system

Abstract

We provide the system. [Solution] A natural language processing system for receiving design requirements from users and analyzing those requirements, A generative model means for generating an initial design proposal based on the analyzed requirements, A user interface for reviewing the generated design proposal and receiving feedback, An integrated optimization method for optimizing design proposals based on feedback, A simulation testing method for evaluating the optimized design, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern product development, since internal design and exterior design are generally carried out separately, there is a problem that a gap occurs between functionality and aesthetics, and the overall quality of the product is impaired. As a result, users are forced to compromise either on functionality or design, which leads to a decrease in user satisfaction.

Means for Solving the Problems

[0005] This invention includes means for receiving design requirements from a user and analyzing those requirements using natural language processing technology. It also includes a generative model means for generating an initial design proposal that simultaneously considers internal and external design based on this analysis. Furthermore, it includes an integrated optimization means for receiving feedback from the user on the generated design proposal and optimizing the design proposal based on that feedback. By providing a simulation testing means to evaluate the reliability and quality of the optimized design, it is possible to realize product development with harmonious internal and external design and improve user satisfaction.

[0006] "Receiving design requirements from users" is the process of obtaining user preferences regarding the product's functions and design.

[0007] "Natural language processing means" refers to technologies that analyze text information entered by a user and understand it as structured data.

[0008] "Generative modeling means" refers to algorithms and methods that automatically generate internal and external designs based on analyzed design requirements.

[0009] "User interface means" refers to the platform and interaction mechanisms that allow users to review design proposals and provide feedback.

[0010] "Integrated optimization methods" refer to methodologies and processes that adjust the functionality and aesthetics of generated design proposals, while incorporating user feedback, to achieve a balanced state.

[0011] "Simulation testing methods" refer to technologies and methods for virtually verifying the operation of generated design proposals in order to confirm their reliability and quality. [Brief explanation of the drawing]

[0012] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention relates to a system for efficiently designing products that combine functionality and aesthetics by integrating internal and external design in product development. This system operates in an environment that includes servers, terminals, and users.

[0034] The server first receives product design requirements from the user via a terminal. The user can input detailed information about the functions and design features required for the product. The server then uses natural language processing technology to analyze the received design requirements. Based on this analysis, the server generates an initial design proposal that considers both internal and external design. This generation process involves searching through a vast amount of existing design data using machine learning and generative models.

[0035] The generated design proposal is sent to the user's device, where the user can review it in detail. The user then provides feedback on the design proposal via their device. This feedback can include specific functional improvements or changes to design preferences.

[0036] The server receives user feedback and initiates an integrated optimization process. Through this integrated optimization process, the server incorporates the feedback and readjusts the design proposal. During this process, the server creates virtual prototypes of the design and uses simulations to verify the reliability and quality of the design proposal.

[0037] As a concrete example, consider a smartwatch design project. The user desires a stylish design with specific health management functions, which they specify on their device. The server generates an initial smartwatch design proposal based on this and presents it to the user. Subsequently, based on the user's feedback, the design's colors, shapes, and function placement are re-evaluated, and the server generates an optimized final design proposal. Through this process, a smartwatch that combines the user's desired functions and style is designed.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user uses a terminal to input the design requirements for the product. These requirements include the type of product, necessary functions, and design preferences.

[0041] Step 2:

[0042] The terminal sends user input data to the server. The transmitted data includes requirements information written in natural language.

[0043] Step 3:

[0044] The server uses natural language processing techniques to analyze the received data. This extracts key requirements and specific design conditions, which are then processed as structured data.

[0045] Step 4:

[0046] Based on the analysis results, the server generates initial design proposals using a generative model. This process includes algorithms that reference information from a large number of existing databases and select the design best suited to the analyzed requirements.

[0047] Step 5:

[0048] The server sends the generated design proposal to the terminal. The terminal displays the received design proposal to the user, who then reviews the details.

[0049] Step 6:

[0050] Users input feedback on the design proposal via their device. This feedback includes specific comments on areas for design improvement and desired additional features.

[0051] Step 7:

[0052] The device sends user feedback to the server. The server receives the feedback and uses it to further refine the design.

[0053] Step 8:

[0054] Based on feedback, the server refines its design using integrated optimization techniques. Necessary modifications are made to achieve a balance between internal and external design.

[0055] Step 9:

[0056] The server will create virtual prototypes of the improved design proposals and verify their reliability and performance through simulations.

