system

Abstract

Provide a system. 【Solution means】 Means for inputting building design requirements, Means for analyzing the design requirements and extracting basic data, Means for automatically generating a plurality of design plans based on the basic data, Means for evaluating the generated design plans based on ease of construction and cost efficiency, Means for selecting optimal members and materials, Means for generating and optimizing the building assembly procedure, Means for predicting labor force and skill level, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to the 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the construction industry, the shortage of labor due to the decrease in the working population has become a serious problem, and the establishment of an efficient construction process is required. To address this problem, it is necessary to optimize the process from design to construction while minimizing the labor force. However, with conventional methods, it has been difficult to generate optimal designs, material selections, and assembly procedures according to individual requirements, so a system that automates and supports this is needed.

Means for Solving the Problems

[0005] This invention provides a system that streamlines the construction process by including means for inputting and analyzing building design requirements, and automatically generating multiple design proposals based on that basic data. Furthermore, the generated design proposals are evaluated based on ease of construction and cost efficiency, and the optimal components and materials are automatically selected. In addition, this system can generate building assembly procedures using a simulation model, and an AI that has learned from the experience of skilled workers optimizes the procedures, thereby predicting and presenting the labor force and skill levels required. This makes it possible to realize efficient and labor-intensive construction projects.

[0006] "Building design requirements" refer to the basic specifications of a building required for a construction project, such as its purpose, size, location, and budget.

[0007] "Basic data" refers to the set of data necessary for generating design proposals, extracted by analyzing design requirements.

[0008] A "design proposal" is a detailed plan for a project that shows the building's shape, structure, spatial arrangement, and other aspects.

[0009] "Components and materials" refer to the physical elements and materials used in the construction of a building, and their selection is influenced by cost and supply conditions.

[0010] An "assembly procedure" is a plan that shows the sequence of how modules and components are combined and assembled during the building construction process.

[0011] A "simulation model" is a digital, virtual model used to evaluate and optimize design and assembly procedures.

[0012] "Workforce and skill level" refers to the number of personnel required to carry out a construction project and the technical capabilities that are necessary for them. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides a system that efficiently and automatically generates building designs using generative AI. The aim of this system is to establish optimal designs and processes from the early stages of a construction project and minimize labor costs.

[0035] The user first inputs the basic design requirements for the building using a terminal. This includes information such as the building's purpose, size, budget, and location. Once this information is sent to the server, the server uses AI to analyze the requirements and extract the basic data necessary for the design.

[0036] The server automatically generates multiple design proposals based on the acquired basic data. These design proposals are evaluated considering ease of construction and cost efficiency. Furthermore, the server consults a market database to gather information for selecting the optimal components and materials. This results in the creation of a material list that takes cost and sustainability into consideration.

[0037] After the user reviews the generated design proposal, the server uses a simulation model to generate building assembly procedures. This simulation models efficient procedures and optimizes each stage of assembly. The server further optimizes the procedures and predicts the required workforce and skill levels using AI learned from the experience of skilled workers. Based on this information, the user can determine the resources needed for the project.

[0038] For example, when constructing an office building, the user inputs the number of floors, total floor area, and budget. Based on this, the server generates multiple design options, selects the optimal materials and components, and automatically generates procedures to efficiently advance the construction process. This entire process provides a practical approach to solving the challenges of labor shortages and rising costs that the construction industry faces.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user uses a terminal to input the building's design requirements. This information includes details such as the building's purpose, size, budget, and location.

[0042] Step 2:

[0043] The terminal sends these design requirements to the server. The server analyzes the received data and identifies the basic data needed for the design.

[0044] Step 3:

[0045] The server automatically generates multiple design proposals using AI based on the underlying data. These proposals include specific plans regarding the building's shape and structural layout.

[0046] Step 4:

[0047] The server evaluates each generated design proposal for ease of construction and cost-effectiveness. This evaluation is performed to determine the ranking of the designs.

[0048] Step 5:

[0049] Based on the evaluation results, the server presents the user with the most suitable design proposal. The user can then review and select this proposal on their terminal.

[0050] Step 6:

[0051] The server consults market databases to select the optimal materials and components based on the design proposal. This process takes into account factors such as cost and supply stability.

[0052] Step 7:

[0053] The server generates a simulation model of the building's assembly procedure using the selected materials and components. An efficient process is optimized within the model.

[0054] Step 8:

[0055] The server uses AI, which has learned from the experience of skilled workers, to optimize the assembly process. This allows it to predict the required workforce and skill level.

[0056] Step 9:

[0057] Users receive information on the human resources and skill levels required for the project on their devices, and then use that information to refine the project plan.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In the construction industry, there is a demand for increased efficiency and cost reduction in the design process. However, traditional methods require considerable time and effort to create design proposals and select optimal materials, exacerbating labor shortages. This presents a challenge in establishing a rapid and cost-effective design process.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for analyzing design information and extracting technical data, means for automatically generating multiple design proposals based on the technical data, and means for generating assembly procedures using a simulation model. This streamlines the process from design to construction, enabling cost reduction and optimization of labor.

[0063] "Design information" refers to the fundamental elements necessary for the design of a structure, and includes information regarding its purpose, scale, budget, and location.

[0064] "Technical data" refers to fundamental data necessary for design, analyzed from design information, and includes structural indicators and technical conditions.

[0065] A "design proposal" is a set of multiple design plans automatically generated based on technical data, taking into account constructability and cost efficiency.

[0066] "Materials" refer to the materials and components used in the construction of structures, and are selected with consideration for mass production and sustainability.

[0067] "Assembly procedure" refers to a series of steps and methods for efficiently assembling a structure based on the design plan.

[0068] "Artificial intelligence" refers to technology that learns from human experience and helps optimize design and construction processes.

[0069] A "market database" refers to a database that stores information on the supply status and costs of materials and supplies.

[0070] The user first inputs building design information using a terminal. This includes basic elements such as the purpose, size, budget, and location of the structure to be built. The terminal then transmits this information to the server via the network.

[0071] The server inputs the received design information into a generative AI model, which then analyzes it to extract technical data. The generative AI model used has the capability to generate the data necessary for the design through analysis and verifies the consistency of various conditions in the design information.

[0072] Next, the server automatically generates multiple design options based on the extracted technical data and evaluates them based on constructability and cost-effectiveness. The design options are proposed by AI, taking into account design diversity and functionality, and are visualized to make it easier for the user to select.

[0073] Furthermore, the server accesses a market database to select the most suitable materials and supplies. This selection process is optimized from the perspective of cost-effectiveness and sustainability, and a list of materials tailored to the design proposal is created.

[0074] Based on the design proposal selected by the user, the server uses a simulation model to generate an efficient assembly procedure. The simulation models the construction process step by step and proposes an efficient procedure.

[0075] Finally, the server utilizes artificial intelligence learned from human experience to further optimize the assembly process and predict the required workforce and skill levels. Based on this information, users can assemble project teams and allocate resources.

[0076] As a concrete example, when a user designs a new office building, the user inputs information such as the number of floors, total floor area, and budget into a terminal. Based on this information, the server generates multiple design proposals, selects the optimal materials and components, and automatically generates an efficient construction process. In this process, an example of a text prompt that the user inputs into the generated AI model is: "Please generate building design proposals. The purpose is an office building, with 10 floors, a total floor area of ​​2000 square meters, and a budget of 50 million yen. Please suggest the optimal list of materials and assembly procedures."

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The user inputs building design information using a terminal. This input information includes the building's purpose, size (e.g., number of floors, total floor area), budget, and location. This data is basic information that is sent directly to the server.

[0080] Step 2:

[0081] The terminal sends the design information entered by the user to the server. This transmission occurs in real time, and the server immediately converts the information into a format that it can analyze. This prepares the server to start the analysis process.

[0082] Step 3:

[0083] The server inputs the received design information into a generating AI model, which then analyzes the design conditions based on this information. Specifically, it extracts the technical data necessary for the design from the input information and stores it as basic data. During this process, checks are also performed to maintain data consistency and integrity. The output is the analyzed technical data.

[0084] Step 4:

[0085] The server automatically generates multiple design proposals using extracted technical data. Data calculations are performed using a generation AI model, and various design options are created. The designs take constructability and cost efficiency into consideration, and multiple design proposals are obtained as output.

[0086] Step 5:

[0087] The server selects the most suitable materials and components for each generated design proposal by accessing a market database. The selection process evaluates the cost-effectiveness and sustainability of the materials. The output is a list of materials corresponding to each design proposal.

[0088] Step 6:

[0089] The user reviews the design proposals provided by the server via their terminal. They select the most suitable design from among several options or send feedback to the server as needed. This selection information is used to generate the assembly procedure in the next step.

[0090] Step 7:

[0091] The server generates assembly procedures using a simulation model based on the selected design proposal. This process models each stage of assembly and designs efficient procedures. The output is a specific set of assembly procedures.

[0092] Step 8:

[0093] The server further optimizes assembly procedures using artificial intelligence learned from the experience of skilled workers. This allows it to predict the required workforce and skill levels. The output provides predictive information regarding the number of workers and skill levels. This information serves as an important guide for users when developing actual construction plans.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] Traditional construction and production line design often involved inefficient processes that relied heavily on human experience and manual labor, requiring significant time and effort, especially for complex designs. Furthermore, predicting the necessary workforce and skill levels was difficult, posing challenges to resource optimization. Similarly, in production line design, developing efficient robot motion plans was challenging, sometimes resulting in low productivity.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] In this invention, the server includes means for inputting building design requirements, means for analyzing the design requirements and extracting basic data, means for automatically generating multiple design proposals based on the basic data, means for inputting production line designs and optimizing efficient work processes, and means for simulating robot movements and generating work procedures based on the design proposals. This enables efficient design of construction projects and production lines, as well as optimization of labor.

[0099] "Building design requirements" is a general term for the basic information necessary for design in a construction project, such as its purpose, scale, budget, and location.

[0100] "Basic data" refers to a collection of fundamental information necessary for generating design proposals, extracted by analyzing the building's design requirements.

[0101] "Automatic generation of design proposals" is a process in which a computer generates multiple design patterns based on basic data.

[0102] "Ease of construction" is a concept that indicates the degree of ease and efficiency in carrying out construction work according to the design proposal.

[0103] "Cost efficiency" is a measure that evaluates how economical a particular design proposal or material selection is within a given budget.

[0104] "Selection of components and materials" refers to the process of choosing the structural and building materials necessary for the design based on various selection criteria.

[0105] "Assembly procedure" refers to the specific work processes and arrangements necessary when constructing a building.

[0106] "Forecasting labor force and skill levels" is the process of estimating the number of personnel required for construction or production, as well as the skill level each of them should possess.

[0107] "Production line design" refers to planning the flow and process of product production in a manufacturing plant.

[0108] "Robot motion simulation" refers to the process of reproducing and examining the movements of factory machinery in a virtual space based on a design proposal, in order to ensure efficient operation.

[0109] The system for implementing this invention aims to improve the efficiency and automation of design processes related to architecture and manufacturing. This system includes a server, user terminals, and factory robots, and utilizes a generative AI model and a simulation engine.

[0110] Users input building design requirements and production line specifications via a terminal. This includes the building's purpose, size, budget, location, and the type and quantity of products to be manufactured. This information is sent to a server, which uses a generative AI model to analyze the input data and extract the necessary foundational data. Based on this foundational data, the server automatically generates multiple design options and evaluates the generated designs based on ease of construction and cost efficiency. The server also accesses a market database to select the most suitable materials and components.

[0111] For building assembly procedures and production line operations, the server uses a simulation engine to generate efficient processes and optimize robot movements. By running simulations of robot system movements, the optimized work procedures can be used in the actual manufacturing environment. This process also predicts the workforce and skill levels required, determining the resources needed for the project.

[0112] A concrete example of this system's use is in an automobile manufacturing plant when producing a new model. The user inputs the production volume of the new model, the factory space, and the budget, and based on that, the system generates an optimal production line design and robot operation procedures.

[0113] Examples of prompts for a generative AI model are as follows:

[0114] "Design a production line for a new car model. The production volume for the Model X is 500 units per month, the total budget is 10 million yen, and we have 2000 square meters of factory space available. Please create the optimal layout and process."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] Users input building design requirements and production line specifications via a terminal. This includes project objectives, scale, budget, location, or product type and quantity. This input data is sent to the server as basic prerequisites for the design.

