System

Abstract

A system is provided.SOLUTION: A system, comprising: means for automatically generating an image of a room after moving by capturing furniture information using a creation eye and combining the furniture information with property data; means for transmitting furniture information input by a user from a terminal to a server; means for generating a simulation by acquiring detailed information of a property selected by the user and combining the detailed information with the furniture information; and means for transmitting the generated simulation image to the terminal and displaying the simulation image to the user.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] Conventional property search sites have the problem that it is difficult to visualize what it will be like to actually live in a new property without viewing the property. Furthermore, there are limited ways to visually confirm how the current furniture will be arranged in the new property, which requires users to visit the property multiple times. This situation increases the time and physical burden, making it extremely difficult to make a decision about moving. Therefore, there is a need for a system that allows users to concretely visualize what the room will be like after moving in, without viewing the property. [Means for solving the problem]

[0005] The present invention provides a system that uses generative AI to import furniture information and combine it with property data to automatically generate an image of what a room will look like after moving in. Specifically, the furniture information entered by the user is sent from the terminal to a server, and the server obtains detailed information about the property selected by the user. The system then combines the furniture information and property information to generate a simulation, and sends the generated simulation image to the terminal to display it to the user. The system also provides a function that allows the user to manually fine-tune the furniture placement, and then generates another simulation image based on the adjustment results and displays it on the terminal. Furthermore, the system provides the user with a link to purchase furniture based on the generated simulation image, allowing them to easily purchase the necessary furniture along with an image of their specific living space.

[0006] "Generative AI" is an artificial intelligence technology that generates new information and images based on data entered by the user.

[0007] "Furniture information" refers to specific information such as dimensions and photos of the furniture the user owns.

[0008] "Property Information" refers to detailed information about a property, such as dimensions, layout, and interior photos, obtained from a real estate database.

[0009] "Simulation" is the process of virtually generating an image of what the room will look like after you move in by combining furniture information and property information.

[0010] "Terminal" refers to a device operated by a user (such as a smartphone, tablet, or PC).

[0011] The "server" is a central computer system that receives furniture and property information and generates simulation images using generation AI.

[0012] "Fine-tuning" refers to an operation by which a user manually changes the arrangement of furniture.

[0013] A "link" refers to a connection path on the web for purchasing furniture based on the generated simulated image.

[0014] "User" refers to a person who uses this system to search for properties and conduct simulations. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and the newly selected property. The operation of this system and a specific example are described below.

[0037] System Overview

[0038] 1. The user enters furniture information

[0039] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[0040] 2. The device sends the furniture information to the server

[0041] The terminal converts the furniture information (photographs and dimensions) entered by the user into a specified data format and sends it to the server.

[0042] 3. The server retrieves the property information

[0043] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos, etc.) of the property corresponding to that ID from the database.

[0044] 4. Running a simulation using generative AI

[0045] The server integrates the acquired furniture information with the property information and uses generative AI to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[0046] 5. Sending and displaying the generated image

[0047] The server transmits the generated simulation image to the terminal, which displays the image to the user.

[0048] 6. Fine-tuning furniture arrangement by users

[0049] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[0050] 7. Providing links to purchase furniture

[0051] If the user decides that they need new furniture based on the final image generated, they can purchase the new furniture from an affiliated furniture store using the link provided.

[0052] Specific examples

[0053] Step 1: Enter furniture information

[0054] Users take a photo of the sofa in their living room with their smartphone and upload it to the app.

[0055] The user enters the sofa dimensions (e.g., length 200 cm, width 90 cm, height 80 cm) on the upload screen.

[0056] Step 2: Submit your furniture information

[0057] The device sends the sofa information entered by the user to the server in JSON format.

[0058] Step 3: Obtain property information

[0059] The user selects the ID of the property they want to purchase. The ID of the selected property is sent to the server, which then retrieves detailed information about the property from the database.

[0060] Property information includes living room dimensions (e.g. 500cm x 600cm), layout diagrams, and interior photos.

[0061] Step 4: Run the AI ​​simulation

[0062] The server combines the acquired sofa information with the property's living room information and uses generative AI to simulate the optimal furniture arrangement.

[0063] The simulation results in an image of a room with a sofa placed in the center of the living room.

[0064] Step 5: Send and view the simulated image

[0065] The server converts the generated image into JPEG format and transmits it to the terminal.

[0066] The device displays the received image to the user within the app, and the user can review the image to get a concrete idea of ​​what the living room will look like after moving in.

[0067] Step 6: Fine-tune your furniture placement

[0068] The user presses the "Adjust" button to fine-tune the position of the sofa based on the displayed image.

[0069] The user uses the drag and drop function to move the sofa to the left.

[0070] The terminal transmits this adjustment information to the server, and the server generates a simulation image again and transmits it to the terminal.

[0071] The user checks the final image after adjustments and presses the "confirm" button if satisfied.

[0072] Step 7: Provide a link to purchase the furniture

[0073] Once the user hits the "confirm" button, they will be provided with a link to purchase their new furniture based on the final image displayed.

[0074] Users can click on this link to purchase their new furniture at the affiliated furniture store's site.

[0075] This allows users to save the trouble of viewing the property and easily get a concrete image of their new home, taking into account the placement of their current furniture.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] The user inputs furniture information. The user uses their device to take a photo of the furniture they own or select an existing photo. Next, the user enters the furniture's dimensions (length, width, and height) into the input form.

[0079] Step 2:

[0080] The device sends the furniture information to the server. The device converts the furniture information entered by the user into a specified data format (e.g., JSON format) and sends it to the server as an HTTP POST request.

[0081] Step 3:

[0082] The server receives the furniture information. The server receives the furniture information sent from the terminal and stores it in a database.

[0083] Step 4:

[0084] The user selects a property ID. The user selects the ID of the property they want on the property search site and sends that ID to the server.

[0085] Step 5:

[0086] The server retrieves property information. The server queries the real estate database based on the property ID sent by the user and retrieves detailed information (dimensions, layout, interior photos) of the corresponding property.

[0087] Step 6:

[0088] The server runs the simulation. The server integrates the received furniture information with the acquired property information and runs the simulation using a generation AI. The generation AI places the furniture in the optimal position and generates an image of what the room will look like after the move.

[0089] Step 7:

[0090] The server sends the generated image to the terminal. The server converts the generated simulation image into an appropriate format (e.g., JPEG) and sends it to the terminal.

[0091] Step 8:

[0092] The terminal displays the simulated image. The terminal displays the image received from the server on the interface of the website or application. The user can check this image and get a concrete vision of what the room will look like after moving in.

[0093] Step 9:

[0094] The user fine-tunes the furniture placement. The user manually adjusts the furniture position using the drag-and-drop function based on the displayed simulation image. After adjustments are complete, the user presses the "Save" button.

[0095] Step 10:

[0096] The terminal transmits the fine-tuning information to the server. The terminal converts the furniture arrangement information fine-tuned by the user into a data format and transmits it to the server.

[0097] Step 11:

[0098] The server performs a re-simulation. The server uses the generation AI to perform a re-simulation based on the fine-tuning information received from the user, and generates the final image.

[0099] Step 12:

[0100] The server sends the final image to the terminal. The server sends the final generated simulation image to the terminal. The terminal displays the image again for the user to confirm.

[0101] Step 13:

[0102] The user checks the final image and confirms it. The user checks the final image and, if satisfied, presses the "confirm" button to decide to move.

[0103] Step 14:

[0104] The device will display a link to purchase the furniture. When the user presses the "Confirm" button, a link to purchase the furniture from the furniture store will be displayed on the device, allowing the user to purchase new furniture.

[0105] Example 1

[0106] 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."

[0107] To easily get a concrete image of the room after moving, it is necessary to view the room on site, which takes time and effort. In addition, it is difficult to perform a simulation that takes into account the layout of the current furniture, making it difficult to accurately grasp the furniture layout in the new property. For this reason, many users are concerned about the furniture layout in their new home.

[0108] 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.

[0109] In this invention, the server includes means for importing furniture information entered by the user into the terminal, means for converting the furniture information into a data format specified by the user and transmitting it to the server, means for acquiring detailed information about the property selected by the user from a database, means for integrating the acquired furniture information and property information and generating a simulation using a generative AI model, and means for converting the generated simulation image into an image format, transmitting it to the terminal, and displaying it to the user. This allows the user to easily grasp a specific image of the room after moving in and simulate the optimal arrangement of the furniture currently owned.

[0110] "Furniture information" is information including photos and dimensions (length, width, height) of furniture owned by the user.

[0111] A "terminal" is a device that a user uses to input furniture information and check simulation images, and includes smartphones, PCs, etc.

[0112] The "server" is a central processing unit that receives furniture and property information sent by users and runs simulations using a generative AI model.

[0113] A "generative AI model" is an artificial intelligence model that simulates optimal furniture arrangement based on user input data and generates an image of a room.

[0114] A "simulation image" is an image generated by a generative AI model that shows a concrete image of what the room will look like after the user's furniture is placed in the new property.

[0115] A "database" is a collection of information that the server accesses to obtain property information, and stores information such as property dimensions, layout, and interior photos.

[0116] The "drag-and-drop function" is an interface function that allows the user to manually move the position of furniture on the simulation image.

[0117] A "link" is a reference to a web page where a user can purchase new furniture based on the generated final simulation image.

[0118] The present invention provides a system that generates a concrete image of a room after a user moves in, using information about furniture owned by the user and information about a newly selected property.

[0119] First, users input furniture information using their smartphone or PC. Specifically, they take or select a photo of the furniture they own and enter its dimensions (length, width, height). This furniture information is then imported into the device.

[0120] The device converts the furniture information (photos and dimensions) entered by the user into a specified data format, such as JSON, and sends it to the server. Through this transmission, the server receives the user's furniture information.

[0121] The server then receives the ID of the property selected by the user, and based on that ID, retrieves the property's details (dimensions, layout, interior photos, etc.) from the database, which are then merged with the furniture information.

[0122] The server inputs the acquired furniture and property information into a generative AI model to simulate the optimal furniture arrangement. This generative AI model operates based on instructions such as a prompt, "Please simulate the optimal room layout based on the following furniture and property information." Examples of specific prompts include, "Furniture information: sofa photo and dimensions (length 200cm, width 90cm, height 80cm)," "Property information: living room dimensions (500cm x 600cm), layout diagram, interior photo."

[0123] The generated simulation image is converted into an image format (e.g., JPEG format) on the server. This image is then sent to the terminal and displayed to the user. By checking this image, the user can get a concrete idea of ​​what the room will look like after moving in.

[0124] In addition, the user can manually adjust the position of the furniture on the displayed simulation image using the drag-and-drop function. After the user makes the adjustment, the device sends the adjustment information back to the server, and the server generates a new simulation image and sends it to the device. This allows the user to adjust the furniture arrangement until they are satisfied.

[0125] Finally, once the user is satisfied with the simulation image, a link to purchase new furniture based on the image is provided. The user can click on this link to purchase the desired furniture on the affiliated furniture store's website.

[0126] In this way, the present invention allows the user to save the trouble of viewing the property and easily get a concrete image of their new home, taking into consideration the placement of their current furniture.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1:

[0129] The user inputs furniture information. Using a smartphone or PC, the user takes or selects a photo of the furniture they own and enters the furniture's dimensions (length, width, and height). This input data consists of a photo of the furniture and its dimensions, and the entered information is imported into the device. Specifically, the user takes a photo of a sofa using the app's photo function and enters, "The sofa is 200 cm long, 90 cm wide, and 80 cm high."

[0130] Step 2:

[0131] The device sends the furniture information to the server. The device converts the furniture information (photo and dimensions) entered by the user into a specified data format (e.g., JSON format). The input for this data conversion is the furniture information entered by the user, and the output is furniture information in JSON format. The converted data is then sent to the server. Specifically, the device sends the JSON-formatted data { "Furniture Name": "Sofa", "Length": 200, "Width": 90, "Height": 80, "Image URL": "https: / / example.com / sofa.jpg"} to the server.

[0132] Step 3:

[0133] The server retrieves property information. The server receives the ID of the property selected by the user. The input is the property ID, and the server retrieves detailed information about the property from the database based on that ID. The input for retrieving information from the database is the property ID, and the output is detailed property information (dimensions, layout, interior photos, etc.). Specifically, the server receives property ID "A123" and retrieves information from the database such as "The living room dimensions are 500cm x 600cm, and a layout diagram and interior photos are included."

[0134] Step 4:

[0135] The server uses the generative AI to run a simulation. The server inputs the acquired furniture information and property information into the generative AI model and simulates the optimal furniture layout. The input for this simulation is furniture information and property information, and the output is a simulation image. Specifically, the server sends the generative AI model a prompt saying, "Please simulate the optimal room layout based on the furniture information and property information below," and the generative AI model generates an image of a room with a sofa placed in the center of the living room.

[0136] Step 5:

[0137] The server sends the generated image to the device and displays it to the user. The server converts the generated simulation image to JPEG format. The input for this image conversion is the simulation image, and the output is a JPEG image. This image is then sent to the device, and the device displays the received image to the user. Specifically, the server sends a JPEG image to the device, and the user views this image within the app.

[0138] Step 6:

[0139] The user fine-tunes the furniture arrangement. The user manually fine-tunes the furniture arrangement on the simulation image using the drag-and-drop function. The input of this operation is the user's adjustment instructions, and the output is the new furniture arrangement information. Specifically, the user presses the "Adjust" button and drags the sofa to the left to move it.

[0140] Step 7:

[0141] The terminal sends the adjustment information to the server and performs a re-simulation. The terminal sends the furniture layout information manually adjusted by the user to the server. The input of this transmission is the new furniture layout information, and the output is data transmission to the server. The server runs the simulation again using the generative AI model to generate a new simulation image. The input of this re-simulation is the adjusted furniture layout information, and the output is a new simulation image. Specifically, the server runs the re-simulation and sends the new image to the terminal.

[0142] Step 8:

[0143] The user confirms the final simulation image and provides a purchase link. When the user presses the "Confirm" button, a link to purchase new furniture based on the generated final simulation image is provided. The input of this confirmation operation is the user's "Confirm" instruction, and the output is the purchase link. Specifically, when the user presses the "Confirm" button, the link "https: / / example-furniture-store.com / new-sofa" is displayed within the app.

[0144] (Application example 1)

[0145] 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."

[0146] When moving, it is difficult to visualize how one's furniture will be arranged in a new property. In particular, users need to confirm whether the size and design of the furniture will fit into the new room, but physically viewing the property is time-consuming and costly. Furthermore, there is a demand for an efficient and easy way to consider purchasing and arranging new furniture. To solve this problem, a system is needed that allows users to easily visualize their new room and simulate appropriate furniture arrangements.

[0147] 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.

[0148] In this invention, the server includes means for taking in furniture information using a generative AI model and combining it with property data to automatically generate an image of the living space after moving in, means for transmitting the furniture information entered by the user from the terminal to the server, means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation, means for transmitting the generated simulation image to the terminal and displaying it to the user, and means for providing the user with a link to select and purchase new furniture in a virtual store. This allows the user to specifically imagine how their furniture will be arranged in their new property, making it easier to purchase new furniture and determine the optimal arrangement.

[0149] A "generative AI model" is an artificial intelligence technology that generates new content based on data such as images and text.

[0150] "Furniture Information" refers to detailed information such as photos, dimensions, and design of furniture.

[0151] "Property data" refers to detailed information such as the property's layout, dimensions, and interior photos.

[0152] "Simulation" is the process of combining the furniture selected by the user with property data to recreate a concrete image of the room after moving in on a computer.

[0153] "Terminal" refers to an electronic device used by a user, such as a smartphone or PC.

[0154] A "server" refers to a computer system that receives and processes data sent from a user's terminal.

[0155] A "virtual store" refers to a virtual shopping site or application operated on the Internet.

[0156] "Link" means an internet reference that provides direct access to a particular web page or App feature.

[0157] "Drag and drop" refers to the operation of selecting and moving an item with a mouse or the like in a computer user interface.

[0158] This invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and information about the property selected by the user. The operation of this system and a specific example are described below.

[0159] System Overview

[0160] Hardware

[0161] User devices include smartphones, personal computers, and the like.

[0162] A server is a computer system used for data processing, and it is desirable for servers to be operated in a cloud environment.

[0163] software

[0164] The front end is an application that uses React Native and provides an interface for users to input furniture information and check the simulation results.

[0165] The backend uses Node.js (Express framework) to process data and provide various APIs.

[0166] MongoDB is used as the database to store and manage furniture and property information.

[0167] TensorFlow.js is used for image processing and analyzes uploaded furniture photos.

[0168] The generative AI model uses OpenAI's DALL-E model to generate furniture placement simulations.

[0169] Operation explanation

[0170] 1. The user enters furniture information

[0171] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[0172] 2. The device sends the furniture information to the server

[0173] The terminal converts the furniture information (photos and dimensions) entered by the user into JSON format and sends it to the server.

[0174] 3. The server retrieves the property information

[0175] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos, etc.) of the property corresponding to that ID from the database.

[0176] 4. Running a simulation using generative AI

[0177] The server integrates the acquired furniture information with the property information and uses a generative AI model to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[0178] Example prompt sentence:

[0179] Generate an interior design layout for a room with dimensions 500cm x 600cm. Place a sofa of dimensions 200cm x 90cm x 80cm in the center of the room. Generate a realistic image of the room with this configuration.

[0180] 5. Sending and displaying the generated image

[0181] The server converts the generated simulation image into JPEG format and sends it to the terminal.

[0182] The terminal displays this image to the user, who can then check it to get a concrete idea of ​​what the room will look like after moving in.

[0183] 6. Fine-tuning furniture arrangement by users

[0184] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[0185] 7. Providing links to purchase furniture

[0186] If the user decides that they need new furniture based on the final image generated, they can access a virtual store via a link provided and purchase the new furniture.

[0187] This allows users to save the trouble of viewing the property, easily get a concrete image of their new home while taking into consideration the placement of their current furniture, and efficiently purchase the new furniture they need.

[0188] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0189] Step 1:

[0190] The user inputs the furniture information.

[0191] Using a smartphone or PC, a user takes or selects a photo of the furniture they own and inputs the furniture's dimensions (length, width, and height). This input information is then imported into the device. The input data obtained here consists of the photo image and dimensional information.

[0192] Step 2:

[0193] The terminal transmits the furniture information to the server.

[0194] The device converts the furniture information (photos and dimensions) entered by the user into JSON format. This JSON format data is sent to the server. The input data is the furniture information entered by the user, and the output data is furniture information in JSON format.

[0195] Step 3:

[0196] The server retrieves the property information.

[0197] The server receives the ID of the property selected by the user. Based on this ID, the server retrieves the property's details (dimensions, layout, interior photos, etc.) from the database. The input data is the property ID, and the output data is the property details.

[0198] Step 4:

[0199] The server runs the simulation using the generated AI.

[0200] The server integrates the acquired furniture information and property information and runs a furniture layout simulation using a generative AI model (OpenAI's DALL-E model). Based on this simulation, an image of the room after moving in is generated in image format. The input data is furniture information and property information, and the output data is an image of the simulation results.

[0201] An example of the prompt that might be generated is:

[0202] Generate an interior design layout for a room with dimensions 500cm x 600cm. Place a sofa of dimensions 200cm x 90cm x 80cm in the center of the room. Generate a realistic image of the room with this configuration.

[0203] Step 5:

[0204] The generated image is sent to the terminal and displayed.

[0205] The server converts the generated simulation image into JPEG format and sends it to the terminal. The terminal receives this image and displays it to the user. The input data is the image of the simulation result, and the output data is the JPEG format image displayed on the user terminal.

[0206] Step 6:

[0207] The user fine-tunes the furniture arrangement.

[0208] Based on the displayed simulation image, the user can manually fine-tune the furniture arrangement using the drag-and-drop function. When the user inputs the adjusted arrangement information, it is sent from the terminal to the server. The server then runs the simulation again, generates a final image of the room, and sends it to the terminal. The input data is the adjusted arrangement information, and the output data is a simulation image of the final arrangement.

[0209] Step 7:

[0210] Provide a link for users to purchase new furniture in a virtual store.

[0211] If the user decides that they need new furniture based on the generated final image, they can access the virtual store via the displayed link and purchase the new furniture. The input data is the final simulation image, and the output data is a link to the virtual store.

[0212] 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.

[0213] The present invention is a system that generates a concrete image of the room after moving based on information about the furniture the user owns and the property they select, and also combines it with an emotion engine that recognizes the user's emotions. The operation of this system and specific examples are described below.

[0214] System Overview

[0215] 1. The user enters furniture information

[0216] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[0217] 2. The device sends the furniture information to the server

[0218] The terminal converts the furniture information (photographs and dimensions) entered by the user into a specified data format and sends it to the server.

[0219] 3. The server retrieves the property information

[0220] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos) of the property corresponding to that ID from the database.

[0221] 4. Running a simulation using generative AI

[0222] The server integrates the acquired furniture information with the property information and uses generative AI to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[0223] 5. User Emotion Recognition by Emotion Engine

[0224] The server uses an emotion engine to recognize the user's emotions by analyzing facial expressions and tone of voice while the user is entering furniture and property information.

[0225] 6. Emotion-based simulation adjustment

[0226] Based on the analysis results of the emotion engine, the server proposes optimal furniture layouts and interior designs that will help users relax. For example, if a user is feeling stressed, the server generates furniture layouts that will reduce stress.

[0227] 7. Sending and displaying the generated image

[0228] The server transmits the simulated image adjusted by the emotion engine to the terminal, which displays the image to the user.