[0057] Step 10:

[0058] The server sends the final, refined design to the terminal for user review. The design approved by the user becomes the final product design.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] The present invention aims to accurately understand user requirements during the product design process, generate design proposals that efficiently and effectively meet those requirements, and provide an optimal design that incorporates user feedback. This aims to achieve a rapid design process while balancing functionality and aesthetics in product development.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes language processing means for receiving and analyzing requirements from a user, generation means for generating design proposals based on the analyzed requirements, and interface means for presenting the generated design proposals and receiving feedback. This makes it possible to generate and optimize design proposals that accurately reflect the user's requirements.

[0064] A "user" is the entity that provides the design requirements for a product and gives feedback on the design proposal.

[0065] "Requirements" refer to information that includes specific preferences regarding the functions and design that users expect from a product.

[0066] "Language processing means" refers to techniques used to analyze requirements received from users, and includes natural language processing.

[0067] "Generation means" refers to the technology used to create an initial design proposal based on the analyzed requirements, and includes generative AI models.

[0068] An "interface means" is a system function that presents the generated design proposal to the user and receives feedback.

[0069] "Optimization methods" refer to the process of improving design proposals based on user feedback to arrive at the optimal design.

[0070] "Testing methods" refer to techniques used to verify the reliability and quality of an optimized design.

[0071] This invention can be implemented as a system in the product development process that efficiently analyzes user design requirements and generates and proposes optimized design options. This system operates in an environment that includes servers, terminals, and users.

[0072] The server first receives product design requirements from the user via a terminal. The user uses the terminal to input detailed information about the functions and design features required for the product. In this process, the terminal functions as a means of transferring the design requirements entered by the user to the server.

[0073] The server analyzes the received design requirements using natural language processing techniques through language processing tools. This analysis extracts the user's requirements as structured data. Natural language processing (NLP) libraries may be used for this purpose. Based on the information extracted through this analysis, the server creates design proposals using generation tools. Generative AI models and machine learning frameworks (e.g., TENSORFLOW® and PyTorch) are used to generate designs that meet the requirements from a vast design database.

[0074] The generated design proposal is sent to the terminal via an interface and reviewed by the user. At this stage, the user can submit feedback on the design proposal through the terminal.

[0075] Upon receiving this feedback, the server improves the design proposal using optimization techniques. Specifically, the design proposal is adjusted based on the feedback, and the reliability and quality of the design are verified through simulation using testing methods.

[0076] As a concrete example, let's consider a smartwatch design project. The user desires a stylish design that includes specific health management functions, and specifies this on their device. The server generates an initial smartwatch design proposal based on this and presents it to the user. Subsequently, based on the user's feedback, the design's colors, shapes, and function placement are re-evaluated, and the server generates an optimized final design proposal.

[0077] An example of a prompt message is: "Generate design proposals for a smartwatch with new health management features. The designs should have modern and stylish elements."

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user inputs product design requirements through a terminal. The input is in the form of a detailed description of the specific functions (e.g., health management functions) and design features (e.g., a stylish appearance) desired for the product. The terminal plays the role of preparing the initial data of these requirements, which will then be sent to the server. At this stage, the input represents the user's requirements, and the output is the transmission of data to the server.

[0081] Step 2:

[0082] The server receives requirements data sent from the terminal and performs natural language processing using language processing tools. Specifically, it uses natural language processing (NLP) techniques to convert the received text data into structured data. This allows each element of the requirements to be analyzed, and the information necessary for the internal and external design of the product is extracted. The input for this step is the user's requirements data, and the output is structured data as a result of the analysis.

[0083] Step 3:

[0084] The server generates initial design proposals using a generation method based on the analyzed structured data. Here, a generative AI model is utilized, and a machine learning framework (e.g., TensorFlow or PyTorch) is used to create design proposals that meet the requirements from a vast amount of existing design data. In this step, structured data is used as input, and the output is the generated design proposal.

[0085] Step 4:

[0086] The server sends the generated design proposal to the terminal for the user to review. The user can then review the presented design proposal in detail on the terminal. After reviewing, the user provides feedback. This feedback may include suggestions for feature improvements or requests for design changes. In this step, the input is a request for review of the generated design proposal, and the output is the user's feedback.

[0087] Step 5:

[0088] The server readjusts the design proposal using optimization techniques based on feedback received from the user. While analyzing the feedback and making necessary design changes, the server utilizes virtual prototyping and simulation technologies to verify the reliability and quality of the design. An optimized design proposal is then obtained. The input for this step is user feedback, and the output is the optimized design proposal.