[0118] Step 2:

[0119] The server uses the received input data to run a generating AI model and analyze the requirements. This process extracts the necessary foundational data, including specific information such as the number of floors in a building and the number of parts required.

[0120] Step 3:

[0121] The server automatically generates multiple design options using an AI model based on the underlying data. During this process, the design options are evaluated considering factors such as ease of construction and cost efficiency. The output is a list of selectable design options.

[0122] Step 4:

[0123] The server accesses a market database and selects the optimal materials and components based on the evaluated design proposal. At this stage, cost and ease of supply are prioritized, and a list of corresponding materials is output.

[0124] Step 5:

[0125] The server uses a simulation engine to generate building assembly procedures and production line operations based on the generated AI model. This results in optimized work procedures being output. Specifically, it instructs the robots on the order in which they should perform their tasks.

[0126] Step 6:

[0127] The user reviews the design proposal and optimized work procedures generated on the terminal and makes adjustments as needed. This step includes simulating the work procedures and evaluating their feasibility.

[0128] Step 7:

[0129] Ultimately, the server outputs an action plan for the robots that make up the production line and supports the execution of that plan. Specifically, the robots autonomously begin their work based on the generated plan.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention provides a system that incorporates user emotional data into the creation and evaluation of design proposals by integrating an emotion engine into the building design process.

[0132] When users input building design requirements using a device, the emotion engine recognizes their emotions in real time from their facial expressions and voice. This emotion data is used to determine which designs the user will respond to more positively.

[0133] The server receives design requirements and emotional data from the user simultaneously. The server's AI generates multiple design proposals based on this information. These proposals are evaluated using the user's emotional data in addition to standard evaluation criteria. This prioritizes the design proposal that the user is most likely to prefer.

[0134] Based on the selected design proposal, the server selects the optimal materials and components from the market database and generates the necessary assembly procedures using a simulation model. This entire process is also displayed on the terminal for the user to review.

[0135] For example, if a user is designing an office building, the emotion engine can recognize positive emotions such as joy and excitement in response to the requirements the user has entered. The server can then incorporate this emotional data into the evaluation of design proposals and present the proposal that best meets the user's expectations.

[0136] This system will enable the creation of design proposals that better fit the user's intentions and emotions, and is expected to improve the accuracy and satisfaction of the design process.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user uses a device to input building design requirements. During this process, an emotion engine analyzes the user's emotions in real time through the user's camera footage and audio.

[0140] Step 2:

[0141] The device sends emotional data to the server along with the entered design requirements. This data includes the user's emotional state and the intensity of their emotions.

[0142] Step 3:

[0143] The server analyzes the design requirements and extracts basic data. The server's AI model automatically generates multiple design options based on this basic data and sentiment data.

[0144] Step 4:

[0145] The server evaluates the generated design proposals, taking into account not only ease of construction and cost-effectiveness, but also user sentiment. In particular, design proposals that evoke positive emotions in users receive high ratings.

[0146] Step 5:

[0147] The user views a list of proposed designs sent from the server on their device. The emotion engine then analyzes the user's reaction to these designs and provides feedback to the server as needed.

[0148] Step 6:

[0149] The server accesses the market database for a more detailed evaluation and selects the optimal materials and components. This verifies whether the proposed selection is realistic and feasible.

[0150] Step 7:

[0151] The server generates the necessary assembly procedures based on the selected design proposal using a simulation model. Fine-tuning based on user sentiment is also possible.

[0152] Step 8:

[0153] The device presents the user with the final design proposal and assembly procedure, which the user can then adopt as the project execution plan. This allows the user to proceed with the project according to a design that better resonates with their emotions.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] Conventional building design systems have the problem that they fail to adequately address the emotions and needs of users because the creation and evaluation of design proposals are based solely on technical performance and cost. This can lead to decreased user satisfaction and an inefficient design process.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for acquiring and evaluating user emotional information, means for selecting a design proposal that harmonizes with the user's emotions based on the evaluation, and means for accessing a market database to select materials and components. This enables the presentation of design proposals that emotionally satisfy the user and efficient resource selection.

[0159] "Building design requirements" refer to information that describes the specific conditions and preferences regarding the structure, function, and design of a building desired by the user.

[0160] "Basic data" refers to the fundamental information and specifications necessary for design, extracted from the design requirements.

[0161] A "design proposal" is a specific design plan for a building that is proposed based on basic data.

[0162] "Means of evaluation" refer to methods and mechanisms for analyzing and comparing generated design proposals based on various criteria.

[0163] "Emotional information" refers to information about emotions that is analyzed from the user's facial expressions, voice, etc., and reflected in the design process.

[0164] "Materials and components" refers to the various materials and parts used in the construction of a building.

[0165] A "simulation model" is a computer model that reproduces a designed building in a virtual space to verify the assembly procedure and feasibility.

[0166] "Labor force and skill level" refers to the number of personnel required for building construction and their respective skills, and is a factor in evaluating the efficiency of design and actual construction.

[0167] This invention provides a system that incorporates user emotional information into the building design process. The system is implemented using hardware and software such as terminals, servers, and generative AI models.

[0168] First, the user uses a device to input the building's design requirements. The device is equipped with a camera and microphone, and captures emotional information in real time from the user's facial expressions and voice. For example, if the user expresses positive emotions when requesting an "open office space," that emotional information is recorded.

[0169] Next, the terminal sends the user's design requirements and emotional information to the server. The server inputs this data into a generating AI model. This model generates multiple design proposals based on the received prompts, such as "Generate office building design proposals that the user will find positive."

[0170] The generated design proposals are evaluated on the server using user sentiment information. Sentiment information is used to increase the importance of design elements that elicit particularly positive user responses.

[0171] The server then accesses a market database to select the most suitable materials and components for the chosen design. This selection takes into account cost efficiency and ease of supply.

[0172] Furthermore, the server uses a simulation model to generate assembly procedures using the selected materials. This simulation visualizes how the design proposal will be realized and presents it to the user.

[0173] In this way, the system provides design proposals that fit the user's emotions, improving the efficiency and satisfaction of the entire design process.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The user inputs building design requirements using a terminal. The terminal uses a camera and microphone to capture the user's facial expressions and voice in real time, acquiring emotional information. The input design requirements and acquired emotional information are converted into digital data by the terminal's processing. The output of this step is the digitized design requirements and emotional data.

[0177] Step 2:

[0178] The terminal sends digitized design requirements and sentiment data to the server. The server analyzes the received data and generates prompt sentences for the generative AI model. For example, it might generate a sentence like, "Generate an office building design proposal that will make the user feel positive." This prompt sentence becomes the input to the generative AI model. The output is the prompt sentence.

[0179] Step 3:

[0180] The server uses a generative AI model to generate design proposals based on the input prompt text. The model creates a variety of proposals using a rich design database and historical training data. In this generation process, the input sentiment data influences the type and style of the design proposals. The output consists of multiple design proposals.

[0181] Step 4:

[0182] The server evaluates the generated design proposals. This process considers user sentiment data, prioritizing design elements that receive positive responses. Ease of construction and cost-effectiveness are also included in the evaluation. The output is a list of the evaluated design proposals.

[0183] Step 5:

[0184] The server accesses a market database and selects the optimal materials and components to match highly-rated design proposals. Cost and ease of supply are also considered in the selection process. This selection process generates a detailed resource list.

[0185] Step 6:

[0186] The server generates building assembly procedures using a simulation model with selected materials. The simulation verifies the feasibility and assembly efficiency of the design proposal. The output is a detailed assembly procedure and its visual simulation.

[0187] Step 7:

[0188] The server sends the final design proposal and simulation results to the terminal. The terminal presents this to the user and requests feedback. The user then makes a final confirmation of the design proposal and provides instructions for any necessary modifications. The output of this step is the presentation of results and feedback to the user.

[0189] (Application Example 2)

[0190] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] In today's world, designing products and recommending items that take user emotions into consideration is becoming increasingly important. However, conventional systems have struggled to adequately reflect user wishes and emotions in design proposals and product recommendations, making it difficult to improve user satisfaction. Therefore, there is a need to analyze user emotions in real time and utilize the results to generate design proposals and recommend customized products.

[0192] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0193] In this invention, the server includes means for inputting design requirements and acquiring user emotion data, means for analyzing the design requirements and emotion data and extracting basic information, and means for automatically generating multiple design proposals based on the basic information. This makes it possible to generate design proposals that take user emotions into consideration and to recommend the most suitable product to each individual user.

[0194] "Design requirements" are the specific conditions and specifications that users need regarding the design of a building or product.

[0195] "Emotional data" refers to information about a user's emotions obtained from their facial expressions and voice.

[0196] "Basic information" refers to fundamental design indicators obtained by analyzing design requirements and sentiment data.

[0197] "Emotion-based product recommendations" is a process that uses user emotional data to suggest products that users are likely to like.

[0198] "Components" refer to the collective term for the parts and materials used to construct a building or product.

[0199] "Assembly procedure" refers to the sequence of steps required to combine the various elements of a building or product to create a finished product.

[0200] "Labor factors" is a concept that refers to the human resources and required skills related to design and construction.

[0201] "Technical level" refers to the degree of specialized knowledge and skills required to carry out a particular design or construction.

[0202] A "user sentiment-based process" refers to a series of processes that are carried out based on user sentiment data.

[0203] A "market database" is a digital database that collects information on costs and supply.

[0204] This invention relates to a system for generating design proposals and recommending products that reflect user emotions. In this embodiment, the server receives design requirements and emotion data from the user terminal and generates an optimal design proposal based on them.

[0205] When users input design requirements using devices such as smartphones or tablets, emotional data is acquired in real time through the device's camera and microphone. Emotion recognition APIs (e.g., Google® Cloud Vision API, Microsoft® Azure® Face API) are used for emotion recognition. The acquired emotional data is analyzed based on the user's facial expressions and voice tone to identify positive and negative emotions, which are then sent to the server as foundational information.

[0206] The server analyzes the received information using machine learning models (e.g., TENSORFLOW®, PyTorch) and generates design proposals. The generated design proposals are evaluated based on user sentiment, and the optimal proposal is selected. In this process, the acquired user sentiment data is given importance, and the design proposals are customized accordingly.

[0207] Furthermore, to recommend products suitable for the user, the server accesses the market database and makes recommendations considering efficiency and supply availability. It also suggests product colors and designs based on the user's preferences to enhance the user experience.

[0208] For example, when a user chooses new office furniture, the emotion engine can recognize positive emotions such as joy and excitement, and suggest products based on those emotions (e.g., a desk in a calming color or a comfortable chair).

[0209] Examples of prompt messages include, "Generate design proposals based on user input and suggest customized products based on emotional data, providing users with a wider range of choices." In this way, the system can contribute to improving the user's purchasing experience and satisfaction with the design process.

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The user enters design requirements on the terminal. The entered data includes the conditions and specifications necessary for the design. This data is then ready to be sent to the server.

[0213] Step 2:

[0214] The device uses its camera and microphone to acquire user emotion data in real time. It utilizes facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and voice. The acquired emotion data is sent to the server as a numerical value indicating whether the emotion is positive or negative.

[0215] Step 3:

[0216] The server receives design requirements and sentiment data sent from the terminal and extracts basic information using a machine learning model. Here, it determines the necessary data points based on the design requirements and, taking sentiment data into account, decides which parts should be prioritized in the design.

[0217] Step 4:

[0218] The server runs a generative AI model to automatically generate multiple design options based on the underlying information. The generated design options are scored by an algorithm, and the evaluation criteria are adjusted based on sentiment data. Through this process, the design option best suited to the user is selected.

[0219] Step 5:

[0220] The server accesses the market database based on the selected design proposal and selects components that consider efficiency and supply availability. The selected components, along with information such as price and supply availability, are presented to the user.

[0221] Step 6:

[0222] The user reviews the design proposals and recommended components received from the server on their device. For products the user shows interest in, customized recommendation comments are generated based on the prompt text, improving the user experience.

[0223] Step 7:

[0224] The user makes the final decision, making revisions to the design proposal and making purchases. The server receives user feedback in real time and uses that information to improve future design proposals and product recommendations.

[0225] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0226] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0227] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0228] [Second Embodiment]

[0229] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0230] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0231] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0232] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0233] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0234] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0235] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0236] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0237] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0238] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0239] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0240] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0241] This invention provides a system that efficiently and automatically generates building designs using generative AI. The aim of this system is to establish optimal designs and processes from the early stages of a construction project and minimize labor costs.