[0229] 8. User-adjusted furniture placement

[0230] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[0231] 9. Providing links to purchase furniture

[0232] If the user decides that they need new furniture based on the final image generated, they can purchase the new furniture from an affiliated furniture store using the link provided.

[0233] Specific examples

[0234] Step 1: Enter furniture information

[0235] Users take a photo of the sofa in their living room with their smartphone and upload it to the app.

[0236] The user enters the sofa dimensions (e.g., length 200 cm, width 90 cm, height 80 cm) on the upload screen.

[0237] Step 2: Submit your furniture information

[0238] The device sends the sofa information entered by the user to the server in JSON format.

[0239] Step 3: Obtain property information

[0240] The user selects the ID of the property they want, and the selected property ID is sent to the server, which retrieves detailed information about the property from the database.

[0241] Property information includes living room dimensions (e.g. 500cm x 600cm), layout diagrams, and interior photos.

[0242] Step 4: Run the AI ​​simulation

[0243] The server combines the acquired sofa information with the property's living room information and uses generative AI to simulate the optimal furniture arrangement.

[0244] The simulation results in an image of a room with a sofa placed in the center of the living room.

[0245] Step 5: Emotion Recognition with the Emotion Engine

[0246] While the user is entering property information, the emotion engine analyzes the user's facial expressions and tone of voice. For example, if the user is smiling, it determines that the user is relaxed.

[0247] Step 6: Adjust the simulation based on emotions

[0248] Based on the analysis results of the emotion engine, the server proposes optimal furniture arrangements that will help the user relax. For example, if the user shows signs of stress, the server will suggest appropriate lighting arrangements and furniture layouts to reduce stress.

[0249] Step 7: Send and view the simulated image

[0250] The server transmits the generated simulation image to the terminal, which displays the image to the user, allowing the user to get a concrete image of what the living room will look like after moving in.

[0251] Step 8: Fine-tune your furniture placement

[0252] Users can manually fine-tune the furniture placement by pressing the "Adjust" button, using the drag-and-drop function to rearrange the furniture, for example, by moving the sofa from the center to the left side.

[0253] The terminal transmits the user's fine-tuning information to the server, and the server runs the simulation again.

[0254] The final adjusted image is sent to the terminal and displayed to the user.

[0255] Step 9: Provide a link to purchase the furniture

[0256] If the user decides that they need new furniture after reviewing the final image, they can click on the link provided, which will take them to the affiliated furniture store's website to purchase the new furniture.

[0257] This system eliminates the need for viewings and allows users to easily visualize their new home while taking into account the placement of their current furniture. Furthermore, by combining it with an emotion engine, it can suggest optimal layouts based on the user's emotions, resulting in a more satisfying move.

[0258] The processing flow will be explained below.

[0259] Step 1:

[0260] The user inputs furniture information. The user uses their device to take a photo of the furniture they own or select an existing photo. Next, the user enters the furniture's dimensions (length, width, height) into the input form. This saves the furniture information to the device.

[0261] Step 2:

[0262] The device sends the furniture information to the server. The device converts the furniture information entered by the user into a specified data format (e.g., JSON format) and sends it to the server as an HTTP POST request.

[0263] Step 3:

[0264] The server receives the furniture information. The server receives the furniture information sent from the terminal and stores it in a database.

[0265] Step 4:

[0266] The user selects a property ID. The user selects the ID of the property they want on the property search site and sends that ID to the server.

[0267] Step 5:

[0268] The server retrieves property information. The server queries the real estate database based on the property ID sent by the user and retrieves detailed information (dimensions, layout, interior photos) of the corresponding property.

[0269] Step 6:

[0270] The server initializes the emotion engine and prepares to analyze the user's emotions. The emotion engine initializes the module for analyzing the user's facial expressions and tone of voice in real time.

[0271] Step 7:

[0272] The device transmits user data to the emotion engine. While the user is entering property information, the device uses a camera and microphone to capture the user's facial expressions and tone of voice, and transmits this data to the emotion engine.

[0273] Step 8:

[0274] The emotion engine recognizes the user's emotions. The emotion engine analyzes the received data and determines the user's current emotional state (e.g., relaxed, stressed, excited).

[0275] Step 9:

[0276] The server runs the simulation. The server integrates the received furniture information with the acquired property information and uses generative AI to run a furniture layout simulation. Based on the results, it generates an image of the room after moving in.

[0277] Step 10:

[0278] The server adjusts the simulation based on emotions. Based on the analysis results of the emotion engine, the server proposes optimal furniture layout and interior design that matches the user's emotions. For example, if the user is feeling stressed, it generates furniture layout that will reduce stress.

[0279] Step 11:

[0280] The server sends the generated simulation image to the terminal. The server converts the simulation image adjusted by the emotion engine into an appropriate format (e.g., JPEG format) and sends it to the terminal.

[0281] Step 12:

[0282] The terminal displays the simulation image. The terminal displays the simulation image received from the server on the device screen. The user can check this image and get a concrete vision of what the room will look like after moving in.

[0283] Step 13:

[0284] The user fine-tunes the furniture placement. Based on the displayed simulation image, the user manually adjusts the furniture position using the drag-and-drop function. After adjustments are made, the user presses the "Save" button to save the changes to the device.

[0285] Step 14:

[0286] The terminal transmits the fine-tuning information to the server. The terminal converts the furniture arrangement information fine-tuned by the user into a data format and transmits it to the server.

[0287] Step 15:

[0288] The server performs a re-simulation. The server uses the generation AI to perform a re-simulation based on the fine-tuning information received from the user, and generates the final image.

[0289] Step 16:

[0290] The server sends the final image to the terminal. The server sends the final generated simulation image to the terminal. The terminal displays the image again for the user to confirm.

[0291] Step 17:

[0292] The user checks the final image and confirms it. The user checks the final image and, if satisfied, presses the "confirm" button to decide to move.

[0293] Step 18:

[0294] The device will display a link to purchase the furniture. When the user presses the "Confirm" button, a link to purchase the furniture from the furniture store will be displayed on the device, allowing the user to purchase new furniture.

[0295] Example 2

[0296] 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."

[0297] Conventional moving simulation systems have difficulty accurately grasping the specific layout of a new property when users arrange their own furniture. Furthermore, because the simulation is performed without taking into account the user's feelings and preferences, the system often fails to propose an optimal layout. Furthermore, the system lacks the functionality to re-simulate the layout based on the user's manual adjustments or to provide links to purchase new furniture.

[0298] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0299] In this invention, the server includes: means for incorporating furniture information using a generative AI model and combining it with property data to automatically generate an image of the room after the user moves in; means for transmitting furniture information entered by the user from the terminal to the server; means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation; and means for recognizing the user's emotions using an emotion engine and adjusting the simulation based on the recognized emotional state. This allows the user to easily grasp a specific image of the room after moving in based on the furniture currently owned, and proposes an optimal layout based on the user's emotions and preferences. It can also provide a re-simulation that reflects the user's manual adjustments and a link to purchase new furniture.

[0300] A "generative AI model" is a type of artificial intelligence that generates new images and text based on user input.

[0301] An "emotion engine" is a system that analyzes data such as a user's facial expressions and tone of voice to recognize their emotional state.

[0302] "Furniture information" refers to all information entered by the user, including photos of furniture, dimensions, and other attribute data.

[0303] "Property Information" refers to detailed data about a property, such as dimensions, layout, and interior images of the property.

[0304] "Simulation image" refers to a visual image of the room after moving in, generated using a generative AI model based on furniture information and property information.

[0305] "Terminal" refers to a device such as a smartphone or PC that a user uses to input information.

[0306] "Server" refers to a computer system for processing data received from users and generating and transmitting simulation images.

[0307] "Means" refers to a method or device for achieving a specific function or purpose.

[0308] "Links" refers to connections to websites and online stores where users can purchase new furniture.

[0309] This invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and information about the property selected, and also combines it with an emotion engine that recognizes the user's emotions.The system aims to propose the optimal room layout and interior design for the user by utilizing a generative AI model and emotion engine.

[0310] First, users launch the application on their smartphone or PC and enter information about the furniture they own. Specifically, they take or select a photo of the furniture and enter its dimensions (length, width, and height). This information is then saved on the device.

[0311] Next, the device converts the furniture information entered by the user into JSON format and sends it to the server as an HTTP POST request. The server then analyzes the received furniture information and requests the property ID selected by the user. When the user enters the property ID and sends it from the device to the server, the server retrieves property information from the database based on the specified property ID. The property information includes the property's dimensions, layout, and interior photos.

[0312] The server combines the acquired furniture information with the property information to generate a "prompt sentence." This prompt sentence is input into a generative AI model (e.g., DALL-E) to generate a simulation image. An example of a prompt sentence is, "The dimensions of the living room are 500cm x 600cm, and a sofa (200cm long, 90cm wide, and 80cm high) is placed in the center."

[0313] The generated simulation image is sent to the terminal by the server and displayed to the user. At this time, the server uses an emotion engine (for example, Microsoft Azure Emotion API) to analyze the user's facial expressions and tone of voice to recognize the user's emotional state. Based on information such as whether the user is relaxed or stressed, the server adjusts the simulation image.

[0314] The user can check the generated image and manually adjust the furniture placement using the drag-and-drop function. The adjusted placement information is sent from the device to the server again, and the server performs a simulation again to generate and send a new image.

[0315] Finally, if the user reviews the final simulation image and decides they need new furniture, they can purchase it through a link displayed on their device. This link is provided by the server and allows the user to access the online furniture store's website and proceed with the purchase.

[0316] This system allows users to easily visualize their new home based on the furniture they currently own. It also suggests optimal layouts based on the user's feelings and preferences, resulting in a more satisfying move.

[0317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0318] Step 1:

[0319] The user enters furniture information

[0320] The user launches an application installed on a smartphone or PC.

[0321] The user accesses the "Enter Furniture Information" screen.

[0322] Users can take a photo of the furniture or select an existing photo.

[0323] The user inputs the dimensions of the furniture (e.g., length 200 cm, width 90 cm, height 80 cm).

[0324] When the user presses the "Send" button, the entered furniture information is saved on the terminal.

[0325] Input: Furniture photos, dimensions

[0326] Output: Furniture information saved on the device

[0327] Step 2:

[0328] The device sends furniture information to the server.

[0329] The terminal acquires the furniture information input by the user.

[0330] The device converts furniture information (photos and dimensions) into JSON format.

[0331] The device sends JSON format data to the server as an HTTP POST request.

[0332] Input: Furniture information (photos, dimensions)

[0333] Output: Furniture information sent to the server in JSON format

[0334] Specific behavior:

[0335] json

[0336] {

[0337] "furniture": "sofa",

[0338] "dimensions": {

[0339] "length": 200,

[0340] "width": 90,

[0341] "height": 80

[0342] },

[0343] "photo": "base64encodedimage"

[0344] }

[0345] Step 3:

[0346] The server retrieves property information

[0347] The server receives the HTTP request and analyzes the furniture information.

[0348] The server requests the property ID selected by the user.

[0349] The user enters the property ID and sends it from the terminal to the server.

[0350] The server retrieves property information from the database based on the specified property ID.

[0351] Input: Property ID

[0352] Output: Acquired property information (dimensions, layout, interior photos)

[0353] Specific behavior:

[0354] json

[0355] {

[0356] "propertyID": "123456",

[0357] "details": {

[0358] "dimensions": {

[0359] "living_room": {

[0360] "length": 500,

[0361] "width": 600

[0362] }

[0363] },

[0364] "layout_image": "base64encodedlayoutimage",

[0365] "interior_photos": ["base64encodedphoto1", "base64encodedphoto2"]

[0366] }

[0367] }

[0368] Step 4:

[0369] The server runs the simulation using the generated AI.

[0370] The server integrates furniture information and property information.

[0371] The server inputs a prompt sentence into the generative AI model.

[0372] The server generates a simulation image using a generative AI model (e.g., DALL-E).

[0373] Input: Furniture information, property information

[0374] Output: Generated simulation image

[0375] Specific action prompt:

[0376] text

[0377] The living room measures 500cm x 600cm with a sofa (200cm long, 90cm wide, 80cm high) placed in the center.

[0378] Step 5:

[0379] The server performs emotion recognition using an emotion engine.

[0380] The server records the user's facial expressions and tone of voice while they are typing.

[0381] The server uses an emotion engine to analyze the user's emotional state.

[0382] Input: User's facial expression, tone of voice

[0383] Output: Recognized emotional state of the user

[0384] Specific behavior:

[0385] json

[0386] {

[0387] "emotion_state": "relaxed",

[0388] "confidence_score": 0.85

[0389] }

[0390] Step 6:

[0391] The server adjusts the simulation based on emotions.

[0392] The server sends new prompt sentences to the generative AI model if necessary based on the analysis results of the emotion engine.

[0393] The server again uses the generative AI model to generate simulated images that match the user's emotions.

[0394] Input: User's emotional state, initial simulation image

[0395] Output: Adjusted simulation image

[0396] Specific action prompt:

[0397] text

[0398] "Place plants around the sofa and use soft lighting to help users relax."

[0399] Step 7:

[0400] The server sends the generated image to the terminal and displays it.

[0401] The server sends the final simulation image to the terminal.

[0402] The terminal displays the received image to the user.

[0403] Input: Final simulation image

[0404] Output: Simulation image displayed on the terminal

[0405] Specific behavior:

[0406] json

[0407] {

[0408] "simulation_image_url": "https: / / example.com / generated_image.png"

[0409] }

[0410] Step 8:

[0411] Users fine-tune furniture arrangement

[0412] The user checks the generated image on the terminal.

[0413] Users can rearrange the furniture using the drag and drop function.

[0414] The terminal sends the new configuration information to the server.

[0415] The server runs the simulation again, generating and sending new images.

[0416] Input: User fine-tuning information

[0417] Output: Resimulated image

[0418] Specific behavior:

[0419] json

[0420] {

[0421] "new_furniture_position": {

[0422] "sofa": {

[0423] "x": 250,

[0424] "y": 150

[0425] }

[0426] }

[0427] }

[0428] Step 9:

[0429] The server provides a link to purchase the furniture.

[0430] The user checks the final simulation image.

[0431] Click on the new furniture link as needed to proceed with the purchase process.

[0432] Input: Final simulation image

[0433] Output: Furniture purchase link

[0434] Specific behavior:

[0435] json

[0436] {

[0437] "furniture_purchase_links": [

[0438] "https: / / furniturestore.com / product / sofa",

[0439] "https: / / furniturestore.com / product / table"

[0440] ]

[0441] }

[0442] (Application example 2)

[0443] 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."

[0444] For users considering moving, visualizing the exact layout of furniture in their new home can be a very troubling problem. It is also difficult to propose optimal interior design that takes into account the user's emotions and stress levels in addition to the furniture layout. Furthermore, the process for users to purchase the perfect furniture for their new home is complicated, resulting in an inconsistent overall moving experience.

[0445] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0446] In this invention, the server includes: means for incorporating furniture information using a generative AI model and combining it with property data to automatically generate an image of the room after moving in; means for transmitting furniture information entered by the user from the terminal to the server; means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation; and means for the server to use an emotion engine that recognizes the user's emotions by analyzing facial expressions and tone of voice to adjust the optimal furniture arrangement and interior design based on the emotions, transmit the generated simulation image to the terminal, and display it to the user. This allows the user to easily imagine the specific furniture arrangement in their new home and receive optimal interior design suggestions that take the user's emotions into consideration. It also makes the purchase of new furniture smoother, improving the overall moving experience.

[0447] A "generative AI model" is an artificial intelligence technology that generates a concrete image of the room the user will move into based on information about the furniture they own and the property they select.

[0448] "Furniture Information" means data about photos, dimensions, and other physical characteristics of furniture owned by a user.

[0449] "Property data" refers to detailed information about the property selected by the user, such as dimensions, layout, and interior photos.

[0450] An "emotion engine" is a technology that analyzes a user's facial expressions and tone of voice to recognize their emotions, and adjusts the generated simulation image based on that.

[0451] A "simulation image" is an image created using a generative AI model that visually shows the specific layout and arrangement of the room after moving in.

[0452] A "terminal" is a digital device such as a smartphone or computer that a user uses to input furniture information and display simulation images.

[0453] A "server" is a computer system that receives data sent by users, executes generative AI models and emotion engines, and generates and transmits simulation images.

[0454] "Furniture arrangement" refers to a layout that shows how furniture is arranged in a user's room.

[0455] The present invention is a system that generates a concrete image of the room after moving based on information about the furniture the user owns and the property they select, and also combines it with an emotion engine that recognizes the user's emotions. The operation of this system and specific examples are described below.

[0456] System Overview

[0457] The server uses a generative AI model to capture furniture information and combine it with property data to generate an image of the room. The furniture information entered by the user is sent from the device to the server. The server obtains detailed information about the property selected by the user and combines it with the furniture information to generate a simulation. The server also uses an emotion engine to recognize the user's emotions and suggests optimal furniture layout based on their emotions. This generated simulation image is sent to the device and displayed to the user.

[0458] Hardware and software used

[0459] Hardware:

[0460] Smartphones and PCs: Devices that allow users to input furniture information and display simulation images.

[0461] Server: Receives data, runs generative AI models and emotion engines, and generates and transmits simulation images.

[0462] software:

[0463] Generative AI model (e.g. FurnitureArrangementAI): AI technology that simulates optimal furniture arrangement based on furniture and property information.

[0464] Emotion engine (e.g., EmotionEngine): Recognizes the user's emotions by analyzing facial expressions and tone of voice.

[0465] Communication library (e.g. requests): A library for sending and receiving furniture information and simulation images.

[0466] Data processing and calculation

[0467] The main tasks performed by the server are:

[0468] 1. Receives furniture information input and stores it in a database. This uses image analysis algorithms to extract furniture dimensions and shapes and stores them along with text data.

[0469] 2. Property data acquisition: In this step, the server uses a RESTful API to obtain detailed property information such as dimensions, layout diagrams, and interior photos.

[0470] 3. Using a generative AI model, furniture information and property information are integrated to simulate optimal furniture placement.

[0471] 4. Analyze the user's emotions using an emotion engine. Specifically, analyze facial expressions and tone of voice in real time while the user is entering furniture and property information.

[0472] 5. Based on the results of the emotion engine, the generated simulation image is adjusted. If the user is feeling stressed, a placement suggestion to reduce stress is made.

[0473] 6. The final simulation image is sent to the terminal and displayed to the user.

[0474] Specific examples

[0475] A user uses their smartphone to take a photo of the sofa in their living room and upload it to the app. They also enter the sofa's dimensions (e.g., length 200 cm, width 90 cm, height 80 cm). The device sends this information to the server in JSON format. Based on the property ID selected by the user, the server retrieves detailed property information from the database. The generative AI model uses this information to simulate the optimal furniture arrangement for the living room. If the user is not satisfied with this simulated image, the emotion engine analyzes the user's emotions and suggests a new arrangement to, for example, reduce stress. The final image is displayed to the user, and a link to purchase new furniture is provided if necessary.

[0476] Prompt Sentence Examples

[0477] "Get the information you need for a moving simulator and use FurnitureArrangementAI and EmotionEngine to suggest room layouts that will help users relax."

[0478] In this way, users can easily visualize the specific arrangement of furniture in their new home and smoothly proceed with the entire moving process.

[0479] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0480] Step 1:

[0481] A user uses a smartphone to take a photo of the furniture in their living room and upload it to the app. They also enter the furniture's dimensions (e.g., length 200 cm, width 90 cm, height 80 cm). This is the device's input. The device converts the furniture information entered by the user into JSON format and sends it to the server.

[0482] Step 2:

[0483] The server decodes and stores the furniture information received from the device. Here, it uses an image analysis algorithm to extract the dimensions and shape of the furniture and records them in a database as text data. This is the server's data processing.

[0484] Step 3:

[0485] The user selects a property ID in the application. This is the terminal input. The terminal sends the selected property ID to the server. The server uses a RESTful API to retrieve detailed information such as the property dimensions, layout diagram, and interior photos from the database based on the received property ID. This is the server output.

[0486] Step 4:

[0487] The server inputs the acquired property information and the user's furniture information into a generative AI model (e.g., FurnitureArrangementAI). The generative AI model uses this information to simulate the optimal furniture arrangement and generate a simulation image. This is the server's data calculation.

[0488] Step 5:

[0489] The server uses an emotion engine (e.g., Emotion Engine) to analyze video of the user's facial expressions and tone of voice while they are entering furniture and property information. The emotion engine uses facial expression and voice analysis algorithms to recognize the user's emotional state and convert it into data. This is the server's data processing.

[0490] Step 6:

[0491] The server adjusts the generated simulation image based on the results of the emotion engine. Specifically, if the user is feeling stressed, it will suggest layout adjustments to reduce stress. For example, it will adjust the layout by changing the position of the lighting. This is the output of the server.

[0492] Step 7:

[0493] The server sends the final simulation image to the terminal, which then displays it to the user. This is the terminal's data output. The user can check the displayed simulation image and, if necessary, fine-tune the furniture placement using the drag-and-drop function.

[0494] Step 8:

[0495] If the user makes minor adjustments to the furniture placement, the device sends this information to the server, which then uses the generative AI model again to generate a new simulated image based on the adjusted information. This is the server's data calculation.

[0496] Step 9:

[0497] The final image is sent to the device and displayed to the user. If the user decides that they need new furniture, they click on the furniture purchase link displayed on the device. This is the user's output. The link will take them to the furniture store's website where they can purchase their new furniture.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] [Second embodiment]

[0502] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0503] 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.

[0504] 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).

[0505] 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.

