System

Abstract

A system is provided.SOLUTION: A system, comprising: means for predicting properties of a new material using a generative model; means for generating a design for the new material based on the generative model; and means for providing the generated design to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional material design struggles to minimize environmental impact while maintaining performance, and there is a lack of efficient methods for developing sustainable materials, particularly in the manufacturing and construction industries. Furthermore, designing new materials requires a trial-and-error approach, which is time-consuming and costly. Furthermore, designing materials to meet the strict standards of each industry requires advanced expertise, making automation difficult. [Means for solving the problem]

[0005] The present invention provides a system that uses a generative model to predict the properties of new materials and automatically generates design plans for new materials based on the generative model. Specifically, the system includes a means for the generative model to predict the strength, durability, sustainability, and cost properties of the material and generate design plans based on these properties. Furthermore, the system includes a means for providing the generated design plans to a user, allowing the user to efficiently design sustainable materials. This makes it possible to develop sustainable materials with a low environmental impact while reducing time and costs.

[0006] A "generative model" is an algorithm or artificial intelligence program that uses data to predict the properties of new materials.

[0007] "Materials" are substances or compounds used in manufacturing and construction that have a specific function or performance.

[0008] "Properties" are specific physical and chemical properties that describe the performance or quality of a material, such as strength, durability, sustainability, and cost.

[0009] "Blueprints" are detailed drawings or models that show the properties and structure of new materials.

[0010] A "server" is a computer system that holds generative models and generates material designs in response to user requests.

[0011] A "user" is a person or entity that requests the generation of a new material design.

[0012] "Predicting" means using a generative model to estimate future characteristics and performance in advance.

[0013] "Automatic generation" means that the system autonomously creates new blueprints without human intervention.

[0014] "Providing" means showing the generated design to the user or giving it to them in a usable form.

[0015] "Strength" is the ability of a material to withstand external forces or pressures.

[0016] "Durability" is the ability of a material to withstand use over an extended period of time.

[0017] "Sustainability" is the property of a material to minimize its environmental impact and be produced from renewable resources.

[0018] "Cost" refers to the economic costs involved in producing or acquiring a material. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] System Overview

[0041] The system of the invention uses generative models to predict the properties of new materials and provides the generated design drawings to users. This system operates using generative models stored on a server.

[0042] System Configuration

[0043] 1. Generative Model:

[0044] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[0045] 2. User Request:

[0046] A user requests a specific number of material designs from the server: the user inputs the number of designs desired and sends the request to the server.

[0047] 3. Generate Material Design:

[0048] The server generates new material designs using the generative model in response to user requests. The generated material designs are saved in list format.

[0049] 4. Providing blueprints:

[0050] The generated material design is provided to the user, who can receive the generated design and use it as needed.

[0051] Program processing

[0052] Initializing the Server

[0053] The server initializes and maintains the generative model, which contains algorithms for predicting material properties. The model randomly predicts new material properties based on data about various properties (e.g., strength, durability, etc.).

[0054] User request processing

[0055] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[0056] Material Design Generation

[0057] The server uses a generative modeling algorithm to generate the requested number of material designs, each predicting properties such as strength, durability, sustainability, and cost. The generated designs are saved in a list and later provided to the user.

[0058] Providing blueprints

[0059] The server provides the generated material designs to the user, who can review these designs and use them to help develop sustainable materials.

[0060] Specific examples

[0061] If a user requests five new material designs, the following results may be obtained:

[0062] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678

[0063] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789

[0064] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123

[0065] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890

[0066] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567

[0067] These blueprints are easily accessible to users, with detailed descriptions of each property, allowing users to select sustainable, high-performance materials.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The server initializes the generative model. The server prepares an algorithm for predicting material properties using the generative model, and instantiates and initializes the algorithm.

[0071] Step 2:

[0072] A request is made to the server for the number of material designs specified by the user. The user inputs the desired number of designs from the terminal and sends this request to the server.

[0073] Step 3:

[0074] The server receives the user's request and prepares to generate the requested number of material designs based on the received request.

[0075] Step 4:

[0076] The server generates blueprints for new materials using generative models, randomly generating values ​​for properties such as strength, durability, sustainability, and cost to create each blueprint.

[0077] Step 5:

[0078] Each generated material design is added to a list. The server saves the generated material designs in list format and prepares them for later provision to the user.

[0079] Step 6:

[0080] The server confirms that blueprint generation is complete. The server confirms that all requested material blueprints have been successfully generated.

[0081] Step 7:

[0082] The server provides the generated material design drawing to the user. The server transmits the design drawing saved in the list to the user's terminal and provides it to the user.

[0083] Step 8:

[0084] The user checks the provided blueprint. The user checks the material blueprint obtained on the terminal and evaluates each characteristic value (strength, durability, sustainability, cost, etc.).

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] In the conventional material design process, predicting the properties of new materials is extremely time-consuming and costly, making it difficult to optimize the design. This problem is particularly pronounced when multiple properties, such as strength, durability, sustainability, and cost, must be considered simultaneously. Furthermore, there has been no means to quickly and efficiently provide a specific number of material designs required by the user.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes means for predicting the properties of new materials using a generative model, means for generating design drawings of new materials based on the generative model, means for providing the generated design drawings to a user, means for the server to receive user requests and generate a specified number of material designs, and means for the server to store the generated design drawings as a list and provide it to the user. This makes it possible to quickly predict the properties of new materials and efficiently generate and provide optimal designs.

[0090] A "generative model" is a computer program that contains algorithms for predicting the properties of new materials based on user input.

[0091] "Material properties" refer to specific physical and economic characteristics of a material, such as its strength, durability, sustainability, and cost.

[0092] A "means for predicting properties" is a method or device for calculating the property values ​​of a material using a generative model.

[0093] A "means for generating a design" is a process or tool for creating a detailed design of a new material based on a generative model.

[0094] The "means for providing a blueprint" refers to a method or interface for presenting the generated material blueprint to the user.

[0095] A "server" is a networked computer system whose role is to receive requests from users, generate material designs using generative models, and provide them to users.

[0096] A "request" is an operation or communication in which a user requests a specific number of material designs from a server.

[0097] The "means for saving as a list" is a method for managing and saving the generated multiple design drawings as a data structure in a computer.

[0098] The "specific number" refers to the number of material designs to be generated that the user specifies in the request.

[0099] The present invention is a system that uses a generative model to predict the properties of new materials, generates material designs based on the predictions, and provides the design drawings to users.

[0100] The server stores the generative model, which contains algorithms for predicting the strength, durability, sustainability, and cost characteristics of materials. Generative models can be implemented using popular deep learning frameworks such as TensorFlow and PyTorch. The server loads the model's trained parameters and initializes the model for use.

[0101] A user requests a specific number of material designs from the server through a web interface or API endpoint. For example, a prompt such as "Please generate five new material designs" is an example of such a request. The server receives this request and begins the process of generating the specified number of material designs.

[0102] During the generation process, the server runs a generative model, which predicts the properties of each design (strength, durability, sustainability, cost) using algorithms that combine random numbers and statistical methods. The generated material designs are stored in a database or memory in the form of a list.

[0103] Finally, the server provides the generated blueprints to the user, who can then acquire them and use them in research, manufacturing processes, etc. The generated blueprints contain detailed data on each material's properties, allowing the user to select the optimal material.

[0104] For example, if a user requests "generate five new material designs," the server will generate and serve the following blueprint results:

[0105] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678

[0106] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789

[0107] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123

[0108] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890

[0109] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567

[0110] The resulting material design is then presented to the user in an easily viewable format, with detailed information clearly displayed for each property, allowing users to efficiently select the optimal materials and create sustainable, high-performance products.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1:

[0113] Initializing the Server

[0114] The server loads the generative model at startup and initializes it for use. Specifically, the server loads pre-trained models into memory using frameworks such as TensorFlow and PyTorch. This prepares the model to predict material properties.

[0115] Input: Pre-saved data for the generative model.

[0116] Output: An initialized generative model.

[0117] Step 2:

[0118] Accepting user requests

[0119] A user requests a specific number of material designs from the server through a web interface or an API endpoint. For example, the user might type "generate five new material designs." The server receives this request and parses it.

[0120] Input: User request (e.g. "Generate 5 new material design images").

[0121] Output: The number of material designs requested.

[0122] Step 3:

[0123] Material Design Generation

[0124] Based on the request, the server generates a specified number of material designs using a generative model that predicts material properties such as strength, durability, sustainability, and cost using a combination of random numbers and statistical methods.

[0125] Specific operation: Run the generative model and calculate the properties of each material design.

[0126] Input: The number of material designs requested.

[0127] Output: Properties of each generated material design (e.g., Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678).

[0128] Step 4:

[0129] Saving Blueprints

[0130] The server saves the generated design drawings as a list. In this step, the generated material designs are temporarily stored in a database or memory.

[0131] Specific operation: Write the generated material design to the database.

[0132] Input: Properties of each generated material design.

[0133] Output: A list of material designs stored in the database.

[0134] Step 5:

[0135] Providing blueprints

[0136] The server provides the generated material designs to the user in the form of a list, and returns the generated design drawings to the user using HTTP or API responses. The user can then retrieve these and use them in their research or manufacturing processes.

[0137] Specific operation: Generates an HTTP response and sends it to the user.

[0138] Input: A list of material designs stored in a database.

[0139] Output: A list of material designs provided to the user.

[0140] Through the above steps, the server can efficiently predict the properties of new materials, generate design drawings, and provide them to the user.

[0141] (Application example 1)

[0142] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0143] In modern manufacturing, material selection and optimization of manufacturing processes are extremely important. However, traditional methods have struggled to accurately predict material properties and quickly provide optimal material designs. This has resulted in time-consuming and costly manufacturing processes, and can lead to quality variations. Furthermore, when operators manually select material properties, there is a high risk of human error. To solve these problems, a system is needed that automates the prediction of material properties and the provision of optimal material designs, thereby optimizing manufacturing processes.

[0144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0145] In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design drawing of the new material based on the generative model, means for providing the generated design drawing to a user, means for receiving a material property request from the user, means for proposing an optimal material selection based on the generated design drawing, and means for optimizing the manufacturing process based on the proposed material design. This enables highly accurate prediction of material properties, rapid provision of an optimal material design, and automation of the entire manufacturing process. Furthermore, the user can quickly and accurately select the optimal material, improving the efficiency and quality of the manufacturing process.

[0146] A "generative model" is a system that includes algorithms that use AI technology to predict the properties of new materials and generate design drawings.

[0147] "Material properties" refer to specific characteristics such as strength, durability, sustainability, and cost, the values ​​of which are predicted by the generative model.

[0148] A "design" includes detailed drawings and information about a material created based on the material's properties predicted using a generative model.

[0149] "User" refers to a person or organization that uses the system to request a material design and selects materials based on the provided design drawings.

[0150] A "request" is a user's request to the system to generate a specific number of material designs.

[0151] "Process optimization" is a means of optimizing the manufacturing process based on the selected material design to improve efficiency and quality.

[0152] System Overview

[0153] This invention implements a system that uses generative AI models to predict the properties of new materials and provide their design blueprints. This system receives requests from users, generates optimal material designs, and supports the optimization of manufacturing processes.

[0154] System Configuration

[0155] This system is realized by the following main components:

[0156] 1. Generative Model

[0157] The server hosts generative models that predict material properties, including built-in algorithms for predicting properties such as strength, durability, sustainability, and cost.

[0158] 2. Receiving a user request

[0159] A user requests specific material properties through a factory robot or terminal, for example by entering the prompt "Produce five materials with high strength and medium durability."

[0160] 3. Generating Material Design

[0161] The server uses the generative model to generate new material designs corresponding to the user's request, and the generated material designs are saved in a list format.

[0162] 4. Providing blueprints

[0163] The generated material design is sent to factory robots and terminals and provided to users, who can use it to optimize their manufacturing processes.

[0164] 5. Process optimization

[0165] Based on the proposed material design, factory robots adjust the production line to manufacture the product using the optimal process.

[0166] Hardware and Software

[0167] Hardware

[0168] Factory robots (e.g. KUKA, ABB)

[0169] Server (cloud-based or on-premise)

[0170] User device (touch panel display, etc.)

[0171] software

[0172] Generative AI models (e.g., GPT-4)

[0173] Communication protocol (e.g. MQTT, HTTP)

[0174] User interface (robot touch panel, remote control app)

[0175] Specific Examples

[0176] For example, a factory operator operates a terminal and types the following prompt:

[0177] Produce 5 materials with high strength and medium durability.

[0178] The server receives this request and generates a new material design using the generative model. The generated design is saved in a list format as follows:

[0179] 1. Design 1: Strength 9.0, Durability 5.5, Sustainability 7.0, Cost 4.5

[0180] 2. Design 2: Strength 8.5, Durability 5.0, Sustainability 6.5, Cost 3.5

[0181] 3. Design 3: Strength 8.8, Durability 5.3, Sustainability 7.2, Cost 4.0

[0182] 4. Design 4: Strength 9.2, Durability 5.7, Sustainability 6.9, Cost 4.8

[0183] 5. Design 5: Strength 8.9, Durability 5.6, Sustainability 7.1, Cost 4.2

[0184] Factory operators review this list and select the optimal material design, after which factory robots adjust the production line based on the selected material design, optimizing the manufacturing process.

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] The user operates the terminal and inputs a material property request.

[0188] Input: Prompts the user to enter specific material properties and quantities.

[0189] Specific action: For example, enter "Produce 5 materials with high strength and medium durability."

[0190] Output: The terminal converts the input prompt text into request data to be sent to the server and sends it.

[0191] Step 2:

[0192] The server receives the user's request and generates a new material design using the generative model.

[0193] Input: The prompt text sent from the terminal.

[0194] What it does: The server uses a generative AI model (e.g., GPT-4) to predict the requested material properties based on the prompt.

[0195] Data processing / computation: Predicting material strength, durability, sustainability, cost, etc.

[0196] Output: A data list of the generated material design.

[0197] Step 3:

[0198] The server saves the generated material design in list format and transmits the list to the terminal.

[0199] Input: Generated material design data list.

[0200] Specific operation: The server formats the generated material design into a list format and sends it to the terminal.

[0201] Output: Material design list sent to user terminal.

[0202] Step 4:

[0203] The terminal displays the generated material design list to the user.

[0204] Input: Material design list sent from the server.

[0205] Specific operation: The device displays the received material design list on the screen so that the user can check it.

[0206] Output: A material design list that can be visually verified by the user.

[0207] Step 5:

[0208] The user selects the optimal material design from the list and instructs the optimization of the manufacturing process.

[0209] Input: Material Design list displayed on the screen.

[0210] Specific operation: The user selects the optimal material design from the list and instructs the optimization of the manufacturing process via the terminal.

[0211] Output: Information on optimal material design selection and instruction data for manufacturing process optimization.

[0212] Step 6:

[0213] The server receives the instruction data and notifies the factory robots to optimize the manufacturing process.

[0214] Input: Material design selection information and manufacturing process optimization instruction data sent from the user terminal.

[0215] Specific operation: The server analyzes the received data and sends instructions to the factory robots to adjust the manufacturing process appropriately.