[0242] The user first inputs the basic design requirements for the building using a terminal. This includes information such as the building's purpose, size, budget, and location. Once this information is sent to the server, the server uses AI to analyze the requirements and extract the basic data necessary for the design.

[0243] The server automatically generates multiple design proposals based on the acquired basic data. These design proposals are evaluated considering ease of construction and cost efficiency. Furthermore, the server consults a market database to gather information for selecting the optimal components and materials. This results in the creation of a material list that takes cost and sustainability into consideration.

[0244] After the user reviews the generated design proposal, the server uses a simulation model to generate building assembly procedures. This simulation models efficient procedures and optimizes each stage of assembly. The server further optimizes the procedures and predicts the required workforce and skill levels using AI learned from the experience of skilled workers. Based on this information, the user can determine the resources needed for the project.

[0245] For example, when constructing an office building, the user inputs the number of floors, total floor area, and budget. Based on this, the server generates multiple design options, selects the optimal materials and components, and automatically generates procedures to efficiently advance the construction process. This entire process provides a practical approach to solving the challenges of labor shortages and rising costs that the construction industry faces.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The user uses a terminal to input the building's design requirements. This information includes details such as the building's purpose, size, budget, and location.

[0249] Step 2:

[0250] The terminal sends these design requirements to the server. The server analyzes the received data and identifies the basic data needed for the design.

[0251] Step 3:

[0252] The server automatically generates multiple design proposals using AI based on the underlying data. These proposals include specific plans regarding the building's shape and structural layout.

[0253] Step 4:

[0254] The server evaluates each generated design proposal for ease of construction and cost-effectiveness. This evaluation is performed to determine the ranking of the designs.

[0255] Step 5:

[0256] Based on the evaluation results, the server presents the user with the most suitable design proposal. The user can then review and select this proposal on their terminal.

[0257] Step 6:

[0258] The server consults market databases to select the optimal materials and components based on the design proposal. This process takes into account factors such as cost and supply stability.

[0259] Step 7:

[0260] The server generates a simulation model of the building's assembly procedure using the selected materials and components. An efficient process is optimized within the model.

[0261] Step 8:

[0262] The server uses AI, which has learned from the experience of skilled workers, to optimize the assembly process. This allows it to predict the required workforce and skill level.

[0263] Step 9:

[0264] Users receive information on the human resources and skill levels required for the project on their devices, and then use that information to refine the project plan.

[0265] (Example 1)

[0266] Next, we will describe Example 1. 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."

[0267] In the construction industry, there is a demand for increased efficiency and cost reduction in the design process. However, traditional methods require considerable time and effort to create design proposals and select optimal materials, exacerbating labor shortages. This presents a challenge in establishing a rapid and cost-effective design process.

[0268] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0269] In this invention, the server includes means for analyzing design information and extracting technical data, means for automatically generating multiple design proposals based on the technical data, and means for generating assembly procedures using a simulation model. This streamlines the process from design to construction, enabling cost reduction and optimization of labor.

[0270] "Design information" refers to the fundamental elements necessary for the design of a structure, and includes information regarding its purpose, scale, budget, and location.

[0271] "Technical data" refers to fundamental data necessary for design, analyzed from design information, and includes structural indicators and technical conditions.

[0272] A "design proposal" is a set of multiple design plans automatically generated based on technical data, taking into account constructability and cost efficiency.

[0273] "Materials" refer to the materials and components used in the construction of structures, and are selected with consideration for mass production and sustainability.

[0274] "Assembly procedure" refers to a series of steps and methods for efficiently assembling a structure based on the design plan.

[0275] "Artificial intelligence" refers to technology that learns from human experience and helps optimize design and construction processes.

[0276] A "market database" refers to a database that stores information on the supply status and costs of materials and supplies.

[0277] The user first inputs building design information using a terminal. This includes basic elements such as the purpose, size, budget, and location of the structure to be built. The terminal then transmits this information to the server via the network.

[0278] The server inputs the received design information into a generative AI model, which then analyzes it to extract technical data. The generative AI model used has the capability to generate the data necessary for the design through analysis and verifies the consistency of various conditions in the design information.

[0279] Next, the server automatically generates multiple design options based on the extracted technical data and evaluates them based on constructability and cost-effectiveness. The design options are proposed by AI, taking into account design diversity and functionality, and are visualized to make it easier for the user to select.

[0280] Furthermore, the server accesses a market database to select the most suitable materials and supplies. This selection process is optimized from the perspective of cost-effectiveness and sustainability, and a list of materials tailored to the design proposal is created.

[0281] Based on the design proposal selected by the user, the server uses a simulation model to generate an efficient assembly procedure. The simulation models the construction process step by step and proposes an efficient procedure.

[0282] Finally, the server utilizes artificial intelligence learned from human experience to further optimize the assembly process and predict the required workforce and skill levels. Based on this information, users can assemble project teams and allocate resources.

[0283] As a specific example, when a user designs a new office building, the user inputs the number of floors, total floor area, and budget information of the building using a terminal. Based on this information, the server generates multiple design plans, selects the optimal materials and components, and automatically generates an efficient construction process. In this process, an example of the text prompt sentence that the user inputs into the generation AI model is "Please generate a design plan for the building. The purpose is an office building, the number of floors is 10, the total floor area is 2000 square meters, and the budget is 50 million yen. Please propose a list of optimal materials and assembly procedures."

[0284] The flow of the specific process in Example 1 will be described using FIG. 11.

[0285] Step 1:

[0286] The user inputs the design information of the building using a terminal. This input information includes the purpose of the building, scale (e.g., number of floors, total floor area), budget, and location. These data are the basic information to be directly transmitted to the server. [[ID=十七]]

[0287] ステップ2:

[0288] The terminal transmits the design information input by the user to the server. This transmission is performed in real time and is converted into a format that can be immediately analyzed by the server, thereby preparing for the start of the analysis process on the server.

[0289] ステップ3:

[0290] The server inputs the received design information into the generation AI model and analyzes the design conditions based on this. Specifically, the technical data required for the design is extracted from the input information and accumulated as basic data. In this process, checks are also performed to ensure the consistency and integrity of the data. As output, the analyzed technical data is obtained.

[0291] ステップ4:

[0292] The server automatically generates multiple design proposals using extracted technical data. Data calculations are performed using a generation AI model, and various design options are created. The designs take constructability and cost efficiency into consideration, and multiple design proposals are obtained as output.

[0293] Step 5:

[0294] The server selects the most suitable materials and components for each generated design proposal by accessing a market database. The selection process evaluates the cost-effectiveness and sustainability of the materials. The output is a list of materials corresponding to each design proposal.

[0295] Step 6:

[0296] The user reviews the design proposals provided by the server via their terminal. They select the most suitable design from among several options or send feedback to the server as needed. This selection information is used to generate the assembly procedure in the next step.

[0297] Step 7:

[0298] The server generates assembly procedures using a simulation model based on the selected design proposal. This process models each stage of assembly and designs efficient procedures. The output is a specific set of assembly procedures.

[0299] Step 8:

[0300] The server further optimizes assembly procedures using artificial intelligence learned from the experience of skilled workers. This allows it to predict the required workforce and skill levels. The output provides predictive information regarding the number of workers and skill levels. This information serves as an important guide for users when developing actual construction plans.

[0301] (Application Example 1)

[0302] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0303] In conventional construction design and production line design, there are many inefficient processes that rely on human experience and manual work. Especially in the case of complex designs, a great deal of time and labor are required. Also, since it was difficult to predict the necessary labor and skill levels, there were problems in optimizing resources. In production line design as well, it was difficult to formulate an efficient operation plan for robots, and as a result, productivity may not have improved.

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0305] In this invention, the server includes means for inputting the design requirements of a building, means for analyzing the design requirements and extracting basic data, means for automatically generating a plurality of design plans based on the basic data, means for inputting the design of a production line and optimizing an efficient work process, and means for simulating robot operations and generating a work procedure based on the design plan. Thereby, efficient design of construction projects and production lines and optimization of labor are made possible.

[0306] The "design requirements of a building" is a general term for the basic information necessary for design, such as the purpose, scale, budget, location, etc. in a construction project.

[0307] The "basic data" is a set of basic information necessary for generating a design plan, which is extracted by analyzing the design requirements of a building.<​​​​​​​​​ "Cost efficiency" is a measure that evaluates how economical a particular design proposal or material selection is within a given budget.

[0311] "Selection of components and materials" refers to the process of choosing the structural and building materials necessary for the design based on various selection criteria.

[0312] "Assembly procedure" refers to the specific work processes and arrangements necessary when constructing a building.

[0313] "Forecasting labor force and skill levels" is the process of estimating the number of personnel required for construction or production, as well as the skill level each of them should possess.

[0314] "Production line design" refers to planning the flow and process of product production in a manufacturing plant.

[0315] "Robot motion simulation" refers to the process of reproducing and examining the movements of factory machinery in a virtual space based on a design proposal, in order to ensure efficient operation.

[0316] The system for implementing this invention aims to improve the efficiency and automation of design processes related to architecture and manufacturing. This system includes a server, user terminals, and factory robots, and utilizes a generative AI model and a simulation engine.

[0317] Users input building design requirements and production line specifications via a terminal. This includes the building's purpose, size, budget, location, and the type and quantity of products to be manufactured. This information is sent to a server, which uses a generative AI model to analyze the input data and extract the necessary foundational data. Based on this foundational data, the server automatically generates multiple design options and evaluates the generated designs based on ease of construction and cost efficiency. The server also accesses a market database to select the most suitable materials and components.

[0318] For building assembly procedures and production line operations, the server uses a simulation engine to generate efficient processes and optimize robot movements. By running simulations of robot system movements, the optimized work procedures can be used in the actual manufacturing environment. This process also predicts the workforce and skill levels required, determining the resources needed for the project.

[0319] A concrete example of this system's use is in an automobile manufacturing plant when producing a new model. The user inputs the production volume of the new model, the factory space, and the budget, and based on that, the system generates an optimal production line design and robot operation procedures.

[0320] Examples of prompts for a generative AI model are as follows:

[0321] "Design a production line for a new car model. The production volume for the Model X is 500 units per month, the total budget is 10 million yen, and we have 2000 square meters of factory space available. Please create the optimal layout and process."

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] Users input building design requirements and production line specifications via a terminal. This includes project objectives, scale, budget, location, or product type and quantity. This input data is sent to the server as basic prerequisites for the design.

[0325] Step 2:

[0326] The server uses the received input data to run a generating AI model and analyze the requirements. This process extracts the necessary foundational data, including specific information such as the number of floors in a building and the number of parts required.

[0327] Step 3:

[0328] The server automatically generates multiple design options using an AI model based on the underlying data. During this process, the design options are evaluated considering factors such as ease of construction and cost efficiency. The output is a list of selectable design options.

[0329] Step 4:

[0330] The server accesses a market database and selects the optimal materials and components based on the evaluated design proposal. At this stage, cost and ease of supply are prioritized, and a list of corresponding materials is output.

[0331] Step 5:

[0332] The server uses a simulation engine to generate building assembly procedures and production line operations based on the generated AI model. This results in optimized work procedures being output. Specifically, it instructs the robots on the order in which they should perform their tasks.

[0333] Step 6:

[0334] The user reviews the design proposal and optimized work procedures generated on the terminal and makes adjustments as needed. This step includes simulating the work procedures and evaluating their feasibility.

[0335] Step 7:

[0336] Ultimately, the server outputs an action plan for the robots that make up the production line and supports the execution of that plan. Specifically, the robots autonomously begin their work based on the generated plan.

[0337] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0338] This invention provides a system that incorporates user emotional data into the creation and evaluation of design proposals by integrating an emotion engine into the building design process.

[0339] When users input building design requirements using a device, the emotion engine recognizes their emotions in real time from their facial expressions and voice. This emotion data is used to determine which designs the user will respond to more positively.

[0340] The server receives design requirements and emotional data from the user simultaneously. The server's AI generates multiple design proposals based on this information. These proposals are evaluated using the user's emotional data in addition to standard evaluation criteria. This prioritizes the design proposal that the user is most likely to prefer.

[0341] Based on the selected design proposal, the server selects the optimal materials and components from the market database and generates the necessary assembly procedures using a simulation model. This entire process is also displayed on the terminal for the user to review.

[0342] For example, if a user is designing an office building, the emotion engine can recognize positive emotions such as joy and excitement in response to the requirements the user has entered. The server can then incorporate this emotional data into the evaluation of design proposals and present the proposal that best meets the user's expectations.