[0089] Step 6:

[0090] The server sends the optimized final design to the terminal for final confirmation. The user reviews the final design on the terminal and requests further adjustments if necessary. In this final step, the input is the presentation of the optimized design, and the output is final confirmation or provision of further feedback.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] In modern product development, efficiently designing and proposing customized products that meet diverse user needs is challenging. Traditional systems require cumbersome adjustments between internal and external design, and efficient means of incorporating feedback sequentially are limited. Furthermore, there is a growing demand for immediate and flexible proposals using smart devices.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes a natural language processing means for receiving design specifications from a user and analyzing the specifications, a generative modeling means for generating an initial design proposal based on the analyzed specifications, and an adaptive presentation means for customizing and proposing the design proposal according to the user's requirements. This enables the efficient design and proposal of customized products that meet the diverse needs of users.

[0096] "Design specifications" refer to a set of detailed requirements regarding the internal structure and external design of a product, based on user requirements.

[0097] "Natural language processing means" refers to technologies that analyze language data provided by users and extract meaning to understand design specifications.

[0098] "Generative model means" refers to algorithms and processes for automatically generating initial product designs based on analyzed design specifications.

[0099] "User interaction means" refers to an interface that allows users to review generated design proposals and provide opinions and feedback.

[0100] An "integrated optimization method" is an integrated process for generating the optimal product design by adjusting the design based on feedback from users.

[0101] A "simulation evaluation method" is a technique for conducting virtual tests to evaluate the reliability and functionality of an optimized design.

[0102] "Adaptive presentation means" refers to a technology that customizes design proposals according to the user's specific requirements and dynamically presents the proposed content.

[0103] A "generative model" is a predictive model and algorithm used to create new design proposals based on a large amount of past design data.

[0104] This embodiment of the invention is a system for rapidly designing customized products that reflect the diverse requirements of users. The server receives product design specifications from the user via a terminal and analyzes these specifications using natural language processing. This makes it possible to understand the user's requirements in detail.

[0105] Based on the analyzed results, the server generates initial design proposals using a generative model. The generative model employs machine learning frameworks such as TensorFlow and PyTorch, and utilizes a prediction algorithm trained on large-scale design data. These design proposals are presented to the user via user interaction, allowing the user to review them and provide feedback through their terminal.

[0106] Upon receiving feedback, the server modifies and optimizes the design proposal using integrated optimization tools and verifies the reliability of the design using simulation evaluation tools. For example, it virtually tests whether the design proposal meets the required functions and conforms to safety standards. Simulation tools from Google Cloud and AWS are often used for evaluation at this stage.

[0107] For example, if a user enters "I want a red, rounded soap dispenser" into an online shopping site, the server analyzes this request and generates appropriate design proposals. The server then presents these proposals to the user, and if the user provides feedback such as "I want it to be smaller," the design is adjusted again and an optimized proposal is presented. This process allows users to freely choose a customized product.

[0108] Examples of prompts for the generating AI model include specific requirements such as, "Choose an exterior design for the dispenser. Consider red color, a rounded form, and improved storage capacity."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The user uses a terminal to input product design specifications (e.g., "I want a red, rounded soap dispenser"). The terminal sends this input data to the server. At this stage, the input is the user's request, and the output is the data transfer to the server.

[0112] Step 2:

[0113] The server analyzes the user's design specifications received using natural language processing. This process uses the Google Cloud Natural Language API to analyze the input text data and extract key intents and elements. The output is structured data, which is then passed on to the next generation step.

[0114] Step 3:

[0115] The server generates initial design proposals using a generative model based on the analyzed structured data. Here, a generative AI model using TensorFlow is employed, and a prediction algorithm operates based on existing design data. The output is the initial design proposal, which is then sent to the terminal.

[0116] Step 4:

[0117] The terminal presents the received initial design proposal to the user. The user reviews it and inputs their feedback (e.g., "I want it to be smaller") into the terminal. This input is user feedback, and the output is the transmission of feedback data to the server.

[0118] Step 5:

[0119] The server readjusts the design proposal based on user feedback received through an integrated optimization mechanism. This process uses an adaptive learning algorithm to optimize the design while incorporating the feedback. The output is the revised design proposal, which then proceeds to verification using a simulation evaluation mechanism.

[0120] Step 6:

[0121] The server verifies the reliability and quality of the revised design proposal using simulation evaluation tools. It virtually checks whether the design meets the specified requirements using simulation tools from AWS or Google Cloud. The output is feedback data, including the final evaluation.

