[0090] The device receives the data and displays a 3D model with the furniture arranged in it within the application, allowing the user to see the virtual design of the room.

[0091] Custom furniture design and ordering

[0092] Step 1:

[0093] The user enters a custom furniture design request via text or voice within the application.

[0094] Step 2:

[0095] The terminal sends custom request data to the server.

[0096] Step 3:

[0097] The server receives the request data and analyzes it to understand the custom furniture design desired by the user.

[0098] Step 4:

[0099] The server uses generative AI to create custom furniture designs, and the design process involves customizing the design based on the user's desired dimensions and style.

[0100] Step 5:

[0101] The server transmits the generated design data for the custom-made furniture to the partner factory as order data.

[0102] In this way, specific actions are performed at each step, allowing the user to efficiently simulate the design of a room, and smoothly select furniture and place custom orders.

[0103] Example 1

[0104] 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."

[0105] In today's residential environment, it takes a lot of time and effort for users to realize their ideal interior design, and designing and ordering custom furniture also requires specialized knowledge and skills. As a result, users often have to pay high costs and go through complicated procedures, making it difficult to easily create their ideal space. To solve this problem, there is a need for a system that allows users to easily design their own rooms virtually and also easily design and order custom furniture.

[0106] 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.

[0107] In this invention, the server includes means for acquiring multiple images of a room taken by a user terminal, server means for analyzing the acquired images and generating a three-dimensional model of the room, server means for receiving budget and design image information from the user in natural language and analyzing it, server means for searching for suitable furniture data based on the analysis results and arranging it in the three-dimensional model, and server means for transmitting the generated three-dimensional model and furniture arrangement information to the user terminal. This allows users to easily virtually design their own rooms and arrange furniture that best suits their budget and design image. In addition, custom furniture can be designed and ordered using the server means, reducing high costs and complicated procedures and realizing ideal spaces.

[0108] "User terminal" refers to an electronic device that a user directly operates to take images of a room, input data, and check a model. Specifically, this applies to a smartphone or tablet.

[0109] "Server means" refers to advanced computing devices installed on the cloud or within a network that are responsible for analyzing data, generating models, and sending and receiving information. Specifically, this refers to high-performance physical servers or virtual servers.

[0110] "Image analysis" refers to the process of extracting the shape and dimensions of a room from images taken by a user device and generating a 3D model based on that information. This process uses AI technology and algorithms.

[0111] A "3D model" refers to digital data that recreates the physical features of a room in three-dimensional space, allowing users to virtually view the interior of the room.

[0112] "Natural language processing" refers to the technology of analyzing text and voice data input by users and understanding their meaning. This technology is used to accurately grasp the user's intentions and requests.

[0113] "Furniture Data" refers to the digital information about furniture held by the system, including information such as the type, shape, dimensions, and price of the furniture.

[0114] "Placing in 3D model" refers to the process of placing the selected furniture data in the appropriate position within the 3D model, allowing the user to check the virtual room design.

[0115] "Custom-made furniture" refers to furniture that is newly designed based on a user's specific requirements. It is designed and manufactured to meet the user's individual needs.

[0116] "Manufacturing equipment" refers to equipment used to manufacture custom furniture based on the design information sent from the server. Specifically, this applies to processing machines and assembly machines installed in the production factory.

[0117] The "dedicated format" refers to a data format used to convert captured images into a format that can be analyzed by the server, improving data uniformity and analysis efficiency.

[0118] The present invention relates to a system that allows users to take photos of their rooms using devices such as smartphones or tablets, and then uses AI to generate a 3D model of the room. Furthermore, users can input their budget and design image using natural language, and digital avatars of real furniture are placed within the 3D model based on that input. This allows users to create a virtual space and specifically consider the design of their ideal room.

[0119] Hardware and software used

[0120] 1. Device: Use a smartphone or tablet. Specific examples include iPhone, iPad, and Android devices.

[0121] 2. Server: Use a high-performance server, such as AWS EC2 or Google Cloud Compute Engine.

[0122] 3. Image analysis technology: YOLO, OpenCV, etc. are used as image analysis algorithms.

[0123] 4. 3D modeling software: Blender, Autodesk Maya.

[0124] 5. Natural Language Processing (NLP): Uses OpenAI GPT and Google BERT.

[0125] 6. Generative AI model: OpenAI DALL-E, using Stable Diffusion.

[0126] System program and processing description

[0127] 3D room model generation

[0128] The user takes photos of the room from multiple angles using their device. The device converts the images into a dedicated format and uploads them to the server. The server receives the images, analyzes them using AI technology, and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the app.

[0129] Enter your image and budget

[0130] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then uses natural language processing technology to analyze the received data and understand the user's preferences and budget.

[0131] Furniture selection and placement

[0132] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The selected furniture avatars are then placed within the 3D model. The server then sends the placed 3D model back to the terminal, allowing the user to virtually check the room design.

[0133] Custom furniture design and ordering

[0134] If a user cannot find the furniture they want, they can input a custom-made furniture design request via text or voice. The device then sends the custom-made request data to the server. The server analyzes the request and uses generative AI to create a custom furniture design. The generated design is then sent to a partner manufacturing factory as order data.

[0135] Specific examples

[0136] Photographing the room and generating a 3D model

[0137] The user takes three photos of their living room from different angles. The device uploads these photos to the server, which then uses AI analysis to generate a 3D model of the living room. The generated 3D model is then sent to the device, where the user can view it through the app.

[0138] Enter your image and budget

[0139] The user enters into the app, "I want a Scandinavian-style living room with a budget of 200,000 yen." The device sends this information to the server, which analyzes it. Based on the results, the app searches a list of Scandinavian-style furniture and selects an appropriate furniture avatar.

[0140] Furniture selection and placement

[0141] The server places furniture avatars such as sofas, tables, and rugs from the search results into the 3D model, and the placed 3D model is sent to the device, allowing the user to view the virtual living room on the app.

[0142] Custom furniture design and ordering

[0143] If a user wants a cabinet with specific dimensions and design, but there is no matching furniture in the system, they can enter a custom-order request into the app. The device then sends the request to the server, which uses generative AI to create a custom cabinet design and sends the order data to the manufacturing equipment.

[0144] In this way, the present invention allows users to virtually design their own rooms and easily realize their ideal interior. In addition, by supporting custom-made furniture, it is possible to meet the diverse needs of users.

[0145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0146] Step 1:

[0147] The user takes photos of the room from multiple angles on their device. This is important to capture the entire room. The user uses a smartphone or tablet to take at least three photos from different angles. At this point, the input is a photo of the room, and the output is image data.

[0148] Step 2:

[0149] The device converts the captured image into a dedicated format. This conversion makes it easier to send the image to the server. Specifically, software on the device compresses the image and performs the format conversion. Through this process, the input image data is output as compressed image data.

[0150] Step 3:

[0151] The terminal uploads the converted image data to the server, where the data is transferred via the network. The input from the terminal is compressed image data, and the data is uploaded by sending it to the server.

[0152] Step 4:

[0153] The server receives the uploaded image and begins analysis. This analysis uses an image analysis algorithm (e.g., YOLO, OpenCV) to extract the room's shape and dimensions. Based on the input image data, the analyzed room's dimension and shape data is output.

[0154] Step 5:

[0155] The server generates a 3D model of the room based on the analysis results. 3D modeling software (e.g., Blender or Autodesk Maya) is used here. The input at this point is the analyzed room dimensions and shape data, and the 3D model data is output.

[0156] Step 6:

[0157] The server sends the generated 3D model to the terminal, and the user can view the 3D model through the application. The input is the generated 3D model data, and the model data is sent to the terminal as output.

[0158] Step 7:

[0159] The user inputs the image and budget for the room design using text or voice within the application. For example, they might input, "I want a Scandinavian-style living room with a budget of 200,000 yen." The input here is the user's text or voice data, which the device outputs as data.

[0160] Step 8:

[0161] The terminal transmits the user's input data to the server. The terminal forwards the user's text or voice input to the server, so the input is the user's text or voice data, and the output is the data transmitted to the server.

[0162] Step 9:

[0163] The server analyzes the received data using natural language processing (NLP) technology. Specifically, an NLP model (e.g., OpenAI GPT, Google BERT) understands the user's preferences and budget and extracts appropriate keywords. In this process, the input text data is analyzed and keywords and condition data based on the user's request are output.

[0164] Step 10:

[0165] The server searches for matching furniture avatars from a furniture database based on the analysis results. The server searches based on conditions such as "Scandinavian-style sofa" and "under 200,000 yen." The input is keywords and condition data from the analysis results, and the output is matching furniture data.

[0166] Step 11:

[0167] The server places the selected furniture avatars in the 3D model. Here, a 3D placement algorithm (e.g., Blender Python script) is used. The input data is the retrieved furniture data, and the output is the 3D model data with the furniture placed.

[0168] Step 12:

[0169] The server then sends the arranged 3D model back to the terminal. The user can then virtually check the room design. The input is the 3D model data with the furniture arranged, and the output is the model data sent to the terminal.

[0170] Step 13:

[0171] If the user cannot find the furniture they want, they can input their custom furniture design request into the application using text or voice. For example, they might input, "I want an antique-style cabinet that is 120cm wide and 80cm high." The input here is the user's text or voice data, and the device sends this as data output.

[0172] Step 14:

[0173] The terminal sends customized request data to the server. The input is the user's customized request data, and the output is the request data sent to the server.

[0174] Step 15:

[0175] The server analyzes the request and uses generative AI to create a custom furniture design. Specifically, a generative AI model (e.g., OpenAI DALL-E, Stable Diffusion) is used. The input data is the custom request data, and the output is the generated furniture design data.

[0176] Step 16:

[0177] The server sends the generated design to the manufacturing equipment as order data. The manufacturing equipment starts manufacturing the custom furniture based on the received design. The input is the generated design data, and the output is the order data sent to the manufacturing equipment.

[0178] (Application example 1)

[0179] 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."

[0180] In the past, there was no system that allowed users to easily generate a 3D model of their own room, and it was difficult to see in real time how the displayed furniture and decorations would affect the overall layout of the room.In addition, there was no efficient method that could quickly respond to user requests for designing and ordering custom furniture.

[0181] 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.

[0182] In this invention, the server includes means for acquiring a plurality of room images taken by a user terminal, server means for analyzing the acquired images and generating a three-dimensional model of the room, server means for receiving budget and design image from the user in natural language and analyzing them, server means for searching for suitable furniture avatars based on the analysis results and arranging them in the three-dimensional model, server means for transmitting the generated three-dimensional model and furniture arrangement information to the user terminal, and means for the user to virtually check and modify the room design in a virtual store. This allows users to virtually design their own rooms and easily realize their ideal interior.

[0183] A "user terminal" is a mobile information terminal used by a user, such as a smartphone, tablet, or smart glasses.

[0184] "Room images" are photographs of the room taken from multiple viewpoints by a user terminal.

[0185] A "3D model" is a three-dimensional digital model of a room generated from a two-dimensional image.

[0186] "Server means" refers to a computer system that has the function of receiving and analyzing data from a user terminal and returning necessary information to the user.

[0187] "Natural language" refers to the language that the user normally uses, and is a format in which instructions can be input by text or voice.

[0188] "Furniture avatars" are digital 3D models of real furniture that can be placed in a virtual space.

[0189] A "virtual store" is a virtual sales and design store space that exists on the Internet.

[0190] A "custom furniture design request" is a request submitted by a user when the user desires furniture with special dimensions or a specific design.

[0191] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new furniture designs based on user instructions.

[0192] A "prompt sentence" is specific input text used to give instructions to a generative AI model.

[0193] A "furniture layout" is the arrangement of furniture placed within a three-dimensional model based on the user's preferences.

[0194] The present invention relates to a system and method for virtually designing a room's interior. A user takes a photo of their room with a smart device, and a server analyzes the photo to generate a 3D model. Furthermore, the user inputs their budget and design image, and the system uses a generative AI model to place digital avatars of matching furniture on the 3D model.

[0195] This system uses the following hardware and software. The hardware includes a user device and a server, and user devices include smartphones, tablets, and smart glasses. The software includes an AI analysis tool for generating 3D models, a database search engine, a generative AI model, and a natural language processing engine.

[0196] The user device takes multiple images of the room and sends them to the server, which uses specialized software to analyze the images and generate a 3D model of the room. This 3D model is then sent to the user device, where the user can view it through an application.

[0197] Users input their budget and image for the room design in natural language. This can be input by text or voice and is sent from the user's device to the server. The server analyzes this data using a natural language processing engine and searches the system's database for digital avatars of furniture that match the user's preferences. A generative AI model is used to select the furniture, and a furniture layout that meets the user's requirements is generated.

[0198] As a specific example, if a user inputs a request such as "I want a monochrome living room with a budget of 300,000 yen," the server will input the following prompt sentence into the generative AI model:

[0199] "Generate a furniture layout for a modern monochrome living room with a budget of 300,000 yen. Provide 3D models in OBJ format."

[0200] This generates a matching furniture layout, which the server sends back to the user's device. The user can then review the virtual room design and make any necessary modifications. Custom furniture design requests can also be entered via text or voice, and the generative AI model will generate the design and place an order with the manufacturing factory.

[0201] This system allows users to design their own rooms in a virtual space, allowing them to consider their ideal interior in a realistic manner, and also allows for custom-made furniture.

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1:

[0204] A user uses a smart device to take pictures of their room from multiple angles. The input is the multiple images of the room taken. The device acquires these images and prepares them as data to send to the server. The output is image data prepared for sending to the server.

[0205] Step 2:

[0206] The device sends the captured images of the room to the server. The input is the image data prepared in step 1. The device uploads these images to the server via the Internet. The output is the image data uploaded to the server.

[0207] Step 3:

[0208] The server analyzes the received image data and generates a 3D model. The input is the image data uploaded to the server. The server uses AI technology to analyze the image features and generate a three-dimensional 3D model. The output is the generated 3D model data.

[0209] Step 4:

[0210] The server sends the generated 3D model to the user terminal. The input is the 3D model data generated in step 3. The server returns this data to the terminal, where the model is displayed. The output is the 3D model displayed on the user terminal.

[0211] Step 5:

[0212] The user uses the application to input a room design image and budget in natural language. The input is natural language text or voice data about the budget and design image. The device prepares this data to send to the server. The output is natural language data prepared for sending to the server.

[0213] Step 6:

[0214] The terminal sends the input design image and budget information to the server. The input is the natural language data prepared in step 5. The terminal uploads this data to the server. The output is the natural language data sent to the server.

[0215] Step 7:

[0216] The server analyzes the received natural language data. The input is the natural language data sent to the server. The server uses natural language processing technology to analyze the user's preferences and budget and identify suitable furniture. The output is a list of specific furniture items as a result of the analysis.

[0217] Step 8:

[0218] Based on the analysis results, the server searches for suitable furniture avatars from the system's database and places them in the 3D model. The input is the analysis results obtained in step 7 and the furniture information in the database. The server uses a generative AI model to generate prompt sentences and determine the optimal furniture layout. The output is 3D model data with the furniture avatars placed.

[0219] Step 9:

[0220] The server sends the 3D model data and furniture layout information to the user terminal. The input is the 3D model data generated in step 8. The server sends this data to the user terminal so that the furniture layout can be confirmed on the terminal. The output is the furniture layout information displayed on the user terminal.

[0221] Step 10:

[0222] A user inputs a custom furniture design request. The input is natural language text or voice data about the dimensions and design of the custom furniture. The terminal prepares this data for transmission to the server. The output is the custom furniture request data prepared for transmission to the server.

[0223] Step 11:

[0224] The server analyzes the custom furniture request and generates the custom furniture design using a generative AI model. The input is the custom furniture request data sent to the server. The server uses the generative AI model to generate prompt sentences and create a new furniture design. The output is the generated custom furniture design data.

[0225] Step 12:

[0226] The server sends the generated design information of the custom-made furniture to the manufacturing factory. The input is the design data of the custom-made furniture generated in step 11. The server sends this data to the manufacturing factory and requests the manufacturing of the custom-made furniture. The output is the design information of the custom-made furniture sent to the manufacturing factory.

[0227] 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.

[0228] This invention relates to a system that generates a 3D model based on images of multiple rooms taken by a user device and simulates furniture placement based on user instructions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it proposes optimal designs according to the user's emotions.

[0229] System Programming and Processing

[0230] 3D room model generation

[0231] Users use a device such as a smartphone or tablet to take photos of their room from multiple angles. The device then imports these photos into a dedicated application and converts them into a dedicated format. The device then uploads the converted photo data to a server. The server uses AI technology to analyze the received photos and generate a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the application.

[0232] Enter your image and budget

[0233] Users input their image of the room design and their budget using text or voice within the application. The device sends the input data to the server, which then analyzes it using natural language processing technology, extracting and understanding related keywords.

[0234] Furniture selection and placement

[0235] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The server then places the selected furniture avatars within the 3D model and determines their placement using an algorithm to calculate the optimal placement. The 3D model with the furniture placed is then sent back to the terminal, allowing the user to check the room design in the virtual space.

[0236] Custom furniture design and ordering

[0237] If the desired furniture item cannot be found, the user can input a design request for custom furniture via text or voice within the application. The device then sends the request data to the server, which analyzes it and uses generative AI to create a custom furniture design. The generated design data is then sent to a partner manufacturing factory.

[0238] Incorporating an emotion engine

[0239] Emotion Recognition and Analysis

[0240] The emotion engine recognizes emotions from the user's facial expressions and voice. For example, it captures the user's facial expressions through a camera and analyzes the facial expression data to identify the user's emotional state. When using voice recognition, it evaluates emotions from the user's tone of voice and speaking style.

[0241] Emotion-based design adjustments

[0242] The server receives the user's emotional data recognized by the emotion engine. Based on this emotional data, the server adjusts the design image and layout. For example, if the user is feeling stressed, it can suggest a relaxing interior style. It is also possible to dynamically change the furniture layout within the 3D model in real time according to changes in the user's emotions.

[0243] Specific examples

[0244] Photographing the room and generating 3DCG

[0245] The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos to generate a 3D model of the living room and sends it to the device. The user can then view the 3D model in the application.

[0246] Emotion Recognition and Furniture Placement

[0247] When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine analyzes the user's facial expression and recognizes that they are in a relaxed state. Based on this information, the server selects a Scandinavian-style furniture avatar that will help them relax and places it on the 3D model.

[0248] Custom furniture design and ordering

[0249] If a user wants a cabinet with specific dimensions and design, they input their request. The device sends the request to the server, which uses generative AI to create a custom cabinet design and sends the design data to a partner factory.

[0250] In this way, the present invention allows users to easily simulate room designs in real time, allowing them to smoothly select furniture and order custom-made furniture. Furthermore, by incorporating an emotion engine, it is possible to propose optimal designs according to the user's emotional state.

[0251] The processing flow will be explained below.

[0252] 3DCG generation of rooms

[0253] Step 1:

[0254] A user uses their smartphone to take photos of a room from multiple angles.

[0255] Step 2:

[0256] The device imports multiple photos taken into a dedicated application and converts them into a format that is easy to process.

[0257] Step 3:

[0258] The terminal transmits a request to upload the converted photo data to the server.

[0259] Step 4:

[0260] The server receives the upload request and returns permission, allowing the device to send the photo data to the server.

[0261] Step 5:

[0262] The server then analyzes the received photos using AI technology (e.g., image recognition algorithms), measuring the room's dimensions and identifying key furniture and features.

[0263] Step 6:

[0264] The server generates a 3D model of the room based on the analysis results. This 3D model is a virtual reproduction of the user's room.

[0265] Step 7:

[0266] The server encodes the generated 3D model and transmits it to the terminal.

[0267] Step 8:

[0268] The terminal displays the received three-dimensional model data, allowing the user to confirm the results.

[0269] Enter your image and budget

[0270] Step 1:

[0271] The user enters the image and budget for the room design using text or voice within the application.

[0272] Step 2:

[0273] The terminal sends the user's input to the server in the appropriate format.

[0274] Step 3:

[0275] The server receives the input and analyzes it using natural language processing technology, extracting relevant keywords based on the design image and budget.

[0276] Furniture selection and placement

[0277] Step 1:

[0278] Based on the analysis results, the server searches for matching furniture avatars from a furniture database, using keywords such as "Scandinavian style" or "relaxing."

[0279] Step 2:

[0280] The server compiles a list of multiple furniture avatars selected from the search results.

[0281] Step 3:

[0282] The server then places the furniture in the 3D model based on the list, running an algorithm to calculate, for example, where to place sofas and tables.

[0283] Step 4:

[0284] The server encodes a three-dimensional model with the furniture arranged and sends it to the terminal.

[0285] Step 5:

[0286] The terminal displays the received data, allowing the user to check the design of the virtual room.

[0287] Custom furniture design and ordering

[0288] Step 1:

[0289] If a user wants custom furniture, they enter their design request in the application by text or voice.

[0290] Step 2:

[0291] The terminal sends custom request data to the server.