[0506] 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.

[0507] 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).

[0508] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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."

[0514] The present invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and the newly selected property. The operation of this system and a specific example are described below.

[0515] System Overview

[0516] 1. The user enters furniture information

[0517] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[0518] 2. The device sends the furniture information to the server

[0519] The terminal converts the furniture information (photographs and dimensions) entered by the user into a specified data format and sends it to the server.

[0520] 3. The server retrieves the property information

[0521] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos, etc.) of the property corresponding to that ID from the database.

[0522] 4. Running a simulation using generative AI

[0523] The server integrates the acquired furniture information with the property information and uses generative AI to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[0524] 5. Sending and displaying the generated image

[0525] The server transmits the generated simulation image to the terminal, which displays the image to the user.

[0526] 6. Fine-tuning furniture arrangement by users

[0527] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[0528] 7. Providing links to purchase furniture

[0529] If the user decides that they need new furniture based on the final image generated, they can purchase the new furniture from an affiliated furniture store using the link provided.

[0530] Specific examples

[0531] Step 1: Enter furniture information

[0532] Users take a photo of the sofa in their living room with their smartphone and upload it to the app.

[0533] The user enters the sofa dimensions (e.g., length 200 cm, width 90 cm, height 80 cm) on the upload screen.

[0534] Step 2: Submit your furniture information

[0535] The device sends the sofa information entered by the user to the server in JSON format.

[0536] Step 3: Obtain property information

[0537] The user selects the ID of the property they want to purchase. The ID of the selected property is sent to the server, which then retrieves detailed information about the property from the database.

[0538] Property information includes living room dimensions (e.g. 500cm x 600cm), layout diagrams, and interior photos.

[0539] Step 4: Run the AI ​​simulation

[0540] The server combines the acquired sofa information with the property's living room information and uses generative AI to simulate the optimal furniture arrangement.

[0541] The simulation results in an image of a room with a sofa placed in the center of the living room.

[0542] Step 5: Send and view the simulated image

[0543] The server converts the generated image into JPEG format and transmits it to the terminal.

[0544] The device displays the received image to the user within the app, and the user can review the image to get a concrete idea of ​​what the living room will look like after moving in.

[0545] Step 6: Fine-tune your furniture placement

[0546] The user presses the "Adjust" button to fine-tune the position of the sofa based on the displayed image.

[0547] The user uses the drag and drop function to move the sofa to the left.

[0548] The terminal transmits this adjustment information to the server, and the server generates a simulation image again and transmits it to the terminal.

[0549] The user checks the final image after adjustments and presses the "confirm" button if satisfied.

[0550] Step 7: Provide a link to purchase the furniture

[0551] Once the user hits the "confirm" button, they will be provided with a link to purchase their new furniture based on the final image displayed.

[0552] Users can click on this link to purchase their new furniture at the affiliated furniture store's site.

[0553] This allows users to save the trouble of viewing the property and easily get a concrete image of their new home, taking into account the placement of their current furniture.

[0554] The processing flow will be explained below.

[0555] Step 1:

[0556] The user inputs furniture information. The user uses their device to take a photo of the furniture they own or select an existing photo. Next, the user enters the furniture's dimensions (length, width, and height) into the input form.

[0557] Step 2:

[0558] The device sends the furniture information to the server. The device converts the furniture information entered by the user into a specified data format (e.g., JSON format) and sends it to the server as an HTTP POST request.

[0559] Step 3:

[0560] The server receives the furniture information. The server receives the furniture information sent from the terminal and stores it in a database.

[0561] Step 4:

[0562] The user selects a property ID. The user selects the ID of the property they want on the property search site and sends that ID to the server.

[0563] Step 5:

[0564] The server retrieves property information. The server queries the real estate database based on the property ID sent by the user and retrieves detailed information (dimensions, layout, interior photos) of the corresponding property.

[0565] Step 6:

[0566] The server runs the simulation. The server integrates the received furniture information with the acquired property information and runs the simulation using a generation AI. The generation AI places the furniture in the optimal position and generates an image of what the room will look like after the move.

[0567] Step 7:

[0568] The server sends the generated image to the terminal. The server converts the generated simulation image into an appropriate format (e.g., JPEG) and sends it to the terminal.

[0569] Step 8:

[0570] The terminal displays the simulated image. The terminal displays the image received from the server on the interface of the website or application. The user can check this image and get a concrete vision of what the room will look like after moving in.

[0571] Step 9:

[0572] The user fine-tunes the furniture placement. The user manually adjusts the furniture position using the drag-and-drop function based on the displayed simulation image. After adjustments are complete, the user presses the "Save" button.

[0573] Step 10:

[0574] The terminal transmits the fine-tuning information to the server. The terminal converts the furniture arrangement information fine-tuned by the user into a data format and transmits it to the server.

[0575] Step 11:

[0576] The server performs a re-simulation. The server uses the generation AI to perform a re-simulation based on the fine-tuning information received from the user, and generates the final image.

[0577] Step 12:

[0578] The server sends the final image to the terminal. The server sends the final generated simulation image to the terminal. The terminal displays the image again for the user to confirm.

[0579] Step 13:

[0580] The user checks the final image and confirms it. The user checks the final image and, if satisfied, presses the "confirm" button to decide to move.

[0581] Step 14:

[0582] The device will display a link to purchase the furniture. When the user presses the "Confirm" button, a link to purchase the furniture from the furniture store will be displayed on the device, allowing the user to purchase new furniture.

[0583] Example 1

[0584] 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."

[0585] To easily get a concrete image of the room after moving, it is necessary to view the room on site, which takes time and effort. In addition, it is difficult to perform a simulation that takes into account the layout of the current furniture, making it difficult to accurately grasp the furniture layout in the new property. For this reason, many users are concerned about the furniture layout in their new home.

[0586] 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.

[0587] In this invention, the server includes means for importing furniture information entered by the user into the terminal, means for converting the furniture information into a data format specified by the user and transmitting it to the server, means for acquiring detailed information about the property selected by the user from a database, means for integrating the acquired furniture information and property information and generating a simulation using a generative AI model, and means for converting the generated simulation image into an image format, transmitting it to the terminal, and displaying it to the user. This allows the user to easily grasp a specific image of the room after moving in and simulate the optimal arrangement of the furniture currently owned.

[0588] "Furniture information" is information including photos and dimensions (length, width, height) of furniture owned by the user.

[0589] A "terminal" is a device that a user uses to input furniture information and check simulation images, and includes smartphones, PCs, etc.

[0590] The "server" is a central processing unit that receives furniture and property information sent by users and runs simulations using a generative AI model.

[0591] A "generative AI model" is an artificial intelligence model that simulates optimal furniture arrangement based on user input data and generates an image of a room.

[0592] A "simulation image" is an image generated by a generative AI model that shows a concrete image of what the room will look like after the user's furniture is placed in the new property.

[0593] A "database" is a collection of information that the server accesses to obtain property information, and stores information such as property dimensions, layout, and interior photos.

[0594] The "drag-and-drop function" is an interface function that allows the user to manually move the position of furniture on the simulation image.

[0595] A "link" is a reference to a web page where a user can purchase new furniture based on the generated final simulation image.

[0596] The present invention provides a system that generates a concrete image of a room after a user moves in, using information about furniture owned by the user and information about a newly selected property.

[0597] First, users input furniture information using their smartphone or PC. Specifically, they take or select a photo of the furniture they own and enter its dimensions (length, width, height). This furniture information is then imported into the device.

[0598] The device converts the furniture information (photos and dimensions) entered by the user into a specified data format, such as JSON, and sends it to the server. Through this transmission, the server receives the user's furniture information.

[0599] The server then receives the ID of the property selected by the user, and based on that ID, retrieves the property's details (dimensions, layout, interior photos, etc.) from the database, which are then merged with the furniture information.

[0600] The server inputs the acquired furniture and property information into a generative AI model to simulate the optimal furniture arrangement. This generative AI model operates based on instructions such as a prompt, "Please simulate the optimal room layout based on the following furniture and property information." Examples of specific prompts include, "Furniture information: sofa photo and dimensions (length 200cm, width 90cm, height 80cm)," "Property information: living room dimensions (500cm x 600cm), layout diagram, interior photo."

[0601] The generated simulation image is converted into an image format (e.g., JPEG format) on the server. This image is then sent to the terminal and displayed to the user. By checking this image, the user can get a concrete idea of ​​what the room will look like after moving in.

[0602] In addition, the user can manually adjust the position of the furniture on the displayed simulation image using the drag-and-drop function. After the user makes the adjustment, the device sends the adjustment information back to the server, and the server generates a new simulation image and sends it to the device. This allows the user to adjust the furniture arrangement until they are satisfied.

[0603] Finally, once the user is satisfied with the simulation image, a link to purchase new furniture based on the image is provided. The user can click on this link to purchase the desired furniture on the affiliated furniture store's website.

[0604] In this way, the present invention allows the user to save the trouble of viewing the property and easily get a concrete image of their new home, taking into consideration the placement of their current furniture.

[0605] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0606] Step 1:

[0607] The user inputs furniture information. Using a smartphone or PC, the user takes or selects a photo of the furniture they own and enters the furniture's dimensions (length, width, and height). This input data consists of a photo of the furniture and its dimensions, and the entered information is imported into the device. Specifically, the user takes a photo of a sofa using the app's photo function and enters, "The sofa is 200 cm long, 90 cm wide, and 80 cm high."

[0608] Step 2:

[0609] The device sends the furniture information to the server. The device converts the furniture information (photo and dimensions) entered by the user into a specified data format (e.g., JSON format). The input for this data conversion is the furniture information entered by the user, and the output is furniture information in JSON format. The converted data is then sent to the server. Specifically, the device sends the JSON-formatted data { "Furniture Name": "Sofa", "Length": 200, "Width": 90, "Height": 80, "Image URL": "https: / / example.com / sofa.jpg"} to the server.

[0610] Step 3:

[0611] The server retrieves property information. The server receives the ID of the property selected by the user. The input is the property ID, and the server retrieves detailed information about the property from the database based on that ID. The input for retrieving information from the database is the property ID, and the output is detailed property information (dimensions, layout, interior photos, etc.). Specifically, the server receives property ID "A123" and retrieves information from the database such as "The living room dimensions are 500cm x 600cm, and a layout diagram and interior photos are included."

[0612] Step 4:

[0613] The server uses the generative AI to run a simulation. The server inputs the acquired furniture information and property information into the generative AI model and simulates the optimal furniture layout. The input for this simulation is furniture information and property information, and the output is a simulation image. Specifically, the server sends the generative AI model a prompt saying, "Please simulate the optimal room layout based on the furniture information and property information below," and the generative AI model generates an image of a room with a sofa placed in the center of the living room.

[0614] Step 5:

[0615] The server sends the generated image to the device and displays it to the user. The server converts the generated simulation image to JPEG format. The input for this image conversion is the simulation image, and the output is a JPEG image. This image is then sent to the device, and the device displays the received image to the user. Specifically, the server sends a JPEG image to the device, and the user views this image within the app.

[0616] Step 6:

[0617] The user fine-tunes the furniture arrangement. The user manually fine-tunes the furniture arrangement on the simulation image using the drag-and-drop function. The input of this operation is the user's adjustment instructions, and the output is the new furniture arrangement information. Specifically, the user presses the "Adjust" button and drags the sofa to the left to move it.

[0618] Step 7:

[0619] The terminal sends the adjustment information to the server and performs a re-simulation. The terminal sends the furniture layout information manually adjusted by the user to the server. The input of this transmission is the new furniture layout information, and the output is data transmission to the server. The server runs the simulation again using the generative AI model to generate a new simulation image. The input of this re-simulation is the adjusted furniture layout information, and the output is a new simulation image. Specifically, the server runs the re-simulation and sends the new image to the terminal.

[0620] Step 8:

[0621] The user confirms the final simulation image and provides a purchase link. When the user presses the "Confirm" button, a link to purchase new furniture based on the generated final simulation image is provided. The input of this confirmation operation is the user's "Confirm" instruction, and the output is the purchase link. Specifically, when the user presses the "Confirm" button, the link "https: / / example-furniture-store.com / new-sofa" is displayed within the app.

[0622] (Application example 1)

[0623] 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."

[0624] When moving, it is difficult to visualize how one's furniture will be arranged in a new property. In particular, users need to confirm whether the size and design of the furniture will fit into the new room, but physically viewing the property is time-consuming and costly. Furthermore, there is a demand for an efficient and easy way to consider purchasing and arranging new furniture. To solve this problem, a system is needed that allows users to easily visualize their new room and simulate appropriate furniture arrangements.

[0625] 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.

[0626] In this invention, the server includes means for taking in furniture information using a generative AI model and combining it with property data to automatically generate an image of the living space after moving in, means for transmitting the furniture information entered by the user from the terminal to the server, means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation, means for transmitting the generated simulation image to the terminal and displaying it to the user, and means for providing the user with a link to select and purchase new furniture in a virtual store. This allows the user to specifically imagine how their furniture will be arranged in their new property, making it easier to purchase new furniture and determine the optimal arrangement.

[0627] A "generative AI model" is an artificial intelligence technology that generates new content based on data such as images and text.

[0628] "Furniture Information" refers to detailed information such as photos, dimensions, and design of furniture.

[0629] "Property data" refers to detailed information such as the property's layout, dimensions, and interior photos.

[0630] "Simulation" is the process of combining the furniture selected by the user with property data to recreate a concrete image of the room after moving in on a computer.

[0631] "Terminal" refers to an electronic device used by a user, such as a smartphone or PC.

[0632] A "server" refers to a computer system that receives and processes data sent from a user's terminal.

[0633] A "virtual store" refers to a virtual shopping site or application operated on the Internet.

[0634] "Link" means an internet reference that provides direct access to a particular web page or App feature.

[0635] "Drag and drop" refers to the operation of selecting and moving an item with a mouse or the like in a computer user interface.

[0636] This invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and information about the property selected by the user. The operation of this system and a specific example are described below.

[0637] System Overview

[0638] Hardware

[0639] User devices include smartphones, personal computers, and the like.

[0640] A server is a computer system used for data processing, and it is desirable for servers to be operated in a cloud environment.

[0641] software

[0642] The front end is an application that uses React Native and provides an interface for users to input furniture information and check the simulation results.

[0643] The backend uses Node.js (Express framework) to process data and provide various APIs.

[0644] MongoDB is used as the database to store and manage furniture and property information.

[0645] TensorFlow.js is used for image processing and analyzes uploaded furniture photos.

[0646] The generative AI model uses OpenAI's DALL-E model to generate furniture placement simulations.

[0647] Operation explanation

[0648] 1. The user enters furniture information

[0649] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[0650] 2. The device sends the furniture information to the server

[0651] The terminal converts the furniture information (photos and dimensions) entered by the user into JSON format and sends it to the server.

[0652] 3. The server retrieves the property information

[0653] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos, etc.) of the property corresponding to that ID from the database.

[0654] 4. Running a simulation using generative AI

[0655] The server integrates the acquired furniture information with the property information and uses a generative AI model to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[0656] Example prompt sentence:

[0657] Generate an interior design layout for a room with dimensions 500cm x 600cm. Place a sofa of dimensions 200cm x 90cm x 80cm in the center of the room. Generate a realistic image of the room with this configuration.

[0658] 5. Sending and displaying the generated image

[0659] The server converts the generated simulation image into JPEG format and sends it to the terminal.

[0660] The terminal displays this image to the user, who can then check it to get a concrete idea of ​​what the room will look like after moving in.

[0661] 6. Fine-tuning furniture arrangement by users

[0662] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[0663] 7. Providing links to purchase furniture

[0664] If the user decides that they need new furniture based on the final image generated, they can access a virtual store via a link provided and purchase the new furniture.

[0665] This allows users to save the trouble of viewing the property, easily get a concrete image of their new home while taking into consideration the placement of their current furniture, and efficiently purchase the new furniture they need.

[0666] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0667] Step 1:

[0668] The user inputs the furniture information.

[0669] Using a smartphone or PC, a user takes or selects a photo of the furniture they own and inputs the furniture's dimensions (length, width, and height). This input information is then imported into the device. The input data obtained here consists of the photo image and dimensional information.

[0670] Step 2:

[0671] The terminal transmits the furniture information to the server.

[0672] The device converts the furniture information (photos and dimensions) entered by the user into JSON format. This JSON format data is sent to the server. The input data is the furniture information entered by the user, and the output data is furniture information in JSON format.

[0673] Step 3:

[0674] The server retrieves the property information.

[0675] The server receives the ID of the property selected by the user. Based on this ID, the server retrieves the property's details (dimensions, layout, interior photos, etc.) from the database. The input data is the property ID, and the output data is the property details.

[0676] Step 4:

[0677] The server runs the simulation using the generated AI.

[0678] The server integrates the acquired furniture information and property information and runs a furniture layout simulation using a generative AI model (OpenAI's DALL-E model). Based on this simulation, an image of the room after moving in is generated in image format. The input data is furniture information and property information, and the output data is an image of the simulation results.

[0679] An example of the prompt that might be generated is:

[0680] Generate an interior design layout for a room with dimensions 500cm x 600cm. Place a sofa of dimensions 200cm x 90cm x 80cm in the center of the room. Generate a realistic image of the room with this configuration.

[0681] Step 5:

[0682] The generated image is sent to the terminal and displayed.

[0683] The server converts the generated simulation image into JPEG format and sends it to the terminal. The terminal receives this image and displays it to the user. The input data is the image of the simulation result, and the output data is the JPEG format image displayed on the user terminal.

[0684] Step 6:

[0685] The user fine-tunes the furniture arrangement.

[0686] Based on the displayed simulation image, the user can manually fine-tune the furniture arrangement using the drag-and-drop function. When the user inputs the adjusted arrangement information, it is sent from the terminal to the server. The server then runs the simulation again, generates a final image of the room, and sends it to the terminal. The input data is the adjusted arrangement information, and the output data is a simulation image of the final arrangement.

[0687] Step 7:

[0688] Provide a link for users to purchase new furniture in a virtual store.

[0689] If the user decides that they need new furniture based on the generated final image, they can access the virtual store via the displayed link and purchase the new furniture. The input data is the final simulation image, and the output data is a link to the virtual store.

[0690] 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.

[0691] The present invention is a system that generates a concrete image of the room after moving based on information about the furniture the user owns and the property they select, and also combines it with an emotion engine that recognizes the user's emotions. The operation of this system and specific examples are described below.

[0692] System Overview

[0693] 1. The user enters furniture information

[0694] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[0695] 2. The device sends the furniture information to the server

[0696] The terminal converts the furniture information (photographs and dimensions) entered by the user into a specified data format and sends it to the server.

[0697] 3. The server retrieves the property information

[0698] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos) of the property corresponding to that ID from the database.

[0699] 4. Running a simulation using generative AI

[0700] The server integrates the acquired furniture information with the property information and uses generative AI to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[0701] 5. User Emotion Recognition by Emotion Engine

[0702] The server uses an emotion engine to recognize the user's emotions by analyzing facial expressions and tone of voice while the user is entering furniture and property information.

[0703] 6. Emotion-based simulation adjustment

[0704] Based on the analysis results of the emotion engine, the server proposes optimal furniture layouts and interior designs that will help users relax. For example, if a user is feeling stressed, the server generates furniture layouts that will reduce stress.

[0705] 7. Sending and displaying the generated image

[0706] The server transmits the simulated image adjusted by the emotion engine to the terminal, which displays the image to the user.

[0707] 8. User-adjusted furniture placement

[0708] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[0709] 9. Providing links to purchase furniture

[0710] If the user decides that they need new furniture based on the final image generated, they can purchase the new furniture from an affiliated furniture store using the link provided.

[0711] Specific examples

[0712] Step 1: Enter furniture information

[0713] Users take a photo of the sofa in their living room with their smartphone and upload it to the app.

[0714] The user enters the sofa dimensions (e.g., length 200 cm, width 90 cm, height 80 cm) on the upload screen.

[0715] Step 2: Submit your furniture information

[0716] The device sends the sofa information entered by the user to the server in JSON format.

[0717] Step 3: Obtain property information

[0718] The user selects the ID of the property they want, and the selected property ID is sent to the server, which retrieves detailed information about the property from the database.

[0719] Property information includes living room dimensions (e.g. 500cm x 600cm), layout diagrams, and interior photos.

[0720] Step 4: Run the AI ​​simulation

[0721] The server combines the acquired sofa information with the property's living room information and uses generative AI to simulate the optimal furniture arrangement.

[0722] The simulation results in an image of a room with a sofa placed in the center of the living room.

[0723] Step 5: Emotion Recognition with the Emotion Engine

[0724] While the user is entering property information, the emotion engine analyzes the user's facial expressions and tone of voice. For example, if the user is smiling, it determines that the user is relaxed.

[0725] Step 6: Adjust the simulation based on emotions

[0726] Based on the analysis results of the emotion engine, the server proposes optimal furniture arrangements that will help the user relax. For example, if the user shows signs of stress, the server will suggest appropriate lighting arrangements and furniture layouts to reduce stress.

[0727] Step 7: Send and view the simulated image

[0728] The server transmits the generated simulation image to the terminal, which displays the image to the user, allowing the user to get a concrete image of what the living room will look like after moving in.

[0729] Step 8: Fine-tune your furniture placement

[0730] Users can manually fine-tune the furniture placement by pressing the "Adjust" button, using the drag-and-drop function to rearrange the furniture, for example, by moving the sofa from the center to the left side.

[0731] The terminal transmits the user's fine-tuning information to the server, and the server runs the simulation again.

