System

Abstract

A system is provided.SOLUTION: The system according to claim 1, further comprising: means for automatically generating a 3D floor plan model on the basis of the extracted information; scoring means for scoring the generated 3D floor plan model on the basis of a building standard and a building technique; and market exhibiting means for exhibiting a model which has acquired a predetermined score by the scoring means on a market in a digital space.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern home design, it is extremely difficult for consumers to reflect their own wishes and desires in a concrete floor plan model. Designs that include detailed floor plans, daily routines, family composition, and furniture placement require specialized knowledge, making them difficult for average consumers. Furthermore, even when users try to refer to other people's design examples, they face challenges due to differences in conditions and circumstances. Furthermore, there are no clear standards for assessing the feasibility and legal compliance of a designed model, making it difficult to confirm these in advance. The present invention aims to solve these problems by enabling users to easily generate realistic 3D floor plan models based on their own wishes and use them in a digital flea market. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. First, it provides a means for users to input their desired floor plan, furniture information, family composition, etc. in natural language. Next, it provides natural language processing means for analyzing the input natural language and extracting information. It also provides floor plan generation means for automatically generating a 3D floor plan model based on the extracted information. It also provides scoring means for scoring the generated 3D floor plan model based on building standards and construction technology. Finally, it provides a system that includes market exhibition means for exhibiting models that have achieved a certain score on a digital market, allowing users to easily create their own designs and share and trade those designs with others. This makes it possible to provide a system that allows even ordinary consumers to easily design, evaluate, and utilize detailed, realistic home models.

[0006] "Natural language" refers to the language used by humans in conversation and writing in everyday life, and the language used for communication between humans.

[0007] "Natural language processing" refers to the technologies and algorithms that allow computers to understand, analyze, and generate natural language.

[0008] A "3D floor plan model" refers to a computer-generated model that visually represents the internal structure and room layout of a building in three-dimensional space.

[0009] "Scoring" refers to assigning a score to an object based on specific criteria or rules, and in this case it means evaluating the realism and legality of the generated 3D floor plan model.

[0010] A "digital flea market" refers to an online marketplace where design models and digital content can be traded over the Internet.

[0011] "Users" refers to consumers and designers who use this system to generate and exhibit floor plan models.

[0012] "Floor plan generation means" refers to software or algorithms that automatically design floor plans based on the wishes and conditions entered by the user.

[0013] "Market exhibiting means" refers to the functions and procedures for posting the generated 3D floor plan model on an online digital marketplace so that other users can view and purchase it.

[0014] "Analysis" refers to breaking down input data or information, understanding its meaning and structure, and extracting the necessary elements.

[0015] The Building Standards Act is a law that sets out certain standards and rules for the design and construction of buildings, and refers to regulations to ensure the safety and livability of buildings. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention relates to a system that automatically generates a 3D floor plan model based on a user's desired floor plan, furniture information, family composition, etc. using natural language, and the realistic model is scored and can be exhibited on a digital flea market. This system allows users to easily design floor plans and provides technology that allows them to share and trade those designs with others.

[0038] System program description

[0039] Accepting input in natural language

[0040] Users access the system's interface and input their desired floor plan, family composition, details of household items, etc. in natural language. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the children."

[0041] natural language analysis

[0042] The server receives natural language requests submitted by users and then uses natural language processing (NLP) techniques to analyze this input and extract information such as specific floor plans, furniture arrangements, and family composition.

[0043] Generate 3D floor plan models

[0044] The server designs a 3D floor plan model based on the extracted elements. For example, it lays out an open space connecting the living room and kitchen, and arranges bedrooms and bathrooms suitable for a family of three. It then extracts the necessary furniture (sofa, dining table, children's desk) from the database and places them in the appropriate locations. Finally, it uses 3D rendering technology to generate a visually checkable 3D model.

[0045] Scoring

[0046] The server then scores the generated 3D model based on building codes and current building technology, including evaluation of ceiling height, seismic standards, energy efficiency, etc. Based on the evaluation, a score is assigned.

[0047] Exhibiting at the Digital Flea Market

[0048] Users can check the scoring results and choose whether or not to exhibit the generated model on the digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by home builders, construction companies, and custom homeowners. Models that do not meet a certain score may be used in other industries (such as the gaming industry).

[0049] Specific examples

[0050] For example, if a user inputs the desired floor plan as "a layout for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," the server first analyzes this input. Through analysis, the following are extracted: "family of four," "combined living room and dining kitchen," and "furniture: large dining table, sofa, and study desk."

[0051] The server then uses this information to generate a 3D floor plan model, designing four bedrooms, a combined living / dining / kitchen area, and furniture arrangements. This model is then rendered in 3D and presented to the user visually.

[0052] The server then evaluates the generated model to see if it complies with building codes and assigns it a technical score. If the score is high, the user can then put the model up on a digital flea market where other consumers and businesses can view and purchase it.

[0053] This system allows users to easily generate 3D floor plan models that meet their needs and then use and share the results on a digital flea market.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] Users access the interface and use natural language to input their desired floor plan, family composition, number of furniture pieces, etc. into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs include a sofa, dining table, and desk for the children."

[0057] Step 2:

[0058] The server receives the input natural language data.

[0059] Step 3:

[0060] The server uses a natural language processing (NLP) engine to analyze the received natural language data, specifically by performing grammar analysis, word tokenization, and context understanding.

[0061] Step 4:

[0062] The server extracts important information from the results of natural language analysis, such as the floor plan, family composition, and the type and number of furniture. For example, it extracts elements such as "living room and kitchen combined," "family of three," and "furniture: sofa, dining table, children's desk."

[0063] Step 5:

[0064] The server then uses the extracted information to automatically generate a 3D floor plan model. First, it designs the basic layout of the floor plan. This involves determining how the living room and kitchen will be connected, and planning the layout of the three bedrooms.

[0065] Step 6:

[0066] The server references a database of pre-placed rooms and furniture and selects appropriate furniture and room layouts based on the extracted information: specifically, placing a sofa in the living room, a dining table in the kitchen area, and a children's desk in the children's room.

[0067] Step 7:

[0068] The server uses a 3D rendering engine to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0069] Step 8:

[0070] The server then scores the generated 3D model based on building standards and construction techniques, such as minimum ceiling height, earthquake resistance standards, and energy efficiency.

[0071] Step 9:

[0072] The server generates an evaluation report based on the scoring results and sends it to the user, who can then check the feasibility and legal compliance of the model.

[0073] Step 10:

[0074] Users can review the scoring results and choose whether or not to exhibit the generated 3D model on a digital flea market.

[0075] Step 11:

[0076] If a user wishes to exhibit their 3D model, the server will post it on the digital market, making it available for viewing and purchase by home builders, construction companies, and owners of custom homes.

[0077] Step 12:

[0078] The server will then separately post the low scoring models on a digital marketplace for use in other industries (e.g., the gaming industry).

[0079] In this way, the system allows users to easily define their desired floor plan, visualize it as a 3D model, evaluate it, and leverage it in the appropriate market.

[0080] Example 1

[0081] 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."

[0082] Modern society demands user-friendly and efficient home designs, which require flexible floor plan designs that can accommodate a wide variety of needs. However, it is difficult for ordinary users without specialized knowledge to design floor plans themselves, and there are limited means for sharing and trading the results with others. To solve this problem, a system is needed that easily realizes users' wishes, evaluates the designs, and automates the entire process of exhibiting them on the market.

[0083] 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.

[0084] In this invention, the server includes: means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; means for analyzing natural language and extracting information; means for automatically generating 3D floor plan models based on the extracted information; means for scoring the generated 3D floor plan models based on building standards and building techniques; means for exhibiting models that have achieved a certain score on a market in a digital space; and means for a user to select an exhibit and for making the exhibited model data available for viewing and trading in the digital space. This enables users to easily generate 3D floor plan models that meet their needs and share and trade the results with others.

[0085] "User" refers to an individual who operates the system to design floor plans and input furniture information.

[0086] "Natural language" refers to a language that is commonly used by humans, and in this case refers to a language that a user uses to input their preferences.

[0087] "Floor plan" refers to the arrangement and configuration of rooms and spaces within a building.

[0088] "Furniture information" refers to detailed information about the furniture to be arranged in the floor plan.

[0089] "Family composition" refers to the number of family members and their relationships within the user's household.

[0090] "Input means" refers to the means by which a user uses natural language to input the desired floor plan, furniture information, family composition, etc.

[0091] "Natural language processing means" refers to technology or systems for analyzing input natural language and extracting necessary information.

[0092] "Floor plan generation means" refers to a system for automatically generating a 3D floor plan model based on the extracted information.

[0093] "3D floor plan model" refers to a three-dimensional digital model of the floor plan generated based on the extracted information.

[0094] "Scoring means" refers to a system for evaluating the generated 3D floor plan model based on certain criteria and assigning a score.

[0095] "Market exhibiting means" refers to a system that allows scored models to be exhibited on a digital marketplace, making them available for viewing and trading.

[0096] "Digital market" refers to a platform provided over the Internet for trading designed 3D models.

[0097] "Construction contractor" refers to a company or individual that designs and constructs buildings.

[0098] A "custom homeowner" refers to an individual who places an order to have a home built based on their own requirements.

[0099] This invention is a system that automatically generates a 3D floor plan model based on a user's natural language input of the desired floor plan, furniture information, family composition, etc., and then scores the model before displaying it at a digital flea market. The main components of this system include an input means, a natural language processing means, a floor plan generation means, a scoring means, and a market exhibition means.

[0100] Users input their desired floor plan, furniture information, family composition, etc. in natural language through the system interface. For example, a user might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the children."

[0101] In the natural language processing means, the server receives input data sent by the user. This data is received by the server's API gateway and then passed to the natural language processing engine. An NLP tool, for example, is used as a natural language processing technology. This analyzes the input natural language and extracts specific elements such as "an open space connecting the living room and kitchen," "a family of three," and "furniture: sofa, dining table, and children's desk."

[0102] The floor plan generation method generates a 3D floor plan model based on the data analyzed by the server. In this process, the server searches the database for appropriate furniture and floor plan templates, and then models them using 3D modeling software such as Blender or SketchUp. The system automatically designs room arrangements and floor plan layouts based on family composition, and generates a 3D model that users can visually check. For example, a layout such as "an open space connecting the living room and kitchen," "a bedroom suitable for a family of three," or "a sofa placed in the center of the living room" may be created.

[0103] In the scoring method, the server scores the generated 3D floor plan model. For this, evaluation criteria such as ceiling height, earthquake resistance standards, and energy efficiency are used, and a scoring algorithm is executed. Evaluation criteria refer to, for example, LEED and CASBEE standards. As a specific example of scoring, the model is scored based on evaluation items such as "high energy efficiency," "earthquake resistance," and "a lot of natural light."

[0104] In the market exhibiting method, the user checks the scoring results provided by the server and chooses whether to exhibit the generated model on the digital flea market. If the user wishes to exhibit, the server uploads the 3D model data to the market in the digital space, where it can be viewed and traded. As a specific example, a scenario can be considered in which the user checks the evaluation results and decides to exhibit the model after confirming that it has a high score.

[0105] A concrete example of a prompt might be the following natural language input:

[0106] "I want an open layout with a connected living room and kitchen. It's for a family of three, and the furniture needs to be a sofa, a dining table, and a desk for the kids."

[0107] "The floor plan for a family of four is an integrated living room and dining kitchen. The furniture needs include a large dining table, sofa, and study desk."

[0108] This system allows users to easily generate 3D floor plan models that meet their needs, even without specialized knowledge, and then share and trade those models with others.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] Users input information such as floor plan, furniture, and family composition in natural language through the system interface, via a text area in a web browser or mobile app.

[0112] Example: "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the kids."

[0113] Output of this step: Natural language input data.

[0114] Step 2:

[0115] The server receives the input data sent by the user and passes it to a natural language processing engine. NLP technology is used to analyze the input data and extract specific floor plan elements, furniture information, family composition, and other information.

[0116] Examples of software used: NLP tools (e.g., Google Cloud Natural Language API) as natural language processing engines.

[0117] Input: "I want an open plan with a living room and kitchen connected to each other. It will accommodate a family of three, and the furniture will need to include a sofa, a dining table, and desks for the kids."

[0118] Output of this step: Analysis results (element extraction data) "Living room and kitchen", "Family of three", "Furniture: sofa, dining table, children's desk".

[0119] Step 3:

[0120] The server generates a 3D floor plan model based on the extracted information, searches for appropriate furniture and floor plan templates in a database, and creates the model using 3D modeling software.

[0121] Hardware and software used: 3D modeling software (e.g. Blender, SketchUp).

[0122] Specific actions: Open space connecting the living room and kitchen, bedrooms suitable for a family of three, bathrooms, and furniture (sofa, dining table, children's desk) properly arranged.

[0123] Input for this step: Element extraction data.

[0124] Output of this step: 3D floor plan model.

[0125] Step 4:

[0126] The server scores the generated 3D floor plan model, using criteria such as ceiling height, earthquake resistance standards, and energy efficiency. A unique scoring algorithm is run to assign a score.

[0127] Criteria and tools used: Scoring tools based on LEED and CASBEE standards.

[0128] Input for this step: 3D floor plan model.

[0129] Output of this step: Scoring result (assigned score).

[0130] Step 5:

[0131] The user checks the scoring results provided by the server and chooses whether or not to exhibit the generated model on the digital flea market. If the user wishes to exhibit, the server uploads the 3D model data to the market in the digital space. Exhibited models can be viewed and traded by construction companies and owners of custom-built homes.

[0132] Specific operation: Click the "Exhibit" button displayed on the interface, and the server will upload the model data.

[0133] Inputs for this step: Scoring results, user selection.

[0134] Output of this step: a 3D model published on a digital marketplace.

[0135] In this way, this system generates 3D floor plan models from user input and automates the process of evaluating and exhibiting those models, making it easy for users to design floor plans and share and trade the results.

[0136] (Application example 1)

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

[0138] Currently, designing homes and interiors requires a high level of specialized knowledge, making it difficult for average users to easily design floor plans and consider furniture arrangements based on their own preferences. However, a system that automatically generates 3D floor plan models by simply inputting users' preferences and requirements in natural language, and then evaluates and visualizes the models and exhibits them on a digital flea market would be useful. This system would allow users to easily design floor plans and share and trade them with others, greatly simplifying the design process.

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

[0140] In this invention, the server includes: means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; floor plan generation means for automatically generating 3D floor plan models based on the extracted information; scoring means for scoring the generated 3D floor plan models based on building standards and building techniques; means for visually displaying the generated 3D floor plan models in a digital space; means for a user to review and make a decision on models that have received a certain score by the scoring means; and market exhibition means for exhibiting the models reviewed and decided upon by the user in a market in the digital space. This enables users to easily design floor plans and furniture arrangements based on their own preferences, evaluate and visualize the designs, and exhibit them in a flea market.

[0141] "Natural language processing means" is a technology for analyzing natural language sentences entered by users and extracting meaning and information.

[0142] A "3D floor plan model" refers to a design drawing visualized in three-dimensional space based on information such as the user's desired floor plan and furniture placement.

[0143] The "scoring method" is a method for evaluating whether the generated 3D floor plan model complies with building standards and construction techniques, and assigning a score.

[0144] The "market exhibit method" is a method of posting 3D floor plan models that have received a certain score on a digital marketplace, allowing other users and businesses to view and purchase them.

[0145] "Visual display means" refers to technology that displays the generated 3D floor plan model on the screen of a digital device, allowing users to check and consider it in real time.

[0146] "Means that allow users to consider and make decisions" refers to a means by which users can review the scored 3D model and decide whether or not to adopt it.

[0147] The present invention relates to a system that allows users to input their desired floor plan, furniture information, family composition, etc. using natural language, and then automatically generates a 3D floor plan model based on that information, scores it, and exhibits it on a digital flea market.

[0148] The system is implemented using the following hardware and software:

[0149] Hardware: smartphones, tablets, servers

[0150] Software: Python, Flask (web framework), natural language processing library (e.g. spaCy), 3D modeling library (e.g. Three.js)

[0151] The server first receives a request sent in natural language by the user. Specifically, the user inputs the desired floor plan, furniture information, family composition, etc. in natural language. For example, the user might input, "A spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk."

[0152] The server then uses natural language processing technology to analyze this input and extract information such as the specific floor plan, furniture layout, and family composition. This information is then used to generate a 3D floor plan model. The 3D model generated at this stage is then laid out based on the user's preferences, such as an open kitchen or a living room layout suitable for a family of four.

[0153] The generated 3D floor plan model is then scored based on building standards and construction techniques. For example, earthquake resistance standards and energy efficiency are evaluated, and a score is assigned based on the evaluation results. After viewing the scoring results, users can then choose whether or not to exhibit the generated model on the digital flea market.

[0154] Visually, the generated 3D model is displayed in real time on the screen of a smartphone or tablet, allowing users to inspect the model in detail, making it easy to consider whether the floor plan and furniture arrangement are exactly as they wanted.

[0155] Finally, the 3D model that the user has considered and decided on will be exhibited on a digital flea market, where other users and vendors can view and purchase it. Models that do not meet a certain score may be used in other fields (such as games or education).

[0156] As a concrete example:

[0157] If a user wants a floor plan and furniture arrangement for a family of four,

[0158] Users input "A spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk as furniture." The server analyzes this input and extracts the elements of a family of four, a spacious living room, an open kitchen, a sofa, a dining set, and a study desk. A 3D floor plan model is generated based on these elements and scored based on architectural standards. Based on the evaluation results, users can exhibit the model at a flea market.

[0159] Example prompts for generative AI models

[0160] "We are looking for a floor plan and furniture arrangement for a family of four. It should have a large living room and an open kitchen. The furniture should include a sofa, dining set, and study desk. Please generate and score appropriate 3D models."

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] Using a smartphone or tablet, the user inputs details such as the desired floor plan, furniture, and family composition in natural language. For example, they might input "a spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk." The input natural language is sent to the system.

[0164] Input: Natural language request

[0165] Output: Send data to the server

[0166] Step 2:

[0167] The server analyzes the received natural language input, using natural language processing (NLP) techniques to parse the input sentences and extract the necessary information (e.g., family composition, floor plan type, required furniture items).

[0168] Input: Natural language input data

[0169] Output: Extracted information (family composition, floor plan, furniture information)

[0170] Step 3:

[0171] The server generates a 3D floor plan model based on the extracted information. Specifically, it uses 3D modeling technology to automatically create a floor plan design, including an open kitchen, living room, furniture arrangement, and more, and creates a 3D model that can be visually confirmed.

[0172] Input: Extracted information

[0173] Output: 3D floor plan model

[0174] Step 4:

[0175] The server then scores the generated 3D floor plan model based on building standards and construction techniques. In this step, scores are assigned using evaluation criteria such as earthquake resistance standards and energy efficiency to evaluate the quality of the model.

[0176] Input: 3D floor plan model

[0177] Output: Scoring results

[0178] Step 5:

[0179] The server then uses a means to visually display the scoring results and displays the 3D model to the user, allowing the user to check and consider their desired floor plan and furniture arrangement in real time.

[0180] Input: Scoring results, 3D model

[0181] Output: 3D model displayed on a smartphone or tablet

[0182] Step 6:

[0183] Users review the generated 3D model and its scoring results and decide whether to exhibit it in the digital flea market. The results of their decision are sent to the system.

[0184] Input: User decision

[0185] Output: Sending data to the system

[0186] Step 7:

[0187] The server will display the models that users have decided to exhibit in a digital flea market. Models that do not meet a certain score may be used in other fields (such as games or education).

[0188] Input: The model that the user has decided to exhibit

[0189] Output: Exhibit at the digital flea market

[0190] 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.

[0191] This invention relates to a system that automatically generates a 3D floor plan model based on a user's desired floor plan, furniture information, family composition, etc., input in natural language, and then combines it with an emotion engine that recognizes the user's emotions to adjust the model according to the user's emotional state. This system allows users to easily design floor plans and provides technology that allows the model to adapt to the user's mood and emotions.

[0192] System program description

[0193] Accepting input in natural language

[0194] Users access the interface and input their desired floor plan, family composition, number of furniture, etc. in natural language into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desk for the children." At this time, the system also inputs the user's tone of voice and emotions from the text.