[0292] Step 3:

[0293] The server receives the customization request and performs analysis to understand the requirements of the user's desired custom furniture.

[0294] Step 4:

[0295] The server uses generative AI to create custom furniture designs, such as cabinets based on user-specified dimensions and styles.

[0296] Step 5:

[0297] The server sends the generated design data for custom-made furniture to the partner factory and starts the ordering process.

[0298] Emotion engine built-in

[0299] Step 1:

[0300] While the user is using the application, the emotion engine captures the user's facial expressions and voice data through the camera and microphone.

[0301] Step 2:

[0302] The device transmits the captured facial expression data and voice data to the server.

[0303] Step 3:

[0304] The server uses an emotion engine to analyze the received data and identify the user's emotional state.

[0305] Step 4:

[0306] The server adjusts the design image and furniture layout based on the recognized emotion data. For example, if the user is feeling stressed, it will suggest interior design that has a relaxing effect.

[0307] Step 5:

[0308] The server transmits three-dimensional model data that has been dynamically updated in accordance with the emotion data to the terminal.

[0309] Step 6:

[0310] The device displays the received data, allowing users to see room designs that correspond to their emotions in real time.

[0311] In this way, the system of the present invention provides optimal room designs tailored to the user's needs through multiple processing steps, and also supports custom-made furniture. Furthermore, by using an emotion engine, it is possible to propose personalized designs based on the user's emotional state.

[0312] Example 2

[0313] 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."

[0314] Conventional interior design systems require users to manually select and arrange furniture, which is time-consuming, and it is difficult to adjust the design based on the user's emotional state. Furthermore, they lack the functionality to accept custom furniture design requests, or the ability to propose designs that reflect the user's specific image and budget. These issues need to be resolved.

[0315] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring a plurality of room images taken by a user terminal, means for analyzing the acquired images to generate a 3D model of the room, means for receiving budget and design image from the user in natural language and analyzing the same, means for searching for suitable furniture avatars based on the analysis results and arranging them in the 3D model, means for transmitting the generated 3D model and furniture arrangement information to the user terminal, means for recognizing the user's emotions, and means for adjusting the design based on the user's emotions. This allows the user to easily create a 3D model of a room and simulate furniture arrangement based on the user's budget and design image, as well as request a design for custom-made furniture, and further enables optimal design proposals to be made in response to the user's emotions.

[0316] A "user terminal" is a device operated by a user, and includes mobile information terminals such as smartphones and tablets.

[0317] "Room images" refer to photographic data that captures the interior of a room from multiple angles and is taken with a user terminal.

[0318] A "three-dimensional model" is a digital representation of the three-dimensional structure of a room, generated by analyzing an image of the room.

[0319] A "server" refers to a computer system that receives and processes requests from multiple clients (here, user terminals).

[0320] "Budget" refers to the amount of money a user can spend on the interior design of a room.

[0321] "Design image" refers to a specific visual or theme related to the room decoration or interior style desired by the user.

[0322] "Natural language" refers to a language that humans use on a daily basis, i.e., information expressed in spoken or text form.

[0323] "Furniture avatars" are digital models stored in the system's furniture database, and refer to virtual furniture data that can be placed within a three-dimensional model of a room.

[0324] "Emotion recognition" refers to a technology that analyzes and identifies a user's emotional state from their facial expressions and voice.

[0325] "Generative AI" refers to artificial intelligence technology that generates new digital data (such as custom furniture designs) based on given prompts.

[0326] "Custom-made furniture" refers to furniture that is made to order for a user to request specific dimensions and designs.

[0327] This system generates a 3D model based on multiple images of a room taken with a user device and simulates furniture placement based on the user's instructions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to propose optimal designs based on the user's emotions.

[0328] System Overview

[0329] Users take photos of their rooms using devices such as smartphones or tablets. These photos are captured by a dedicated application, converted into a dedicated format, and then uploaded to a server. The server analyzes the received image data and generates a 3D model of the room. This process uses Google's TensorFlow AI technology. The generated 3D model is then sent back to the device, where the user can view it through the application.

[0330] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then analyzes it using natural language processing technology (e.g., OpenAI's GPT-3). As a result, relevant keywords are extracted and understood, and matching furniture avatars are searched for within the system's furniture database.

[0331] Furniture placement and custom furniture generation

[0332] The server places the selected furniture avatars within the 3D model and determines the optimal layout. This process uses genetic algorithms and A-search. The placed 3D model is then sent back to the terminal, allowing the user to check the room design in the virtual space.

[0333] If the desired furniture item cannot be found, the user can input a design request for custom furniture via text or voice within the application. This request is sent to the server, which then uses generative AI (e.g., OpenAI's GPT-3) to create a custom furniture design. The generated design data is then sent to a partner manufacturing factory.

[0334] Incorporating an emotion engine

[0335] The emotion engine recognizes emotions from the user's facial expressions and voice. For example, it captures the user's facial expressions through the camera and analyzes the facial data using Microsoft's Azure Face API. When using speech recognition, it analyzes the user's voice using Google Cloud Speech-to-Text API and evaluates emotions from the tone and speaking style.

[0336] The server receives the user's emotional data recognized by the emotion engine and adjusts the design image and layout based on this emotional data. If the user is feeling stressed, the server will suggest a relaxing interior style. It is also possible to dynamically change the furniture layout within the 3D model in real time.

[0337] Specific examples

[0338] Photographing the room and generating 3DCG

[0339] The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos using Google's TensorFlow, generates a 3D model of the living room, and sends it to the device. The user can then view the 3D model in the application.

[0340] Emotion Recognition and Furniture Placement

[0341] When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine simultaneously analyzes the user's facial expressions using Microsoft's Azure Face API and recognizes that the user is in a relaxed state. Based on this information, the server selects a Scandinavian-style furniture avatar that will help them relax and places it on the 3D model.

[0342] Custom furniture design and ordering

[0343] If a user wants a cabinet with specific dimensions and design, they input their request, and the device sends it to the server, which uses OpenAI's GPT-3 to create a custom cabinet design and sends the design data to the manufacturing factory.

[0344] Prompt Sentence Examples

[0345] "I'd like to create a relaxing Scandinavian-style living room. My budget is within 200,000 yen. Please suggest some designs that I can use as reference for furniture layout and colors."

[0346] This allows users to easily simulate room designs and smoothly select and order custom furniture. Furthermore, by incorporating an emotion engine, it is possible to propose optimal designs according to the user's emotional state.

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1: Take a photo of your room and upload it

[0349] A user takes photos of a room from multiple angles using a smartphone or tablet. The device imports the photos into a dedicated application and converts them from JPEG format to a dedicated format (for example, XYZ format). This format conversion is performed to standardize and compress the image data. The device then uploads the converted data to the server via an HTTP request. The input is an image of the room, and the output is image data in the dedicated format that is sent to the server.

[0350] Step 2: 3D model generation

[0351] The server analyzes the received image data using AI technology (Google's TensorFlow) and generates a 3D model of the room. Specifically, it digitizes the three-dimensional structure of the room as point cloud and mesh data based on images taken from multiple angles. The input is image data in a dedicated format, and the output is a 3D model (OBJ format). The server sends the generated 3D model to the terminal as an HTTP response. The user can view the 3D model through an application.

[0352] Step 3: Enter your image and budget

[0353] Within the application, the user inputs the image and budget for the room design using text or voice. The device sends this input data to the server via a POST request. The input is the user's text or voice data, and the output is natural language data sent to the server. For example, the user might input, "I want a Scandinavian-style living room with a budget of 200,000 yen."

[0354] Step 4: Image and budget analysis

[0355] The server uses natural language processing technology (OpenAI GPT-3) to analyze the image and budget data received from the user. This allows it to extract and understand the keywords "Scandinavian style" and "200,000 yen." The input is the transmitted natural language data, and the output is the analyzed keywords and phrases.

[0356] Step 5: Select and arrange furniture

[0357] Based on the analysis results, the server searches for suitable furniture avatars from the furniture database within the system. The retrieved furniture avatars are placed within the 3D model, and a genetic algorithm or A-search is used to determine the optimal placement. The input is the analyzed keywords and the 3D model, and the output is an updated 3D model with the furniture arranged. The server sends this updated 3D model to the terminal. The user can then check the room design in the virtual space using the application.

[0358] Step 6: Custom Furniture Design Request

[0359] If a user desires furniture with specific dimensions or design, they input a custom furniture design request within the application. The device sends the request data to the server. The input is a text or voice design request from the user, and the output is the request data sent to the server. For example, a user might input, "I'm looking for a Scandinavian-style cabinet that is 150cm wide and 75cm high."

[0360] Step 7: Create and submit your custom furniture design

[0361] The server uses generative AI (OpenAI's GPT-3) to create custom furniture designs. The generated design data (e.g., PNG format) is sent to partner manufacturing factories via email or a dedicated API. The input is the user's design request data, and the output is the custom furniture design data sent to the manufacturing factory.

[0362] Step 8: Emotion Recognition

[0363] The emotion engine, which recognizes emotions from the user's facial expressions and voice, captures user data using the device's camera and microphone. Emotion analysis is performed using Microsoft's Azure Face API and Google Cloud Speech-to-Text API. The input is the user's facial expression data and voice data, and the output is analyzed emotion data. For example, if the user enables the camera function, the emotion engine recognizes that the user is relaxed.

[0364] Step 9: Adjust your design based on emotion

[0365] The server adjusts the design image and furniture layout based on the emotional data obtained through emotion recognition. In particular, if the user is feeling stressed, it suggests a relaxing interior style. The input is the analyzed emotional data, and the output is an adjusted 3D model and design proposal. The adjusted design is sent to the user's device, and the user can view the updated design in the application.

[0366] (Application example 2)

[0367] 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."

[0368] Conventional interior design simulation systems have difficulty providing satisfying interior designs because they do not adequately consider the user's emotions when proposing designs. In addition, the design creation and ordering process for custom furniture is complicated and lacks automation.

[0369] The specification processing by the specification 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 acquiring multiple room images taken by a user terminal, means for analyzing the acquired images to generate a three-dimensional model of the room, means for receiving and analyzing the user's budget and design image in natural language, means for searching for suitable furniture avatars based on the analysis results and placing them in the three-dimensional model, means for transmitting the generated three-dimensional model and furniture placement information to the user terminal, emotion recognition means for recognizing the user's emotion, and means for proposing an optimal design based on the recognized emotion data. This makes it possible to propose optimal interior designs based on the user's emotions and to automate the design, creation, and ordering of custom furniture.

[0370] A "user terminal" is an electronic device that can be operated by a user, and includes smartphones, tablets, smart glasses, head-mounted displays, etc.

[0371] The term "server means" refers to a server system for analyzing captured images, generating three-dimensional models, analyzing natural language, placing furniture avatars, and transmitting generated data.

[0372] "Emotion recognition means" refers to a device or software that has the function of analyzing and recognizing emotions from a user's facial expressions and voice.

[0373] "Furniture avatar" refers to a three-dimensional model of furniture used in interior simulations in a virtual space.

[0374] "Custom furniture" refers to furniture that is designed and manufactured based on a user's specific requirements.

[0375] "Generative AI model" refers to an artificial intelligence model that automatically generates custom furniture designs based on input data.

[0376] The present invention provides a system for generating a three-dimensional model based on images of a plurality of rooms taken by a user terminal, and proposing an interior design based on the user's emotions. Specific embodiments will be described below.

[0377] System configuration

[0378] Hardware

[0379] User devices: smartphones, tablets, smart glasses, head-mounted displays, etc.

[0380] Server: Cloud servers with high-performance computing power and storage (e.g. AWS, Google Cloud).

[0381] Emotion recognition devices: Cameras and microphones that can analyze a user's facial expressions and voice (e.g., high-resolution webcams, directional microphones).

[0382] software

[0383] Image processing library: An image analysis library for generating 3D models, such as OpenCV.

[0384] Natural language processing engine: An engine for parsing user input data (e.g., NLTK, spaCy).

[0385] Emotion Recognition Library: A library for recognizing user emotions (e.g., Affectiva SDK).

[0386] Generative AI models: Models for automatically generating custom furniture designs (e.g., TensorFlow).

[0387] System Operation

[0388] 3D room model generation

[0389] Users use devices such as smartphones, tablets, or smart glasses to take photos of their room from multiple angles. The device then imports these photos into a dedicated application and converts them into a dedicated format. The device then uploads the converted photo data to a server. The server analyzes the received photos and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the application.

[0390] Emotion Recognition and Design Proposals

[0391] An emotion recognition device is used to capture the user's facial expressions and voice, and this data is analyzed using an emotion recognition library. The analysis results are sent to a server, which then adjusts the design image and layout based on the user's emotional state. This design proposal provides an interior style that the user can relax in, and dynamically changes the furniture layout in real time according to changes in emotion.

[0392] Custom furniture design and ordering

[0393] If a user desires furniture with specific dimensions and design, they input their custom furniture request within the application. The device then sends the request data to the server, which then uses a generative AI model to create a custom furniture design. The generated design data is then sent to partner manufacturing factories. This allows users to quickly design and order the custom furniture they desire.

[0394] Specific examples

[0395] Room photography and 3D model generation: The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos to generate a 3D model of the living room and sends it to the device. The user can then view the 3D model in the application.

[0396] Emotion recognition and furniture placement: When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine analyzes the user's facial expression and recognizes that the user is in a relaxed state. Based on this information, the server selects Scandinavian-style furniture avatars that will help the user relax and places them on the 3D model.

[0397] Design and order custom furniture: If a user wants a cabinet with specific dimensions and design, they input the request. The device sends the request to the server, which uses a generative AI model to create a custom cabinet design and sends the design data to a partner factory.

[0398] Prompt Sentence Examples

[0399] "Using an emotion engine, can you suggest a Scandinavian-inspired living room design that would suit a user with a relaxed expression? Also, can you tell us about a system that creates custom cabinets and automates the process of placing an order?"

[0400] As described above, the system of the present invention efficiently proposes interior designs based on the user's emotions and designs and orders custom-made furniture.

[0401] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0402] Step 1:

[0403] The user uses a device (smartphone, tablet, smart glasses, head-mounted display, etc.) to take photos of the room from multiple angles. The input is multiple images of the room, which are then converted into a dedicated format. The converted image data is uploaded from the device to the server. The server receives the uploaded image data and prepares it for 3D model generation.

[0404] Step 2:

[0405] The server analyzes the received image data and generates a 3D model of the room using photogrammetry techniques (e.g., image processing libraries such as OpenCV). This process involves extracting feature points from the images and reconstructing a 3D point cloud from multiple images. The output is the generated 3D model of the room.

[0406] Step 3:

[0407] The generated 3D model is then sent from the server to the user's device. The device receives this data and allows the user to visually confirm it. The input is the 3D model data sent from the server, and the output is the display of the 3D model on the device. The user can use this model to check the layout of the room.

[0408] Step 4:

[0409] The user inputs the budget and image of the room design on the device. This input data is in natural language, so the device sends it to the server. The server uses a natural language processing engine (e.g., NLTK, spaCy) to analyze the input data and extract relevant keywords. The input is the user's text or voice data, and the output is the analyzed keywords.

[0410] Step 5:

[0411] The server searches for matching furniture avatars from a furniture database based on the analyzed keywords. The retrieved furniture avatars are placed in the 3D model. Based on this, the optimal furniture placement is calculated. The output is a 3D model containing the placed furniture avatars.

[0412] Step 6:

[0413] An emotion recognition device (camera, microphone, etc.) is used to capture the user's facial expressions and voice. The input is the user's facial image and voice data. This data is analyzed by an emotion recognition library (e.g., Affectiva SDK) to recognize the user's emotional state. The output is the recognized user's emotional data.

[0414] Step 7:

[0415] The server adjusts design suggestions based on the emotion data. For example, if it determines that the user is relaxed, it will suggest a relaxing interior style. This suggestion is reflected in the 3D model in real time. The input is the recognized emotion data, and the output is the adjusted design suggestion.

[0416] Step 8:

[0417] When a user wants custom furniture with specific dimensions and design, they input their custom furniture request in the application. This request data is sent to the server. The server uses a generative AI model (e.g., TensorFlow) to create a custom furniture design and sends the design data to a partner manufacturing factory. The input is the user's custom furniture request data, and the output is the generated furniture design data.

[0418] In this way, this system efficiently proposes optimal interior designs based on the user's emotions and designs and orders custom furniture.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] [Second embodiment]

[0423] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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."

[0435] The present invention relates to a system that allows users to take photos of their rooms using devices such as smartphones or tablets, and then uses AI to generate a 3D model of the room. Furthermore, users can input their budget and design image using natural language, and digital avatars of real furniture are placed within the 3D model based on that input. This allows users to create a virtual space and specifically consider the design of their ideal room.

[0436] System Programming and Processing

[0437] 3D room model generation

[0438] The user takes photos of the room from multiple angles using their device. The device then converts the images into a dedicated format and uploads them to the server. The server receives the images, analyzes them using AI technology, and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the app.

[0439] Enter your image and budget

[0440] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then uses natural language processing technology to analyze the received data and understand the user's preferences and budget.

[0441] Furniture selection and placement

[0442] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The selected furniture avatars are then placed in the 3D model. The server then sends the placed 3D model back to the terminal, allowing the user to virtually check the room design.

[0443] Custom furniture design and ordering

[0444] If a user cannot find the furniture they want, they can input a custom-made furniture design request via text or voice. The device then sends the custom-made request data to the server. The server analyzes the request and uses generative AI to create a custom furniture design. The generated design is then sent to a partner manufacturing factory as order data.

[0445] Specific examples

[0446] Photographing the room and generating 3DCG

[0447] The user takes three photos of their living room from different angles. The device uploads these photos to the server, which then uses AI analysis to generate a 3D model of the living room. The generated 3D model is then sent to the device, where the user can view it through the app.

[0448] Enter your image and budget

[0449] The user enters into the app, "I want a Scandinavian-style living room with a budget of 200,000 yen." The device sends this information to the server, which analyzes it. Based on the results, the app searches a list of Scandinavian-style furniture and selects an appropriate furniture avatar.

[0450] Furniture selection and placement

[0451] The server places furniture avatars such as sofas, tables, and rugs from the search results into the 3D model, and the placed 3D model is sent to the device, allowing the user to view the virtual living room on the app.

[0452] Custom furniture design and ordering

[0453] If a user wants a cabinet with specific dimensions and design, but there is no matching furniture in the system, they can enter a custom-order request into the app. The device sends the request to the server, which uses AI to create a custom cabinet design and sends the order data to a partner factory.

[0454] In this way, the present invention allows users to virtually design their own rooms and easily realize their ideal interior. In addition, by supporting custom-made furniture, it is possible to meet the diverse needs of users.

[0455] The processing flow will be explained below.

[0456] 3DCG generation of rooms

[0457] Step 1:

[0458] A user uses their smartphone to take photos of a room from multiple angles.

[0459] Step 2:

[0460] The device imports the photos taken into a dedicated application and converts the photo data into a format that is easy to analyze.

[0461] Step 3:

[0462] The device uploads the converted photo data to the server by sending an upload request, and the server receives the request and returns permission.

[0463] Step 4:

[0464] The server receives the photo data and analyzes it using AI technology (e.g., image recognition algorithms) to determine the dimensions of the room and the location of furniture.

[0465] Step 5:

[0466] The server generates a 3D model based on the identified information, which is a virtual reproduction of the user's room.

[0467] Step 6:

[0468] The server sends the generated 3D model to the device, which receives the data and displays the 3D model within the application.

[0469] Enter your image and budget

[0470] Step 1:

[0471] The user inputs the image and budget for the room design using text or voice within the dedicated application.

[0472] Step 2:

[0473] The terminal transmits the user's input data to the server.

[0474] Step 3:

[0475] The server receives the input data and analyzes it using natural language processing technology, understanding the design image and budget details and extracting related keywords.

[0476] Furniture selection and placement

[0477] Step 1:

[0478] The server searches a furniture database based on the user's desired design and budget.

[0479] Step 2:

[0480] Based on the search results, it generates a list of matching furniture avatars, including sofas, tables, chairs, etc.

[0481] Step 3:

[0482] The server places the selected furniture avatars in the 3D model, using an algorithm to calculate the optimal placement.

[0483] Step 4:

[0484] The server sends 3D model data with furniture arranged on it to the terminal.

[0485] Step 5:

[0486] The device receives the data and displays a 3D model with the furniture arranged in it within the application, allowing the user to see the virtual design of the room.

[0487] Custom furniture design and ordering

[0488] Step 1:

[0489] The user enters a custom furniture design request via text or voice within the application.

[0490] Step 2:

[0491] The terminal sends custom request data to the server.

[0492] Step 3:

[0493] The server receives the request data and analyzes it to understand the custom furniture design desired by the user.

[0494] Step 4:

[0495] The server uses generative AI to create custom furniture designs, and the design process involves customizing the design based on the user's desired dimensions and style.

[0496] Step 5:

[0497] The server transmits the generated design data for the custom-made furniture to the partner factory as order data.