[0216] Output: Instruction data for factory robots to optimize the manufacturing process.

[0217] Step 7:

[0218] Factory robots manufacture products based on optimized manufacturing processes.

[0219] Input: Instruction data for optimizing the manufacturing process sent from the server.

[0220] Specific operation: Factory robots adjust the production line based on instruction data and manufacture products using the optimal process.

[0221] Output: A product from an optimized manufacturing process.

[0222] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0223] System Overview

[0224] The system of the invention uses generative models to predict the properties of new materials and provides the generated design to the user. The system also incorporates an emotion engine that recognizes the user's emotions and can adjust the material design based on the user's emotions.

[0225] System Configuration

[0226] 1. Generative Model:

[0227] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[0228] 2. Emotion Engine:

[0229] The server has an emotion engine that recognizes the user's emotions. This emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[0230] 3. User Request:

[0231] A user requests a specific number of material designs from the server by entering the number of designs desired and sending the request to the server.

[0232] 4. Generate Material Design:

[0233] The server generates new material designs using the generative model in response to user requests, and adjusts the designs based on the user's emotions. The generated material designs are saved in a list format.

[0234] 5. Provision of blueprints:

[0235] The generated material design is provided to the user, who can receive the generated design and evaluate the design based on the information provided by the emotion engine, if necessary.

[0236] Program processing

[0237] Initializing the Server

[0238] The server initializes the generative model and the emotion engine at the same time. The generative model has a built-in algorithm for predicting material properties, and the emotion engine has the ability to analyze voice and facial expression data.

[0239] User request processing

[0240] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[0241] emotion recognition

[0242] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's voice data and facial expression data to identify the user's emotional state. This emotional information is reflected in the generation of material design.

[0243] Material Design Generation

[0244] The server uses a generative model algorithm to generate the requested number of material designs. Each design predicts properties such as strength, durability, sustainability, and cost. Furthermore, the design is adjusted based on the user's emotional information obtained from the emotion engine. The generated designs are saved in a list and later provided to the user.

[0245] Providing blueprints

[0246] The server provides the generated material designs to the user, who can then review these designs and evaluate and select designs based on the emotional information provided by the emotion engine.

[0247] Specific examples

[0248] If a user requests five new material designs and the emotion engine recognizes the user's emotional state as "Satisfied," the following results may occur:

[0249] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678, Adjusted based on user emotion "Satisfaction"

[0250] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789, Adjustment based on user emotion "Satisfaction"

[0251] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123, Adjustment based on user emotion "Satisfaction"

[0252] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890, Adjustment based on user emotion "Satisfaction"

[0253] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567, Adjustment based on user emotion "Satisfaction"

[0254] These blueprints are easily accessible to users, with detailed descriptions of each property. Users can use these blueprints to select sustainable, high-performance materials. The emotional engine adjusts the design to provide optimal results, taking into account the user's emotional state.

[0255] The processing flow will be explained below.

[0256] Step 1:

[0257] The server initializes the generative model and emotion engine. The generative model contains algorithms that predict material properties such as strength, durability, sustainability, and cost. The emotion engine has the ability to recognize emotions by analyzing the user's voice and facial expression data.

[0258] Step 2:

[0259] The user requests a specific number of material designs from the server. The user inputs the desired number of material designs from the terminal and sends this request to the server.

[0260] Step 3:

[0261] The server receives the user's request and prepares to generate the requested number of material designs based on the received request.

[0262] Step 4:

[0263] The server activates an emotion engine to recognize the user's emotions. The user sends voice data and facial expression data to the server via their device. The server analyzes this data and identifies the user's emotions.

[0264] Step 5:

[0265] The server adjusts the material design based on the user's emotions. For example, if the user expresses "satisfied" emotion, the server will optimize the design based on the user's positive feedback.

[0266] Step 6:

[0267] The server uses generative models to generate material designs. Each design randomly predicts properties such as strength, durability, sustainability, and cost. The results of the emotion engine are also taken into account, and appropriate adjustments are made.

[0268] Step 7:

[0269] The server adds each generated material design to a list. The list will keep as many generated designs as requested.

[0270] Step 8:

[0271] The server confirms that blueprint generation is complete and that all requested material designs have been successfully generated.

[0272] Step 9:

[0273] The server provides the generated material blueprints to the user, each in a format that is easy for the user to understand.

[0274] Step 10:

[0275] The user checks the provided blueprint. The user can use their device to check the material blueprint obtained and evaluate each characteristic value (strength, durability, sustainability, cost, etc.). The results of the emotion engine are also displayed, allowing the user to see feedback based on their emotions.

[0276] Example 2

[0277] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0278] Conventional material design systems only predict material properties without considering user emotions when making design adjustments. As a result, they are unable to provide optimal material designs that reflect the user's emotions and needs, resulting in a lack of improvement in the user experience.

[0279] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design plan for the new material based on the generative model, means for analyzing a user's emotions using emotion recognition technology, means for adjusting the material design based on the analysis results, and means for providing the generated design plan to the user. This enables optimal material design that reflects the user's emotions.

[0280] A "generative model" is a set of algorithms or functions used to predict the properties of a material.

[0281] "Properties" are specific attributes or parameters related to the performance of a material, including its strength, durability, sustainability, and cost.

[0282] A "design" is a drawing or diagram that visually represents the material properties predicted and adjusted by the generative model.

[0283] "Emotion recognition technology" is a technology that analyzes voice data and facial expression data to identify a user's emotional state.

[0284] The "analysis results" are user emotional information obtained using emotion recognition technology, and are information that is reflected in material design.

[0285] "Tuning" is the process of changing or modifying the properties of a material design based on analytical results.

[0286] System Overview

[0287] The system of the present invention uses generative AI models to predict the properties of new materials and provides the generated design drawings to the user. The system incorporates an emotion engine that recognizes the user's emotions and can adjust the material design based on the user's emotions.

[0288] System Configuration

[0289] The system consists of the following main components:

[0290] 1. Generative Model:

[0291] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[0292] 2. Emotion Engine:

[0293] The server has an emotion engine that recognizes the user's emotions. This emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[0294] 3. User Request:

[0295] A user requests a specific number of material designs from the server by entering the number of designs desired and sending the request to the server.

[0296] 4. Generate Material Design:

[0297] The server generates new material designs using the generative model in response to user requests, and adjusts the designs based on the user's emotions. The generated material designs are saved in a list format.

[0298] 5. Provision of blueprints:

[0299] The generated material design is provided to the user, who can receive the generated design and evaluate the design based on the information provided by the emotion engine, if necessary.

[0300] Hardware and software used

[0301] Hardware: GPU accelerator, microphone, camera, etc.

[0302] Software: Emotion recognition libraries such as DeepFace, OpenSmile, etc.

[0303] Program processing overview

[0304] 1. Initialize the server:

[0305] The server initializes the generative model and emotion engine. The generative model has built-in algorithms for predicting material properties, and the emotion engine has the ability to analyze voice and facial expression data.

[0306] 2. User request processing:

[0307] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[0308] 3. Emotion recognition:

[0309] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's voice data and facial expression data to identify the user's emotional state. This emotional information is reflected in the generation of material design.

[0310] 4. Generate Material Design:

[0311] The server uses a generative model algorithm to generate the requested number of material designs. Each design predicts properties such as strength, durability, sustainability, and cost. Furthermore, the design is adjusted based on the user's emotional information obtained from the emotion engine. The generated designs are saved in a list and later provided to the user.

[0312] 5. Provision of blueprints:

[0313] The server provides the generated material designs to the user, who can then review these designs and evaluate and select designs based on the emotional information provided by the emotion engine.

[0314] Specific examples

[0315] The following concrete example shows a scenario in which a user requests five new material designs and the emotion engine recognizes the user's emotional state as "Satisfied."

[0316] Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678, adjusted based on user emotion "Satisfaction"

[0317] Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789, adjusted based on user emotion "Satisfaction"

[0318] Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123, adjusted based on user emotion "Satisfaction"

[0319] Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890, adjusted based on user emotion "Satisfaction"

[0320] Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567, adjusted based on user emotion "Satisfaction"

[0321] Prompt Sentence Examples

[0322] "Please describe a system that uses an emotion engine to recognize user emotions and generate new material designs. Include a concrete scenario."

[0323] As described above, this system aims to provide a blueprint for new materials that take user emotions into account by utilizing generative AI models and emotion recognition technology. The detailed operating procedures and instructions, including the hardware and software used, will be helpful for implementing and practicing the system.

[0324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0325] Step 1: Initialize the server

[0326] The server initializes the generative model and emotion engine when the system starts up. The generative model has built-in algorithms that predict material properties (strength, durability, sustainability, cost). The emotion engine has the ability to analyze voice data and facial expression data. Specifically, the server loads the generative model into memory, starts the emotion engine, and checks the connection status with the microphone and camera. The input is the initial setting data for the generative model and emotion engine, and the output is the initialized model and engine.

[0327] Step 2: Processing the User Request

[0328] A user uses a terminal to request a specific number of material designs from the server. For example, the user enters "Please generate five material designs" into the terminal. The terminal sends this request to the server. The input is the user's request, and the output is the request data sent to the server. The server stores the received request as a log.

[0329] Step 3: Emotion Recognition

[0330] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the voice and facial expression data obtained from the user to identify the user's emotional state. For example, the device's microphone records the user's voice and the camera captures their facial expressions. The server inputs this data into the emotion engine and obtains the analysis results. The input is the user's voice data and facial expression data, and the output is the user's emotional state (e.g., "satisfied").

[0331] Step 4: Generate Material Design

[0332] The server uses a generative model algorithm to generate new material designs. It generates multiple designs based on the number of user requests and predicts the characteristics of each design (strength, durability, sustainability, cost). It also adjusts the design based on the user's emotional information obtained from the emotion engine. For example, if the user's emotional state is "satisfied," it will adjust the design accordingly. The input is the number of user requests and emotional information, and the output is a list of generated material designs.

[0333] Step 5: Provide the blueprint

[0334] The server provides the generated material design to the user. The design drawings are saved in list format and sent to the user's device. The user checks the design drawings on the device and evaluates and selects based on the emotional information provided by the emotion engine. The input is the generated material design list, and the output is the provision of the design drawings to the user. Specific operations include the user downloading the design drawings on their device and displaying detailed information.

[0335] Through these steps, the system can provide a blueprint for new materials that take into account the user's emotions.

[0336] (Application example 2)

[0337] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0338] Conventional material design systems have difficulty in considering user feedback based on their emotions. Furthermore, there is no way to provide the results of material design in real time, which hinders efficient work. Therefore, there is a need for a system that can improve user satisfaction and work efficiency in material design.

[0339] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0340] In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design plan for the new material based on the generative model, means for detecting a user's emotion using an emotion engine that recognizes emotions based on the user's voice and facial expression, means for adjusting the material design based on the detected emotion, and means for providing the generated design plan to the user in real time via a smart device. This makes it possible to quickly provide an optimal material design that corresponds to the user's emotion, significantly improving work efficiency and satisfaction.

[0341] A "generative model" is a mathematical model that predicts the properties of materials and generates designs for new materials based on that information.

[0342] "Properties" are the physical and economic attributes of a material, such as strength, durability, sustainability, and cost.

[0343] A "blueprint" is a drawing or diagram that visually shows the composition and manufacturing method of a new material.

[0344] An "emotion engine" is a technology that analyzes a user's voice and facial expressions and recognizes the user's emotions based on the results.

[0345] "Detection" is the act of using an emotion engine to understand and identify a user's emotion.

[0346] "Tuning" is the process of modifying and optimizing material design parameters based on detected user emotions.

[0347] A "smart device" is an advanced device that is equipped with internet and communication functions and can interactively exchange information with users.

[0348] "Real-time" refers to a method of time management that minimizes delays and provides updated and immediate information and data.

[0349] A "user" is someone who uses a system or device to obtain and evaluate information about new material designs.

[0350] MODE FOR CARRYING OUT THE INVENTION

[0351] To implement the present invention, the following system configuration and procedures are required.

[0352] System Configuration

[0353] 1. Server:

[0354] The server maintains a generative model and an emotion engine. The generative model contains algorithms for predicting the properties of the generated new material. The emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[0355] 2. Smart Devices:

[0356] Smart glasses and other interactive devices are used, which are equipped with cameras and microphones to capture the user's facial expressions and voice in real time, and the captured data is sent to a server.

[0357] Data processing and calculation

[0358] 1. Facial and Emotion Recognition:

[0359] The camera on the smart device captures the user's facial expressions, and OpenCV is used to detect specific facial features (eyes, mouth, eyebrows, etc.). The detected facial data is input into a facial emotion model built with Keras and analyzed by the emotion engine. Audio data captured by the microphone is also input into the emotion engine.

[0360] 2. Prediction of material properties:

[0361] The user's emotional information obtained by the emotion engine is sent to the server and input into the generative model algorithm, which then generates a blueprint for a new material, taking into account the material's strength, durability, sustainability, cost, and other characteristics along with the emotional information.

[0362] 3. View blueprints:

[0363] The generated blueprints are displayed in real time on the smart device screen, allowing users to select the optimal material design based on this information.

[0364] Specific examples

[0365] For example, if a user wants to design a new lightweight, strong material, and the smart glasses detect the emotion of "excitement" from the user's facial expression, the generated material design will be based on the emotion and will be lightweight and strong.

[0366] Example prompt sentence:

[0367] Based on the user's desired design, generate a material design that corresponds to the user's emotion of "excitement."

[0368] This invention makes it possible to quickly provide an optimal material design that corresponds to the user's emotions, thereby significantly improving work efficiency and satisfaction.

[0369] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0370] Step 1:

[0371] A smart device (such as smart glasses) is worn by a user and uses a camera and microphone to capture the user's facial expressions and voice data, which serve as input data for recognizing the user's emotions.

[0372] Step 2:

[0373] The smart device sends the captured facial expression data to the server, which uses a facial recognition algorithm (OpenCV) to detect specific facial features (eyes, mouth, eyebrows, etc.) and inputs this data into the emotion engine.

[0374] Step 3:

[0375] The server's emotion engine analyzes the facial recognition data and voice data to identify the user's emotions. This process uses an emotion recognition model using Keras. The analysis results in the user's emotions (e.g., "excitement" or "satisfaction").

[0376] Step 4:

[0377] The server inputs the identified user's emotional information into a generative model to predict the properties (strength, durability, sustainability, cost, etc.) of the new material. The generative model adjusts the material properties based on the emotional information to generate an optimal design.

[0378] Step 5:

[0379] The server stores a list of blueprints of new materials generated by the generative model, including predicted properties and adjustments based on emotional information.

[0380] Step 6:

[0381] The server sends the generated blueprint to the smart device, where the blueprint information is displayed in real time on the smart device's display. The user can check this information and proceed with the work as appropriate.

[0382] As a specific example of operation, if a user requests a new lightweight, strong material and the smart glasses detect the emotion of "excitement," the server will generate a lightweight, strong material design in response to the "excitement" and display the design on the smart glasses' display.