[0122] Step 7:

[0123] The server sends a final design proposal, incorporating the evaluation results, to the terminal for the user to view. The user can review the final design and repeat the process of submitting further adjustment requests as needed. The output of this step is the final design proposal, and the project is completed based on the user's decision.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention relates to a system for recognizing user emotions and incorporating feedback corresponding to those emotions into the product design optimization process. This system operates in an environment that includes a server, terminals, and users.

[0126] The server first receives the requirements for product design from the user via a terminal. The user can input detailed information about the product type, required functions, and design preferences. The terminal sends this information to the server. The server analyzes the received design requirements using natural language processing technology and generates initial design proposals using a generative model based on this analysis.

[0127] The generated design proposals are sent from the server to the user's device, where they can view the details and input their reactions and emotions as feedback. During this process, an emotion engine operates on the device, analyzing the user's facial expressions and voice to recognize their emotions. For example, various emotional states such as smiles, expressions of surprise, and expressions of disinterest are analyzed.

[0128] The server receives feedback and sentiment data transmitted from the terminal and adjusts the design proposal through an integrated optimization mechanism. The data obtained by the sentiment engine is used to adjust design elements that should be particularly emphasized in the optimization process. The server performs sentiment-based adaptive learning to improve the design.

[0129] As a concrete example, consider a scenario where a user is considering the design of a smartphone. The user inputs their preferences regarding a specific screen size and camera performance. The server generates and presents initial design proposals, but at this time, the device analyzes the user's facial expressions and communicates to the server, via an emotion engine, how satisfied the user is with the design or whether improvements are needed. For example, if the user shows interest, an instruction is sent to the server to emphasize that part of the design.

[0130] Through the above process, the present invention achieves optimization of product design that takes user emotions into account, enabling product development that is more closely aligned with user needs.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user inputs and submits specific design requirements for the product (such as product type, functions, and design preferences) via a terminal.

[0134] Step 2:

[0135] The terminal transfers the entered design requirements to the server. The data is written in natural language.

[0136] Step 3:

[0137] The server uses natural language processing technology to analyze the received requirements. As a result, it extracts the structured data necessary for product design.

[0138] Step 4:

[0139] Based on the analyzed data, the server generates an initial design proposal using a generative model. At this stage, it creates an integrated proposal that takes into account both the internal and external design.

[0140] Step 5:

[0141] The server sends the generated design proposal to the terminal and presents it to the user. The user then reviews the design proposal in detail on the terminal.

[0142] Step 6:

[0143] An emotion engine operates on the device to analyze the user's emotional state (facial expressions, voice, etc.). Emotional data is obtained when the user views the design proposal.

[0144] Step 7:

[0145] Users input their feedback on their device and send emotional data in response to it to the server. The feedback content and emotional state are treated together.

[0146] Step 8:

[0147] The server receives feedback and sentiment data to optimize the design proposal. It analyzes the sentiment data to identify design elements that should be particularly emphasized and areas for improvement.

[0148] Step 9:

[0149] The server will virtually prototype the improved design and verify its reliability and performance through simulation tests.

[0150] Step 10:

[0151] The server sends the final optimization results to the terminal. The user reviews the optimized design proposal on the terminal and makes a final approval.

[0152] (Example 2)

[0153] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0154] In traditional product design processes, it was difficult to take user emotions into account, making it challenging to efficiently deliver highly satisfying product designs. Furthermore, there was a lack of effective methods for incorporating user feedback into design optimization. This hindered product development that truly met user needs.

[0155] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0156] In this invention, the server includes language processing means for receiving and analyzing requests from users, modeling means for generating an initial design based on the analyzed requests, and emotion analysis means for recognizing the user's emotions during feedback. This makes it possible to optimize product design while taking user emotions into consideration.

[0157] "Language processing means" refers to methods for analyzing requests received from users and converting natural language into data that a computer can understand.

[0158] A "modeling tool" is a method or process for automatically generating an initial design based on analyzed requirements.

[0159] An "interface means" is a mechanism or medium for users to review the generated design and provide feedback.

[0160] "Emotion analysis methods" refer to the process of recognizing emotions during user feedback and determining the user's emotional state from their facial expressions and voice.

[0161] An "integrated optimization method" is a method for adjusting and optimizing a design based on collected feedback and emotional data.

[0162] "Verification testing methods" refer to processes for evaluating optimized designs and confirming their effectiveness and practicality.

[0163] "Adaptive learning methods" are learning methods that use user feedback and sentiment data to continuously improve designs.

[0164] This invention relates to a system for optimizing product design to reflect user emotions. This system operates in an environment that includes servers, terminals, and users.