[0498] In this way, specific actions are performed at each step, allowing the user to efficiently simulate the design of a room, and smoothly select furniture and place custom orders.

[0499] Example 1

[0500] 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."

[0501] In today's residential environment, it takes a lot of time and effort for users to realize their ideal interior design, and designing and ordering custom furniture also requires specialized knowledge and skills. As a result, users often have to pay high costs and go through complicated procedures, making it difficult to easily create their ideal space. To solve this problem, there is a need for a system that allows users to easily design their own rooms virtually and also easily design and order custom furniture.

[0502] 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.

[0503] In this invention, the server includes means for acquiring multiple images of a room taken by a user terminal, server means for analyzing the acquired images and generating a three-dimensional model of the room, server means for receiving budget and design image information from the user in natural language and analyzing it, server means for searching for suitable furniture data based on the analysis results and arranging it in the three-dimensional model, and server means for transmitting the generated three-dimensional model and furniture arrangement information to the user terminal. This allows users to easily virtually design their own rooms and arrange furniture that best suits their budget and design image. In addition, custom furniture can be designed and ordered using the server means, reducing high costs and complicated procedures and realizing ideal spaces.

[0504] "User terminal" refers to an electronic device that a user directly operates to take images of a room, input data, and check a model. Specifically, this applies to a smartphone or tablet.

[0505] "Server means" refers to advanced computing devices installed on the cloud or within a network that are responsible for analyzing data, generating models, and sending and receiving information. Specifically, this refers to high-performance physical servers or virtual servers.

[0506] "Image analysis" refers to the process of extracting the shape and dimensions of a room from images taken by a user device and generating a 3D model based on that information. This process uses AI technology and algorithms.

[0507] A "3D model" refers to digital data that recreates the physical features of a room in three-dimensional space, allowing users to virtually view the interior of the room.

[0508] "Natural language processing" refers to the technology of analyzing text and voice data input by users and understanding their meaning. This technology is used to accurately grasp the user's intentions and requests.

[0509] "Furniture Data" refers to the digital information about furniture held by the system, including information such as the type, shape, dimensions, and price of the furniture.

[0510] "Placing in 3D model" refers to the process of placing the selected furniture data in the appropriate position within the 3D model, allowing the user to check the virtual room design.

[0511] "Custom-made furniture" refers to furniture that is newly designed based on a user's specific requirements. It is designed and manufactured to meet the user's individual needs.

[0512] "Manufacturing equipment" refers to equipment used to manufacture custom furniture based on the design information sent from the server. Specifically, this applies to processing machines and assembly machines installed in the production factory.

[0513] The "dedicated format" refers to a data format used to convert captured images into a format that can be analyzed by the server, improving data uniformity and analysis efficiency.

[0514] The present invention relates to a system that allows users to take photos of their rooms using devices such as smartphones or tablets, and then uses AI to generate a 3D model of the room. Furthermore, users can input their budget and design image using natural language, and digital avatars of real furniture are placed within the 3D model based on that input. This allows users to create a virtual space and specifically consider the design of their ideal room.

[0515] Hardware and software used

[0516] 1. Device: Use a smartphone or tablet. Specific examples include iPhone, iPad, and Android devices.

[0517] 2. Server: Use a high-performance server, such as AWS EC2 or Google Cloud Compute Engine.

[0518] 3. Image analysis technology: YOLO, OpenCV, etc. are used as image analysis algorithms.

[0519] 4. 3D modeling software: Blender, Autodesk Maya.

[0520] 5. Natural Language Processing (NLP): Uses OpenAI GPT and Google BERT.

[0521] 6. Generative AI model: OpenAI DALL-E, using Stable Diffusion.

[0522] System program and processing description

[0523] 3D room model generation

[0524] The user takes photos of the room from multiple angles using their device. The device converts the images into a dedicated format and uploads them to the server. The server receives the images, analyzes them using AI technology, and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the app.

[0525] Enter your image and budget

[0526] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then uses natural language processing technology to analyze the received data and understand the user's preferences and budget.

[0527] Furniture selection and placement

[0528] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The selected furniture avatars are then placed within the 3D model. The server then sends the placed 3D model back to the terminal, allowing the user to virtually check the room design.

[0529] Custom furniture design and ordering

[0530] If a user cannot find the furniture they want, they can input a custom-made furniture design request via text or voice. The device then sends the custom-made request data to the server. The server analyzes the request and uses generative AI to create a custom furniture design. The generated design is then sent to a partner manufacturing factory as order data.

[0531] Specific examples

[0532] Photographing the room and generating a 3D model

[0533] The user takes three photos of their living room from different angles. The device uploads these photos to the server, which then uses AI analysis to generate a 3D model of the living room. The generated 3D model is then sent to the device, where the user can view it through the app.

[0534] Enter your image and budget

[0535] The user enters into the app, "I want a Scandinavian-style living room with a budget of 200,000 yen." The device sends this information to the server, which analyzes it. Based on the results, the app searches a list of Scandinavian-style furniture and selects an appropriate furniture avatar.

[0536] Furniture selection and placement

[0537] The server places furniture avatars such as sofas, tables, and rugs from the search results into the 3D model, and the placed 3D model is sent to the device, allowing the user to view the virtual living room on the app.

[0538] Custom furniture design and ordering

[0539] If a user wants a cabinet with specific dimensions and design, but there is no matching furniture in the system, they can enter a custom-order request into the app. The device then sends the request to the server, which uses generative AI to create a custom cabinet design and sends the order data to the manufacturing equipment.

[0540] In this way, the present invention allows users to virtually design their own rooms and easily realize their ideal interior. In addition, by supporting custom-made furniture, it is possible to meet the diverse needs of users.

[0541] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0542] Step 1:

[0543] The user takes photos of the room from multiple angles on their device. This is important to capture the entire room. The user uses a smartphone or tablet to take at least three photos from different angles. At this point, the input is a photo of the room, and the output is image data.

[0544] Step 2:

[0545] The device converts the captured image into a dedicated format. This conversion makes it easier to send the image to the server. Specifically, software on the device compresses the image and performs the format conversion. Through this process, the input image data is output as compressed image data.

[0546] Step 3:

[0547] The terminal uploads the converted image data to the server, where the data is transferred via the network. The input from the terminal is compressed image data, and the data is uploaded by sending it to the server.

[0548] Step 4:

[0549] The server receives the uploaded image and begins analysis. This analysis uses an image analysis algorithm (e.g., YOLO, OpenCV) to extract the room's shape and dimensions. Based on the input image data, the analyzed room's dimension and shape data is output.

[0550] Step 5:

[0551] The server generates a 3D model of the room based on the analysis results. 3D modeling software (e.g., Blender or Autodesk Maya) is used here. The input at this point is the analyzed room dimensions and shape data, and the 3D model data is output.

[0552] Step 6:

[0553] The server sends the generated 3D model to the terminal, and the user can view the 3D model through the application. The input is the generated 3D model data, and the model data is sent to the terminal as output.

[0554] Step 7:

[0555] The user inputs the image and budget for the room design using text or voice within the application. For example, they might input, "I want a Scandinavian-style living room with a budget of 200,000 yen." The input here is the user's text or voice data, which the device outputs as data.

[0556] Step 8:

[0557] The terminal transmits the user's input data to the server. The terminal forwards the user's text or voice input to the server, so the input is the user's text or voice data, and the output is the data transmitted to the server.

[0558] Step 9:

[0559] The server analyzes the received data using natural language processing (NLP) technology. Specifically, an NLP model (e.g., OpenAI GPT, Google BERT) understands the user's preferences and budget and extracts appropriate keywords. In this process, the input text data is analyzed and keywords and condition data based on the user's request are output.

[0560] Step 10:

[0561] The server searches for matching furniture avatars from a furniture database based on the analysis results. The server searches based on conditions such as "Scandinavian-style sofa" and "under 200,000 yen." The input is keywords and condition data from the analysis results, and the output is matching furniture data.

[0562] Step 11:

[0563] The server places the selected furniture avatars in the 3D model. Here, a 3D placement algorithm (e.g., Blender Python script) is used. The input data is the retrieved furniture data, and the output is the 3D model data with the furniture placed.

[0564] Step 12:

[0565] The server then sends the arranged 3D model back to the terminal. The user can then virtually check the room design. The input is the 3D model data with the furniture arranged, and the output is the model data sent to the terminal.

[0566] Step 13:

[0567] If the user cannot find the furniture they want, they can input their custom furniture design request into the application using text or voice. For example, they might input, "I want an antique-style cabinet that is 120cm wide and 80cm high." The input here is the user's text or voice data, and the device sends this as data output.

[0568] Step 14:

[0569] The terminal sends customized request data to the server. The input is the user's customized request data, and the output is the request data sent to the server.

[0570] Step 15:

[0571] The server analyzes the request and uses generative AI to create a custom furniture design. Specifically, a generative AI model (e.g., OpenAI DALL-E, Stable Diffusion) is used. The input data is the custom request data, and the output is the generated furniture design data.

[0572] Step 16:

[0573] The server sends the generated design to the manufacturing equipment as order data. The manufacturing equipment starts manufacturing the custom furniture based on the received design. The input is the generated design data, and the output is the order data sent to the manufacturing equipment.

[0574] (Application example 1)

[0575] 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."

[0576] In the past, there was no system that allowed users to easily generate a 3D model of their own room, and it was difficult to see in real time how the displayed furniture and decorations would affect the overall layout of the room.In addition, there was no efficient method that could quickly respond to user requests for designing and ordering custom furniture.

[0577] 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.

[0578] In this invention, the server includes means for acquiring a plurality of room images taken by a user terminal, server means for analyzing the acquired images and generating a three-dimensional model of the room, server means for receiving budget and design image from the user in natural language and analyzing them, server means for searching for suitable furniture avatars based on the analysis results and arranging them in the three-dimensional model, server means for transmitting the generated three-dimensional model and furniture arrangement information to the user terminal, and means for the user to virtually check and modify the room design in a virtual store. This allows users to virtually design their own rooms and easily realize their ideal interior.

[0579] A "user terminal" is a mobile information terminal used by a user, such as a smartphone, tablet, or smart glasses.

[0580] "Room images" are photographs of the room taken from multiple viewpoints by a user terminal.

[0581] A "3D model" is a three-dimensional digital model of a room generated from a two-dimensional image.

[0582] "Server means" refers to a computer system that has the function of receiving and analyzing data from a user terminal and returning necessary information to the user.

[0583] "Natural language" refers to the language that the user normally uses, and is a format in which instructions can be input by text or voice.

[0584] "Furniture avatars" are digital 3D models of real furniture that can be placed in a virtual space.

[0585] A "virtual store" is a virtual sales and design store space that exists on the Internet.

[0586] A "custom furniture design request" is a request submitted by a user when the user desires furniture with special dimensions or a specific design.

[0587] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new furniture designs based on user instructions.

[0588] A "prompt sentence" is specific input text used to give instructions to a generative AI model.

[0589] A "furniture layout" is the arrangement of furniture placed within a three-dimensional model based on the user's preferences.

[0590] The present invention relates to a system and method for virtually designing a room's interior. A user takes a photo of their room with a smart device, and a server analyzes the photo to generate a 3D model. Furthermore, the user inputs their budget and design image, and the system uses a generative AI model to place digital avatars of matching furniture on the 3D model.

[0591] This system uses the following hardware and software. The hardware includes a user device and a server, and user devices include smartphones, tablets, and smart glasses. The software includes an AI analysis tool for generating 3D models, a database search engine, a generative AI model, and a natural language processing engine.

[0592] The user device takes multiple images of the room and sends them to the server, which uses specialized software to analyze the images and generate a 3D model of the room. This 3D model is then sent to the user device, where the user can view it through an application.

[0593] Users input their budget and image for the room design in natural language. This can be input by text or voice and is sent from the user's device to the server. The server analyzes this data using a natural language processing engine and searches the system's database for digital avatars of furniture that match the user's preferences. A generative AI model is used to select the furniture, and a furniture layout that meets the user's requirements is generated.

[0594] As a specific example, if a user inputs a request such as "I want a monochrome living room with a budget of 300,000 yen," the server will input the following prompt sentence into the generative AI model:

[0595] "Generate a furniture layout for a modern monochrome living room with a budget of 300,000 yen. Provide 3D models in OBJ format."

[0596] This generates a matching furniture layout, which the server sends back to the user's device. The user can then review the virtual room design and make any necessary modifications. Custom furniture design requests can also be entered via text or voice, and the generative AI model will generate the design and place an order with the manufacturing factory.

[0597] This system allows users to design their own rooms in a virtual space, allowing them to consider their ideal interior in a realistic manner, and also allows for custom-made furniture.

[0598] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0599] Step 1:

[0600] A user uses a smart device to take pictures of their room from multiple angles. The input is the multiple images of the room taken. The device acquires these images and prepares them as data to send to the server. The output is image data prepared for sending to the server.

[0601] Step 2:

[0602] The device sends the captured images of the room to the server. The input is the image data prepared in step 1. The device uploads these images to the server via the Internet. The output is the image data uploaded to the server.

[0603] Step 3:

[0604] The server analyzes the received image data and generates a 3D model. The input is the image data uploaded to the server. The server uses AI technology to analyze the image features and generate a three-dimensional 3D model. The output is the generated 3D model data.

[0605] Step 4:

[0606] The server sends the generated 3D model to the user terminal. The input is the 3D model data generated in step 3. The server returns this data to the terminal, where the model is displayed. The output is the 3D model displayed on the user terminal.

[0607] Step 5:

[0608] The user uses the application to input a room design image and budget in natural language. The input is natural language text or voice data about the budget and design image. The device prepares this data to send to the server. The output is natural language data prepared for sending to the server.

[0609] Step 6:

[0610] The terminal sends the input design image and budget information to the server. The input is the natural language data prepared in step 5. The terminal uploads this data to the server. The output is the natural language data sent to the server.

[0611] Step 7:

[0612] The server analyzes the received natural language data. The input is the natural language data sent to the server. The server uses natural language processing technology to analyze the user's preferences and budget and identify suitable furniture. The output is a list of specific furniture items as a result of the analysis.

[0613] Step 8:

[0614] Based on the analysis results, the server searches for suitable furniture avatars from the system's database and places them in the 3D model. The input is the analysis results obtained in step 7 and the furniture information in the database. The server uses a generative AI model to generate prompt sentences and determine the optimal furniture layout. The output is 3D model data with the furniture avatars placed.

[0615] Step 9:

[0616] The server sends the 3D model data and furniture layout information to the user terminal. The input is the 3D model data generated in step 8. The server sends this data to the user terminal so that the furniture layout can be confirmed on the terminal. The output is the furniture layout information displayed on the user terminal.

[0617] Step 10:

[0618] A user inputs a custom furniture design request. The input is natural language text or voice data about the dimensions and design of the custom furniture. The terminal prepares this data for transmission to the server. The output is the custom furniture request data prepared for transmission to the server.

[0619] Step 11:

[0620] The server analyzes the custom furniture request and generates the custom furniture design using a generative AI model. The input is the custom furniture request data sent to the server. The server uses the generative AI model to generate prompt sentences and create a new furniture design. The output is the generated custom furniture design data.

[0621] Step 12:

[0622] The server sends the generated design information of the custom-made furniture to the manufacturing factory. The input is the design data of the custom-made furniture generated in step 11. The server sends this data to the manufacturing factory and requests the manufacturing of the custom-made furniture. The output is the design information of the custom-made furniture sent to the manufacturing factory.

[0623] 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.

[0624] This invention relates to a system that generates a 3D model based on images of multiple rooms taken by a user device and simulates furniture placement based on user instructions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it proposes optimal designs according to the user's emotions.

[0625] System Programming and Processing

[0626] 3D room model generation

[0627] Users use a device such as a smartphone or tablet to take photos of their room from multiple angles. The device then imports these photos into a dedicated application and converts them into a dedicated format. The device then uploads the converted photo data to a server. The server uses AI technology to analyze the received photos and generate a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the application.

[0628] Enter your image and budget

[0629] Users input their image of the room design and their budget using text or voice within the application. The device sends the input data to the server, which then analyzes it using natural language processing technology, extracting and understanding related keywords.

[0630] Furniture selection and placement

[0631] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The server then places the selected furniture avatars within the 3D model and determines their placement using an algorithm to calculate the optimal placement. The 3D model with the furniture placed is then sent back to the terminal, allowing the user to check the room design in the virtual space.

[0632] Custom furniture design and ordering

[0633] If the desired furniture item cannot be found, the user can input a design request for custom furniture via text or voice within the application. The device then sends the request data to the server, which analyzes it and uses generative AI to create a custom furniture design. The generated design data is then sent to a partner manufacturing factory.

[0634] Incorporating an emotion engine

[0635] Emotion Recognition and Analysis

[0636] The emotion engine recognizes emotions from the user's facial expressions and voice. For example, it captures the user's facial expressions through a camera and analyzes the facial expression data to identify the user's emotional state. When using voice recognition, it evaluates emotions from the user's tone of voice and speaking style.

[0637] Emotion-based design adjustments

[0638] The server receives the user's emotional data recognized by the emotion engine. Based on this emotional data, the server adjusts the design image and layout. For example, if the user is feeling stressed, it can suggest a relaxing interior style. It is also possible to dynamically change the furniture layout within the 3D model in real time according to changes in the user's emotions.

[0639] Specific examples

[0640] Photographing the room and generating 3DCG

[0641] The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos to generate a 3D model of the living room and sends it to the device. The user can then view the 3D model in the application.

[0642] Emotion Recognition and Furniture Placement

[0643] When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine analyzes the user's facial expression and recognizes that they are in a relaxed state. Based on this information, the server selects a Scandinavian-style furniture avatar that will help them relax and places it on the 3D model.

[0644] Custom furniture design and ordering

[0645] If a user wants a cabinet with specific dimensions and design, they input their request. The device sends the request to the server, which uses generative AI to create a custom cabinet design and sends the design data to a partner factory.

[0646] In this way, the present invention allows users to easily simulate room designs in real time, allowing them to smoothly select furniture and order custom-made furniture. Furthermore, by incorporating an emotion engine, it is possible to propose optimal designs according to the user's emotional state.

[0647] The processing flow will be explained below.

[0648] 3DCG generation of rooms

[0649] Step 1:

[0650] A user uses their smartphone to take photos of a room from multiple angles.

[0651] Step 2:

[0652] The device imports multiple photos taken into a dedicated application and converts them into a format that is easy to process.

[0653] Step 3:

[0654] The terminal transmits a request to upload the converted photo data to the server.

[0655] Step 4:

[0656] The server receives the upload request and returns permission, allowing the device to send the photo data to the server.

[0657] Step 5:

[0658] The server then analyzes the received photos using AI technology (e.g., image recognition algorithms), measuring the room's dimensions and identifying key furniture and features.

[0659] Step 6:

[0660] The server generates a 3D model of the room based on the analysis results. This 3D model is a virtual reproduction of the user's room.

[0661] Step 7:

[0662] The server encodes the generated 3D model and transmits it to the terminal.

[0663] Step 8:

[0664] The terminal displays the received three-dimensional model data, allowing the user to confirm the results.

[0665] Enter your image and budget

[0666] Step 1:

[0667] The user enters the image and budget for the room design using text or voice within the application.

[0668] Step 2:

[0669] The terminal sends the user's input to the server in the appropriate format.

[0670] Step 3:

[0671] The server receives the input and analyzes it using natural language processing technology, extracting relevant keywords based on the design image and budget.

[0672] Furniture selection and placement

[0673] Step 1:

[0674] Based on the analysis results, the server searches for matching furniture avatars from a furniture database, using keywords such as "Scandinavian style" or "relaxing."

[0675] Step 2:

[0676] The server compiles a list of multiple furniture avatars selected from the search results.

[0677] Step 3:

[0678] The server then places the furniture in the 3D model based on the list, running an algorithm to calculate, for example, where to place sofas and tables.

[0679] Step 4:

[0680] The server encodes a three-dimensional model with the furniture arranged and sends it to the terminal.

[0681] Step 5:

[0682] The terminal displays the received data, allowing the user to check the design of the virtual room.

[0683] Custom furniture design and ordering

[0684] Step 1:

[0685] If a user wants custom furniture, they enter their design request in the application by text or voice.

[0686] Step 2:

[0687] The terminal sends custom request data to the server.

[0688] Step 3:

[0689] The server receives the customization request and performs analysis to understand the requirements of the user's desired custom furniture.

[0690] Step 4:

[0691] The server uses generative AI to create custom furniture designs, such as cabinets based on user-specified dimensions and styles.

[0692] Step 5:

[0693] The server sends the generated design data for custom-made furniture to the partner factory and starts the ordering process.

[0694] Emotion engine built-in

[0695] Step 1:

[0696] While the user is using the application, the emotion engine captures the user's facial expressions and voice data through the camera and microphone.

[0697] Step 2:

[0698] The device transmits the captured facial expression data and voice data to the server.

[0699] Step 3:

[0700] The server uses an emotion engine to analyze the received data and identify the user's emotional state.