[0195] Natural Language Analysis and Emotion Recognition

[0196] The server receives the input natural language and emotion data. It uses a natural language processing (NLP) engine to analyze the input sentences and extract information such as the specific floor plan, furniture layout, and family composition. At the same time, the emotion engine analyzes the user's text and tone of voice and classifies them into positive, negative, or neutral emotion categories.

[0197] 3D floor plan model generation and emotional feedback

[0198] The server then begins the process of generating a 3D floor plan model based on the extracted information and emotion recognition results. First, it designs a basic floor plan layout, for example, laying out an open space connecting the living room and kitchen, and arranging three bedrooms. It also appropriately adjusts the model's design, color, and atmosphere based on the emotion recognition results. For example, if the user is in a positive emotional state, it may use more brightly colored interiors, and if they are in a negative emotional state, it may choose more subdued colors.

[0199] 3D rendering

[0200] The server uses 3D rendering technology to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0201] Scoring

[0202] The server evaluates whether the generated 3D model complies with building standards and construction techniques, and assigns a technical score. The emotion recognition results of the emotion engine are also fed back into the scoring, affecting the score. For example, if the user is very satisfied, the score may be slightly increased.

[0203] Exhibiting at the Digital Flea Market

[0204] Users can check the scoring results and choose whether or not to exhibit the generated model on the digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by home builders, construction companies, and custom homeowners. Models that do not meet a certain score may also be used in other industries (such as the gaming industry).

[0205] Specific examples

[0206] For example, if a user inputs "A floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," while speaking in an extremely cheerful tone, the server will first analyze this input. The analysis will extract "family of four," "combined living room and dining kitchen," and "furniture: large dining table, sofa, study desk," and the emotion engine will recognize positive emotions.

[0207] The server then uses this information to generate a 3D floor plan model and designs an open space connecting the living room and kitchen. Based on the emotion recognition results, the server adjusts the design to match positive emotions, using a lot of bright interior colors.

[0208] The server then evaluates the generated model to see if it complies with building standards, and assigns a score based on both technical and emotional evaluations. If the model receives a high rating, the user can then exhibit it on a digital flea market, where it can be viewed and purchased by other consumers and businesses.

[0209] In this way, this system allows users to easily generate 3D floor plan models that meet their needs and share them in a digital flea market. Furthermore, by combining this with an emotion engine to analyze users' emotions, the system can generate models that are more satisfying and adapt to the user's emotional state.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] Users access the interface and use natural language to input their desired floor plan, family composition, number of furniture, etc. into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desk for the children."

[0213] Step 2:

[0214] The server receives the input natural language data.

[0215] Step 3:

[0216] The server uses a natural language processing (NLP) engine to analyze the received natural language data, specifically by performing grammar analysis, word tokenization, and context understanding.

[0217] Step 4:

[0218] The server extracts important information from the results of natural language analysis, such as the floor plan, family composition, and the type and number of furniture. For example, it extracts elements such as "living room and kitchen combined," "family of three," and "furniture: sofa, dining table, children's desk."

[0219] Step 5:

[0220] The emotion engine recognizes the user's emotions from the text and voice input, for example by analyzing the style of the text, the words used, and the tone and tone of the voice, and classifies the user's emotions as positive, negative, or neutral.

[0221] Step 6:

[0222] The server then begins the process of generating a 3D floor plan model based on the extracted information and the recognized emotion data. First, it designs the basic floor plan layout. Here, it determines the layout of the living room and kitchen, and also plans the layout of the three bedrooms.

[0223] Step 7:

[0224] The server adjusts the model's design elements based on the emotion data, specifically selecting bright interior colors for positive emotions and muted colors for negative emotions.

[0225] Step 8:

[0226] The server references a database of pre-placed rooms and furniture and selects appropriate furniture and room layouts based on the extracted information: specifically, placing a sofa in the living room, a dining table in the kitchen area, and a children's desk in the children's room.

[0227] Step 9:

[0228] The server uses a 3D rendering engine to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0229] Step 10:

[0230] The server scores the generated 3D model based on building standards and construction techniques. Specifically, it evaluates and assigns a score to minimum ceiling height, earthquake resistance standards, energy efficiency, etc. Emotion recognition results are also fed back into the scoring process, affecting the score.

[0231] Step 11:

[0232] The server generates an evaluation report based on the scoring results and sends it to the user, who can then check the feasibility and legal compliance of the model.

[0233] Step 12:

[0234] Users can review the scoring results and choose whether or not to exhibit the generated 3D model on a digital flea market.

[0235] Step 13:

[0236] If a user wishes to exhibit their 3D model, the server will post it on the digital market, making it available for viewing and purchase by home builders, construction companies, and owners of custom homes.

[0237] Step 14:

[0238] The server will then separately post the low scoring models on a digital marketplace for use in other industries (e.g., the gaming industry).

[0239] In this way, the system allows users to easily define their desired floor plan and visualize it as an emotionally tailored 3D model, allowing them to evaluate the model and deploy it in the appropriate market.

[0240] Example 2

[0241] 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."

[0242] Existing floor plan design systems have the problem that users need specialized knowledge to input their specific preferences, making intuitive operation difficult. Furthermore, it is difficult to create designs that reflect the user's emotions and preferences, which prevents satisfaction from being increased. Furthermore, there are issues with the time-consuming and labor-intensive process of evaluating the quality and suitability of the generated models and releasing them to the market.

[0243] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input desired spatial layout, interior information, household configuration, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; emotion recognition means for recognizing emotions from the tone and text of the user's input; model generation means for automatically generating a 3D spatial layout model based on the extracted information and emotion recognition results; scoring means for scoring the generated 3D spatial layout model based on building standards and technical requirements; and market exhibition means for exhibiting models that have achieved a certain score by the scoring means on a market in a digital space. This allows users to intuitively input their desires in natural language and easily generate, evaluate, and exhibit 3D models that match their emotions on a market.

[0244] A "user" is an entity that uses the system to input information such as desired spatial layout, interior design information, and household configuration in natural language.

[0245] "Natural language" is language used by humans on a daily basis, as opposed to formal program code.

[0246] "Desired spatial arrangement" refers to the layout or arrangement of buildings or rooms desired by the user.

[0247] "Interior information" refers to information about furniture and decorations, and is related to the atmosphere and functionality of a space.

[0248] "Family composition" refers to information such as the number of family members and their age groups.

[0249] "Natural language processing means" refers to technology or equipment that analyzes natural language input by a user and extracts related information.

[0250] An "emotion recognition means" is a technology or device that analyzes emotions from the tone and text content of a user's input and classifies them as positive, negative, neutral, etc.

[0251] "Model generation means" refers to a technology or device that automatically generates a three-dimensional spatial layout model based on the extracted information and emotion recognition results.

[0252] A "3D spatial layout model" is a model that represents the layout and interior of an actual building or room in a three-dimensional visual format.

[0253] A "scoring means" is a technology or device that evaluates whether the generated 3D spatial layout model complies with building standards and technical requirements and assigns a score.

[0254] "Market exhibiting means" refers to a technology or device that exhibits models that have earned a certain score in the digital marketplace, allowing other users and businesses to view and purchase them.

[0255] A "digital market" is a virtual market built on the Internet where 3D models and other items are bought and sold.

[0256] "Technical requirements" are requirements based on specific technical standards or laws and regulations.

[0257] "Tone of input" refers to the pitch and emotion of the voice used when a user inputs information by voice.

[0258] The present invention relates to a system that automatically generates a 3D spatial layout model based on a user's desired spatial layout, interior information, family composition, etc., input in natural language, and further combines it with an emotion engine that recognizes the user's emotions to make adjustments according to the user's emotional state.

[0259] This system is implemented by the following procedure.

[0260] First, the user accesses the interface and inputs their desired spatial layout, interior information, and family composition in natural language into a chat-style input screen. For example, they can input specific requests such as, "I'd like a floor plan with an integrated living room and dining kitchen. It's for a family of four, and I need a large dining table, sofa, and study desk." At this time, the system also inputs the user's tone of voice and emotions from the text.

[0261] The server then receives the input natural language data and analyzes the user's input using a natural language processing (NLP) engine (e.g., GPT-3 or BERT). This extracts information from the input, such as the specific floor plan, furniture layout, and family composition. At the same time, an emotion engine analyzes the user's text and tone of voice and classifies them into positive, negative, or neutral emotion categories.

[0262] The server then begins the process of generating a 3D spatial layout model based on the extracted information and emotion recognition results. First, it designs a basic floor plan, creating an open space connecting the living room and kitchen, for example, and then appropriately arranges the necessary furniture. It also adjusts the model's design, color, and atmosphere based on the emotion recognition results. If the user is in a positive emotional state, it uses a lot of bright interior colors, and if they are in a negative state, it chooses calm colors.

[0263] Furthermore, the server generates a 3D model of the designed floor plan and furniture arrangement using 3D rendering technology (e.g., Blender or Unity), which is provided to the user for visual confirmation.

[0264] The server evaluates whether the generated 3D model complies with building standards and technical requirements, and assigns a technical score. The emotion recognition results of the emotion engine are also taken into account in the evaluation. For example, if the user is very satisfied, the score will be slightly increased.

[0265] Finally, the user reviews the scoring results and chooses whether to exhibit the generated model on a digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by builders, interior decorators, and homeowners. Models that do not meet a certain score may also be used in other industries (e.g., the gaming industry).

[0266] For example, if a user enters the following statement in a very positive tone of voice: "We would like a floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," the server analyzes this and extracts the following information: "Family of four," "Combined living room and dining kitchen," "Large dining table," "Sofa," and "Study desk." The emotion engine recognizes positive emotions. Based on this information, the server creates a 3D model of an open space with a connected living room and kitchen, featuring a brightly colored interior. The server then evaluates this model for compliance with building codes and assigns a high score, reflecting the user's high satisfaction. If the model receives a high rating, it will be exhibited on a digital flea market, where it can be viewed and purchased by other consumers and businesses.

[0267] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0268] Step 1:

[0269] Users access the interface and input their desired spatial layout, interior information, and family composition using natural language.

[0270] Specifically, the user inputs a prompt statement into the terminal such as, "I would like a layout with a combined living room and dining kitchen. It is for a family of four and requires a large dining table, sofa, and study desk."

[0271] Input: User-entered text data

[0272] Output: Sends input text data to the server

[0273] Step 2:

[0274] The server receives the natural language data sent from the terminal.

[0275] Input: Text data received from the user

[0276] Output: Prepare the data for input to the natural language processing engine

[0277] Step 3:

[0278] The server runs a natural language processing (NLP) engine to parse the user's input.

[0279] Specifically, it uses an NLP engine (e.g., GPT-3 or BERT) to analyze the input sentence.

[0280] Input: User-entered text data

[0281] Output: Analyzed information (e.g., floor plan, furniture, family composition)

[0282] Step 4:

[0283] The server uses an emotion engine to analyze the user's text content and tone of voice to recognize emotions.

[0284] Specific actions are classified into positive, negative, and neutral emotional categories.

[0285] Input: User text data and tone of voice

[0286] Output: Emotion recognition result

[0287] Step 5:

[0288] The server starts the process of generating a 3D spatial layout model based on the extracted information and emotion recognition results.

[0289] Specifically, the task involves designing a basic floor plan and properly arranging the necessary furniture.

[0290] Input: Parsed information and emotion recognition results

[0291] Output: Initial 3D spatial layout model

[0292] Step 6:

[0293] The server adjusts the design and color of the 3D model based on the emotion recognition results.

[0294] Specifically, when you are in a positive emotional state, you should use bright colors in your interior, and when you are in a negative emotional state, you should choose calm colors.

[0295] Input: Initial 3D spatial layout model and emotion recognition results

[0296] Output: Emotionally adjusted 3D spatial layout model

[0297] Step 7:

[0298] The server uses 3D rendering technology to generate a 3D model of the designed floor plan and furniture arrangement.

[0299] Specifically, the process involves generating a visual model using 3D modeling software (e.g., Blender or Unity).

[0300] Input: Adjusted 3D spatial layout model

[0301] Output: A finished 3D rendered model

[0302] Step 8:

[0303] The server evaluates whether the generated 3D model complies with building standards and technical requirements and assigns it a score.

[0304] Specifically, it uses a scoring algorithm to evaluate the score and adds emotional evaluation to the technical score.

[0305] Input: A completed 3D rendered model

[0306] Output: Scoring results

[0307] Step 9:

[0308] The user checks the scoring results and decides whether or not to exhibit the generated model on a digital flea market.

[0309] Specifically, the user checks the score through the interface and clicks the "Submit" button.

[0310] Input: Scoring results

[0311] Output: Digital Flea Market exhibit request

[0312] Step 10:

[0313] The server receives the exhibition request and posts the generated model on the digital market.

[0314] Specifically, the model is registered in the digital market database, making it available for other users and vendors to view and purchase.

[0315] Input:Exhibition request

[0316] Output: Model listing on the digital market

[0317] (Application example 2)

[0318] 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."

[0319] Modern users demand efficient interior and layout design for brick-and-mortar stores and adjustments based on their emotions. However, conventional methods require time and effort to change or adjust the design, making it difficult to achieve adaptive designs that reflect the user's emotional state. Furthermore, the scope and usability of the generated designs are limited, and it is also time-consuming to verify that they comply with building regulations.

[0320] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; a natural language processing means for analyzing the input natural language and extracting information; a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information; an emotion identification means for analyzing the user's emotions and adjusting the 3D floor plan model based on the user's emotional state; a scoring means for scoring the generated 3D floor plan model based on building standards and construction techniques; a market exhibiting means for exhibiting models that have achieved a certain score by the scoring means on a market in a digital space; and a means for generating and sharing 3D models for proposing interior and layout designs for physical stores. This allows users to easily generate 3D floor plan models that reflect their desired emotional state and confirm designs that comply with building standards. Furthermore, the system streamlines interior design proposals for physical stores and allows 3D models to be shared and purchased, enabling the creation and utilization of more effective and adaptive designs.

[0321] A "user" is someone who designs the interior and layout of a physical store and generates a 3D floor plan model based on that design.

[0322] "Natural language" is a means by which users input their desired floor plan, furniture information, family composition, etc., and is a language that is used on a daily basis.

[0323] "Natural language processing means" refers to technical means for analyzing input natural language and extracting information.

[0324] The "floor plan generation means" is a technical means for automatically generating a 3D floor plan model based on the extracted information.

[0325] The "emotion identification means" is a means for analyzing the user's emotions and adjusting the 3D floor plan model based on the user's emotional state.

[0326] The "scoring method" is a method for evaluating the generated 3D floor plan model based on building standards and construction techniques and assigning a score.

[0327] "Market exhibiting means" refers to a means for exhibiting models that have achieved a certain score on a market in the digital space.

[0328] "Digital space" refers to markets and platforms in virtual spaces such as the Internet.

[0329] A "physical store" is a store that exists in a physical space and provides goods and services.

[0330] "Layout" refers to the arrangement and design of equipment, furniture, decorations, etc. within a store.

[0331] A "3D floor plan model" is a digital model that visually reproduces the interior and layout of a store in three-dimensional space.

[0332] "Emotional state" is the result of analyzing the user's psychological state and mood.

[0333] As an embodiment of this invention, a system for proposing interior and layout designs for brick-and-mortar stores is described below. This system allows users to input their desired interior and layout designs in natural language, generates a 3D floor plan model based on this, and then uses emotion recognition means to make adjustments according to the user's emotional state. The generated model is evaluated using scoring means based on building standards and construction techniques, and can be exhibited on a digital market.

[0334] The system uses the following major hardware and software:

[0335] 1. Device:

[0336] Smartphone or tablet: A device that allows users to input their desired floor plan in natural language.

[0337] Server: Performs data analysis, model generation, emotion identification, and scoring.

[0338] 2. Software:

[0339] Natural language processing engines (e.g., BERT model from Hugging Face Transformers):

[0340] Analyzes the input natural language and extracts the necessary information.

[0341] Sentiment Identification Engine (e.g. nlptown / bert-base-multilingual-uncased-sentiment):

[0342] Analyzes the user's emotional state and classifies it as positive, negative, or neutral.

[0343] 3D Rendering Engine:

[0344] A 3D floor plan model is generated based on the extracted information.

[0345] Rating and Scoring Engine:

[0346] The generated model is evaluated based on building standards and technology and a score is assigned.

[0347] System Operation

[0348] The server receives a means for users to input their desired floor plan, furniture information, family composition, etc. in natural language using a smartphone or tablet. For example, a user might input, "I want the interior of the cafe to have a woody style, and I want it to have a bright atmosphere." This input is first sent to the server and analyzed by a natural language processing engine.

[0349] Next, the emotion recognition engine analyzes the emotional state of the text entered by the user and classifies it as positive, negative, or neutral. In this example, the user wants to emphasize a positive mood, so the emotion is classified as positive.

[0350] The 3D rendering engine then generates a 3D floor plan model that reflects the desired layout and interior design based on the analyzed information and the results of emotion identification. Based on a positive emotional state, the space is designed using woody materials and bright colors.

[0351] The generated 3D floor plan model is then scored by an evaluation and scoring engine based on building standards and technology, which determines whether the model complies with building standards and its market value.

[0352] Finally, users can post their scored models on a digital marketplace, where other brick-and-mortar store owners and design firms can purchase and use them.

[0353] Prompt sentences in specific examples

[0354] "I want the interior of the cafe to have a woody style. I want the layout to have a bright atmosphere."

[0355] "The floor plan for a family of four is an integrated living room and dining kitchen. The furniture needs include a large dining table, sofa, and study desk."

[0356] In this way, this invention allows users to easily create interior and layout designs that meet their needs and apply them to physical stores. It also allows users to exhibit these designs on the digital market, allowing them to be widely shared.

[0357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0358] Step 1:

[0359] The user uses a smartphone or tablet to input the desired floor plan, interior, and furniture information in natural language. For example, they might give instructions such as, "I want the interior of the cafe to have a woody style, and I want it to have a bright atmosphere." This input is then sent to the server.

[0360] Input: User input data in natural language

[0361] Output: Natural language input data

[0362] Step 2:

[0363] The server sends the received natural language input data to a natural language processing engine (e.g., the BERT model from Hugging Face Transformers), which analyzes the input data and extracts information about the desired floor plan, interior, and furniture.

[0364] Input: Natural language input data

[0365] Output: Extracted floor plan, interior, and furniture information

[0366] Step 3:

[0367] The server sends the extracted information to an emotion recognition engine (e.g., nlptown / bert-base-multilingual-uncased-sentiment), which analyzes the user's text for emotional states (positive, negative, neutral). This process classifies the user's emotional state.

[0368] Input: Extracted floor plan, interior, and furniture information

[0369] Output: User's emotional state (positive, negative, neutral)

[0370] Step 4:

[0371] The server automatically generates a 3D floor plan model using a 3D rendering engine based on the analyzed floor plan, interior, and furniture information, as well as the user's emotional state. If the user desires a "bright atmosphere," a design using woody materials and bright colors will be applied based on the user's positive emotional state.

[0372] Input: Floor plan, interior, furniture information, and emotional state

[0373] Output: 3D floor plan model

[0374] Step 5:

[0375] The server then sends the generated 3D floor plan model to an evaluation and scoring engine, which evaluates the model's compliance with architectural standards and technology and assigns a technical score based on factors such as how well the model captures light and how efficiently it is positioned.

[0376] Input: 3D floor plan model

[0377] Output: Scoring results

[0378] Step 6:

[0379] The server notifies the user of the scoring results and, if the user wishes, takes steps to have the 3D floor plan model posted on the digital marketplace, allowing other brick-and-mortar store owners and design firms to view and purchase the model.

[0380] Input: Scoring results

[0381] Output: Exhibit on the digital market

[0382] Specific working example:

[0383] A user enters, "A floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk."

[0384] The server analyzes this information and uses an emotion recognition engine to determine that the emotion is positive.

[0385] The 3D rendering engine generates a 3D model of the design using bright colors based on the specified floor plan and furniture arrangement.

[0386] The scoring engine checks compliance with building standards and awards a high score.

[0387] Users can then exhibit this model on a digital marketplace where other interested parties can purchase it.