[0732] The final adjusted image is sent to the terminal and displayed to the user.

[0733] Step 9: Provide a link to purchase the furniture

[0734] If the user decides that they need new furniture after reviewing the final image, they can click on the link provided, which will take them to the affiliated furniture store's website to purchase the new furniture.

[0735] This system eliminates the need for viewings and allows users to easily visualize their new home while taking into account the placement of their current furniture. Furthermore, by combining it with an emotion engine, it can suggest optimal layouts based on the user's emotions, resulting in a more satisfying move.

[0736] The processing flow will be explained below.

[0737] Step 1:

[0738] The user inputs furniture information. The user uses their device to take a photo of the furniture they own or select an existing photo. Next, the user enters the furniture's dimensions (length, width, height) into the input form. This saves the furniture information to the device.

[0739] Step 2:

[0740] The device sends the furniture information to the server. The device converts the furniture information entered by the user into a specified data format (e.g., JSON format) and sends it to the server as an HTTP POST request.

[0741] Step 3:

[0742] The server receives the furniture information. The server receives the furniture information sent from the terminal and stores it in a database.

[0743] Step 4:

[0744] The user selects a property ID. The user selects the ID of the property they want on the property search site and sends that ID to the server.

[0745] Step 5:

[0746] The server retrieves property information. The server queries the real estate database based on the property ID sent by the user and retrieves detailed information (dimensions, layout, interior photos) of the corresponding property.

[0747] Step 6:

[0748] The server initializes the emotion engine and prepares to analyze the user's emotions. The emotion engine initializes the module for analyzing the user's facial expressions and tone of voice in real time.

[0749] Step 7:

[0750] The device transmits user data to the emotion engine. While the user is entering property information, the device uses a camera and microphone to capture the user's facial expressions and tone of voice, and transmits this data to the emotion engine.

[0751] Step 8:

[0752] The emotion engine recognizes the user's emotions. The emotion engine analyzes the received data and determines the user's current emotional state (e.g., relaxed, stressed, excited).

[0753] Step 9:

[0754] The server runs the simulation. The server integrates the received furniture information with the acquired property information and uses generative AI to run a furniture layout simulation. Based on the results, it generates an image of the room after moving in.

[0755] Step 10:

[0756] The server adjusts the simulation based on emotions. Based on the analysis results of the emotion engine, the server proposes optimal furniture layout and interior design that matches the user's emotions. For example, if the user is feeling stressed, it generates furniture layout that will reduce stress.

[0757] Step 11:

[0758] The server sends the generated simulation image to the terminal. The server converts the simulation image adjusted by the emotion engine into an appropriate format (e.g., JPEG format) and sends it to the terminal.

[0759] Step 12:

[0760] The terminal displays the simulation image. The terminal displays the simulation image received from the server on the device screen. The user can check this image and get a concrete vision of what the room will look like after moving in.

[0761] Step 13:

[0762] The user fine-tunes the furniture placement. Based on the displayed simulation image, the user manually adjusts the furniture position using the drag-and-drop function. After adjustments are made, the user presses the "Save" button to save the changes to the device.

[0763] Step 14:

[0764] The terminal transmits the fine-tuning information to the server. The terminal converts the furniture arrangement information fine-tuned by the user into a data format and transmits it to the server.

[0765] Step 15:

[0766] The server performs a re-simulation. The server uses the generation AI to perform a re-simulation based on the fine-tuning information received from the user, and generates the final image.

[0767] Step 16:

[0768] The server sends the final image to the terminal. The server sends the final generated simulation image to the terminal. The terminal displays the image again for the user to confirm.

[0769] Step 17:

[0770] The user checks the final image and confirms it. The user checks the final image and, if satisfied, presses the "confirm" button to decide to move.

[0771] Step 18:

[0772] The device will display a link to purchase the furniture. When the user presses the "Confirm" button, a link to purchase the furniture from the furniture store will be displayed on the device, allowing the user to purchase new furniture.

[0773] Example 2

[0774] 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."

[0775] Conventional moving simulation systems have difficulty accurately grasping the specific layout of a new property when users arrange their own furniture. Furthermore, because the simulation is performed without taking into account the user's feelings and preferences, the system often fails to propose an optimal layout. Furthermore, the system lacks the functionality to re-simulate the layout based on the user's manual adjustments or to provide links to purchase new furniture.

[0776] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0777] In this invention, the server includes: means for incorporating furniture information using a generative AI model and combining it with property data to automatically generate an image of the room after the user moves in; means for transmitting furniture information entered by the user from the terminal to the server; means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation; and means for recognizing the user's emotions using an emotion engine and adjusting the simulation based on the recognized emotional state. This allows the user to easily grasp a specific image of the room after moving in based on the furniture currently owned, and proposes an optimal layout based on the user's emotions and preferences. It can also provide a re-simulation that reflects the user's manual adjustments and a link to purchase new furniture.

[0778] A "generative AI model" is a type of artificial intelligence that generates new images and text based on user input.

[0779] An "emotion engine" is a system that analyzes data such as a user's facial expressions and tone of voice to recognize their emotional state.

[0780] "Furniture information" refers to all information entered by the user, including photos of furniture, dimensions, and other attribute data.

[0781] "Property Information" refers to detailed data about a property, such as dimensions, layout, and interior images of the property.

[0782] "Simulation image" refers to a visual image of the room after moving in, generated using a generative AI model based on furniture information and property information.

[0783] "Terminal" refers to a device such as a smartphone or PC that a user uses to input information.

[0784] "Server" refers to a computer system for processing data received from users and generating and transmitting simulation images.

[0785] "Means" refers to a method or device for achieving a specific function or purpose.

[0786] "Links" refers to connections to websites and online stores where users can purchase new furniture.

[0787] This invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and information about the property selected, and also combines it with an emotion engine that recognizes the user's emotions.The system aims to propose the optimal room layout and interior design for the user by utilizing a generative AI model and emotion engine.

[0788] First, users launch the application on their smartphone or PC and enter information about the furniture they own. Specifically, they take or select a photo of the furniture and enter its dimensions (length, width, and height). This information is then saved on the device.

[0789] Next, the device converts the furniture information entered by the user into JSON format and sends it to the server as an HTTP POST request. The server then analyzes the received furniture information and requests the property ID selected by the user. When the user enters the property ID and sends it from the device to the server, the server retrieves property information from the database based on the specified property ID. The property information includes the property's dimensions, layout, and interior photos.

[0790] The server combines the acquired furniture information with the property information to generate a "prompt sentence." This prompt sentence is input into a generative AI model (e.g., DALL-E) to generate a simulation image. An example of a prompt sentence is, "The dimensions of the living room are 500cm x 600cm, and a sofa (200cm long, 90cm wide, and 80cm high) is placed in the center."

[0791] The generated simulation image is sent to the terminal by the server and displayed to the user. At this time, the server uses an emotion engine (for example, Microsoft Azure Emotion API) to analyze the user's facial expressions and tone of voice to recognize the user's emotional state. Based on information such as whether the user is relaxed or stressed, the server adjusts the simulation image.

[0792] The user can check the generated image and manually adjust the furniture placement using the drag-and-drop function. The adjusted placement information is sent from the device to the server again, and the server performs a simulation again to generate and send a new image.

[0793] Finally, if the user reviews the final simulation image and decides they need new furniture, they can purchase it through a link displayed on their device. This link is provided by the server and allows the user to access the online furniture store's website and proceed with the purchase.

[0794] This system allows users to easily visualize their new home based on the furniture they currently own. It also suggests optimal layouts based on the user's feelings and preferences, resulting in a more satisfying move.

[0795] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0796] Step 1:

[0797] The user enters furniture information

[0798] The user launches an application installed on a smartphone or PC.

[0799] The user accesses the "Enter Furniture Information" screen.

[0800] Users can take a photo of the furniture or select an existing photo.

[0801] The user inputs the dimensions of the furniture (e.g., length 200 cm, width 90 cm, height 80 cm).

[0802] When the user presses the "Send" button, the entered furniture information is saved on the terminal.

[0803] Input: Furniture photos, dimensions

[0804] Output: Furniture information saved on the device

[0805] Step 2:

[0806] The device sends furniture information to the server.

[0807] The terminal acquires the furniture information input by the user.

[0808] The device converts furniture information (photos and dimensions) into JSON format.

[0809] The device sends JSON format data to the server as an HTTP POST request.

[0810] Input: Furniture information (photos, dimensions)

[0811] Output: Furniture information sent to the server in JSON format

[0812] Specific behavior:

[0813] json

[0814] {

[0815] "furniture": "sofa",

[0816] "dimensions": {

[0817] "length": 200,

[0818] "width": 90,

[0819] "height": 80

[0820] },

[0821] "photo": "base64encodedimage"

[0822] }

[0823] Step 3:

[0824] The server retrieves property information

[0825] The server receives the HTTP request and analyzes the furniture information.

[0826] The server requests the property ID selected by the user.

[0827] The user enters the property ID and sends it from the terminal to the server.

[0828] The server retrieves property information from the database based on the specified property ID.

[0829] Input: Property ID

[0830] Output: Acquired property information (dimensions, layout, interior photos)

[0831] Specific behavior:

[0832] json

[0833] {

[0834] "propertyID": "123456",

[0835] "details": {

[0836] "dimensions": {

[0837] "living_room": {

[0838] "length": 500,

[0839] "width": 600

[0840] }

[0841] },

[0842] "layout_image": "base64encodedlayoutimage",

[0843] "interior_photos": ["base64encodedphoto1", "base64encodedphoto2"]

[0844] }

[0845] }

[0846] Step 4:

[0847] The server runs the simulation using the generated AI.

[0848] The server integrates furniture information and property information.

[0849] The server inputs a prompt sentence into the generative AI model.

[0850] The server generates a simulation image using a generative AI model (e.g., DALL-E).

[0851] Input: Furniture information, property information

[0852] Output: Generated simulation image

[0853] Specific action prompt:

[0854] text

[0855] The living room measures 500cm x 600cm with a sofa (200cm long, 90cm wide, 80cm high) placed in the center.

[0856] Step 5:

[0857] The server performs emotion recognition using an emotion engine.

[0858] The server records the user's facial expressions and tone of voice while they are typing.

[0859] The server uses an emotion engine to analyze the user's emotional state.

[0860] Input: User's facial expression, tone of voice

[0861] Output: Recognized emotional state of the user

[0862] Specific behavior:

[0863] json

[0864] {

[0865] "emotion_state": "relaxed",

[0866] "confidence_score": 0.85

[0867] }

[0868] Step 6:

[0869] The server adjusts the simulation based on emotions.

[0870] The server sends new prompt sentences to the generative AI model if necessary based on the analysis results of the emotion engine.

[0871] The server again uses the generative AI model to generate simulated images that match the user's emotions.

[0872] Input: User's emotional state, initial simulation image

[0873] Output: Adjusted simulation image

[0874] Specific action prompt:

[0875] text

[0876] "Place plants around the sofa and use soft lighting to help users relax."

[0877] Step 7:

[0878] The server sends the generated image to the terminal and displays it.

[0879] The server sends the final simulation image to the terminal.

[0880] The terminal displays the received image to the user.

[0881] Input: Final simulation image

[0882] Output: Simulation image displayed on the terminal

[0883] Specific behavior:

[0884] json

[0885] {

[0886] "simulation_image_url": "https: / / example.com / generated_image.png"

[0887] }

[0888] Step 8:

[0889] Users fine-tune furniture arrangement

[0890] The user checks the generated image on the terminal.

[0891] Users can rearrange the furniture using the drag and drop function.

[0892] The terminal sends the new configuration information to the server.

[0893] The server runs the simulation again, generating and sending new images.

[0894] Input: User fine-tuning information

[0895] Output: Resimulated image

[0896] Specific behavior:

[0897] json

[0898] {

[0899] "new_furniture_position": {

[0900] "sofa": {

[0901] "x": 250,

[0902] "y": 150

[0903] }

[0904] }

[0905] }

[0906] Step 9:

[0907] The server provides a link to purchase the furniture.

[0908] The user checks the final simulation image.

[0909] Click on the new furniture link as needed to proceed with the purchase process.

[0910] Input: Final simulation image

[0911] Output: Furniture purchase link

[0912] Specific behavior:

[0913] json

[0914] {

[0915] "furniture_purchase_links": [

[0916] "https: / / furniturestore.com / product / sofa",

[0917] "https: / / furniturestore.com / product / table"

[0918] ]

[0919] }

[0920] (Application example 2)

[0921] 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."

[0922] For users considering moving, visualizing the exact layout of furniture in their new home can be a very troubling problem. It is also difficult to propose optimal interior design that takes into account the user's emotions and stress levels in addition to the furniture layout. Furthermore, the process for users to purchase the perfect furniture for their new home is complicated, resulting in an inconsistent overall moving experience.

[0923] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0924] In this invention, the server includes: means for incorporating furniture information using a generative AI model and combining it with property data to automatically generate an image of the room after moving in; means for transmitting furniture information entered by the user from the terminal to the server; means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation; and means for the server to use an emotion engine that recognizes the user's emotions by analyzing facial expressions and tone of voice to adjust the optimal furniture arrangement and interior design based on the emotions, transmit the generated simulation image to the terminal, and display it to the user. This allows the user to easily imagine the specific furniture arrangement in their new home and receive optimal interior design suggestions that take the user's emotions into consideration. It also makes the purchase of new furniture smoother, improving the overall moving experience.

[0925] A "generative AI model" is an artificial intelligence technology that generates a concrete image of the room the user will move into based on information about the furniture they own and the property they select.

[0926] "Furniture Information" means data about photos, dimensions, and other physical characteristics of furniture owned by a user.

[0927] "Property data" refers to detailed information about the property selected by the user, such as dimensions, layout, and interior photos.

[0928] An "emotion engine" is a technology that analyzes a user's facial expressions and tone of voice to recognize their emotions, and adjusts the generated simulation image based on that.

[0929] A "simulation image" is an image created using a generative AI model that visually shows the specific layout and arrangement of the room after moving in.

[0930] A "terminal" is a digital device such as a smartphone or computer that a user uses to input furniture information and display simulation images.

[0931] A "server" is a computer system that receives data sent by users, executes generative AI models and emotion engines, and generates and transmits simulation images.

[0932] "Furniture arrangement" refers to a layout that shows how furniture is arranged in a user's room.

[0933] The present invention is a system that generates a concrete image of the room after moving based on information about the furniture the user owns and the property they select, and also combines it with an emotion engine that recognizes the user's emotions. The operation of this system and specific examples are described below.

[0934] System Overview

[0935] The server uses a generative AI model to capture furniture information and combine it with property data to generate an image of the room. The furniture information entered by the user is sent from the device to the server. The server obtains detailed information about the property selected by the user and combines it with the furniture information to generate a simulation. The server also uses an emotion engine to recognize the user's emotions and suggests optimal furniture layout based on their emotions. This generated simulation image is sent to the device and displayed to the user.

[0936] Hardware and software used

[0937] Hardware:

[0938] Smartphones and PCs: Devices that allow users to input furniture information and display simulation images.

[0939] Server: Receives data, runs generative AI models and emotion engines, and generates and transmits simulation images.

[0940] software:

[0941] Generative AI model (e.g. FurnitureArrangementAI): AI technology that simulates optimal furniture arrangement based on furniture and property information.

[0942] Emotion engine (e.g., EmotionEngine): Recognizes the user's emotions by analyzing facial expressions and tone of voice.

[0943] Communication library (e.g. requests): A library for sending and receiving furniture information and simulation images.

[0944] Data processing and calculation

[0945] The main tasks performed by the server are:

[0946] 1. Receives furniture information input and stores it in a database. This uses image analysis algorithms to extract furniture dimensions and shapes and stores them along with text data.

[0947] 2. Property data acquisition: In this step, the server uses a RESTful API to obtain detailed property information such as dimensions, layout diagrams, and interior photos.

[0948] 3. Using a generative AI model, furniture information and property information are integrated to simulate optimal furniture placement.

[0949] 4. Analyze the user's emotions using an emotion engine. Specifically, analyze facial expressions and tone of voice in real time while the user is entering furniture and property information.

[0950] 5. Based on the results of the emotion engine, the generated simulation image is adjusted. If the user is feeling stressed, a placement suggestion to reduce stress is made.

[0951] 6. The final simulation image is sent to the terminal and displayed to the user.

[0952] Specific examples

[0953] A user uses their smartphone to take a photo of the sofa in their living room and upload it to the app. They also enter the sofa's dimensions (e.g., length 200 cm, width 90 cm, height 80 cm). The device sends this information to the server in JSON format. Based on the property ID selected by the user, the server retrieves detailed property information from the database. The generative AI model uses this information to simulate the optimal furniture arrangement for the living room. If the user is not satisfied with this simulated image, the emotion engine analyzes the user's emotions and suggests a new arrangement to, for example, reduce stress. The final image is displayed to the user, and a link to purchase new furniture is provided if necessary.

[0954] Prompt Sentence Examples

[0955] "Get the information you need for a moving simulator and use FurnitureArrangementAI and EmotionEngine to suggest room layouts that will help users relax."

[0956] In this way, users can easily visualize the specific arrangement of furniture in their new home and smoothly proceed with the entire moving process.

[0957] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0958] Step 1:

[0959] A user uses a smartphone to take a photo of the furniture in their living room and upload it to the app. They also enter the furniture's dimensions (e.g., length 200 cm, width 90 cm, height 80 cm). This is the device's input. The device converts the furniture information entered by the user into JSON format and sends it to the server.

[0960] Step 2:

[0961] The server decodes and stores the furniture information received from the device. Here, it uses an image analysis algorithm to extract the dimensions and shape of the furniture and records them in a database as text data. This is the server's data processing.

[0962] Step 3:

[0963] The user selects a property ID in the application. This is the terminal input. The terminal sends the selected property ID to the server. The server uses a RESTful API to retrieve detailed information such as the property dimensions, layout diagram, and interior photos from the database based on the received property ID. This is the server output.

[0964] Step 4:

[0965] The server inputs the acquired property information and the user's furniture information into a generative AI model (e.g., FurnitureArrangementAI). The generative AI model uses this information to simulate the optimal furniture arrangement and generate a simulation image. This is the server's data calculation.

[0966] Step 5:

[0967] The server uses an emotion engine (e.g., Emotion Engine) to analyze video of the user's facial expressions and tone of voice while they are entering furniture and property information. The emotion engine uses facial expression and voice analysis algorithms to recognize the user's emotional state and convert it into data. This is the server's data processing.

[0968] Step 6:

[0969] The server adjusts the generated simulation image based on the results of the emotion engine. Specifically, if the user is feeling stressed, it will suggest layout adjustments to reduce stress. For example, it will adjust the layout by changing the position of the lighting. This is the output of the server.

[0970] Step 7:

[0971] The server sends the final simulation image to the terminal, which then displays it to the user. This is the terminal's data output. The user can check the displayed simulation image and, if necessary, fine-tune the furniture placement using the drag-and-drop function.

[0972] Step 8:

[0973] If the user makes minor adjustments to the furniture placement, the device sends this information to the server, which then uses the generative AI model again to generate a new simulated image based on the adjusted information. This is the server's data calculation.

[0974] Step 9:

[0975] The final image is sent to the device and displayed to the user. If the user decides that they need new furniture, they click on the furniture purchase link displayed on the device. This is the user's output. The link will take them to the furniture store's website where they can purchase their new furniture.

[0976] 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.

[0977] 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.

[0978] 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.

[0979] [Third embodiment]

[0980] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0981] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0982] 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).

[0983] 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.

[0984] 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.

[0985] 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).

[0986] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] 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."

[0992] The present invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and the newly selected property. The operation of this system and a specific example are described below.

[0993] System Overview

[0994] 1. The user enters furniture information

[0995] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[0996] 2. The device sends the furniture information to the server

[0997] The terminal converts the furniture information (photographs and dimensions) entered by the user into a specified data format and sends it to the server.

[0998] 3. The server retrieves the property information

[0999] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos, etc.) of the property corresponding to that ID from the database.

[1000] 4. Running a simulation using generative AI

[1001] The server integrates the acquired furniture information with the property information and uses generative AI to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[1002] 5. Sending and displaying the generated image

[1003] The server transmits the generated simulation image to the terminal, which displays the image to the user.

[1004] 6. Fine-tuning furniture arrangement by users

[1005] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[1006] 7. Providing links to purchase furniture

[1007] If the user decides that they need new furniture based on the final image generated, they can purchase the new furniture from an affiliated furniture store using the link provided.

[1008] Specific examples

[1009] Step 1: Enter furniture information

[1010] Users take a photo of the sofa in their living room with their smartphone and upload it to the app.

[1011] The user enters the sofa dimensions (e.g., length 200 cm, width 90 cm, height 80 cm) on the upload screen.

[1012] Step 2: Submit your furniture information

[1013] The device sends the sofa information entered by the user to the server in JSON format.

[1014] Step 3: Obtain property information

[1015] The user selects the ID of the property they want to purchase. The ID of the selected property is sent to the server, which then retrieves detailed information about the property from the database.

[1016] Property information includes living room dimensions (e.g. 500cm x 600cm), layout diagrams, and interior photos.

[1017] Step 4: Run the AI ​​simulation

[1018] The server combines the acquired sofa information with the property's living room information and uses generative AI to simulate the optimal furniture arrangement.

[1019] The simulation results in an image of a room with a sofa placed in the center of the living room.

[1020] Step 5: Send and view the simulated image

[1021] The server converts the generated image into JPEG format and transmits it to the terminal.

[1022] The device displays the received image to the user within the app, and the user can review the image to get a concrete idea of ​​what the living room will look like after moving in.