[0701] Step 4:

[0702] The server adjusts the design image and furniture layout based on the recognized emotion data. For example, if the user is feeling stressed, it will suggest interior design that has a relaxing effect.

[0703] Step 5:

[0704] The server transmits three-dimensional model data that has been dynamically updated in accordance with the emotion data to the terminal.

[0705] Step 6:

[0706] The device displays the received data, allowing users to see room designs that correspond to their emotions in real time.

[0707] In this way, the system of the present invention provides optimal room designs tailored to the user's needs through multiple processing steps, and also supports custom-made furniture. Furthermore, by using an emotion engine, it is possible to propose personalized designs based on the user's emotional state.

[0708] Example 2

[0709] 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."

[0710] Conventional interior design systems require users to manually select and arrange furniture, which is time-consuming, and it is difficult to adjust the design based on the user's emotional state. Furthermore, they lack the functionality to accept custom furniture design requests, or the ability to propose designs that reflect the user's specific image and budget. These issues need to be resolved.

[0711] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring a plurality of room images taken by a user terminal, means for analyzing the acquired images to generate a 3D model of the room, means for receiving budget and design image from the user in natural language and analyzing the same, means for searching for suitable furniture avatars based on the analysis results and arranging them in the 3D model, means for transmitting the generated 3D model and furniture arrangement information to the user terminal, means for recognizing the user's emotions, and means for adjusting the design based on the user's emotions. This allows the user to easily create a 3D model of a room and simulate furniture arrangement based on the user's budget and design image, as well as request a design for custom-made furniture, and further enables optimal design proposals to be made in response to the user's emotions.

[0712] A "user terminal" is a device operated by a user, and includes mobile information terminals such as smartphones and tablets.

[0713] "Room images" refer to photographic data that captures the interior of a room from multiple angles and is taken with a user terminal.

[0714] A "three-dimensional model" is a digital representation of the three-dimensional structure of a room, generated by analyzing an image of the room.

[0715] A "server" refers to a computer system that receives and processes requests from multiple clients (user terminals in this case).

[0716] "Budget" refers to the amount of money a user can spend on the interior design of a room.

[0717] "Design image" refers to a specific visual or theme related to the room decoration or interior style desired by the user.

[0718] "Natural language" refers to a language that humans use on a daily basis, i.e., information expressed in spoken or text form.

[0719] "Furniture avatars" are digital models stored in the system's furniture database, and refer to virtual furniture data that can be placed within a three-dimensional model of a room.

[0720] "Emotion recognition" refers to a technology that analyzes and identifies a user's emotional state from their facial expressions and voice.

[0721] "Generative AI" refers to artificial intelligence technology that generates new digital data (such as custom furniture designs) based on given prompts.

[0722] "Custom-made furniture" refers to furniture that is made to order for a user to request specific dimensions and designs.

[0723] This system generates a 3D model based on multiple images of a room taken with a user device and simulates furniture placement based on the user's instructions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to propose optimal designs based on the user's emotions.

[0724] System Overview

[0725] Users take photos of their rooms using devices such as smartphones or tablets. These photos are captured by a dedicated application, converted into a dedicated format, and then uploaded to a server. The server analyzes the received image data and generates a 3D model of the room. This process uses Google's TensorFlow AI technology. The generated 3D model is then sent back to the device, where the user can view it through the application.

[0726] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then analyzes it using natural language processing technology (e.g., OpenAI's GPT-3). As a result, relevant keywords are extracted and understood, and matching furniture avatars are searched for within the system's furniture database.

[0727] Furniture placement and custom furniture generation

[0728] The server places the selected furniture avatars within the 3D model and determines the optimal layout. This process uses genetic algorithms and A-search. The placed 3D model is then sent back to the terminal, allowing the user to check the room design in the virtual space.

[0729] If the desired furniture item cannot be found, the user can input a design request for custom furniture via text or voice within the application. This request is sent to the server, which then uses generative AI (e.g., OpenAI's GPT-3) to create a custom furniture design. The generated design data is then sent to a partner manufacturing factory.

[0730] Incorporating an emotion engine

[0731] The emotion engine recognizes emotions from the user's facial expressions and voice. For example, it captures the user's facial expressions through the camera and analyzes the facial data using Microsoft's Azure Face API. When using speech recognition, it analyzes the user's voice using Google Cloud Speech-to-Text API and evaluates emotions from the tone and speaking style.

[0732] The server receives the user's emotional data recognized by the emotion engine and adjusts the design image and layout based on this emotional data. If the user is feeling stressed, the server will suggest a relaxing interior style. It is also possible to dynamically change the furniture layout within the 3D model in real time.

[0733] Specific examples

[0734] Photographing the room and generating 3DCG

[0735] The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos using Google's TensorFlow, generates a 3D model of the living room, and sends it to the device. The user can then view the 3D model in the application.

[0736] Emotion Recognition and Furniture Placement

[0737] When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine simultaneously analyzes the user's facial expressions using Microsoft's Azure Face API and recognizes that the user is in a relaxed state. Based on this information, the server selects a Scandinavian-style furniture avatar that will help them relax and places it on the 3D model.

[0738] Custom furniture design and ordering

[0739] If a user wants a cabinet with specific dimensions and design, they input their request, and the device sends it to the server, which uses OpenAI's GPT-3 to create a custom cabinet design and sends the design data to the manufacturing factory.

[0740] Prompt Sentence Examples

[0741] "I'd like to create a relaxing Scandinavian-style living room. My budget is within 200,000 yen. Please suggest some designs that I can use as reference for furniture layout and colors."

[0742] This allows users to easily simulate room designs and smoothly select and order custom furniture. Furthermore, by incorporating an emotion engine, it is possible to propose optimal designs according to the user's emotional state.

[0743] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0744] Step 1: Take a photo of your room and upload it

[0745] A user takes photos of a room from multiple angles using a smartphone or tablet. The device imports the photos into a dedicated application and converts them from JPEG format to a dedicated format (for example, XYZ format). This format conversion is performed to standardize and compress the image data. The device then uploads the converted data to the server via an HTTP request. The input is an image of the room, and the output is image data in the dedicated format that is sent to the server.

[0746] Step 2: 3D model generation

[0747] The server analyzes the received image data using AI technology (Google's TensorFlow) and generates a 3D model of the room. Specifically, it digitizes the three-dimensional structure of the room as point cloud and mesh data based on images taken from multiple angles. The input is image data in a dedicated format, and the output is a 3D model (OBJ format). The server sends the generated 3D model to the terminal as an HTTP response. The user can view the 3D model through an application.

[0748] Step 3: Enter your image and budget

[0749] Within the application, the user inputs the image and budget for the room design using text or voice. The device sends this input data to the server via a POST request. The input is the user's text or voice data, and the output is natural language data sent to the server. For example, the user might input, "I want a Scandinavian-style living room with a budget of 200,000 yen."

[0750] Step 4: Image and budget analysis

[0751] The server uses natural language processing technology (OpenAI GPT-3) to analyze the image and budget data received from the user. This allows it to extract and understand the keywords "Scandinavian style" and "200,000 yen." The input is the transmitted natural language data, and the output is the analyzed keywords and phrases.

[0752] Step 5: Select and arrange furniture

[0753] Based on the analysis results, the server searches for suitable furniture avatars from the furniture database within the system. The retrieved furniture avatars are placed within the 3D model, and a genetic algorithm or A-search is used to determine the optimal placement. The input is the analyzed keywords and the 3D model, and the output is an updated 3D model with the furniture arranged. The server sends this updated 3D model to the terminal. The user can then check the room design in the virtual space using the application.

[0754] Step 6: Custom Furniture Design Request

[0755] If a user desires furniture with specific dimensions or design, they input a custom furniture design request within the application. The device sends the request data to the server. The input is a text or voice design request from the user, and the output is the request data sent to the server. For example, a user might input, "I'm looking for a Scandinavian-style cabinet that is 150cm wide and 75cm high."

[0756] Step 7: Create and submit your custom furniture design

[0757] The server uses generative AI (OpenAI's GPT-3) to create custom furniture designs. The generated design data (e.g., PNG format) is sent to partner manufacturing factories via email or a dedicated API. The input is the user's design request data, and the output is the custom furniture design data sent to the manufacturing factory.

[0758] Step 8: Emotion Recognition

[0759] The emotion engine, which recognizes emotions from the user's facial expressions and voice, captures user data using the device's camera and microphone. Emotion analysis is performed using Microsoft's Azure Face API and Google Cloud Speech-to-Text API. The input is the user's facial expression data and voice data, and the output is analyzed emotion data. For example, if the user enables the camera function, the emotion engine recognizes that the user is relaxed.

[0760] Step 9: Adjust your design based on emotion

[0761] The server adjusts the design image and furniture layout based on the emotional data obtained through emotion recognition. In particular, if the user is feeling stressed, it suggests a relaxing interior style. The input is the analyzed emotional data, and the output is an adjusted 3D model and design proposal. The adjusted design is sent to the user's device, and the user can view the updated design in the application.

[0762] (Application example 2)

[0763] 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."

[0764] Conventional interior design simulation systems have difficulty providing satisfying interior designs because they do not adequately consider the user's emotions when proposing designs. In addition, the design creation and ordering process for custom furniture is complicated and lacks automation.

[0765] The specification processing by the specification 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 acquiring multiple room images taken by a user terminal, means for analyzing the acquired images to generate a three-dimensional model of the room, means for receiving and analyzing the user's budget and design image in natural language, means for searching for suitable furniture avatars based on the analysis results and placing them in the three-dimensional model, means for transmitting the generated three-dimensional model and furniture placement information to the user terminal, emotion recognition means for recognizing the user's emotion, and means for proposing an optimal design based on the recognized emotion data. This makes it possible to propose optimal interior designs based on the user's emotions and to automate the design, creation, and ordering of custom furniture.

[0766] A "user terminal" is an electronic device that can be operated by a user, and includes smartphones, tablets, smart glasses, head-mounted displays, etc.

[0767] The term "server means" refers to a server system for analyzing captured images, generating three-dimensional models, analyzing natural language, placing furniture avatars, and transmitting generated data.

[0768] "Emotion recognition means" refers to a device or software that has the function of analyzing and recognizing emotions from a user's facial expressions and voice.

[0769] "Furniture avatar" refers to a three-dimensional model of furniture used in interior simulations in a virtual space.

[0770] "Custom furniture" refers to furniture that is designed and manufactured based on a user's specific requirements.

[0771] "Generative AI model" refers to an artificial intelligence model that automatically generates custom furniture designs based on input data.

[0772] The present invention provides a system for generating a three-dimensional model based on images of a plurality of rooms taken by a user terminal, and proposing an interior design based on the user's emotions. Specific embodiments will be described below.

[0773] System configuration

[0774] Hardware

[0775] User devices: smartphones, tablets, smart glasses, head-mounted displays, etc.

[0776] Server: Cloud servers with high-performance computing power and storage (e.g. AWS, Google Cloud).

[0777] Emotion recognition devices: Cameras and microphones that can analyze a user's facial expressions and voice (e.g., high-resolution webcams, directional microphones).

[0778] software

[0779] Image processing library: An image analysis library for generating 3D models, such as OpenCV.

[0780] Natural language processing engine: An engine for parsing user input data (e.g., NLTK, spaCy).

[0781] Emotion Recognition Library: A library for recognizing user emotions (e.g., Affectiva SDK).

[0782] Generative AI models: Models for automatically generating custom furniture designs (e.g., TensorFlow).

[0783] System Operation

[0784] 3D room model generation

[0785] Users use devices such as smartphones, tablets, or smart glasses to take photos of their room from multiple angles. The device then imports these photos into a dedicated application and converts them into a dedicated format. The device then uploads the converted photo data to a server. The server analyzes the received photos and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the application.

[0786] Emotion Recognition and Design Proposals

[0787] An emotion recognition device is used to capture the user's facial expressions and voice, and this data is analyzed using an emotion recognition library. The analysis results are sent to a server, which then adjusts the design image and layout based on the user's emotional state. This design proposal provides an interior style that the user can relax in, and dynamically changes the furniture layout in real time according to changes in emotion.

[0788] Custom furniture design and ordering

[0789] If a user desires furniture with specific dimensions and design, they input their custom furniture request within the application. The device then sends the request data to the server, which then uses a generative AI model to create a custom furniture design. The generated design data is then sent to partner manufacturing factories. This allows users to quickly design and order the custom furniture they desire.

[0790] Specific examples

[0791] Room photography and 3D model generation: The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos to generate a 3D model of the living room and sends it to the device. The user can then view the 3D model in the application.

[0792] Emotion recognition and furniture placement: When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine analyzes the user's facial expression and recognizes that the user is in a relaxed state. Based on this information, the server selects Scandinavian-style furniture avatars that will help the user relax and places them on the 3D model.

[0793] Design and order custom furniture: If a user wants a cabinet with specific dimensions and design, they input the request. The device sends the request to the server, which uses a generative AI model to create a custom cabinet design and sends the design data to a partner factory.

[0794] Prompt Sentence Examples

[0795] "Using an emotion engine, can you suggest a Scandinavian-inspired living room design that would suit a user with a relaxed expression? Also, can you tell us about a system that creates custom cabinets and automates the process of placing an order?"

[0796] As described above, the system of the present invention efficiently proposes interior designs based on the user's emotions and designs and orders custom-made furniture.

[0797] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0798] Step 1:

[0799] The user uses a device (smartphone, tablet, smart glasses, head-mounted display, etc.) to take photos of the room from multiple angles. The input is multiple images of the room, which are then converted into a dedicated format. The converted image data is uploaded from the device to the server. The server receives the uploaded image data and prepares it for 3D model generation.

[0800] Step 2:

[0801] The server analyzes the received image data and generates a 3D model of the room using photogrammetry techniques (e.g., image processing libraries such as OpenCV). This process involves extracting feature points from the images and reconstructing a 3D point cloud from multiple images. The output is the generated 3D model of the room.

[0802] Step 3:

[0803] The generated 3D model is then sent from the server to the user's device. The device receives this data and allows the user to visually confirm it. The input is the 3D model data sent from the server, and the output is the display of the 3D model on the device. The user can use this model to check the layout of the room.

[0804] Step 4:

[0805] The user inputs the budget and image of the room design on the device. This input data is in natural language, so the device sends it to the server. The server uses a natural language processing engine (e.g., NLTK, spaCy) to analyze the input data and extract relevant keywords. The input is the user's text or voice data, and the output is the analyzed keywords.

[0806] Step 5:

[0807] The server searches for matching furniture avatars from a furniture database based on the analyzed keywords. The retrieved furniture avatars are placed in the 3D model. Based on this, the optimal furniture placement is calculated. The output is a 3D model containing the placed furniture avatars.

[0808] Step 6:

[0809] An emotion recognition device (camera, microphone, etc.) is used to capture the user's facial expressions and voice. The input is the user's facial image and voice data. This data is analyzed by an emotion recognition library (e.g., Affectiva SDK) to recognize the user's emotional state. The output is the recognized user's emotional data.

[0810] Step 7:

[0811] The server adjusts design suggestions based on the emotion data. For example, if it determines that the user is relaxed, it will suggest a relaxing interior style. This suggestion is reflected in the 3D model in real time. The input is the recognized emotion data, and the output is the adjusted design suggestion.

[0812] Step 8:

[0813] When a user wants custom furniture with specific dimensions and design, they input their custom furniture request in the application. This request data is sent to the server. The server uses a generative AI model (e.g., TensorFlow) to create a custom furniture design and sends the design data to a partner manufacturing factory. The input is the user's custom furniture request data, and the output is the generated furniture design data.

[0814] In this way, this system efficiently proposes optimal interior designs based on the user's emotions and designs and orders custom furniture.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] [Third embodiment]

[0819] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0820] 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.

[0821] 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).

[0822] 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.

[0823] 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.

[0824] 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).

[0825] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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."

[0831] The present invention relates to a system that allows users to take photos of their rooms using devices such as smartphones or tablets, and then uses AI to generate a 3D model of the room. Furthermore, users can input their budget and design image using natural language, and digital avatars of real furniture are placed within the 3D model based on that input. This allows users to create a virtual space and specifically consider the design of their ideal room.

[0832] System Programming and Processing

[0833] 3D room model generation

[0834] The user takes photos of the room from multiple angles using their device. The device then converts the images into a dedicated format and uploads them to the server. The server receives the images, analyzes them using AI technology, and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the app.

[0835] Enter your image and budget

[0836] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then uses natural language processing technology to analyze the received data and understand the user's preferences and budget.

[0837] Furniture selection and placement

[0838] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The selected furniture avatars are then placed in the 3D model. The server then sends the placed 3D model back to the terminal, allowing the user to virtually check the room design.

[0839] Custom furniture design and ordering

[0840] If a user cannot find the furniture they want, they can input a custom-made furniture design request via text or voice. The device then sends the custom-made request data to the server. The server analyzes the request and uses generative AI to create a custom furniture design. The generated design is then sent to a partner manufacturing factory as order data.

[0841] Specific examples

[0842] Photographing the room and generating 3DCG

[0843] The user takes three photos of their living room from different angles. The device uploads these photos to the server, which then uses AI analysis to generate a 3D model of the living room. The generated 3D model is then sent to the device, where the user can view it through the app.

[0844] Enter your image and budget

[0845] The user enters into the app, "I want a Scandinavian-style living room with a budget of 200,000 yen." The device sends this information to the server, which analyzes it. Based on the results, the app searches a list of Scandinavian-style furniture and selects an appropriate furniture avatar.

[0846] Furniture selection and placement

[0847] The server places furniture avatars such as sofas, tables, and rugs from the search results into the 3D model, and the placed 3D model is sent to the device, allowing the user to view the virtual living room on the app.

[0848] Custom furniture design and ordering

[0849] If a user wants a cabinet with specific dimensions and design, but there is no matching furniture in the system, they can enter a custom-order request into the app. The device sends the request to the server, which uses AI to create a custom cabinet design and sends the order data to a partner factory.

[0850] In this way, the present invention allows users to virtually design their own rooms and easily realize their ideal interior. In addition, by supporting custom-made furniture, it is possible to meet the diverse needs of users.

[0851] The processing flow will be explained below.

[0852] 3DCG generation of rooms

[0853] Step 1:

[0854] A user uses their smartphone to take photos of a room from multiple angles.

[0855] Step 2:

[0856] The device imports the photos taken into a dedicated application and converts the photo data into a format that is easy to analyze.

[0857] Step 3:

[0858] The device uploads the converted photo data to the server by sending an upload request, and the server receives the request and returns permission.

[0859] Step 4:

[0860] The server receives the photo data and analyzes it using AI technology (e.g., image recognition algorithms) to determine the dimensions of the room and the location of furniture.

[0861] Step 5:

[0862] The server generates a 3D model based on the identified information, which is a virtual reproduction of the user's room.

[0863] Step 6:

[0864] The server sends the generated 3D model to the device, which receives the data and displays the 3D model within the application.

[0865] Enter your image and budget

[0866] Step 1:

[0867] The user inputs the image and budget for the room design using text or voice within the dedicated application.

[0868] Step 2:

[0869] The terminal transmits the user's input data to the server.

[0870] Step 3:

[0871] The server receives the input data and analyzes it using natural language processing technology, understanding the design image and budget details and extracting related keywords.

[0872] Furniture selection and placement

[0873] Step 1:

[0874] The server searches a furniture database based on the user's desired design and budget.

[0875] Step 2:

[0876] Based on the search results, it generates a list of matching furniture avatars, including sofas, tables, chairs, etc.

[0877] Step 3:

[0878] The server places the selected furniture avatars in the 3D model, using an algorithm to calculate the optimal placement.

[0879] Step 4:

[0880] The server sends 3D model data with furniture arranged on it to the terminal.

[0881] Step 5:

[0882] The device receives the data and displays a 3D model with the furniture arranged in it within the application, allowing the user to see the virtual design of the room.

[0883] Custom furniture design and ordering

[0884] Step 1:

[0885] The user enters a custom furniture design request via text or voice within the application.

[0886] Step 2:

[0887] The terminal sends custom request data to the server.

[0888] Step 3:

[0889] The server receives the request data and analyzes it to understand the custom furniture design desired by the user.

[0890] Step 4:

[0891] The server uses generative AI to create custom furniture designs, and the design process involves customizing the design based on the user's desired dimensions and style.

[0892] Step 5:

[0893] The server transmits the generated design data for the custom-made furniture to the partner factory as order data.

[0894] In this way, specific actions are performed at each step, allowing the user to efficiently simulate the design of a room and smoothly select furniture and place custom orders.

[0895] Example 1

[0896] 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."

[0897] In today's residential environment, it takes a lot of time and effort for users to realize their ideal interior design, and designing and ordering custom furniture also requires specialized knowledge and skills. As a result, users often have to pay high costs and go through complicated procedures, making it difficult to easily create their ideal space. To solve this problem, there is a need for a system that allows users to easily design their own rooms virtually and also easily design and order custom furniture.