[0388] This allows users to easily create interior and layout designs that suit their preferences, and even share and utilize those designs on the digital market.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] [Second embodiment]

[0393] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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).

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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."

[0405] This invention relates to a system that automatically generates a 3D floor plan model based on a user's desired floor plan, furniture information, family composition, etc. using natural language, and the realistic model is scored and can be exhibited on a digital flea market. This system allows users to easily design floor plans and provides technology that allows them to share and trade those designs with others.

[0406] System program description

[0407] Accepting input in natural language

[0408] Users access the system's interface and input their desired floor plan, family composition, details of household items, etc. in natural language. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the children."

[0409] natural language analysis

[0410] The server receives natural language requests submitted by users and then uses natural language processing (NLP) techniques to analyze this input and extract information such as specific floor plans, furniture arrangements, and family composition.

[0411] Generate 3D floor plan models

[0412] The server designs a 3D floor plan model based on the extracted elements. For example, it lays out an open space connecting the living room and kitchen, and arranges bedrooms and bathrooms suitable for a family of three. It then extracts the necessary furniture (sofa, dining table, children's desk) from the database and places them in the appropriate locations. Finally, it uses 3D rendering technology to generate a visually checkable 3D model.

[0413] Scoring

[0414] The server then scores the generated 3D model based on building codes and current building technology, including evaluation of ceiling height, seismic standards, energy efficiency, etc. Based on the evaluation, a score is assigned.

[0415] Exhibiting at the Digital Flea Market

[0416] Users can check the scoring results and choose whether or not to exhibit the generated model on the digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by home builders, construction companies, and custom homeowners. Models that do not meet a certain score may be used in other industries (such as the gaming industry).

[0417] Specific examples

[0418] For example, if a user inputs the desired floor plan as "a layout for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," the server first analyzes this input. Through analysis, the following are extracted: "family of four," "combined living room and dining kitchen," and "furniture: large dining table, sofa, and study desk."

[0419] The server then uses this information to generate a 3D floor plan model, designing four bedrooms, a combined living / dining / kitchen area, and furniture arrangements. This model is then rendered in 3D and presented to the user visually.

[0420] The server then evaluates the generated model to see if it complies with building codes and assigns it a technical score. If the score is high, the user can then put the model up on a digital flea market where other consumers and businesses can view and purchase it.

[0421] This system allows users to easily generate 3D floor plan models that meet their needs and then use and share the results on a digital flea market.

[0422] The processing flow will be explained below.

[0423] Step 1:

[0424] Users access the interface and use natural language to input their desired floor plan, family composition, number of furniture pieces, etc. into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs include a sofa, dining table, and desk for the children."

[0425] Step 2:

[0426] The server receives the input natural language data.

[0427] Step 3:

[0428] The server uses a natural language processing (NLP) engine to analyze the received natural language data, specifically by performing grammar analysis, word tokenization, and context understanding.

[0429] Step 4:

[0430] The server extracts important information from the results of natural language analysis, such as the floor plan, family composition, and the type and number of furniture. For example, it extracts elements such as "living room and kitchen combined," "family of three," and "furniture: sofa, dining table, children's desk."

[0431] Step 5:

[0432] The server then uses the extracted information to automatically generate a 3D floor plan model. First, it designs the basic layout of the floor plan. This involves determining how the living room and kitchen will be connected, and planning the layout of the three bedrooms.

[0433] Step 6:

[0434] The server references a database of pre-placed rooms and furniture and selects appropriate furniture and room layouts based on the extracted information: specifically, placing a sofa in the living room, a dining table in the kitchen area, and a children's desk in the children's room.

[0435] Step 7:

[0436] The server uses a 3D rendering engine to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0437] Step 8:

[0438] The server then scores the generated 3D model based on building standards and construction techniques, such as minimum ceiling height, earthquake resistance standards, and energy efficiency.

[0439] Step 9:

[0440] The server generates an evaluation report based on the scoring results and sends it to the user, who can then check the feasibility and legal compliance of the model.

[0441] Step 10:

[0442] Users can review the scoring results and choose whether or not to exhibit the generated 3D model on a digital flea market.

[0443] Step 11:

[0444] If a user wishes to exhibit their 3D model, the server will post it on the digital market, making it available for viewing and purchase by home builders, construction companies, and owners of custom homes.

[0445] Step 12:

[0446] The server will then separately post the low scoring models on a digital marketplace for use in other industries (e.g., the gaming industry).

[0447] In this way, the system allows users to easily define their desired floor plan, visualize it as a 3D model, evaluate it, and leverage it in the appropriate market.

[0448] Example 1

[0449] 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."

[0450] Modern society demands user-friendly and efficient home designs, which require flexible floor plan designs that can accommodate a wide variety of needs. However, it is difficult for ordinary users without specialized knowledge to design floor plans themselves, and there are limited means for sharing and trading the results with others. To solve this problem, a system is needed that easily realizes users' wishes, evaluates the designs, and automates the entire process of exhibiting them on the market.

[0451] 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.

[0452] In this invention, the server includes: means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; means for analyzing natural language and extracting information; means for automatically generating 3D floor plan models based on the extracted information; means for scoring the generated 3D floor plan models based on building standards and building techniques; means for exhibiting models that have achieved a certain score on a market in a digital space; and means for a user to select an exhibit and for making the exhibited model data available for viewing and trading in the digital space. This enables users to easily generate 3D floor plan models that meet their needs and share and trade the results with others.

[0453] "User" refers to an individual who operates the system to design floor plans and input furniture information.

[0454] "Natural language" refers to a language that is commonly used by humans, and in this case refers to a language that a user uses to input their preferences.

[0455] "Floor plan" refers to the arrangement and configuration of rooms and spaces within a building.

[0456] "Furniture information" refers to detailed information about the furniture to be arranged in the floor plan.

[0457] "Family composition" refers to the number of family members and their relationships within the user's household.

[0458] "Input means" refers to the means by which a user uses natural language to input the desired floor plan, furniture information, family composition, etc.

[0459] "Natural language processing means" refers to technology or systems for analyzing input natural language and extracting necessary information.

[0460] "Floor plan generation means" refers to a system for automatically generating a 3D floor plan model based on the extracted information.

[0461] "3D floor plan model" refers to a three-dimensional digital model of the floor plan generated based on the extracted information.

[0462] "Scoring means" refers to a system for evaluating the generated 3D floor plan model based on certain criteria and assigning a score.

[0463] "Market exhibiting means" refers to a system that allows scored models to be exhibited on a digital marketplace, making them available for viewing and trading.

[0464] "Digital market" refers to a platform provided over the Internet for trading designed 3D models.

[0465] "Construction contractor" refers to a company or individual that designs and constructs buildings.

[0466] A "custom homeowner" refers to an individual who places an order to have a home built based on their own requirements.

[0467] This invention is a system that automatically generates a 3D floor plan model based on a user's natural language input of the desired floor plan, furniture information, family composition, etc., and then scores the model before displaying it at a digital flea market. The main components of this system include an input means, a natural language processing means, a floor plan generation means, a scoring means, and a market exhibition means.

[0468] Users input their desired floor plan, furniture information, family composition, etc. in natural language through the system interface. For example, a user might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the children."

[0469] In the natural language processing means, the server receives input data sent by the user. This data is received by the server's API gateway and then passed to the natural language processing engine. An NLP tool, for example, is used as a natural language processing technology. This analyzes the input natural language and extracts specific elements such as "an open space connecting the living room and kitchen," "a family of three," and "furniture: sofa, dining table, and children's desk."

[0470] The floor plan generation method generates a 3D floor plan model based on the data analyzed by the server. In this process, the server searches the database for appropriate furniture and floor plan templates, and then models them using 3D modeling software such as Blender or SketchUp. The system automatically designs room arrangements and floor plan layouts based on family composition, and generates a 3D model that users can visually check. For example, a layout such as "an open space connecting the living room and kitchen," "a bedroom suitable for a family of three," or "a sofa placed in the center of the living room" may be created.

[0471] In the scoring method, the server scores the generated 3D floor plan model. For this, evaluation criteria such as ceiling height, earthquake resistance standards, and energy efficiency are used, and a scoring algorithm is executed. Evaluation criteria refer to, for example, LEED and CASBEE standards. As a specific example of scoring, the model is scored based on evaluation items such as "high energy efficiency," "earthquake resistance," and "a lot of natural light."

[0472] In the market exhibiting method, the user checks the scoring results provided by the server and chooses whether to exhibit the generated model on the digital flea market. If the user wishes to exhibit, the server uploads the 3D model data to the market in the digital space, where it can be viewed and traded. As a specific example, a scenario can be considered in which the user checks the evaluation results and decides to exhibit the model after confirming that it has a high score.

[0473] A concrete example of a prompt might be the following natural language input:

[0474] "I want an open layout with a connected living room and kitchen. It's for a family of three, and the furniture needs to be a sofa, a dining table, and a desk for the kids."

[0475] "The floor plan for a family of four is an integrated living room and dining kitchen. The furniture needs include a large dining table, sofa, and study desk."

[0476] This system allows users to easily generate 3D floor plan models that meet their needs, even without specialized knowledge, and then share and trade those models with others.

[0477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0478] Step 1:

[0479] Users input information such as floor plan, furniture, and family composition in natural language through the system interface, via a text area in a web browser or mobile app.

[0480] Example: "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the kids."

[0481] Output of this step: Natural language input data.

[0482] Step 2:

[0483] The server receives the input data sent by the user and passes it to a natural language processing engine. NLP technology is used to analyze the input data and extract specific floor plan elements, furniture information, family composition, and other information.

[0484] Examples of software used: NLP tools (e.g., Google Cloud Natural Language API) as natural language processing engines.

[0485] Input: "I want an open plan with a living room and kitchen connected to each other. It will accommodate a family of three, and the furniture will need to include a sofa, a dining table, and desks for the kids."

[0486] Output of this step: Analysis results (element extraction data) "Living room and kitchen", "Family of three", "Furniture: sofa, dining table, children's desk".

[0487] Step 3:

[0488] The server generates a 3D floor plan model based on the extracted information, searches for appropriate furniture and floor plan templates in a database, and creates the model using 3D modeling software.

[0489] Hardware and software used: 3D modeling software (e.g. Blender, SketchUp).

[0490] Specific actions: Open space connecting the living room and kitchen, bedrooms suitable for a family of three, bathrooms, and furniture (sofa, dining table, children's desk) properly arranged.

[0491] Input for this step: Element extraction data.

[0492] Output of this step: 3D floor plan model.

[0493] Step 4:

[0494] The server scores the generated 3D floor plan model, using criteria such as ceiling height, earthquake resistance standards, and energy efficiency. A unique scoring algorithm is run to assign a score.

[0495] Criteria and tools used: Scoring tools based on LEED and CASBEE standards.

[0496] Input for this step: 3D floor plan model.

[0497] Output of this step: Scoring result (assigned score).

[0498] Step 5:

[0499] The user checks the scoring results provided by the server and chooses whether or not to exhibit the generated model on the digital flea market. If the user wishes to exhibit, the server uploads the 3D model data to the market in the digital space. Exhibited models can be viewed and traded by construction companies and owners of custom-built homes.

[0500] Specific operation: Click the "Exhibit" button displayed on the interface, and the server will upload the model data.

[0501] Inputs for this step: Scoring results, user selection.

[0502] Output of this step: a 3D model published on a digital marketplace.

[0503] In this way, this system generates 3D floor plan models from user input and automates the process of evaluating and exhibiting those models, making it easy for users to design floor plans and share and trade the results.

[0504] (Application example 1)

[0505] 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."

[0506] Currently, designing homes and interiors requires a high level of specialized knowledge, making it difficult for average users to easily design floor plans and consider furniture arrangements based on their own preferences. However, a system that automatically generates 3D floor plan models by simply inputting users' preferences and requirements in natural language, and then evaluates and visualizes the models and exhibits them on a digital flea market would be useful. This system would allow users to easily design floor plans and share and trade them with others, greatly simplifying the design process.

[0507] 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.

[0508] In this invention, the server includes: means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; floor plan generation means for automatically generating 3D floor plan models based on the extracted information; scoring means for scoring the generated 3D floor plan models based on building standards and building techniques; means for visually displaying the generated 3D floor plan models in a digital space; means for a user to review and make a decision on models that have received a certain score by the scoring means; and market exhibition means for exhibiting the models reviewed and decided upon by the user in a market in the digital space. This enables users to easily design floor plans and furniture arrangements based on their own preferences, evaluate and visualize the designs, and exhibit them in a flea market.

[0509] "Natural language processing means" is a technology for analyzing natural language sentences entered by users and extracting meaning and information.

[0510] A "3D floor plan model" refers to a design drawing visualized in three-dimensional space based on information such as the user's desired floor plan and furniture placement.

[0511] The "scoring method" is a method for evaluating whether the generated 3D floor plan model complies with building standards and construction techniques, and assigning a score.

[0512] The "market exhibit method" is a method of posting 3D floor plan models that have received a certain score on a digital marketplace, allowing other users and businesses to view and purchase them.

[0513] "Visual display means" refers to technology that displays the generated 3D floor plan model on the screen of a digital device, allowing users to check and consider it in real time.

[0514] "Means that allow users to consider and make decisions" refers to a means by which users can review the scored 3D model and decide whether or not to adopt it.

[0515] The present invention relates to a system that allows users to input their desired floor plan, furniture information, family composition, etc. using natural language, and then automatically generates a 3D floor plan model based on that information, scores it, and exhibits it on a digital flea market.

[0516] The system is implemented using the following hardware and software:

[0517] Hardware: smartphones, tablets, servers

[0518] Software: Python, Flask (web framework), natural language processing library (e.g. spaCy), 3D modeling library (e.g. Three.js)

[0519] The server first receives a request sent in natural language by the user. Specifically, the user inputs the desired floor plan, furniture information, family composition, etc. in natural language. For example, the user might input, "A spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk."

[0520] The server then uses natural language processing technology to analyze this input and extract information such as the specific floor plan, furniture layout, and family composition. This information is then used to generate a 3D floor plan model. The 3D model generated at this stage is then laid out based on the user's preferences, such as an open kitchen or a living room layout suitable for a family of four.

[0521] The generated 3D floor plan model is then scored based on building standards and construction techniques. For example, earthquake resistance standards and energy efficiency are evaluated, and a score is assigned based on the evaluation results. After viewing the scoring results, users can then choose whether or not to exhibit the generated model on the digital flea market.

[0522] Visually, the generated 3D model is displayed in real time on the screen of a smartphone or tablet, allowing users to inspect the model in detail, making it easy to consider whether the floor plan and furniture arrangement are exactly as they wanted.

[0523] Finally, the 3D model that the user has considered and decided on will be exhibited on a digital flea market, where other users and vendors can view and purchase it. Models that do not meet a certain score may be used in other fields (such as games or education).

[0524] As a concrete example:

[0525] If a user wants a floor plan and furniture arrangement for a family of four,

[0526] Users input "A spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk as furniture." The server analyzes this input and extracts the elements of a family of four, a spacious living room, an open kitchen, a sofa, a dining set, and a study desk. A 3D floor plan model is generated based on these elements and scored based on architectural standards. Based on the evaluation results, users can exhibit the model at a flea market.

[0527] Example prompts for generative AI models

[0528] "We are looking for a floor plan and furniture arrangement for a family of four. It should have a large living room and an open kitchen. The furniture should include a sofa, dining set, and study desk. Please generate and score appropriate 3D models."

[0529] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0530] Step 1:

[0531] Using a smartphone or tablet, the user inputs details such as the desired floor plan, furniture, and family composition in natural language. For example, they might input "a spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk." The input natural language is sent to the system.

[0532] Input: Natural language request

[0533] Output: Send data to the server

[0534] Step 2:

[0535] The server analyzes the received natural language input, using natural language processing (NLP) techniques to parse the input sentences and extract the necessary information (e.g., family composition, floor plan type, required furniture items).

[0536] Input: Natural language input data

[0537] Output: Extracted information (family composition, floor plan, furniture information)

[0538] Step 3:

[0539] The server generates a 3D floor plan model based on the extracted information. Specifically, it uses 3D modeling technology to automatically create a floor plan design, including an open kitchen, living room, furniture arrangement, and more, and creates a 3D model that can be visually confirmed.

[0540] Input: Extracted information

[0541] Output: 3D floor plan model

[0542] Step 4:

[0543] The server then scores the generated 3D floor plan model based on building standards and construction techniques. In this step, scores are assigned using evaluation criteria such as earthquake resistance standards and energy efficiency to evaluate the quality of the model.

[0544] Input: 3D floor plan model

[0545] Output: Scoring results

[0546] Step 5:

[0547] The server then uses a means to visually display the scoring results and displays the 3D model to the user, allowing the user to check and consider their desired floor plan and furniture arrangement in real time.

[0548] Input: Scoring results, 3D model

[0549] Output: 3D model displayed on a smartphone or tablet

[0550] Step 6:

[0551] Users review the generated 3D model and its scoring results and decide whether to exhibit it in the digital flea market. The results of their decision are sent to the system.

[0552] Input: User decision

[0553] Output: Sending data to the system

[0554] Step 7:

[0555] The server will display the models that users have decided to exhibit in a digital flea market. Models that do not meet a certain score may be used in other fields (such as games or education).

[0556] Input: The model that the user has decided to exhibit

[0557] Output: Exhibit at the digital flea market

[0558] 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.

[0559] This invention relates to a system that automatically generates a 3D floor plan model based on a user's desired floor plan, furniture information, family composition, etc., input in natural language, and then combines it with an emotion engine that recognizes the user's emotions to adjust the model according to the user's emotional state. This system allows users to easily design floor plans and provides technology that allows the model to adapt to the user's mood and emotions.

[0560] System program description

[0561] Accepting input in natural language

[0562] Users access the interface and input their desired floor plan, family composition, number of furniture, etc. in natural language into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desk for the children." At this time, the system also inputs the user's tone of voice and emotions from the text.

[0563] Natural Language Analysis and Emotion Recognition

[0564] The server receives the input natural language and emotion data. It uses a natural language processing (NLP) engine to analyze the input sentences and extract information such as the specific floor plan, furniture layout, and family composition. At the same time, the emotion engine analyzes the user's text and tone of voice and classifies them into positive, negative, or neutral emotion categories.

[0565] 3D floor plan model generation and emotional feedback

[0566] The server then begins the process of generating a 3D floor plan model based on the extracted information and emotion recognition results. First, it designs a basic floor plan layout, for example, laying out an open space connecting the living room and kitchen, and arranging three bedrooms. It also appropriately adjusts the model's design, color, and atmosphere based on the emotion recognition results. For example, if the user is in a positive emotional state, it may use more brightly colored interiors, and if they are in a negative emotional state, it may choose more subdued colors.

[0567] 3D rendering

[0568] The server uses 3D rendering technology to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0569] Scoring

[0570] The server evaluates whether the generated 3D model complies with building standards and construction techniques, and assigns a technical score. The emotion recognition results of the emotion engine are also fed back into the scoring, affecting the score. For example, if the user is very satisfied, the score may be slightly increased.

[0571] Exhibiting at the Digital Flea Market

[0572] Users can check the scoring results and choose whether or not to exhibit the generated model on the digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by home builders, construction companies, and custom homeowners. Models that do not meet a certain score may also be used in other industries (such as the gaming industry).

[0573] Specific examples

[0574] For example, if a user inputs "A floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," while speaking in an extremely cheerful tone, the server will first analyze this input. The analysis will extract "family of four," "combined living room and dining kitchen," and "furniture: large dining table, sofa, study desk," and the emotion engine will recognize positive emotions.

[0575] The server then uses this information to generate a 3D floor plan model and designs an open space connecting the living room and kitchen. Based on the emotion recognition results, the server adjusts the design to match positive emotions, using a lot of bright interior colors.

[0576] The server then evaluates the generated model to see if it complies with building standards, and assigns a score based on both technical and emotional evaluations. If the model receives a high rating, the user can then exhibit it on a digital flea market, where it can be viewed and purchased by other consumers and businesses.

[0577] In this way, this system allows users to easily generate 3D floor plan models that meet their needs and share them in a digital flea market. Furthermore, by combining this with an emotion engine to analyze users' emotions, the system can generate models that are more satisfying and adapt to the user's emotional state.

[0578] The processing flow will be explained below.