[0383] Through this series of processes, the optimal material design based on the user's feelings is quickly provided, which significantly improves work efficiency and user satisfaction.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0385] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0387] [Second embodiment]

[0388] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0389] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0390] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0392] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0394] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0395] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0396] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0399] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0400] System Overview

[0401] The system of the invention uses generative models to predict the properties of new materials and provides the generated design drawings to users. This system operates using generative models stored on a server.

[0402] System Configuration

[0403] 1. Generative Model:

[0404] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[0405] 2. User Request:

[0406] A user requests a specific number of material designs from the server: the user inputs the number of designs desired and sends the request to the server.

[0407] 3. Generate Material Design:

[0408] The server generates new material designs using the generative model in response to user requests. The generated material designs are saved in list format.

[0409] 4. Providing blueprints:

[0410] The generated material design is provided to the user, who can receive the generated design and use it as needed.

[0411] Program processing

[0412] Initializing the Server

[0413] The server initializes and maintains the generative model, which contains algorithms for predicting material properties. The model randomly predicts new material properties based on data about various properties (e.g., strength, durability, etc.).

[0414] User request processing

[0415] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[0416] Material Design Generation

[0417] The server uses a generative modeling algorithm to generate the requested number of material designs, each predicting properties such as strength, durability, sustainability, and cost. The generated designs are saved in a list and later provided to the user.

[0418] Providing blueprints

[0419] The server provides the generated material designs to the user, who can review these designs and use them to help develop sustainable materials.

[0420] Specific examples

[0421] If a user requests five new material designs, the following results may be obtained:

[0422] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678

[0423] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789

[0424] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123

[0425] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890

[0426] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567

[0427] These blueprints are easily accessible to users, with detailed descriptions of each property, allowing users to select sustainable, high-performance materials.

[0428] The processing flow will be explained below.

[0429] Step 1:

[0430] The server initializes the generative model. The server prepares an algorithm for predicting material properties using the generative model, and instantiates and initializes the algorithm.

[0431] Step 2:

[0432] A request is made to the server for the number of material designs specified by the user. The user inputs the desired number of designs from the terminal and sends this request to the server.

[0433] Step 3:

[0434] The server receives the user's request and prepares to generate the requested number of material designs based on the received request.

[0435] Step 4:

[0436] The server generates blueprints for new materials using generative models, randomly generating values ​​for properties such as strength, durability, sustainability, and cost to create each blueprint.

[0437] Step 5:

[0438] Each generated material design is added to a list. The server saves the generated material designs in list format and prepares them for later provision to the user.

[0439] Step 6:

[0440] The server confirms that blueprint generation is complete. The server confirms that all requested material blueprints have been successfully generated.

[0441] Step 7:

[0442] The server provides the generated material design drawing to the user. The server transmits the design drawing saved in the list to the user's terminal and provides it to the user.

[0443] Step 8:

[0444] The user checks the provided blueprint. The user checks the material blueprint obtained on the terminal and evaluates each characteristic value (strength, durability, sustainability, cost, etc.).

[0445] Example 1

[0446] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0447] In the conventional material design process, predicting the properties of new materials is extremely time-consuming and costly, making it difficult to optimize the design. This problem is particularly pronounced when multiple properties, such as strength, durability, sustainability, and cost, must be considered simultaneously. Furthermore, there has been no means to quickly and efficiently provide a specific number of material designs required by the user.

[0448] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0449] In this invention, the server includes means for predicting the properties of new materials using a generative model, means for generating design drawings of new materials based on the generative model, means for providing the generated design drawings to a user, means for the server to receive user requests and generate a specified number of material designs, and means for the server to store the generated design drawings as a list and provide it to the user. This makes it possible to quickly predict the properties of new materials and efficiently generate and provide optimal designs.

[0450] A "generative model" is a computer program that contains algorithms for predicting the properties of new materials based on user input.

[0451] "Material properties" refer to specific physical and economic characteristics of a material, such as its strength, durability, sustainability, and cost.

[0452] A "means for predicting properties" is a method or device for calculating the property values ​​of a material using a generative model.

[0453] A "means for generating a design" is a process or tool for creating a detailed design of a new material based on a generative model.

[0454] The "means for providing a blueprint" refers to a method or interface for presenting the generated material blueprint to the user.

[0455] A "server" is a networked computer system whose role is to receive requests from users, generate material designs using generative models, and provide them to users.

[0456] A "request" is an operation or communication in which a user requests a specific number of material designs from a server.

[0457] The "means for saving as a list" is a method for managing and saving the generated multiple design drawings as a data structure in a computer.

[0458] The "specific number" refers to the number of material designs to be generated that the user specifies in the request.

[0459] The present invention is a system that uses a generative model to predict the properties of new materials, generates material designs based on the predictions, and provides the design drawings to users.

[0460] The server stores the generative model, which contains algorithms for predicting the strength, durability, sustainability, and cost characteristics of materials. Generative models can be implemented using popular deep learning frameworks such as TensorFlow and PyTorch. The server loads the model's trained parameters and initializes the model for use.

[0461] A user requests a specific number of material designs from the server through a web interface or API endpoint. For example, a prompt such as "Please generate five new material designs" is an example of such a request. The server receives this request and begins the process of generating the specified number of material designs.

[0462] During the generation process, the server runs a generative model, which predicts the properties of each design (strength, durability, sustainability, cost) using algorithms that combine random numbers and statistical methods. The generated material designs are stored in a database or memory in the form of a list.

[0463] Finally, the server provides the generated blueprints to the user, who can then acquire them and use them in research, manufacturing processes, etc. The generated blueprints contain detailed data on each material's properties, allowing the user to select the optimal material.

[0464] For example, if a user requests "generate five new material designs," the server will generate and serve the following blueprint results:

[0465] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678

[0466] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789

[0467] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123

[0468] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890

[0469] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567

[0470] The resulting material design is then presented to the user in an easily viewable format, with detailed information clearly displayed for each property, allowing users to efficiently select the optimal materials and create sustainable, high-performance products.

[0471] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0472] Step 1:

[0473] Initializing the Server

[0474] The server loads the generative model at startup and initializes it for use. Specifically, the server loads pre-trained models into memory using frameworks such as TensorFlow and PyTorch. This prepares the model to predict material properties.

[0475] Input: Pre-saved data for the generative model.

[0476] Output: An initialized generative model.

[0477] Step 2:

[0478] Accepting user requests

[0479] A user requests a specific number of material designs from the server through a web interface or an API endpoint. For example, the user might type "generate five new material designs." The server receives this request and parses it.

[0480] Input: User request (e.g. "Generate 5 new material design images").

[0481] Output: The number of material designs requested.

[0482] Step 3:

[0483] Material Design Generation

[0484] Based on the request, the server generates a specified number of material designs using a generative model that predicts material properties such as strength, durability, sustainability, and cost using a combination of random numbers and statistical methods.

[0485] Specific operation: Run the generative model and calculate the properties of each material design.

[0486] Input: The number of material designs requested.

[0487] Output: Properties of each generated material design (e.g., Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678).

[0488] Step 4:

[0489] Saving Blueprints

[0490] The server saves the generated design drawings as a list. In this step, the generated material designs are temporarily stored in a database or memory.

[0491] Specific operation: Write the generated material design to the database.

[0492] Input: Properties of each generated material design.

[0493] Output: A list of material designs stored in the database.

[0494] Step 5:

[0495] Providing blueprints

[0496] The server provides the generated material designs to the user in the form of a list, and returns the generated design drawings to the user using HTTP or API responses. The user can then retrieve these and use them in their research or manufacturing processes.

[0497] Specific operation: Generates an HTTP response and sends it to the user.

[0498] Input: A list of material designs stored in a database.

[0499] Output: A list of material designs provided to the user.

[0500] Through the above steps, the server can efficiently predict the properties of new materials, generate design drawings, and provide them to the user.

[0501] (Application example 1)

[0502] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0503] In modern manufacturing, material selection and optimization of manufacturing processes are extremely important. However, traditional methods have struggled to accurately predict material properties and quickly provide optimal material designs. This has resulted in time-consuming and costly manufacturing processes, and can lead to quality variations. Furthermore, when operators manually select material properties, there is a high risk of human error. To solve these problems, a system is needed that automates the prediction of material properties and the provision of optimal material designs, thereby optimizing manufacturing processes.

[0504] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0505] In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design drawing of the new material based on the generative model, means for providing the generated design drawing to a user, means for receiving a material property request from the user, means for proposing an optimal material selection based on the generated design drawing, and means for optimizing the manufacturing process based on the proposed material design. This enables highly accurate prediction of material properties, rapid provision of an optimal material design, and automation of the entire manufacturing process. Furthermore, the user can quickly and accurately select the optimal material, improving the efficiency and quality of the manufacturing process.

[0506] A "generative model" is a system that includes algorithms that use AI technology to predict the properties of new materials and generate design drawings.

[0507] "Material properties" refer to specific characteristics such as strength, durability, sustainability, and cost, the values ​​of which are predicted by the generative model.

[0508] A "design" includes detailed drawings and information about a material created based on the material's properties predicted using a generative model.

[0509] "User" refers to a person or organization that uses the system to request a material design and selects materials based on the provided design drawings.

[0510] A "request" is a user's request to the system to generate a specific number of material designs.

[0511] "Process optimization" is a means of optimizing the manufacturing process based on the selected material design to improve efficiency and quality.

[0512] System Overview

[0513] This invention implements a system that uses generative AI models to predict the properties of new materials and provide their design blueprints. This system receives requests from users, generates optimal material designs, and supports the optimization of manufacturing processes.

[0514] System Configuration

[0515] This system is realized by the following main components:

[0516] 1. Generative Model

[0517] The server hosts generative models that predict material properties, including built-in algorithms for predicting properties such as strength, durability, sustainability, and cost.

[0518] 2. Receiving a user request

[0519] A user requests specific material properties through a factory robot or terminal, for example by entering the prompt "Produce five materials with high strength and medium durability."

[0520] 3. Generating Material Design

[0521] The server uses the generative model to generate new material designs corresponding to the user's request, and the generated material designs are saved in a list format.

[0522] 4. Providing blueprints

[0523] The generated material design is sent to factory robots and terminals and provided to users, who can use it to optimize their manufacturing processes.

[0524] 5. Process optimization

[0525] Based on the proposed material design, factory robots adjust the production line to manufacture the product using the optimal process.

[0526] Hardware and Software

[0527] Hardware

[0528] Factory robots (e.g. KUKA, ABB)

[0529] Server (cloud-based or on-premise)

[0530] User device (touch panel display, etc.)

[0531] software

[0532] Generative AI models (e.g., GPT-4)

[0533] Communication protocol (e.g. MQTT, HTTP)

[0534] User interface (robot touch panel, remote control app)

[0535] Specific Examples

[0536] For example, a factory operator operates a terminal and types the following prompt:

[0537] Produce 5 materials with high strength and medium durability.

[0538] The server receives this request and generates a new material design using the generative model. The generated design is saved in a list format as follows:

[0539] 1. Design 1: Strength 9.0, Durability 5.5, Sustainability 7.0, Cost 4.5

[0540] 2. Design 2: Strength 8.5, Durability 5.0, Sustainability 6.5, Cost 3.5

[0541] 3. Design 3: Strength 8.8, Durability 5.3, Sustainability 7.2, Cost 4.0

[0542] 4. Design 4: Strength 9.2, Durability 5.7, Sustainability 6.9, Cost 4.8

[0543] 5. Design 5: Strength 8.9, Durability 5.6, Sustainability 7.1, Cost 4.2

[0544] Factory operators review this list and select the optimal material design, after which factory robots adjust the production line based on the selected material design, optimizing the manufacturing process.

[0545] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0546] Step 1:

[0547] The user operates the terminal and inputs a material property request.

[0548] Input: Prompts the user to enter specific material properties and quantities.

[0549] Specific action: For example, enter "Produce 5 materials with high strength and medium durability."

[0550] Output: The terminal converts the input prompt text into request data to be sent to the server and sends it.

[0551] Step 2:

[0552] The server receives the user's request and generates a new material design using the generative model.

[0553] Input: The prompt text sent from the terminal.

[0554] What it does: The server uses a generative AI model (e.g., GPT-4) to predict the requested material properties based on the prompt.

[0555] Data processing / computation: Predicting material strength, durability, sustainability, cost, etc.

[0556] Output: A data list of the generated material design.

[0557] Step 3:

[0558] The server saves the generated material design in list format and transmits the list to the terminal.

[0559] Input: Generated material design data list.

[0560] Specific operation: The server formats the generated material design into a list format and sends it to the terminal.

[0561] Output: Material design list sent to user terminal.

[0562] Step 4:

[0563] The terminal displays the generated material design list to the user.

[0564] Input: Material design list sent from the server.

[0565] Specific operation: The device displays the received material design list on the screen so that the user can check it.

[0566] Output: A material design list that can be visually verified by the user.

[0567] Step 5:

[0568] The user selects the optimal material design from the list and instructs the optimization of the manufacturing process.

[0569] Input: Material Design list displayed on the screen.

[0570] Specific operation: The user selects the optimal material design from the list and instructs the optimization of the manufacturing process via the terminal.

[0571] Output: Information on optimal material design selection and instruction data for manufacturing process optimization.

[0572] Step 6:

[0573] The server receives the instruction data and notifies the factory robots to optimize the manufacturing process.

[0574] Input: Material design selection information and manufacturing process optimization instruction data sent from the user terminal.

[0575] Specific operation: The server analyzes the received data and sends instructions to the factory robots to adjust the manufacturing process appropriately.

[0576] Output: Instruction data for factory robots to optimize the manufacturing process.

[0577] Step 7:

[0578] Factory robots manufacture products based on optimized manufacturing processes.

[0579] Input: Instruction data for optimizing the manufacturing process sent from the server.

[0580] Specific operation: Factory robots adjust the production line based on instruction data and manufacture products using the optimal process.

[0581] Output: A product from an optimized manufacturing process.

[0582] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0583] System Overview

[0584] The system of the invention uses generative models to predict the properties of new materials and provides the generated design to the user. The system also incorporates an emotion engine that recognizes the user's emotions and can adjust the material design based on the user's emotions.

[0585] System Configuration

[0586] 1. Generative Model:

[0587] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[0588] 2. Emotion Engine:

[0589] The server has an emotion engine that recognizes the user's emotions. This emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[0590] 3. User Request:

[0591] A user requests a specific number of material designs from the server by entering the number of designs desired and sending the request to the server.

[0592] 4. Generate Material Design:

[0593] The server generates new material designs using the generative model in response to user requests, and adjusts the designs based on the user's emotions. The generated material designs are saved in a list format.

[0594] 5. Provision of blueprints:

[0595] The generated material design is provided to the user, who can receive the generated design and evaluate the design based on the information provided by the emotion engine, if necessary.

[0596] Program processing

[0597] Initializing the Server

[0598] The server initializes the generative model and the emotion engine at the same time. The generative model has a built-in algorithm for predicting material properties, and the emotion engine has the ability to analyze voice and facial expression data.

[0599] User request processing

[0600] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[0601] emotion recognition

[0602] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's voice data and facial expression data to identify the user's emotional state. This emotional information is reflected in the generation of material design.