[1023] Step 6: Fine-tune your furniture placement

[1024] The user presses the "Adjust" button to fine-tune the position of the sofa based on the displayed image.

[1025] The user uses the drag and drop function to move the sofa to the left.

[1026] The terminal transmits this adjustment information to the server, and the server generates a simulation image again and transmits it to the terminal.

[1027] The user checks the final image after adjustments and presses the "confirm" button if satisfied.

[1028] Step 7: Provide a link to purchase the furniture

[1029] Once the user hits the "confirm" button, they will be provided with a link to purchase their new furniture based on the final image displayed.

[1030] Users can click on this link to purchase their new furniture at the affiliated furniture store's site.

[1031] This allows users to save the trouble of viewing the property and easily get a concrete image of their new home, taking into account the placement of their current furniture.

[1032] The processing flow will be explained below.

[1033] Step 1:

[1034] The user inputs furniture information. The user uses their device to take a photo of the furniture they own or select an existing photo. Next, the user enters the furniture's dimensions (length, width, and height) into the input form.

[1035] Step 2:

[1036] The device sends the furniture information to the server. The device converts the furniture information entered by the user into a specified data format (e.g., JSON format) and sends it to the server as an HTTP POST request.

[1037] Step 3:

[1038] The server receives the furniture information. The server receives the furniture information sent from the terminal and stores it in a database.

[1039] Step 4:

[1040] The user selects a property ID. The user selects the ID of the property they want on the property search site and sends that ID to the server.

[1041] Step 5:

[1042] The server retrieves property information. The server queries the real estate database based on the property ID sent by the user and retrieves detailed information (dimensions, layout, interior photos) of the corresponding property.

[1043] Step 6:

[1044] The server runs the simulation. The server integrates the received furniture information with the acquired property information and runs the simulation using a generation AI. The generation AI places the furniture in the optimal position and generates an image of what the room will look like after the move.

[1045] Step 7:

[1046] The server sends the generated image to the terminal. The server converts the generated simulation image into an appropriate format (e.g., JPEG) and sends it to the terminal.

[1047] Step 8:

[1048] The terminal displays the simulated image. The terminal displays the image received from the server on the interface of the website or application. The user can check this image and get a concrete vision of what the room will look like after moving in.

[1049] Step 9:

[1050] The user fine-tunes the furniture placement. The user manually adjusts the furniture position using the drag-and-drop function based on the displayed simulation image. After adjustments are complete, the user presses the "Save" button.

[1051] Step 10:

[1052] The terminal transmits the fine-tuning information to the server. The terminal converts the furniture arrangement information fine-tuned by the user into a data format and transmits it to the server.

[1053] Step 11:

[1054] The server performs a re-simulation. The server uses the generation AI to perform a re-simulation based on the fine-tuning information received from the user, and generates the final image.

[1055] Step 12:

[1056] The server sends the final image to the terminal. The server sends the final generated simulation image to the terminal. The terminal displays the image again for the user to confirm.

[1057] Step 13:

[1058] The user checks the final image and confirms it. The user checks the final image and, if satisfied, presses the "confirm" button to decide to move.

[1059] Step 14:

[1060] The device will display a link to purchase the furniture. When the user presses the "Confirm" button, a link to purchase the furniture from the furniture store will be displayed on the device, allowing the user to purchase new furniture.

[1061] Example 1

[1062] 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."

[1063] To easily get a concrete image of the room after moving, it is necessary to view the room on site, which takes time and effort. In addition, it is difficult to perform a simulation that takes into account the layout of the current furniture, making it difficult to accurately grasp the furniture layout in the new property. For this reason, many users are concerned about the furniture layout in their new home.

[1064] 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.

[1065] In this invention, the server includes means for importing furniture information entered by the user into the terminal, means for converting the furniture information into a data format specified by the user and transmitting it to the server, means for acquiring detailed information about the property selected by the user from a database, means for integrating the acquired furniture information and property information and generating a simulation using a generative AI model, and means for converting the generated simulation image into an image format, transmitting it to the terminal, and displaying it to the user. This allows the user to easily grasp a specific image of the room after moving in and simulate the optimal arrangement of the furniture currently owned.

[1066] "Furniture information" is information including photos and dimensions (length, width, height) of furniture owned by the user.

[1067] A "terminal" is a device that a user uses to input furniture information and check simulation images, and includes smartphones, PCs, etc.

[1068] The "server" is a central processing unit that receives furniture and property information sent by users and runs simulations using a generative AI model.

[1069] A "generative AI model" is an artificial intelligence model that simulates optimal furniture arrangement based on user input data and generates an image of a room.

[1070] A "simulation image" is an image generated by a generative AI model that shows a concrete image of what the room will look like after the user's furniture is placed in the new property.

[1071] A "database" is a collection of information that the server accesses to obtain property information, and stores information such as property dimensions, layout, and interior photos.

[1072] The "drag-and-drop function" is an interface function that allows the user to manually move the position of furniture on the simulation image.

[1073] A "link" is a reference to a web page where a user can purchase new furniture based on the generated final simulation image.

[1074] The present invention provides a system that generates a concrete image of a room after a user moves in, using information about furniture owned by the user and information about a newly selected property.

[1075] First, users input furniture information using their smartphone or PC. Specifically, they take or select a photo of the furniture they own and enter its dimensions (length, width, height). This furniture information is then imported into the device.

[1076] The device converts the furniture information (photos and dimensions) entered by the user into a specified data format, such as JSON, and sends it to the server. Through this transmission, the server receives the user's furniture information.

[1077] The server then receives the ID of the property selected by the user, and based on that ID, retrieves the property's details (dimensions, layout, interior photos, etc.) from the database, which are then merged with the furniture information.

[1078] The server inputs the acquired furniture and property information into a generative AI model to simulate the optimal furniture arrangement. This generative AI model operates based on instructions such as a prompt, "Please simulate the optimal room layout based on the following furniture and property information." Examples of specific prompts include, "Furniture information: sofa photo and dimensions (length 200cm, width 90cm, height 80cm)," "Property information: living room dimensions (500cm x 600cm), layout diagram, interior photo."

[1079] The generated simulation image is converted into an image format (e.g., JPEG format) on the server. This image is then sent to the terminal and displayed to the user. By checking this image, the user can get a concrete idea of ​​what the room will look like after moving in.

[1080] In addition, the user can manually adjust the position of the furniture on the displayed simulation image using the drag-and-drop function. After the user makes the adjustment, the device sends the adjustment information back to the server, and the server generates a new simulation image and sends it to the device. This allows the user to adjust the furniture arrangement until they are satisfied.

[1081] Finally, once the user is satisfied with the simulation image, a link to purchase new furniture based on the image is provided. The user can click on this link to purchase the desired furniture on the affiliated furniture store's website.

[1082] In this way, the present invention allows the user to save the trouble of viewing the property and easily get a concrete image of their new home, taking into consideration the placement of their current furniture.

[1083] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1084] Step 1:

[1085] The user inputs furniture information. Using a smartphone or PC, the user takes or selects a photo of the furniture they own and enters the furniture's dimensions (length, width, and height). This input data consists of a photo of the furniture and its dimensions, and the entered information is imported into the device. Specifically, the user takes a photo of a sofa using the app's photo function and enters, "The sofa is 200 cm long, 90 cm wide, and 80 cm high."

[1086] Step 2:

[1087] The device sends the furniture information to the server. The device converts the furniture information (photo and dimensions) entered by the user into a specified data format (e.g., JSON format). The input for this data conversion is the furniture information entered by the user, and the output is furniture information in JSON format. The converted data is then sent to the server. Specifically, the device sends the JSON-formatted data { "Furniture Name": "Sofa", "Length": 200, "Width": 90, "Height": 80, "Image URL": "https: / / example.com / sofa.jpg"} to the server.

[1088] Step 3:

[1089] The server retrieves property information. The server receives the ID of the property selected by the user. The input is the property ID, and the server retrieves detailed information about the property from the database based on that ID. The input for retrieving information from the database is the property ID, and the output is detailed property information (dimensions, layout, interior photos, etc.). Specifically, the server receives property ID "A123" and retrieves information from the database such as "The living room dimensions are 500cm x 600cm, and a layout diagram and interior photos are included."

[1090] Step 4:

[1091] The server uses the generative AI to run a simulation. The server inputs the acquired furniture information and property information into the generative AI model and simulates the optimal furniture layout. The input for this simulation is furniture information and property information, and the output is a simulation image. Specifically, the server sends the generative AI model a prompt saying, "Please simulate the optimal room layout based on the furniture information and property information below," and the generative AI model generates an image of a room with a sofa placed in the center of the living room.

[1092] Step 5:

[1093] The server sends the generated image to the device and displays it to the user. The server converts the generated simulation image to JPEG format. The input for this image conversion is the simulation image, and the output is a JPEG image. This image is then sent to the device, and the device displays the received image to the user. Specifically, the server sends a JPEG image to the device, and the user views this image within the app.

[1094] Step 6:

[1095] The user fine-tunes the furniture arrangement. The user manually fine-tunes the furniture arrangement on the simulation image using the drag-and-drop function. The input of this operation is the user's adjustment instructions, and the output is the new furniture arrangement information. Specifically, the user presses the "Adjust" button and drags the sofa to the left to move it.

[1096] Step 7:

[1097] The terminal sends the adjustment information to the server and performs a re-simulation. The terminal sends the furniture layout information manually adjusted by the user to the server. The input of this transmission is the new furniture layout information, and the output is data transmission to the server. The server runs the simulation again using the generative AI model to generate a new simulation image. The input of this re-simulation is the adjusted furniture layout information, and the output is a new simulation image. Specifically, the server runs the re-simulation and sends the new image to the terminal.

[1098] Step 8:

[1099] The user confirms the final simulation image and provides a purchase link. When the user presses the "Confirm" button, a link to purchase new furniture based on the generated final simulation image is provided. The input of this confirmation operation is the user's "Confirm" instruction, and the output is the purchase link. Specifically, when the user presses the "Confirm" button, the link "https: / / example-furniture-store.com / new-sofa" is displayed within the app.

[1100] (Application example 1)

[1101] 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."

[1102] When moving, it is difficult to visualize how one's furniture will be arranged in a new property. In particular, users need to confirm whether the size and design of the furniture will fit into the new room, but physically viewing the property is time-consuming and costly. Furthermore, there is a demand for an efficient and easy way to consider purchasing and arranging new furniture. To solve this problem, a system is needed that allows users to easily visualize their new room and simulate appropriate furniture arrangements.

[1103] 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.

[1104] In this invention, the server includes means for taking in furniture information using a generative AI model and combining it with property data to automatically generate an image of the living space after moving in, means for transmitting the furniture information entered by the user from the terminal to the server, means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation, means for transmitting the generated simulation image to the terminal and displaying it to the user, and means for providing the user with a link to select and purchase new furniture in a virtual store. This allows the user to specifically imagine how their furniture will be arranged in their new property, making it easier to purchase new furniture and determine the optimal arrangement.

[1105] A "generative AI model" is an artificial intelligence technology that generates new content based on data such as images and text.

[1106] "Furniture Information" refers to detailed information such as photos, dimensions, and design of furniture.

[1107] "Property data" refers to detailed information such as the property's layout, dimensions, and interior photos.

[1108] "Simulation" is the process of combining the furniture selected by the user with property data to recreate a concrete image of the room after moving in on a computer.

[1109] "Terminal" refers to an electronic device used by a user, such as a smartphone or PC.

[1110] A "server" refers to a computer system that receives and processes data sent from a user's terminal.

[1111] A "virtual store" refers to a virtual shopping site or application operated on the Internet.

[1112] "Link" means an internet reference that provides direct access to a particular web page or App feature.

[1113] "Drag and drop" refers to the operation of selecting and moving an item with a mouse or the like in a computer user interface.

[1114] This invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and information about the property selected by the user. The operation of this system and a specific example are described below.

[1115] System Overview

[1116] Hardware

[1117] User devices include smartphones, personal computers, and the like.

[1118] A server is a computer system used for data processing, and it is desirable for servers to be operated in a cloud environment.

[1119] software

[1120] The front end is an application that uses React Native and provides an interface for users to input furniture information and check the simulation results.

[1121] The backend uses Node.js (Express framework) to process data and provide various APIs.

[1122] MongoDB is used as the database to store and manage furniture and property information.

[1123] TensorFlow.js is used for image processing and analyzes uploaded furniture photos.

[1124] The generative AI model uses OpenAI's DALL-E model to generate furniture placement simulations.

[1125] Operation explanation

[1126] 1. The user enters furniture information

[1127] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[1128] 2. The device sends the furniture information to the server

[1129] The terminal converts the furniture information (photos and dimensions) entered by the user into JSON format and sends it to the server.

[1130] 3. The server retrieves the property information

[1131] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos, etc.) of the property corresponding to that ID from the database.

[1132] 4. Running a simulation using generative AI

[1133] The server integrates the acquired furniture information with the property information and uses a generative AI model to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[1134] Example prompt sentence:

[1135] Generate an interior design layout for a room with dimensions 500cm x 600cm. Place a sofa of dimensions 200cm x 90cm x 80cm in the center of the room. Generate a realistic image of the room with this configuration.

[1136] 5. Sending and displaying the generated image

[1137] The server converts the generated simulation image into JPEG format and sends it to the terminal.

[1138] The terminal displays this image to the user, who can then check it to get a concrete idea of ​​what the room will look like after moving in.

[1139] 6. Fine-tuning furniture arrangement by users

[1140] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[1141] 7. Providing links to purchase furniture

[1142] If the user decides that they need new furniture based on the final image generated, they can access a virtual store via a link provided and purchase the new furniture.

[1143] This allows users to save the trouble of viewing the property, easily get a concrete image of their new home while taking into consideration the placement of their current furniture, and efficiently purchase the new furniture they need.

[1144] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1145] Step 1:

[1146] The user inputs the furniture information.

[1147] Using a smartphone or PC, a user takes or selects a photo of the furniture they own and inputs the furniture's dimensions (length, width, and height). This input information is then imported into the device. The input data obtained here consists of the photo image and dimensional information.

[1148] Step 2:

[1149] The terminal transmits the furniture information to the server.

[1150] The device converts the furniture information (photos and dimensions) entered by the user into JSON format. This JSON format data is sent to the server. The input data is the furniture information entered by the user, and the output data is furniture information in JSON format.

[1151] Step 3:

[1152] The server retrieves the property information.

[1153] The server receives the ID of the property selected by the user. Based on this ID, the server retrieves the property's details (dimensions, layout, interior photos, etc.) from the database. The input data is the property ID, and the output data is the property details.

[1154] Step 4:

[1155] The server runs the simulation using the generated AI.

[1156] The server integrates the acquired furniture information and property information and runs a furniture layout simulation using a generative AI model (OpenAI's DALL-E model). Based on this simulation, an image of the room after moving in is generated in image format. The input data is furniture information and property information, and the output data is an image of the simulation results.

[1157] An example of the prompt that might be generated is:

[1158] Generate an interior design layout for a room with dimensions 500cm x 600cm. Place a sofa of dimensions 200cm x 90cm x 80cm in the center of the room. Generate a realistic image of the room with this configuration.

[1159] Step 5:

[1160] The generated image is sent to the terminal and displayed.

[1161] The server converts the generated simulation image into JPEG format and sends it to the terminal. The terminal receives this image and displays it to the user. The input data is the image of the simulation result, and the output data is the JPEG format image displayed on the user terminal.

[1162] Step 6:

[1163] The user fine-tunes the furniture arrangement.

[1164] Based on the displayed simulation image, the user can manually fine-tune the furniture arrangement using the drag-and-drop function. When the user inputs the adjusted arrangement information, it is sent from the terminal to the server. The server then runs the simulation again, generates a final image of the room, and sends it to the terminal. The input data is the adjusted arrangement information, and the output data is a simulation image of the final arrangement.

[1165] Step 7:

[1166] Provide a link for users to purchase new furniture in a virtual store.

[1167] If the user decides that they need new furniture based on the generated final image, they can access the virtual store via the displayed link and purchase the new furniture. The input data is the final simulation image, and the output data is a link to the virtual store.

[1168] 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.

[1169] The present invention is a system that generates a concrete image of the room after moving based on information about the furniture the user owns and the property they select, and also combines it with an emotion engine that recognizes the user's emotions. The operation of this system and specific examples are described below.

[1170] System Overview

[1171] 1. The user enters furniture information

[1172] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[1173] 2. The device sends the furniture information to the server

[1174] The terminal converts the furniture information (photographs and dimensions) entered by the user into a specified data format and sends it to the server.

[1175] 3. The server retrieves the property information

[1176] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos) of the property corresponding to that ID from the database.

[1177] 4. Running a simulation using generative AI

[1178] The server integrates the acquired furniture information with the property information and uses generative AI to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[1179] 5. User Emotion Recognition by Emotion Engine

[1180] The server uses an emotion engine to recognize the user's emotions by analyzing facial expressions and tone of voice while the user is entering furniture and property information.

[1181] 6. Emotion-based simulation adjustment

[1182] Based on the analysis results of the emotion engine, the server proposes optimal furniture layouts and interior designs that will help users relax. For example, if a user is feeling stressed, the server generates furniture layouts that will reduce stress.

[1183] 7. Sending and displaying the generated image

[1184] The server transmits the simulated image adjusted by the emotion engine to the terminal, which displays the image to the user.

[1185] 8. User-adjusted furniture placement

[1186] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[1187] 9. Providing links to purchase furniture

[1188] If the user decides that they need new furniture based on the final image generated, they can purchase the new furniture from an affiliated furniture store using the link provided.

[1189] Specific examples

[1190] Step 1: Enter furniture information

[1191] Users take a photo of the sofa in their living room with their smartphone and upload it to the app.

[1192] The user enters the sofa dimensions (e.g., length 200 cm, width 90 cm, height 80 cm) on the upload screen.

[1193] Step 2: Submit your furniture information

[1194] The device sends the sofa information entered by the user to the server in JSON format.

[1195] Step 3: Obtain property information

[1196] The user selects the ID of the property they want, and the selected property ID is sent to the server, which retrieves detailed information about the property from the database.

[1197] Property information includes living room dimensions (e.g. 500cm x 600cm), layout diagrams, and interior photos.

[1198] Step 4: Run the AI ​​simulation

[1199] The server combines the acquired sofa information with the property's living room information and uses generative AI to simulate the optimal furniture arrangement.

[1200] The simulation results in an image of a room with a sofa placed in the center of the living room.

[1201] Step 5: Emotion Recognition with the Emotion Engine

[1202] While the user is entering property information, the emotion engine analyzes the user's facial expressions and tone of voice. For example, if the user is smiling, it determines that the user is relaxed.

[1203] Step 6: Adjust the simulation based on emotions

[1204] Based on the analysis results of the emotion engine, the server proposes optimal furniture arrangements that will help the user relax. For example, if the user shows signs of stress, the server will suggest appropriate lighting arrangements and furniture layouts to reduce stress.

[1205] Step 7: Send and view the simulated image

[1206] The server transmits the generated simulation image to the terminal, which displays the image to the user, allowing the user to get a concrete image of what the living room will look like after moving in.

[1207] Step 8: Fine-tune your furniture placement

[1208] Users can manually fine-tune the furniture placement by pressing the "Adjust" button, using the drag-and-drop function to rearrange the furniture, for example, by moving the sofa from the center to the left side.

[1209] The terminal transmits the user's fine-tuning information to the server, and the server runs the simulation again.

[1210] The final adjusted image is sent to the terminal and displayed to the user.

[1211] Step 9: Provide a link to purchase the furniture

[1212] If the user decides that they need new furniture after reviewing the final image, they can click on the link provided, which will take them to the affiliated furniture store's website to purchase the new furniture.

[1213] This system eliminates the need for viewings and allows users to easily visualize their new home while taking into account the placement of their current furniture. Furthermore, by combining it with an emotion engine, it can suggest optimal layouts based on the user's emotions, resulting in a more satisfying move.

[1214] The processing flow will be explained below.

[1215] Step 1:

[1216] The user inputs furniture information. The user uses their device to take a photo of the furniture they own or select an existing photo. Next, the user enters the furniture's dimensions (length, width, height) into the input form. This saves the furniture information to the device.

[1217] Step 2:

[1218] The device sends the furniture information to the server. The device converts the furniture information entered by the user into a specified data format (e.g., JSON format) and sends it to the server as an HTTP POST request.

[1219] Step 3:

[1220] The server receives the furniture information. The server receives the furniture information sent from the terminal and stores it in a database.

[1221] Step 4:

[1222] The user selects a property ID. The user selects the ID of the property they want on the property search site and sends that ID to the server.

[1223] Step 5:

[1224] The server retrieves property information. The server queries the real estate database based on the property ID sent by the user and retrieves detailed information (dimensions, layout, interior photos) of the corresponding property.

[1225] Step 6:

[1226] The server initializes the emotion engine and prepares to analyze the user's emotions. The emotion engine initializes the module for analyzing the user's facial expressions and tone of voice in real time.

[1227] Step 7:

[1228] The device transmits user data to the emotion engine. While the user is entering property information, the device uses a camera and microphone to capture the user's facial expressions and tone of voice, and transmits this data to the emotion engine.

[1229] Step 8:

[1230] The emotion engine recognizes the user's emotions. The emotion engine analyzes the received data and determines the user's current emotional state (e.g., relaxed, stressed, excited).

[1231] Step 9:

[1232] The server runs the simulation. The server integrates the received furniture information with the acquired property information and uses generative AI to run a furniture layout simulation. Based on the results, it generates an image of the room after moving in.