[0165] The server first receives the requirements for product design from the user via a terminal. The user can input the product type, required functions, and design preferences through the terminal. The terminal sends this information to the server as digital data. The server analyzes this data using natural language processing technology. Specifically, a language processing engine is used to convert the requirements received from the user into structured data. The analyzed information is then sent to a generative AI model, which operates based on this data.

[0166] This generative AI model generates initial designs based on prompt input. For example, if a user inputs "screen size 6.5 inches, camera performance 48MP, design preference simple and modern style" on their device, the server receives this prompt as input and generates suitable design proposals through the AI ​​model. These generated proposals are sent to the device and presented to the user.

[0167] On the device, an emotion engine operates in response to the design proposals presented to the user, and a function is implemented to recognize emotions by analyzing the user's facial expressions and voice. For example, if the user smiles in response to a design, the device sends this information to the server as emotion data.

[0168] The server receives feedback and sentiment data from the terminal and adjusts the design proposal via an integrated optimization mechanism. This information is used to determine which parts of the design should be improved. Then, an adaptive learning mechanism learns from this data and further optimizes the design.

[0169] In this way, this invention enables the optimization of product design that takes user emotions into account, and realizes the development of products that are tailored to the needs of users.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] The user uses a terminal to input requirements regarding the product design. These requirements include the type of product, necessary functions, and design preferences. For example, they might enter specific requirements such as, "The screen size should be 6.5 inches, the camera performance 48MP, and a simple design is preferred."

[0173] Step 2:

[0174] The terminal sends the user's input request as digital data to the server. The input information is structured and transferred to the server. This allows the server to accurately receive the user's request and proceed with subsequent analysis.

[0175] Step 3:

[0176] The server analyzes the received data using natural language processing techniques. This process involves data processing that tokenizes, classifies, and extracts meaning from the input request. As a result, the analyzed request is output in a format that can be input into a generative AI model.

[0177] Step 4:

[0178] The server inputs the analyzed data into the generating AI model and generates an initial product design proposal. Based on the prompts, a design is generated according to the input requirements. In this process, design parameters are determined through data calculations, and a virtual design proposal is created.

[0179] Step 5:

[0180] The server sends the generated design proposal to the terminal. The terminal prepares to display this design proposal to the user and formats the data so that the user can visually confirm its contents.

[0181] Step 6:

[0182] The user reviews the design proposals presented on the device and provides feedback. The device collects the user's facial expressions and voice responses, which are then analyzed using an emotion engine. Specifically, facial expressions such as smiles and surprise are recorded as data and output as emotional states.

[0183] Step 7:

[0184] The device sends analyzed sentiment data and user feedback to the server. All collected information is transferred to the server as feedback data and sentiment data. This data is used for further analysis and design adjustments.

[0185] Step 8:

[0186] The server compares the received feedback with sentiment data and adjusts the design. An integrated optimization mechanism performs data calculations that reflect user sentiment and feedback, optimizing the new design proposal. The final output is an improved design.

[0187] Step 9:

[0188] The server performs adaptive learning and continuously analyzes data to improve the design. Based on the accumulated feedback, it learns more effective design strategies and incorporates them into future design proposal generation.

[0189] (Application Example 2)

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

[0191] The present invention aims to provide a system that can offer product suggestions that better match user preferences by incorporating user emotional feedback into product design. Furthermore, it aims to improve the accuracy of suggestions by analyzing user emotions in real time and immediately reflecting them in the design.

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

[0193] In this invention, the server includes a natural language processing means for receiving and analyzing design requirements from the user, a design generation means for generating initial design proposals based on the analysis results, and an emotion analysis means for analyzing the user's emotions and using them for feedback. This enables the optimization of designs based on the user's emotions and the suggestion of products that match their preferences.

[0194] "Natural language processing means" refers to technologies for analyzing design requirements received from users, where a computer understands human language and analyzes its meaning.

[0195] "Design generation means" refers to algorithms or models that automatically generate initial design proposals based on analyzed requirements.

[0196] "User information terminal means" refers to devices or systems that provide an interface for users to review designs and input feedback.

[0197] "Integrated optimization means" refers to the entire process of improving and optimizing design proposals based on the feedback received.

[0198] "Emotional analysis means" refers to technology for analyzing a user's emotions, and is a function that recognizes emotional states through facial expressions and voice.

[0199] "Product suggestion method" refers to a function that proposes appropriate product designs based on user feedback and sentiment data.

[0200] A "smart device" refers to any device that processes information interactively, such as a terminal that can detect and analyze a user's emotions in real time.