[0603] Material Design Generation

[0604] The server uses a generative model algorithm to generate the requested number of material designs. Each design predicts properties such as strength, durability, sustainability, and cost. Furthermore, the design is adjusted based on the user's emotional information obtained from the emotion engine. The generated designs are saved in a list and later provided to the user.

[0605] Providing blueprints

[0606] The server provides the generated material designs to the user, who can then review these designs and evaluate and select designs based on the emotional information provided by the emotion engine.

[0607] Specific examples

[0608] If a user requests five new material designs and the emotion engine recognizes the user's emotional state as "Satisfied," the following results may occur:

[0609] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678, Adjusted based on user emotion "Satisfaction"

[0610] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789, Adjustment based on user emotion "Satisfaction"

[0611] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123, Adjustment based on user emotion "Satisfaction"

[0612] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890, Adjustment based on user emotion "Satisfaction"

[0613] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567, Adjustment based on user emotion "Satisfaction"

[0614] These blueprints are easily accessible to users, with detailed descriptions of each property. Users can use these blueprints to select sustainable, high-performance materials. The emotional engine adjusts the design to provide optimal results, taking into account the user's emotional state.

[0615] The processing flow will be explained below.

[0616] Step 1:

[0617] The server initializes the generative model and emotion engine. The generative model contains algorithms that predict material properties such as strength, durability, sustainability, and cost. The emotion engine has the ability to recognize emotions by analyzing the user's voice and facial expression data.

[0618] Step 2:

[0619] The user requests a specific number of material designs from the server. The user inputs the desired number of material designs from the terminal and sends this request to the server.

[0620] Step 3:

[0621] The server receives the user's request and prepares to generate the requested number of material designs based on the received request.

[0622] Step 4:

[0623] The server activates an emotion engine to recognize the user's emotions. The user sends voice data and facial expression data to the server via their device. The server analyzes this data and identifies the user's emotions.

[0624] Step 5:

[0625] The server adjusts the material design based on the user's emotions. For example, if the user expresses "satisfied" emotion, the server will optimize the design based on the user's positive feedback.

[0626] Step 6:

[0627] The server uses generative models to generate material designs. Each design randomly predicts properties such as strength, durability, sustainability, and cost. The results of the emotion engine are also taken into account, and appropriate adjustments are made.

[0628] Step 7:

[0629] The server adds each generated material design to a list. The list will keep as many generated designs as requested.

[0630] Step 8:

[0631] The server confirms that blueprint generation is complete and that all requested material designs have been successfully generated.

[0632] Step 9:

[0633] The server provides the generated material blueprints to the user, each in a format that is easy for the user to understand.

[0634] Step 10:

[0635] The user checks the provided blueprint. The user can use their device to check the material blueprint obtained and evaluate each characteristic value (strength, durability, sustainability, cost, etc.). The results of the emotion engine are also displayed, allowing the user to see feedback based on their emotions.

[0636] Example 2

[0637] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0638] Conventional material design systems only predict material properties without considering user emotions when making design adjustments. As a result, they are unable to provide optimal material designs that reflect the user's emotions and needs, resulting in a lack of improvement in the user experience.

[0639] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design plan for the new material based on the generative model, means for analyzing a user's emotions using emotion recognition technology, means for adjusting the material design based on the analysis results, and means for providing the generated design plan to the user. This enables optimal material design that reflects the user's emotions.

[0640] A "generative model" is a set of algorithms or functions used to predict the properties of a material.

[0641] "Properties" are specific attributes or parameters related to the performance of a material, including its strength, durability, sustainability, and cost.

[0642] A "design" is a drawing or diagram that visually represents the material properties predicted and adjusted by the generative model.

[0643] "Emotion recognition technology" is a technology that analyzes voice data and facial expression data to identify a user's emotional state.

[0644] The "analysis results" are user emotional information obtained using emotion recognition technology, and are information that is reflected in material design.

[0645] "Tuning" is the process of changing or modifying the properties of a material design based on analytical results.

[0646] System Overview

[0647] The system of the present invention uses generative AI models to predict the properties of new materials and provides the generated design drawings to the user. The system incorporates an emotion engine that recognizes the user's emotions and can adjust the material design based on the user's emotions.

[0648] System Configuration

[0649] The system consists of the following main components:

[0650] 1. Generative Model:

[0651] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[0652] 2. Emotion Engine:

[0653] The server has an emotion engine that recognizes the user's emotions. This emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[0654] 3. User Request:

[0655] A user requests a specific number of material designs from the server by entering the number of designs desired and sending the request to the server.

[0656] 4. Generate Material Design:

[0657] The server generates new material designs using the generative model in response to user requests, and adjusts the designs based on the user's emotions. The generated material designs are saved in a list format.

[0658] 5. Provision of blueprints:

[0659] The generated material design is provided to the user, who can receive the generated design and evaluate the design based on the information provided by the emotion engine, if necessary.

[0660] Hardware and software used

[0661] Hardware: GPU accelerator, microphone, camera, etc.

[0662] Software: Emotion recognition libraries such as DeepFace, OpenSmile, etc.

[0663] Program processing overview

[0664] 1. Initialize the server:

[0665] The server initializes the generative model and emotion engine. The generative model has built-in algorithms for predicting material properties, and the emotion engine has the ability to analyze voice and facial expression data.

[0666] 2. User request processing:

[0667] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[0668] 3. Emotion recognition:

[0669] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's voice data and facial expression data to identify the user's emotional state. This emotional information is reflected in the generation of material design.

[0670] 4. Generate Material Design:

[0671] The server uses a generative model algorithm to generate the requested number of material designs. Each design predicts properties such as strength, durability, sustainability, and cost. Furthermore, the design is adjusted based on the user's emotional information obtained from the emotion engine. The generated designs are saved in a list and later provided to the user.

[0672] 5. Provision of blueprints:

[0673] The server provides the generated material designs to the user, who can then review these designs and evaluate and select designs based on the emotional information provided by the emotion engine.

[0674] Specific examples

[0675] The following concrete example shows a scenario in which a user requests five new material designs and the emotion engine recognizes the user's emotional state as "Satisfied."

[0676] Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678, adjusted based on user emotion "Satisfaction"

[0677] Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789, adjusted based on user emotion "Satisfaction"

[0678] Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123, adjusted based on user emotion "Satisfaction"

[0679] Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890, adjusted based on user emotion "Satisfaction"

[0680] Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567, adjusted based on user emotion "Satisfaction"

[0681] Prompt Sentence Examples

[0682] "Please describe a system that uses an emotion engine to recognize user emotions and generate new material designs. Include a concrete scenario."

[0683] As described above, this system aims to provide a blueprint for new materials that take user emotions into account by utilizing generative AI models and emotion recognition technology. The detailed operating procedures and instructions, including the hardware and software used, will be helpful for implementing and practicing the system.

[0684] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0685] Step 1: Initialize the server

[0686] The server initializes the generative model and emotion engine when the system starts up. The generative model has built-in algorithms that predict material properties (strength, durability, sustainability, cost). The emotion engine has the ability to analyze voice data and facial expression data. Specifically, the server loads the generative model into memory, starts the emotion engine, and checks the connection status with the microphone and camera. The input is the initial setting data for the generative model and emotion engine, and the output is the initialized model and engine.

[0687] Step 2: Processing the User Request

[0688] A user uses a terminal to request a specific number of material designs from the server. For example, the user enters "Please generate five material designs" into the terminal. The terminal sends this request to the server. The input is the user's request, and the output is the request data sent to the server. The server stores the received request as a log.

[0689] Step 3: Emotion Recognition

[0690] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the voice and facial expression data obtained from the user to identify the user's emotional state. For example, the device's microphone records the user's voice and the camera captures their facial expressions. The server inputs this data into the emotion engine and obtains the analysis results. The input is the user's voice data and facial expression data, and the output is the user's emotional state (e.g., "satisfied").

[0691] Step 4: Generate Material Design

[0692] The server uses a generative model algorithm to generate new material designs. It generates multiple designs based on the number of user requests and predicts the characteristics of each design (strength, durability, sustainability, cost). It also adjusts the design based on the user's emotional information obtained from the emotion engine. For example, if the user's emotional state is "satisfied," it will adjust the design accordingly. The input is the number of user requests and emotional information, and the output is a list of generated material designs.

[0693] Step 5: Provide the blueprint

[0694] The server provides the generated material design to the user. The design drawings are saved in list format and sent to the user's device. The user checks the design drawings on the device and evaluates and selects based on the emotional information provided by the emotion engine. The input is the generated material design list, and the output is the provision of the design drawings to the user. Specific operations include the user downloading the design drawings on their device and displaying detailed information.

[0695] Through these steps, the system can provide a blueprint for new materials that take into account the user's emotions.

[0696] (Application example 2)

[0697] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0698] Conventional material design systems have difficulty in considering user feedback based on their emotions. Furthermore, there is no way to provide the results of material design in real time, which hinders efficient work. Therefore, there is a need for a system that can improve user satisfaction and work efficiency in material design.

[0699] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0700] In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design plan for the new material based on the generative model, means for detecting a user's emotion using an emotion engine that recognizes emotions based on the user's voice and facial expression, means for adjusting the material design based on the detected emotion, and means for providing the generated design plan to the user in real time via a smart device. This makes it possible to quickly provide an optimal material design that corresponds to the user's emotion, significantly improving work efficiency and satisfaction.

[0701] A "generative model" is a mathematical model that predicts the properties of materials and generates designs for new materials based on that information.

[0702] "Properties" are the physical and economic attributes of a material, such as strength, durability, sustainability, and cost.

[0703] A "blueprint" is a drawing or diagram that visually shows the composition and manufacturing method of a new material.

[0704] An "emotion engine" is a technology that analyzes a user's voice and facial expressions and recognizes the user's emotions based on the results.

[0705] "Detection" is the act of using an emotion engine to understand and identify a user's emotion.

[0706] "Tuning" is the process of modifying and optimizing material design parameters based on detected user emotions.

[0707] A "smart device" is an advanced device that is equipped with internet and communication functions and can interactively exchange information with users.

[0708] "Real-time" refers to a method of time management that minimizes delays and provides updated and immediate information and data.

[0709] A "user" is someone who uses a system or device to obtain and evaluate information about new material designs.

[0710] MODE FOR CARRYING OUT THE INVENTION

[0711] To implement the present invention, the following system configuration and procedures are required.

[0712] System Configuration

[0713] 1. Server:

[0714] The server maintains a generative model and an emotion engine. The generative model contains algorithms for predicting the properties of the generated new material. The emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[0715] 2. Smart Devices:

[0716] Smart glasses and other interactive devices are used, which are equipped with cameras and microphones to capture the user's facial expressions and voice in real time, and the captured data is sent to a server.

[0717] Data processing and calculation

[0718] 1. Facial and Emotion Recognition:

[0719] The camera on the smart device captures the user's facial expressions, and OpenCV is used to detect specific facial features (eyes, mouth, eyebrows, etc.). The detected facial data is input into a facial emotion model built with Keras and analyzed by the emotion engine. Audio data captured by the microphone is also input into the emotion engine.

[0720] 2. Prediction of material properties:

[0721] The user's emotional information obtained by the emotion engine is sent to the server and input into the generative model algorithm, which then generates a blueprint for a new material, taking into account the material's strength, durability, sustainability, cost, and other characteristics along with the emotional information.

[0722] 3. View blueprints:

[0723] The generated blueprints are displayed in real time on the smart device screen, allowing users to select the optimal material design based on this information.

[0724] Specific examples

[0725] For example, if a user wants to design a new lightweight, strong material, and the smart glasses detect the emotion of "excitement" from the user's facial expression, the generated material design will be based on the emotion and will be lightweight and strong.

[0726] Example prompt sentence:

[0727] Based on the user's desired design, generate a material design that corresponds to the user's emotion of "excitement."

[0728] This invention makes it possible to quickly provide an optimal material design that corresponds to the user's emotions, thereby significantly improving work efficiency and satisfaction.

[0729] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0730] Step 1:

[0731] A smart device (such as smart glasses) is worn by a user and uses a camera and microphone to capture the user's facial expressions and voice data, which serve as input data for recognizing the user's emotions.

[0732] Step 2:

[0733] The smart device sends the captured facial expression data to the server, which uses a facial recognition algorithm (OpenCV) to detect specific facial features (eyes, mouth, eyebrows, etc.) and inputs this data into the emotion engine.

[0734] Step 3:

[0735] The server's emotion engine analyzes the facial recognition data and voice data to identify the user's emotions. This process uses an emotion recognition model using Keras. The analysis results in the user's emotions (e.g., "excitement" or "satisfaction").

[0736] Step 4:

[0737] The server inputs the identified user's emotional information into a generative model to predict the properties (strength, durability, sustainability, cost, etc.) of the new material. The generative model adjusts the material properties based on the emotional information to generate an optimal design.

[0738] Step 5:

[0739] The server stores a list of blueprints of new materials generated by the generative model, including predicted properties and adjustments based on emotional information.

[0740] Step 6:

[0741] The server sends the generated blueprint to the smart device, where the blueprint information is displayed in real time on the smart device's display. The user can check this information and proceed with the work as appropriate.

[0742] As a specific example of operation, if a user requests a new lightweight, strong material and the smart glasses detect the emotion of "excitement," the server will generate a lightweight, strong material design in response to the "excitement" and display the design on the smart glasses' display.

[0743] Through this series of processes, the optimal material design based on the user's feelings is quickly provided, which significantly improves work efficiency and user satisfaction.

[0744] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0745] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0746] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0747] [Third embodiment]

[0748] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0749] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0750] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0751] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0752] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0753] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0754] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0755] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0756] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0757] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0758] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0759] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0760] System Overview

[0761] The system of the invention uses generative models to predict the properties of new materials and provides the generated design drawings to users. This system operates using generative models stored on a server.

[0762] System Configuration

[0763] 1. Generative Model:

[0764] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[0765] 2. User Request:

[0766] A user requests a specific number of material designs from the server: the user inputs the number of designs desired and sends the request to the server.

[0767] 3. Generate Material Design:

[0768] The server generates new material designs using the generative model in response to user requests. The generated material designs are saved in list format.

[0769] 4. Providing blueprints:

[0770] The generated material design is provided to the user, who can receive the generated design and use it as needed.

[0771] Program processing

[0772] Initializing the Server

[0773] The server initializes and maintains the generative model, which contains algorithms for predicting material properties. The model randomly predicts new material properties based on data about various properties (e.g., strength, durability, etc.).

[0774] User request processing

[0775] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[0776] Material Design Generation

[0777] The server uses a generative modeling algorithm to generate the requested number of material designs, each predicting properties such as strength, durability, sustainability, and cost. The generated designs are saved in a list and later provided to the user.

[0778] Providing blueprints

[0779] The server provides the generated material designs to the user, who can review these designs and use them to help develop sustainable materials.

[0780] Specific examples

[0781] If a user requests five new material designs, the following results may be obtained:

[0782] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678

[0783] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789

[0784] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123

[0785] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890

[0786] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567

[0787] These blueprints are easily accessible to users, with detailed descriptions of each property, allowing users to select sustainable, high-performance materials.