[0343] This system will enable the creation of design proposals that better fit the user's intentions and emotions, and is expected to improve the accuracy and satisfaction of the design process.

[0344] The following describes the processing flow.

[0345] Step 1:

[0346] The user uses a device to input building design requirements. During this process, an emotion engine analyzes the user's emotions in real time through the user's camera footage and audio.

[0347] Step 2:

[0348] The device sends emotional data to the server along with the entered design requirements. This data includes the user's emotional state and the intensity of their emotions.

[0349] Step 3:

[0350] The server analyzes the design requirements and extracts basic data. The server's AI model automatically generates multiple design options based on this basic data and sentiment data.

[0351] Step 4:

[0352] The server evaluates the generated design proposals, taking into account not only ease of construction and cost-effectiveness, but also user sentiment. In particular, design proposals that evoke positive emotions in users receive high ratings.

[0353] Step 5:

[0354] The user views a list of proposed designs sent from the server on their device. The emotion engine then analyzes the user's reaction to these designs and provides feedback to the server as needed.

[0355] Step 6:

[0356] The server accesses the market database for a more detailed evaluation and selects the optimal materials and components. This verifies whether the proposed selection is realistic and feasible.

[0357] Step 7:

[0358] The server generates the necessary assembly procedures based on the selected design proposal using a simulation model. Fine-tuning based on user sentiment is also possible.

[0359] Step 8:

[0360] The device presents the user with the final design proposal and assembly procedure, which the user can then adopt as the project execution plan. This allows the user to proceed with the project according to a design that better resonates with their emotions.

[0361] (Example 2)

[0362] Next, we will describe Example 2. 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".

[0363] Conventional building design systems have the problem that they fail to adequately address the emotions and needs of users because the creation and evaluation of design proposals are based solely on technical performance and cost. This can lead to decreased user satisfaction and an inefficient design process.

[0364] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0365] In this invention, the server includes means for acquiring and evaluating user emotional information, means for selecting a design proposal that harmonizes with the user's emotions based on the evaluation, and means for accessing a market database to select materials and components. This enables the presentation of design proposals that emotionally satisfy the user and efficient resource selection.

[0366] "Building design requirements" refer to information that describes the specific conditions and preferences regarding the structure, function, and design of a building desired by the user.

[0367] "Basic data" refers to the fundamental information and specifications necessary for design, extracted from the design requirements.

[0368] A "design proposal" is a specific design plan for a building that is proposed based on basic data.

[0369] "Means of evaluation" refer to methods and mechanisms for analyzing and comparing generated design proposals based on various criteria.

[0370] "Emotional information" refers to information about emotions that is analyzed from the user's facial expressions, voice, etc., and reflected in the design process.

[0371] "Materials and components" refers to the various materials and parts used in the construction of a building.

[0372] A "simulation model" is a computer model that reproduces a designed building in a virtual space to verify the assembly procedure and feasibility.

[0373] "Labor force and skill level" refers to the number of personnel required for building construction and their respective skills, and is a factor in evaluating the efficiency of design and actual construction.

[0374] This invention provides a system that incorporates user emotional information into the building design process. The system is implemented using hardware and software such as terminals, servers, and generative AI models.

[0375] First, the user uses a device to input the building's design requirements. The device is equipped with a camera and microphone, and captures emotional information in real time from the user's facial expressions and voice. For example, if the user expresses positive emotions when requesting an "open office space," that emotional information is recorded.

[0376] Next, the terminal sends the user's design requirements and emotional information to the server. The server inputs this data into a generating AI model. This model generates multiple design proposals based on the received prompts, such as "Generate office building design proposals that the user will find positive."

[0377] The generated design proposals are evaluated on the server using user sentiment information. Sentiment information is used to increase the importance of design elements that elicit particularly positive user responses.

[0378] The server then accesses a market database to select the most suitable materials and components for the chosen design. This selection takes into account cost efficiency and ease of supply.

[0379] Furthermore, the server uses a simulation model to generate assembly procedures using the selected materials. This simulation visualizes how the design proposal will be realized and presents it to the user.

[0380] In this way, the system provides design proposals that fit the user's emotions, improving the efficiency and satisfaction of the entire design process.

[0381] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0382] Step 1:

[0383] The user inputs building design requirements using a terminal. The terminal uses a camera and microphone to capture the user's facial expressions and voice in real time, acquiring emotional information. The input design requirements and acquired emotional information are converted into digital data by the terminal's processing. The output of this step is the digitized design requirements and emotional data.

[0384] Step 2:

[0385] The terminal sends digitized design requirements and sentiment data to the server. The server analyzes the received data and generates prompt sentences for the generative AI model. For example, it might generate a sentence like, "Generate an office building design proposal that will make the user feel positive." This prompt sentence becomes the input to the generative AI model. The output is the prompt sentence.

[0386] Step 3:

[0387] The server uses a generative AI model to generate design proposals based on the input prompt text. The model creates a variety of proposals using a rich design database and historical training data. In this generation process, the input sentiment data influences the type and style of the design proposals. The output consists of multiple design proposals.

[0388] Step 4:

[0389] The server evaluates the generated design proposals. This process considers user sentiment data, prioritizing design elements that receive positive responses. Ease of construction and cost-effectiveness are also included in the evaluation. The output is a list of the evaluated design proposals.

[0390] Step 5:

[0391] The server accesses a market database and selects the optimal materials and components to match highly-rated design proposals. Cost and ease of supply are also considered in the selection process. This selection process generates a detailed resource list.

[0392] Step 6:

[0393] The server generates building assembly procedures using a simulation model with selected materials. The simulation verifies the feasibility and assembly efficiency of the design proposal. The output is a detailed assembly procedure and its visual simulation.

[0394] Step 7:

[0395] The server sends the final design proposal and simulation results to the terminal. The terminal presents this to the user and requests feedback. The user then makes a final confirmation of the design proposal and provides instructions for any necessary modifications. The output of this step is the presentation of results and feedback to the user.

[0396] (Application Example 2)

[0397] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0398] In today's world, designing products and recommending items that take user emotions into consideration is becoming increasingly important. However, conventional systems have struggled to adequately reflect user wishes and emotions in design proposals and product recommendations, making it difficult to improve user satisfaction. Therefore, there is a need to analyze user emotions in real time and utilize the results to generate design proposals and recommend customized products.

[0399] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0400] In this invention, the server includes means for inputting design requirements and acquiring user emotion data, means for analyzing the design requirements and emotion data and extracting basic information, and means for automatically generating multiple design proposals based on the basic information. This makes it possible to generate design proposals that take user emotions into consideration and to recommend the most suitable product to each individual user.

[0401] "Design requirements" are the specific conditions and specifications that users need regarding the design of a building or product.

[0402] "Emotional data" refers to information about a user's emotions obtained from their facial expressions and voice.

[0403] "Basic information" refers to fundamental design indicators obtained by analyzing design requirements and sentiment data.

[0404] "Emotion-based product recommendations" is a process that uses user emotional data to suggest products that users are likely to like.

[0405] "Components" refer to the collective term for the parts and materials used to construct a building or product.

[0406] "Assembly procedure" refers to the sequence of steps required to combine the various elements of a building or product to create a finished product.

[0407] "Labor factors" is a concept that refers to the human resources and required skills related to design and construction.

[0408] "Technical level" refers to the degree of specialized knowledge and skills required to carry out a particular design or construction.

[0409] A "user sentiment-based process" refers to a series of processes that are carried out based on user sentiment data.

[0410] A "market database" is a digital database that collects information on costs and supply.

[0411] This invention relates to a system for generating design proposals and recommending products that reflect user emotions. In this embodiment, the server receives design requirements and emotion data from the user terminal and generates an optimal design proposal based on them.

[0412] When users input design requirements using devices such as smartphones or tablets, emotional data is acquired in real time through the device's camera and microphone. Emotion recognition APIs (e.g., Google Cloud Vision API, Microsoft Azure Face API) are used for emotion recognition. The acquired emotional data is analyzed based on the user's facial expressions and voice tone to identify positive and negative emotions, which are then sent to the server as foundational information.

[0413] The server analyzes the received information using machine learning models (e.g., TensorFlow, PyTorch) and generates design proposals. These proposals are then evaluated based on user sentiment, and the optimal proposal is selected. Throughout this process, the acquired user sentiment data is given significant weight, and the design proposals are customized accordingly.

[0414] Furthermore, to recommend products suitable for the user, the server accesses the market database and makes recommendations considering efficiency and supply availability. It also suggests product colors and designs based on the user's preferences to enhance the user experience.

[0415] For example, when a user chooses new office furniture, the emotion engine can recognize positive emotions such as joy and excitement, and suggest products based on those emotions (e.g., a desk in a calming color or a comfortable chair).

[0416] Examples of prompt messages include, "Generate design proposals based on user input and suggest customized products based on emotional data, providing users with a wider range of choices." In this way, the system can contribute to improving the user's purchasing experience and satisfaction with the design process.

[0417] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0418] Step 1:

[0419] The user enters design requirements on the terminal. The entered data includes the conditions and specifications necessary for the design. This data is then ready to be sent to the server.

[0420] Step 2:

[0421] The device uses its camera and microphone to acquire user emotion data in real time. It utilizes facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and voice. The acquired emotion data is sent to the server as a numerical value indicating whether the emotion is positive or negative.

[0422] Step 3:

[0423] The server receives design requirements and sentiment data sent from the terminal and extracts basic information using a machine learning model. Here, it determines the necessary data points based on the design requirements and, taking sentiment data into account, decides which parts should be prioritized in the design.

[0424] Step 4:

[0425] The server runs a generative AI model to automatically generate multiple design options based on the underlying information. The generated design options are scored by an algorithm, and the evaluation criteria are adjusted based on sentiment data. Through this process, the design option best suited to the user is selected.

[0426] Step 5:

[0427] The server accesses the market database based on the selected design proposal and selects components that consider efficiency and supply availability. The selected components, along with information such as price and supply availability, are presented to the user.

[0428] Step 6:

[0429] The user reviews the design proposals and recommended components received from the server on their device. For products the user shows interest in, customized recommendation comments are generated based on the prompt text, improving the user experience.

[0430] Step 7:

[0431] The user makes the final decision, making revisions to the design proposal and making purchases. The server receives user feedback in real time and uses that information to improve future design proposals and product recommendations.

[0432] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0433] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0434] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0435] [Third Embodiment]

[0436] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0437] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0438] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0439] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0440] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0441] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0442] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0443] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0444] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0445] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0446] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0447] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0448] This invention provides a system that efficiently and automatically generates building designs using generative AI. The aim of this system is to establish optimal designs and processes from the early stages of a construction project and minimize labor costs.

[0449] The user first inputs the basic design requirements for the building using a terminal. This includes information such as the building's purpose, size, budget, and location. Once this information is sent to the server, the server uses AI to analyze the requirements and extract the basic data necessary for the design.

[0450] The server automatically generates multiple design proposals based on the acquired basic data. These design proposals are evaluated considering ease of construction and cost efficiency. Furthermore, the server consults a market database to gather information for selecting the optimal components and materials. This results in the creation of a material list that takes cost and sustainability into consideration.

[0451] After the user reviews the generated design proposal, the server uses a simulation model to generate building assembly procedures. This simulation models efficient procedures and optimizes each stage of assembly. The server further optimizes the procedures and predicts the required workforce and skill levels using AI learned from the experience of skilled workers. Based on this information, the user can determine the resources needed for the project.

[0452] For example, when constructing an office building, the user inputs the number of floors, total floor area, and budget. Based on this, the server generates multiple design options, selects the optimal materials and components, and automatically generates procedures to efficiently advance the construction process. This entire process provides a practical approach to solving the challenges of labor shortages and rising costs that the construction industry faces.

[0453] The following describes the processing flow.

[0454] Step 1:

[0455] The user uses a terminal to input the building's design requirements. This information includes details such as the building's purpose, size, budget, and location.

[0456] Step 2:

[0457] The terminal sends these design requirements to the server. The server analyzes the received data and identifies the basic data needed for the design.

[0458] Step 3:

[0459] The server automatically generates multiple design proposals using AI based on the underlying data. These proposals include specific plans regarding the building's shape and structural layout.

[0460] Step 4:

[0461] The server evaluates each generated design proposal for ease of construction and cost-effectiveness. This evaluation is performed to determine the ranking of the designs.

[0462] Step 5:

[0463] Based on the evaluation results, the server presents the user with the most suitable design proposal. The user can then review and select this proposal on their terminal.