[0201] "Adaptive learning methods" are technologies that sequentially learn from user feedback and use that feedback to improve the overall design functions of the system.

[0202] This system enables a product design optimization process that leverages user sentiment analysis. Its main components include a server, smart devices (e.g., smart glasses), and a user interface.

[0203] First, the server receives design requirements from the user and analyzes them using natural language processing. This includes the elements the user wants in the design and their preferred specifications. Then, using a design generation system, it generates initial design proposals based on the received requirements. The generated proposals are presented to the user via a smart device.

[0204] Users can react to presented designs via their smart devices, and simultaneously, an emotion analysis system operates to collect emotional data from the user's facial expressions and voice. The emotional data collected in real time by the smart device is sent to a server and used by an integrated optimization system to optimize the design proposal. This process is then passed on to a product recommendation system, which provides optimal product recommendations based on the user's preferences.

[0205] As a concrete example, when a user wearing a smart device while shopping smiles upon seeing the design of a displayed product, that emotion is analyzed, and the server then suggests designs that are even closer to the user's preferences.

[0206] Example of a prompt

[0207] "The user is observing casual bags. They are showing a positive expression. Suggest the following design: casual, bright colors, and plenty of storage."

[0208] This system enables highly accurate product design proposals that take user emotions into account, which is expected to improve the user experience.

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] The server receives design requirements for product design from the user. This input includes the type of product, its functions, and design preferences. The server uses natural language processing to analyze these design requirements and translate the user's needs into specific design parameters. This process generates requirements data for input into a generative AI model.

[0212] Step 2:

[0213] Based on the analyzed requirements data, the server generates initial design proposals using a design generation mechanism. This generation process utilizes a generation AI model to create appropriate design proposals based on the requirements. These design proposals are then ready to be sent to the user via the user interface.

[0214] Step 3:

[0215] The user reviews the design proposals presented via their device. During this process, if a smart device is worn, the user's facial expressions and speech are captured in real time. This input data is used to identify the user's emotions through emotion analysis, and emotion data related to interest, satisfaction, etc., is generated.

[0216] Step 4:

[0217] The server integrates emotional data and feedback received from the terminal. An integration and optimization mechanism analyzes this data and adjusts and optimizes the design proposal. Specifically, design elements are emphasized or improved in response to positive or negative user reactions. This step yields an improved design proposal.

[0218] Step 5:

[0219] Based on the improved design proposals, specific product suggestions are generated for the user through a product suggestion system. These suggestions select the most suitable product based on the user's individual preferences. This further personalizes the user experience, leading to greater satisfaction.

[0220] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0236] This invention relates to a system for efficiently designing products that combine functionality and aesthetics by integrating internal and external design in product development. This system operates in an environment that includes servers, terminals, and users.

[0237] The server first receives product design requirements from the user via a terminal. The user can input detailed information about the functions and design features required for the product. The server then uses natural language processing technology to analyze the received design requirements. Based on this analysis, the server generates an initial design proposal that considers both internal and external design. This generation process involves searching through a vast amount of existing design data using machine learning and generative models.

[0238] The generated design proposal is sent to the user's device, where the user can review it in detail. The user then provides feedback on the design proposal via their device. This feedback can include specific functional improvements or changes to design preferences.

[0239] The server receives user feedback and initiates an integrated optimization process. Through this integrated optimization process, the server incorporates the feedback and readjusts the design proposal. During this process, the server creates virtual prototypes of the design and uses simulations to verify the reliability and quality of the design proposal.

[0240] As a concrete example, consider a smartwatch design project. The user desires a stylish design with specific health management functions, which they specify on their device. The server generates an initial smartwatch design proposal based on this and presents it to the user. Subsequently, based on the user's feedback, the design's colors, shapes, and function placement are re-evaluated, and the server generates an optimized final design proposal. Through this process, a smartwatch that combines the user's desired functions and style is designed.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The user uses a terminal to input the design requirements for the product. These requirements include the type of product, necessary functions, and design preferences.

[0244] Step 2:

[0245] The terminal sends user input data to the server. The transmitted data includes requirements information written in natural language.

[0246] Step 3:

[0247] The server uses natural language processing techniques to analyze the received data. This extracts key requirements and specific design conditions, which are then processed as structured data.

[0248] Step 4:

[0249] Based on the analysis results, the server generates initial design proposals using a generative model. This process includes algorithms that reference information from a large number of existing databases and select the design best suited to the analyzed requirements.

[0250] Step 5:

[0251] The server sends the generated design proposal to the terminal. The terminal displays the received design proposal to the user, who then reviews the details.