[0898] 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.

[0899] In this invention, the server includes means for acquiring multiple images of a room taken by a user terminal, server means for analyzing the acquired images and generating a three-dimensional model of the room, server means for receiving budget and design image information from the user in natural language and analyzing it, server means for searching for suitable furniture data based on the analysis results and arranging it in the three-dimensional model, and server means for transmitting the generated three-dimensional model and furniture arrangement information to the user terminal. This allows users to easily virtually design their own rooms and arrange furniture that best suits their budget and design image. In addition, custom furniture can be designed and ordered using the server means, reducing high costs and complicated procedures and realizing ideal spaces.

[0900] "User terminal" refers to an electronic device that a user directly operates to take images of a room, input data, and check a model. Specifically, this applies to a smartphone or tablet.

[0901] "Server means" refers to advanced computing devices installed on the cloud or within a network that are responsible for analyzing data, generating models, and sending and receiving information. Specifically, this refers to high-performance physical servers or virtual servers.

[0902] "Image analysis" refers to the process of extracting the shape and dimensions of a room from images taken by a user device and generating a 3D model based on that information. This process uses AI technology and algorithms.

[0903] A "3D model" refers to digital data that recreates the physical features of a room in three-dimensional space, allowing users to virtually view the interior of the room.

[0904] "Natural language processing" refers to the technology of analyzing text and voice data input by users and understanding their meaning. This technology is used to accurately grasp the user's intentions and requests.

[0905] "Furniture Data" refers to the digital information about furniture held by the system, including information such as the type, shape, dimensions, and price of the furniture.

[0906] "Placing in 3D model" refers to the process of placing the selected furniture data in the appropriate position within the 3D model, allowing the user to check the virtual room design.

[0907] "Custom-made furniture" refers to furniture that is newly designed based on a user's specific requirements. It is designed and manufactured to meet the user's individual needs.

[0908] "Manufacturing equipment" refers to equipment used to manufacture custom furniture based on the design information sent from the server. Specifically, this applies to processing machines and assembly machines installed in the production factory.

[0909] The "dedicated format" refers to a data format used to convert captured images into a format that can be analyzed by the server, improving data uniformity and analysis efficiency.

[0910] The present invention relates to a system that allows users to take photos of their rooms using devices such as smartphones or tablets, and then uses AI to generate a 3D model of the room. Furthermore, users can input their budget and design image using natural language, and digital avatars of real furniture are placed within the 3D model based on that input. This allows users to create a virtual space and specifically consider the design of their ideal room.

[0911] Hardware and software used

[0912] 1. Device: Use a smartphone or tablet. Specific examples include iPhone, iPad, and Android devices.

[0913] 2. Server: Use a high-performance server, such as AWS EC2 or Google Cloud Compute Engine.

[0914] 3. Image analysis technology: YOLO, OpenCV, etc. are used as image analysis algorithms.

[0915] 4. 3D modeling software: Blender, Autodesk Maya.

[0916] 5. Natural Language Processing (NLP): Uses OpenAI GPT and Google BERT.

[0917] 6. Generative AI model: OpenAI DALL-E, using Stable Diffusion.

[0918] System program and processing description

[0919] 3D room model generation

[0920] The user takes photos of the room from multiple angles using their device. The device converts the images into a dedicated format and uploads them to the server. The server receives the images, analyzes them using AI technology, and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the app.

[0921] Enter your image and budget

[0922] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then uses natural language processing technology to analyze the received data and understand the user's preferences and budget.

[0923] Furniture selection and placement

[0924] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The selected furniture avatars are then placed within the 3D model. The server then sends the placed 3D model back to the terminal, allowing the user to virtually check the room design.

[0925] Custom furniture design and ordering

[0926] If a user cannot find the furniture they want, they can input a custom-made furniture design request via text or voice. The device then sends the custom-made request data to the server. The server analyzes the request and uses generative AI to create a custom furniture design. The generated design is then sent to a partner manufacturing factory as order data.

[0927] Specific examples

[0928] Photographing the room and generating a 3D model

[0929] The user takes three photos of their living room from different angles. The device uploads these photos to the server, which then uses AI analysis to generate a 3D model of the living room. The generated 3D model is then sent to the device, where the user can view it through the app.

[0930] Enter your image and budget

[0931] The user enters into the app, "I want a Scandinavian-style living room with a budget of 200,000 yen." The device sends this information to the server, which analyzes it. Based on the results, the app searches a list of Scandinavian-style furniture and selects an appropriate furniture avatar.

[0932] Furniture selection and placement

[0933] The server places furniture avatars such as sofas, tables, and rugs from the search results into the 3D model, and the placed 3D model is sent to the device, allowing the user to view the virtual living room on the app.

[0934] Custom furniture design and ordering

[0935] If a user wants a cabinet with specific dimensions and design, but there is no matching furniture in the system, they can enter a custom-order request into the app. The device then sends the request to the server, which uses generative AI to create a custom cabinet design and sends the order data to the manufacturing equipment.

[0936] In this way, the present invention allows users to virtually design their own rooms and easily realize their ideal interior. In addition, by supporting custom-made furniture, it is possible to meet the diverse needs of users.

[0937] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0938] Step 1:

[0939] The user takes photos of the room from multiple angles on their device. This is important to capture the entire room. The user uses a smartphone or tablet to take at least three photos from different angles. At this point, the input is a photo of the room, and the output is image data.

[0940] Step 2:

[0941] The device converts the captured image into a dedicated format. This conversion makes it easier to send the image to the server. Specifically, software on the device compresses the image and performs the format conversion. Through this process, the input image data is output as compressed image data.

[0942] Step 3:

[0943] The terminal uploads the converted image data to the server, where the data is transferred via the network. The input from the terminal is compressed image data, and the data is uploaded by sending it to the server.

[0944] Step 4:

[0945] The server receives the uploaded image and begins analysis. This analysis uses an image analysis algorithm (e.g., YOLO, OpenCV) to extract the room's shape and dimensions. Based on the input image data, the analyzed room's dimension and shape data is output.

[0946] Step 5:

[0947] The server generates a 3D model of the room based on the analysis results. 3D modeling software (e.g., Blender or Autodesk Maya) is used here. The input at this point is the analyzed room dimensions and shape data, and the 3D model data is output.

[0948] Step 6:

[0949] The server sends the generated 3D model to the terminal, and the user can view the 3D model through the application. The input is the generated 3D model data, and the model data is sent to the terminal as output.

[0950] Step 7:

[0951] The user inputs the image and budget for the room design using text or voice within the application. For example, they might input, "I want a Scandinavian-style living room with a budget of 200,000 yen." The input here is the user's text or voice data, which the device outputs as data.

[0952] Step 8:

[0953] The terminal transmits the user's input data to the server. The terminal forwards the user's text or voice input to the server, so the input is the user's text or voice data, and the output is the data transmitted to the server.

[0954] Step 9:

[0955] The server analyzes the received data using natural language processing (NLP) technology. Specifically, an NLP model (e.g., OpenAI GPT, Google BERT) understands the user's preferences and budget and extracts appropriate keywords. In this process, the input text data is analyzed and keywords and condition data based on the user's request are output.

[0956] Step 10:

[0957] The server searches for matching furniture avatars from a furniture database based on the analysis results. The server searches based on conditions such as "Scandinavian-style sofa" and "under 200,000 yen." The input is keywords and condition data from the analysis results, and the output is matching furniture data.

[0958] Step 11:

[0959] The server places the selected furniture avatars in the 3D model. Here, a 3D placement algorithm (e.g., Blender Python script) is used. The input data is the retrieved furniture data, and the output is the 3D model data with the furniture placed.

[0960] Step 12:

[0961] The server then sends the arranged 3D model back to the terminal. The user can then virtually check the room design. The input is the 3D model data with the furniture arranged, and the output is the model data sent to the terminal.

[0962] Step 13:

[0963] If the user cannot find the furniture they want, they can input their custom furniture design request into the application using text or voice. For example, they might input, "I want an antique-style cabinet that is 120cm wide and 80cm high." The input here is the user's text or voice data, and the device sends this as data output.

[0964] Step 14:

[0965] The terminal sends customized request data to the server. The input is the user's customized request data, and the output is the request data sent to the server.

[0966] Step 15:

[0967] The server analyzes the request and uses generative AI to create a custom furniture design. Specifically, a generative AI model (e.g., OpenAI DALL-E, Stable Diffusion) is used. The input data is the custom request data, and the output is the generated furniture design data.

[0968] Step 16:

[0969] The server sends the generated design to the manufacturing equipment as order data. The manufacturing equipment starts manufacturing the custom furniture based on the received design. The input is the generated design data, and the output is the order data sent to the manufacturing equipment.

[0970] (Application example 1)

[0971] 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."

[0972] In the past, there was no system that allowed users to easily generate a 3D model of their own room, and it was difficult to see in real time how the displayed furniture and decorations would affect the overall layout of the room.In addition, there was no efficient method that could quickly respond to user requests for designing and ordering custom furniture.

[0973] 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.

[0974] In this invention, the server includes means for acquiring a plurality of room images taken by a user terminal, server means for analyzing the acquired images and generating a three-dimensional model of the room, server means for receiving budget and design image from the user in natural language and analyzing them, server means for searching for suitable furniture avatars based on the analysis results and arranging them in the three-dimensional model, server means for transmitting the generated three-dimensional model and furniture arrangement information to the user terminal, and means for the user to virtually check and modify the room design in a virtual store. This allows users to virtually design their own rooms and easily realize their ideal interior.

[0975] A "user terminal" is a mobile information terminal used by a user, such as a smartphone, tablet, or smart glasses.

[0976] "Room images" are photographs of the room taken from multiple viewpoints by a user terminal.

[0977] A "3D model" is a three-dimensional digital model of a room generated from a two-dimensional image.

[0978] "Server means" refers to a computer system that has the function of receiving and analyzing data from a user terminal and returning necessary information to the user.

[0979] "Natural language" refers to the language that the user normally uses, and is a format in which instructions can be input by text or voice.

[0980] "Furniture avatars" are digital 3D models of real furniture that can be placed in a virtual space.

[0981] A "virtual store" is a virtual sales and design store space that exists on the Internet.

[0982] A "custom furniture design request" is a request submitted by a user when the user desires furniture with special dimensions or a specific design.

[0983] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new furniture designs based on user instructions.

[0984] A "prompt sentence" is specific input text used to give instructions to a generative AI model.

[0985] A "furniture layout" is the arrangement of furniture placed within a three-dimensional model based on the user's preferences.

[0986] The present invention relates to a system and method for virtually designing a room's interior. A user takes a photo of their room with a smart device, and a server analyzes the photo to generate a 3D model. Furthermore, the user inputs their budget and design image, and the system uses a generative AI model to place digital avatars of matching furniture on the 3D model.

[0987] This system uses the following hardware and software. The hardware includes a user device and a server, and user devices include smartphones, tablets, and smart glasses. The software includes an AI analysis tool for generating 3D models, a database search engine, a generative AI model, and a natural language processing engine.

[0988] The user device takes multiple images of the room and sends them to the server, which uses specialized software to analyze the images and generate a 3D model of the room. This 3D model is then sent to the user device, where the user can view it through an application.

[0989] Users input their budget and image for the room design in natural language. This can be input by text or voice and is sent from the user's device to the server. The server analyzes this data using a natural language processing engine and searches the system's database for digital avatars of furniture that match the user's preferences. A generative AI model is used to select the furniture, and a furniture layout that meets the user's requirements is generated.

[0990] As a specific example, if a user inputs a request such as "I want a monochrome living room with a budget of 300,000 yen," the server will input the following prompt sentence into the generative AI model:

[0991] "Generate a furniture layout for a modern monochrome living room with a budget of 300,000 yen. Provide 3D models in OBJ format."

[0992] This generates a matching furniture layout, which the server sends back to the user's device. The user can then review the virtual room design and make any necessary modifications. Custom furniture design requests can also be entered via text or voice, and the generative AI model will generate the design and place an order with the manufacturing factory.

[0993] This system allows users to design their own rooms in a virtual space, allowing them to consider their ideal interior in a realistic manner, and also allows for custom-made furniture.

[0994] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0995] Step 1:

[0996] A user uses a smart device to take pictures of their room from multiple angles. The input is the multiple images of the room taken. The device acquires these images and prepares them as data to send to the server. The output is image data prepared for sending to the server.

[0997] Step 2:

[0998] The device sends the captured images of the room to the server. The input is the image data prepared in step 1. The device uploads these images to the server via the Internet. The output is the image data uploaded to the server.

[0999] Step 3:

[1000] The server analyzes the received image data and generates a 3D model. The input is the image data uploaded to the server. The server uses AI technology to analyze the image features and generate a three-dimensional 3D model. The output is the generated 3D model data.

[1001] Step 4:

[1002] The server sends the generated 3D model to the user terminal. The input is the 3D model data generated in step 3. The server returns this data to the terminal, where the model is displayed. The output is the 3D model displayed on the user terminal.

[1003] Step 5:

[1004] The user uses the application to input a room design image and budget in natural language. The input is natural language text or voice data about the budget and design image. The device prepares this data to send to the server. The output is natural language data prepared for sending to the server.

[1005] Step 6:

[1006] The terminal sends the input design image and budget information to the server. The input is the natural language data prepared in step 5. The terminal uploads this data to the server. The output is the natural language data sent to the server.

[1007] Step 7:

[1008] The server analyzes the received natural language data. The input is the natural language data sent to the server. The server uses natural language processing technology to analyze the user's preferences and budget and identify suitable furniture. The output is a list of specific furniture items as a result of the analysis.

[1009] Step 8:

[1010] Based on the analysis results, the server searches for suitable furniture avatars from the system's database and places them in the 3D model. The input is the analysis results obtained in step 7 and the furniture information in the database. The server uses a generative AI model to generate prompt sentences and determine the optimal furniture layout. The output is 3D model data with the furniture avatars placed.

[1011] Step 9:

[1012] The server sends the 3D model data and furniture layout information to the user terminal. The input is the 3D model data generated in step 8. The server sends this data to the user terminal so that the furniture layout can be confirmed on the terminal. The output is the furniture layout information displayed on the user terminal.

[1013] Step 10:

[1014] A user inputs a custom furniture design request. The input is natural language text or voice data about the dimensions and design of the custom furniture. The terminal prepares this data for transmission to the server. The output is the custom furniture request data prepared for transmission to the server.

[1015] Step 11:

[1016] The server analyzes the custom furniture request and generates the custom furniture design using a generative AI model. The input is the custom furniture request data sent to the server. The server uses the generative AI model to generate prompt sentences and create a new furniture design. The output is the generated custom furniture design data.

[1017] Step 12:

[1018] The server sends the generated design information of the custom-made furniture to the manufacturing factory. The input is the design data of the custom-made furniture generated in step 11. The server sends this data to the manufacturing factory and requests the manufacturing of the custom-made furniture. The output is the design information of the custom-made furniture sent to the manufacturing factory.

[1019] 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.

[1020] This invention relates to a system that generates a 3D model based on images of multiple rooms taken by a user device and simulates furniture placement based on user instructions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it proposes optimal designs according to the user's emotions.

[1021] System Programming and Processing

[1022] 3D room model generation

[1023] Users use a device such as a smartphone or tablet to take photos of their room from multiple angles. The device then imports these photos into a dedicated application and converts them into a dedicated format. The device then uploads the converted photo data to a server. The server uses AI technology to analyze the received photos and generate a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the application.

[1024] Enter your image and budget

[1025] Users input their image of the room design and their budget using text or voice within the application. The device sends the input data to the server, which then analyzes it using natural language processing technology, extracting and understanding related keywords.

[1026] Furniture selection and placement

[1027] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The server then places the selected furniture avatars within the 3D model and determines their placement using an algorithm to calculate the optimal placement. The 3D model with the furniture placed is then sent back to the terminal, allowing the user to check the room design in the virtual space.

[1028] Custom furniture design and ordering

[1029] If the desired furniture item cannot be found, the user can input a design request for custom furniture via text or voice within the application. The device then sends the request data to the server, which analyzes it and uses generative AI to create a custom furniture design. The generated design data is then sent to a partner manufacturing factory.

[1030] Incorporating an emotion engine

[1031] Emotion Recognition and Analysis

[1032] The emotion engine recognizes emotions from the user's facial expressions and voice. For example, it captures the user's facial expressions through a camera and analyzes the facial expression data to identify the user's emotional state. When using voice recognition, it evaluates emotions from the user's tone of voice and speaking style.

[1033] Emotion-based design adjustments

[1034] The server receives the user's emotional data recognized by the emotion engine. Based on this emotional data, the server adjusts the design image and layout. For example, if the user is feeling stressed, it can suggest a relaxing interior style. It is also possible to dynamically change the furniture layout within the 3D model in real time according to changes in the user's emotions.

[1035] Specific examples

[1036] Photographing the room and generating 3DCG

[1037] The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos to generate a 3D model of the living room and sends it to the device. The user can then view the 3D model in the application.

[1038] Emotion Recognition and Furniture Placement

[1039] When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine analyzes the user's facial expression and recognizes that they are in a relaxed state. Based on this information, the server selects a Scandinavian-style furniture avatar that will help them relax and places it on the 3D model.

[1040] Custom furniture design and ordering

[1041] If a user wants a cabinet with specific dimensions and design, they input their request. The device sends the request to the server, which uses generative AI to create a custom cabinet design and sends the design data to a partner factory.

[1042] In this way, the present invention allows users to easily simulate room designs in real time, allowing them to smoothly select furniture and order custom-made furniture. Furthermore, by incorporating an emotion engine, it is possible to propose optimal designs according to the user's emotional state.

[1043] The processing flow will be explained below.

[1044] 3DCG generation of rooms

[1045] Step 1:

[1046] A user uses their smartphone to take photos of a room from multiple angles.

[1047] Step 2:

[1048] The device imports multiple photos taken into a dedicated application and converts them into a format that is easy to process.

[1049] Step 3:

[1050] The terminal transmits a request to upload the converted photo data to the server.

[1051] Step 4:

[1052] The server receives the upload request and returns permission, allowing the device to send the photo data to the server.

[1053] Step 5:

[1054] The server then analyzes the received photos using AI technology (e.g., image recognition algorithms), measuring the room's dimensions and identifying key furniture and features.

[1055] Step 6:

[1056] The server generates a 3D model of the room based on the analysis results. This 3D model is a virtual reproduction of the user's room.

[1057] Step 7:

[1058] The server encodes the generated 3D model and transmits it to the terminal.

[1059] Step 8:

[1060] The terminal displays the received three-dimensional model data, allowing the user to confirm the results.

[1061] Enter your image and budget

[1062] Step 1:

[1063] The user enters the image and budget for the room design using text or voice within the application.

[1064] Step 2:

[1065] The terminal sends the user's input to the server in the appropriate format.

[1066] Step 3:

[1067] The server receives the input and analyzes it using natural language processing technology, extracting relevant keywords based on the design image and budget.

[1068] Furniture selection and placement

[1069] Step 1:

[1070] Based on the analysis results, the server searches for matching furniture avatars from a furniture database, using keywords such as "Scandinavian style" or "relaxing."

[1071] Step 2:

[1072] The server compiles a list of multiple furniture avatars selected from the search results.

[1073] Step 3:

[1074] The server then places the furniture in the 3D model based on the list, running an algorithm to calculate, for example, where to place sofas and tables.

[1075] Step 4:

[1076] The server encodes a three-dimensional model with the furniture arranged and sends it to the terminal.

[1077] Step 5:

[1078] The terminal displays the received data, allowing the user to check the design of the virtual room.

[1079] Custom furniture design and ordering

[1080] Step 1:

[1081] If a user wants custom furniture, they enter their design request in the application by text or voice.

[1082] Step 2:

[1083] The terminal sends custom request data to the server.

[1084] Step 3:

[1085] The server receives the customization request and performs analysis to understand the requirements of the user's desired custom furniture.

[1086] Step 4:

[1087] The server uses generative AI to create custom furniture designs, such as cabinets based on user-specified dimensions and styles.

[1088] Step 5:

[1089] The server sends the generated design data for custom-made furniture to the partner factory and starts the ordering process.

[1090] Emotion engine built-in

[1091] Step 1:

[1092] While the user is using the application, the emotion engine captures the user's facial expressions and voice data through the camera and microphone.

[1093] Step 2:

[1094] The device transmits the captured facial expression data and voice data to the server.

[1095] Step 3:

[1096] The server uses an emotion engine to analyze the received data and identify the user's emotional state.

[1097] Step 4:

[1098] The server adjusts the design image and furniture layout based on the recognized emotion data. For example, if the user is feeling stressed, it will suggest interior design that has a relaxing effect.

[1099] Step 5:

[1100] The server transmits three-dimensional model data that has been dynamically updated in accordance with the emotion data to the terminal.

[1101] Step 6:

[1102] The device displays the received data, allowing users to see room designs that correspond to their emotions in real time.