[0788] The processing flow will be explained below.

[0789] Step 1:

[0790] The server initializes the generative model. The server prepares an algorithm for predicting material properties using the generative model, and instantiates and initializes the algorithm.

[0791] Step 2:

[0792] A request is made to the server for the number of material designs specified by the user. The user inputs the desired number of designs from the terminal and sends this request to the server.

[0793] Step 3:

[0794] The server receives the user's request and prepares to generate the requested number of material designs based on the received request.

[0795] Step 4:

[0796] The server generates blueprints for new materials using generative models, randomly generating values ​​for properties such as strength, durability, sustainability, and cost to create each blueprint.

[0797] Step 5:

[0798] Each generated material design is added to a list. The server saves the generated material designs in list format and prepares them for later provision to the user.

[0799] Step 6:

[0800] The server confirms that blueprint generation is complete. The server confirms that all requested material blueprints have been successfully generated.

[0801] Step 7:

[0802] The server provides the generated material design drawing to the user. The server transmits the design drawing saved in the list to the user's terminal and provides it to the user.

[0803] Step 8:

[0804] The user checks the provided blueprint. The user checks the material blueprint obtained on the terminal and evaluates each characteristic value (strength, durability, sustainability, cost, etc.).

[0805] Example 1

[0806] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0807] In the conventional material design process, predicting the properties of new materials is extremely time-consuming and costly, making it difficult to optimize the design. This problem is particularly pronounced when multiple properties, such as strength, durability, sustainability, and cost, must be considered simultaneously. Furthermore, there has been no means to quickly and efficiently provide a specific number of material designs required by the user.

[0808] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0809] In this invention, the server includes means for predicting the properties of new materials using a generative model, means for generating design drawings of new materials based on the generative model, means for providing the generated design drawings to a user, means for the server to receive user requests and generate a specified number of material designs, and means for the server to store the generated design drawings as a list and provide it to the user. This makes it possible to quickly predict the properties of new materials and efficiently generate and provide optimal designs.

[0810] A "generative model" is a computer program that contains algorithms for predicting the properties of new materials based on user input.

[0811] "Material properties" refer to specific physical and economic characteristics of a material, such as its strength, durability, sustainability, and cost.

[0812] A "means for predicting properties" is a method or device for calculating the property values ​​of a material using a generative model.

[0813] A "means for generating a design" is a process or tool for creating a detailed design of a new material based on a generative model.

[0814] The "means for providing a blueprint" refers to a method or interface for presenting the generated material blueprint to the user.

[0815] A "server" is a networked computer system whose role is to receive requests from users, generate material designs using generative models, and provide them to users.

[0816] A "request" is an operation or communication in which a user requests a specific number of material designs from a server.

[0817] The "means for saving as a list" is a method for managing and saving the generated multiple design drawings as a data structure in a computer.

[0818] The "specific number" refers to the number of material designs to be generated that the user specifies in the request.

[0819] The present invention is a system that uses a generative model to predict the properties of new materials, generates material designs based on the predictions, and provides the design drawings to users.

[0820] The server stores the generative model, which contains algorithms for predicting the strength, durability, sustainability, and cost characteristics of materials. Generative models can be implemented using popular deep learning frameworks such as TensorFlow and PyTorch. The server loads the model's trained parameters and initializes the model for use.

[0821] A user requests a specific number of material designs from the server through a web interface or API endpoint. For example, a prompt such as "Please generate five new material designs" is an example of such a request. The server receives this request and begins the process of generating the specified number of material designs.

[0822] During the generation process, the server runs a generative model, which predicts the properties of each design (strength, durability, sustainability, cost) using algorithms that combine random numbers and statistical methods. The generated material designs are stored in a database or memory in the form of a list.

[0823] Finally, the server provides the generated blueprints to the user, who can then acquire them and use them in research, manufacturing processes, etc. The generated blueprints contain detailed data on each material's properties, allowing the user to select the optimal material.

[0824] For example, if a user requests "generate five new material designs," the server will generate and serve the following blueprint results:

[0825] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678

[0826] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789

[0827] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123

[0828] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890

[0829] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567

[0830] The resulting material design is then presented to the user in an easily viewable format, with detailed information clearly displayed for each property, allowing users to efficiently select the optimal materials and create sustainable, high-performance products.

[0831] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0832] Step 1:

[0833] Initializing the Server

[0834] The server loads the generative model at startup and initializes it for use. Specifically, the server loads pre-trained models into memory using frameworks such as TensorFlow and PyTorch. This prepares the model to predict material properties.

[0835] Input: Pre-saved data for the generative model.

[0836] Output: An initialized generative model.

[0837] Step 2:

[0838] Accepting user requests

[0839] A user requests a specific number of material designs from the server through a web interface or an API endpoint. For example, the user might type "generate five new material designs." The server receives this request and parses it.

[0840] Input: User request (e.g. "Generate 5 new material design images").

[0841] Output: The number of material designs requested.

[0842] Step 3:

[0843] Material Design Generation

[0844] Based on the request, the server generates a specified number of material designs using a generative model that predicts material properties such as strength, durability, sustainability, and cost using a combination of random numbers and statistical methods.

[0845] Specific operation: Run the generative model and calculate the properties of each material design.

[0846] Input: The number of material designs requested.

[0847] Output: Properties of each generated material design (e.g., Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678).

[0848] Step 4:

[0849] Saving Blueprints

[0850] The server saves the generated design drawings as a list. In this step, the generated material designs are temporarily stored in a database or memory.

[0851] Specific operation: Write the generated material design to the database.

[0852] Input: Properties of each generated material design.

[0853] Output: A list of material designs stored in the database.

[0854] Step 5:

[0855] Providing blueprints

[0856] The server provides the generated material designs to the user in the form of a list, and returns the generated design drawings to the user using HTTP or API responses. The user can then retrieve these and use them in their research or manufacturing processes.

[0857] Specific operation: Generates an HTTP response and sends it to the user.

[0858] Input: A list of material designs stored in a database.

[0859] Output: A list of material designs provided to the user.

[0860] Through the above steps, the server can efficiently predict the properties of new materials, generate design drawings, and provide them to the user.

[0861] (Application example 1)

[0862] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0863] In modern manufacturing, material selection and optimization of manufacturing processes are extremely important. However, traditional methods have struggled to accurately predict material properties and quickly provide optimal material designs. This has resulted in time-consuming and costly manufacturing processes, and can lead to quality variations. Furthermore, when operators manually select material properties, there is a high risk of human error. To solve these problems, a system is needed that automates the prediction of material properties and the provision of optimal material designs, thereby optimizing manufacturing processes.

[0864] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0865] In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design drawing of the new material based on the generative model, means for providing the generated design drawing to a user, means for receiving a material property request from the user, means for proposing an optimal material selection based on the generated design drawing, and means for optimizing the manufacturing process based on the proposed material design. This enables highly accurate prediction of material properties, rapid provision of an optimal material design, and automation of the entire manufacturing process. Furthermore, the user can quickly and accurately select the optimal material, improving the efficiency and quality of the manufacturing process.

[0866] A "generative model" is a system that includes algorithms that use AI technology to predict the properties of new materials and generate design drawings.

[0867] "Material properties" refer to specific characteristics such as strength, durability, sustainability, and cost, the values ​​of which are predicted by the generative model.

[0868] A "design" includes detailed drawings and information about a material created based on the material's properties predicted using a generative model.

[0869] "User" refers to a person or organization that uses the system to request a material design and selects materials based on the provided design drawings.

[0870] A "request" is a user's request to the system to generate a specific number of material designs.

[0871] "Process optimization" is a means of optimizing the manufacturing process based on the selected material design to improve efficiency and quality.

[0872] System Overview

[0873] This invention implements a system that uses generative AI models to predict the properties of new materials and provide their design blueprints. This system receives requests from users, generates optimal material designs, and supports the optimization of manufacturing processes.

[0874] System Configuration

[0875] This system is realized by the following main components:

[0876] 1. Generative Model

[0877] The server hosts generative models that predict material properties, including built-in algorithms for predicting properties such as strength, durability, sustainability, and cost.

[0878] 2. Receiving a user request

[0879] A user requests specific material properties through a factory robot or terminal, for example by entering the prompt "Produce five materials with high strength and medium durability."

[0880] 3. Generating Material Design

[0881] The server uses the generative model to generate new material designs corresponding to the user's request, and the generated material designs are saved in a list format.

[0882] 4. Providing blueprints

[0883] The generated material design is sent to factory robots and terminals and provided to users, who can use it to optimize their manufacturing processes.

[0884] 5. Process optimization

[0885] Based on the proposed material design, factory robots adjust the production line to manufacture the product using the optimal process.

[0886] Hardware and Software

[0887] Hardware

[0888] Factory robots (e.g. KUKA, ABB)

[0889] Server (cloud-based or on-premise)

[0890] User device (touch panel display, etc.)

[0891] software

[0892] Generative AI models (e.g., GPT-4)

[0893] Communication protocol (e.g. MQTT, HTTP)

[0894] User interface (robot touch panel, remote control app)

[0895] Specific Examples

[0896] For example, a factory operator operates a terminal and types the following prompt:

[0897] Produce 5 materials with high strength and medium durability.

[0898] The server receives this request and generates a new material design using the generative model. The generated design is saved in a list format as follows:

[0899] 1. Design 1: Strength 9.0, Durability 5.5, Sustainability 7.0, Cost 4.5

[0900] 2. Design 2: Strength 8.5, Durability 5.0, Sustainability 6.5, Cost 3.5

[0901] 3. Design 3: Strength 8.8, Durability 5.3, Sustainability 7.2, Cost 4.0

[0902] 4. Design 4: Strength 9.2, Durability 5.7, Sustainability 6.9, Cost 4.8

[0903] 5. Design 5: Strength 8.9, Durability 5.6, Sustainability 7.1, Cost 4.2

[0904] Factory operators review this list and select the optimal material design, after which factory robots adjust the production line based on the selected material design, optimizing the manufacturing process.

[0905] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0906] Step 1:

[0907] The user operates the terminal and inputs a material property request.

[0908] Input: Prompts the user to enter specific material properties and quantities.

[0909] Specific action: For example, enter "Produce 5 materials with high strength and medium durability."

[0910] Output: The terminal converts the input prompt text into request data to be sent to the server and sends it.

[0911] Step 2:

[0912] The server receives the user's request and generates a new material design using the generative model.

[0913] Input: The prompt text sent from the terminal.

[0914] What it does: The server uses a generative AI model (e.g., GPT-4) to predict the requested material properties based on the prompt.

[0915] Data processing / computation: Predicting material strength, durability, sustainability, cost, etc.

[0916] Output: A data list of the generated material design.

[0917] Step 3:

[0918] The server saves the generated material design in list format and transmits the list to the terminal.

[0919] Input: Generated material design data list.

[0920] Specific operation: The server formats the generated material design into a list format and sends it to the terminal.

[0921] Output: Material design list sent to user terminal.

[0922] Step 4:

[0923] The terminal displays the generated material design list to the user.

[0924] Input: Material design list sent from the server.

[0925] Specific operation: The device displays the received material design list on the screen so that the user can check it.

[0926] Output: A material design list that can be visually verified by the user.

[0927] Step 5:

[0928] The user selects the optimal material design from the list and instructs the optimization of the manufacturing process.

[0929] Input: Material Design list displayed on the screen.

[0930] Specific operation: The user selects the optimal material design from the list and instructs the optimization of the manufacturing process via the terminal.

[0931] Output: Information on optimal material design selection and instruction data for manufacturing process optimization.

[0932] Step 6:

[0933] The server receives the instruction data and notifies the factory robots to optimize the manufacturing process.

[0934] Input: Material design selection information and manufacturing process optimization instruction data sent from the user terminal.

[0935] Specific operation: The server analyzes the received data and sends instructions to the factory robots to adjust the manufacturing process appropriately.

[0936] Output: Instruction data for factory robots to optimize the manufacturing process.

[0937] Step 7:

[0938] Factory robots manufacture products based on optimized manufacturing processes.

[0939] Input: Instruction data for optimizing the manufacturing process sent from the server.

[0940] Specific operation: Factory robots adjust the production line based on instruction data and manufacture products using the optimal process.

[0941] Output: A product from an optimized manufacturing process.

[0942] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0943] System Overview

[0944] The system of the invention uses generative models to predict the properties of new materials and provides the generated design to the user. The system also incorporates an emotion engine that recognizes the user's emotions and can adjust the material design based on the user's emotions.

[0945] System Configuration

[0946] 1. Generative Model:

[0947] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[0948] 2. Emotion Engine:

[0949] The server has an emotion engine that recognizes the user's emotions. This emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[0950] 3. User Request:

[0951] A user requests a specific number of material designs from the server by entering the number of designs desired and sending the request to the server.

[0952] 4. Generate Material Design:

[0953] The server generates new material designs using the generative model in response to user requests, and adjusts the designs based on the user's emotions. The generated material designs are saved in a list format.

[0954] 5. Provision of blueprints:

[0955] The generated material design is provided to the user, who can receive the generated design and evaluate the design based on the information provided by the emotion engine, if necessary.

[0956] Program processing

[0957] Initializing the Server

[0958] The server initializes the generative model and the emotion engine at the same time. The generative model has a built-in algorithm for predicting material properties, and the emotion engine has the ability to analyze voice and facial expression data.

[0959] User request processing

[0960] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[0961] emotion recognition

[0962] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's voice data and facial expression data to identify the user's emotional state. This emotional information is reflected in the generation of material design.

[0963] Material Design Generation

[0964] The server uses a generative model algorithm to generate the requested number of material designs. Each design predicts properties such as strength, durability, sustainability, and cost. Furthermore, the design is adjusted based on the user's emotional information obtained from the emotion engine. The generated designs are saved in a list and later provided to the user.

[0965] Providing blueprints

[0966] The server provides the generated material designs to the user, who can then review these designs and evaluate and select designs based on the emotional information provided by the emotion engine.

[0967] Specific examples

[0968] If a user requests five new material designs and the emotion engine recognizes the user's emotional state as "Satisfied," the following results may occur:

[0969] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678, Adjusted based on user emotion "Satisfaction"

[0970] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789, Adjustment based on user emotion "Satisfaction"

[0971] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123, Adjustment based on user emotion "Satisfaction"

[0972] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890, Adjustment based on user emotion "Satisfaction"

[0973] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567, Adjustment based on user emotion "Satisfaction"

[0974] These blueprints are easily accessible to users, with detailed descriptions of each property. Users can use these blueprints to select sustainable, high-performance materials. The emotional engine adjusts the design to provide optimal results, taking into account the user's emotional state.

[0975] The processing flow will be explained below.

[0976] Step 1:

[0977] The server initializes the generative model and emotion engine. The generative model contains algorithms that predict material properties such as strength, durability, sustainability, and cost. The emotion engine has the ability to recognize emotions by analyzing the user's voice and facial expression data.

[0978] Step 2:

[0979] The user requests a specific number of material designs from the server. The user inputs the desired number of material designs from the terminal and sends this request to the server.