[0579] Step 1:

[0580] Users access the interface and use natural language to input their desired floor plan, family composition, number of furniture, etc. into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desk for the children."

[0581] Step 2:

[0582] The server receives the input natural language data.

[0583] Step 3:

[0584] The server uses a natural language processing (NLP) engine to analyze the received natural language data, specifically by performing grammar analysis, word tokenization, and context understanding.

[0585] Step 4:

[0586] The server extracts important information from the results of natural language analysis, such as the floor plan, family composition, and the type and number of furniture. For example, it extracts elements such as "living room and kitchen combined," "family of three," and "furniture: sofa, dining table, children's desk."

[0587] Step 5:

[0588] The emotion engine recognizes the user's emotions from the text and voice input, for example by analyzing the style of the text, the words used, and the tone and tone of the voice, and classifies the user's emotions as positive, negative, or neutral.

[0589] Step 6:

[0590] The server then begins the process of generating a 3D floor plan model based on the extracted information and the recognized emotion data. First, it designs the basic floor plan layout. Here, it determines the layout of the living room and kitchen, and also plans the layout of the three bedrooms.

[0591] Step 7:

[0592] The server adjusts the model's design elements based on the emotion data, specifically selecting bright interior colors for positive emotions and muted colors for negative emotions.

[0593] Step 8:

[0594] The server references a database of pre-placed rooms and furniture and selects appropriate furniture and room layouts based on the extracted information: specifically, placing a sofa in the living room, a dining table in the kitchen area, and a children's desk in the children's room.

[0595] Step 9:

[0596] The server uses a 3D rendering engine to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0597] Step 10:

[0598] The server scores the generated 3D model based on building standards and construction techniques. Specifically, it evaluates and assigns a score to minimum ceiling height, earthquake resistance standards, energy efficiency, etc. Emotion recognition results are also fed back into the scoring process, affecting the score.

[0599] Step 11:

[0600] The server generates an evaluation report based on the scoring results and sends it to the user, who can then check the feasibility and legal compliance of the model.

[0601] Step 12:

[0602] Users can review the scoring results and choose whether or not to exhibit the generated 3D model on a digital flea market.

[0603] Step 13:

[0604] If a user wishes to exhibit their 3D model, the server will post it on the digital market, making it available for viewing and purchase by home builders, construction companies, and owners of custom homes.

[0605] Step 14:

[0606] The server will then separately post the low scoring models on a digital marketplace for use in other industries (e.g., the gaming industry).

[0607] In this way, the system allows users to easily define their desired floor plan and visualize it as an emotionally tailored 3D model, allowing them to evaluate the model and deploy it in the appropriate market.

[0608] Example 2

[0609] 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."

[0610] Existing floor plan design systems have the problem that users need specialized knowledge to input their specific preferences, making intuitive operation difficult. Furthermore, it is difficult to create designs that reflect the user's emotions and preferences, which prevents satisfaction from being increased. Furthermore, there are issues with the time-consuming and labor-intensive process of evaluating the quality and suitability of the generated models and releasing them to the market.

[0611] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input desired spatial layout, interior information, household configuration, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; emotion recognition means for recognizing emotions from the tone and text of the user's input; model generation means for automatically generating a 3D spatial layout model based on the extracted information and emotion recognition results; scoring means for scoring the generated 3D spatial layout model based on building standards and technical requirements; and market exhibition means for exhibiting models that have achieved a certain score by the scoring means on a market in a digital space. This allows users to intuitively input their desires in natural language and easily generate, evaluate, and exhibit 3D models that match their emotions on a market.

[0612] A "user" is an entity that uses the system to input information such as desired spatial layout, interior design information, and household configuration in natural language.

[0613] "Natural language" is language used by humans on a daily basis, as opposed to formal program code.

[0614] "Desired spatial arrangement" refers to the layout or arrangement of buildings or rooms desired by the user.

[0615] "Interior information" refers to information about furniture and decorations, and is related to the atmosphere and functionality of a space.

[0616] "Family composition" refers to information such as the number of family members and their age groups.

[0617] "Natural language processing means" refers to technology or equipment that analyzes natural language input by a user and extracts related information.

[0618] An "emotion recognition means" is a technology or device that analyzes emotions from the tone and text content of a user's input and classifies them as positive, negative, neutral, etc.

[0619] "Model generation means" refers to a technology or device that automatically generates a three-dimensional spatial layout model based on the extracted information and emotion recognition results.

[0620] A "3D spatial layout model" is a model that represents the layout and interior of an actual building or room in a three-dimensional visual format.

[0621] A "scoring means" is a technology or device that evaluates whether the generated 3D spatial layout model complies with building standards and technical requirements and assigns a score.

[0622] "Market exhibiting means" refers to a technology or device that exhibits models that have earned a certain score in the digital marketplace, allowing other users and businesses to view and purchase them.

[0623] A "digital market" is a virtual market built on the Internet where 3D models and other items are bought and sold.

[0624] "Technical requirements" are requirements based on specific technical standards or laws and regulations.

[0625] "Tone of input" refers to the pitch and emotion of the voice used when a user inputs information by voice.

[0626] The present invention relates to a system that automatically generates a 3D spatial layout model based on a user's desired spatial layout, interior information, family composition, etc., input in natural language, and further combines it with an emotion engine that recognizes the user's emotions to make adjustments according to the user's emotional state.

[0627] This system is implemented by the following procedure.

[0628] First, the user accesses the interface and inputs their desired spatial layout, interior information, and family composition in natural language into a chat-style input screen. For example, they can input specific requests such as, "I'd like a floor plan with an integrated living room and dining kitchen. It's for a family of four, and I need a large dining table, sofa, and study desk." At this time, the system also inputs the user's tone of voice and emotions from the text.

[0629] The server then receives the input natural language data and analyzes the user's input using a natural language processing (NLP) engine (e.g., GPT-3 or BERT). This extracts information from the input, such as the specific floor plan, furniture layout, and family composition. At the same time, an emotion engine analyzes the user's text and tone of voice and classifies them into positive, negative, or neutral emotion categories.

[0630] The server then begins the process of generating a 3D spatial layout model based on the extracted information and emotion recognition results. First, it designs a basic floor plan, creating an open space connecting the living room and kitchen, for example, and then appropriately arranges the necessary furniture. It also adjusts the model's design, color, and atmosphere based on the emotion recognition results. If the user is in a positive emotional state, it uses a lot of bright interior colors, and if they are in a negative state, it chooses calm colors.

[0631] Furthermore, the server generates a 3D model of the designed floor plan and furniture arrangement using 3D rendering technology (e.g., Blender or Unity), which is provided to the user for visual confirmation.

[0632] The server evaluates whether the generated 3D model complies with building standards and technical requirements, and assigns a technical score. The emotion recognition results of the emotion engine are also taken into account in the evaluation. For example, if the user is very satisfied, the score will be slightly increased.

[0633] Finally, the user reviews the scoring results and chooses whether to exhibit the generated model on a digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by builders, interior decorators, and homeowners. Models that do not meet a certain score may also be used in other industries (e.g., the gaming industry).

[0634] For example, if a user enters the following statement in a very positive tone of voice: "We would like a floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," the server analyzes this and extracts the following information: "Family of four," "Combined living room and dining kitchen," "Large dining table," "Sofa," and "Study desk." The emotion engine recognizes positive emotions. Based on this information, the server creates a 3D model of an open space with a connected living room and kitchen, featuring a brightly colored interior. The server then evaluates this model for compliance with building codes and assigns a high score, reflecting the user's high satisfaction. If the model receives a high rating, it will be exhibited on a digital flea market, where it can be viewed and purchased by other consumers and businesses.

[0635] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0636] Step 1:

[0637] Users access the interface and input their desired spatial layout, interior information, and family composition using natural language.

[0638] Specifically, the user inputs a prompt statement into the terminal such as, "I would like a layout with a combined living room and dining kitchen. It is for a family of four and requires a large dining table, sofa, and study desk."

[0639] Input: User-entered text data

[0640] Output: Sends input text data to the server

[0641] Step 2:

[0642] The server receives the natural language data sent from the terminal.

[0643] Input: Text data received from the user

[0644] Output: Prepare the data for input to the natural language processing engine

[0645] Step 3:

[0646] The server runs a natural language processing (NLP) engine to parse the user's input.

[0647] Specifically, it uses an NLP engine (e.g., GPT-3 or BERT) to analyze the input sentence.

[0648] Input: User-entered text data

[0649] Output: Analyzed information (e.g., floor plan, furniture, family composition)

[0650] Step 4:

[0651] The server uses an emotion engine to analyze the user's text content and tone of voice to recognize emotions.

[0652] Specific actions are classified into positive, negative, and neutral emotional categories.

[0653] Input: User text data and tone of voice

[0654] Output: Emotion recognition result

[0655] Step 5:

[0656] The server starts the process of generating a 3D spatial layout model based on the extracted information and emotion recognition results.

[0657] Specifically, the task involves designing a basic floor plan and properly arranging the necessary furniture.

[0658] Input: Parsed information and emotion recognition results

[0659] Output: Initial 3D spatial layout model

[0660] Step 6:

[0661] The server adjusts the design and color of the 3D model based on the emotion recognition results.

[0662] Specifically, when you are in a positive emotional state, you should use bright colors in your interior, and when you are in a negative emotional state, you should choose calm colors.

[0663] Input: Initial 3D spatial layout model and emotion recognition results

[0664] Output: Emotionally adjusted 3D spatial layout model

[0665] Step 7:

[0666] The server uses 3D rendering technology to generate a 3D model of the designed floor plan and furniture arrangement.

[0667] Specifically, the process involves generating a visual model using 3D modeling software (e.g., Blender or Unity).

[0668] Input: Adjusted 3D spatial layout model

[0669] Output: A finished 3D rendered model

[0670] Step 8:

[0671] The server evaluates whether the generated 3D model complies with building standards and technical requirements and assigns it a score.

[0672] Specifically, it uses a scoring algorithm to evaluate the score and adds emotional evaluation to the technical score.

[0673] Input: A completed 3D rendered model

[0674] Output: Scoring results

[0675] Step 9:

[0676] The user checks the scoring results and decides whether or not to exhibit the generated model on a digital flea market.

[0677] Specifically, the user checks the score through the interface and clicks the "Submit" button.

[0678] Input: Scoring results

[0679] Output: Digital Flea Market exhibit request

[0680] Step 10:

[0681] The server receives the exhibition request and posts the generated model on the digital market.

[0682] Specifically, the model is registered in the digital market database, making it available for other users and vendors to view and purchase.

[0683] Input:Exhibition request

[0684] Output: Model listing on the digital market

[0685] (Application example 2)

[0686] 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."

[0687] Modern users demand efficient interior and layout design for brick-and-mortar stores and adjustments based on their emotions. However, conventional methods require time and effort to change or adjust the design, making it difficult to achieve adaptive designs that reflect the user's emotional state. Furthermore, the scope and usability of the generated designs are limited, and it is also time-consuming to verify that they comply with building regulations.

[0688] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; a natural language processing means for analyzing the input natural language and extracting information; a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information; an emotion identification means for analyzing the user's emotions and adjusting the 3D floor plan model based on the user's emotional state; a scoring means for scoring the generated 3D floor plan model based on building standards and construction techniques; a market exhibiting means for exhibiting models that have achieved a certain score by the scoring means on a market in a digital space; and a means for generating and sharing 3D models for proposing interior and layout designs for physical stores. This allows users to easily generate 3D floor plan models that reflect their desired emotional state and confirm designs that comply with building standards. Furthermore, the system streamlines interior design proposals for physical stores and allows 3D models to be shared and purchased, enabling the creation and utilization of more effective and adaptive designs.

[0689] A "user" is someone who designs the interior and layout of a physical store and generates a 3D floor plan model based on that design.

[0690] "Natural language" is a means by which users input their desired floor plan, furniture information, family composition, etc., and is a language that is used on a daily basis.

[0691] "Natural language processing means" refers to technical means for analyzing input natural language and extracting information.

[0692] The "floor plan generation means" is a technical means for automatically generating a 3D floor plan model based on the extracted information.

[0693] The "emotion identification means" is a means for analyzing the user's emotions and adjusting the 3D floor plan model based on the user's emotional state.

[0694] The "scoring method" is a method for evaluating the generated 3D floor plan model based on building standards and construction techniques and assigning a score.

[0695] "Market exhibiting means" refers to a means for exhibiting models that have achieved a certain score on a market in the digital space.

[0696] "Digital space" refers to markets and platforms in virtual spaces such as the Internet.

[0697] A "physical store" is a store that exists in a physical space and provides goods and services.

[0698] "Layout" refers to the arrangement and design of equipment, furniture, decorations, etc. within a store.

[0699] A "3D floor plan model" is a digital model that visually reproduces the interior and layout of a store in three-dimensional space.

[0700] "Emotional state" is the result of analyzing the user's psychological state and mood.

[0701] As an embodiment of this invention, a system for proposing interior and layout designs for brick-and-mortar stores is described below. This system allows users to input their desired interior and layout designs in natural language, generates a 3D floor plan model based on this, and then uses emotion recognition means to make adjustments according to the user's emotional state. The generated model is evaluated using scoring means based on building standards and construction techniques, and can be exhibited on a digital market.

[0702] The system uses the following major hardware and software:

[0703] 1. Device:

[0704] Smartphone or tablet: A device that allows users to input their desired floor plan in natural language.

[0705] Server: Performs data analysis, model generation, emotion identification, and scoring.

[0706] 2. Software:

[0707] Natural language processing engines (e.g., BERT model from Hugging Face Transformers):

[0708] Analyzes the input natural language and extracts the necessary information.

[0709] Sentiment Identification Engine (e.g. nlptown / bert-base-multilingual-uncased-sentiment):

[0710] Analyzes the user's emotional state and classifies it as positive, negative, or neutral.

[0711] 3D Rendering Engine:

[0712] A 3D floor plan model is generated based on the extracted information.

[0713] Rating and Scoring Engine:

[0714] The generated model is evaluated based on building standards and technology and a score is assigned.

[0715] System Operation

[0716] The server receives a means for users to input their desired floor plan, furniture information, family composition, etc. in natural language using a smartphone or tablet. For example, a user might input, "I want the interior of the cafe to have a woody style, and I want it to have a bright atmosphere." This input is first sent to the server and analyzed by a natural language processing engine.

[0717] Next, the emotion recognition engine analyzes the emotional state of the text entered by the user and classifies it as positive, negative, or neutral. In this example, the user wants to emphasize a positive mood, so the emotion is classified as positive.

[0718] The 3D rendering engine then generates a 3D floor plan model that reflects the desired layout and interior design based on the analyzed information and the results of emotion identification. Based on a positive emotional state, the space is designed using woody materials and bright colors.

[0719] The generated 3D floor plan model is then scored by an evaluation and scoring engine based on building standards and technology, which determines whether the model complies with building standards and its market value.

[0720] Finally, users can post their scored models on a digital marketplace, where other brick-and-mortar store owners and design firms can purchase and use them.

[0721] Prompt sentences in specific examples

[0722] "I want the interior of the cafe to have a woody style. I want the layout to have a bright atmosphere."

[0723] "The floor plan for a family of four is an integrated living room and dining kitchen. The furniture needs include a large dining table, sofa, and study desk."

[0724] In this way, this invention allows users to easily create interior and layout designs that meet their needs and apply them to physical stores. It also allows users to exhibit these designs on the digital market, allowing them to be widely shared.

[0725] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0726] Step 1:

[0727] The user uses a smartphone or tablet to input the desired floor plan, interior, and furniture information in natural language. For example, they might give instructions such as, "I want the interior of the cafe to have a woody style, and I want it to have a bright atmosphere." This input is then sent to the server.

[0728] Input: User input data in natural language

[0729] Output: Natural language input data

[0730] Step 2:

[0731] The server sends the received natural language input data to a natural language processing engine (e.g., the BERT model from Hugging Face Transformers), which analyzes the input data and extracts information about the desired floor plan, interior, and furniture.

[0732] Input: Natural language input data

[0733] Output: Extracted floor plan, interior, and furniture information

[0734] Step 3:

[0735] The server sends the extracted information to an emotion recognition engine (e.g., nlptown / bert-base-multilingual-uncased-sentiment), which analyzes the user's text for emotional states (positive, negative, neutral). This process classifies the user's emotional state.

[0736] Input: Extracted floor plan, interior, and furniture information

[0737] Output: User's emotional state (positive, negative, neutral)

[0738] Step 4:

[0739] The server automatically generates a 3D floor plan model using a 3D rendering engine based on the analyzed floor plan, interior, and furniture information, as well as the user's emotional state. If the user desires a "bright atmosphere," a design using woody materials and bright colors will be applied based on the user's positive emotional state.

[0740] Input: Floor plan, interior, furniture information, and emotional state

[0741] Output: 3D floor plan model

[0742] Step 5:

[0743] The server then sends the generated 3D floor plan model to an evaluation and scoring engine, which evaluates the model's compliance with architectural standards and technology and assigns a technical score based on factors such as how well the model captures light and how efficiently it is positioned.

[0744] Input: 3D floor plan model

[0745] Output: Scoring results

[0746] Step 6:

[0747] The server notifies the user of the scoring results and, if the user wishes, takes steps to have the 3D floor plan model posted on the digital marketplace, allowing other brick-and-mortar store owners and design firms to view and purchase the model.

[0748] Input: Scoring results

[0749] Output: Exhibit on the digital market

[0750] Specific working example:

[0751] A user enters, "A floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk."

[0752] The server analyzes this information and uses an emotion recognition engine to determine that the emotion is positive.

[0753] The 3D rendering engine generates a 3D model of the design using bright colors based on the specified floor plan and furniture arrangement.

[0754] The scoring engine checks compliance with building standards and awards a high score.

[0755] Users can then exhibit this model on a digital marketplace where other interested parties can purchase it.

[0756] This allows users to easily create interior and layout designs that suit their preferences, and even share and utilize those designs on the digital market.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] [Third embodiment]

[0761] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0762] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0763] 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).

[0764] 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.

[0765] 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.

[0766] 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).

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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."

[0773] This invention relates to a system that automatically generates a 3D floor plan model based on a user's desired floor plan, furniture information, family composition, etc. using natural language, and the realistic model is scored and can be exhibited on a digital flea market. This system allows users to easily design floor plans and provides technology that allows them to share and trade those designs with others.

[0774] System program description

[0775] Accepting input in natural language

[0776] Users access the system's interface and input their desired floor plan, family composition, details of household items, etc. in natural language. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the children."

[0777] natural language analysis

[0778] The server receives natural language requests submitted by users and then uses natural language processing (NLP) techniques to analyze this input and extract information such as specific floor plans, furniture arrangements, and family composition.

[0779] Generate 3D floor plan models

[0780] The server designs a 3D floor plan model based on the extracted elements. For example, it lays out an open space connecting the living room and kitchen, and arranges bedrooms and bathrooms suitable for a family of three. It then extracts the necessary furniture (sofa, dining table, children's desk) from the database and places them in the appropriate locations. Finally, it uses 3D rendering technology to generate a visually checkable 3D model.

[0781] Scoring

[0782] The server then scores the generated 3D model based on building codes and current building technology, including evaluation of ceiling height, seismic standards, energy efficiency, etc. Based on the evaluation, a score is assigned.

[0783] Exhibiting at the Digital Flea Market

[0784] Users can check the scoring results and choose whether or not to exhibit the generated model on the digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by home builders, construction companies, and custom homeowners. Models that do not meet a certain score may be used in other industries (such as the gaming industry).

[0785] Specific examples

[0786] For example, if a user inputs the desired floor plan as "a layout for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," the server first analyzes this input. Through analysis, the following are extracted: "family of four," "combined living room and dining kitchen," and "furniture: large dining table, sofa, and study desk."

[0787] The server then uses this information to generate a 3D floor plan model, designing four bedrooms, a combined living / dining / kitchen area, and furniture arrangements. This model is then rendered in 3D and presented to the user visually.

[0788] The server then evaluates the generated model to see if it complies with building codes and assigns it a technical score. If the score is high, the user can then put the model up on a digital flea market where other consumers and businesses can view and purchase it.

[0789] This system allows users to easily generate 3D floor plan models that meet their needs and then use and share the results on a digital flea market.