[1233] Step 10:

[1234] The server adjusts the simulation based on emotions. Based on the analysis results of the emotion engine, the server proposes optimal furniture layout and interior design that matches the user's emotions. For example, if the user is feeling stressed, it generates furniture layout that will reduce stress.

[1235] Step 11:

[1236] The server sends the generated simulation image to the terminal. The server converts the simulation image adjusted by the emotion engine into an appropriate format (e.g., JPEG format) and sends it to the terminal.

[1237] Step 12:

[1238] The terminal displays the simulation image. The terminal displays the simulation image received from the server on the device screen. The user can check this image and get a concrete vision of what the room will look like after moving in.

[1239] Step 13:

[1240] The user fine-tunes the furniture placement. Based on the displayed simulation image, the user manually adjusts the furniture position using the drag-and-drop function. After adjustments are made, the user presses the "Save" button to save the changes to the device.

[1241] Step 14:

[1242] The terminal transmits the fine-tuning information to the server. The terminal converts the furniture arrangement information fine-tuned by the user into a data format and transmits it to the server.

[1243] Step 15:

[1244] The server performs a re-simulation. The server uses the generation AI to perform a re-simulation based on the fine-tuning information received from the user, and generates the final image.

[1245] Step 16:

[1246] The server sends the final image to the terminal. The server sends the final generated simulation image to the terminal. The terminal displays the image again for the user to confirm.

[1247] Step 17:

[1248] The user checks the final image and confirms it. The user checks the final image and, if satisfied, presses the "confirm" button to decide to move.

[1249] Step 18:

[1250] The device will display a link to purchase the furniture. When the user presses the "Confirm" button, a link to purchase the furniture from the furniture store will be displayed on the device, allowing the user to purchase new furniture.

[1251] Example 2

[1252] 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."

[1253] Conventional moving simulation systems have difficulty accurately grasping the specific layout of a new property when users arrange their own furniture. Furthermore, because the simulation is performed without taking into account the user's feelings and preferences, the system often fails to propose an optimal layout. Furthermore, the system lacks the functionality to re-simulate the layout based on the user's manual adjustments or to provide links to purchase new furniture.

[1254] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1255] In this invention, the server includes: means for incorporating furniture information using a generative AI model and combining it with property data to automatically generate an image of the room after the user moves in; means for transmitting furniture information entered by the user from the terminal to the server; means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation; and means for recognizing the user's emotions using an emotion engine and adjusting the simulation based on the recognized emotional state. This allows the user to easily grasp a specific image of the room after moving in based on the furniture currently owned, and proposes an optimal layout based on the user's emotions and preferences. It can also provide a re-simulation that reflects the user's manual adjustments and a link to purchase new furniture.

[1256] A "generative AI model" is a type of artificial intelligence that generates new images and text based on user input.

[1257] An "emotion engine" is a system that analyzes data such as a user's facial expressions and tone of voice to recognize their emotional state.

[1258] "Furniture information" refers to all information entered by the user, including photos of furniture, dimensions, and other attribute data.

[1259] "Property Information" refers to detailed data about a property, such as dimensions, layout, and interior images of the property.

[1260] "Simulation image" refers to a visual image of the room after moving in, generated using a generative AI model based on furniture information and property information.

[1261] "Terminal" refers to a device such as a smartphone or PC that a user uses to input information.

[1262] "Server" refers to a computer system for processing data received from users and generating and transmitting simulation images.

[1263] "Means" refers to a method or device for achieving a specific function or purpose.

[1264] "Links" refers to connections to websites and online stores where users can purchase new furniture.

[1265] This invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and information about the property selected, and also combines it with an emotion engine that recognizes the user's emotions.The system aims to propose the optimal room layout and interior design for the user by utilizing a generative AI model and emotion engine.

[1266] First, users launch the application on their smartphone or PC and enter information about the furniture they own. Specifically, they take or select a photo of the furniture and enter its dimensions (length, width, and height). This information is then saved on the device.

[1267] Next, the device converts the furniture information entered by the user into JSON format and sends it to the server as an HTTP POST request. The server then analyzes the received furniture information and requests the property ID selected by the user. When the user enters the property ID and sends it from the device to the server, the server retrieves property information from the database based on the specified property ID. The property information includes the property's dimensions, layout, and interior photos.

[1268] The server combines the acquired furniture information with the property information to generate a "prompt sentence." This prompt sentence is input into a generative AI model (e.g., DALL-E) to generate a simulation image. An example of a prompt sentence is, "The dimensions of the living room are 500cm x 600cm, and a sofa (200cm long, 90cm wide, and 80cm high) is placed in the center."

[1269] The generated simulation image is sent to the terminal by the server and displayed to the user. At this time, the server uses an emotion engine (for example, Microsoft Azure Emotion API) to analyze the user's facial expressions and tone of voice to recognize the user's emotional state. Based on information such as whether the user is relaxed or stressed, the server adjusts the simulation image.

[1270] The user can check the generated image and manually adjust the furniture placement using the drag-and-drop function. The adjusted placement information is sent from the device to the server again, and the server performs a simulation again to generate and send a new image.

[1271] Finally, if the user reviews the final simulation image and decides they need new furniture, they can purchase it through a link displayed on their device. This link is provided by the server and allows the user to access the online furniture store's website and proceed with the purchase.

[1272] This system allows users to easily visualize their new home based on the furniture they currently own. It also suggests optimal layouts based on the user's feelings and preferences, resulting in a more satisfying move.

[1273] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1274] Step 1:

[1275] The user enters furniture information

[1276] The user launches an application installed on a smartphone or PC.

[1277] The user accesses the "Enter Furniture Information" screen.

[1278] Users can take a photo of the furniture or select an existing photo.

[1279] The user inputs the dimensions of the furniture (e.g., length 200 cm, width 90 cm, height 80 cm).

[1280] When the user presses the "Send" button, the entered furniture information is saved on the terminal.

[1281] Input: Furniture photos, dimensions

[1282] Output: Furniture information saved on the device

[1283] Step 2:

[1284] The device sends furniture information to the server.

[1285] The terminal acquires the furniture information input by the user.

[1286] The device converts furniture information (photos and dimensions) into JSON format.

[1287] The device sends JSON format data to the server as an HTTP POST request.

[1288] Input: Furniture information (photos, dimensions)

[1289] Output: Furniture information sent to the server in JSON format

[1290] Specific behavior:

[1291] json

[1292] {

[1293] "furniture": "sofa",

[1294] "dimensions": {

[1295] "length": 200,

[1296] "width": 90,

[1297] "height": 80

[1298] },

[1299] "photo": "base64encodedimage"

[1300] }

[1301] Step 3:

[1302] The server retrieves property information

[1303] The server receives the HTTP request and analyzes the furniture information.

[1304] The server requests the property ID selected by the user.

[1305] The user enters the property ID and sends it from the terminal to the server.

[1306] The server retrieves property information from the database based on the specified property ID.

[1307] Input: Property ID

[1308] Output: Acquired property information (dimensions, layout, interior photos)

[1309] Specific behavior:

[1310] json

[1311] {

[1312] "propertyID": "123456",

[1313] "details": {

[1314] "dimensions": {

[1315] "living_room": {

[1316] "length": 500,

[1317] "width": 600

[1318] }

[1319] },

[1320] "layout_image": "base64encodedlayoutimage",

[1321] "interior_photos": ["base64encodedphoto1", "base64encodedphoto2"]

[1322] }

[1323] }

[1324] Step 4:

[1325] The server runs the simulation using the generated AI.

[1326] The server integrates furniture information and property information.

[1327] The server inputs a prompt sentence into the generative AI model.

[1328] The server generates a simulation image using a generative AI model (e.g., DALL-E).

[1329] Input: Furniture information, property information

[1330] Output: Generated simulation image

[1331] Specific action prompt:

[1332] text

[1333] The living room measures 500cm x 600cm with a sofa (200cm long, 90cm wide, 80cm high) placed in the center.

[1334] Step 5:

[1335] The server performs emotion recognition using an emotion engine.

[1336] The server records the user's facial expressions and tone of voice while they are typing.

[1337] The server uses an emotion engine to analyze the user's emotional state.

[1338] Input: User's facial expression, tone of voice

[1339] Output: Recognized emotional state of the user

[1340] Specific behavior:

[1341] json

[1342] {

[1343] "emotion_state": "relaxed",

[1344] "confidence_score": 0.85

[1345] }

[1346] Step 6:

[1347] The server adjusts the simulation based on emotions.

[1348] The server sends new prompt sentences to the generative AI model if necessary based on the analysis results of the emotion engine.

[1349] The server again uses the generative AI model to generate simulated images that match the user's emotions.

[1350] Input: User's emotional state, initial simulation image

[1351] Output: Adjusted simulation image

[1352] Specific action prompt:

[1353] text

[1354] "Place plants around the sofa and use soft lighting to help users relax."

[1355] Step 7:

[1356] The server sends the generated image to the terminal and displays it.

[1357] The server sends the final simulation image to the terminal.

[1358] The terminal displays the received image to the user.

[1359] Input: Final simulation image

[1360] Output: Simulation image displayed on the terminal

[1361] Specific behavior:

[1362] json

[1363] {

[1364] "simulation_image_url": "https: / / example.com / generated_image.png"

[1365] }

[1366] Step 8:

[1367] Users fine-tune furniture arrangement

[1368] The user checks the generated image on the terminal.

[1369] Users can rearrange the furniture using the drag and drop function.

[1370] The terminal sends the new configuration information to the server.

[1371] The server runs the simulation again, generating and sending new images.

[1372] Input: User fine-tuning information

[1373] Output: Resimulated image

[1374] Specific behavior:

[1375] json

[1376] {

[1377] "new_furniture_position": {

[1378] "sofa": {

[1379] "x": 250,

[1380] "y": 150

[1381] }

[1382] }

[1383] }

[1384] Step 9:

[1385] The server provides a link to purchase the furniture.

[1386] The user checks the final simulation image.

[1387] Click on the new furniture link as needed to proceed with the purchase process.

[1388] Input: Final simulation image

[1389] Output: Furniture purchase link

[1390] Specific behavior:

[1391] json

[1392] {

[1393] "furniture_purchase_links": [

[1394] "https: / / furniturestore.com / product / sofa",

[1395] "https: / / furniturestore.com / product / table"

[1396] ]

[1397] }

[1398] (Application example 2)

[1399] 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."

[1400] For users considering moving, visualizing the exact layout of furniture in their new home can be a very troubling problem. It is also difficult to propose optimal interior design that takes into account the user's emotions and stress levels in addition to the furniture layout. Furthermore, the process for users to purchase the perfect furniture for their new home is complicated, resulting in an inconsistent overall moving experience.

[1401] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1402] In this invention, the server includes: means for incorporating furniture information using a generative AI model and combining it with property data to automatically generate an image of the room after moving in; means for transmitting furniture information entered by the user from the terminal to the server; means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation; and means for the server to use an emotion engine that recognizes the user's emotions by analyzing facial expressions and tone of voice to adjust the optimal furniture arrangement and interior design based on the emotions, transmit the generated simulation image to the terminal, and display it to the user. This allows the user to easily imagine the specific furniture arrangement in their new home and receive optimal interior design suggestions that take the user's emotions into consideration. It also makes the purchase of new furniture smoother, improving the overall moving experience.

[1403] A "generative AI model" is an artificial intelligence technology that generates a concrete image of the room the user will move into based on information about the furniture they own and the property they select.

[1404] "Furniture Information" means data about photos, dimensions, and other physical characteristics of furniture owned by a user.

[1405] "Property data" refers to detailed information about the property selected by the user, such as dimensions, layout, and interior photos.

[1406] An "emotion engine" is a technology that analyzes a user's facial expressions and tone of voice to recognize their emotions, and adjusts the generated simulation image based on that.

[1407] A "simulation image" is an image created using a generative AI model that visually shows the specific layout and arrangement of the room after moving in.

[1408] A "terminal" is a digital device such as a smartphone or computer that a user uses to input furniture information and display simulation images.

[1409] A "server" is a computer system that receives data sent by users, executes generative AI models and emotion engines, and generates and transmits simulation images.

[1410] "Furniture arrangement" refers to a layout that shows how furniture is arranged in a user's room.

[1411] The present invention is a system that generates a concrete image of the room after moving based on information about the furniture the user owns and the property they select, and also combines it with an emotion engine that recognizes the user's emotions. The operation of this system and specific examples are described below.

[1412] System Overview

[1413] The server uses a generative AI model to capture furniture information and combine it with property data to generate an image of the room. The furniture information entered by the user is sent from the device to the server. The server obtains detailed information about the property selected by the user and combines it with the furniture information to generate a simulation. The server also uses an emotion engine to recognize the user's emotions and suggests optimal furniture layout based on their emotions. This generated simulation image is sent to the device and displayed to the user.

[1414] Hardware and software used

[1415] Hardware:

[1416] Smartphones and PCs: Devices that allow users to input furniture information and display simulation images.

[1417] Server: Receives data, runs generative AI models and emotion engines, and generates and transmits simulation images.

[1418] software:

[1419] Generative AI model (e.g. FurnitureArrangementAI): AI technology that simulates optimal furniture arrangement based on furniture and property information.

[1420] Emotion engine (e.g., EmotionEngine): Recognizes the user's emotions by analyzing facial expressions and tone of voice.

[1421] Communication library (e.g. requests): A library for sending and receiving furniture information and simulation images.

[1422] Data processing and calculation

[1423] The main tasks performed by the server are:

[1424] 1. Receives furniture information input and stores it in a database. This uses image analysis algorithms to extract furniture dimensions and shapes and stores them along with text data.

[1425] 2. Property data acquisition: In this step, the server uses a RESTful API to obtain detailed property information such as dimensions, layout diagrams, and interior photos.

[1426] 3. Using a generative AI model, furniture information and property information are integrated to simulate optimal furniture placement.

[1427] 4. Analyze the user's emotions using an emotion engine. Specifically, analyze facial expressions and tone of voice in real time while the user is entering furniture and property information.

[1428] 5. Based on the results of the emotion engine, the generated simulation image is adjusted. If the user is feeling stressed, a placement suggestion to reduce stress is made.

[1429] 6. The final simulation image is sent to the terminal and displayed to the user.

[1430] Specific examples

[1431] A user uses their smartphone to take a photo of the sofa in their living room and upload it to the app. They also enter the sofa's dimensions (e.g., length 200 cm, width 90 cm, height 80 cm). The device sends this information to the server in JSON format. Based on the property ID selected by the user, the server retrieves detailed property information from the database. The generative AI model uses this information to simulate the optimal furniture arrangement for the living room. If the user is not satisfied with this simulated image, the emotion engine analyzes the user's emotions and suggests a new arrangement to, for example, reduce stress. The final image is displayed to the user, and a link to purchase new furniture is provided if necessary.

[1432] Prompt Sentence Examples

[1433] "Get the information you need for a moving simulator and use FurnitureArrangementAI and EmotionEngine to suggest room layouts that will help users relax."

[1434] In this way, users can easily visualize the specific arrangement of furniture in their new home and smoothly proceed with the entire moving process.

[1435] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1436] Step 1:

[1437] A user uses a smartphone to take a photo of the furniture in their living room and upload it to the app. They also enter the furniture's dimensions (e.g., length 200 cm, width 90 cm, height 80 cm). This is the device's input. The device converts the furniture information entered by the user into JSON format and sends it to the server.

[1438] Step 2:

[1439] The server decodes and stores the furniture information received from the device. Here, it uses an image analysis algorithm to extract the dimensions and shape of the furniture and records them in a database as text data. This is the server's data processing.

[1440] Step 3:

[1441] The user selects a property ID in the application. This is the terminal input. The terminal sends the selected property ID to the server. The server uses a RESTful API to retrieve detailed information such as the property dimensions, layout diagram, and interior photos from the database based on the received property ID. This is the server output.

[1442] Step 4:

[1443] The server inputs the acquired property information and the user's furniture information into a generative AI model (e.g., FurnitureArrangementAI). The generative AI model uses this information to simulate the optimal furniture arrangement and generate a simulation image. This is the server's data calculation.

[1444] Step 5:

[1445] The server uses an emotion engine (e.g., Emotion Engine) to analyze video of the user's facial expressions and tone of voice while they are entering furniture and property information. The emotion engine uses facial expression and voice analysis algorithms to recognize the user's emotional state and convert it into data. This is the server's data processing.

[1446] Step 6:

[1447] The server adjusts the generated simulation image based on the results of the emotion engine. Specifically, if the user is feeling stressed, it will suggest layout adjustments to reduce stress. For example, it will adjust the layout by changing the position of the lighting. This is the output of the server.

[1448] Step 7:

[1449] The server sends the final simulation image to the terminal, which then displays it to the user. This is the terminal's data output. The user can check the displayed simulation image and, if necessary, fine-tune the furniture placement using the drag-and-drop function.

[1450] Step 8:

[1451] If the user makes minor adjustments to the furniture placement, the device sends this information to the server, which then uses the generative AI model again to generate a new simulated image based on the adjusted information. This is the server's data calculation.

[1452] Step 9:

[1453] The final image is sent to the device and displayed to the user. If the user decides that they need new furniture, they click on the furniture purchase link displayed on the device. This is the user's output. The link will take them to the furniture store's website where they can purchase their new furniture.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] [Fourth embodiment]

[1458] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1459] 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.

[1460] 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).

[1461] 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.

[1462] 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.

[1463] 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).

[1464] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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."

[1471] The present invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and the newly selected property. The operation of this system and a specific example are described below.

[1472] System Overview

[1473] 1. The user enters furniture information

[1474] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[1475] 2. The device sends the furniture information to the server

[1476] The terminal converts the furniture information (photographs and dimensions) entered by the user into a specified data format and sends it to the server.

[1477] 3. The server retrieves the property information

[1478] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos, etc.) of the property corresponding to that ID from the database.

[1479] 4. Running a simulation using generative AI

[1480] The server integrates the acquired furniture information with the property information and uses generative AI to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[1481] 5. Sending and displaying the generated image

[1482] The server transmits the generated simulation image to the terminal, which displays the image to the user.

[1483] 6. Fine-tuning furniture arrangement by users

[1484] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[1485] 7. Providing links to purchase furniture

[1486] If the user decides that they need new furniture based on the final image generated, they can purchase the new furniture from an affiliated furniture store using the link provided.

[1487] Specific examples

[1488] Step 1: Enter furniture information

[1489] Users take a photo of the sofa in their living room with their smartphone and upload it to the app.

[1490] The user enters the sofa dimensions (e.g., length 200 cm, width 90 cm, height 80 cm) on the upload screen.

[1491] Step 2: Submit your furniture information

[1492] The device sends the sofa information entered by the user to the server in JSON format.

[1493] Step 3: Obtain property information

[1494] The user selects the ID of the property they want to purchase. The ID of the selected property is sent to the server, which then retrieves detailed information about the property from the database.

[1495] Property information includes living room dimensions (e.g. 500cm x 600cm), layout diagrams, and interior photos.

[1496] Step 4: Run the AI ​​simulation

[1497] The server combines the acquired sofa information with the property's living room information and uses generative AI to simulate the optimal furniture arrangement.

[1498] The simulation results in an image of a room with a sofa placed in the center of the living room.

[1499] Step 5: Send and view the simulated image

[1500] The server converts the generated image into JPEG format and transmits it to the terminal.

[1501] The device displays the received image to the user within the app, and the user can review the image to get a concrete idea of ​​what the living room will look like after moving in.

[1502] Step 6: Fine-tune your furniture placement

[1503] The user presses the "Adjust" button to fine-tune the position of the sofa based on the displayed image.

[1504] The user uses the drag and drop function to move the sofa to the left.

[1505] The terminal transmits this adjustment information to the server, and the server generates a simulation image again and transmits it to the terminal.

[1506] The user checks the final image after adjustments and presses the "confirm" button if satisfied.

[1507] Step 7: Provide a link to purchase the furniture

[1508] Once the user hits the "confirm" button, they will be provided with a link to purchase their new furniture based on the final image displayed.

[1509] Users can click on this link to purchase their new furniture at the affiliated furniture store's site.

[1510] This allows users to save the trouble of viewing the property and easily get a concrete image of their new home, taking into account the placement of their current furniture.

[1511] The processing flow will be explained below.

[1512] Step 1:

[1513] The user inputs furniture information. The user uses their device to take a photo of the furniture they own or select an existing photo. Next, the user enters the furniture's dimensions (length, width, and height) into the input form.

[1514] Step 2:

[1515] The device sends the furniture information to the server. The device converts the furniture information entered by the user into a specified data format (e.g., JSON format) and sends it to the server as an HTTP POST request.

[1516] Step 3:

[1517] The server receives the furniture information. The server receives the furniture information sent from the terminal and stores it in a database.

[1518] Step 4:

[1519] The user selects a property ID. The user selects the ID of the property they want on the property search site and sends that ID to the server.

[1520] Step 5:

[1521] The server retrieves property information. The server queries the real estate database based on the property ID sent by the user and retrieves detailed information (dimensions, layout, interior photos) of the corresponding property.

[1522] Step 6:

[1523] The server runs the simulation. The server integrates the received furniture information with the acquired property information and runs the simulation using a generation AI. The generation AI places the furniture in the optimal position and generates an image of what the room will look like after the move.

[1524] Step 7:

[1525] The server sends the generated image to the terminal. The server converts the generated simulation image into an appropriate format (e.g., JPEG) and sends it to the terminal.

[1526] Step 8:

[1527] The terminal displays the simulated image. The terminal displays the image received from the server on the interface of the website or application. The user can check this image and get a concrete vision of what the room will look like after moving in.