[0464] Step 6:

[0465] The server consults market databases to select the optimal materials and components based on the design proposal. This process takes into account factors such as cost and supply stability.

[0466] Step 7:

[0467] The server generates a simulation model of the building's assembly procedure using the selected materials and components. An efficient process is optimized within the model.

[0468] Step 8:

[0469] The server uses AI, which has learned from the experience of skilled workers, to optimize the assembly process. This allows it to predict the required workforce and skill level.

[0470] Step 9:

[0471] Users receive information on the human resources and skill levels required for the project on their devices, and then use that information to refine the project plan.

[0472] (Example 1)

[0473] Next, we will describe Example 1. 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."

[0474] In the construction industry, there is a demand for increased efficiency and cost reduction in the design process. However, traditional methods require considerable time and effort to create design proposals and select optimal materials, exacerbating labor shortages. This presents a challenge in establishing a rapid and cost-effective design process.

[0475] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0476] In this invention, the server includes means for analyzing design information and extracting technical data, means for automatically generating multiple design proposals based on the technical data, and means for generating assembly procedures using a simulation model. This streamlines the process from design to construction, enabling cost reduction and optimization of labor.

[0477] "Design information" refers to the fundamental elements necessary for the design of a structure, and includes information regarding its purpose, scale, budget, and location.

[0478] "Technical data" refers to fundamental data necessary for design, analyzed from design information, and includes structural indicators and technical conditions.

[0479] A "design proposal" is a set of multiple design plans automatically generated based on technical data, taking into account constructability and cost efficiency.

[0480] "Materials" refer to the materials and components used in the construction of structures, and are selected with consideration for mass production and sustainability.

[0481] "Assembly procedure" refers to a series of steps and methods for efficiently assembling a structure based on the design plan.

[0482] "Artificial intelligence" refers to technology that learns from human experience and helps optimize design and construction processes.

[0483] A "market database" refers to a database that stores information on the supply status and costs of materials and supplies.

[0484] The user first inputs building design information using a terminal. This includes basic elements such as the purpose, size, budget, and location of the structure to be built. The terminal then transmits this information to the server via the network.

[0485] The server inputs the received design information into a generative AI model, which then analyzes it to extract technical data. The generative AI model used has the capability to generate the data necessary for the design through analysis and verifies the consistency of various conditions in the design information.

[0486] Next, the server automatically generates multiple design options based on the extracted technical data and evaluates them based on constructability and cost-effectiveness. The design options are proposed by AI, taking into account design diversity and functionality, and are visualized to make it easier for the user to select.

[0487] Furthermore, the server accesses a market database to select the most suitable materials and supplies. This selection process is optimized from the perspective of cost-effectiveness and sustainability, and a list of materials tailored to the design proposal is created.

[0488] Based on the design proposal selected by the user, the server uses a simulation model to generate an efficient assembly procedure. The simulation models the construction process step by step and proposes an efficient procedure.

[0489] Finally, the server utilizes artificial intelligence learned from human experience to further optimize the assembly process and predict the required workforce and skill levels. Based on this information, users can assemble project teams and allocate resources.

[0490] As a concrete example, when a user designs a new office building, the user inputs information such as the number of floors, total floor area, and budget into a terminal. Based on this information, the server generates multiple design proposals, selects the optimal materials and components, and automatically generates an efficient construction process. In this process, an example of a text prompt that the user inputs into the generated AI model is: "Please generate building design proposals. The purpose is an office building, with 10 floors, a total floor area of ​​2000 square meters, and a budget of 50 million yen. Please suggest the optimal list of materials and assembly procedures."

[0491] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0492] Step 1:

[0493] The user inputs building design information using a terminal. This input information includes the building's purpose, size (e.g., number of floors, total floor area), budget, and location. This data is basic information that is sent directly to the server.

[0494] Step 2:

[0495] The terminal sends the design information entered by the user to the server. This transmission occurs in real time, and the server immediately converts the information into a format that it can analyze. This prepares the server to start the analysis process.

[0496] Step 3:

[0497] The server inputs the received design information into a generating AI model, which then analyzes the design conditions based on this information. Specifically, it extracts the technical data necessary for the design from the input information and stores it as basic data. During this process, checks are also performed to maintain data consistency and integrity. The output is the analyzed technical data.

[0498] Step 4:

[0499] The server automatically generates multiple design proposals using extracted technical data. Data calculations are performed using a generation AI model, and various design options are created. The designs take constructability and cost efficiency into consideration, and multiple design proposals are obtained as output.

[0500] Step 5:

[0501] The server selects the most suitable materials and components for each generated design proposal by accessing a market database. The selection process evaluates the cost-effectiveness and sustainability of the materials. The output is a list of materials corresponding to each design proposal.

[0502] Step 6:

[0503] The user reviews the design proposals provided by the server via their terminal. They select the most suitable design from among several options or send feedback to the server as needed. This selection information is used to generate the assembly procedure in the next step.

[0504] Step 7:

[0505] The server generates assembly procedures using a simulation model based on the selected design proposal. This process models each stage of assembly and designs efficient procedures. The output is a specific set of assembly procedures.

[0506] Step 8:

[0507] The server further optimizes assembly procedures using artificial intelligence learned from the experience of skilled workers. This allows it to predict the required workforce and skill levels. The output provides predictive information regarding the number of workers and skill levels. This information serves as an important guide for users when developing actual construction plans.

[0508] (Application Example 1)

[0509] Next, we will explain Application Example 1. In the following explanation, 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."

[0510] Traditional construction and production line design often involved inefficient processes that relied heavily on human experience and manual labor, requiring significant time and effort, especially for complex designs. Furthermore, predicting the necessary workforce and skill levels was difficult, posing challenges to resource optimization. Similarly, in production line design, developing efficient robot motion plans was challenging, sometimes resulting in low productivity.

[0511] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0512] In this invention, the server includes means for inputting building design requirements, means for analyzing the design requirements and extracting basic data, means for automatically generating multiple design proposals based on the basic data, means for inputting production line designs and optimizing efficient work processes, and means for simulating robot movements and generating work procedures based on the design proposals. This enables efficient design of construction projects and production lines, as well as optimization of labor.

[0513] "Building design requirements" is a general term for the basic information necessary for design in a construction project, such as its purpose, scale, budget, and location.

[0514] "Basic data" refers to a collection of fundamental information necessary for generating design proposals, extracted by analyzing the building's design requirements.

[0515] "Automatic generation of design proposals" is a process in which a computer generates multiple design patterns based on basic data.

[0516] "Ease of construction" is a concept that indicates the degree of ease and efficiency in carrying out construction work according to the design proposal.

[0517] "Cost efficiency" is a measure that evaluates how economical a particular design proposal or material selection is within a given budget.

[0518] "Selection of components and materials" refers to the process of choosing the structural and building materials necessary for the design based on various selection criteria.

[0519] "Assembly procedure" refers to the specific work processes and arrangements necessary when constructing a building.

[0520] "Forecasting labor force and skill levels" is the process of estimating the number of personnel required for construction or production, as well as the skill level each of them should possess.

[0521] "Production line design" refers to planning the flow and process of product production in a manufacturing plant.

[0522] "Robot motion simulation" refers to the process of reproducing and examining the movements of factory machinery in a virtual space based on a design proposal, in order to ensure efficient operation.

[0523] The system for implementing this invention aims to improve the efficiency and automation of design processes related to architecture and manufacturing. This system includes a server, user terminals, and factory robots, and utilizes a generative AI model and a simulation engine.

[0524] Users input building design requirements and production line specifications via a terminal. This includes the building's purpose, size, budget, location, and the type and quantity of products to be manufactured. This information is sent to a server, which uses a generative AI model to analyze the input data and extract the necessary foundational data. Based on this foundational data, the server automatically generates multiple design options and evaluates the generated designs based on ease of construction and cost efficiency. The server also accesses a market database to select the most suitable materials and components.

[0525] For building assembly procedures and production line operations, the server uses a simulation engine to generate efficient processes and optimize robot movements. By running simulations of robot system movements, the optimized work procedures can be used in the actual manufacturing environment. This process also predicts the workforce and skill levels required, determining the resources needed for the project.

[0526] A concrete example of this system's use is in an automobile manufacturing plant when producing a new model. The user inputs the production volume of the new model, the factory space, and the budget, and based on that, the system generates an optimal production line design and robot operation procedures.

[0527] Examples of prompts for a generative AI model are as follows:

[0528] "Design a production line for a new car model. The production volume for the Model X is 500 units per month, the total budget is 10 million yen, and we have 2000 square meters of factory space available. Please create the optimal layout and process."

[0529] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0530] Step 1:

[0531] Users input building design requirements and production line specifications via a terminal. This includes project objectives, scale, budget, location, or product type and quantity. This input data is sent to the server as basic prerequisites for the design.

[0532] Step 2:

[0533] The server uses the received input data to run a generating AI model and analyze the requirements. This process extracts the necessary foundational data, including specific information such as the number of floors in a building and the number of parts required.

[0534] Step 3:

[0535] The server automatically generates multiple design options using an AI model based on the underlying data. During this process, the design options are evaluated considering factors such as ease of construction and cost efficiency. The output is a list of selectable design options.

[0536] Step 4:

[0537] The server accesses a market database and selects the optimal materials and components based on the evaluated design proposal. At this stage, cost and ease of supply are prioritized, and a list of corresponding materials is output.

[0538] Step 5:

[0539] The server uses a simulation engine to generate building assembly procedures and production line operations based on the generated AI model. This results in optimized work procedures being output. Specifically, it instructs the robots on the order in which they should perform their tasks.

[0540] Step 6:

[0541] The user reviews the design proposal and optimized work procedures generated on the terminal and makes adjustments as needed. This step includes simulating the work procedures and evaluating their feasibility.

[0542] Step 7:

[0543] Ultimately, the server outputs an action plan for the robots that make up the production line and supports the execution of that plan. Specifically, the robots autonomously begin their work based on the generated plan.

[0544] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0545] This invention provides a system that incorporates user emotional data into the creation and evaluation of design proposals by integrating an emotion engine into the building design process.

[0546] When users input building design requirements using a device, the emotion engine recognizes their emotions in real time from their facial expressions and voice. This emotion data is used to determine which designs the user will respond to more positively.

[0547] The server receives design requirements and emotional data from the user simultaneously. The server's AI generates multiple design proposals based on this information. These proposals are evaluated using the user's emotional data in addition to standard evaluation criteria. This prioritizes the design proposal that the user is most likely to prefer.

[0548] Based on the selected design proposal, the server selects the optimal materials and components from the market database and generates the necessary assembly procedures using a simulation model. This entire process is also displayed on the terminal for the user to review.

[0549] For example, if a user is designing an office building, the emotion engine can recognize positive emotions such as joy and excitement in response to the requirements the user has entered. The server can then incorporate this emotional data into the evaluation of design proposals and present the proposal that best meets the user's expectations.

[0550] This system will enable the creation of design proposals that better fit the user's intentions and emotions, and is expected to improve the accuracy and satisfaction of the design process.

[0551] The following describes the processing flow.

[0552] Step 1:

[0553] The user uses a device to input building design requirements. During this process, an emotion engine analyzes the user's emotions in real time through the user's camera footage and audio.

[0554] Step 2:

[0555] The device sends emotional data to the server along with the entered design requirements. This data includes the user's emotional state and the intensity of their emotions.

[0556] Step 3:

[0557] The server analyzes the design requirements and extracts basic data. The server's AI model automatically generates multiple design options based on this basic data and sentiment data.

[0558] Step 4:

[0559] The server evaluates the generated design proposals, taking into account not only ease of construction and cost-effectiveness, but also user sentiment. In particular, design proposals that evoke positive emotions in users receive high ratings.

[0560] Step 5:

[0561] The user views a list of proposed designs sent from the server on their device. The emotion engine then analyzes the user's reaction to these designs and provides feedback to the server as needed.

[0562] Step 6:

[0563] The server accesses the market database for a more detailed evaluation and selects the optimal materials and components. This verifies whether the proposed selection is realistic and feasible.

[0564] Step 7:

[0565] The server generates the necessary assembly procedures based on the selected design proposal using a simulation model. Fine-tuning based on user sentiment is also possible.

[0566] Step 8:

[0567] The device presents the user with the final design proposal and assembly procedure, which the user can then adopt as the project execution plan. This allows the user to proceed with the project according to a design that better resonates with their emotions.