[0790] The processing flow will be explained below.

[0791] Step 1:

[0792] Users access the interface and use natural language to input their desired floor plan, family composition, number of furniture pieces, etc. into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs include a sofa, dining table, and desk for the children."

[0793] Step 2:

[0794] The server receives the input natural language data.

[0795] Step 3:

[0796] The server uses a natural language processing (NLP) engine to analyze the received natural language data, specifically by performing grammar analysis, word tokenization, and context understanding.

[0797] Step 4:

[0798] The server extracts important information from the results of natural language analysis, such as the floor plan, family composition, and the type and number of furniture. For example, it extracts elements such as "living room and kitchen combined," "family of three," and "furniture: sofa, dining table, children's desk."

[0799] Step 5:

[0800] The server then uses the extracted information to automatically generate a 3D floor plan model. First, it designs the basic layout of the floor plan. This involves determining how the living room and kitchen will be connected, and planning the layout of the three bedrooms.

[0801] Step 6:

[0802] The server references a database of pre-placed rooms and furniture and selects appropriate furniture and room layouts based on the extracted information: specifically, placing a sofa in the living room, a dining table in the kitchen area, and a children's desk in the children's room.

[0803] Step 7:

[0804] The server uses a 3D rendering engine to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0805] Step 8:

[0806] The server then scores the generated 3D model based on building standards and construction techniques, such as minimum ceiling height, earthquake resistance standards, and energy efficiency.

[0807] Step 9:

[0808] The server generates an evaluation report based on the scoring results and sends it to the user, who can then check the feasibility and legal compliance of the model.

[0809] Step 10:

[0810] Users can review the scoring results and choose whether or not to exhibit the generated 3D model on a digital flea market.

[0811] Step 11:

[0812] If a user wishes to exhibit their 3D model, the server will post it on the digital market, making it available for viewing and purchase by home builders, construction companies, and owners of custom homes.

[0813] Step 12:

[0814] The server will then separately post the low scoring models on a digital marketplace for use in other industries (e.g., the gaming industry).

[0815] In this way, the system allows users to easily define their desired floor plan, visualize it as a 3D model, evaluate it, and leverage it in the appropriate market.

[0816] Example 1

[0817] 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."

[0818] Modern society demands user-friendly and efficient home designs, which require flexible floor plan designs that can accommodate a wide variety of needs. However, it is difficult for ordinary users without specialized knowledge to design floor plans themselves, and there are limited means for sharing and trading the results with others. To solve this problem, a system is needed that easily realizes users' wishes, evaluates the designs, and automates the entire process of exhibiting them on the market.

[0819] 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.

[0820] In this invention, the server includes: means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; means for analyzing natural language and extracting information; means for automatically generating 3D floor plan models based on the extracted information; means for scoring the generated 3D floor plan models based on building standards and building techniques; means for exhibiting models that have achieved a certain score on a market in a digital space; and means for a user to select an exhibit and for making the exhibited model data available for viewing and trading in the digital space. This enables users to easily generate 3D floor plan models that meet their needs and share and trade the results with others.

[0821] "User" refers to an individual who operates the system to design floor plans and input furniture information.

[0822] "Natural language" refers to a language that is commonly used by humans, and in this case refers to a language that a user uses to input their preferences.

[0823] "Floor plan" refers to the arrangement and configuration of rooms and spaces within a building.

[0824] "Furniture information" refers to detailed information about the furniture to be arranged in the floor plan.

[0825] "Family composition" refers to the number of family members and their relationships within the user's household.

[0826] "Input means" refers to the means by which a user uses natural language to input the desired floor plan, furniture information, family composition, etc.

[0827] "Natural language processing means" refers to technology or systems for analyzing input natural language and extracting necessary information.

[0828] "Floor plan generation means" refers to a system for automatically generating a 3D floor plan model based on the extracted information.

[0829] "3D floor plan model" refers to a three-dimensional digital model of the floor plan generated based on the extracted information.

[0830] "Scoring means" refers to a system for evaluating the generated 3D floor plan model based on certain criteria and assigning a score.

[0831] "Market exhibiting means" refers to a system that allows scored models to be exhibited on a digital marketplace, making them available for viewing and trading.

[0832] "Digital market" refers to a platform provided over the Internet for trading designed 3D models.

[0833] "Construction contractor" refers to a company or individual that designs and constructs buildings.

[0834] A "custom homeowner" refers to an individual who places an order to have a home built based on their own requirements.

[0835] This invention is a system that automatically generates a 3D floor plan model based on a user's natural language input of the desired floor plan, furniture information, family composition, etc., and then scores the model before displaying it at a digital flea market. The main components of this system include an input means, a natural language processing means, a floor plan generation means, a scoring means, and a market exhibition means.

[0836] Users input their desired floor plan, furniture information, family composition, etc. in natural language through the system interface. For example, a user might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the children."

[0837] In the natural language processing means, the server receives input data sent by the user. This data is received by the server's API gateway and then passed to the natural language processing engine. An NLP tool, for example, is used as a natural language processing technology. This analyzes the input natural language and extracts specific elements such as "an open space connecting the living room and kitchen," "a family of three," and "furniture: sofa, dining table, and children's desk."

[0838] The floor plan generation method generates a 3D floor plan model based on the data analyzed by the server. In this process, the server searches the database for appropriate furniture and floor plan templates, and then models them using 3D modeling software such as Blender or SketchUp. The system automatically designs room arrangements and floor plan layouts based on family composition, and generates a 3D model that users can visually check. For example, a layout such as "an open space connecting the living room and kitchen," "a bedroom suitable for a family of three," or "a sofa placed in the center of the living room" may be created.

[0839] In the scoring method, the server scores the generated 3D floor plan model. For this, evaluation criteria such as ceiling height, earthquake resistance standards, and energy efficiency are used, and a scoring algorithm is executed. Evaluation criteria refer to, for example, LEED and CASBEE standards. As a specific example of scoring, the model is scored based on evaluation items such as "high energy efficiency," "earthquake resistance," and "a lot of natural light."

[0840] In the market exhibiting method, the user checks the scoring results provided by the server and chooses whether to exhibit the generated model on the digital flea market. If the user wishes to exhibit, the server uploads the 3D model data to the market in the digital space, where it can be viewed and traded. As a specific example, a scenario can be considered in which the user checks the evaluation results and decides to exhibit the model after confirming that it has a high score.

[0841] A concrete example of a prompt might be the following natural language input:

[0842] "I want an open layout with a connected living room and kitchen. It's for a family of three, and the furniture needs to be a sofa, a dining table, and a desk for the kids."

[0843] "The floor plan for a family of four is an integrated living room and dining kitchen. The furniture needs include a large dining table, sofa, and study desk."

[0844] This system allows users to easily generate 3D floor plan models that meet their needs, even without specialized knowledge, and then share and trade those models with others.

[0845] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0846] Step 1:

[0847] Users input information such as floor plan, furniture, and family composition in natural language through the system interface, via a text area in a web browser or mobile app.

[0848] Example: "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the kids."

[0849] Output of this step: Natural language input data.

[0850] Step 2:

[0851] The server receives the input data sent by the user and passes it to a natural language processing engine. NLP technology is used to analyze the input data and extract specific floor plan elements, furniture information, family composition, and other information.

[0852] Examples of software used: NLP tools (e.g., Google Cloud Natural Language API) as natural language processing engines.

[0853] Input: "I want an open plan with a living room and kitchen connected to each other. It will accommodate a family of three, and the furniture will need to include a sofa, a dining table, and desks for the kids."

[0854] Output of this step: Analysis results (element extraction data) "Living room and kitchen", "Family of three", "Furniture: sofa, dining table, children's desk".

[0855] Step 3:

[0856] The server generates a 3D floor plan model based on the extracted information, searches for appropriate furniture and floor plan templates in a database, and creates the model using 3D modeling software.

[0857] Hardware and software used: 3D modeling software (e.g. Blender, SketchUp).

[0858] Specific actions: Open space connecting the living room and kitchen, bedrooms suitable for a family of three, bathrooms, and furniture (sofa, dining table, children's desk) properly arranged.

[0859] Input for this step: Element extraction data.

[0860] Output of this step: 3D floor plan model.

[0861] Step 4:

[0862] The server scores the generated 3D floor plan model, using criteria such as ceiling height, earthquake resistance standards, and energy efficiency. A unique scoring algorithm is run to assign a score.

[0863] Criteria and tools used: Scoring tools based on LEED and CASBEE standards.

[0864] Input for this step: 3D floor plan model.

[0865] Output of this step: Scoring result (assigned score).

[0866] Step 5:

[0867] The user checks the scoring results provided by the server and chooses whether or not to exhibit the generated model on the digital flea market. If the user wishes to exhibit, the server uploads the 3D model data to the market in the digital space. Exhibited models can be viewed and traded by construction companies and owners of custom-built homes.

[0868] Specific operation: Click the "Exhibit" button displayed on the interface, and the server will upload the model data.

[0869] Inputs for this step: Scoring results, user selection.

[0870] Output of this step: a 3D model published on a digital marketplace.

[0871] In this way, this system generates 3D floor plan models from user input and automates the process of evaluating and exhibiting those models, making it easy for users to design floor plans and share and trade the results.

[0872] (Application example 1)

[0873] 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."

[0874] Currently, designing homes and interiors requires a high level of specialized knowledge, making it difficult for average users to easily design floor plans and consider furniture arrangements based on their own preferences. However, a system that automatically generates 3D floor plan models by simply inputting users' preferences and requirements in natural language, and then evaluates and visualizes the models and exhibits them on a digital flea market would be useful. This system would allow users to easily design floor plans and share and trade them with others, greatly simplifying the design process.

[0875] 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.

[0876] In this invention, the server includes: means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; floor plan generation means for automatically generating 3D floor plan models based on the extracted information; scoring means for scoring the generated 3D floor plan models based on building standards and building techniques; means for visually displaying the generated 3D floor plan models in a digital space; means for a user to review and make a decision on models that have received a certain score by the scoring means; and market exhibition means for exhibiting the models reviewed and decided upon by the user in a market in the digital space. This enables users to easily design floor plans and furniture arrangements based on their own preferences, evaluate and visualize the designs, and exhibit them in a flea market.

[0877] "Natural language processing means" is a technology for analyzing natural language sentences entered by users and extracting meaning and information.

[0878] A "3D floor plan model" refers to a design drawing visualized in three-dimensional space based on information such as the user's desired floor plan and furniture placement.

[0879] The "scoring method" is a method for evaluating whether the generated 3D floor plan model complies with building standards and construction techniques, and assigning a score.

[0880] The "market exhibit method" is a method of posting 3D floor plan models that have received a certain score on a digital marketplace, allowing other users and businesses to view and purchase them.

[0881] "Visual display means" refers to technology that displays the generated 3D floor plan model on the screen of a digital device, allowing users to check and consider it in real time.

[0882] "Means that allow users to consider and make decisions" refers to a means by which users can review the scored 3D model and decide whether or not to adopt it.

[0883] The present invention relates to a system that allows users to input their desired floor plan, furniture information, family composition, etc. using natural language, and then automatically generates a 3D floor plan model based on that information, scores it, and exhibits it on a digital flea market.

[0884] The system is implemented using the following hardware and software:

[0885] Hardware: smartphones, tablets, servers

[0886] Software: Python, Flask (web framework), natural language processing library (e.g. spaCy), 3D modeling library (e.g. Three.js)

[0887] The server first receives a request sent in natural language by the user. Specifically, the user inputs the desired floor plan, furniture information, family composition, etc. in natural language. For example, the user might input, "A spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk."

[0888] The server then uses natural language processing technology to analyze this input and extract information such as the specific floor plan, furniture layout, and family composition. This information is then used to generate a 3D floor plan model. The 3D model generated at this stage is then laid out based on the user's preferences, such as an open kitchen or a living room layout suitable for a family of four.

[0889] The generated 3D floor plan model is then scored based on building standards and construction techniques. For example, earthquake resistance standards and energy efficiency are evaluated, and a score is assigned based on the evaluation results. After viewing the scoring results, users can then choose whether or not to exhibit the generated model on the digital flea market.

[0890] Visually, the generated 3D model is displayed in real time on the screen of a smartphone or tablet, allowing users to inspect the model in detail, making it easy to consider whether the floor plan and furniture arrangement are exactly as they wanted.

[0891] Finally, the 3D model that the user has considered and decided on will be exhibited on a digital flea market, where other users and vendors can view and purchase it. Models that do not meet a certain score may be used in other fields (such as games or education).

[0892] As a concrete example:

[0893] If a user wants a floor plan and furniture arrangement for a family of four,

[0894] Users input "A spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk as furniture." The server analyzes this input and extracts the elements of a family of four, a spacious living room, an open kitchen, a sofa, a dining set, and a study desk. A 3D floor plan model is generated based on these elements and scored based on architectural standards. Based on the evaluation results, users can exhibit the model at a flea market.

[0895] Example prompts for generative AI models

[0896] "We are looking for a floor plan and furniture arrangement for a family of four. It should have a large living room and an open kitchen. The furniture should include a sofa, dining set, and study desk. Please generate and score appropriate 3D models."

[0897] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0898] Step 1:

[0899] Using a smartphone or tablet, the user inputs details such as the desired floor plan, furniture, and family composition in natural language. For example, they might input "a spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk." The input natural language is sent to the system.

[0900] Input: Natural language request

[0901] Output: Send data to the server

[0902] Step 2:

[0903] The server analyzes the received natural language input, using natural language processing (NLP) techniques to parse the input sentences and extract the necessary information (e.g., family composition, floor plan type, required furniture items).

[0904] Input: Natural language input data

[0905] Output: Extracted information (family composition, floor plan, furniture information)

[0906] Step 3:

[0907] The server generates a 3D floor plan model based on the extracted information. Specifically, it uses 3D modeling technology to automatically create a floor plan design, including an open kitchen, living room, furniture arrangement, and more, and creates a 3D model that can be visually confirmed.

[0908] Input: Extracted information

[0909] Output: 3D floor plan model

[0910] Step 4:

[0911] The server then scores the generated 3D floor plan model based on building standards and construction techniques. In this step, scores are assigned using evaluation criteria such as earthquake resistance standards and energy efficiency to evaluate the quality of the model.

[0912] Input: 3D floor plan model

[0913] Output: Scoring results

[0914] Step 5:

[0915] The server then uses a means to visually display the scoring results and displays the 3D model to the user, allowing the user to check and consider their desired floor plan and furniture arrangement in real time.

[0916] Input: Scoring results, 3D model

[0917] Output: 3D model displayed on a smartphone or tablet

[0918] Step 6:

[0919] Users review the generated 3D model and its scoring results and decide whether to exhibit it in the digital flea market. The results of their decision are sent to the system.

[0920] Input: User decision

[0921] Output: Sending data to the system

[0922] Step 7:

[0923] The server will display the models that users have decided to exhibit in a digital flea market. Models that do not meet a certain score may be used in other fields (such as games or education).

[0924] Input: The model that the user has decided to exhibit

[0925] Output: Exhibit at the digital flea market

[0926] 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.

[0927] This invention relates to a system that automatically generates a 3D floor plan model based on a user's desired floor plan, furniture information, family composition, etc., input in natural language, and then combines it with an emotion engine that recognizes the user's emotions to adjust the model according to the user's emotional state. This system allows users to easily design floor plans and provides technology that allows the model to adapt to the user's mood and emotions.

[0928] System program description

[0929] Accepting input in natural language

[0930] Users access the interface and input their desired floor plan, family composition, number of furniture, etc. in natural language into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desk for the children." At this time, the system also inputs the user's tone of voice and emotions from the text.

[0931] Natural Language Analysis and Emotion Recognition

[0932] The server receives the input natural language and emotion data. It uses a natural language processing (NLP) engine to analyze the input sentences and extract information such as the specific floor plan, furniture layout, and family composition. At the same time, the emotion engine analyzes the user's text and tone of voice and classifies them into positive, negative, or neutral emotion categories.

[0933] 3D floor plan model generation and emotional feedback

[0934] The server then begins the process of generating a 3D floor plan model based on the extracted information and emotion recognition results. First, it designs a basic floor plan layout, for example, laying out an open space connecting the living room and kitchen, and arranging three bedrooms. It also appropriately adjusts the model's design, color, and atmosphere based on the emotion recognition results. For example, if the user is in a positive emotional state, it may use more brightly colored interiors, and if they are in a negative emotional state, it may choose more subdued colors.

[0935] 3D rendering

[0936] The server uses 3D rendering technology to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0937] Scoring

[0938] The server evaluates whether the generated 3D model complies with building standards and construction techniques, and assigns a technical score. The emotion recognition results of the emotion engine are also fed back into the scoring, affecting the score. For example, if the user is very satisfied, the score may be slightly increased.

[0939] Exhibiting at the Digital Flea Market

[0940] Users can check the scoring results and choose whether or not to exhibit the generated model on the digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by home builders, construction companies, and custom homeowners. Models that do not meet a certain score may also be used in other industries (such as the gaming industry).

[0941] Specific examples

[0942] For example, if a user inputs "A floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," while speaking in an extremely cheerful tone, the server will first analyze this input. The analysis will extract "family of four," "combined living room and dining kitchen," and "furniture: large dining table, sofa, study desk," and the emotion engine will recognize positive emotions.

[0943] The server then uses this information to generate a 3D floor plan model and designs an open space connecting the living room and kitchen. Based on the emotion recognition results, the server adjusts the design to match positive emotions, using a lot of bright interior colors.

[0944] The server then evaluates the generated model to see if it complies with building standards, and assigns a score based on both technical and emotional evaluations. If the model receives a high rating, the user can then exhibit it on a digital flea market, where it can be viewed and purchased by other consumers and businesses.

[0945] In this way, this system allows users to easily generate 3D floor plan models that meet their needs and share them in a digital flea market. Furthermore, by combining this with an emotion engine to analyze users' emotions, the system can generate models that are more satisfying and adapt to the user's emotional state.

[0946] The processing flow will be explained below.

[0947] Step 1:

[0948] Users access the interface and use natural language to input their desired floor plan, family composition, number of furniture, etc. into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desk for the children."

[0949] Step 2:

[0950] The server receives the input natural language data.

[0951] Step 3:

[0952] The server uses a natural language processing (NLP) engine to analyze the received natural language data, specifically by performing grammar analysis, word tokenization, and context understanding.

[0953] Step 4:

[0954] The server extracts important information from the results of natural language analysis, such as the floor plan, family composition, and the type and number of furniture. For example, it extracts elements such as "living room and kitchen combined," "family of three," and "furniture: sofa, dining table, children's desk."

[0955] Step 5:

[0956] The emotion engine recognizes the user's emotions from the text and voice input, for example by analyzing the style of the text, the words used, and the tone and tone of the voice, and classifies the user's emotions as positive, negative, or neutral.

[0957] Step 6:

[0958] The server then begins the process of generating a 3D floor plan model based on the extracted information and the recognized emotion data. First, it designs the basic floor plan layout. Here, it determines the layout of the living room and kitchen, and also plans the layout of the three bedrooms.

[0959] Step 7:

[0960] The server adjusts the model's design elements based on the emotion data, specifically selecting bright interior colors for positive emotions and muted colors for negative emotions.

[0961] Step 8:

[0962] The server references a database of pre-placed rooms and furniture and selects appropriate furniture and room layouts based on the extracted information: specifically, placing a sofa in the living room, a dining table in the kitchen area, and a children's desk in the children's room.

[0963] Step 9:

[0964] The server uses a 3D rendering engine to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[0965] Step 10:

[0966] The server scores the generated 3D model based on building standards and construction techniques. Specifically, it evaluates and assigns a score to minimum ceiling height, earthquake resistance standards, energy efficiency, etc. Emotion recognition results are also fed back into the scoring process, affecting the score.

[0967] Step 11:

[0968] The server generates an evaluation report based on the scoring results and sends it to the user, who can then check the feasibility and legal compliance of the model.

[0969] Step 12:

[0970] Users can review the scoring results and choose whether or not to exhibit the generated 3D model on a digital flea market.

[0971] Step 13:

[0972] If a user wishes to exhibit their 3D model, the server will post it on the digital market, making it available for viewing and purchase by home builders, construction companies, and owners of custom homes.