[0252] Step 6:

[0253] Users input feedback on the design proposal via their device. This feedback includes specific comments on areas for design improvement and desired additional features.

[0254] Step 7:

[0255] The device sends user feedback to the server. The server receives the feedback and uses it to further refine the design.

[0256] Step 8:

[0257] Based on feedback, the server refines its design using integrated optimization techniques. Necessary modifications are made to achieve a balance between internal and external design.

[0258] Step 9:

[0259] The server will create virtual prototypes of the improved design proposals and verify their reliability and performance through simulations.

[0260] Step 10:

[0261] The server sends the final, refined design to the terminal for user review. The design approved by the user becomes the final product design.

[0262] (Example 1)

[0263] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] The present invention aims to accurately understand user requirements during the product design process, generate design proposals that efficiently and effectively meet those requirements, and provide an optimal design that incorporates user feedback. This aims to achieve a rapid design process while balancing functionality and aesthetics in product development.

[0265] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0266] In this invention, the server includes language processing means for receiving and analyzing requirements from a user, generation means for generating design proposals based on the analyzed requirements, and interface means for presenting the generated design proposals and receiving feedback. This makes it possible to generate and optimize design proposals that accurately reflect the user's requirements.

[0267] A "user" is the entity that provides the design requirements for a product and gives feedback on the design proposal.

[0268] "Requirements" refer to information that includes specific preferences regarding the functions and design that users expect from a product.

[0269] "Language processing means" refers to techniques used to analyze requirements received from users, and includes natural language processing.

[0270] "Generation means" refers to the technology used to create an initial design proposal based on the analyzed requirements, and includes generative AI models.

[0271] An "interface means" is a system function that presents the generated design proposal to the user and receives feedback.

[0272] "Optimization methods" refer to the process of improving design proposals based on user feedback to arrive at the optimal design.

[0273] "Testing methods" refer to techniques used to verify the reliability and quality of an optimized design.

[0274] This invention can be implemented as a system in the product development process that efficiently analyzes user design requirements and generates and proposes optimized design options. This system operates in an environment that includes servers, terminals, and users.

[0275] The server first receives product design requirements from the user via a terminal. The user uses the terminal to input detailed information about the functions and design features required for the product. In this process, the terminal functions as a means of transferring the design requirements entered by the user to the server.

[0276] The server analyzes the received design requirements using natural language processing techniques through language processing tools. This analysis extracts the user's requirements as structured data. Natural language processing (NLP) libraries may be used for this. Based on the information extracted through this analysis, the server creates design proposals using generation tools. It utilizes generative AI models and machine learning frameworks (e.g., TensorFlow and PyTorch) to generate designs that meet the requirements from a vast design database.

[0277] The generated design proposal is sent to the terminal via an interface and reviewed by the user. At this stage, the user can submit feedback on the design proposal through the terminal.

[0278] Upon receiving this feedback, the server improves the design proposal using optimization techniques. Specifically, the design proposal is adjusted based on the feedback, and the reliability and quality of the design are verified through simulation using testing methods.

[0279] As a concrete example, let's consider a smartwatch design project. The user desires a stylish design that includes specific health management functions, and specifies this on their device. The server generates an initial smartwatch design proposal based on this and presents it to the user. Subsequently, based on the user's feedback, the design's colors, shapes, and function placement are re-evaluated, and the server generates an optimized final design proposal.

[0280] An example of a prompt message is: "Generate design proposals for a smartwatch with new health management features. The designs should have modern and stylish elements."

[0281] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0282] Step 1:

[0283] The user inputs the design requirements of the product through the terminal. The input is in a form that details the specific functions required for the product (e.g., health management function) and design features (e.g., stylish appearance). The terminal plays the role of preparing the initial data of the requirements by sending this input data to the server. The input at this stage is the user's requirements, and the output is the data transmission to the server.

[0284] Step 2:

[0285] The server receives the requirement data sent from the terminal and performs natural language processing using language processing means. Specifically, natural language processing (NLP) technology is used to convert the received text data into structured data. As a result, each element of the requirements is analyzed, and the information necessary for the internal design and exterior design of the product is extracted. The input of this step is the user's requirement data, and the output is the structured data as the analysis result.

[0286] Step 3:

[0287] Based on the analyzed structured data, the server uses generation means to generate an initial design proposal. Here, a generation AI model is utilized, and a machine learning framework (e.g., TensorFlow or PyTorch) is used to create a design proposal that meets the requirements from a vast amount of existing design data. In this step, structured data is used as the input, and the output is the generated design proposal.