[0568] (Example 2)

[0569] Next, we will describe Example 2. 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."

[0570] Conventional building design systems have the problem that they fail to adequately address the emotions and needs of users because the creation and evaluation of design proposals are based solely on technical performance and cost. This can lead to decreased user satisfaction and an inefficient design process.

[0571] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0572] In this invention, the server includes means for acquiring and evaluating user emotional information, means for selecting a design proposal that harmonizes with the user's emotions based on the evaluation, and means for accessing a market database to select materials and components. This enables the presentation of design proposals that emotionally satisfy the user and efficient resource selection.

[0573] "Building design requirements" refer to information that describes the specific conditions and preferences regarding the structure, function, and design of a building desired by the user.

[0574] "Basic data" refers to the fundamental information and specifications necessary for design, extracted from the design requirements.

[0575] A "design proposal" is a specific design plan for a building that is proposed based on basic data.

[0576] "Means of evaluation" refer to methods and mechanisms for analyzing and comparing generated design proposals based on various criteria.

[0577] "Emotional information" refers to information about emotions that is analyzed from the user's facial expressions, voice, etc., and reflected in the design process.

[0578] "Materials and components" refers to the various materials and parts used in the construction of a building.

[0579] A "simulation model" is a computer model that reproduces a designed building in a virtual space to verify the assembly procedure and feasibility.

[0580] "Labor force and skill level" refers to the number of personnel required for building construction and their respective skills, and is a factor in evaluating the efficiency of design and actual construction.

[0581] This invention provides a system that incorporates user emotional information into the building design process. The system is implemented using hardware and software such as terminals, servers, and generative AI models.

[0582] First, the user uses a device to input the building's design requirements. The device is equipped with a camera and microphone, and captures emotional information in real time from the user's facial expressions and voice. For example, if the user expresses positive emotions when requesting an "open office space," that emotional information is recorded.

[0583] Next, the terminal sends the user's design requirements and emotional information to the server. The server inputs this data into a generating AI model. This model generates multiple design proposals based on the received prompts, such as "Generate office building design proposals that the user will find positive."

[0584] The generated design proposals are evaluated on the server using user sentiment information. Sentiment information is used to increase the importance of design elements that elicit particularly positive user responses.

[0585] The server then accesses a market database to select the most suitable materials and components for the chosen design. This selection takes into account cost efficiency and ease of supply.

[0586] Furthermore, the server uses a simulation model to generate assembly procedures using the selected materials. This simulation visualizes how the design proposal will be realized and presents it to the user.

[0587] In this way, the system provides design proposals that fit the user's emotions, improving the efficiency and satisfaction of the entire design process.

[0588] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0589] Step 1:

[0590] The user inputs building design requirements using a terminal. The terminal uses a camera and microphone to capture the user's facial expressions and voice in real time, acquiring emotional information. The input design requirements and acquired emotional information are converted into digital data by the terminal's processing. The output of this step is the digitized design requirements and emotional data.

[0591] Step 2:

[0592] The terminal sends digitized design requirements and sentiment data to the server. The server analyzes the received data and generates prompt sentences for the generative AI model. For example, it might generate a sentence like, "Generate an office building design proposal that will make the user feel positive." This prompt sentence becomes the input to the generative AI model. The output is the prompt sentence.

[0593] Step 3:

[0594] The server uses a generative AI model to generate design proposals based on the input prompt text. The model creates a variety of proposals using a rich design database and historical training data. In this generation process, the input sentiment data influences the type and style of the design proposals. The output consists of multiple design proposals.

[0595] Step 4:

[0596] The server evaluates the generated design proposals. This process considers user sentiment data, prioritizing design elements that receive positive responses. Ease of construction and cost-effectiveness are also included in the evaluation. The output is a list of the evaluated design proposals.

[0597] Step 5:

[0598] The server accesses a market database and selects the optimal materials and components to match highly-rated design proposals. Cost and ease of supply are also considered in the selection process. This selection process generates a detailed resource list.

[0599] Step 6:

[0600] The server generates building assembly procedures using a simulation model with selected materials. The simulation verifies the feasibility and assembly efficiency of the design proposal. The output is a detailed assembly procedure and its visual simulation.

[0601] Step 7:

[0602] The server sends the final design proposal and simulation results to the terminal. The terminal presents this to the user and requests feedback. The user then makes a final confirmation of the design proposal and provides instructions for any necessary modifications. The output of this step is the presentation of results and feedback to the user.

[0603] (Application Example 2)

[0604] Next, we will explain application example 2. In the following explanation, 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."

[0605] In today's world, designing products and recommending items that take user emotions into consideration is becoming increasingly important. However, conventional systems have struggled to adequately reflect user wishes and emotions in design proposals and product recommendations, making it difficult to improve user satisfaction. Therefore, there is a need to analyze user emotions in real time and utilize the results to generate design proposals and recommend customized products.

[0606] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0607] In this invention, the server includes means for inputting design requirements and acquiring user emotion data, means for analyzing the design requirements and emotion data and extracting basic information, and means for automatically generating multiple design proposals based on the basic information. This makes it possible to generate design proposals that take user emotions into consideration and to recommend the most suitable product to each individual user.

[0608] "Design requirements" are the specific conditions and specifications that users need regarding the design of a building or product.

[0609] "Emotional data" refers to information about a user's emotions obtained from their facial expressions and voice.

[0610] "Basic information" refers to fundamental design indicators obtained by analyzing design requirements and sentiment data.

[0611] "Emotion-based product recommendations" is a process that uses user emotional data to suggest products that users are likely to like.

[0612] "Components" refer to the collective term for the parts and materials used to construct a building or product.

[0613] "Assembly procedure" refers to the sequence of steps required to combine the various elements of a building or product to create a finished product.

[0614] "Labor factors" is a concept that refers to the human resources and required skills related to design and construction.

[0615] "Technical level" refers to the degree of specialized knowledge and skills required to carry out a particular design or construction.

[0616] A "user sentiment-based process" refers to a series of processes that are carried out based on user sentiment data.

[0617] A "market database" is a digital database that collects information on costs and supply.

[0618] This invention relates to a system for generating design proposals and recommending products that reflect user emotions. In this embodiment, the server receives design requirements and emotion data from the user terminal and generates an optimal design proposal based on them.

[0619] When users input design requirements using devices such as smartphones or tablets, emotional data is acquired in real time through the device's camera and microphone. Emotion recognition APIs (e.g., Google Cloud Vision API, Microsoft Azure Face API) are used for emotion recognition. The acquired emotional data is analyzed based on the user's facial expressions and voice tone to identify positive and negative emotions, which are then sent to the server as foundational information.

[0620] The server analyzes the received information using machine learning models (e.g., TensorFlow, PyTorch) and generates design proposals. These proposals are then evaluated based on user sentiment, and the optimal proposal is selected. Throughout this process, the acquired user sentiment data is given significant weight, and the design proposals are customized accordingly.

[0621] Furthermore, to recommend products suitable for the user, the server accesses the market database and makes recommendations considering efficiency and supply availability. It also suggests product colors and designs based on the user's preferences to enhance the user experience.

[0622] For example, when a user chooses new office furniture, the emotion engine can recognize positive emotions such as joy and excitement, and suggest products based on those emotions (e.g., a desk in a calming color or a comfortable chair).

[0623] Examples of prompt messages include, "Generate design proposals based on user input and suggest customized products based on emotional data, providing users with a wider range of choices." In this way, the system can contribute to improving the user's purchasing experience and satisfaction with the design process.

[0624] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0625] Step 1:

[0626] The user enters design requirements on the terminal. The entered data includes the conditions and specifications necessary for the design. This data is then ready to be sent to the server.

[0627] Step 2:

[0628] The device uses its camera and microphone to acquire user emotion data in real time. It utilizes facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and voice. The acquired emotion data is sent to the server as a numerical value indicating whether the emotion is positive or negative.

[0629] Step 3:

[0630] The server receives design requirements and sentiment data sent from the terminal and extracts basic information using a machine learning model. Here, it determines the necessary data points based on the design requirements and, taking sentiment data into account, decides which parts should be prioritized in the design.

[0631] Step 4:

[0632] The server runs a generative AI model to automatically generate multiple design options based on the underlying information. The generated design options are scored by an algorithm, and the evaluation criteria are adjusted based on sentiment data. Through this process, the design option best suited to the user is selected.

[0633] Step 5:

[0634] The server accesses the market database based on the selected design proposal and selects components that consider efficiency and supply availability. The selected components, along with information such as price and supply availability, are presented to the user.

[0635] Step 6:

[0636] The user reviews the design proposals and recommended components received from the server on their device. For products the user shows interest in, customized recommendation comments are generated based on the prompt text, improving the user experience.

[0637] Step 7:

[0638] The user makes the final decision, making revisions to the design proposal and making purchases. The server receives user feedback in real time and uses that information to improve future design proposals and product recommendations.

[0639] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0640] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0641] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0642] [Fourth Embodiment]

[0643] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0644] As shown in Figure 7, the 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.

[0645] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0646] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0647] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0648] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0649] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0650] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors in the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0651] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0652] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0653] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0654] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0655] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0656] This invention provides a system that efficiently and automatically generates building designs using generative AI. The aim of this system is to establish optimal designs and processes from the early stages of a construction project and minimize labor costs.

[0657] The user first inputs the basic design requirements for the building using a terminal. This includes information such as the building's purpose, size, budget, and location. Once this information is sent to the server, the server uses AI to analyze the requirements and extract the basic data necessary for the design.

[0658] The server automatically generates multiple design proposals based on the acquired basic data. These design proposals are evaluated considering ease of construction and cost efficiency. Furthermore, the server consults a market database to gather information for selecting the optimal components and materials. This results in the creation of a material list that takes cost and sustainability into consideration.

[0659] After the user reviews the generated design proposal, the server uses a simulation model to generate building assembly procedures. This simulation models efficient procedures and optimizes each stage of assembly. The server further optimizes the procedures and predicts the required workforce and skill levels using AI learned from the experience of skilled workers. Based on this information, the user can determine the resources needed for the project.

[0660] For example, when constructing an office building, the user inputs the number of floors, total floor area, and budget. Based on this, the server generates multiple design options, selects the optimal materials and components, and automatically generates procedures to efficiently advance the construction process. This entire process provides a practical approach to solving the challenges of labor shortages and rising costs that the construction industry faces.

[0661] The following describes the processing flow.

[0662] Step 1:

[0663] The user uses a terminal to input the building's design requirements. This information includes details such as the building's purpose, size, budget, and location.

[0664] Step 2:

[0665] The terminal sends these design requirements to the server. The server analyzes the received data and identifies the basic data needed for the design.

[0666] Step 3:

[0667] The server automatically generates multiple design proposals using AI based on the underlying data. These proposals include specific plans regarding the building's shape and structural layout.

[0668] Step 4:

[0669] The server evaluates each generated design proposal for ease of construction and cost-effectiveness. This evaluation is performed to determine the ranking of the designs.

[0670] Step 5:

[0671] Based on the evaluation results, the server presents the user with the most suitable design proposal. The user can then review and select this proposal on their terminal.

[0672] Step 6:

[0673] The server consults market databases to select the optimal materials and components based on the design proposal. This process takes into account factors such as cost and supply stability.

[0674] Step 7:

[0675] The server generates a simulation model of the building's assembly procedure using the selected materials and components. An efficient process is optimized within the model.

[0676] Step 8:

[0677] The server uses AI, which has learned from the experience of skilled workers, to optimize the assembly process. This allows it to predict the required workforce and skill level.

[0678] Step 9:

[0679] Users receive information on the human resources and skill levels required for the project on their devices, and then use that information to refine the project plan.

[0680] (Example 1)

[0681] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0682] In the construction industry, there is a demand for increased efficiency and cost reduction in the design process. However, traditional methods require considerable time and effort to create design proposals and select optimal materials, exacerbating labor shortages. This presents a challenge in establishing a rapid and cost-effective design process.

[0683] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0684] In this invention, the server includes means for analyzing design information and extracting technical data, means for automatically generating multiple design proposals based on the technical data, and means for generating assembly procedures using a simulation model. This streamlines the process from design to construction, enabling cost reduction and optimization of labor.

[0685] "Design information" refers to the fundamental elements necessary for the design of a structure, and includes information regarding its purpose, scale, budget, and location.

[0686] "Technical data" refers to fundamental data necessary for design, analyzed from design information, and includes structural indicators and technical conditions.