[1103] In this way, the system of the present invention provides optimal room designs tailored to the user's needs through multiple processing steps, and also supports custom-made furniture. Furthermore, by using an emotion engine, it is possible to propose personalized designs based on the user's emotional state.

[1104] Example 2

[1105] 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."

[1106] Conventional interior design systems require users to manually select and arrange furniture, which is time-consuming, and it is difficult to adjust the design based on the user's emotional state. Furthermore, they lack the functionality to accept custom furniture design requests, or the ability to propose designs that reflect the user's specific image and budget. These issues need to be resolved.

[1107] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring a plurality of room images taken by a user terminal, means for analyzing the acquired images to generate a 3D model of the room, means for receiving budget and design image from the user in natural language and analyzing the same, means for searching for suitable furniture avatars based on the analysis results and arranging them in the 3D model, means for transmitting the generated 3D model and furniture arrangement information to the user terminal, means for recognizing the user's emotions, and means for adjusting the design based on the user's emotions. This allows the user to easily create a 3D model of a room and simulate furniture arrangement based on the user's budget and design image, as well as request a design for custom-made furniture, and further enables optimal design proposals to be made in response to the user's emotions.

[1108] A "user terminal" is a device operated by a user, and includes mobile information terminals such as smartphones and tablets.

[1109] "Room images" refer to photographic data that captures the interior of a room from multiple angles and is taken with a user terminal.

[1110] A "three-dimensional model" is a digital representation of the three-dimensional structure of a room, generated by analyzing an image of the room.

[1111] A "server" refers to a computer system that receives and processes requests from multiple clients (user terminals in this case).

[1112] "Budget" refers to the amount of money a user can spend on the interior design of a room.

[1113] "Design image" refers to a specific visual or theme related to the room decoration or interior style desired by the user.

[1114] "Natural language" refers to a language that humans use on a daily basis, i.e., information expressed in spoken or text form.

[1115] "Furniture avatars" are digital models stored in the system's furniture database, and refer to virtual furniture data that can be placed within a three-dimensional model of a room.

[1116] "Emotion recognition" refers to a technology that analyzes and identifies a user's emotional state from their facial expressions and voice.

[1117] "Generative AI" refers to artificial intelligence technology that generates new digital data (such as custom furniture designs) based on given prompts.

[1118] "Custom-made furniture" refers to furniture that is made to order for a user to request specific dimensions and designs.

[1119] This system generates a 3D model based on multiple images of a room taken with a user device and simulates furniture placement based on the user's instructions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to propose optimal designs based on the user's emotions.

[1120] System Overview

[1121] Users take photos of their rooms using devices such as smartphones or tablets. These photos are captured by a dedicated application, converted into a dedicated format, and then uploaded to a server. The server analyzes the received image data and generates a 3D model of the room. This process uses Google's TensorFlow AI technology. The generated 3D model is then sent back to the device, where the user can view it through the application.

[1122] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then analyzes it using natural language processing technology (e.g., OpenAI's GPT-3). As a result, relevant keywords are extracted and understood, and matching furniture avatars are searched for within the system's furniture database.

[1123] Furniture placement and custom furniture generation

[1124] The server places the selected furniture avatars within the 3D model and determines the optimal layout. This process uses genetic algorithms and A-search. The placed 3D model is then sent back to the terminal, allowing the user to check the room design in the virtual space.

[1125] If the desired furniture item cannot be found, the user can input a design request for custom furniture via text or voice within the application. This request is sent to the server, which then uses generative AI (e.g., OpenAI's GPT-3) to create a custom furniture design. The generated design data is then sent to a partner manufacturing factory.

[1126] Incorporating an emotion engine

[1127] The emotion engine recognizes emotions from the user's facial expressions and voice. For example, it captures the user's facial expressions through the camera and analyzes the facial data using Microsoft's Azure Face API. When using speech recognition, it analyzes the user's voice using Google Cloud Speech-to-Text API and evaluates emotions from the tone and speaking style.

[1128] The server receives the user's emotional data recognized by the emotion engine and adjusts the design image and layout based on this emotional data. If the user is feeling stressed, the server will suggest a relaxing interior style. It is also possible to dynamically change the furniture layout within the 3D model in real time.

[1129] Specific examples

[1130] Photographing the room and generating 3DCG

[1131] The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos using Google's TensorFlow, generates a 3D model of the living room, and sends it to the device. The user can then view the 3D model in the application.

[1132] Emotion Recognition and Furniture Placement

[1133] When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine simultaneously analyzes the user's facial expressions using Microsoft's Azure Face API and recognizes that the user is in a relaxed state. Based on this information, the server selects a Scandinavian-style furniture avatar that will help them relax and places it on the 3D model.

[1134] Custom furniture design and ordering

[1135] If a user wants a cabinet with specific dimensions and design, they input their request, and the device sends it to the server, which uses OpenAI's GPT-3 to create a custom cabinet design and sends the design data to the manufacturing factory.

[1136] Prompt Sentence Examples

[1137] "I'd like to create a relaxing Scandinavian-style living room. My budget is within 200,000 yen. Please suggest some designs that I can use as reference for furniture layout and colors."

[1138] This allows users to easily simulate room designs and smoothly select and order custom furniture. Furthermore, by incorporating an emotion engine, it is possible to propose optimal designs according to the user's emotional state.

[1139] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1140] Step 1: Take a photo of your room and upload it

[1141] A user takes photos of a room from multiple angles using a smartphone or tablet. The device imports the photos into a dedicated application and converts them from JPEG format to a dedicated format (for example, XYZ format). This format conversion is performed to standardize and compress the image data. The device then uploads the converted data to the server via an HTTP request. The input is an image of the room, and the output is image data in the dedicated format that is sent to the server.

[1142] Step 2: 3D model generation

[1143] The server analyzes the received image data using AI technology (Google's TensorFlow) and generates a 3D model of the room. Specifically, it digitizes the three-dimensional structure of the room as point cloud and mesh data based on images taken from multiple angles. The input is image data in a dedicated format, and the output is a 3D model (OBJ format). The server sends the generated 3D model to the terminal as an HTTP response. The user can view the 3D model through an application.

[1144] Step 3: Enter your image and budget

[1145] Within the application, the user inputs the image and budget for the room design using text or voice. The device sends this input data to the server via a POST request. The input is the user's text or voice data, and the output is natural language data sent to the server. For example, the user might input, "I want a Scandinavian-style living room with a budget of 200,000 yen."

[1146] Step 4: Image and budget analysis

[1147] The server uses natural language processing technology (OpenAI GPT-3) to analyze the image and budget data received from the user. This allows it to extract and understand the keywords "Scandinavian style" and "200,000 yen." The input is the transmitted natural language data, and the output is the analyzed keywords and phrases.

[1148] Step 5: Select and arrange furniture

[1149] Based on the analysis results, the server searches for suitable furniture avatars from the furniture database within the system. The retrieved furniture avatars are placed within the 3D model, and a genetic algorithm or A-search is used to determine the optimal placement. The input is the analyzed keywords and the 3D model, and the output is an updated 3D model with the furniture arranged. The server sends this updated 3D model to the terminal. The user can then check the room design in the virtual space using the application.

[1150] Step 6: Custom Furniture Design Request

[1151] If a user desires furniture with specific dimensions or design, they input a custom furniture design request within the application. The device sends the request data to the server. The input is a text or voice design request from the user, and the output is the request data sent to the server. For example, a user might input, "I'm looking for a Scandinavian-style cabinet that is 150cm wide and 75cm high."

[1152] Step 7: Create and submit your custom furniture design

[1153] The server uses generative AI (OpenAI's GPT-3) to create custom furniture designs. The generated design data (e.g., PNG format) is sent to partner manufacturing factories via email or a dedicated API. The input is the user's design request data, and the output is the custom furniture design data sent to the manufacturing factory.

[1154] Step 8: Emotion Recognition

[1155] The emotion engine, which recognizes emotions from the user's facial expressions and voice, captures user data using the device's camera and microphone. Emotion analysis is performed using Microsoft's Azure Face API and Google Cloud Speech-to-Text API. The input is the user's facial expression data and voice data, and the output is analyzed emotion data. For example, if the user enables the camera function, the emotion engine recognizes that the user is relaxed.

[1156] Step 9: Adjust your design based on emotion

[1157] The server adjusts the design image and furniture layout based on the emotional data obtained through emotion recognition. In particular, if the user is feeling stressed, it suggests a relaxing interior style. The input is the analyzed emotional data, and the output is an adjusted 3D model and design proposal. The adjusted design is sent to the user's device, and the user can view the updated design in the application.

[1158] (Application example 2)

[1159] 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."

[1160] Conventional interior design simulation systems have difficulty providing satisfying interior designs because they do not adequately consider the user's emotions when proposing designs. In addition, the design creation and ordering process for custom furniture is complicated and lacks automation.

[1161] The specification processing by the specification 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 acquiring multiple room images taken by a user terminal, means for analyzing the acquired images to generate a three-dimensional model of the room, means for receiving and analyzing the user's budget and design image in natural language, means for searching for suitable furniture avatars based on the analysis results and placing them in the three-dimensional model, means for transmitting the generated three-dimensional model and furniture placement information to the user terminal, emotion recognition means for recognizing the user's emotion, and means for proposing an optimal design based on the recognized emotion data. This makes it possible to propose optimal interior designs based on the user's emotions and to automate the design, creation, and ordering of custom furniture.

[1162] A "user terminal" is an electronic device that can be operated by a user, and includes smartphones, tablets, smart glasses, head-mounted displays, etc.

[1163] The term "server means" refers to a server system for analyzing captured images, generating three-dimensional models, analyzing natural language, placing furniture avatars, and transmitting generated data.

[1164] "Emotion recognition means" refers to a device or software that has the function of analyzing and recognizing emotions from a user's facial expressions and voice.

[1165] "Furniture avatar" refers to a three-dimensional model of furniture used in interior simulations in a virtual space.

[1166] "Custom furniture" refers to furniture that is designed and manufactured based on a user's specific requirements.

[1167] "Generative AI model" refers to an artificial intelligence model that automatically generates custom furniture designs based on input data.

[1168] The present invention provides a system for generating a three-dimensional model based on images of a plurality of rooms taken by a user terminal, and proposing an interior design based on the user's emotions. Specific embodiments will be described below.

[1169] System configuration

[1170] Hardware

[1171] User devices: smartphones, tablets, smart glasses, head-mounted displays, etc.

[1172] Server: Cloud servers with high-performance computing power and storage (e.g. AWS, Google Cloud).

[1173] Emotion recognition devices: Cameras and microphones that can analyze a user's facial expressions and voice (e.g., high-resolution webcams, directional microphones).

[1174] software

[1175] Image processing library: An image analysis library for generating 3D models, such as OpenCV.

[1176] Natural language processing engine: An engine for parsing user input data (e.g., NLTK, spaCy).

[1177] Emotion Recognition Library: A library for recognizing user emotions (e.g., Affectiva SDK).

[1178] Generative AI models: Models for automatically generating custom furniture designs (e.g., TensorFlow).

[1179] System Operation

[1180] 3D room model generation

[1181] Users use devices such as smartphones, tablets, or smart glasses to take photos of their room from multiple angles. The device then imports these photos into a dedicated application and converts them into a dedicated format. The device then uploads the converted photo data to a server. The server analyzes the received photos and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the application.

[1182] Emotion Recognition and Design Proposals

[1183] An emotion recognition device is used to capture the user's facial expressions and voice, and this data is analyzed using an emotion recognition library. The analysis results are sent to a server, which then adjusts the design image and layout based on the user's emotional state. This design proposal provides an interior style that the user can relax in, and dynamically changes the furniture layout in real time according to changes in emotion.

[1184] Custom furniture design and ordering

[1185] If a user desires furniture with specific dimensions and design, they input their custom furniture request within the application. The device then sends the request data to the server, which then uses a generative AI model to create a custom furniture design. The generated design data is then sent to partner manufacturing factories. This allows users to quickly design and order the custom furniture they desire.

[1186] Specific examples

[1187] Room photography and 3D model generation: The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos to generate a 3D model of the living room and sends it to the device. The user can then view the 3D model in the application.

[1188] Emotion recognition and furniture placement: When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine analyzes the user's facial expression and recognizes that the user is in a relaxed state. Based on this information, the server selects Scandinavian-style furniture avatars that will help the user relax and places them on the 3D model.

[1189] Design and order custom furniture: If a user wants a cabinet with specific dimensions and design, they input the request. The device sends the request to the server, which uses a generative AI model to create a custom cabinet design and sends the design data to a partner factory.

[1190] Prompt Sentence Examples

[1191] "Using an emotion engine, can you suggest a Scandinavian-inspired living room design that would suit a user with a relaxed expression? Also, can you tell us about a system that creates custom cabinets and automates the process of placing an order?"

[1192] As described above, the system of the present invention efficiently proposes interior designs based on the user's emotions and designs and orders custom-made furniture.

[1193] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1194] Step 1:

[1195] The user uses a device (smartphone, tablet, smart glasses, head-mounted display, etc.) to take photos of the room from multiple angles. The input is multiple images of the room, which are then converted into a dedicated format. The converted image data is uploaded from the device to the server. The server receives the uploaded image data and prepares it for 3D model generation.

[1196] Step 2:

[1197] The server analyzes the received image data and generates a 3D model of the room using photogrammetry techniques (e.g., image processing libraries such as OpenCV). This process involves extracting feature points from the images and reconstructing a 3D point cloud from multiple images. The output is the generated 3D model of the room.

[1198] Step 3:

[1199] The generated 3D model is then sent from the server to the user's device. The device receives this data and allows the user to visually confirm it. The input is the 3D model data sent from the server, and the output is the display of the 3D model on the device. The user can use this model to check the layout of the room.

[1200] Step 4:

[1201] The user inputs the budget and image of the room design on the device. This input data is in natural language, so the device sends it to the server. The server uses a natural language processing engine (e.g., NLTK, spaCy) to analyze the input data and extract relevant keywords. The input is the user's text or voice data, and the output is the analyzed keywords.

[1202] Step 5:

[1203] The server searches for matching furniture avatars from a furniture database based on the analyzed keywords. The retrieved furniture avatars are placed in the 3D model. Based on this, the optimal furniture placement is calculated. The output is a 3D model containing the placed furniture avatars.

[1204] Step 6:

[1205] An emotion recognition device (camera, microphone, etc.) is used to capture the user's facial expressions and voice. The input is the user's facial image and voice data. This data is analyzed by an emotion recognition library (e.g., Affectiva SDK) to recognize the user's emotional state. The output is the recognized user's emotional data.

[1206] Step 7:

[1207] The server adjusts design suggestions based on the emotion data. For example, if it determines that the user is relaxed, it will suggest a relaxing interior style. This suggestion is reflected in the 3D model in real time. The input is the recognized emotion data, and the output is the adjusted design suggestion.

[1208] Step 8:

[1209] When a user wants custom furniture with specific dimensions and design, they input their custom furniture request in the application. This request data is sent to the server. The server uses a generative AI model (e.g., TensorFlow) to create a custom furniture design and sends the design data to a partner manufacturing factory. The input is the user's custom furniture request data, and the output is the generated furniture design data.

[1210] In this way, this system efficiently proposes optimal interior designs based on the user's emotions and designs and orders custom furniture.

[1211] 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.

[1212] 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.

[1213] 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.

[1214] [Fourth embodiment]

[1215] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1216] 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.

[1217] 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).

[1218] 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.

[1219] 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.

[1220] 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).

[1221] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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.

[1226] 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.

[1227] 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."

[1228] The present invention relates to a system that allows users to take photos of their rooms using devices such as smartphones or tablets, and then uses AI to generate a 3D model of the room. Furthermore, users can input their budget and design image using natural language, and digital avatars of real furniture are placed within the 3D model based on that input. This allows users to create a virtual space and specifically consider the design of their ideal room.

[1229] System Programming and Processing

[1230] 3D room model generation

[1231] The user takes photos of the room from multiple angles using their device. The device then converts the images into a dedicated format and uploads them to the server. The server receives the images, analyzes them using AI technology, and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the app.

[1232] Enter your image and budget

[1233] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then uses natural language processing technology to analyze the received data and understand the user's preferences and budget.

[1234] Furniture selection and placement

[1235] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The selected furniture avatars are then placed in the 3D model. The server then sends the placed 3D model back to the terminal, allowing the user to virtually check the room design.

[1236] Custom furniture design and ordering

[1237] If a user cannot find the furniture they want, they can input a custom-made furniture design request via text or voice. The device then sends the custom-made request data to the server. The server analyzes the request and uses generative AI to create a custom furniture design. The generated design is then sent to a partner manufacturing factory as order data.

[1238] Specific examples

[1239] Photographing the room and generating 3DCG

[1240] The user takes three photos of their living room from different angles. The device uploads these photos to the server, which then uses AI analysis to generate a 3D model of the living room. The generated 3D model is then sent to the device, where the user can view it through the app.

[1241] Enter your image and budget

[1242] The user enters into the app, "I want a Scandinavian-style living room with a budget of 200,000 yen." The device sends this information to the server, which analyzes it. Based on the results, the app searches a list of Scandinavian-style furniture and selects an appropriate furniture avatar.

[1243] Furniture selection and placement

[1244] The server places furniture avatars such as sofas, tables, and rugs from the search results into the 3D model, and the placed 3D model is sent to the device, allowing the user to view the virtual living room on the app.

[1245] Custom furniture design and ordering

[1246] If a user wants a cabinet with specific dimensions and design, but there is no matching furniture in the system, they can enter a custom-order request into the app. The device sends the request to the server, which uses AI to create a custom cabinet design and sends the order data to a partner factory.

[1247] In this way, the present invention allows users to virtually design their own rooms and easily realize their ideal interior. In addition, by supporting custom-made furniture, it is possible to meet the diverse needs of users.

[1248] The processing flow will be explained below.

[1249] 3DCG generation of rooms

[1250] Step 1:

[1251] A user uses their smartphone to take photos of a room from multiple angles.

[1252] Step 2:

[1253] The device imports the photos taken into a dedicated application and converts the photo data into a format that is easy to analyze.

[1254] Step 3:

[1255] The device uploads the converted photo data to the server by sending an upload request, and the server receives the request and returns permission.

[1256] Step 4:

[1257] The server receives the photo data and analyzes it using AI technology (e.g., image recognition algorithms) to determine the dimensions of the room and the location of furniture.

[1258] Step 5:

[1259] The server generates a 3D model based on the identified information, which is a virtual reproduction of the user's room.

[1260] Step 6:

[1261] The server sends the generated 3D model to the device, which receives the data and displays the 3D model within the application.

[1262] Enter your image and budget

[1263] Step 1:

[1264] The user inputs the image and budget for the room design using text or voice within the dedicated application.

[1265] Step 2:

[1266] The terminal transmits the user's input data to the server.

[1267] Step 3:

[1268] The server receives the input data and analyzes it using natural language processing technology, understanding the design image and budget details and extracting related keywords.

[1269] Furniture selection and placement

[1270] Step 1:

[1271] The server searches a furniture database based on the user's desired design and budget.

[1272] Step 2:

[1273] Based on the search results, it generates a list of matching furniture avatars, including sofas, tables, chairs, etc.

[1274] Step 3:

[1275] The server places the selected furniture avatars in the 3D model, using an algorithm to calculate the optimal placement.

[1276] Step 4:

[1277] The server sends 3D model data with furniture arranged on it to the terminal.

[1278] Step 5:

[1279] The device receives the data and displays a 3D model with the furniture arranged in it within the application, allowing the user to see the virtual design of the room.

[1280] Custom furniture design and ordering

[1281] Step 1:

[1282] The user enters a custom furniture design request via text or voice within the application.

[1283] Step 2:

[1284] The terminal sends custom request data to the server.

[1285] Step 3:

[1286] The server receives the request data and analyzes it to understand the custom furniture design desired by the user.

[1287] Step 4:

[1288] The server uses generative AI to create custom furniture designs, and the design process involves customizing the design based on the user's desired dimensions and style.

[1289] Step 5:

[1290] The server transmits the generated design data for the custom-made furniture to the partner factory as order data.

[1291] In this way, specific actions are performed at each step, allowing the user to efficiently simulate the design of a room, and smoothly select furniture and place custom orders.

[1292] Example 1

[1293] 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."

[1294] In today's residential environment, it takes a lot of time and effort for users to realize their ideal interior design, and designing and ordering custom furniture also requires specialized knowledge and skills. As a result, users often have to pay high costs and go through complicated procedures, making it difficult to easily create their ideal space. To solve this problem, there is a need for a system that allows users to easily design their own rooms virtually and also easily design and order custom furniture.

[1295] 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.

[1296] In this invention, the server includes means for acquiring multiple images of a room taken by a user terminal, server means for analyzing the acquired images and generating a three-dimensional model of the room, server means for receiving budget and design image information from the user in natural language and analyzing it, server means for searching for suitable furniture data based on the analysis results and arranging it in the three-dimensional model, and server means for transmitting the generated three-dimensional model and furniture arrangement information to the user terminal. This allows users to easily virtually design their own rooms and arrange furniture that best suits their budget and design image. In addition, custom furniture can be designed and ordered using the server means, reducing high costs and complicated procedures and realizing ideal spaces.