[0973] Step 14:

[0974] The server will then separately post the low scoring models on a digital marketplace for use in other industries (e.g., the gaming industry).

[0975] In this way, the system allows users to easily define their desired floor plan and visualize it as an emotionally tailored 3D model, allowing them to evaluate the model and deploy it in the appropriate market.

[0976] Example 2

[0977] 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."

[0978] Existing floor plan design systems have the problem that users need specialized knowledge to input their specific preferences, making intuitive operation difficult. Furthermore, it is difficult to create designs that reflect the user's emotions and preferences, which prevents satisfaction from being increased. Furthermore, there are issues with the time-consuming and labor-intensive process of evaluating the quality and suitability of the generated models and releasing them to the market.

[0979] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input desired spatial layout, interior information, household configuration, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; emotion recognition means for recognizing emotions from the tone and text of the user's input; model generation means for automatically generating a 3D spatial layout model based on the extracted information and emotion recognition results; scoring means for scoring the generated 3D spatial layout model based on building standards and technical requirements; and market exhibition means for exhibiting models that have achieved a certain score by the scoring means on a market in a digital space. This allows users to intuitively input their desires in natural language and easily generate, evaluate, and exhibit 3D models that match their emotions on a market.

[0980] A "user" is an entity that uses the system to input information such as desired spatial layout, interior design information, and household configuration in natural language.

[0981] "Natural language" is language used by humans on a daily basis, as opposed to formal program code.

[0982] "Desired spatial arrangement" refers to the layout or arrangement of buildings or rooms desired by the user.

[0983] "Interior information" refers to information about furniture and decorations, and is related to the atmosphere and functionality of a space.

[0984] "Family composition" refers to information such as the number of family members and their age groups.

[0985] "Natural language processing means" refers to technology or equipment that analyzes natural language input by a user and extracts related information.

[0986] An "emotion recognition means" is a technology or device that analyzes emotions from the tone and text content of a user's input and classifies them as positive, negative, neutral, etc.

[0987] "Model generation means" refers to a technology or device that automatically generates a three-dimensional spatial layout model based on the extracted information and emotion recognition results.

[0988] A "3D spatial layout model" is a model that represents the layout and interior of an actual building or room in a three-dimensional visual format.

[0989] A "scoring means" is a technology or device that evaluates whether the generated 3D spatial layout model complies with building standards and technical requirements and assigns a score.

[0990] "Market exhibiting means" refers to a technology or device that exhibits models that have earned a certain score in the digital marketplace, allowing other users and businesses to view and purchase them.

[0991] A "digital market" is a virtual market built on the Internet where 3D models and other items are bought and sold.

[0992] "Technical requirements" are requirements based on specific technical standards or laws and regulations.

[0993] "Tone of input" refers to the pitch and emotion of the voice used when a user inputs information by voice.

[0994] The present invention relates to a system that automatically generates a 3D spatial layout model based on a user's desired spatial layout, interior information, family composition, etc., input in natural language, and further combines it with an emotion engine that recognizes the user's emotions to make adjustments according to the user's emotional state.

[0995] This system is implemented by the following procedure.

[0996] First, the user accesses the interface and inputs their desired spatial layout, interior information, and family composition in natural language into a chat-style input screen. For example, they can input specific requests such as, "I'd like a floor plan with an integrated living room and dining kitchen. It's for a family of four, and I need a large dining table, sofa, and study desk." At this time, the system also inputs the user's tone of voice and emotions from the text.

[0997] The server then receives the input natural language data and analyzes the user's input using a natural language processing (NLP) engine (e.g., GPT-3 or BERT). This extracts information from the input, such as the specific floor plan, furniture layout, and family composition. At the same time, an emotion engine analyzes the user's text and tone of voice and classifies them into positive, negative, or neutral emotion categories.

[0998] The server then begins the process of generating a 3D spatial layout model based on the extracted information and emotion recognition results. First, it designs a basic floor plan, creating an open space connecting the living room and kitchen, for example, and then appropriately arranges the necessary furniture. It also adjusts the model's design, color, and atmosphere based on the emotion recognition results. If the user is in a positive emotional state, it uses a lot of bright interior colors, and if they are in a negative state, it chooses calm colors.

[0999] Furthermore, the server generates a 3D model of the designed floor plan and furniture arrangement using 3D rendering technology (e.g., Blender or Unity), which is provided to the user for visual confirmation.

[1000] The server evaluates whether the generated 3D model complies with building standards and technical requirements, and assigns a technical score. The emotion recognition results of the emotion engine are also taken into account in the evaluation. For example, if the user is very satisfied, the score will be slightly increased.

[1001] Finally, the user reviews the scoring results and chooses whether to exhibit the generated model on a digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by builders, interior decorators, and homeowners. Models that do not meet a certain score may also be used in other industries (e.g., the gaming industry).

[1002] For example, if a user enters the following statement in a very positive tone of voice: "We would like a floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," the server analyzes this and extracts the following information: "Family of four," "Combined living room and dining kitchen," "Large dining table," "Sofa," and "Study desk." The emotion engine recognizes positive emotions. Based on this information, the server creates a 3D model of an open space with a connected living room and kitchen, featuring a brightly colored interior. The server then evaluates this model for compliance with building codes and assigns a high score, reflecting the user's high satisfaction. If the model receives a high rating, it will be exhibited on a digital flea market, where it can be viewed and purchased by other consumers and businesses.

[1003] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1004] Step 1:

[1005] Users access the interface and input their desired spatial layout, interior information, and family composition using natural language.

[1006] Specifically, the user inputs a prompt statement into the terminal such as, "I would like a layout with a combined living room and dining kitchen. It is for a family of four and requires a large dining table, sofa, and study desk."

[1007] Input: User-entered text data

[1008] Output: Sends input text data to the server

[1009] Step 2:

[1010] The server receives the natural language data sent from the terminal.

[1011] Input: Text data received from the user

[1012] Output: Prepare the data for input to the natural language processing engine

[1013] Step 3:

[1014] The server runs a natural language processing (NLP) engine to parse the user's input.

[1015] Specifically, it uses an NLP engine (e.g., GPT-3 or BERT) to analyze the input sentence.

[1016] Input: User-entered text data

[1017] Output: Analyzed information (e.g., floor plan, furniture, family composition)

[1018] Step 4:

[1019] The server uses an emotion engine to analyze the user's text content and tone of voice to recognize emotions.

[1020] Specific actions are classified into positive, negative, and neutral emotional categories.

[1021] Input: User text data and tone of voice

[1022] Output: Emotion recognition result

[1023] Step 5:

[1024] The server starts the process of generating a 3D spatial layout model based on the extracted information and emotion recognition results.

[1025] Specifically, the task involves designing a basic floor plan and properly arranging the necessary furniture.

[1026] Input: Parsed information and emotion recognition results

[1027] Output: Initial 3D spatial layout model

[1028] Step 6:

[1029] The server adjusts the design and color of the 3D model based on the emotion recognition results.

[1030] Specifically, when you are in a positive emotional state, you should use bright colors in your interior, and when you are in a negative emotional state, you should choose calm colors.

[1031] Input: Initial 3D spatial layout model and emotion recognition results

[1032] Output: Emotionally adjusted 3D spatial layout model

[1033] Step 7:

[1034] The server uses 3D rendering technology to generate a 3D model of the designed floor plan and furniture arrangement.

[1035] Specifically, the process involves generating a visual model using 3D modeling software (e.g., Blender or Unity).

[1036] Input: Adjusted 3D spatial layout model

[1037] Output: A finished 3D rendered model

[1038] Step 8:

[1039] The server evaluates whether the generated 3D model complies with building standards and technical requirements and assigns it a score.

[1040] Specifically, it uses a scoring algorithm to evaluate the score and adds emotional evaluation to the technical score.

[1041] Input: A completed 3D rendered model

[1042] Output: Scoring results

[1043] Step 9:

[1044] The user checks the scoring results and decides whether or not to exhibit the generated model on a digital flea market.

[1045] Specifically, the user checks the score through the interface and clicks the "Submit" button.

[1046] Input: Scoring results

[1047] Output: Digital Flea Market exhibit request

[1048] Step 10:

[1049] The server receives the exhibition request and posts the generated model on the digital market.

[1050] Specifically, the model is registered in the digital market database, making it available for other users and vendors to view and purchase.

[1051] Input:Exhibition request

[1052] Output: Model listing on the digital market

[1053] (Application example 2)

[1054] 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."

[1055] Modern users demand efficient interior and layout design for brick-and-mortar stores and adjustments based on their emotions. However, conventional methods require time and effort to change or adjust the design, making it difficult to achieve adaptive designs that reflect the user's emotional state. Furthermore, the scope and usability of the generated designs are limited, and it is also time-consuming to verify that they comply with building regulations.

[1056] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; a natural language processing means for analyzing the input natural language and extracting information; a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information; an emotion identification means for analyzing the user's emotions and adjusting the 3D floor plan model based on the user's emotional state; a scoring means for scoring the generated 3D floor plan model based on building standards and construction techniques; a market exhibiting means for exhibiting models that have achieved a certain score by the scoring means on a market in a digital space; and a means for generating and sharing 3D models for proposing interior and layout designs for physical stores. This allows users to easily generate 3D floor plan models that reflect their desired emotional state and confirm designs that comply with building standards. Furthermore, the system streamlines interior design proposals for physical stores and allows 3D models to be shared and purchased, enabling the creation and utilization of more effective and adaptive designs.

[1057] A "user" is someone who designs the interior and layout of a physical store and generates a 3D floor plan model based on that design.

[1058] "Natural language" is a means by which users input their desired floor plan, furniture information, family composition, etc., and is a language that is used on a daily basis.

[1059] "Natural language processing means" refers to technical means for analyzing input natural language and extracting information.

[1060] The "floor plan generation means" is a technical means for automatically generating a 3D floor plan model based on the extracted information.

[1061] The "emotion identification means" is a means for analyzing the user's emotions and adjusting the 3D floor plan model based on the user's emotional state.

[1062] The "scoring method" is a method for evaluating the generated 3D floor plan model based on building standards and construction techniques and assigning a score.

[1063] "Market exhibiting means" refers to a means for exhibiting models that have achieved a certain score on a market in the digital space.

[1064] "Digital space" refers to markets and platforms in virtual spaces such as the Internet.

[1065] A "physical store" is a store that exists in a physical space and provides goods and services.

[1066] "Layout" refers to the arrangement and design of equipment, furniture, decorations, etc. within a store.

[1067] A "3D floor plan model" is a digital model that visually reproduces the interior and layout of a store in three-dimensional space.

[1068] "Emotional state" is the result of analyzing the user's psychological state and mood.

[1069] As an embodiment of this invention, a system for proposing interior and layout designs for brick-and-mortar stores is described below. This system allows users to input their desired interior and layout designs in natural language, generates a 3D floor plan model based on this, and then uses emotion recognition means to make adjustments according to the user's emotional state. The generated model is evaluated using scoring means based on building standards and construction techniques, and can be exhibited on a digital market.

[1070] The system uses the following major hardware and software:

[1071] 1. Device:

[1072] Smartphone or tablet: A device that allows users to input their desired floor plan in natural language.

[1073] Server: Performs data analysis, model generation, emotion identification, and scoring.

[1074] 2. Software:

[1075] Natural language processing engines (e.g., BERT model from Hugging Face Transformers):

[1076] Analyzes the input natural language and extracts the necessary information.

[1077] Sentiment Identification Engine (e.g. nlptown / bert-base-multilingual-uncased-sentiment):

[1078] Analyzes the user's emotional state and classifies it as positive, negative, or neutral.

[1079] 3D Rendering Engine:

[1080] A 3D floor plan model is generated based on the extracted information.

[1081] Rating and Scoring Engine:

[1082] The generated model is evaluated based on building standards and technology and a score is assigned.

[1083] System Operation

[1084] The server receives a means for users to input their desired floor plan, furniture information, family composition, etc. in natural language using a smartphone or tablet. For example, a user might input, "I want the interior of the cafe to have a woody style, and I want it to have a bright atmosphere." This input is first sent to the server and analyzed by a natural language processing engine.

[1085] Next, the emotion recognition engine analyzes the emotional state of the text entered by the user and classifies it as positive, negative, or neutral. In this example, the user wants to emphasize a positive mood, so the emotion is classified as positive.

[1086] The 3D rendering engine then generates a 3D floor plan model that reflects the desired layout and interior design based on the analyzed information and the results of emotion identification. Based on a positive emotional state, the space is designed using woody materials and bright colors.

[1087] The generated 3D floor plan model is then scored by an evaluation and scoring engine based on building standards and technology, which determines whether the model complies with building standards and its market value.

[1088] Finally, users can post their scored models on a digital marketplace, where other brick-and-mortar store owners and design firms can purchase and use them.

[1089] Prompt sentences in specific examples

[1090] "I want the interior of the cafe to have a woody style. I want the layout to have a bright atmosphere."

[1091] "The floor plan for a family of four is an integrated living room and dining kitchen. The furniture needs include a large dining table, sofa, and study desk."

[1092] In this way, this invention allows users to easily create interior and layout designs that meet their needs and apply them to physical stores. It also allows users to exhibit these designs on the digital market, allowing them to be widely shared.

[1093] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1094] Step 1:

[1095] The user uses a smartphone or tablet to input the desired floor plan, interior, and furniture information in natural language. For example, they might give instructions such as, "I want the interior of the cafe to have a woody style, and I want it to have a bright atmosphere." This input is then sent to the server.

[1096] Input: User input data in natural language

[1097] Output: Natural language input data

[1098] Step 2:

[1099] The server sends the received natural language input data to a natural language processing engine (e.g., the BERT model from Hugging Face Transformers), which analyzes the input data and extracts information about the desired floor plan, interior, and furniture.

[1100] Input: Natural language input data

[1101] Output: Extracted floor plan, interior, and furniture information

[1102] Step 3:

[1103] The server sends the extracted information to an emotion recognition engine (e.g., nlptown / bert-base-multilingual-uncased-sentiment), which analyzes the user's text for emotional states (positive, negative, neutral). This process classifies the user's emotional state.

[1104] Input: Extracted floor plan, interior, and furniture information

[1105] Output: User's emotional state (positive, negative, neutral)

[1106] Step 4:

[1107] The server automatically generates a 3D floor plan model using a 3D rendering engine based on the analyzed floor plan, interior, and furniture information, as well as the user's emotional state. If the user desires a "bright atmosphere," a design using woody materials and bright colors will be applied based on the user's positive emotional state.

[1108] Input: Floor plan, interior, furniture information, and emotional state

[1109] Output: 3D floor plan model

[1110] Step 5:

[1111] The server then sends the generated 3D floor plan model to an evaluation and scoring engine, which evaluates the model's compliance with architectural standards and technology and assigns a technical score based on factors such as how well the model captures light and how efficiently it is positioned.

[1112] Input: 3D floor plan model

[1113] Output: Scoring results

[1114] Step 6:

[1115] The server notifies the user of the scoring results and, if the user wishes, takes steps to have the 3D floor plan model posted on the digital marketplace, allowing other brick-and-mortar store owners and design firms to view and purchase the model.

[1116] Input: Scoring results

[1117] Output: Exhibit on the digital market

[1118] Specific working example:

[1119] A user enters, "A floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk."

[1120] The server analyzes this information and uses an emotion recognition engine to determine that the emotion is positive.

[1121] The 3D rendering engine generates a 3D model of the design using bright colors based on the specified floor plan and furniture arrangement.

[1122] The scoring engine checks compliance with building standards and awards a high score.

[1123] Users can then exhibit this model on a digital marketplace where other interested parties can purchase it.

[1124] This allows users to easily create interior and layout designs that suit their preferences, and even share and utilize those designs on the digital market.

[1125] 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.

[1126] 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.

[1127] 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.

[1128] [Fourth embodiment]

[1129] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1130] 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.

[1131] 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).

[1132] 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.

[1133] 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.

[1134] 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).

[1135] 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.

[1136] 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.

[1137] 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.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] 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."

[1142] This invention relates to a system that automatically generates a 3D floor plan model based on a user's desired floor plan, furniture information, family composition, etc. using natural language, and the realistic model is scored and can be exhibited on a digital flea market. This system allows users to easily design floor plans and provides technology that allows them to share and trade those designs with others.

[1143] System program description

[1144] Accepting input in natural language

[1145] Users access the system's interface and input their desired floor plan, family composition, details of household items, etc. in natural language. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the children."

[1146] natural language analysis

[1147] The server receives natural language requests submitted by users and then uses natural language processing (NLP) techniques to analyze this input and extract information such as specific floor plans, furniture arrangements, and family composition.

[1148] Generate 3D floor plan models

[1149] The server designs a 3D floor plan model based on the extracted elements. For example, it lays out an open space connecting the living room and kitchen, and arranges bedrooms and bathrooms suitable for a family of three. It then extracts the necessary furniture (sofa, dining table, children's desk) from the database and places them in the appropriate locations. Finally, it uses 3D rendering technology to generate a visually checkable 3D model.

[1150] Scoring

[1151] The server then scores the generated 3D model based on building codes and current building technology, including evaluation of ceiling height, seismic standards, energy efficiency, etc. Based on the evaluation, a score is assigned.

[1152] Exhibiting at the Digital Flea Market

[1153] Users can check the scoring results and choose whether or not to exhibit the generated model on the digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by home builders, construction companies, and custom homeowners. Models that do not meet a certain score may be used in other industries (such as the gaming industry).

[1154] Specific examples

[1155] For example, if a user inputs the desired floor plan as "a layout for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," the server first analyzes this input. Through analysis, the following are extracted: "family of four," "combined living room and dining kitchen," and "furniture: large dining table, sofa, and study desk."

[1156] The server then uses this information to generate a 3D floor plan model, designing four bedrooms, a combined living / dining / kitchen area, and furniture arrangements. This model is then rendered in 3D and presented to the user visually.

[1157] The server then evaluates the generated model to see if it complies with building codes and assigns it a technical score. If the score is high, the user can then put the model up on a digital flea market where other consumers and businesses can view and purchase it.

[1158] This system allows users to easily generate 3D floor plan models that meet their needs and then use and share the results on a digital flea market.

[1159] The processing flow will be explained below.

[1160] Step 1:

[1161] Users access the interface and use natural language to input their desired floor plan, family composition, number of furniture pieces, etc. into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs include a sofa, dining table, and desk for the children."

[1162] Step 2:

[1163] The server receives the input natural language data.

[1164] Step 3:

[1165] The server uses a natural language processing (NLP) engine to analyze the received natural language data, specifically by performing grammar analysis, word tokenization, and context understanding.

[1166] Step 4:

[1167] The server extracts important information from the results of natural language analysis, such as the floor plan, family composition, and the type and number of furniture. For example, it extracts elements such as "living room and kitchen combined," "family of three," and "furniture: sofa, dining table, children's desk."

[1168] Step 5:

[1169] The server then uses the extracted information to automatically generate a 3D floor plan model. First, it designs the basic layout of the floor plan. This involves determining how the living room and kitchen will be connected, and planning the layout of the three bedrooms.

[1170] Step 6:

[1171] The server references a database of pre-placed rooms and furniture and selects appropriate furniture and room layouts based on the extracted information: specifically, placing a sofa in the living room, a dining table in the kitchen area, and a children's desk in the children's room.

[1172] Step 7:

[1173] The server uses a 3D rendering engine to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[1174] Step 8:

[1175] The server then scores the generated 3D model based on building standards and construction techniques, such as minimum ceiling height, earthquake resistance standards, and energy efficiency.

[1176] Step 9:

[1177] The server generates an evaluation report based on the scoring results and sends it to the user, who can then check the feasibility and legal compliance of the model.

[1178] Step 10:

[1179] Users can review the scoring results and choose whether or not to exhibit the generated 3D model on a digital flea market.

[1180] Step 11:

[1181] If a user wishes to exhibit their 3D model, the server will post it on the digital market, making it available for viewing and purchase by home builders, construction companies, and owners of custom homes.

[1182] Step 12:

[1183] The server will then separately post the low scoring models on a digital marketplace for use in other industries (e.g., the gaming industry).

[1184] In this way, the system allows users to easily define their desired floor plan, visualize it as a 3D model, evaluate it, and leverage it in the appropriate market.