[0687] A "design proposal" is a set of multiple design plans automatically generated based on technical data, taking into account constructability and cost efficiency.

[0688] "Materials" refer to the materials and components used in the construction of structures, and are selected with consideration for mass production and sustainability.

[0689] "Assembly procedure" refers to a series of steps and methods for efficiently assembling a structure based on the design plan.

[0690] "Artificial intelligence" refers to technology that learns from human experience and helps optimize design and construction processes.

[0691] A "market database" refers to a database that stores information on the supply status and costs of materials and supplies.

[0692] The user first inputs building design information using a terminal. This includes basic elements such as the purpose, size, budget, and location of the structure to be built. The terminal then transmits this information to the server via the network.

[0693] The server inputs the received design information into a generative AI model, which then analyzes it to extract technical data. The generative AI model used has the capability to generate the data necessary for the design through analysis and verifies the consistency of various conditions in the design information.

[0694] Next, the server automatically generates multiple design options based on the extracted technical data and evaluates them based on constructability and cost-effectiveness. The design options are proposed by AI, taking into account design diversity and functionality, and are visualized to make it easier for the user to select.

[0695] Furthermore, the server accesses a market database to select the most suitable materials and supplies. This selection process is optimized from the perspective of cost-effectiveness and sustainability, and a list of materials tailored to the design proposal is created.

[0696] Based on the design proposal selected by the user, the server uses a simulation model to generate an efficient assembly procedure. The simulation models the construction process step by step and proposes an efficient procedure.

[0697] Finally, the server utilizes artificial intelligence learned from human experience to further optimize the assembly process and predict the required workforce and skill levels. Based on this information, users can assemble project teams and allocate resources.

[0698] As a concrete example, when a user designs a new office building, the user inputs information such as the number of floors, total floor area, and budget into a terminal. Based on this information, the server generates multiple design proposals, selects the optimal materials and components, and automatically generates an efficient construction process. In this process, an example of a text prompt that the user inputs into the generated AI model is: "Please generate building design proposals. The purpose is an office building, with 10 floors, a total floor area of ​​2000 square meters, and a budget of 50 million yen. Please suggest the optimal list of materials and assembly procedures."

[0699] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0700] Step 1:

[0701] The user inputs building design information using a terminal. This input information includes the building's purpose, size (e.g., number of floors, total floor area), budget, and location. This data is basic information that is sent directly to the server.

[0702] Step 2:

[0703] The terminal sends the design information entered by the user to the server. This transmission occurs in real time, and the server immediately converts the information into a format that it can analyze. This prepares the server to start the analysis process.

[0704] Step 3:

[0705] The server inputs the received design information into a generating AI model, which then analyzes the design conditions based on this information. Specifically, it extracts the technical data necessary for the design from the input information and stores it as basic data. During this process, checks are also performed to maintain data consistency and integrity. The output is the analyzed technical data.

[0706] Step 4:

[0707] The server automatically generates multiple design proposals using extracted technical data. Data calculations are performed using a generation AI model, and various design options are created. The designs take constructability and cost efficiency into consideration, and multiple design proposals are obtained as output.

[0708] Step 5:

[0709] The server selects the most suitable materials and components for each generated design proposal by accessing a market database. The selection process evaluates the cost-effectiveness and sustainability of the materials. The output is a list of materials corresponding to each design proposal.

[0710] Step 6:

[0711] The user reviews the design proposals provided by the server via their terminal. They select the most suitable design from among several options or send feedback to the server as needed. This selection information is used to generate the assembly procedure in the next step.

[0712] Step 7:

[0713] The server generates assembly procedures using a simulation model based on the selected design proposal. This process models each stage of assembly and designs efficient procedures. The output is a specific set of assembly procedures.

[0714] Step 8:

[0715] The server further optimizes assembly procedures using artificial intelligence learned from the experience of skilled workers. This allows it to predict the required workforce and skill levels. The output provides predictive information regarding the number of workers and skill levels. This information serves as an important guide for users when developing actual construction plans.

[0716] (Application Example 1)

[0717] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0718] Traditional construction and production line design often involved inefficient processes that relied heavily on human experience and manual labor, requiring significant time and effort, especially for complex designs. Furthermore, predicting the necessary workforce and skill levels was difficult, posing challenges to resource optimization. Similarly, in production line design, developing efficient robot motion plans was challenging, sometimes resulting in low productivity.

[0719] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0720] In this invention, the server includes means for inputting building design requirements, means for analyzing the design requirements and extracting basic data, means for automatically generating multiple design proposals based on the basic data, means for inputting production line designs and optimizing efficient work processes, and means for simulating robot movements and generating work procedures based on the design proposals. This enables efficient design of construction projects and production lines, as well as optimization of labor.

[0721] "Building design requirements" is a general term for the basic information necessary for design in a construction project, such as its purpose, scale, budget, and location.

[0722] "Basic data" refers to a collection of fundamental information necessary for generating design proposals, extracted by analyzing the building's design requirements.

[0723] "Automatic generation of design proposals" is a process in which a computer generates multiple design patterns based on basic data.

[0724] "Ease of construction" is a concept that indicates the degree of ease and efficiency in carrying out construction work according to the design proposal.

[0725] "Cost efficiency" is a measure that evaluates how economical a particular design proposal or material selection is within a given budget.

[0726] "Selection of components and materials" refers to the process of choosing the structural and building materials necessary for the design based on various selection criteria.

[0727] "Assembly procedure" refers to the specific work processes and arrangements necessary when constructing a building.

[0728] "Forecasting labor force and skill levels" is the process of estimating the number of personnel required for construction or production, as well as the skill level each of them should possess.

[0729] "Production line design" refers to planning the flow and process of product production in a manufacturing plant.

[0730] "Robot motion simulation" refers to the process of reproducing and examining the movements of factory machinery in a virtual space based on a design proposal, in order to ensure efficient operation.

[0731] The system for implementing this invention aims to improve the efficiency and automation of design processes related to architecture and manufacturing. This system includes a server, user terminals, and factory robots, and utilizes a generative AI model and a simulation engine.

[0732] Users input building design requirements and production line specifications via a terminal. This includes the building's purpose, size, budget, location, and the type and quantity of products to be manufactured. This information is sent to a server, which uses a generative AI model to analyze the input data and extract the necessary foundational data. Based on this foundational data, the server automatically generates multiple design options and evaluates the generated designs based on ease of construction and cost efficiency. The server also accesses a market database to select the most suitable materials and components.

[0733] For building assembly procedures and production line operations, the server uses a simulation engine to generate efficient processes and optimize robot movements. By running simulations of robot system movements, the optimized work procedures can be used in the actual manufacturing environment. This process also predicts the workforce and skill levels required, determining the resources needed for the project.

[0734] A concrete example of this system's use is in an automobile manufacturing plant when producing a new model. The user inputs the production volume of the new model, the factory space, and the budget, and based on that, the system generates an optimal production line design and robot operation procedures.

[0735] Examples of prompts for a generative AI model are as follows:

[0736] "Design a production line for a new car model. The production volume for the Model X is 500 units per month, the total budget is 10 million yen, and we have 2000 square meters of factory space available. Please create the optimal layout and process."

[0737] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0738] Step 1:

[0739] Users input building design requirements and production line specifications via a terminal. This includes project objectives, scale, budget, location, or product type and quantity. This input data is sent to the server as basic prerequisites for the design.

[0740] Step 2:

[0741] The server uses the received input data to run a generating AI model and analyze the requirements. This process extracts the necessary foundational data, including specific information such as the number of floors in a building and the number of parts required.

[0742] Step 3:

[0743] The server automatically generates multiple design options using an AI model based on the underlying data. During this process, the design options are evaluated considering factors such as ease of construction and cost efficiency. The output is a list of selectable design options.

[0744] Step 4:

[0745] The server accesses a market database and selects the optimal materials and components based on the evaluated design proposal. At this stage, cost and ease of supply are prioritized, and a list of corresponding materials is output.

[0746] Step 5:

[0747] The server uses a simulation engine to generate building assembly procedures and production line operations based on the generated AI model. This results in optimized work procedures being output. Specifically, it instructs the robots on the order in which they should perform their tasks.

[0748] Step 6:

[0749] The user reviews the design proposal and optimized work procedures generated on the terminal and makes adjustments as needed. This step includes simulating the work procedures and evaluating their feasibility.

[0750] Step 7:

[0751] Ultimately, the server outputs an action plan for the robots that make up the production line and supports the execution of that plan. Specifically, the robots autonomously begin their work based on the generated plan.

[0752] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0753] This invention provides a system that incorporates user emotional data into the creation and evaluation of design proposals by integrating an emotion engine into the building design process.

[0754] When users input building design requirements using a device, the emotion engine recognizes their emotions in real time from their facial expressions and voice. This emotion data is used to determine which designs the user will respond to more positively.

[0755] The server receives design requirements and emotional data from the user simultaneously. The server's AI generates multiple design proposals based on this information. These proposals are evaluated using the user's emotional data in addition to standard evaluation criteria. This prioritizes the design proposal that the user is most likely to prefer.

[0756] Based on the selected design proposal, the server selects the optimal materials and components from the market database and generates the necessary assembly procedures using a simulation model. This entire process is also displayed on the terminal for the user to review.

[0757] For example, if a user is designing an office building, the emotion engine can recognize positive emotions such as joy and excitement in response to the requirements the user has entered. The server can then incorporate this emotional data into the evaluation of design proposals and present the proposal that best meets the user's expectations.

[0758] This system will enable the creation of design proposals that better fit the user's intentions and emotions, and is expected to improve the accuracy and satisfaction of the design process.

[0759] The following describes the processing flow.

[0760] Step 1:

[0761] The user uses a device to input building design requirements. During this process, an emotion engine analyzes the user's emotions in real time through the user's camera footage and audio.

[0762] Step 2:

[0763] The device sends emotional data to the server along with the entered design requirements. This data includes the user's emotional state and the intensity of their emotions.

[0764] Step 3:

[0765] The server analyzes the design requirements and extracts basic data. The server's AI model automatically generates multiple design options based on this basic data and sentiment data.

[0766] Step 4:

[0767] The server evaluates the generated design proposals, taking into account not only ease of construction and cost-effectiveness, but also user sentiment. In particular, design proposals that evoke positive emotions in users receive high ratings.

[0768] Step 5:

[0769] The user views a list of proposed designs sent from the server on their device. The emotion engine then analyzes the user's reaction to these designs and provides feedback to the server as needed.

[0770] Step 6:

[0771] The server accesses the market database for a more detailed evaluation and selects the optimal materials and components. This verifies whether the proposed selection is realistic and feasible.

[0772] Step 7:

[0773] The server generates the necessary assembly procedures based on the selected design proposal using a simulation model. Fine-tuning based on user sentiment is also possible.

[0774] Step 8:

[0775] The device presents the user with the final design proposal and assembly procedure, which the user can then adopt as the project execution plan. This allows the user to proceed with the project according to a design that better resonates with their emotions.

[0776] (Example 2)

[0777] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0778] Conventional building design systems have the problem that they fail to adequately address the emotions and needs of users because the creation and evaluation of design proposals are based solely on technical performance and cost. This can lead to decreased user satisfaction and an inefficient design process.

[0779] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0780] In this invention, the server includes means for acquiring and evaluating user emotional information, means for selecting a design proposal that harmonizes with the user's emotions based on the evaluation, and means for accessing a market database to select materials and components. This enables the presentation of design proposals that emotionally satisfy the user and efficient resource selection.

[0781] "Building design requirements" refer to information that describes the specific conditions and preferences regarding the structure, function, and design of a building desired by the user.

[0782] "Basic data" refers to the fundamental information and specifications necessary for design, extracted from the design requirements.

[0783] A "design proposal" is a specific design plan for a building that is proposed based on basic data.

[0784] "Means of evaluation" refer to methods and mechanisms for analyzing and comparing generated design proposals based on various criteria.

[0785] "Emotional information" refers to information about emotions that is analyzed from the user's facial expressions, voice, etc., and reflected in the design process.

[0786] "Materials and components" refers to the various materials and parts used in the construction of a building.

[0787] A "simulation model" is a computer model that reproduces a designed building in a virtual space to verify the assembly procedure and feasibility.

[0788] "Labor force and skill level" refers to the number of personnel required for building construction and their respective skills, and is a factor in evaluating the efficiency of design and actual construction.