[1528] Step 9:

[1529] The user fine-tunes the furniture placement. The user manually adjusts the furniture position using the drag-and-drop function based on the displayed simulation image. After adjustments are complete, the user presses the "Save" button.

[1530] Step 10:

[1531] The terminal transmits the fine-tuning information to the server. The terminal converts the furniture arrangement information fine-tuned by the user into a data format and transmits it to the server.

[1532] Step 11:

[1533] The server performs a re-simulation. The server uses the generation AI to perform a re-simulation based on the fine-tuning information received from the user, and generates the final image.

[1534] Step 12:

[1535] The server sends the final image to the terminal. The server sends the final generated simulation image to the terminal. The terminal displays the image again for the user to confirm.

[1536] Step 13:

[1537] The user checks the final image and confirms it. The user checks the final image and, if satisfied, presses the "confirm" button to decide to move.

[1538] Step 14:

[1539] The device will display a link to purchase the furniture. When the user presses the "Confirm" button, a link to purchase the furniture from the furniture store will be displayed on the device, allowing the user to purchase new furniture.

[1540] Example 1

[1541] 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."

[1542] To easily get a concrete image of the room after moving, it is necessary to view the room on site, which takes time and effort. In addition, it is difficult to perform a simulation that takes into account the layout of the current furniture, making it difficult to accurately grasp the furniture layout in the new property. For this reason, many users are concerned about the furniture layout in their new home.

[1543] 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.

[1544] In this invention, the server includes means for importing furniture information entered by the user into the terminal, means for converting the furniture information into a data format specified by the user and transmitting it to the server, means for acquiring detailed information about the property selected by the user from a database, means for integrating the acquired furniture information and property information and generating a simulation using a generative AI model, and means for converting the generated simulation image into an image format, transmitting it to the terminal, and displaying it to the user. This allows the user to easily grasp a specific image of the room after moving in and simulate the optimal arrangement of the furniture currently owned.

[1545] "Furniture information" is information including photos and dimensions (length, width, height) of furniture owned by the user.

[1546] A "terminal" is a device that a user uses to input furniture information and check simulation images, and includes smartphones, PCs, etc.

[1547] The "server" is a central processing unit that receives furniture and property information sent by users and runs simulations using a generative AI model.

[1548] A "generative AI model" is an artificial intelligence model that simulates optimal furniture arrangement based on user input data and generates an image of a room.

[1549] A "simulation image" is an image generated by a generative AI model that shows a concrete image of what the room will look like after the user's furniture is placed in the new property.

[1550] A "database" is a collection of information that the server accesses to obtain property information, and stores information such as property dimensions, layout, and interior photos.

[1551] The "drag-and-drop function" is an interface function that allows the user to manually move the position of furniture on the simulation image.

[1552] A "link" is a reference to a web page where a user can purchase new furniture based on the generated final simulation image.

[1553] The present invention provides a system that generates a concrete image of a room after a user moves in, using information about furniture owned by the user and information about a newly selected property.

[1554] First, users input furniture information using their smartphone or PC. Specifically, they take or select a photo of the furniture they own and enter its dimensions (length, width, height). This furniture information is then imported into the device.

[1555] The device converts the furniture information (photos and dimensions) entered by the user into a specified data format, such as JSON, and sends it to the server. Through this transmission, the server receives the user's furniture information.

[1556] The server then receives the ID of the property selected by the user, and based on that ID, retrieves the property's details (dimensions, layout, interior photos, etc.) from the database, which are then merged with the furniture information.

[1557] The server inputs the acquired furniture and property information into a generative AI model to simulate the optimal furniture arrangement. This generative AI model operates based on instructions such as a prompt, "Please simulate the optimal room layout based on the following furniture and property information." Examples of specific prompts include, "Furniture information: sofa photo and dimensions (length 200cm, width 90cm, height 80cm)," "Property information: living room dimensions (500cm x 600cm), layout diagram, interior photo."

[1558] The generated simulation image is converted into an image format (e.g., JPEG format) on the server. This image is then sent to the terminal and displayed to the user. By checking this image, the user can get a concrete idea of ​​what the room will look like after moving in.

[1559] In addition, the user can manually adjust the position of the furniture on the displayed simulation image using the drag-and-drop function. After the user makes the adjustment, the device sends the adjustment information back to the server, and the server generates a new simulation image and sends it to the device. This allows the user to adjust the furniture arrangement until they are satisfied.

[1560] Finally, once the user is satisfied with the simulation image, a link to purchase new furniture based on the image is provided. The user can click on this link to purchase the desired furniture on the affiliated furniture store's website.

[1561] In this way, the present invention allows the user to save the trouble of viewing the property and easily get a concrete image of their new home, taking into consideration the placement of their current furniture.

[1562] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1563] Step 1:

[1564] The user inputs furniture information. Using a smartphone or PC, the user takes or selects a photo of the furniture they own and enters the furniture's dimensions (length, width, and height). This input data consists of a photo of the furniture and its dimensions, and the entered information is imported into the device. Specifically, the user takes a photo of a sofa using the app's photo function and enters, "The sofa is 200 cm long, 90 cm wide, and 80 cm high."

[1565] Step 2:

[1566] The device sends the furniture information to the server. The device converts the furniture information (photo and dimensions) entered by the user into a specified data format (e.g., JSON format). The input for this data conversion is the furniture information entered by the user, and the output is furniture information in JSON format. The converted data is then sent to the server. Specifically, the device sends the JSON-formatted data { "Furniture Name": "Sofa", "Length": 200, "Width": 90, "Height": 80, "Image URL": "https: / / example.com / sofa.jpg"} to the server.

[1567] Step 3:

[1568] The server retrieves property information. The server receives the ID of the property selected by the user. The input is the property ID, and the server retrieves detailed information about the property from the database based on that ID. The input for retrieving information from the database is the property ID, and the output is detailed property information (dimensions, layout, interior photos, etc.). Specifically, the server receives property ID "A123" and retrieves information from the database such as "The living room dimensions are 500cm x 600cm, and a layout diagram and interior photos are included."

[1569] Step 4:

[1570] The server uses the generative AI to run a simulation. The server inputs the acquired furniture information and property information into the generative AI model and simulates the optimal furniture layout. The input for this simulation is furniture information and property information, and the output is a simulation image. Specifically, the server sends the generative AI model a prompt saying, "Please simulate the optimal room layout based on the furniture information and property information below," and the generative AI model generates an image of a room with a sofa placed in the center of the living room.

[1571] Step 5:

[1572] The server sends the generated image to the device and displays it to the user. The server converts the generated simulation image to JPEG format. The input for this image conversion is the simulation image, and the output is a JPEG image. This image is then sent to the device, and the device displays the received image to the user. Specifically, the server sends a JPEG image to the device, and the user views this image within the app.

[1573] Step 6:

[1574] The user fine-tunes the furniture arrangement. The user manually fine-tunes the furniture arrangement on the simulation image using the drag-and-drop function. The input of this operation is the user's adjustment instructions, and the output is the new furniture arrangement information. Specifically, the user presses the "Adjust" button and drags the sofa to the left to move it.

[1575] Step 7:

[1576] The terminal sends the adjustment information to the server and performs a re-simulation. The terminal sends the furniture layout information manually adjusted by the user to the server. The input of this transmission is the new furniture layout information, and the output is data transmission to the server. The server runs the simulation again using the generative AI model to generate a new simulation image. The input of this re-simulation is the adjusted furniture layout information, and the output is a new simulation image. Specifically, the server runs the re-simulation and sends the new image to the terminal.

[1577] Step 8:

[1578] The user confirms the final simulation image and provides a purchase link. When the user presses the "Confirm" button, a link to purchase new furniture based on the generated final simulation image is provided. The input of this confirmation operation is the user's "Confirm" instruction, and the output is the purchase link. Specifically, when the user presses the "Confirm" button, the link "https: / / example-furniture-store.com / new-sofa" is displayed within the app.

[1579] (Application example 1)

[1580] 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."

[1581] When moving, it is difficult to visualize how one's furniture will be arranged in a new property. In particular, users need to confirm whether the size and design of the furniture will fit into the new room, but physically viewing the property is time-consuming and costly. Furthermore, there is a demand for an efficient and easy way to consider purchasing and arranging new furniture. To solve this problem, a system is needed that allows users to easily visualize their new room and simulate appropriate furniture arrangements.

[1582] 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.

[1583] In this invention, the server includes means for taking in furniture information using a generative AI model and combining it with property data to automatically generate an image of the living space after moving in, means for transmitting the furniture information entered by the user from the terminal to the server, means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation, means for transmitting the generated simulation image to the terminal and displaying it to the user, and means for providing the user with a link to select and purchase new furniture in a virtual store. This allows the user to specifically imagine how their furniture will be arranged in their new property, making it easier to purchase new furniture and determine the optimal arrangement.

[1584] A "generative AI model" is an artificial intelligence technology that generates new content based on data such as images and text.

[1585] "Furniture Information" refers to detailed information such as photos, dimensions, and design of furniture.

[1586] "Property data" refers to detailed information such as the property's layout, dimensions, and interior photos.

[1587] "Simulation" is the process of combining the furniture selected by the user with property data to recreate a concrete image of the room after moving in on a computer.

[1588] "Terminal" refers to an electronic device used by a user, such as a smartphone or PC.

[1589] A "server" refers to a computer system that receives and processes data sent from a user's terminal.

[1590] A "virtual store" refers to a virtual shopping site or application operated on the Internet.

[1591] "Link" means an internet reference that provides direct access to a particular web page or App feature.

[1592] "Drag and drop" refers to the operation of selecting and moving an item with a mouse or the like in a computer user interface.

[1593] This invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and information about the property selected by the user. The operation of this system and a specific example are described below.

[1594] System Overview

[1595] Hardware

[1596] User devices include smartphones, personal computers, and the like.

[1597] A server is a computer system used for data processing, and it is desirable for servers to be operated in a cloud environment.

[1598] software

[1599] The front end is an application that uses React Native and provides an interface for users to input furniture information and check the simulation results.

[1600] The backend uses Node.js (Express framework) to process data and provide various APIs.

[1601] MongoDB is used as the database to store and manage furniture and property information.

[1602] TensorFlow.js is used for image processing and analyzes uploaded furniture photos.

[1603] The generative AI model uses OpenAI's DALL-E model to generate furniture placement simulations.

[1604] Operation explanation

[1605] 1. The user enters furniture information

[1606] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[1607] 2. The device sends the furniture information to the server

[1608] The terminal converts the furniture information (photos and dimensions) entered by the user into JSON format and sends it to the server.

[1609] 3. The server retrieves the property information

[1610] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos, etc.) of the property corresponding to that ID from the database.

[1611] 4. Running a simulation using generative AI

[1612] The server integrates the acquired furniture information with the property information and uses a generative AI model to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[1613] Example prompt sentence:

[1614] Generate an interior design layout for a room with dimensions 500cm x 600cm. Place a sofa of dimensions 200cm x 90cm x 80cm in the center of the room. Generate a realistic image of the room with this configuration.

[1615] 5. Sending and displaying the generated image

[1616] The server converts the generated simulation image into JPEG format and sends it to the terminal.

[1617] The terminal displays this image to the user, who can then check it to get a concrete idea of ​​what the room will look like after moving in.

[1618] 6. Fine-tuning furniture arrangement by users

[1619] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[1620] 7. Providing links to purchase furniture

[1621] If the user decides that they need new furniture based on the final image generated, they can access a virtual store via a link provided and purchase the new furniture.

[1622] This allows users to save the trouble of viewing the property, easily get a concrete image of their new home while taking into consideration the placement of their current furniture, and efficiently purchase the new furniture they need.

[1623] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1624] Step 1:

[1625] The user inputs the furniture information.

[1626] Using a smartphone or PC, a user takes or selects a photo of the furniture they own and inputs the furniture's dimensions (length, width, and height). This input information is then imported into the device. The input data obtained here consists of the photo image and dimensional information.

[1627] Step 2:

[1628] The terminal transmits the furniture information to the server.

[1629] The device converts the furniture information (photos and dimensions) entered by the user into JSON format. This JSON format data is sent to the server. The input data is the furniture information entered by the user, and the output data is furniture information in JSON format.

[1630] Step 3:

[1631] The server retrieves the property information.

[1632] The server receives the ID of the property selected by the user. Based on this ID, the server retrieves the property's details (dimensions, layout, interior photos, etc.) from the database. The input data is the property ID, and the output data is the property details.

[1633] Step 4:

[1634] The server runs the simulation using the generated AI.

[1635] The server integrates the acquired furniture information and property information and runs a furniture layout simulation using a generative AI model (OpenAI's DALL-E model). Based on this simulation, an image of the room after moving in is generated in image format. The input data is furniture information and property information, and the output data is an image of the simulation results.

[1636] An example of the prompt that might be generated is:

[1637] Generate an interior design layout for a room with dimensions 500cm x 600cm. Place a sofa of dimensions 200cm x 90cm x 80cm in the center of the room. Generate a realistic image of the room with this configuration.

[1638] Step 5:

[1639] The generated image is sent to the terminal and displayed.

[1640] The server converts the generated simulation image into JPEG format and sends it to the terminal. The terminal receives this image and displays it to the user. The input data is the image of the simulation result, and the output data is the JPEG format image displayed on the user terminal.

[1641] Step 6:

[1642] The user fine-tunes the furniture arrangement.

[1643] Based on the displayed simulation image, the user can manually fine-tune the furniture arrangement using the drag-and-drop function. When the user inputs the adjusted arrangement information, it is sent from the terminal to the server. The server then runs the simulation again, generates a final image of the room, and sends it to the terminal. The input data is the adjusted arrangement information, and the output data is a simulation image of the final arrangement.

[1644] Step 7:

[1645] Provide a link for users to purchase new furniture in a virtual store.

[1646] If the user decides that they need new furniture based on the generated final image, they can access the virtual store via the displayed link and purchase the new furniture. The input data is the final simulation image, and the output data is a link to the virtual store.

[1647] 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.

[1648] The present invention is a system that generates a concrete image of the room after moving based on information about the furniture the user owns and the property they select, and also combines it with an emotion engine that recognizes the user's emotions. The operation of this system and specific examples are described below.

[1649] System Overview

[1650] 1. The user enters furniture information

[1651] Users can use their smartphones or PCs to take or select photos of furniture they own and input the furniture's dimensions (length, width, and height), which then imports the furniture information into the device.

[1652] 2. The device sends the furniture information to the server

[1653] The terminal converts the furniture information (photographs and dimensions) entered by the user into a specified data format and sends it to the server.

[1654] 3. The server retrieves the property information

[1655] The server receives the ID of the property selected by the user and retrieves detailed information (dimensions, layout, interior photos) of the property corresponding to that ID from the database.

[1656] 4. Running a simulation using generative AI

[1657] The server integrates the acquired furniture information with the property information and uses generative AI to run a furniture layout simulation. Based on this simulation, an image of the room after moving in is generated in image format.

[1658] 5. User Emotion Recognition by Emotion Engine

[1659] The server uses an emotion engine to recognize the user's emotions by analyzing facial expressions and tone of voice while the user is entering furniture and property information.

[1660] 6. Emotion-based simulation adjustment

[1661] Based on the analysis results of the emotion engine, the server proposes optimal furniture layouts and interior designs that will help users relax. For example, if a user is feeling stressed, the server generates furniture layouts that will reduce stress.

[1662] 7. Sending and displaying the generated image

[1663] The server transmits the simulated image adjusted by the emotion engine to the terminal, which displays the image to the user.

[1664] 8. User-adjusted furniture placement

[1665] Users can manually adjust the furniture placement using the drag-and-drop function based on the displayed simulation image, then run the simulation again to generate the final room image and display it on their device.

[1666] 9. Providing links to purchase furniture

[1667] If the user decides that they need new furniture based on the final image generated, they can purchase the new furniture from an affiliated furniture store using the link provided.

[1668] Specific examples

[1669] Step 1: Enter furniture information

[1670] Users take a photo of the sofa in their living room with their smartphone and upload it to the app.

[1671] The user enters the sofa dimensions (e.g., length 200 cm, width 90 cm, height 80 cm) on the upload screen.

[1672] Step 2: Submit your furniture information

[1673] The device sends the sofa information entered by the user to the server in JSON format.

[1674] Step 3: Obtain property information

[1675] The user selects the ID of the property they want, and the selected property ID is sent to the server, which retrieves detailed information about the property from the database.

[1676] Property information includes living room dimensions (e.g. 500cm x 600cm), layout diagrams, and interior photos.

[1677] Step 4: Run the AI ​​simulation

[1678] The server combines the acquired sofa information with the property's living room information and uses generative AI to simulate the optimal furniture arrangement.

[1679] The simulation results in an image of a room with a sofa placed in the center of the living room.

[1680] Step 5: Emotion Recognition with the Emotion Engine

[1681] While the user is entering property information, the emotion engine analyzes the user's facial expressions and tone of voice. For example, if the user is smiling, it determines that the user is relaxed.

[1682] Step 6: Adjust the simulation based on emotions

[1683] Based on the analysis results of the emotion engine, the server proposes optimal furniture arrangements that will help the user relax. For example, if the user shows signs of stress, the server will suggest appropriate lighting arrangements and furniture layouts to reduce stress.

[1684] Step 7: Send and view the simulated image

[1685] The server transmits the generated simulation image to the terminal, which displays the image to the user, allowing the user to get a concrete image of what the living room will look like after moving in.

[1686] Step 8: Fine-tune your furniture placement

[1687] Users can manually fine-tune the furniture placement by pressing the "Adjust" button, using the drag-and-drop function to rearrange the furniture, for example, by moving the sofa from the center to the left side.

[1688] The terminal transmits the user's fine-tuning information to the server, and the server runs the simulation again.

[1689] The final adjusted image is sent to the terminal and displayed to the user.

[1690] Step 9: Provide a link to purchase the furniture

[1691] If the user decides that they need new furniture after reviewing the final image, they can click on the link provided, which will take them to the affiliated furniture store's website to purchase the new furniture.

[1692] This system eliminates the need for viewings and allows users to easily visualize their new home while taking into account the placement of their current furniture. Furthermore, by combining it with an emotion engine, it can suggest optimal layouts based on the user's emotions, resulting in a more satisfying move.

[1693] The processing flow will be explained below.

[1694] Step 1:

[1695] The user inputs furniture information. The user uses their device to take a photo of the furniture they own or select an existing photo. Next, the user enters the furniture's dimensions (length, width, height) into the input form. This saves the furniture information to the device.

[1696] Step 2:

[1697] The device sends the furniture information to the server. The device converts the furniture information entered by the user into a specified data format (e.g., JSON format) and sends it to the server as an HTTP POST request.

[1698] Step 3:

[1699] The server receives the furniture information. The server receives the furniture information sent from the terminal and stores it in a database.

[1700] Step 4:

[1701] The user selects a property ID. The user selects the ID of the property they want on the property search site and sends that ID to the server.

[1702] Step 5:

[1703] The server retrieves property information. The server queries the real estate database based on the property ID sent by the user and retrieves detailed information (dimensions, layout, interior photos) of the corresponding property.

[1704] Step 6:

[1705] The server initializes the emotion engine and prepares to analyze the user's emotions. The emotion engine initializes the module for analyzing the user's facial expressions and tone of voice in real time.

[1706] Step 7:

[1707] The device transmits user data to the emotion engine. While the user is entering property information, the device uses a camera and microphone to capture the user's facial expressions and tone of voice, and transmits this data to the emotion engine.

[1708] Step 8:

[1709] The emotion engine recognizes the user's emotions. The emotion engine analyzes the received data and determines the user's current emotional state (e.g., relaxed, stressed, excited).

[1710] Step 9:

[1711] The server runs the simulation. The server integrates the received furniture information with the acquired property information and uses generative AI to run a furniture layout simulation. Based on the results, it generates an image of the room after moving in.

[1712] Step 10:

[1713] The server adjusts the simulation based on emotions. Based on the analysis results of the emotion engine, the server proposes optimal furniture layout and interior design that matches the user's emotions. For example, if the user is feeling stressed, it generates furniture layout that will reduce stress.

[1714] Step 11:

[1715] The server sends the generated simulation image to the terminal. The server converts the simulation image adjusted by the emotion engine into an appropriate format (e.g., JPEG format) and sends it to the terminal.

[1716] Step 12:

[1717] The terminal displays the simulation image. The terminal displays the simulation image received from the server on the device screen. The user can check this image and get a concrete vision of what the room will look like after moving in.

[1718] Step 13:

[1719] The user fine-tunes the furniture placement. Based on the displayed simulation image, the user manually adjusts the furniture position using the drag-and-drop function. After adjustments are made, the user presses the "Save" button to save the changes to the device.

[1720] Step 14:

[1721] The terminal transmits the fine-tuning information to the server. The terminal converts the furniture arrangement information fine-tuned by the user into a data format and transmits it to the server.

[1722] Step 15:

[1723] The server performs a re-simulation. The server uses the generation AI to perform a re-simulation based on the fine-tuning information received from the user, and generates the final image.

[1724] Step 16:

[1725] The server sends the final image to the terminal. The server sends the final generated simulation image to the terminal. The terminal displays the image again for the user to confirm.

[1726] Step 17:

[1727] The user checks the final image and confirms it. The user checks the final image and, if satisfied, presses the "confirm" button to decide to move.

[1728] Step 18:

[1729] The device will display a link to purchase the furniture. When the user presses the "Confirm" button, a link to purchase the furniture from the furniture store will be displayed on the device, allowing the user to purchase new furniture.