[0980] Step 3:

[0981] The server receives the user's request and prepares to generate the requested number of material designs based on the received request.

[0982] Step 4:

[0983] The server activates an emotion engine to recognize the user's emotions. The user sends voice data and facial expression data to the server via their device. The server analyzes this data and identifies the user's emotions.

[0984] Step 5:

[0985] The server adjusts the material design based on the user's emotions. For example, if the user expresses "satisfied" emotion, the server will optimize the design based on the user's positive feedback.

[0986] Step 6:

[0987] The server uses generative models to generate material designs. Each design randomly predicts properties such as strength, durability, sustainability, and cost. The results of the emotion engine are also taken into account, and appropriate adjustments are made.

[0988] Step 7:

[0989] The server adds each generated material design to a list. The list will keep as many generated designs as requested.

[0990] Step 8:

[0991] The server confirms that blueprint generation is complete and that all requested material designs have been successfully generated.

[0992] Step 9:

[0993] The server provides the generated material blueprints to the user, each in a format that is easy for the user to understand.

[0994] Step 10:

[0995] The user checks the provided blueprint. The user can use their device to check the material blueprint obtained and evaluate each characteristic value (strength, durability, sustainability, cost, etc.). The results of the emotion engine are also displayed, allowing the user to see feedback based on their emotions.

[0996] Example 2

[0997] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0998] Conventional material design systems only predict material properties without considering user emotions when making design adjustments. As a result, they are unable to provide optimal material designs that reflect the user's emotions and needs, resulting in a lack of improvement in the user experience.

[0999] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design plan for the new material based on the generative model, means for analyzing a user's emotions using emotion recognition technology, means for adjusting the material design based on the analysis results, and means for providing the generated design plan to the user. This enables optimal material design that reflects the user's emotions.

[1000] A "generative model" is a set of algorithms or functions used to predict the properties of a material.

[1001] "Properties" are specific attributes or parameters related to the performance of a material, including its strength, durability, sustainability, and cost.

[1002] A "design" is a drawing or diagram that visually represents the material properties predicted and adjusted by the generative model.

[1003] "Emotion recognition technology" is a technology that analyzes voice data and facial expression data to identify a user's emotional state.

[1004] The "analysis results" are user emotional information obtained using emotion recognition technology, and are information that is reflected in material design.

[1005] "Tuning" is the process of changing or modifying the properties of a material design based on analytical results.

[1006] System Overview

[1007] The system of the present invention uses generative AI models to predict the properties of new materials and provides the generated design drawings to the user. The system incorporates an emotion engine that recognizes the user's emotions and can adjust the material design based on the user's emotions.

[1008] System Configuration

[1009] The system consists of the following main components:

[1010] 1. Generative Model:

[1011] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[1012] 2. Emotion Engine:

[1013] The server has an emotion engine that recognizes the user's emotions. This emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[1014] 3. User Request:

[1015] A user requests a specific number of material designs from the server by entering the number of designs desired and sending the request to the server.

[1016] 4. Generate Material Design:

[1017] The server generates new material designs using the generative model in response to user requests, and adjusts the designs based on the user's emotions. The generated material designs are saved in a list format.

[1018] 5. Provision of blueprints:

[1019] The generated material design is provided to the user, who can receive the generated design and evaluate the design based on the information provided by the emotion engine, if necessary.

[1020] Hardware and software used

[1021] Hardware: GPU accelerator, microphone, camera, etc.

[1022] Software: Emotion recognition libraries such as DeepFace, OpenSmile, etc.

[1023] Program processing overview

[1024] 1. Initialize the server:

[1025] The server initializes the generative model and emotion engine. The generative model has built-in algorithms for predicting material properties, and the emotion engine has the ability to analyze voice and facial expression data.

[1026] 2. User request processing:

[1027] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[1028] 3. Emotion recognition:

[1029] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's voice data and facial expression data to identify the user's emotional state. This emotional information is reflected in the generation of material design.

[1030] 4. Generate Material Design:

[1031] The server uses a generative model algorithm to generate the requested number of material designs. Each design predicts properties such as strength, durability, sustainability, and cost. Furthermore, the design is adjusted based on the user's emotional information obtained from the emotion engine. The generated designs are saved in a list and later provided to the user.

[1032] 5. Provision of blueprints:

[1033] The server provides the generated material designs to the user, who can then review these designs and evaluate and select designs based on the emotional information provided by the emotion engine.

[1034] Specific examples

[1035] The following concrete example shows a scenario in which a user requests five new material designs and the emotion engine recognizes the user's emotional state as "Satisfied."

[1036] Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678, adjusted based on user emotion "Satisfaction"

[1037] Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789, adjusted based on user emotion "Satisfaction"

[1038] Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123, adjusted based on user emotion "Satisfaction"

[1039] Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890, adjusted based on user emotion "Satisfaction"

[1040] Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567, adjusted based on user emotion "Satisfaction"

[1041] Prompt Sentence Examples

[1042] "Please describe a system that uses an emotion engine to recognize user emotions and generate new material designs. Include a concrete scenario."

[1043] As described above, this system aims to provide a blueprint for new materials that take user emotions into account by utilizing generative AI models and emotion recognition technology. The detailed operating procedures and instructions, including the hardware and software used, will be helpful for implementing and practicing the system.

[1044] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1045] Step 1: Initialize the server

[1046] The server initializes the generative model and emotion engine when the system starts up. The generative model has built-in algorithms that predict material properties (strength, durability, sustainability, cost). The emotion engine has the ability to analyze voice data and facial expression data. Specifically, the server loads the generative model into memory, starts the emotion engine, and checks the connection status with the microphone and camera. The input is the initial setting data for the generative model and emotion engine, and the output is the initialized model and engine.

[1047] Step 2: Processing the User Request

[1048] A user uses a terminal to request a specific number of material designs from the server. For example, the user enters "Please generate five material designs" into the terminal. The terminal sends this request to the server. The input is the user's request, and the output is the request data sent to the server. The server stores the received request as a log.

[1049] Step 3: Emotion Recognition

[1050] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the voice and facial expression data obtained from the user to identify the user's emotional state. For example, the device's microphone records the user's voice and the camera captures their facial expressions. The server inputs this data into the emotion engine and obtains the analysis results. The input is the user's voice data and facial expression data, and the output is the user's emotional state (e.g., "satisfied").

[1051] Step 4: Generate Material Design

[1052] The server uses a generative model algorithm to generate new material designs. It generates multiple designs based on the number of user requests and predicts the characteristics of each design (strength, durability, sustainability, cost). It also adjusts the design based on the user's emotional information obtained from the emotion engine. For example, if the user's emotional state is "satisfied," it will adjust the design accordingly. The input is the number of user requests and emotional information, and the output is a list of generated material designs.

[1053] Step 5: Provide the blueprint

[1054] The server provides the generated material design to the user. The design drawings are saved in list format and sent to the user's device. The user checks the design drawings on the device and evaluates and selects based on the emotional information provided by the emotion engine. The input is the generated material design list, and the output is the provision of the design drawings to the user. Specific operations include the user downloading the design drawings on their device and displaying detailed information.

[1055] Through these steps, the system can provide a blueprint for new materials that take into account the user's emotions.

[1056] (Application example 2)

[1057] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1058] Conventional material design systems have difficulty in considering user feedback based on their emotions. Furthermore, there is no way to provide the results of material design in real time, which hinders efficient work. Therefore, there is a need for a system that can improve user satisfaction and work efficiency in material design.

[1059] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1060] In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design plan for the new material based on the generative model, means for detecting a user's emotion using an emotion engine that recognizes emotions based on the user's voice and facial expression, means for adjusting the material design based on the detected emotion, and means for providing the generated design plan to the user in real time via a smart device. This makes it possible to quickly provide an optimal material design that corresponds to the user's emotion, significantly improving work efficiency and satisfaction.

[1061] A "generative model" is a mathematical model that predicts the properties of materials and generates designs for new materials based on that information.

[1062] "Properties" are the physical and economic attributes of a material, such as strength, durability, sustainability, and cost.

[1063] A "blueprint" is a drawing or diagram that visually shows the composition and manufacturing method of a new material.

[1064] An "emotion engine" is a technology that analyzes a user's voice and facial expressions and recognizes the user's emotions based on the results.

[1065] "Detection" is the act of using an emotion engine to understand and identify a user's emotion.

[1066] "Tuning" is the process of modifying and optimizing material design parameters based on detected user emotions.

[1067] A "smart device" is an advanced device that is equipped with internet and communication functions and can interactively exchange information with users.

[1068] "Real-time" refers to a method of time management that minimizes delays and provides updated and immediate information and data.

[1069] A "user" is someone who uses a system or device to obtain and evaluate information about new material designs.

[1070] MODE FOR CARRYING OUT THE INVENTION

[1071] To implement the present invention, the following system configuration and procedures are required.

[1072] System Configuration

[1073] 1. Server:

[1074] The server maintains a generative model and an emotion engine. The generative model contains algorithms for predicting the properties of the generated new material. The emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[1075] 2. Smart Devices:

[1076] Smart glasses and other interactive devices are used, which are equipped with cameras and microphones to capture the user's facial expressions and voice in real time, and the captured data is sent to a server.

[1077] Data processing and calculation

[1078] 1. Facial and Emotion Recognition:

[1079] The camera on the smart device captures the user's facial expressions, and OpenCV is used to detect specific facial features (eyes, mouth, eyebrows, etc.). The detected facial data is input into a facial emotion model built with Keras and analyzed by the emotion engine. Audio data captured by the microphone is also input into the emotion engine.

[1080] 2. Prediction of material properties:

[1081] The user's emotional information obtained by the emotion engine is sent to the server and input into the generative model algorithm, which then generates a blueprint for a new material, taking into account the material's strength, durability, sustainability, cost, and other characteristics along with the emotional information.

[1082] 3. View blueprints:

[1083] The generated blueprints are displayed in real time on the smart device screen, allowing users to select the optimal material design based on this information.

[1084] Specific examples

[1085] For example, if a user wants to design a new lightweight, strong material, and the smart glasses detect the emotion of "excitement" from the user's facial expression, the generated material design will be based on the emotion and will be lightweight and strong.

[1086] Example prompt sentence:

[1087] Based on the user's desired design, generate a material design that corresponds to the user's emotion of "excitement."

[1088] This invention makes it possible to quickly provide an optimal material design that corresponds to the user's emotions, thereby significantly improving work efficiency and satisfaction.

[1089] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1090] Step 1:

[1091] A smart device (such as smart glasses) is worn by a user and uses a camera and microphone to capture the user's facial expressions and voice data, which serve as input data for recognizing the user's emotions.

[1092] Step 2:

[1093] The smart device sends the captured facial expression data to the server, which uses a facial recognition algorithm (OpenCV) to detect specific facial features (eyes, mouth, eyebrows, etc.) and inputs this data into the emotion engine.

[1094] Step 3:

[1095] The server's emotion engine analyzes the facial recognition data and voice data to identify the user's emotions. This process uses an emotion recognition model using Keras. The analysis results in the user's emotions (e.g., "excitement" or "satisfaction").

[1096] Step 4:

[1097] The server inputs the identified user's emotional information into a generative model to predict the properties (strength, durability, sustainability, cost, etc.) of the new material. The generative model adjusts the material properties based on the emotional information to generate an optimal design.

[1098] Step 5:

[1099] The server stores a list of blueprints of new materials generated by the generative model, including predicted properties and adjustments based on emotional information.

[1100] Step 6:

[1101] The server sends the generated blueprint to the smart device, where the blueprint information is displayed in real time on the smart device's display. The user can check this information and proceed with the work as appropriate.

[1102] As a specific example of operation, if a user requests a new lightweight, strong material and the smart glasses detect the emotion of "excitement," the server will generate a lightweight, strong material design in response to the "excitement" and display the design on the smart glasses' display.

[1103] Through this series of processes, the optimal material design based on the user's feelings is quickly provided, which significantly improves work efficiency and user satisfaction.

[1104] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1106] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1107] [Fourth embodiment]

[1108] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1109] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1110] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1111] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1112] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1113] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1114] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1115] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1116] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1117] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1118] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1119] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1120] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1121] System Overview

[1122] The system of the invention uses generative models to predict the properties of new materials and provides the generated design drawings to users. This system operates using generative models stored on a server.

[1123] System Configuration

[1124] 1. Generative Model:

[1125] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[1126] 2. User Request:

[1127] A user requests a specific number of material designs from the server: the user inputs the number of designs desired and sends the request to the server.

[1128] 3. Generate Material Design:

[1129] The server generates new material designs using the generative model in response to user requests. The generated material designs are saved in list format.

[1130] 4. Providing blueprints:

[1131] The generated material design is provided to the user, who can receive the generated design and use it as needed.

[1132] Program processing

[1133] Initializing the Server

[1134] The server initializes and maintains the generative model, which contains algorithms for predicting material properties. The model randomly predicts new material properties based on data about various properties (e.g., strength, durability, etc.).

[1135] User request processing

[1136] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[1137] Material Design Generation

[1138] The server uses a generative modeling algorithm to generate the requested number of material designs, each predicting properties such as strength, durability, sustainability, and cost. The generated designs are saved in a list and later provided to the user.

[1139] Providing blueprints

[1140] The server provides the generated material designs to the user, who can review these designs and use them to help develop sustainable materials.

[1141] Specific examples

[1142] If a user requests five new material designs, the following results may be obtained:

[1143] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678

[1144] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789

[1145] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123

[1146] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890

[1147] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567

[1148] These blueprints are easily accessible to users, with detailed descriptions of each property, allowing users to select sustainable, high-performance materials.

[1149] The processing flow will be explained below.

[1150] Step 1:

[1151] The server initializes the generative model. The server prepares an algorithm for predicting material properties using the generative model, and instantiates and initializes the algorithm.

[1152] Step 2:

[1153] A request is made to the server for the number of material designs specified by the user. The user inputs the desired number of designs from the terminal and sends this request to the server.

[1154] Step 3:

[1155] The server receives the user's request and prepares to generate the requested number of material designs based on the received request.

[1156] Step 4:

[1157] The server generates blueprints for new materials using generative models, randomly generating values ​​for properties such as strength, durability, sustainability, and cost to create each blueprint.

[1158] Step 5:

[1159] Each generated material design is added to a list. The server saves the generated material designs in list format and prepares them for later provision to the user.

[1160] Step 6:

[1161] The server confirms that blueprint generation is complete. The server confirms that all requested material blueprints have been successfully generated.

[1162] Step 7:

[1163] The server provides the generated material design drawing to the user. The server transmits the design drawing saved in the list to the user's terminal and provides it to the user.

[1164] Step 8:

[1165] The user checks the provided blueprint. The user checks the material blueprint obtained on the terminal and evaluates each characteristic value (strength, durability, sustainability, cost, etc.).

[1166] Example 1

[1167] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1168] In the conventional material design process, predicting the properties of new materials is extremely time-consuming and costly, making it difficult to optimize the design. This problem is particularly pronounced when multiple properties, such as strength, durability, sustainability, and cost, must be considered simultaneously. Furthermore, there has been no means to quickly and efficiently provide a specific number of material designs required by the user.