[1297] "User terminal" refers to an electronic device that a user directly operates to take images of a room, input data, and check a model. Specifically, this applies to a smartphone or tablet.

[1298] "Server means" refers to advanced computing devices installed on the cloud or within a network that are responsible for analyzing data, generating models, and sending and receiving information. Specifically, this refers to high-performance physical servers or virtual servers.

[1299] "Image analysis" refers to the process of extracting the shape and dimensions of a room from images taken by a user device and generating a 3D model based on that information. This process uses AI technology and algorithms.

[1300] A "3D model" refers to digital data that recreates the physical features of a room in three-dimensional space, allowing users to virtually view the interior of the room.

[1301] "Natural language processing" refers to the technology of analyzing text and voice data input by users and understanding their meaning. This technology is used to accurately grasp the user's intentions and requests.

[1302] "Furniture Data" refers to the digital information about furniture held by the system, including information such as the type, shape, dimensions, and price of the furniture.

[1303] "Placing in 3D model" refers to the process of placing the selected furniture data in the appropriate position within the 3D model, allowing the user to check the virtual room design.

[1304] "Custom-made furniture" refers to furniture that is newly designed based on a user's specific requirements. It is designed and manufactured to meet the user's individual needs.

[1305] "Manufacturing equipment" refers to equipment used to manufacture custom furniture based on the design information sent from the server. Specifically, this applies to processing machines and assembly machines installed in the production factory.

[1306] The "dedicated format" refers to a data format used to convert captured images into a format that can be analyzed by the server, improving data uniformity and analysis efficiency.

[1307] The present invention relates to a system that allows users to take photos of their rooms using devices such as smartphones or tablets, and then uses AI to generate a 3D model of the room. Furthermore, users can input their budget and design image using natural language, and digital avatars of real furniture are placed within the 3D model based on that input. This allows users to create a virtual space and specifically consider the design of their ideal room.

[1308] Hardware and software used

[1309] 1. Device: Use a smartphone or tablet. Specific examples include iPhone, iPad, and Android devices.

[1310] 2. Server: Use a high-performance server, such as AWS EC2 or Google Cloud Compute Engine.

[1311] 3. Image analysis technology: YOLO, OpenCV, etc. are used as image analysis algorithms.

[1312] 4. 3D modeling software: Blender, Autodesk Maya.

[1313] 5. Natural Language Processing (NLP): Uses OpenAI GPT and Google BERT.

[1314] 6. Generative AI model: OpenAI DALL-E, using Stable Diffusion.

[1315] System program and processing description

[1316] 3D room model generation

[1317] The user takes photos of the room from multiple angles using their device. The device converts the images into a dedicated format and uploads them to the server. The server receives the images, analyzes them using AI technology, and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the app.

[1318] Enter your image and budget

[1319] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then uses natural language processing technology to analyze the received data and understand the user's preferences and budget.

[1320] Furniture selection and placement

[1321] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The selected furniture avatars are then placed within the 3D model. The server then sends the placed 3D model back to the terminal, allowing the user to virtually check the room design.

[1322] Custom furniture design and ordering

[1323] If a user cannot find the furniture they want, they can input a custom-made furniture design request via text or voice. The device then sends the custom-made request data to the server. The server analyzes the request and uses generative AI to create a custom furniture design. The generated design is then sent to a partner manufacturing factory as order data.

[1324] Specific examples

[1325] Photographing the room and generating a 3D model

[1326] The user takes three photos of their living room from different angles. The device uploads these photos to the server, which then uses AI analysis to generate a 3D model of the living room. The generated 3D model is then sent to the device, where the user can view it through the app.

[1327] Enter your image and budget

[1328] The user enters into the app, "I want a Scandinavian-style living room with a budget of 200,000 yen." The device sends this information to the server, which analyzes it. Based on the results, the app searches a list of Scandinavian-style furniture and selects an appropriate furniture avatar.

[1329] Furniture selection and placement

[1330] The server places furniture avatars such as sofas, tables, and rugs from the search results into the 3D model, and the placed 3D model is sent to the device, allowing the user to view the virtual living room on the app.

[1331] Custom furniture design and ordering

[1332] If a user wants a cabinet with specific dimensions and design, but there is no matching furniture in the system, they can enter a custom-order request into the app. The device then sends the request to the server, which uses generative AI to create a custom cabinet design and sends the order data to the manufacturing equipment.

[1333] In this way, the present invention allows users to virtually design their own rooms and easily realize their ideal interior. In addition, by supporting custom-made furniture, it is possible to meet the diverse needs of users.

[1334] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1335] Step 1:

[1336] The user takes photos of the room from multiple angles on their device. This is important to capture the entire room. The user uses a smartphone or tablet to take at least three photos from different angles. At this point, the input is a photo of the room, and the output is image data.

[1337] Step 2:

[1338] The device converts the captured image into a dedicated format. This conversion makes it easier to send the image to the server. Specifically, software on the device compresses the image and performs the format conversion. Through this process, the input image data is output as compressed image data.

[1339] Step 3:

[1340] The terminal uploads the converted image data to the server, where the data is transferred via the network. The input from the terminal is compressed image data, and the data is uploaded by sending it to the server.

[1341] Step 4:

[1342] The server receives the uploaded image and begins analysis. This analysis uses an image analysis algorithm (e.g., YOLO, OpenCV) to extract the room's shape and dimensions. Based on the input image data, the analyzed room's dimension and shape data is output.

[1343] Step 5:

[1344] The server generates a 3D model of the room based on the analysis results. 3D modeling software (e.g., Blender or Autodesk Maya) is used here. The input at this point is the analyzed room dimensions and shape data, and the 3D model data is output.

[1345] Step 6:

[1346] The server sends the generated 3D model to the terminal, and the user can view the 3D model through the application. The input is the generated 3D model data, and the model data is sent to the terminal as output.

[1347] Step 7:

[1348] The user inputs the image and budget for the room design using text or voice within the application. For example, they might input, "I want a Scandinavian-style living room with a budget of 200,000 yen." The input here is the user's text or voice data, which the device outputs as data.

[1349] Step 8:

[1350] The terminal transmits the user's input data to the server. The terminal forwards the user's text or voice input to the server, so the input is the user's text or voice data, and the output is the data transmitted to the server.

[1351] Step 9:

[1352] The server analyzes the received data using natural language processing (NLP) technology. Specifically, an NLP model (e.g., OpenAI GPT, Google BERT) understands the user's preferences and budget and extracts appropriate keywords. In this process, the input text data is analyzed and keywords and condition data based on the user's request are output.

[1353] Step 10:

[1354] The server searches for matching furniture avatars from a furniture database based on the analysis results. The server searches based on conditions such as "Scandinavian-style sofa" and "under 200,000 yen." The input is keywords and condition data from the analysis results, and the output is matching furniture data.

[1355] Step 11:

[1356] The server places the selected furniture avatars in the 3D model. Here, a 3D placement algorithm (e.g., Blender Python script) is used. The input data is the retrieved furniture data, and the output is the 3D model data with the furniture placed.

[1357] Step 12:

[1358] The server then sends the arranged 3D model back to the terminal. The user can then virtually check the room design. The input is the 3D model data with the furniture arranged, and the output is the model data sent to the terminal.

[1359] Step 13:

[1360] If the user cannot find the furniture they want, they can input their custom furniture design request into the application using text or voice. For example, they might input, "I want an antique-style cabinet that is 120cm wide and 80cm high." The input here is the user's text or voice data, and the device sends this as data output.

[1361] Step 14:

[1362] The terminal sends customized request data to the server. The input is the user's customized request data, and the output is the request data sent to the server.

[1363] Step 15:

[1364] The server analyzes the request and uses generative AI to create a custom furniture design. Specifically, a generative AI model (e.g., OpenAI DALL-E, Stable Diffusion) is used. The input data is the custom request data, and the output is the generated furniture design data.

[1365] Step 16:

[1366] The server sends the generated design to the manufacturing equipment as order data. The manufacturing equipment starts manufacturing the custom furniture based on the received design. The input is the generated design data, and the output is the order data sent to the manufacturing equipment.

[1367] (Application example 1)

[1368] 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."

[1369] In the past, there was no system that allowed users to easily generate a 3D model of their own room, and it was difficult to see in real time how the displayed furniture and decorations would affect the overall layout of the room.In addition, there was no efficient method that could quickly respond to user requests for designing and ordering custom furniture.

[1370] 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.

[1371] In this invention, the server includes means for acquiring a plurality of room images taken by a user terminal, server means for analyzing the acquired images and generating a three-dimensional model of the room, server means for receiving budget and design image from the user in natural language and analyzing them, server means for searching for suitable furniture avatars based on the analysis results and arranging them in the three-dimensional model, server means for transmitting the generated three-dimensional model and furniture arrangement information to the user terminal, and means for the user to virtually check and modify the room design in a virtual store. This allows users to virtually design their own rooms and easily realize their ideal interior.

[1372] A "user terminal" is a mobile information terminal used by a user, such as a smartphone, tablet, or smart glasses.

[1373] "Room images" are photographs of the room taken from multiple viewpoints by a user terminal.

[1374] A "3D model" is a three-dimensional digital model of a room generated from a two-dimensional image.

[1375] "Server means" refers to a computer system that has the function of receiving and analyzing data from a user terminal and returning necessary information to the user.

[1376] "Natural language" refers to the language that the user normally uses, and is a format in which instructions can be input by text or voice.

[1377] "Furniture avatars" are digital 3D models of real furniture that can be placed in a virtual space.

[1378] A "virtual store" is a virtual sales and design store space that exists on the Internet.

[1379] A "custom furniture design request" is a request submitted by a user when the user desires furniture with special dimensions or a specific design.

[1380] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new furniture designs based on user instructions.

[1381] A "prompt sentence" is specific input text used to give instructions to a generative AI model.

[1382] A "furniture layout" is the arrangement of furniture placed within a three-dimensional model based on the user's preferences.

[1383] The present invention relates to a system and method for virtually designing a room's interior. A user takes a photo of their room with a smart device, and a server analyzes the photo to generate a 3D model. Furthermore, the user inputs their budget and design image, and the system uses a generative AI model to place digital avatars of matching furniture on the 3D model.

[1384] This system uses the following hardware and software. The hardware includes a user device and a server, and user devices include smartphones, tablets, and smart glasses. The software includes an AI analysis tool for generating 3D models, a database search engine, a generative AI model, and a natural language processing engine.

[1385] The user device takes multiple images of the room and sends them to the server, which uses specialized software to analyze the images and generate a 3D model of the room. This 3D model is then sent to the user device, where the user can view it through an application.

[1386] Users input their budget and image for the room design in natural language. This can be input by text or voice and is sent from the user's device to the server. The server analyzes this data using a natural language processing engine and searches the system's database for digital avatars of furniture that match the user's preferences. A generative AI model is used to select the furniture, and a furniture layout that meets the user's requirements is generated.

[1387] As a specific example, if a user inputs a request such as "I want a monochrome living room with a budget of 300,000 yen," the server will input the following prompt sentence into the generative AI model:

[1388] "Generate a furniture layout for a modern monochrome living room with a budget of 300,000 yen. Provide 3D models in OBJ format."

[1389] This generates a matching furniture layout, which the server sends back to the user's device. The user can then review the virtual room design and make any necessary modifications. Custom furniture design requests can also be entered via text or voice, and the generative AI model will generate the design and place an order with the manufacturing factory.

[1390] This system allows users to design their own rooms in a virtual space, allowing them to consider their ideal interior in a realistic manner, and also allows for custom-made furniture.

[1391] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1392] Step 1:

[1393] A user uses a smart device to take pictures of their room from multiple angles. The input is the multiple images of the room taken. The device acquires these images and prepares them as data to send to the server. The output is image data prepared for sending to the server.

[1394] Step 2:

[1395] The device sends the captured images of the room to the server. The input is the image data prepared in step 1. The device uploads these images to the server via the Internet. The output is the image data uploaded to the server.

[1396] Step 3:

[1397] The server analyzes the received image data and generates a 3D model. The input is the image data uploaded to the server. The server uses AI technology to analyze the image features and generate a three-dimensional 3D model. The output is the generated 3D model data.

[1398] Step 4:

[1399] The server sends the generated 3D model to the user terminal. The input is the 3D model data generated in step 3. The server returns this data to the terminal, where the model is displayed. The output is the 3D model displayed on the user terminal.

[1400] Step 5:

[1401] The user uses the application to input a room design image and budget in natural language. The input is natural language text or voice data about the budget and design image. The device prepares this data to send to the server. The output is natural language data prepared for sending to the server.

[1402] Step 6:

[1403] The terminal sends the input design image and budget information to the server. The input is the natural language data prepared in step 5. The terminal uploads this data to the server. The output is the natural language data sent to the server.

[1404] Step 7:

[1405] The server analyzes the received natural language data. The input is the natural language data sent to the server. The server uses natural language processing technology to analyze the user's preferences and budget and identify suitable furniture. The output is a list of specific furniture items as a result of the analysis.

[1406] Step 8:

[1407] Based on the analysis results, the server searches for suitable furniture avatars from the system's database and places them in the 3D model. The input is the analysis results obtained in step 7 and the furniture information in the database. The server uses a generative AI model to generate prompt sentences and determine the optimal furniture layout. The output is 3D model data with the furniture avatars placed.

[1408] Step 9:

[1409] The server sends the 3D model data and furniture layout information to the user terminal. The input is the 3D model data generated in step 8. The server sends this data to the user terminal so that the furniture layout can be confirmed on the terminal. The output is the furniture layout information displayed on the user terminal.

[1410] Step 10:

[1411] A user inputs a custom furniture design request. The input is natural language text or voice data about the dimensions and design of the custom furniture. The terminal prepares this data for transmission to the server. The output is the custom furniture request data prepared for transmission to the server.

[1412] Step 11:

[1413] The server analyzes the custom furniture request and generates the custom furniture design using a generative AI model. The input is the custom furniture request data sent to the server. The server uses the generative AI model to generate prompt sentences and create a new furniture design. The output is the generated custom furniture design data.

[1414] Step 12:

[1415] The server sends the generated design information of the custom-made furniture to the manufacturing factory. The input is the design data of the custom-made furniture generated in step 11. The server sends this data to the manufacturing factory and requests the manufacturing of the custom-made furniture. The output is the design information of the custom-made furniture sent to the manufacturing factory.

[1416] 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.

[1417] This invention relates to a system that generates a 3D model based on images of multiple rooms taken by a user device and simulates furniture placement based on user instructions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it proposes optimal designs according to the user's emotions.

[1418] System Programming and Processing

[1419] 3D room model generation

[1420] Users use a device such as a smartphone or tablet to take photos of their room from multiple angles. The device then imports these photos into a dedicated application and converts them into a dedicated format. The device then uploads the converted photo data to a server. The server uses AI technology to analyze the received photos and generate a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the application.

[1421] Enter your image and budget

[1422] Users input their image of the room design and their budget using text or voice within the application. The device sends the input data to the server, which then analyzes it using natural language processing technology, extracting and understanding related keywords.

[1423] Furniture selection and placement

[1424] Based on the analysis results, the server searches for suitable furniture avatars from the system's furniture database. The server then places the selected furniture avatars within the 3D model and determines their placement using an algorithm to calculate the optimal placement. The 3D model with the furniture placed is then sent back to the terminal, allowing the user to check the room design in the virtual space.

[1425] Custom furniture design and ordering

[1426] If the desired furniture item cannot be found, the user can input a design request for custom furniture via text or voice within the application. The device then sends the request data to the server, which analyzes it and uses generative AI to create a custom furniture design. The generated design data is then sent to a partner manufacturing factory.

[1427] Incorporating an emotion engine

[1428] Emotion Recognition and Analysis

[1429] The emotion engine recognizes emotions from the user's facial expressions and voice. For example, it captures the user's facial expressions through a camera and analyzes the facial expression data to identify the user's emotional state. When using voice recognition, it evaluates emotions from the user's tone of voice and speaking style.

[1430] Emotion-based design adjustments

[1431] The server receives the user's emotional data recognized by the emotion engine. Based on this emotional data, the server adjusts the design image and layout. For example, if the user is feeling stressed, it can suggest a relaxing interior style. It is also possible to dynamically change the furniture layout within the 3D model in real time according to changes in the user's emotions.

[1432] Specific examples

[1433] Photographing the room and generating 3DCG

[1434] The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos to generate a 3D model of the living room and sends it to the device. The user can then view the 3D model in the application.

[1435] Emotion Recognition and Furniture Placement

[1436] When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine analyzes the user's facial expression and recognizes that they are in a relaxed state. Based on this information, the server selects a Scandinavian-style furniture avatar that will help them relax and places it on the 3D model.

[1437] Custom furniture design and ordering

[1438] If a user wants a cabinet with specific dimensions and design, they input their request. The device sends the request to the server, which uses generative AI to create a custom cabinet design and sends the design data to a partner factory.

[1439] In this way, the present invention allows users to easily simulate room designs in real time, allowing them to smoothly select furniture and order custom-made furniture. Furthermore, by incorporating an emotion engine, it is possible to propose optimal designs according to the user's emotional state.

[1440] The processing flow will be explained below.

[1441] 3DCG generation of rooms

[1442] Step 1:

[1443] A user uses their smartphone to take photos of a room from multiple angles.

[1444] Step 2:

[1445] The device imports multiple photos taken into a dedicated application and converts them into a format that is easy to process.

[1446] Step 3:

[1447] The terminal transmits a request to upload the converted photo data to the server.

[1448] Step 4:

[1449] The server receives the upload request and returns permission, allowing the device to send the photo data to the server.

[1450] Step 5:

[1451] The server then analyzes the received photos using AI technology (e.g., image recognition algorithms), measuring the room's dimensions and identifying key furniture and features.

[1452] Step 6:

[1453] The server generates a 3D model of the room based on the analysis results. This 3D model is a virtual reproduction of the user's room.

[1454] Step 7:

[1455] The server encodes the generated 3D model and transmits it to the terminal.

[1456] Step 8:

[1457] The terminal displays the received three-dimensional model data, allowing the user to confirm the results.

[1458] Enter your image and budget

[1459] Step 1:

[1460] The user enters the image and budget for the room design using text or voice within the application.

[1461] Step 2:

[1462] The terminal sends the user's input to the server in the appropriate format.

[1463] Step 3:

[1464] The server receives the input and analyzes it using natural language processing technology, extracting relevant keywords based on the design image and budget.

[1465] Furniture selection and placement

[1466] Step 1:

[1467] Based on the analysis results, the server searches for matching furniture avatars from a furniture database, using keywords such as "Scandinavian style" or "relaxing."

[1468] Step 2:

[1469] The server compiles a list of multiple furniture avatars selected from the search results.

[1470] Step 3:

[1471] The server then places the furniture in the 3D model based on the list, running an algorithm to calculate, for example, where to place sofas and tables.

[1472] Step 4:

[1473] The server encodes a three-dimensional model with the furniture arranged and sends it to the terminal.

[1474] Step 5:

[1475] The terminal displays the received data, allowing the user to check the design of the virtual room.

[1476] Custom furniture design and ordering

[1477] Step 1:

[1478] If a user wants custom furniture, they enter their design request in the application by text or voice.

[1479] Step 2:

[1480] The terminal sends custom request data to the server.

[1481] Step 3:

[1482] The server receives the customization request and performs analysis to understand the requirements of the user's desired custom furniture.

[1483] Step 4:

[1484] The server uses generative AI to create custom furniture designs, such as cabinets based on user-specified dimensions and styles.

[1485] Step 5:

[1486] The server sends the generated design data for custom-made furniture to the partner factory and starts the ordering process.

[1487] Emotion engine built-in

[1488] Step 1:

[1489] While the user is using the application, the emotion engine captures the user's facial expressions and voice data through the camera and microphone.

[1490] Step 2:

[1491] The device transmits the captured facial expression data and voice data to the server.

[1492] Step 3:

[1493] The server uses an emotion engine to analyze the received data and identify the user's emotional state.

[1494] Step 4:

[1495] The server adjusts the design image and furniture layout based on the recognized emotion data. For example, if the user is feeling stressed, it will suggest interior design that has a relaxing effect.

[1496] Step 5:

[1497] The server transmits three-dimensional model data that has been dynamically updated in accordance with the emotion data to the terminal.

[1498] Step 6:

[1499] The device displays the received data, allowing users to see room designs that correspond to their emotions in real time.

[1500] In this way, the system of the present invention provides optimal room designs tailored to the user's needs through multiple processing steps, and also supports custom-made furniture. Furthermore, by using an emotion engine, it is possible to propose personalized designs based on the user's emotional state.

[1501] Example 2

[1502] 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."