[1730] Example 2

[1731] 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."

[1732] Conventional moving simulation systems have difficulty accurately grasping the specific layout of a new property when users arrange their own furniture. Furthermore, because the simulation is performed without taking into account the user's feelings and preferences, the system often fails to propose an optimal layout. Furthermore, the system lacks the functionality to re-simulate the layout based on the user's manual adjustments or to provide links to purchase new furniture.

[1733] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1734] In this invention, the server includes: means for incorporating furniture information using a generative AI model and combining it with property data to automatically generate an image of the room after the user moves in; means for transmitting furniture information entered by the user from the terminal to the server; means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation; and means for recognizing the user's emotions using an emotion engine and adjusting the simulation based on the recognized emotional state. This allows the user to easily grasp a specific image of the room after moving in based on the furniture currently owned, and proposes an optimal layout based on the user's emotions and preferences. It can also provide a re-simulation that reflects the user's manual adjustments and a link to purchase new furniture.

[1735] A "generative AI model" is a type of artificial intelligence that generates new images and text based on user input.

[1736] An "emotion engine" is a system that analyzes data such as a user's facial expressions and tone of voice to recognize their emotional state.

[1737] "Furniture information" refers to all information entered by the user, including photos of furniture, dimensions, and other attribute data.

[1738] "Property Information" refers to detailed data about a property, such as dimensions, layout, and interior images of the property.

[1739] "Simulation image" refers to a visual image of the room after moving in, generated using a generative AI model based on furniture information and property information.

[1740] "Terminal" refers to a device such as a smartphone or PC that a user uses to input information.

[1741] "Server" refers to a computer system for processing data received from users and generating and transmitting simulation images.

[1742] "Means" refers to a method or device for achieving a specific function or purpose.

[1743] "Links" refers to connections to websites and online stores where users can purchase new furniture.

[1744] This invention is a system that generates a concrete image of the room after moving in based on information about the furniture owned by the user and information about the property selected, and also combines it with an emotion engine that recognizes the user's emotions.The system aims to propose the optimal room layout and interior design for the user by utilizing a generative AI model and emotion engine.

[1745] First, users launch the application on their smartphone or PC and enter information about the furniture they own. Specifically, they take or select a photo of the furniture and enter its dimensions (length, width, and height). This information is then saved on the device.

[1746] Next, the device converts the furniture information entered by the user into JSON format and sends it to the server as an HTTP POST request. The server then analyzes the received furniture information and requests the property ID selected by the user. When the user enters the property ID and sends it from the device to the server, the server retrieves property information from the database based on the specified property ID. The property information includes the property's dimensions, layout, and interior photos.

[1747] The server combines the acquired furniture information with the property information to generate a "prompt sentence." This prompt sentence is input into a generative AI model (e.g., DALL-E) to generate a simulation image. An example of a prompt sentence is, "The dimensions of the living room are 500cm x 600cm, and a sofa (200cm long, 90cm wide, and 80cm high) is placed in the center."

[1748] The generated simulation image is sent to the terminal by the server and displayed to the user. At this time, the server uses an emotion engine (for example, Microsoft Azure Emotion API) to analyze the user's facial expressions and tone of voice to recognize the user's emotional state. Based on information such as whether the user is relaxed or stressed, the server adjusts the simulation image.

[1749] The user can check the generated image and manually adjust the furniture placement using the drag-and-drop function. The adjusted placement information is sent from the device to the server again, and the server performs a simulation again to generate and send a new image.

[1750] Finally, if the user reviews the final simulation image and decides they need new furniture, they can purchase it through a link displayed on their device. This link is provided by the server and allows the user to access the online furniture store's website and proceed with the purchase.

[1751] This system allows users to easily visualize their new home based on the furniture they currently own. It also suggests optimal layouts based on the user's feelings and preferences, resulting in a more satisfying move.

[1752] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1753] Step 1:

[1754] The user enters furniture information

[1755] The user launches an application installed on a smartphone or PC.

[1756] The user accesses the "Enter Furniture Information" screen.

[1757] Users can take a photo of the furniture or select an existing photo.

[1758] The user inputs the dimensions of the furniture (e.g., length 200 cm, width 90 cm, height 80 cm).

[1759] When the user presses the "Send" button, the entered furniture information is saved on the terminal.

[1760] Input: Furniture photos, dimensions

[1761] Output: Furniture information saved on the device

[1762] Step 2:

[1763] The device sends furniture information to the server.

[1764] The terminal acquires the furniture information input by the user.

[1765] The device converts furniture information (photos and dimensions) into JSON format.

[1766] The device sends JSON format data to the server as an HTTP POST request.

[1767] Input: Furniture information (photos, dimensions)

[1768] Output: Furniture information sent to the server in JSON format

[1769] Specific behavior:

[1770] json

[1771] {

[1772] "furniture": "sofa",

[1773] "dimensions": {

[1774] "length": 200,

[1775] "width": 90,

[1776] "height": 80

[1777] },

[1778] "photo": "base64encodedimage"

[1779] }

[1780] Step 3:

[1781] The server retrieves property information

[1782] The server receives the HTTP request and analyzes the furniture information.

[1783] The server requests the property ID selected by the user.

[1784] The user enters the property ID and sends it from the terminal to the server.

[1785] The server retrieves property information from the database based on the specified property ID.

[1786] Input: Property ID

[1787] Output: Acquired property information (dimensions, layout, interior photos)

[1788] Specific behavior:

[1789] json

[1790] {

[1791] "propertyID": "123456",

[1792] "details": {

[1793] "dimensions": {

[1794] "living_room": {

[1795] "length": 500,

[1796] "width": 600

[1797] }

[1798] },

[1799] "layout_image": "base64encodedlayoutimage",

[1800] "interior_photos": ["base64encodedphoto1", "base64encodedphoto2"]

[1801] }

[1802] }

[1803] Step 4:

[1804] The server runs the simulation using the generated AI.

[1805] The server integrates furniture information and property information.

[1806] The server inputs a prompt sentence into the generative AI model.

[1807] The server generates a simulation image using a generative AI model (e.g., DALL-E).

[1808] Input: Furniture information, property information

[1809] Output: Generated simulation image

[1810] Specific action prompt:

[1811] text

[1812] The living room measures 500cm x 600cm with a sofa (200cm long, 90cm wide, 80cm high) placed in the center.

[1813] Step 5:

[1814] The server performs emotion recognition using an emotion engine.

[1815] The server records the user's facial expressions and tone of voice while they are typing.

[1816] The server uses an emotion engine to analyze the user's emotional state.

[1817] Input: User's facial expression, tone of voice

[1818] Output: Recognized emotional state of the user

[1819] Specific behavior:

[1820] json

[1821] {

[1822] "emotion_state": "relaxed",

[1823] "confidence_score": 0.85

[1824] }

[1825] Step 6:

[1826] The server adjusts the simulation based on emotions.

[1827] The server sends new prompt sentences to the generative AI model if necessary based on the analysis results of the emotion engine.

[1828] The server again uses the generative AI model to generate simulated images that match the user's emotions.

[1829] Input: User's emotional state, initial simulation image

[1830] Output: Adjusted simulation image

[1831] Specific action prompt:

[1832] text

[1833] "Place plants around the sofa and use soft lighting to help users relax."

[1834] Step 7:

[1835] The server sends the generated image to the terminal and displays it.

[1836] The server sends the final simulation image to the terminal.

[1837] The terminal displays the received image to the user.

[1838] Input: Final simulation image

[1839] Output: Simulation image displayed on the terminal

[1840] Specific behavior:

[1841] json

[1842] {

[1843] "simulation_image_url": "https: / / example.com / generated_image.png"

[1844] }

[1845] Step 8:

[1846] Users fine-tune furniture arrangement

[1847] The user checks the generated image on the terminal.

[1848] Users can rearrange the furniture using the drag and drop function.

[1849] The terminal sends the new configuration information to the server.

[1850] The server runs the simulation again, generating and sending new images.

[1851] Input: User fine-tuning information

[1852] Output: Resimulated image

[1853] Specific behavior:

[1854] json

[1855] {

[1856] "new_furniture_position": {

[1857] "sofa": {

[1858] "x": 250,

[1859] "y": 150

[1860] }

[1861] }

[1862] }

[1863] Step 9:

[1864] The server provides a link to purchase the furniture.

[1865] The user checks the final simulation image.

[1866] Click on the new furniture link as needed to proceed with the purchase process.

[1867] Input: Final simulation image

[1868] Output: Furniture purchase link

[1869] Specific behavior:

[1870] json

[1871] {

[1872] "furniture_purchase_links": [

[1873] "https: / / furniturestore.com / product / sofa",

[1874] "https: / / furniturestore.com / product / table"

[1875] ]

[1876] }

[1877] (Application example 2)

[1878] 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."

[1879] For users considering moving, visualizing the exact layout of furniture in their new home can be a very troubling problem. It is also difficult to propose optimal interior design that takes into account the user's emotions and stress levels in addition to the furniture layout. Furthermore, the process for users to purchase the perfect furniture for their new home is complicated, resulting in an inconsistent overall moving experience.

[1880] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1881] In this invention, the server includes: means for incorporating furniture information using a generative AI model and combining it with property data to automatically generate an image of the room after moving in; means for transmitting furniture information entered by the user from the terminal to the server; means for acquiring detailed information about the property selected by the user and combining it with the furniture information to generate a simulation; and means for the server to use an emotion engine that recognizes the user's emotions by analyzing facial expressions and tone of voice to adjust the optimal furniture arrangement and interior design based on the emotions, transmit the generated simulation image to the terminal, and display it to the user. This allows the user to easily imagine the specific furniture arrangement in their new home and receive optimal interior design suggestions that take the user's emotions into consideration. It also makes the purchase of new furniture smoother, improving the overall moving experience.

[1882] A "generative AI model" is an artificial intelligence technology that generates a concrete image of the room the user will move into based on information about the furniture they own and the property they select.

[1883] "Furniture Information" means data about photos, dimensions, and other physical characteristics of furniture owned by a user.

[1884] "Property data" refers to detailed information about the property selected by the user, such as dimensions, layout, and interior photos.

[1885] An "emotion engine" is a technology that analyzes a user's facial expressions and tone of voice to recognize their emotions, and adjusts the generated simulation image based on that.

[1886] A "simulation image" is an image created using a generative AI model that visually shows the specific layout and arrangement of the room after moving in.

[1887] A "terminal" is a digital device such as a smartphone or computer that a user uses to input furniture information and display simulation images.

[1888] A "server" is a computer system that receives data sent by users, executes generative AI models and emotion engines, and generates and transmits simulation images.

[1889] "Furniture arrangement" refers to a layout that shows how furniture is arranged in a user's room.

[1890] The present invention is a system that generates a concrete image of the room after moving based on information about the furniture the user owns and the property they select, and also combines it with an emotion engine that recognizes the user's emotions. The operation of this system and specific examples are described below.

[1891] System Overview

[1892] The server uses a generative AI model to capture furniture information and combine it with property data to generate an image of the room. The furniture information entered by the user is sent from the device to the server. The server obtains detailed information about the property selected by the user and combines it with the furniture information to generate a simulation. The server also uses an emotion engine to recognize the user's emotions and suggests optimal furniture layout based on their emotions. This generated simulation image is sent to the device and displayed to the user.

[1893] Hardware and software used

[1894] Hardware:

[1895] Smartphones and PCs: Devices that allow users to input furniture information and display simulation images.

[1896] Server: Receives data, runs generative AI models and emotion engines, and generates and transmits simulation images.

[1897] software:

[1898] Generative AI model (e.g. FurnitureArrangementAI): AI technology that simulates optimal furniture arrangement based on furniture and property information.

[1899] Emotion engine (e.g., EmotionEngine): Recognizes the user's emotions by analyzing facial expressions and tone of voice.

[1900] Communication library (e.g. requests): A library for sending and receiving furniture information and simulation images.

[1901] Data processing and calculation

[1902] The main tasks performed by the server are:

[1903] 1. Receives furniture information input and stores it in a database. This uses image analysis algorithms to extract furniture dimensions and shapes and stores them along with text data.

[1904] 2. Property data acquisition: In this step, the server uses a RESTful API to obtain detailed property information such as dimensions, layout diagrams, and interior photos.

[1905] 3. Using a generative AI model, furniture information and property information are integrated to simulate optimal furniture placement.

[1906] 4. Analyze the user's emotions using an emotion engine. Specifically, analyze facial expressions and tone of voice in real time while the user is entering furniture and property information.

[1907] 5. Based on the results of the emotion engine, the generated simulation image is adjusted. If the user is feeling stressed, a placement suggestion to reduce stress is made.

[1908] 6. The final simulation image is sent to the terminal and displayed to the user.

[1909] Specific examples

[1910] A user uses their smartphone to take a photo of the sofa in their living room and upload it to the app. They also enter the sofa's dimensions (e.g., length 200 cm, width 90 cm, height 80 cm). The device sends this information to the server in JSON format. Based on the property ID selected by the user, the server retrieves detailed property information from the database. The generative AI model uses this information to simulate the optimal furniture arrangement for the living room. If the user is not satisfied with this simulated image, the emotion engine analyzes the user's emotions and suggests a new arrangement to, for example, reduce stress. The final image is displayed to the user, and a link to purchase new furniture is provided if necessary.

[1911] Prompt Sentence Examples

[1912] "Get the information you need for a moving simulator and use FurnitureArrangementAI and EmotionEngine to suggest room layouts that will help users relax."

[1913] In this way, users can easily visualize the specific arrangement of furniture in their new home and smoothly proceed with the entire moving process.

[1914] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1915] Step 1:

[1916] A user uses a smartphone to take a photo of the furniture in their living room and upload it to the app. They also enter the furniture's dimensions (e.g., length 200 cm, width 90 cm, height 80 cm). This is the device's input. The device converts the furniture information entered by the user into JSON format and sends it to the server.

[1917] Step 2:

[1918] The server decodes and stores the furniture information received from the device. Here, it uses an image analysis algorithm to extract the dimensions and shape of the furniture and records them in a database as text data. This is the server's data processing.

[1919] Step 3:

[1920] The user selects a property ID in the application. This is the terminal input. The terminal sends the selected property ID to the server. The server uses a RESTful API to retrieve detailed information such as the property dimensions, layout diagram, and interior photos from the database based on the received property ID. This is the server output.

[1921] Step 4:

[1922] The server inputs the acquired property information and the user's furniture information into a generative AI model (e.g., FurnitureArrangementAI). The generative AI model uses this information to simulate the optimal furniture arrangement and generate a simulation image. This is the server's data calculation.

[1923] Step 5:

[1924] The server uses an emotion engine (e.g., Emotion Engine) to analyze video of the user's facial expressions and tone of voice while they are entering furniture and property information. The emotion engine uses facial expression and voice analysis algorithms to recognize the user's emotional state and convert it into data. This is the server's data processing.

[1925] Step 6:

[1926] The server adjusts the generated simulation image based on the results of the emotion engine. Specifically, if the user is feeling stressed, it will suggest layout adjustments to reduce stress. For example, it will adjust the layout by changing the position of the lighting. This is the output of the server.

[1927] Step 7:

[1928] The server sends the final simulation image to the terminal, which then displays it to the user. This is the terminal's data output. The user can check the displayed simulation image and, if necessary, fine-tune the furniture placement using the drag-and-drop function.

[1929] Step 8:

[1930] If the user makes minor adjustments to the furniture placement, the device sends this information to the server, which then uses the generative AI model again to generate a new simulated image based on the adjusted information. This is the server's data calculation.

[1931] Step 9:

[1932] The final image is sent to the device and displayed to the user. If the user decides that they need new furniture, they click on the furniture purchase link displayed on the device. This is the user's output. The link will take them to the furniture store's website where they can purchase their new furniture.

[1933] 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.

[1934] 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.

[1935] 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.

[1936] 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.

[1937] 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.

[1938] 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.

[1939] 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).

[1940] 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.

[1941] 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."

[1942] 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.

[1943] 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).

[1944] 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.

[1945] 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.

[1946] 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.

[1947] 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.

[1948] 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.

[1949] 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.

[1950] 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.

[1951] 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.

[1952] 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.

[1953] 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.

[1954] The following is further disclosed regarding the above embodiment.

[1955] (Claim 1)

[1956] Using generative eye, furniture information is captured,

[1957] Combined with property data,

[1958] Automatically generate an image of the room after moving in

[1959] Means and

[1960] The furniture information entered by the user is sent from the device to the server.

[1961] Means and

[1962] Obtain detailed information about the property selected by the user,

[1963] Combine with furniture information to generate a simulation

[1964] Means and

[1965] The generated simulation image is sent to the terminal,

[1966] Visible to users

[1967] A system including a means.

[1968] (Claim 2)

[1969] Users can manually fine-tune the placement of furniture.

[1970] Based on the adjustment results, a simulation image is generated again.

[1971] Display on device

[1972] 10. The system of claim 1.

[1973] (Claim 3)

[1974] Based on the generated simulation image,

[1975] Provide a link for users to purchase the furniture

[1976] 10. The system of claim 1.

[1977] "Example 1"

[1978] (Claim 1)

[1979] means for capturing furniture information input by a user into a terminal;

[1980] A means for converting furniture information into a data format designated by a user and transmitting the converted information to a server;

[1981] A means for retrieving detailed information of a property selected by a user from a database;

[1982] A means of integrating the acquired furniture information and property information and generating a simulation using a generative AI model;

[1983] The system includes a means for converting the generated simulation image into an image format, transmitting it to a terminal, and displaying it to a user.

[1984] (Claim 2)

[1985] The system according to claim 1, wherein the user can manually fine-tune the furniture placement using a drag-and-drop function, and the system generates a new simulation image based on the results of the adjustments and displays it on the terminal.

[1986] (Claim 3)

[1987] The system of claim 1, further comprising a link for the user to purchase new furniture based on the generated final simulation image.

[1988] "Application Example 1"

[1989] (Claim 1)

[1990] Using generative AI models to capture furniture information,

[1991] Combined with property data,

[1992] Automatically generate an image of your living space after moving in

[1993] Means and

[1994] The furniture information entered by the user is sent from the device to the server.

[1995] Means and

[1996] Obtain detailed information about the property selected by the user,

[1997] Combine with furniture information to generate a simulation

[1998] Means and

[1999] The generated simulation image is sent to the terminal,

[2000] Visible to users

[2001] Means and

[2002] Providing a link for users to select and purchase new furniture in a virtual store

[2003] A system including a means.

[2004] (Claim 2)

[2005] Users can manually fine-tune the placement of furniture.

[2006] Based on the adjustment results, a simulation image is generated again.

[2007] Display on device

[2008] 10. The system of claim 1.

[2009] (Claim 3)

[2010] Based on the generated simulation image,

[2011] Providing a link for users to purchase new furniture from a virtual store

[2012] 10. The system of claim 1.

[2013] "Example 2: Combining Emotion Engines"

[2014] (Claim 1)

[2015] Using generative AI models to capture furniture information,

[2016] Combined with property data,

[2017] Automatically generate an image of the room after moving in

[2018] Means and

[2019] The furniture information entered by the user is sent from the device to the server.

[2020] Means and

[2021] Obtain detailed information about the property selected by the user,

[2022] Combine with furniture information to generate a simulation

[2023] Means and

[2024] The generated simulation image is sent to the terminal,

[2025] Visible to users

[2026] Means and

[2027] Uses an emotion engine to recognize user emotions,

[2028] Adjusting the simulation based on perceived emotional state

[2029] Means and

[2030] A system including:

[2031] (Claim 2)

[2032] Users can manually fine-tune the placement of furniture.

[2033] Based on the adjustment results, a simulation image is generated again.

[2034] Display on device

[2035] 10. The system of claim 1.

[2036] (Claim 3)

[2037] Based on the generated simulation image,

[2038] Provide a link for users to purchase the furniture

[2039] 10. The system of claim 1.

[2040] "Application example 2 when combining emotion engines"

[2041] (Claim 1)

[2042] Using generative AI models to capture furniture information,

[2043] Combined with property data,

[2044] Automatically generate an image of the room after moving in

[2045] Means and

[2046] The furniture information entered by the user is sent from the device to the server.

[2047] Means and

[2048] Obtain detailed information about the property selected by the user,

[2049] Combine with furniture information to generate a simulation

[2050] Means and

[2051] The server uses an emotion engine that analyzes facial expressions and tone of voice to recognize the user's emotions.

[2052] We adjust the furniture arrangement and interior based on your emotions.

[2053] The generated simulation image is sent to the terminal,

[2054] Visible to users

[2055] A system including a means.

[2056] (Claim 2)

[2057] Users can manually fine-tune the placement of furniture.

[2058] Based on the adjustment results, a simulation image is generated again.

[2059] Display on device

[2060] 10. The system of claim 1.

[2061] (Claim 3)

[2062] Based on the generated simulation image,

[2063] Provide a link for users to purchase the furniture

[2064] 10. The system of claim 1. [Explanation of symbols]

[2065] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:>...

Claims

1. Using generative eye, furniture information is captured, Combined with property data, Automatically generate an image of the room after moving in Means and The furniture information entered by the user is sent from the device to the server. Means and Obtain detailed information about the property selected by the user, Combine with furniture information to generate a simulation Means and The generated simulation image is sent to the terminal, Display to the user A system including a means.

2. Users can manually fine-tune the placement of furniture. Based on the adjustment results, a simulation image is generated again. Display on device The system of claim 1 .

3. Based on the generated simulation image, Provide a link for users to purchase the furniture The system of claim 1 .

Images