[1169] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1170] In this invention, the server includes means for predicting the properties of new materials using a generative model, means for generating design drawings of new materials based on the generative model, means for providing the generated design drawings to a user, means for the server to receive user requests and generate a specified number of material designs, and means for the server to store the generated design drawings as a list and provide it to the user. This makes it possible to quickly predict the properties of new materials and efficiently generate and provide optimal designs.

[1171] A "generative model" is a computer program that contains algorithms for predicting the properties of new materials based on user input.

[1172] "Material properties" refer to specific physical and economic characteristics of a material, such as its strength, durability, sustainability, and cost.

[1173] A "means for predicting properties" is a method or device for calculating the property values ​​of a material using a generative model.

[1174] A "means for generating a design" is a process or tool for creating a detailed design of a new material based on a generative model.

[1175] The "means for providing a blueprint" refers to a method or interface for presenting the generated material blueprint to the user.

[1176] A "server" is a networked computer system whose role is to receive requests from users, generate material designs using generative models, and provide them to users.

[1177] A "request" is an operation or communication in which a user requests a specific number of material designs from a server.

[1178] The "means for saving as a list" is a method for managing and saving the generated multiple design drawings as a data structure in a computer.

[1179] The "specific number" refers to the number of material designs to be generated that the user specifies in the request.

[1180] The present invention is a system that uses a generative model to predict the properties of new materials, generates material designs based on the predictions, and provides the design drawings to users.

[1181] The server stores the generative model, which contains algorithms for predicting the strength, durability, sustainability, and cost characteristics of materials. Generative models can be implemented using popular deep learning frameworks such as TensorFlow and PyTorch. The server loads the model's trained parameters and initializes the model for use.

[1182] A user requests a specific number of material designs from the server through a web interface or API endpoint. For example, a prompt such as "Please generate five new material designs" is an example of such a request. The server receives this request and begins the process of generating the specified number of material designs.

[1183] During the generation process, the server runs a generative model, which predicts the properties of each design (strength, durability, sustainability, cost) using algorithms that combine random numbers and statistical methods. The generated material designs are stored in a database or memory in the form of a list.

[1184] Finally, the server provides the generated blueprints to the user, who can then acquire them and use them in research, manufacturing processes, etc. The generated blueprints contain detailed data on each material's properties, allowing the user to select the optimal material.

[1185] For example, if a user requests "generate five new material designs," the server will generate and serve the following blueprint results:

[1186] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678

[1187] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789

[1188] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123

[1189] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890

[1190] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567

[1191] The resulting material design is then presented to the user in an easily viewable format, with detailed information clearly displayed for each property, allowing users to efficiently select the optimal materials and create sustainable, high-performance products.

[1192] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1193] Step 1:

[1194] Initializing the Server

[1195] The server loads the generative model at startup and initializes it for use. Specifically, the server loads pre-trained models into memory using frameworks such as TensorFlow and PyTorch. This prepares the model to predict material properties.

[1196] Input: Pre-saved data for the generative model.

[1197] Output: An initialized generative model.

[1198] Step 2:

[1199] Accepting user requests

[1200] A user requests a specific number of material designs from the server through a web interface or an API endpoint. For example, the user might type "generate five new material designs." The server receives this request and parses it.

[1201] Input: User request (e.g. "Generate 5 new material design images").

[1202] Output: The number of material designs requested.

[1203] Step 3:

[1204] Material Design Generation

[1205] Based on the request, the server generates a specified number of material designs using a generative model that predicts material properties such as strength, durability, sustainability, and cost using a combination of random numbers and statistical methods.

[1206] Specific operation: Run the generative model and calculate the properties of each material design.

[1207] Input: The number of material designs requested.

[1208] Output: Properties of each generated material design (e.g., Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678).

[1209] Step 4:

[1210] Saving Blueprints

[1211] The server saves the generated design drawings as a list. In this step, the generated material designs are temporarily stored in a database or memory.

[1212] Specific operation: Write the generated material design to the database.

[1213] Input: Properties of each generated material design.

[1214] Output: A list of material designs stored in the database.

[1215] Step 5:

[1216] Providing blueprints

[1217] The server provides the generated material designs to the user in the form of a list, and returns the generated design drawings to the user using HTTP or API responses. The user can then retrieve these and use them in their research or manufacturing processes.

[1218] Specific operation: Generates an HTTP response and sends it to the user.

[1219] Input: A list of material designs stored in a database.

[1220] Output: A list of material designs provided to the user.

[1221] Through the above steps, the server can efficiently predict the properties of new materials, generate design drawings, and provide them to the user.

[1222] (Application example 1)

[1223] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1224] In modern manufacturing, material selection and optimization of manufacturing processes are extremely important. However, traditional methods have struggled to accurately predict material properties and quickly provide optimal material designs. This has resulted in time-consuming and costly manufacturing processes, and can lead to quality variations. Furthermore, when operators manually select material properties, there is a high risk of human error. To solve these problems, a system is needed that automates the prediction of material properties and the provision of optimal material designs, thereby optimizing manufacturing processes.

[1225] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1226] In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design drawing of the new material based on the generative model, means for providing the generated design drawing to a user, means for receiving a material property request from the user, means for proposing an optimal material selection based on the generated design drawing, and means for optimizing the manufacturing process based on the proposed material design. This enables highly accurate prediction of material properties, rapid provision of an optimal material design, and automation of the entire manufacturing process. Furthermore, the user can quickly and accurately select the optimal material, improving the efficiency and quality of the manufacturing process.

[1227] A "generative model" is a system that includes algorithms that use AI technology to predict the properties of new materials and generate design drawings.

[1228] "Material properties" refer to specific characteristics such as strength, durability, sustainability, and cost, the values ​​of which are predicted by the generative model.

[1229] A "design" includes detailed drawings and information about a material created based on the material's properties predicted using a generative model.

[1230] "User" refers to a person or organization that uses the system to request a material design and selects materials based on the provided design drawings.

[1231] A "request" is a user's request to the system to generate a specific number of material designs.

[1232] "Process optimization" is a means of optimizing the manufacturing process based on the selected material design to improve efficiency and quality.

[1233] System Overview

[1234] This invention implements a system that uses generative AI models to predict the properties of new materials and provide their design blueprints. This system receives requests from users, generates optimal material designs, and supports the optimization of manufacturing processes.

[1235] System Configuration

[1236] This system is realized by the following main components:

[1237] 1. Generative Model

[1238] The server hosts generative models that predict material properties, including built-in algorithms for predicting properties such as strength, durability, sustainability, and cost.

[1239] 2. Receiving a user request

[1240] A user requests specific material properties through a factory robot or terminal, for example by entering the prompt "Produce five materials with high strength and medium durability."

[1241] 3. Generating Material Design

[1242] The server uses the generative model to generate new material designs corresponding to the user's request, and the generated material designs are saved in a list format.

[1243] 4. Providing blueprints

[1244] The generated material design is sent to factory robots and terminals and provided to users, who can use it to optimize their manufacturing processes.

[1245] 5. Process optimization

[1246] Based on the proposed material design, factory robots adjust the production line to manufacture the product using the optimal process.

[1247] Hardware and Software

[1248] Hardware

[1249] Factory robots (e.g. KUKA, ABB)

[1250] Server (cloud-based or on-premise)

[1251] User device (touch panel display, etc.)

[1252] software

[1253] Generative AI models (e.g., GPT-4)

[1254] Communication protocol (e.g. MQTT, HTTP)

[1255] User interface (robot touch panel, remote control app)

[1256] Specific Examples

[1257] For example, a factory operator operates a terminal and types the following prompt:

[1258] Produce 5 materials with high strength and medium durability.

[1259] The server receives this request and generates a new material design using the generative model. The generated design is saved in a list format as follows:

[1260] 1. Design 1: Strength 9.0, Durability 5.5, Sustainability 7.0, Cost 4.5

[1261] 2. Design 2: Strength 8.5, Durability 5.0, Sustainability 6.5, Cost 3.5

[1262] 3. Design 3: Strength 8.8, Durability 5.3, Sustainability 7.2, Cost 4.0

[1263] 4. Design 4: Strength 9.2, Durability 5.7, Sustainability 6.9, Cost 4.8

[1264] 5. Design 5: Strength 8.9, Durability 5.6, Sustainability 7.1, Cost 4.2

[1265] Factory operators review this list and select the optimal material design, after which factory robots adjust the production line based on the selected material design, optimizing the manufacturing process.

[1266] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1267] Step 1:

[1268] The user operates the terminal and inputs a material property request.

[1269] Input: Prompts the user to enter specific material properties and quantities.

[1270] Specific action: For example, enter "Produce 5 materials with high strength and medium durability."

[1271] Output: The terminal converts the input prompt text into request data to be sent to the server and sends it.

[1272] Step 2:

[1273] The server receives the user's request and generates a new material design using the generative model.

[1274] Input: The prompt text sent from the terminal.

[1275] What it does: The server uses a generative AI model (e.g., GPT-4) to predict the requested material properties based on the prompt.

[1276] Data processing / computation: Predicting material strength, durability, sustainability, cost, etc.

[1277] Output: A data list of the generated material design.

[1278] Step 3:

[1279] The server saves the generated material design in list format and transmits the list to the terminal.

[1280] Input: Generated material design data list.

[1281] Specific operation: The server formats the generated material design into a list format and sends it to the terminal.

[1282] Output: Material design list sent to user terminal.

[1283] Step 4:

[1284] The terminal displays the generated material design list to the user.

[1285] Input: Material design list sent from the server.

[1286] Specific operation: The device displays the received material design list on the screen so that the user can check it.

[1287] Output: A material design list that can be visually verified by the user.

[1288] Step 5:

[1289] The user selects the optimal material design from the list and instructs the optimization of the manufacturing process.

[1290] Input: Material Design list displayed on the screen.

[1291] Specific operation: The user selects the optimal material design from the list and instructs the optimization of the manufacturing process via the terminal.

[1292] Output: Information on optimal material design selection and instruction data for manufacturing process optimization.

[1293] Step 6:

[1294] The server receives the instruction data and notifies the factory robots to optimize the manufacturing process.

[1295] Input: Material design selection information and manufacturing process optimization instruction data sent from the user terminal.

[1296] Specific operation: The server analyzes the received data and sends instructions to the factory robots to adjust the manufacturing process appropriately.

[1297] Output: Instruction data for factory robots to optimize the manufacturing process.

[1298] Step 7:

[1299] Factory robots manufacture products based on optimized manufacturing processes.

[1300] Input: Instruction data for optimizing the manufacturing process sent from the server.

[1301] Specific operation: Factory robots adjust the production line based on instruction data and manufacture products using the optimal process.

[1302] Output: A product from an optimized manufacturing process.

[1303] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1304] System Overview

[1305] The system of the invention uses generative models to predict the properties of new materials and provides the generated design to the user. The system also incorporates an emotion engine that recognizes the user's emotions and can adjust the material design based on the user's emotions.

[1306] System Configuration

[1307] 1. Generative Model:

[1308] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[1309] 2. Emotion Engine:

[1310] The server has an emotion engine that recognizes the user's emotions. This emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[1311] 3. User Request:

[1312] A user requests a specific number of material designs from the server by entering the number of designs desired and sending the request to the server.

[1313] 4. Generate Material Design:

[1314] The server generates new material designs using the generative model in response to user requests, and adjusts the designs based on the user's emotions. The generated material designs are saved in a list format.

[1315] 5. Provision of blueprints:

[1316] The generated material design is provided to the user, who can receive the generated design and evaluate the design based on the information provided by the emotion engine, if necessary.

[1317] Program processing

[1318] Initializing the Server

[1319] The server initializes the generative model and the emotion engine at the same time. The generative model has a built-in algorithm for predicting material properties, and the emotion engine has the ability to analyze voice and facial expression data.

[1320] User request processing

[1321] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[1322] emotion recognition

[1323] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's voice data and facial expression data to identify the user's emotional state. This emotional information is reflected in the generation of material design.

[1324] Material Design Generation

[1325] The server uses a generative model algorithm to generate the requested number of material designs. Each design predicts properties such as strength, durability, sustainability, and cost. Furthermore, the design is adjusted based on the user's emotional information obtained from the emotion engine. The generated designs are saved in a list and later provided to the user.

[1326] Providing blueprints

[1327] The server provides the generated material designs to the user, who can then review these designs and evaluate and select designs based on the emotional information provided by the emotion engine.

[1328] Specific examples

[1329] If a user requests five new material designs and the emotion engine recognizes the user's emotional state as "Satisfied," the following results may occur:

[1330] 1. Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678, Adjusted based on user emotion "Satisfaction"

[1331] 2. Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789, Adjustment based on user emotion "Satisfaction"

[1332] 3. Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123, Adjustment based on user emotion "Satisfaction"

[1333] 4. Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890, Adjustment based on user emotion "Satisfaction"

[1334] 5. Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567, Adjustment based on user emotion "Satisfaction"

[1335] These blueprints are easily accessible to users, with detailed descriptions of each property. Users can use these blueprints to select sustainable, high-performance materials. The emotional engine adjusts the design to provide optimal results, taking into account the user's emotional state.

[1336] The processing flow will be explained below.

[1337] Step 1:

[1338] The server initializes the generative model and emotion engine. The generative model contains algorithms that predict material properties such as strength, durability, sustainability, and cost. The emotion engine has the ability to recognize emotions by analyzing the user's voice and facial expression data.

[1339] Step 2:

[1340] The user requests a specific number of material designs from the server. The user inputs the desired number of material designs from the terminal and sends this request to the server.

[1341] Step 3:

[1342] The server receives the user's request and prepares to generate the requested number of material designs based on the received request.

[1343] Step 4:

[1344] The server activates an emotion engine to recognize the user's emotions. The user sends voice data and facial expression data to the server via their device. The server analyzes this data and identifies the user's emotions.

[1345] Step 5:

[1346] The server adjusts the material design based on the user's emotions. For example, if the user expresses "satisfied" emotion, the server will optimize the design based on the user's positive feedback.

[1347] Step 6:

[1348] The server uses generative models to generate material designs. Each design randomly predicts properties such as strength, durability, sustainability, and cost. The results of the emotion engine are also taken into account, and appropriate adjustments are made.

[1349] Step 7:

[1350] The server adds each generated material design to a list. The list will keep as many generated designs as requested.

[1351] Step 8:

[1352] The server confirms that blueprint generation is complete and that all requested material designs have been successfully generated.

[1353] Step 9:

[1354] The server provides the generated material blueprints to the user, each in a format that is easy for the user to understand.

[1355] Step 10:

[1356] The user checks the provided blueprint. The user can use their device to check the material blueprint obtained and evaluate each characteristic value (strength, durability, sustainability, cost, etc.). The results of the emotion engine are also displayed, allowing the user to see feedback based on their emotions.

[1357] Example 2

[1358] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1359] Conventional material design systems only predict material properties without considering user emotions when making design adjustments. As a result, they are unable to provide optimal material designs that reflect the user's emotions and needs, resulting in a lack of improvement in the user experience.