[1185] Example 1

[1186] 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."

[1187] Modern society demands user-friendly and efficient home designs, which require flexible floor plan designs that can accommodate a wide variety of needs. However, it is difficult for ordinary users without specialized knowledge to design floor plans themselves, and there are limited means for sharing and trading the results with others. To solve this problem, a system is needed that easily realizes users' wishes, evaluates the designs, and automates the entire process of exhibiting them on the market.

[1188] 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.

[1189] In this invention, the server includes: means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; means for analyzing natural language and extracting information; means for automatically generating 3D floor plan models based on the extracted information; means for scoring the generated 3D floor plan models based on building standards and building techniques; means for exhibiting models that have achieved a certain score on a market in a digital space; and means for a user to select an exhibit and for making the exhibited model data available for viewing and trading in the digital space. This enables users to easily generate 3D floor plan models that meet their needs and share and trade the results with others.

[1190] "User" refers to an individual who operates the system to design floor plans and input furniture information.

[1191] "Natural language" refers to a language that is commonly used by humans, and in this case refers to a language that a user uses to input their preferences.

[1192] "Floor plan" refers to the arrangement and configuration of rooms and spaces within a building.

[1193] "Furniture information" refers to detailed information about the furniture to be arranged in the floor plan.

[1194] "Family composition" refers to the number of family members and their relationships within the user's household.

[1195] "Input means" refers to the means by which a user uses natural language to input the desired floor plan, furniture information, family composition, etc.

[1196] "Natural language processing means" refers to technology or systems for analyzing input natural language and extracting necessary information.

[1197] "Floor plan generation means" refers to a system for automatically generating a 3D floor plan model based on the extracted information.

[1198] "3D floor plan model" refers to a three-dimensional digital model of the floor plan generated based on the extracted information.

[1199] "Scoring means" refers to a system for evaluating the generated 3D floor plan model based on certain criteria and assigning a score.

[1200] "Market exhibiting means" refers to a system that allows scored models to be exhibited on a digital marketplace, making them available for viewing and trading.

[1201] "Digital market" refers to a platform provided over the Internet for trading designed 3D models.

[1202] "Construction contractor" refers to a company or individual that designs and constructs buildings.

[1203] A "custom homeowner" refers to an individual who places an order to have a home built based on their own requirements.

[1204] This invention is a system that automatically generates a 3D floor plan model based on a user's natural language input of the desired floor plan, furniture information, family composition, etc., and then scores the model before displaying it at a digital flea market. The main components of this system include an input means, a natural language processing means, a floor plan generation means, a scoring means, and a market exhibition means.

[1205] Users input their desired floor plan, furniture information, family composition, etc. in natural language through the system interface. For example, a user might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the children."

[1206] In the natural language processing means, the server receives input data sent by the user. This data is received by the server's API gateway and then passed to the natural language processing engine. An NLP tool, for example, is used as a natural language processing technology. This analyzes the input natural language and extracts specific elements such as "an open space connecting the living room and kitchen," "a family of three," and "furniture: sofa, dining table, and children's desk."

[1207] The floor plan generation method generates a 3D floor plan model based on the data analyzed by the server. In this process, the server searches the database for appropriate furniture and floor plan templates, and then models them using 3D modeling software such as Blender or SketchUp. The system automatically designs room arrangements and floor plan layouts based on family composition, and generates a 3D model that users can visually check. For example, a layout such as "an open space connecting the living room and kitchen," "a bedroom suitable for a family of three," or "a sofa placed in the center of the living room" may be created.

[1208] In the scoring method, the server scores the generated 3D floor plan model. For this, evaluation criteria such as ceiling height, earthquake resistance standards, and energy efficiency are used, and a scoring algorithm is executed. Evaluation criteria refer to, for example, LEED and CASBEE standards. As a specific example of scoring, the model is scored based on evaluation items such as "high energy efficiency," "earthquake resistance," and "a lot of natural light."

[1209] In the market exhibiting method, the user checks the scoring results provided by the server and chooses whether to exhibit the generated model on the digital flea market. If the user wishes to exhibit, the server uploads the 3D model data to the market in the digital space, where it can be viewed and traded. As a specific example, a scenario can be considered in which the user checks the evaluation results and decides to exhibit the model after confirming that it has a high score.

[1210] A concrete example of a prompt might be the following natural language input:

[1211] "I want an open layout with a connected living room and kitchen. It's for a family of three, and the furniture needs to be a sofa, a dining table, and a desk for the kids."

[1212] "The floor plan for a family of four is an integrated living room and dining kitchen. The furniture needs include a large dining table, sofa, and study desk."

[1213] This system allows users to easily generate 3D floor plan models that meet their needs, even without specialized knowledge, and then share and trade those models with others.

[1214] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1215] Step 1:

[1216] Users input information such as floor plan, furniture, and family composition in natural language through the system interface, via a text area in a web browser or mobile app.

[1217] Example: "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desks for the kids."

[1218] Output of this step: Natural language input data.

[1219] Step 2:

[1220] The server receives the input data sent by the user and passes it to a natural language processing engine. NLP technology is used to analyze the input data and extract specific floor plan elements, furniture information, family composition, and other information.

[1221] Examples of software used: NLP tools (e.g., Google Cloud Natural Language API) as natural language processing engines.

[1222] Input: "I want an open plan with a living room and kitchen connected to each other. It will accommodate a family of three, and the furniture will need to include a sofa, a dining table, and desks for the kids."

[1223] Output of this step: Analysis results (element extraction data) "Living room and kitchen", "Family of three", "Furniture: sofa, dining table, children's desk".

[1224] Step 3:

[1225] The server generates a 3D floor plan model based on the extracted information, searches for appropriate furniture and floor plan templates in a database, and creates the model using 3D modeling software.

[1226] Hardware and software used: 3D modeling software (e.g. Blender, SketchUp).

[1227] Specific actions: Open space connecting the living room and kitchen, bedrooms suitable for a family of three, bathrooms, and furniture (sofa, dining table, children's desk) properly arranged.

[1228] Input for this step: Element extraction data.

[1229] Output of this step: 3D floor plan model.

[1230] Step 4:

[1231] The server scores the generated 3D floor plan model, using criteria such as ceiling height, earthquake resistance standards, and energy efficiency. A unique scoring algorithm is run to assign a score.

[1232] Criteria and tools used: Scoring tools based on LEED and CASBEE standards.

[1233] Input for this step: 3D floor plan model.

[1234] Output of this step: Scoring result (assigned score).

[1235] Step 5:

[1236] The user checks the scoring results provided by the server and chooses whether or not to exhibit the generated model on the digital flea market. If the user wishes to exhibit, the server uploads the 3D model data to the market in the digital space. Exhibited models can be viewed and traded by construction companies and owners of custom-built homes.

[1237] Specific operation: Click the "Exhibit" button displayed on the interface, and the server will upload the model data.

[1238] Inputs for this step: Scoring results, user selection.

[1239] Output of this step: a 3D model published on a digital marketplace.

[1240] In this way, this system generates 3D floor plan models from user input and automates the process of evaluating and exhibiting those models, making it easy for users to design floor plans and share and trade the results.

[1241] (Application example 1)

[1242] 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."

[1243] Currently, designing homes and interiors requires a high level of specialized knowledge, making it difficult for average users to easily design floor plans and consider furniture arrangements based on their own preferences. However, a system that automatically generates 3D floor plan models by simply inputting users' preferences and requirements in natural language, and then evaluates and visualizes the models and exhibits them on a digital flea market would be useful. This system would allow users to easily design floor plans and share and trade them with others, greatly simplifying the design process.

[1244] 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.

[1245] In this invention, the server includes: means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; floor plan generation means for automatically generating 3D floor plan models based on the extracted information; scoring means for scoring the generated 3D floor plan models based on building standards and building techniques; means for visually displaying the generated 3D floor plan models in a digital space; means for a user to review and make a decision on models that have received a certain score by the scoring means; and market exhibition means for exhibiting the models reviewed and decided upon by the user in a market in the digital space. This enables users to easily design floor plans and furniture arrangements based on their own preferences, evaluate and visualize the designs, and exhibit them in a flea market.

[1246] "Natural language processing means" is a technology for analyzing natural language sentences entered by users and extracting meaning and information.

[1247] A "3D floor plan model" refers to a design drawing visualized in three-dimensional space based on information such as the user's desired floor plan and furniture placement.

[1248] The "scoring method" is a method for evaluating whether the generated 3D floor plan model complies with building standards and construction techniques, and assigning a score.

[1249] The "market exhibit method" is a method of posting 3D floor plan models that have received a certain score on a digital marketplace, allowing other users and businesses to view and purchase them.

[1250] "Visual display means" refers to technology that displays the generated 3D floor plan model on the screen of a digital device, allowing users to check and consider it in real time.

[1251] "Means that allow users to consider and make decisions" refers to a means by which users can review the scored 3D model and decide whether or not to adopt it.

[1252] The present invention relates to a system that allows users to input their desired floor plan, furniture information, family composition, etc. using natural language, and then automatically generates a 3D floor plan model based on that information, scores it, and exhibits it on a digital flea market.

[1253] The system is implemented using the following hardware and software:

[1254] Hardware: smartphones, tablets, servers

[1255] Software: Python, Flask (web framework), natural language processing library (e.g. spaCy), 3D modeling library (e.g. Three.js)

[1256] The server first receives a request sent in natural language by the user. Specifically, the user inputs the desired floor plan, furniture information, family composition, etc. in natural language. For example, the user might input, "A spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk."

[1257] The server then uses natural language processing technology to analyze this input and extract information such as the specific floor plan, furniture layout, and family composition. This information is then used to generate a 3D floor plan model. The 3D model generated at this stage is then laid out based on the user's preferences, such as an open kitchen or a living room layout suitable for a family of four.

[1258] The generated 3D floor plan model is then scored based on building standards and construction techniques. For example, earthquake resistance standards and energy efficiency are evaluated, and a score is assigned based on the evaluation results. After viewing the scoring results, users can then choose whether or not to exhibit the generated model on the digital flea market.

[1259] Visually, the generated 3D model is displayed in real time on the screen of a smartphone or tablet, allowing users to inspect the model in detail, making it easy to consider whether the floor plan and furniture arrangement are exactly as they wanted.

[1260] Finally, the 3D model that the user has considered and decided on will be exhibited on a digital flea market, where other users and vendors can view and purchase it. Models that do not meet a certain score may be used in other fields (such as games or education).

[1261] As a concrete example:

[1262] If a user wants a floor plan and furniture arrangement for a family of four,

[1263] Users input "A spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk as furniture." The server analyzes this input and extracts the elements of a family of four, a spacious living room, an open kitchen, a sofa, a dining set, and a study desk. A 3D floor plan model is generated based on these elements and scored based on architectural standards. Based on the evaluation results, users can exhibit the model at a flea market.

[1264] Example prompts for generative AI models

[1265] "We are looking for a floor plan and furniture arrangement for a family of four. It should have a large living room and an open kitchen. The furniture should include a sofa, dining set, and study desk. Please generate and score appropriate 3D models."

[1266] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1267] Step 1:

[1268] Using a smartphone or tablet, the user inputs details such as the desired floor plan, furniture, and family composition in natural language. For example, they might input "a spacious living room and open kitchen for a family of four, with a sofa, dining set, and study desk." The input natural language is sent to the system.

[1269] Input: Natural language request

[1270] Output: Send data to the server

[1271] Step 2:

[1272] The server analyzes the received natural language input, using natural language processing (NLP) techniques to parse the input sentences and extract the necessary information (e.g., family composition, floor plan type, required furniture items).

[1273] Input: Natural language input data

[1274] Output: Extracted information (family composition, floor plan, furniture information)

[1275] Step 3:

[1276] The server generates a 3D floor plan model based on the extracted information. Specifically, it uses 3D modeling technology to automatically create a floor plan design, including an open kitchen, living room, furniture arrangement, and more, and creates a 3D model that can be visually confirmed.

[1277] Input: Extracted information

[1278] Output: 3D floor plan model

[1279] Step 4:

[1280] The server then scores the generated 3D floor plan model based on building standards and construction techniques. In this step, scores are assigned using evaluation criteria such as earthquake resistance standards and energy efficiency to evaluate the quality of the model.

[1281] Input: 3D floor plan model

[1282] Output: Scoring results

[1283] Step 5:

[1284] The server then uses a means to visually display the scoring results and displays the 3D model to the user, allowing the user to check and consider their desired floor plan and furniture arrangement in real time.

[1285] Input: Scoring results, 3D model

[1286] Output: 3D model displayed on a smartphone or tablet

[1287] Step 6:

[1288] Users review the generated 3D model and its scoring results and decide whether to exhibit it in the digital flea market. The results of their decision are sent to the system.

[1289] Input: User decision

[1290] Output: Sending data to the system

[1291] Step 7:

[1292] The server will display the models that users have decided to exhibit in a digital flea market. Models that do not meet a certain score may be used in other fields (such as games or education).

[1293] Input: The model that the user has decided to exhibit

[1294] Output: Exhibit at the digital flea market

[1295] 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.

[1296] This invention relates to a system that automatically generates a 3D floor plan model based on a user's desired floor plan, furniture information, family composition, etc., input in natural language, and then combines it with an emotion engine that recognizes the user's emotions to adjust the model according to the user's emotional state. This system allows users to easily design floor plans and provides technology that allows the model to adapt to the user's mood and emotions.

[1297] System program description

[1298] Accepting input in natural language

[1299] Users access the interface and input their desired floor plan, family composition, number of furniture, etc. in natural language into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desk for the children." At this time, the system also inputs the user's tone of voice and emotions from the text.

[1300] Natural Language Analysis and Emotion Recognition

[1301] The server receives the input natural language and emotion data. It uses a natural language processing (NLP) engine to analyze the input sentences and extract information such as the specific floor plan, furniture layout, and family composition. At the same time, the emotion engine analyzes the user's text and tone of voice and classifies them into positive, negative, or neutral emotion categories.

[1302] 3D floor plan model generation and emotional feedback

[1303] The server then begins the process of generating a 3D floor plan model based on the extracted information and emotion recognition results. First, it designs a basic floor plan layout, for example, laying out an open space connecting the living room and kitchen, and arranging three bedrooms. It also appropriately adjusts the model's design, color, and atmosphere based on the emotion recognition results. For example, if the user is in a positive emotional state, it may use more brightly colored interiors, and if they are in a negative emotional state, it may choose more subdued colors.

[1304] 3D rendering

[1305] The server uses 3D rendering technology to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[1306] Scoring

[1307] The server evaluates whether the generated 3D model complies with building standards and construction techniques, and assigns a technical score. The emotion recognition results of the emotion engine are also fed back into the scoring, affecting the score. For example, if the user is very satisfied, the score may be slightly increased.

[1308] Exhibiting at the Digital Flea Market

[1309] Users can check the scoring results and choose whether or not to exhibit the generated model on the digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by home builders, construction companies, and custom homeowners. Models that do not meet a certain score may also be used in other industries (such as the gaming industry).

[1310] Specific examples

[1311] For example, if a user inputs "A floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," while speaking in an extremely cheerful tone, the server will first analyze this input. The analysis will extract "family of four," "combined living room and dining kitchen," and "furniture: large dining table, sofa, study desk," and the emotion engine will recognize positive emotions.

[1312] The server then uses this information to generate a 3D floor plan model and designs an open space connecting the living room and kitchen. Based on the emotion recognition results, the server adjusts the design to match positive emotions, using a lot of bright interior colors.

[1313] The server then evaluates the generated model to see if it complies with building standards, and assigns a score based on both technical and emotional evaluations. If the model receives a high rating, the user can then exhibit it on a digital flea market, where it can be viewed and purchased by other consumers and businesses.

[1314] In this way, this system allows users to easily generate 3D floor plan models that meet their needs and share them in a digital flea market. Furthermore, by combining this with an emotion engine to analyze users' emotions, the system can generate models that are more satisfying and adapt to the user's emotional state.

[1315] The processing flow will be explained below.

[1316] Step 1:

[1317] Users access the interface and use natural language to input their desired floor plan, family composition, number of furniture, etc. into a chat-style input screen. For example, they might input, "I want an open floor plan with a connected living room and kitchen. It's for a family of three, and the furniture needs to include a sofa, dining table, and desk for the children."

[1318] Step 2:

[1319] The server receives the input natural language data.

[1320] Step 3:

[1321] The server uses a natural language processing (NLP) engine to analyze the received natural language data, specifically by performing grammar analysis, word tokenization, and context understanding.

[1322] Step 4:

[1323] The server extracts important information from the results of natural language analysis, such as the floor plan, family composition, and the type and number of furniture. For example, it extracts elements such as "living room and kitchen combined," "family of three," and "furniture: sofa, dining table, children's desk."

[1324] Step 5:

[1325] The emotion engine recognizes the user's emotions from the text and voice input, for example by analyzing the style of the text, the words used, and the tone and tone of the voice, and classifies the user's emotions as positive, negative, or neutral.

[1326] Step 6:

[1327] The server then begins the process of generating a 3D floor plan model based on the extracted information and the recognized emotion data. First, it designs the basic floor plan layout. Here, it determines the layout of the living room and kitchen, and also plans the layout of the three bedrooms.

[1328] Step 7:

[1329] The server adjusts the model's design elements based on the emotion data, specifically selecting bright interior colors for positive emotions and muted colors for negative emotions.

[1330] Step 8:

[1331] The server references a database of pre-placed rooms and furniture and selects appropriate furniture and room layouts based on the extracted information: specifically, placing a sofa in the living room, a dining table in the kitchen area, and a children's desk in the children's room.

[1332] Step 9:

[1333] The server uses a 3D rendering engine to generate a 3D model of the designed floor plan and furniture arrangement, which is then provided to the user for visual confirmation.

[1334] Step 10:

[1335] The server scores the generated 3D model based on building standards and construction techniques. Specifically, it evaluates and assigns a score to minimum ceiling height, earthquake resistance standards, energy efficiency, etc. Emotion recognition results are also fed back into the scoring process, affecting the score.

[1336] Step 11:

[1337] The server generates an evaluation report based on the scoring results and sends it to the user, who can then check the feasibility and legal compliance of the model.

[1338] Step 12:

[1339] Users can review the scoring results and choose whether or not to exhibit the generated 3D model on a digital flea market.

[1340] Step 13:

[1341] If a user wishes to exhibit their 3D model, the server will post it on the digital market, making it available for viewing and purchase by home builders, construction companies, and owners of custom homes.

[1342] Step 14:

[1343] The server will then separately post the low scoring models on a digital marketplace for use in other industries (e.g., the gaming industry).

[1344] In this way, the system allows users to easily define their desired floor plan and visualize it as an emotionally tailored 3D model, allowing them to evaluate the model and deploy it in the appropriate market.

[1345] Example 2

[1346] 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."

[1347] Existing floor plan design systems have the problem that users need specialized knowledge to input their specific preferences, making intuitive operation difficult. Furthermore, it is difficult to create designs that reflect the user's emotions and preferences, which prevents satisfaction from being increased. Furthermore, there are issues with the time-consuming and labor-intensive process of evaluating the quality and suitability of the generated models and releasing them to the market.

[1348] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input desired spatial layout, interior information, household configuration, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; emotion recognition means for recognizing emotions from the tone and text of the user's input; model generation means for automatically generating a 3D spatial layout model based on the extracted information and emotion recognition results; scoring means for scoring the generated 3D spatial layout model based on building standards and technical requirements; and market exhibition means for exhibiting models that have achieved a certain score by the scoring means on a market in a digital space. This allows users to intuitively input their desires in natural language and easily generate, evaluate, and exhibit 3D models that match their emotions on a market.

[1349] A "user" is an entity that uses the system to input information such as desired spatial layout, interior design information, and household configuration in natural language.

[1350] "Natural language" is language used by humans on a daily basis, as opposed to formal program code.

[1351] "Desired spatial arrangement" refers to the layout or arrangement of buildings or rooms desired by the user.

[1352] "Interior information" refers to information about furniture and decorations, and is related to the atmosphere and functionality of a space.

[1353] "Family composition" refers to information such as the number of family members and their age groups.

[1354] "Natural language processing means" refers to technology or equipment that analyzes natural language input by a user and extracts related information.