[1503] Conventional interior design systems require users to manually select and arrange furniture, which is time-consuming, and it is difficult to adjust the design based on the user's emotional state. Furthermore, they lack the functionality to accept custom furniture design requests, or the ability to propose designs that reflect the user's specific image and budget. These issues need to be resolved.

[1504] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring a plurality of room images taken by a user terminal, means for analyzing the acquired images to generate a 3D model of the room, means for receiving budget and design image from the user in natural language and analyzing the same, means for searching for suitable furniture avatars based on the analysis results and arranging them in the 3D model, means for transmitting the generated 3D model and furniture arrangement information to the user terminal, means for recognizing the user's emotions, and means for adjusting the design based on the user's emotions. This allows the user to easily create a 3D model of a room and simulate furniture arrangement based on the user's budget and design image, as well as request a design for custom-made furniture, and further enables optimal design proposals to be made in response to the user's emotions.

[1505] A "user terminal" is a device operated by a user, and includes mobile information terminals such as smartphones and tablets.

[1506] "Room images" refer to photographic data that captures the interior of a room from multiple angles and is taken with a user terminal.

[1507] A "three-dimensional model" is a digital representation of the three-dimensional structure of a room, generated by analyzing an image of the room.

[1508] A "server" refers to a computer system that receives and processes requests from multiple clients (user terminals in this case).

[1509] "Budget" refers to the amount of money a user can spend on the interior design of a room.

[1510] "Design image" refers to a specific visual or theme related to the room decoration or interior style desired by the user.

[1511] "Natural language" refers to a language that humans use on a daily basis, i.e., information expressed in spoken or text form.

[1512] "Furniture avatars" are digital models stored in the system's furniture database, and refer to virtual furniture data that can be placed within a three-dimensional model of a room.

[1513] "Emotion recognition" refers to a technology that analyzes and identifies a user's emotional state from their facial expressions and voice.

[1514] "Generative AI" refers to artificial intelligence technology that generates new digital data (such as custom furniture designs) based on given prompts.

[1515] "Custom-made furniture" refers to furniture that is made to order for a user to request specific dimensions and designs.

[1516] This system generates a 3D model based on multiple images of a room taken with a user device and simulates furniture placement based on the user's instructions. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to propose optimal designs based on the user's emotions.

[1517] System Overview

[1518] Users take photos of their rooms using devices such as smartphones or tablets. These photos are captured by a dedicated application, converted into a dedicated format, and then uploaded to a server. The server analyzes the received image data and generates a 3D model of the room. This process uses Google's TensorFlow AI technology. The generated 3D model is then sent back to the device, where the user can view it through the application.

[1519] Within the application, users input their image of the room design and their budget using text or voice. The device then sends this input data to the server, which then analyzes it using natural language processing technology (e.g., OpenAI's GPT-3). As a result, relevant keywords are extracted and understood, and matching furniture avatars are searched for within the system's furniture database.

[1520] Furniture placement and custom furniture generation

[1521] The server places the selected furniture avatars within the 3D model and determines the optimal layout. This process uses genetic algorithms and A-search. The placed 3D model is then sent back to the terminal, allowing the user to check the room design in the virtual space.

[1522] If the desired furniture item cannot be found, the user can input a design request for custom furniture via text or voice within the application. This request is sent to the server, which then uses generative AI (e.g., OpenAI's GPT-3) to create a custom furniture design. The generated design data is then sent to a partner manufacturing factory.

[1523] Incorporating an emotion engine

[1524] The emotion engine recognizes emotions from the user's facial expressions and voice. For example, it captures the user's facial expressions through the camera and analyzes the facial data using Microsoft's Azure Face API. When using speech recognition, it analyzes the user's voice using Google Cloud Speech-to-Text API and evaluates emotions from the tone and speaking style.

[1525] The server receives the user's emotional data recognized by the emotion engine and adjusts the design image and layout based on this emotional data. If the user is feeling stressed, the server will suggest a relaxing interior style. It is also possible to dynamically change the furniture layout within the 3D model in real time.

[1526] Specific examples

[1527] Photographing the room and generating 3DCG

[1528] The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos using Google's TensorFlow, generates a 3D model of the living room, and sends it to the device. The user can then view the 3D model in the application.

[1529] Emotion Recognition and Furniture Placement

[1530] When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine simultaneously analyzes the user's facial expressions using Microsoft's Azure Face API and recognizes that the user is in a relaxed state. Based on this information, the server selects a Scandinavian-style furniture avatar that will help them relax and places it on the 3D model.

[1531] Custom furniture design and ordering

[1532] If a user wants a cabinet with specific dimensions and design, they input their request, and the device sends it to the server, which uses OpenAI's GPT-3 to create a custom cabinet design and sends the design data to the manufacturing factory.

[1533] Prompt Sentence Examples

[1534] "I'd like to create a relaxing Scandinavian-style living room. My budget is within 200,000 yen. Please suggest some designs that I can use as reference for furniture layout and colors."

[1535] This allows users to easily simulate room designs and smoothly select and order custom furniture. Furthermore, by incorporating an emotion engine, it is possible to propose optimal designs according to the user's emotional state.

[1536] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1537] Step 1: Take a photo of your room and upload it

[1538] A user takes photos of a room from multiple angles using a smartphone or tablet. The device imports the photos into a dedicated application and converts them from JPEG format to a dedicated format (for example, XYZ format). This format conversion is performed to standardize and compress the image data. The device then uploads the converted data to the server via an HTTP request. The input is an image of the room, and the output is image data in the dedicated format that is sent to the server.

[1539] Step 2: 3D model generation

[1540] The server analyzes the received image data using AI technology (Google's TensorFlow) and generates a 3D model of the room. Specifically, it digitizes the three-dimensional structure of the room as point cloud and mesh data based on images taken from multiple angles. The input is image data in a dedicated format, and the output is a 3D model (OBJ format). The server sends the generated 3D model to the terminal as an HTTP response. The user can view the 3D model through an application.

[1541] Step 3: Enter your image and budget

[1542] Within the application, the user inputs the image and budget for the room design using text or voice. The device sends this input data to the server via a POST request. The input is the user's text or voice data, and the output is natural language data sent to the server. For example, the user might input, "I want a Scandinavian-style living room with a budget of 200,000 yen."

[1543] Step 4: Image and budget analysis

[1544] The server uses natural language processing technology (OpenAI GPT-3) to analyze the image and budget data received from the user. This allows it to extract and understand the keywords "Scandinavian style" and "200,000 yen." The input is the transmitted natural language data, and the output is the analyzed keywords and phrases.

[1545] Step 5: Select and arrange furniture

[1546] Based on the analysis results, the server searches for suitable furniture avatars from the furniture database within the system. The retrieved furniture avatars are placed within the 3D model, and a genetic algorithm or A-search is used to determine the optimal placement. The input is the analyzed keywords and the 3D model, and the output is an updated 3D model with the furniture arranged. The server sends this updated 3D model to the terminal. The user can then check the room design in the virtual space using the application.

[1547] Step 6: Custom Furniture Design Request

[1548] If a user desires furniture with specific dimensions or design, they input a custom furniture design request within the application. The device sends the request data to the server. The input is a text or voice design request from the user, and the output is the request data sent to the server. For example, a user might input, "I'm looking for a Scandinavian-style cabinet that is 150cm wide and 75cm high."

[1549] Step 7: Create and submit your custom furniture design

[1550] The server uses generative AI (OpenAI's GPT-3) to create custom furniture designs. The generated design data (e.g., PNG format) is sent to partner manufacturing factories via email or a dedicated API. The input is the user's design request data, and the output is the custom furniture design data sent to the manufacturing factory.

[1551] Step 8: Emotion Recognition

[1552] The emotion engine, which recognizes emotions from the user's facial expressions and voice, captures user data using the device's camera and microphone. Emotion analysis is performed using Microsoft's Azure Face API and Google Cloud Speech-to-Text API. The input is the user's facial expression data and voice data, and the output is analyzed emotion data. For example, if the user enables the camera function, the emotion engine recognizes that the user is relaxed.

[1553] Step 9: Adjust your design based on emotion

[1554] The server adjusts the design image and furniture layout based on the emotional data obtained through emotion recognition. In particular, if the user is feeling stressed, it suggests a relaxing interior style. The input is the analyzed emotional data, and the output is an adjusted 3D model and design proposal. The adjusted design is sent to the user's device, and the user can view the updated design in the application.

[1555] (Application example 2)

[1556] 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."

[1557] Conventional interior design simulation systems have difficulty providing satisfying interior designs because they do not adequately consider the user's emotions when proposing designs. In addition, the design creation and ordering process for custom furniture is complicated and lacks automation.

[1558] The specification processing by the specification 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 acquiring multiple room images taken by a user terminal, means for analyzing the acquired images to generate a three-dimensional model of the room, means for receiving and analyzing the user's budget and design image in natural language, means for searching for suitable furniture avatars based on the analysis results and placing them in the three-dimensional model, means for transmitting the generated three-dimensional model and furniture placement information to the user terminal, emotion recognition means for recognizing the user's emotion, and means for proposing an optimal design based on the recognized emotion data. This makes it possible to propose optimal interior designs based on the user's emotions and to automate the design, creation, and ordering of custom furniture.

[1559] A "user terminal" is an electronic device that can be operated by a user, and includes smartphones, tablets, smart glasses, head-mounted displays, etc.

[1560] The term "server means" refers to a server system for analyzing captured images, generating three-dimensional models, analyzing natural language, placing furniture avatars, and transmitting generated data.

[1561] "Emotion recognition means" refers to a device or software that has the function of analyzing and recognizing emotions from a user's facial expressions and voice.

[1562] "Furniture avatar" refers to a three-dimensional model of furniture used in interior simulations in a virtual space.

[1563] "Custom furniture" refers to furniture that is designed and manufactured based on a user's specific requirements.

[1564] "Generative AI model" refers to an artificial intelligence model that automatically generates custom furniture designs based on input data.

[1565] The present invention provides a system for generating a three-dimensional model based on images of a plurality of rooms taken by a user terminal, and proposing an interior design based on the user's emotions. Specific embodiments will be described below.

[1566] System configuration

[1567] Hardware

[1568] User devices: smartphones, tablets, smart glasses, head-mounted displays, etc.

[1569] Server: Cloud servers with high-performance computing power and storage (e.g. AWS, Google Cloud).

[1570] Emotion recognition devices: Cameras and microphones that can analyze a user's facial expressions and voice (e.g., high-resolution webcams, directional microphones).

[1571] software

[1572] Image processing library: An image analysis library for generating 3D models, such as OpenCV.

[1573] Natural language processing engine: An engine for parsing user input data (e.g., NLTK, spaCy).

[1574] Emotion Recognition Library: A library for recognizing user emotions (e.g., Affectiva SDK).

[1575] Generative AI models: Models for automatically generating custom furniture designs (e.g., TensorFlow).

[1576] System Operation

[1577] 3D room model generation

[1578] Users use devices such as smartphones, tablets, or smart glasses to take photos of their room from multiple angles. The device then imports these photos into a dedicated application and converts them into a dedicated format. The device then uploads the converted photo data to a server. The server analyzes the received photos and generates a 3D model of the room. The generated 3D model is then sent back to the device, where the user can view it through the application.

[1579] Emotion Recognition and Design Proposals

[1580] An emotion recognition device is used to capture the user's facial expressions and voice, and this data is analyzed using an emotion recognition library. The analysis results are sent to a server, which then adjusts the design image and layout based on the user's emotional state. This design proposal provides an interior style that the user can relax in, and dynamically changes the furniture layout in real time according to changes in emotion.

[1581] Custom furniture design and ordering

[1582] If a user desires furniture with specific dimensions and design, they input their custom furniture request within the application. The device then sends the request data to the server, which then uses a generative AI model to create a custom furniture design. The generated design data is then sent to partner manufacturing factories. This allows users to quickly design and order the custom furniture they desire.

[1583] Specific examples

[1584] Room photography and 3D model generation: The user takes photos of their living room from different angles, and the device sends the photo data to the server. The server analyzes the photos to generate a 3D model of the living room and sends it to the device. The user can then view the 3D model in the application.

[1585] Emotion recognition and furniture placement: When a user inputs "I want a Scandinavian-style living room with a budget of 200,000 yen," the emotion engine analyzes the user's facial expression and recognizes that the user is in a relaxed state. Based on this information, the server selects Scandinavian-style furniture avatars that will help the user relax and places them on the 3D model.

[1586] Design and order custom furniture: If a user wants a cabinet with specific dimensions and design, they input the request. The device sends the request to the server, which uses a generative AI model to create a custom cabinet design and sends the design data to a partner factory.

[1587] Prompt Sentence Examples

[1588] "Using an emotion engine, can you suggest a Scandinavian-inspired living room design that would suit a user with a relaxed expression? Also, can you tell us about a system that creates custom cabinets and automates the process of placing an order?"

[1589] As described above, the system of the present invention efficiently proposes interior designs based on the user's emotions and designs and orders custom-made furniture.

[1590] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1591] Step 1:

[1592] The user uses a device (smartphone, tablet, smart glasses, head-mounted display, etc.) to take photos of the room from multiple angles. The input is multiple images of the room, which are then converted into a dedicated format. The converted image data is uploaded from the device to the server. The server receives the uploaded image data and prepares it for 3D model generation.

[1593] Step 2:

[1594] The server analyzes the received image data and generates a 3D model of the room using photogrammetry techniques (e.g., image processing libraries such as OpenCV). This process involves extracting feature points from the images and reconstructing a 3D point cloud from multiple images. The output is the generated 3D model of the room.

[1595] Step 3:

[1596] The generated 3D model is then sent from the server to the user's device. The device receives this data and allows the user to visually confirm it. The input is the 3D model data sent from the server, and the output is the display of the 3D model on the device. The user can use this model to check the layout of the room.

[1597] Step 4:

[1598] The user inputs the budget and image of the room design on the device. This input data is in natural language, so the device sends it to the server. The server uses a natural language processing engine (e.g., NLTK, spaCy) to analyze the input data and extract relevant keywords. The input is the user's text or voice data, and the output is the analyzed keywords.

[1599] Step 5:

[1600] The server searches for matching furniture avatars from a furniture database based on the analyzed keywords. The retrieved furniture avatars are placed in the 3D model. Based on this, the optimal furniture placement is calculated. The output is a 3D model containing the placed furniture avatars.

[1601] Step 6:

[1602] An emotion recognition device (camera, microphone, etc.) is used to capture the user's facial expressions and voice. The input is the user's facial image and voice data. This data is analyzed by an emotion recognition library (e.g., Affectiva SDK) to recognize the user's emotional state. The output is the recognized user's emotional data.

[1603] Step 7:

[1604] The server adjusts design suggestions based on the emotion data. For example, if it determines that the user is relaxed, it will suggest a relaxing interior style. This suggestion is reflected in the 3D model in real time. The input is the recognized emotion data, and the output is the adjusted design suggestion.

[1605] Step 8:

[1606] When a user wants custom furniture with specific dimensions and design, they input their custom furniture request in the application. This request data is sent to the server. The server uses a generative AI model (e.g., TensorFlow) to create a custom furniture design and sends the design data to a partner manufacturing factory. The input is the user's custom furniture request data, and the output is the generated furniture design data.

[1607] In this way, this system efficiently proposes optimal interior designs based on the user's emotions and designs and orders custom furniture.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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).

[1615] 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.

[1616] 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."

[1617] 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.

[1618] 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).

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] 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.

[1625] 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.

[1626] 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.

[1627] 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.

[1628] 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.

[1629] The following is further disclosed regarding the above embodiment.

[1630] (Claim 1)

[1631] A means for acquiring images of a plurality of rooms taken by a user terminal;

[1632] a server means for analyzing the acquired images and generating a three-dimensional model of the room;

[1633] A server means for receiving and analyzing the budget and design image from the user in natural language;

[1634] A server means for searching for suitable furniture avatars based on the analysis results and placing them on the three-dimensional model;

[1635] a server means for transmitting the generated three-dimensional model and furniture placement information to a user terminal;

[1636] A system including:

[1637] (Claim 2)

[1638] a server means for analyzing a custom-made furniture design request received from a user and generating a custom-made furniture design;

[1639] a server means for transmitting the generated design information to a manufacturing factory;

[1640] 10. The system of claim 1, further comprising:

[1641] (Claim 3)

[1642] means for converting the image of the room sent from the user terminal into a dedicated format;

[1643] means for transmitting the converted format to a server;

[1644] means for displaying the three-dimensional model data received from the server;

[1645] 10. The system of claim 1, further comprising:

[1646] "Example 1"

[1647] (Claim 1)

[1648] A means for acquiring images of a plurality of rooms taken by a user terminal;

[1649] a server means for analyzing the acquired images and generating a three-dimensional model of the room;

[1650] A server means for receiving and analyzing the budget and design image from the user in natural language;

[1651] A server means for searching for suitable furniture data based on the analysis results and arranging the data in the three-dimensional model;

[1652] a server means for transmitting the generated three-dimensional model and furniture placement information to a user terminal;

[1653] A system including:

[1654] (Claim 2)

[1655] a server means for analyzing a custom-made furniture design request received from a user and generating a custom-made furniture design;

[1656] a server means for transmitting the generated design information to a manufacturing device;

[1657] 10. The system of claim 1, further comprising:

[1658] (Claim 3)

[1659] means for converting the image of the room sent from the user terminal into a dedicated format;

[1660] means for transmitting the converted format to a server;

[1661] means for displaying the three-dimensional model data received from the server;

[1662] 10. The system of claim 1, further comprising:

[1663] "Application Example 1"

[1664] (Claim 1)

[1665] A means for acquiring images of a plurality of rooms taken by a user terminal;

[1666] a server means for analyzing the acquired images and generating a three-dimensional model of the room;

[1667] A server means for receiving and analyzing the budget and design image from the user in natural language;

[1668] A server means for searching for suitable furniture avatars based on the analysis results and placing them on the three-dimensional model;

[1669] a server means for transmitting the generated three-dimensional model and furniture placement information to a user terminal;

[1670] A means for users to virtually check and modify the design of a room in a virtual store;

[1671] A system including:

[1672] (Claim 2)

[1673] a server means for analyzing a custom-made furniture design request received from a user and generating a custom-made furniture design;

[1674] A means for generating custom furniture prompts utilizing a generative AI model; and

[1675] a server means for transmitting the generated design information to a manufacturing factory;

[1676] 10. The system of claim 1, further comprising:

[1677] (Claim 3)

[1678] means for converting the image of the room sent from the user terminal into a dedicated format;

[1679] means for transmitting the converted format to a server;

[1680] means for displaying the three-dimensional model data received from the server;

[1681] means for generating a virtual furniture layout;

[1682] 10. The system of claim 1, further comprising:

[1683] "Example 2: Combining Emotion Engines"

[1684] (Claim 1)

[1685] A means for acquiring images of a plurality of rooms taken by a user terminal;

[1686] a server means for analyzing the acquired images and generating a three-dimensional model of the room;

[1687] A server means for receiving and analyzing the budget and design image from the user in natural language;

[1688] A server means for searching for suitable furniture avatars based on the analysis results and placing them on the three-dimensional model;

[1689] a server means for transmitting the generated three-dimensional model and furniture placement information to a user terminal;

[1690] emotion recognition means for recognizing an emotion of a user;

[1691] a server means for adjusting the design based on the user's emotions;

[1692] A system including:

[1693] (Claim 2)

[1694] a server means for analyzing a custom-made furniture design request received from a user and generating a custom-made furniture design;

[1695] a server means for transmitting the generated design information to a manufacturing factory;

[1696] 10. The system of claim 1, further comprising:

[1697] (Claim 3)

[1698] means for converting the image of the room sent from the user terminal into a dedicated format;

[1699] means for transmitting the converted format to a server;

[1700] means for displaying the three-dimensional model data received from the server;

[1701] 10. The system of claim 1, further comprising:

[1702] "Application example 2 when combining emotion engines"

[1703] (Claim 1)

[1704] A means for acquiring images of a plurality of rooms taken by a user terminal;

[1705] a server means for analyzing the acquired images and generating a three-dimensional model of the room;

[1706] A server means for receiving and analyzing the budget and design image from the user in natural language;

[1707] A server means for searching for suitable furniture avatars based on the analysis results and placing them on the three-dimensional model;

[1708] a server means for transmitting ...

Claims

1. A means for acquiring images of a plurality of rooms taken by a user terminal; a server means for analyzing the acquired images and generating a three-dimensional model of the room; A server means for receiving and analyzing the budget and design image from the user in natural language; A server means for searching for suitable furniture avatars based on the analysis results and placing them on the three-dimensional model; a server means for transmitting the generated three-dimensional model and furniture placement information to a user terminal; A system including:

2. a server means for analyzing a custom-made furniture design request received from a user and generating a custom-made furniture design; a server means for transmitting the generated design information to a manufacturing factory; The system of claim 1 further comprising:

3. means for converting the image of the room sent from the user terminal into a dedicated format; means for transmitting the converted format to a server; means for displaying the three-dimensional model data received from the server; The system of claim 1 further comprising:

Images