[1360] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design plan for the new material based on the generative model, means for analyzing a user's emotions using emotion recognition technology, means for adjusting the material design based on the analysis results, and means for providing the generated design plan to the user. This enables optimal material design that reflects the user's emotions.

[1361] A "generative model" is a set of algorithms or functions used to predict the properties of a material.

[1362] "Properties" are specific attributes or parameters related to the performance of a material, including its strength, durability, sustainability, and cost.

[1363] A "design" is a drawing or diagram that visually represents the material properties predicted and adjusted by the generative model.

[1364] "Emotion recognition technology" is a technology that analyzes voice data and facial expression data to identify a user's emotional state.

[1365] The "analysis results" are user emotional information obtained using emotion recognition technology, and are information that is reflected in material design.

[1366] "Tuning" is the process of changing or modifying the properties of a material design based on analytical results.

[1367] System Overview

[1368] The system of the present invention uses generative AI models to predict the properties of new materials and provides the generated design drawings to the user. The system incorporates an emotion engine that recognizes the user's emotions and can adjust the material design based on the user's emotions.

[1369] System Configuration

[1370] The system consists of the following main components:

[1371] 1. Generative Model:

[1372] The server maintains generative models that predict material properties, including algorithms that predict properties such as strength, durability, sustainability, and cost.

[1373] 2. Emotion Engine:

[1374] The server has an emotion engine that recognizes the user's emotions. This emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[1375] 3. User Request:

[1376] A user requests a specific number of material designs from the server by entering the number of designs desired and sending the request to the server.

[1377] 4. Generate Material Design:

[1378] The server generates new material designs using the generative model in response to user requests, and adjusts the designs based on the user's emotions. The generated material designs are saved in a list format.

[1379] 5. Provision of blueprints:

[1380] The generated material design is provided to the user, who can receive the generated design and evaluate the design based on the information provided by the emotion engine, if necessary.

[1381] Hardware and software used

[1382] Hardware: GPU accelerator, microphone, camera, etc.

[1383] Software: Emotion recognition libraries such as DeepFace, OpenSmile, etc.

[1384] Program processing overview

[1385] 1. Initialize the server:

[1386] The server initializes the generative model and emotion engine. The generative model has built-in algorithms for predicting material properties, and the emotion engine has the ability to analyze voice and facial expression data.

[1387] 2. User request processing:

[1388] The user requests a certain number of material designs from the server. For example, if the user requests five material designs, the server goes into the process of generating five new designs.

[1389] 3. Emotion recognition:

[1390] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's voice data and facial expression data to identify the user's emotional state. This emotional information is reflected in the generation of material design.

[1391] 4. Generate Material Design:

[1392] The server uses a generative model algorithm to generate the requested number of material designs. Each design predicts properties such as strength, durability, sustainability, and cost. Furthermore, the design is adjusted based on the user's emotional information obtained from the emotion engine. The generated designs are saved in a list and later provided to the user.

[1393] 5. Provision of blueprints:

[1394] The server provides the generated material designs to the user, who can then review these designs and evaluate and select designs based on the emotional information provided by the emotion engine.

[1395] Specific examples

[1396] The following concrete example shows a scenario in which a user requests five new material designs and the emotion engine recognizes the user's emotional state as "Satisfied."

[1397] Design 1: Strength 4.567, Durability 7.890, Sustainability 5.345, Cost 3.678, adjusted based on user emotion "Satisfaction"

[1398] Design 2: Strength 6.123, Durability 4.567, Sustainability 7.234, Cost 6.789, adjusted based on user emotion "Satisfaction"

[1399] Design 3: Strength 8.901, Durability 2.345, Sustainability 4.567, Cost 2.123, adjusted based on user emotion "Satisfaction"

[1400] Design 4: Strength 3.456, Durability 6.789, Sustainability 5.123, Cost 7.890, adjusted based on user emotion "Satisfaction"

[1401] Design 5: Strength 9.012, Durability 8.345, Sustainability 6.789, Cost 4.567, adjusted based on user emotion "Satisfaction"

[1402] Prompt Sentence Examples

[1403] "Please describe a system that uses an emotion engine to recognize user emotions and generate new material designs. Include a concrete scenario."

[1404] As described above, this system aims to provide a blueprint for new materials that take user emotions into account by utilizing generative AI models and emotion recognition technology. The detailed operating procedures and instructions, including the hardware and software used, will be helpful for implementing and practicing the system.

[1405] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1406] Step 1: Initialize the server

[1407] The server initializes the generative model and emotion engine when the system starts up. The generative model has built-in algorithms that predict material properties (strength, durability, sustainability, cost). The emotion engine has the ability to analyze voice data and facial expression data. Specifically, the server loads the generative model into memory, starts the emotion engine, and checks the connection status with the microphone and camera. The input is the initial setting data for the generative model and emotion engine, and the output is the initialized model and engine.

[1408] Step 2: Processing the User Request

[1409] A user uses a terminal to request a specific number of material designs from the server. For example, the user enters "Please generate five material designs" into the terminal. The terminal sends this request to the server. The input is the user's request, and the output is the request data sent to the server. The server stores the received request as a log.

[1410] Step 3: Emotion Recognition

[1411] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the voice and facial expression data obtained from the user to identify the user's emotional state. For example, the device's microphone records the user's voice and the camera captures their facial expressions. The server inputs this data into the emotion engine and obtains the analysis results. The input is the user's voice data and facial expression data, and the output is the user's emotional state (e.g., "satisfied").

[1412] Step 4: Generate Material Design

[1413] The server uses a generative model algorithm to generate new material designs. It generates multiple designs based on the number of user requests and predicts the characteristics of each design (strength, durability, sustainability, cost). It also adjusts the design based on the user's emotional information obtained from the emotion engine. For example, if the user's emotional state is "satisfied," it will adjust the design accordingly. The input is the number of user requests and emotional information, and the output is a list of generated material designs.

[1414] Step 5: Provide the blueprint

[1415] The server provides the generated material design to the user. The design drawings are saved in list format and sent to the user's device. The user checks the design drawings on the device and evaluates and selects based on the emotional information provided by the emotion engine. The input is the generated material design list, and the output is the provision of the design drawings to the user. Specific operations include the user downloading the design drawings on their device and displaying detailed information.

[1416] Through these steps, the system can provide a blueprint for new materials that take into account the user's emotions.

[1417] (Application example 2)

[1418] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1419] Conventional material design systems have difficulty in considering user feedback based on their emotions. Furthermore, there is no way to provide the results of material design in real time, which hinders efficient work. Therefore, there is a need for a system that can improve user satisfaction and work efficiency in material design.

[1420] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1421] In this invention, the server includes means for predicting the properties of a new material using a generative model, means for generating a design plan for the new material based on the generative model, means for detecting a user's emotion using an emotion engine that recognizes emotions based on the user's voice and facial expression, means for adjusting the material design based on the detected emotion, and means for providing the generated design plan to the user in real time via a smart device. This makes it possible to quickly provide an optimal material design that corresponds to the user's emotion, significantly improving work efficiency and satisfaction.

[1422] A "generative model" is a mathematical model that predicts the properties of materials and generates designs for new materials based on that information.

[1423] "Properties" are the physical and economic attributes of a material, such as strength, durability, sustainability, and cost.

[1424] A "blueprint" is a drawing or diagram that visually shows the composition and manufacturing method of a new material.

[1425] An "emotion engine" is a technology that analyzes a user's voice and facial expressions and recognizes the user's emotions based on the results.

[1426] "Detection" is the act of using an emotion engine to understand and identify a user's emotion.

[1427] "Tuning" is the process of modifying and optimizing material design parameters based on detected user emotions.

[1428] A "smart device" is an advanced device that is equipped with internet and communication functions and can interactively exchange information with users.

[1429] "Real-time" refers to a method of time management that minimizes delays and provides updated and immediate information and data.

[1430] A "user" is someone who uses a system or device to obtain and evaluate information about new material designs.

[1431] MODE FOR CARRYING OUT THE INVENTION

[1432] To implement the present invention, the following system configuration and procedures are required.

[1433] System Configuration

[1434] 1. Server:

[1435] The server maintains a generative model and an emotion engine. The generative model contains algorithms for predicting the properties of the generated new material. The emotion engine has the function of recognizing the user's emotions by analyzing voice data and facial expression data.

[1436] 2. Smart Devices:

[1437] Smart glasses and other interactive devices are used, which are equipped with cameras and microphones to capture the user's facial expressions and voice in real time, and the captured data is sent to a server.

[1438] Data processing and calculation

[1439] 1. Facial and Emotion Recognition:

[1440] The camera on the smart device captures the user's facial expressions, and OpenCV is used to detect specific facial features (eyes, mouth, eyebrows, etc.). The detected facial data is input into a facial emotion model built with Keras and analyzed by the emotion engine. Audio data captured by the microphone is also input into the emotion engine.

[1441] 2. Prediction of material properties:

[1442] The user's emotional information obtained by the emotion engine is sent to the server and input into the generative model algorithm, which then generates a blueprint for a new material, taking into account the material's strength, durability, sustainability, cost, and other characteristics along with the emotional information.

[1443] 3. View blueprints:

[1444] The generated blueprints are displayed in real time on the smart device screen, allowing users to select the optimal material design based on this information.

[1445] Specific examples

[1446] For example, if a user wants to design a new lightweight, strong material, and the smart glasses detect the emotion of "excitement" from the user's facial expression, the generated material design will be based on the emotion and will be lightweight and strong.

[1447] Example prompt sentence:

[1448] Based on the user's desired design, generate a material design that corresponds to the user's emotion of "excitement."

[1449] This invention makes it possible to quickly provide an optimal material design that corresponds to the user's emotions, thereby significantly improving work efficiency and satisfaction.

[1450] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1451] Step 1:

[1452] A smart device (such as smart glasses) is worn by a user and uses a camera and microphone to capture the user's facial expressions and voice data, which serve as input data for recognizing the user's emotions.

[1453] Step 2:

[1454] The smart device sends the captured facial expression data to the server, which uses a facial recognition algorithm (OpenCV) to detect specific facial features (eyes, mouth, eyebrows, etc.) and inputs this data into the emotion engine.

[1455] Step 3:

[1456] The server's emotion engine analyzes the facial recognition data and voice data to identify the user's emotions. This process uses an emotion recognition model using Keras. The analysis results in the user's emotions (e.g., "excitement" or "satisfaction").

[1457] Step 4:

[1458] The server inputs the identified user's emotional information into a generative model to predict the properties (strength, durability, sustainability, cost, etc.) of the new material. The generative model adjusts the material properties based on the emotional information to generate an optimal design.

[1459] Step 5:

[1460] The server stores a list of blueprints of new materials generated by the generative model, including predicted properties and adjustments based on emotional information.

[1461] Step 6:

[1462] The server sends the generated blueprint to the smart device, where the blueprint information is displayed in real time on the smart device's display. The user can check this information and proceed with the work as appropriate.

[1463] As a specific example of operation, if a user requests a new lightweight, strong material and the smart glasses detect the emotion of "excitement," the server will generate a lightweight, strong material design in response to the "excitement" and display the design on the smart glasses' display.

[1464] Through this series of processes, the optimal material design based on the user's feelings is quickly provided, which significantly improves work efficiency and user satisfaction.

[1465] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1466] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1467] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1468] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1469] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1470] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1471] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1472] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1473] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1474] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1475] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1476] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1477] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1478] 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.

[1479] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1480] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1481] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1482] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1483] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1484] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1485] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1486] The following is further disclosed regarding the above embodiment.

[1487] (Claim 1)

[1488] a means of predicting properties of new materials using generative models;

[1489] means for generating a design of a new material based on the generative model;

[1490] means for providing the generated design drawing to a user;

[1491] A system including:

[1492] (Claim 2)

[1493] 10. The system of claim 1, wherein the generative model predicts material strength, durability, sustainability, and cost characteristics.

[1494] (Claim 3)

[1495] 10. The system of claim 1, wherein the generative model includes an algorithm that determines material properties using random numbers.

[1496] "Example 1"

[1497] (Claim 1)

[1498] a means of predicting properties of new materials using generative models;

[1499] means for generating a design of a new material based on the generative model;

[1500] means for providing the generated design drawing to a user;

[1501] A server receives a user request and generates a specified number of material designs;

[1502] A means for the server to store the generated design drawings as a list and provide the list to the user;

[1503] A system including:

[1504] (Claim 2)

[1505] 10. The system of claim 1, wherein the generative model predicts material strength, durability, sustainability, and cost characteristics.

[1506] (Claim 3)

[1507] The system of claim 1, wherein the generative model includes an algorithm that determines material properties using random numbers, and the server initializes and maintains the generative model.

[1508] "Application Example 1"

[1509] (Claim 1)

[1510] a means of predicting properties of new materials using generative models;

[1511] means for generating a design of a new material based on the generative model;

[1512] means for providing the generated design drawing to a user;

[1513] means for receiving a material property request from a user;

[1514] a means for proposing an optimal material selection based on the generated design drawing;

[1515] a means for optimizing the manufacturing process based on the proposed material design;

[1516] A system including:

[1517] (Claim 2)

[1518] 10. The system of claim 1, wherein the generative model predicts material strength, durability, sustainability, and cost characteristics.

[1519] (Claim 3)

[1520] 10. The system of claim 1, wherein the generative model includes an algorithm that determines material properties using random numbers.

[1521] "Example 2: Combining Emotion Engines"

[1522] (Claim 1)

[1523] a means of predicting properties of new materials using generative models;

[1524] means for generating a design of a new material based on the generative model;

[1525] A means for analyzing a user's emotions using emotion recognition technology;

[1526] a means for adjusting a material design based on the analysis results;

[1527] means for providing the generated design drawing to a user;

[1528] A system including:

[1529] (Claim 2)

[1530] 10. The system of claim 1, wherein the generative model predicts material strength, durability, sustainability, and cost characteristics.

[1531] (Claim 3)

[1532] 10. The system of claim 1, wherein the generative model includes means for generating a specified number of material designs.

[1533] "Application example 2 when combining emotion engines"

[1534] (Claim 1)

[1535] a means of predicting properties of new materials using generative models;

[1536] means for generating a design of a new material based on the generative model;

[1537] means for detecting a user's emotions using an emotion engine that recognizes emotions based on the user's voice and facial expressions;

[1538] means for adjusting a material design based on the detected emotion;

[1539] A means for providing the generated design drawing to a user in real time via a smart device;

[1540] A system including:

[1541] (Claim 2)

[1542] 10. The system of claim 1, wherein the generative model predicts strength, durability, sustainability, and cost characteristics of new materials and further adjusts these characteristics based on user sentiment.

[1543] (Claim 3)

[1544] 2. The system of claim 1, wherein the generative model includes an algorithm that uses random numbers as material characteristics and an algorithm that uses emotional information detected from the user's voice and facial expressions. [Explanation of symbols]

[1545] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of predicting properties of new materials using generative models; means for generating a design of a new material based on the generative model; means for providing the generated design drawing to a user; A system including:

2. 10. The system of claim 1, wherein the generative model predicts strength, durability, sustainability, and cost properties of a material.

3. 10. The system of claim 1, wherein the generative model includes an algorithm that uses random numbers to determine material properties.

Images