[1355] An "emotion recognition means" is a technology or device that analyzes emotions from the tone and text content of a user's input and classifies them as positive, negative, neutral, etc.

[1356] "Model generation means" refers to a technology or device that automatically generates a three-dimensional spatial layout model based on the extracted information and emotion recognition results.

[1357] A "3D spatial layout model" is a model that represents the layout and interior of an actual building or room in a three-dimensional visual format.

[1358] A "scoring means" is a technology or device that evaluates whether the generated 3D spatial layout model complies with building standards and technical requirements and assigns a score.

[1359] "Market exhibiting means" refers to a technology or device that exhibits models that have earned a certain score in the digital marketplace, allowing other users and businesses to view and purchase them.

[1360] A "digital market" is a virtual market built on the Internet where 3D models and other items are bought and sold.

[1361] "Technical requirements" are requirements based on specific technical standards or laws and regulations.

[1362] "Tone of input" refers to the pitch and emotion of the voice used when a user inputs information by voice.

[1363] The present invention relates to a system that automatically generates a 3D spatial layout model based on a user's desired spatial layout, interior information, family composition, etc., input in natural language, and further combines it with an emotion engine that recognizes the user's emotions to make adjustments according to the user's emotional state.

[1364] This system is implemented by the following procedure.

[1365] First, the user accesses the interface and inputs their desired spatial layout, interior information, and family composition in natural language into a chat-style input screen. For example, they can input specific requests such as, "I'd like a floor plan with an integrated living room and dining kitchen. It's for a family of four, and I need a large dining table, sofa, and study desk." At this time, the system also inputs the user's tone of voice and emotions from the text.

[1366] The server then receives the input natural language data and analyzes the user's input using a natural language processing (NLP) engine (e.g., GPT-3 or BERT). This extracts information from the input, such as the specific floor plan, furniture layout, and family composition. At the same time, an emotion engine analyzes the user's text and tone of voice and classifies them into positive, negative, or neutral emotion categories.

[1367] The server then begins the process of generating a 3D spatial layout model based on the extracted information and emotion recognition results. First, it designs a basic floor plan, creating an open space connecting the living room and kitchen, for example, and then appropriately arranges the necessary furniture. It also adjusts the model's design, color, and atmosphere based on the emotion recognition results. If the user is in a positive emotional state, it uses a lot of bright interior colors, and if they are in a negative state, it chooses calm colors.

[1368] Furthermore, the server generates a 3D model of the designed floor plan and furniture arrangement using 3D rendering technology (e.g., Blender or Unity), which is provided to the user for visual confirmation.

[1369] The server evaluates whether the generated 3D model complies with building standards and technical requirements, and assigns a technical score. The emotion recognition results of the emotion engine are also taken into account in the evaluation. For example, if the user is very satisfied, the score will be slightly increased.

[1370] Finally, the user reviews the scoring results and chooses whether to exhibit the generated model on a digital flea market. If the user chooses to exhibit, the server will post the model on the digital market, where it can be viewed and purchased by builders, interior decorators, and homeowners. Models that do not meet a certain score may also be used in other industries (e.g., the gaming industry).

[1371] For example, if a user enters the following statement in a very positive tone of voice: "We would like a floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk," the server analyzes this and extracts the following information: "Family of four," "Combined living room and dining kitchen," "Large dining table," "Sofa," and "Study desk." The emotion engine recognizes positive emotions. Based on this information, the server creates a 3D model of an open space with a connected living room and kitchen, featuring a brightly colored interior. The server then evaluates this model for compliance with building codes and assigns a high score, reflecting the user's high satisfaction. If the model receives a high rating, it will be exhibited on a digital flea market, where it can be viewed and purchased by other consumers and businesses.

[1372] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1373] Step 1:

[1374] Users access the interface and input their desired spatial layout, interior information, and family composition using natural language.

[1375] Specifically, the user inputs a prompt statement into the terminal such as, "I would like a layout with a combined living room and dining kitchen. It is for a family of four and requires a large dining table, sofa, and study desk."

[1376] Input: User-entered text data

[1377] Output: Sends input text data to the server

[1378] Step 2:

[1379] The server receives the natural language data sent from the terminal.

[1380] Input: Text data received from the user

[1381] Output: Prepare the data for input to the natural language processing engine

[1382] Step 3:

[1383] The server runs a natural language processing (NLP) engine to parse the user's input.

[1384] Specifically, it uses an NLP engine (e.g., GPT-3 or BERT) to analyze the input sentence.

[1385] Input: User-entered text data

[1386] Output: Analyzed information (e.g., floor plan, furniture, family composition)

[1387] Step 4:

[1388] The server uses an emotion engine to analyze the user's text content and tone of voice to recognize emotions.

[1389] Specific actions are classified into positive, negative, and neutral emotional categories.

[1390] Input: User text data and tone of voice

[1391] Output: Emotion recognition result

[1392] Step 5:

[1393] The server starts the process of generating a 3D spatial layout model based on the extracted information and emotion recognition results.

[1394] Specifically, the task involves designing a basic floor plan and properly arranging the necessary furniture.

[1395] Input: Parsed information and emotion recognition results

[1396] Output: Initial 3D spatial layout model

[1397] Step 6:

[1398] The server adjusts the design and color of the 3D model based on the emotion recognition results.

[1399] Specifically, when you are in a positive emotional state, you should use bright colors in your interior, and when you are in a negative emotional state, you should choose calm colors.

[1400] Input: Initial 3D spatial layout model and emotion recognition results

[1401] Output: Emotionally adjusted 3D spatial layout model

[1402] Step 7:

[1403] The server uses 3D rendering technology to generate a 3D model of the designed floor plan and furniture arrangement.

[1404] Specifically, the process involves generating a visual model using 3D modeling software (e.g., Blender or Unity).

[1405] Input: Adjusted 3D spatial layout model

[1406] Output: A finished 3D rendered model

[1407] Step 8:

[1408] The server evaluates whether the generated 3D model complies with building standards and technical requirements and assigns it a score.

[1409] Specifically, it uses a scoring algorithm to evaluate the score and adds emotional evaluation to the technical score.

[1410] Input: A completed 3D rendered model

[1411] Output: Scoring results

[1412] Step 9:

[1413] The user checks the scoring results and decides whether or not to exhibit the generated model on a digital flea market.

[1414] Specifically, the user checks the score through the interface and clicks the "Submit" button.

[1415] Input: Scoring results

[1416] Output: Digital Flea Market exhibit request

[1417] Step 10:

[1418] The server receives the exhibition request and posts the generated model on the digital market.

[1419] Specifically, the model is registered in the digital market database, making it available for other users and vendors to view and purchase.

[1420] Input:Exhibition request

[1421] Output: Model listing on the digital market

[1422] (Application example 2)

[1423] 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."

[1424] Modern users demand efficient interior and layout design for brick-and-mortar stores and adjustments based on their emotions. However, conventional methods require time and effort to change or adjust the design, making it difficult to achieve adaptive designs that reflect the user's emotional state. Furthermore, the scope and usability of the generated designs are limited, and it is also time-consuming to verify that they comply with building regulations.

[1425] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input desired floor plans, furniture information, family composition, etc. in natural language; a natural language processing means for analyzing the input natural language and extracting information; a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information; an emotion identification means for analyzing the user's emotions and adjusting the 3D floor plan model based on the user's emotional state; a scoring means for scoring the generated 3D floor plan model based on building standards and construction techniques; a market exhibiting means for exhibiting models that have achieved a certain score by the scoring means on a market in a digital space; and a means for generating and sharing 3D models for proposing interior and layout designs for physical stores. This allows users to easily generate 3D floor plan models that reflect their desired emotional state and confirm designs that comply with building standards. Furthermore, the system streamlines interior design proposals for physical stores and allows 3D models to be shared and purchased, enabling the creation and utilization of more effective and adaptive designs.

[1426] A "user" is someone who designs the interior and layout of a physical store and generates a 3D floor plan model based on that design.

[1427] "Natural language" is a means by which users input their desired floor plan, furniture information, family composition, etc., and is a language that is used on a daily basis.

[1428] "Natural language processing means" refers to technical means for analyzing input natural language and extracting information.

[1429] The "floor plan generation means" is a technical means for automatically generating a 3D floor plan model based on the extracted information.

[1430] The "emotion identification means" is a means for analyzing the user's emotions and adjusting the 3D floor plan model based on the user's emotional state.

[1431] The "scoring method" is a method for evaluating the generated 3D floor plan model based on building standards and construction techniques and assigning a score.

[1432] "Market exhibiting means" refers to a means for exhibiting models that have achieved a certain score on a market in the digital space.

[1433] "Digital space" refers to markets and platforms in virtual spaces such as the Internet.

[1434] A "physical store" is a store that exists in a physical space and provides goods and services.

[1435] "Layout" refers to the arrangement and design of equipment, furniture, decorations, etc. within a store.

[1436] A "3D floor plan model" is a digital model that visually reproduces the interior and layout of a store in three-dimensional space.

[1437] "Emotional state" is the result of analyzing the user's psychological state and mood.

[1438] As an embodiment of this invention, a system for proposing interior and layout designs for brick-and-mortar stores is described below. This system allows users to input their desired interior and layout designs in natural language, generates a 3D floor plan model based on this, and then uses emotion recognition means to make adjustments according to the user's emotional state. The generated model is evaluated using scoring means based on building standards and construction techniques, and can be exhibited on a digital market.

[1439] The system uses the following major hardware and software:

[1440] 1. Device:

[1441] Smartphone or tablet: A device that allows users to input their desired floor plan in natural language.

[1442] Server: Performs data analysis, model generation, emotion identification, and scoring.

[1443] 2. Software:

[1444] Natural language processing engines (e.g., BERT model from Hugging Face Transformers):

[1445] Analyzes the input natural language and extracts the necessary information.

[1446] Sentiment Identification Engine (e.g. nlptown / bert-base-multilingual-uncased-sentiment):

[1447] Analyzes the user's emotional state and classifies it as positive, negative, or neutral.

[1448] 3D Rendering Engine:

[1449] A 3D floor plan model is generated based on the extracted information.

[1450] Rating and Scoring Engine:

[1451] The generated model is evaluated based on building standards and technology and a score is assigned.

[1452] System Operation

[1453] The server receives a means for users to input their desired floor plan, furniture information, family composition, etc. in natural language using a smartphone or tablet. For example, a user might input, "I want the interior of the cafe to have a woody style, and I want it to have a bright atmosphere." This input is first sent to the server and analyzed by a natural language processing engine.

[1454] Next, the emotion recognition engine analyzes the emotional state of the text entered by the user and classifies it as positive, negative, or neutral. In this example, the user wants to emphasize a positive mood, so the emotion is classified as positive.

[1455] The 3D rendering engine then generates a 3D floor plan model that reflects the desired layout and interior design based on the analyzed information and the results of emotion identification. Based on a positive emotional state, the space is designed using woody materials and bright colors.

[1456] The generated 3D floor plan model is then scored by an evaluation and scoring engine based on building standards and technology, which determines whether the model complies with building standards and its market value.

[1457] Finally, users can post their scored models on a digital marketplace, where other brick-and-mortar store owners and design firms can purchase and use them.

[1458] Prompt sentences in specific examples

[1459] "I want the interior of the cafe to have a woody style. I want the layout to have a bright atmosphere."

[1460] "The floor plan for a family of four is an integrated living room and dining kitchen. The furniture needs include a large dining table, sofa, and study desk."

[1461] In this way, this invention allows users to easily create interior and layout designs that meet their needs and apply them to physical stores. It also allows users to exhibit these designs on the digital market, allowing them to be widely shared.

[1462] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1463] Step 1:

[1464] The user uses a smartphone or tablet to input the desired floor plan, interior, and furniture information in natural language. For example, they might give instructions such as, "I want the interior of the cafe to have a woody style, and I want it to have a bright atmosphere." This input is then sent to the server.

[1465] Input: User input data in natural language

[1466] Output: Natural language input data

[1467] Step 2:

[1468] The server sends the received natural language input data to a natural language processing engine (e.g., the BERT model from Hugging Face Transformers), which analyzes the input data and extracts information about the desired floor plan, interior, and furniture.

[1469] Input: Natural language input data

[1470] Output: Extracted floor plan, interior, and furniture information

[1471] Step 3:

[1472] The server sends the extracted information to an emotion recognition engine (e.g., nlptown / bert-base-multilingual-uncased-sentiment), which analyzes the user's text for emotional states (positive, negative, neutral). This process classifies the user's emotional state.

[1473] Input: Extracted floor plan, interior, and furniture information

[1474] Output: User's emotional state (positive, negative, neutral)

[1475] Step 4:

[1476] The server automatically generates a 3D floor plan model using a 3D rendering engine based on the analyzed floor plan, interior, and furniture information, as well as the user's emotional state. If the user desires a "bright atmosphere," a design using woody materials and bright colors will be applied based on the user's positive emotional state.

[1477] Input: Floor plan, interior, furniture information, and emotional state

[1478] Output: 3D floor plan model

[1479] Step 5:

[1480] The server then sends the generated 3D floor plan model to an evaluation and scoring engine, which evaluates the model's compliance with architectural standards and technology and assigns a technical score based on factors such as how well the model captures light and how efficiently it is positioned.

[1481] Input: 3D floor plan model

[1482] Output: Scoring results

[1483] Step 6:

[1484] The server notifies the user of the scoring results and, if the user wishes, takes steps to have the 3D floor plan model posted on the digital marketplace, allowing other brick-and-mortar store owners and design firms to view and purchase the model.

[1485] Input: Scoring results

[1486] Output: Exhibit on the digital market

[1487] Specific working example:

[1488] A user enters, "A floor plan for a family of four with a combined living room and dining kitchen. Furniture needs include a large dining table, sofa, and study desk."

[1489] The server analyzes this information and uses an emotion recognition engine to determine that the emotion is positive.

[1490] The 3D rendering engine generates a 3D model of the design using bright colors based on the specified floor plan and furniture arrangement.

[1491] The scoring engine checks compliance with building standards and awards a high score.

[1492] Users can then exhibit this model on a digital marketplace where other interested parties can purchase it.

[1493] This allows users to easily create interior and layout designs that suit their preferences, and even share and utilize those designs on the digital market.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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).

[1501] 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.

[1502] 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."

[1503] 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.

[1504] 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).

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] 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.

[1515] The following is further disclosed regarding the above embodiment.

[1516] (Claim 1)

[1517] A means for users to input desired floor plan, furniture information, family composition, etc. in natural language;

[1518] natural language processing means for analyzing the input natural language and extracting information;

[1519] a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information;

[1520] a scoring means for scoring the generated 3D floor plan model based on building standards and building techniques;

[1521] a market exhibiting means for exhibiting a model that has received a certain score by the scoring means on a market in a digital space;

[1522] A system including:

[1523] (Claim 2)

[1524] 2. The system according to claim 1, wherein the scoring means evaluates whether the generated 3D floor plan model complies with the Building Standards Act and assigns a score based on the evaluation result.

[1525] (Claim 3)

[1526] The system of claim 1, wherein the market exhibiting means is a means for making models that have achieved a certain score in the digital market available for purchase by home builders, construction companies, or owners of custom-built homes, and includes a means for making models that do not meet the certain score available for use in other industries.

[1527] "Example 1"

[1528] (Claim 1)

[1529] A means for users to input desired floor plan, furniture information, family composition, etc. in natural language;

[1530] natural language processing means for analyzing the input natural language and extracting information;

[1531] a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information;

[1532] a scoring means for scoring the generated 3D floor plan model based on building standards and building techniques;

[1533] a market exhibiting means for exhibiting a model that has received a certain score by the scoring means on a market in a digital space;

[1534] The market exhibiting means includes a means for a user to select an exhibit, and a means for making the exhibited model data available for viewing and trading in a digital space;

[1535] A system including:

[1536] (Claim 2)

[1537] 2. The system according to claim 1, wherein the scoring means evaluates whether the generated 3D floor plan model complies with the Building Standards Act and assigns a score based on the evaluation result.

[1538] (Claim 3)

[1539] The system of claim 1, wherein the market exhibiting means is a means for making models that have achieved a certain score in the digital market available for purchase by builders or owners of custom-built homes, and includes a means for making models that do not meet the certain score available for use in other industries.

[1540] "Application Example 1"

[1541] (Claim 1)

[1542] A means for users to input desired floor plan, furniture information, family composition, etc. in natural language;

[1543] natural language processing means for analyzing the input natural language and extracting information;

[1544] a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information;

[1545] a scoring means for scoring the generated 3D floor plan model based on building standards and building techniques;

[1546] a means for visually displaying the generated 3D floor plan model in a digital space;

[1547] A means for allowing a user to review and make decisions about models that have received a certain score by the scoring means;

[1548] a market exhibiting means for exhibiting the model that the user has considered and decided on in a market in a digital space;

[1549] A system including:

[1550] (Claim 2)

[1551] 2. The system according to claim 1, wherein the scoring means evaluates whether the generated 3D floor plan model complies with the Building Standards Act and assigns a score based on the evaluation result.

[1552] (Claim 3)

[1553] The system of claim 1, wherein the market exhibiting means is a means for making models that have achieved a certain score in the digital market available for purchase by construction companies, home builders, or custom homeowners, and includes a means for making models that do not meet the certain score available for use in other fields.

[1554] "Example 2: Combining Emotion Engines"

[1555] (Claim 1)

[1556] A means for users to input desired spatial layout, interior information, household configuration, etc. in natural language;

[1557] natural language processing means for analyzing the input natural language and extracting information;

[1558] an emotion recognition means for recognizing emotions from the tone or text of a user's input;

[1559] a model generation means for automatically generating a 3D spatial layout model based on the extracted information and emotion recognition results;

[1560] a scoring means for scoring the generated 3D spatial layout model based on architectural standards and technical requirements;

[1561] a market exhibiting means for exhibiting a model that has received a certain score by the scoring means on a market in a digital space;

[1562] A system including:

[1563] (Claim 2)

[1564] 2. The system according to claim 1, wherein the scoring means evaluates whether the generated 3D spatial layout model complies with building code requirements and assigns a score based on the evaluation result.

[1565] (Claim 3)

[1566] The system of claim 1, wherein the market exhibiting means makes models that have achieved a certain score available for purchase by construction companies, interior decorators, or homeowners on a digital marketplace, and includes means for making models that do not meet the certain score available to other industries.

[1567] "Application example 2 when combining emotion engines"

[1568] (Claim 1)

[1569] A means for users to input desired floor plan, furniture information, family composition, etc. in natural language;

[1570] natural language processing means for analyzing the input natural language and extracting information;

[1571] a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information;

[1572] an emotion identification means for analyzing the emotion of the user and adjusting the 3D floor plan model based on the emotional state of the user;

[1573] a scoring means for scoring the generated 3D floor plan model based on building standards and building techniques;

[1574] a market exhibiting means for exhibiting a model that has received a certain score by the scoring means on a market in a digital space;

[1575] A means to generate and share 3D models to propose interior and layout designs for physical stores,

[1576] A system including:

[1577] (Claim 2)

[1578] 2. The system according to claim 1, wherein the scoring means evaluates whether the generated 3D floor plan model complies with the Building Standards Act and assigns a score based on the evaluation result.

[1579] (Claim 3)

[1580] The system of claim 1, wherein the market exhibiting means is a means for making models that have achieved a certain score in the digital market available for purchase by home builders, construction companies, or owners of custom-built homes, and includes a means for making models that do not meet the certain score available for use in other industries. [Explanation of symbols]

[1581] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to input desired floor plan, furniture information, family composition, etc. in natural language; natural language processing means for analyzing the input natural language and extracting information; a floor plan generation means for automatically generating a 3D floor plan model based on the extracted information; a scoring means for scoring the generated 3D floor plan model based on building standards and building techniques; a market exhibiting means for exhibiting a model that has received a certain score by the scoring means on a market in a digital space; A system including:

2. The system according to claim 1 , wherein the scoring means evaluates whether the generated 3D floor plan model complies with building standards and assigns a score based on the evaluation result.

3. The system of claim 1, wherein the market exhibiting means is a means for making models that have achieved a certain score in the digital market available for purchase by home builders, construction companies, or owners of custom-built homes, and includes a means for making models that do not meet the certain score available for use in other industries.

Images