[0789] This invention provides a system that incorporates user emotional information into the building design process. The system is implemented using hardware and software such as terminals, servers, and generative AI models.

[0790] First, the user uses a device to input the building's design requirements. The device is equipped with a camera and microphone, and captures emotional information in real time from the user's facial expressions and voice. For example, if the user expresses positive emotions when requesting an "open office space," that emotional information is recorded.

[0791] Next, the terminal sends the user's design requirements and emotional information to the server. The server inputs this data into a generating AI model. This model generates multiple design proposals based on the received prompts, such as "Generate office building design proposals that the user will find positive."

[0792] The generated design proposals are evaluated on the server using user sentiment information. Sentiment information is used to increase the importance of design elements that elicit particularly positive user responses.

[0793] The server then accesses a market database to select the most suitable materials and components for the chosen design. This selection takes into account cost efficiency and ease of supply.

[0794] Furthermore, the server uses a simulation model to generate assembly procedures using the selected materials. This simulation visualizes how the design proposal will be realized and presents it to the user.

[0795] In this way, the system provides design proposals that fit the user's emotions, improving the efficiency and satisfaction of the entire design process.

[0796] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0797] Step 1:

[0798] The user inputs building design requirements using a terminal. The terminal uses a camera and microphone to capture the user's facial expressions and voice in real time, acquiring emotional information. The input design requirements and acquired emotional information are converted into digital data by the terminal's processing. The output of this step is the digitized design requirements and emotional data.

[0799] Step 2:

[0800] The terminal sends digitized design requirements and sentiment data to the server. The server analyzes the received data and generates prompt sentences for the generative AI model. For example, it might generate a sentence like, "Generate an office building design proposal that will make the user feel positive." This prompt sentence becomes the input to the generative AI model. The output is the prompt sentence.

[0801] Step 3:

[0802] The server uses a generative AI model to generate design proposals based on the input prompt text. The model creates a variety of proposals using a rich design database and historical training data. In this generation process, the input sentiment data influences the type and style of the design proposals. The output consists of multiple design proposals.

[0803] Step 4:

[0804] The server evaluates the generated design proposals. This process considers user sentiment data, prioritizing design elements that receive positive responses. Ease of construction and cost-effectiveness are also included in the evaluation. The output is a list of the evaluated design proposals.

[0805] Step 5:

[0806] The server accesses a market database and selects the optimal materials and components to match highly-rated design proposals. Cost and ease of supply are also considered in the selection process. This selection process generates a detailed resource list.

[0807] Step 6:

[0808] The server generates building assembly procedures using a simulation model with selected materials. The simulation verifies the feasibility and assembly efficiency of the design proposal. The output is a detailed assembly procedure and its visual simulation.

[0809] Step 7:

[0810] The server sends the final design proposal and simulation results to the terminal. The terminal presents this to the user and requests feedback. The user then makes a final confirmation of the design proposal and provides instructions for any necessary modifications. The output of this step is the presentation of results and feedback to the user.

[0811] (Application Example 2)

[0812] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0813] In today's world, designing products and recommending items that take user emotions into consideration is becoming increasingly important. However, conventional systems have struggled to adequately reflect user wishes and emotions in design proposals and product recommendations, making it difficult to improve user satisfaction. Therefore, there is a need to analyze user emotions in real time and utilize the results to generate design proposals and recommend customized products.

[0814] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0815] In this invention, the server includes means for inputting design requirements and acquiring user emotion data, means for analyzing the design requirements and emotion data and extracting basic information, and means for automatically generating multiple design proposals based on the basic information. This makes it possible to generate design proposals that take user emotions into consideration and to recommend the most suitable product to each individual user.

[0816] "Design requirements" are the specific conditions and specifications that users need regarding the design of a building or product.

[0817] "Emotional data" refers to information about a user's emotions obtained from their facial expressions and voice.

[0818] "Basic information" refers to fundamental design indicators obtained by analyzing design requirements and sentiment data.

[0819] "Emotion-based product recommendations" is a process that uses user emotional data to suggest products that users are likely to like.

[0820] "Components" refer to the collective term for the parts and materials used to construct a building or product.

[0821] "Assembly procedure" refers to the sequence of steps required to combine the various elements of a building or product to create a finished product.

[0822] "Labor factors" is a concept that refers to the human resources and required skills related to design and construction.

[0823] "Technical level" refers to the degree of specialized knowledge and skills required to carry out a particular design or construction.

[0824] A "user sentiment-based process" refers to a series of processes that are carried out based on user sentiment data.

[0825] A "market database" is a digital database that collects information on costs and supply.

[0826] This invention relates to a system for generating design proposals and recommending products that reflect user emotions. In this embodiment, the server receives design requirements and emotion data from the user terminal and generates an optimal design proposal based on them.

[0827] When users input design requirements using devices such as smartphones or tablets, emotional data is acquired in real time through the device's camera and microphone. Emotion recognition APIs (e.g., Google Cloud Vision API, Microsoft Azure Face API) are used for emotion recognition. The acquired emotional data is analyzed based on the user's facial expressions and voice tone to identify positive and negative emotions, which are then sent to the server as foundational information.

[0828] The server analyzes the received information using machine learning models (e.g., TensorFlow, PyTorch) and generates design proposals. These proposals are then evaluated based on user sentiment, and the optimal proposal is selected. Throughout this process, the acquired user sentiment data is given significant weight, and the design proposals are customized accordingly.

[0829] Furthermore, to recommend products suitable for the user, the server accesses the market database and makes recommendations considering efficiency and supply availability. It also suggests product colors and designs based on the user's preferences to enhance the user experience.

[0830] For example, when a user chooses new office furniture, the emotion engine can recognize positive emotions such as joy and excitement, and suggest products based on those emotions (e.g., a desk in a calming color or a comfortable chair).

[0831] Examples of prompt messages include, "Generate design proposals based on user input and suggest customized products based on emotional data, providing users with a wider range of choices." In this way, the system can contribute to improving the user's purchasing experience and satisfaction with the design process.

[0832] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0833] Step 1:

[0834] The user enters design requirements on the terminal. The entered data includes the conditions and specifications necessary for the design. This data is then ready to be sent to the server.

[0835] Step 2:

[0836] The device uses its camera and microphone to acquire user emotion data in real time. It utilizes facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and voice. The acquired emotion data is sent to the server as a numerical value indicating whether the emotion is positive or negative.

[0837] Step 3:

[0838] The server receives design requirements and sentiment data sent from the terminal and extracts basic information using a machine learning model. Here, it determines the necessary data points based on the design requirements and, taking sentiment data into account, decides which parts should be prioritized in the design.

[0839] Step 4:

[0840] The server runs a generative AI model to automatically generate multiple design options based on the underlying information. The generated design options are scored by an algorithm, and the evaluation criteria are adjusted based on sentiment data. Through this process, the design option best suited to the user is selected.

[0841] Step 5:

[0842] The server accesses the market database based on the selected design proposal and selects components that consider efficiency and supply availability. The selected components, along with information such as price and supply availability, are presented to the user.

[0843] Step 6:

[0844] The user reviews the design proposals and recommended components received from the server on their device. For products the user shows interest in, customized recommendation comments are generated based on the prompt text, improving the user experience.

[0845] Step 7:

[0846] The user makes the final decision, making revisions to the design proposal and making purchases. The server receives user feedback in real time and uses that information to improve future design proposals and product recommendations.

[0847] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0848] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0849] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0850] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0851] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0852] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0853] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0854] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0855] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0856] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0857] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0858] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0859] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0860] 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.

[0861] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0862] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0863] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0864] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0865] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0866] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0867] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0868] The following is further disclosed regarding the embodiments described above.

[0869] (Claim 1)

[0870] A means for inputting building design requirements,

[0871] A means for analyzing the aforementioned design requirements and extracting basic data,

[0872] A means for automatically generating multiple design proposals based on the aforementioned basic data,

[0873] A means of evaluating the generated design proposals based on ease of construction and cost efficiency,

[0874] A means of selecting the optimal components and materials,

[0875] A means for generating and optimizing building assembly procedures,

[0876] Means for predicting the workforce and skill levels,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, further comprising means for generating the assembly procedures necessary for design based on the designed building using a simulation model.

[0880] (Claim 3)

[0881] The system according to claim 1, comprising means for accessing a market database and selecting materials and components considering cost efficiency and ease of supply.

[0882] "Example 1"

[0883] (Claim 1)

[0884] A means for inputting design information,

[0885] A means for analyzing the aforementioned design information and extracting technical data,

[0886] A means for automatically generating multiple design proposals based on the aforementioned technical data,

[0887] A means of evaluating the generated design proposals based on constructability and cost efficiency,

[0888] Methods for selecting the optimal materials and components,

[0889] A means for generating and optimizing the assembly procedure of a structure,

[0890] A means of predicting personnel allocation and skill levels,

[0891] A means of improving assembly procedures using artificial intelligence learned from human experience,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, further comprising means for generating the procedures necessary for assembly based on the designed structure using a simulation model.

[0895] (Claim 3)

[0896] The system according to claim 1, comprising means for accessing a market database and selecting materials and supplies considering cost-effectiveness and ease of supply.

[0897] "Application Example 1"

[0898] (Claim 1)

[0899] A means for inputting building design requirements,

[0900] A means for analyzing the aforementioned design requirements and extracting basic data,

[0901] A means for automatically generating multiple design proposals based on the aforementioned basic data,

[0902] A means of evaluating the generated design proposals based on ease of construction and cost efficiency,

[0903] A means of selecting the optimal components and materials,

[0904] A means for generating and optimizing building assembly procedures,

[0905] Means for predicting the workforce and skill levels,

[0906] A means of inputting the design of the production line and optimizing efficient work processes,

[0907] A means for simulating robot movements and generating work procedures based on the design proposal,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] The system according to claim 1, further comprising means for generating the assembly procedures necessary for design based on the designed building using a simulation model.

[0911] (Claim 3)

[0912] The system according to claim 1, comprising means for accessing a market database and selecting materials and components considering cost efficiency and ease of supply.

[0913] "Example 2 of combining an emotion engine"

[0914] (Claim 1)

[0915] A means for inputting building design requirements,

[0916] A means for analyzing the aforementioned design requirements and extracting basic data,

[0917] A means for automatically generating multiple design proposals based on the aforementioned basic data,

[0918] A means of evaluating the generated design proposals based on ease of construction and cost efficiency,

[0919] A means of acquiring and evaluating user emotional information,

[0920] A means of selecting a design proposal that harmonizes with the user's emotions based on evaluation,

[0921] A means of selecting the optimal components and materials,

[0922] A means for generating and optimizing building assembly procedures,

[0923] Means for predicting the workforce and skill levels,

[0924] A system that includes this.

[0925] (Claim 2)

[0926] The system according to claim 1, further comprising means for generating the assembly procedures necessary for design based on the designed building using a simulation model.

[0927] (Claim 3)

[0928] The system according to claim 1, comprising means for accessing a market database and selecting materials and components considering cost efficiency and ease of supply.

[0929] "Application example 2 when combining with an emotional engine"

[0930] (Claim 1)

[0931] A means of inputting design requirements and acquiring user sentiment data,

[0932] A means for analyzing the aforementioned design requirements and emotional data to extract basic information,

[0933] A means for automatically generating multiple design proposals based on the aforementioned basic information,

[0934] A means of evaluating the generated design proposals based on construction efficiency and user sentiment,

[0935] Means for selecting appropriate components,

[0936] Means for generating and improving assembly procedures,

[0937] Means for estimating labor factors and skill levels,

[0938] A means of recommending products based on user emotions,

[0939] A system that includes this.

[0940] (Claim 2)

[0941] The system according to claim 1, further comprising means for performing a customized product recommendation process based on user sentiment information.

[0942] (Claim 3)

[0943] The system according to claim 1, comprising means for accessing a market database and selecting components with regard to efficiency and supply availability. [Explanation of Symbols]

[0944] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for inputting building design requirements, A means for analyzing the aforementioned design requirements and extracting basic data, A means for automatically generating multiple design proposals based on the aforementioned basic data, A means of evaluating the generated design proposals based on ease of construction and cost efficiency, A means of selecting the optimal components and materials, A means for generating and optimizing building assembly procedures, Means for predicting the workforce and skill levels, A system that includes this.

2. The system according to claim 1, further comprising means for generating the assembly procedures necessary for design based on the designed building using a simulation model.

3. The system according to claim 1, comprising means for accessing a market database and selecting materials and components considering cost efficiency and ease of supply.

Images