[0288] Step 4:

[0289] The server sends the generated design proposal to the terminal for the user to confirm. The user can carefully check the design proposal presented on the terminal. After the user's confirmation, feedback is input. The feedback provided by the user includes suggestions for improving functions and desires for design changes. In this step, the input is the request for confirmation of the generated design proposal, and the output is the feedback from the user.

[0290] Step 5:

[0291] The server readjusts the design proposal using optimization techniques based on feedback received from the user. While analyzing the feedback and making necessary design changes, the server utilizes virtual prototyping and simulation technologies to verify the reliability and quality of the design. An optimized design proposal is then obtained. The input for this step is user feedback, and the output is the optimized design proposal.

[0292] Step 6:

[0293] The server sends the optimized final design to the terminal for final confirmation. The user reviews the final design on the terminal and requests further adjustments if necessary. In this final step, the input is the presentation of the optimized design, and the output is final confirmation or provision of further feedback.

[0294] (Application Example 1)

[0295] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0296] In modern product development, efficiently designing and proposing customized products that meet diverse user needs is challenging. Traditional systems require cumbersome adjustments between internal and external design, and efficient means of incorporating feedback sequentially are limited. Furthermore, there is a growing demand for immediate and flexible proposals using smart devices.

[0297] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0298] In this invention, the server includes a natural language processing means for receiving design specifications from a user and analyzing the specifications, a generative modeling means for generating an initial design proposal based on the analyzed specifications, and an adaptive presentation means for customizing and proposing the design proposal according to the user's requirements. This enables the efficient design and proposal of customized products that meet the diverse needs of users.

[0299] "Design specifications" refer to a set of detailed requirements regarding the internal structure and external design of a product, based on user requirements.

[0300] "Natural language processing means" refers to technologies that analyze language data provided by users and extract meaning to understand design specifications.

[0301] "Generative model means" refers to algorithms and processes for automatically generating initial product designs based on analyzed design specifications.

[0302] "User interaction means" refers to an interface that allows users to review generated design proposals and provide opinions and feedback.

[0303] An "integrated optimization method" is an integrated process for generating the optimal product design by adjusting the design based on feedback from users.

[0304] A "simulation evaluation method" is a technique for conducting virtual tests to evaluate the reliability and functionality of an optimized design.

[0305] "Adaptive presentation means" refers to a technology that customizes design proposals according to the user's specific requirements and dynamically presents the proposed content.

[0306] A "generative model" is a predictive model and algorithm used to create new design proposals based on a large amount of past design data.

[0307] Embodiments of this invention are systems for quickly performing customized product design that reflects diverse user requirements. The server receives product design specifications from the user via a terminal and analyzes the specifications using natural language processing means. This makes it possible to understand the user's requirements in detail.

[0308] Based on the analyzed results, the server uses generation model means to generate an initial design proposal. For the generation model, machine learning frameworks such as TensorFlow and PyTorch are used, and a prediction algorithm learned from a large amount of design data is employed. This design proposal is presented to the user by user operation means, and the user can confirm it through the terminal and provide feedback.

[0309] The server that receives the feedback modifies and optimizes the design proposal with integration optimization means and verifies the reliability of the design using simulation evaluation means. For example, it virtually tests whether the design proposal meets the required functions and conforms to safety standards. In the evaluation at this stage, simulation tools of Google Cloud or AWS are often utilized.

[0310] As a specific example, when a user inputs "want a red and round soap dispenser" on an e-commerce site, the server analyzes this request and generates an appropriate design proposal. The server presents the generated design proposal to the user. If the user provides feedback such as "want it to be smaller", the design is adjusted again and an optimized proposal is made. Through this process, the user can freely select a customized product.

[0311] Examples of prompt texts for the generation AI model include specific requirements such as "Select the exterior design of the dispenser. Consider red color, round form, and improved storage."

[0312] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0313] Step 1:

[0314] The user uses a terminal to input product design specifications (e.g., "I want a red, rounded soap dispenser"). The terminal sends this input data to the server. At this stage, the input is the user's request, and the output is the data transfer to the server.

[0315] Step 2:

[0316] The server analyzes the user's design specifications received using natural language processing. This process uses the Google Cloud Natural Language API to analyze the input text data and extract key intents and elements. The output is structured data, which is then passed on to the next generation step.

[0317] Step 3:

[0318] The server generates initial design proposals using a generative model based on the analyzed structured data. Here, a generative AI model using TensorFlow is employed, and a prediction algorithm operates based on existing design data. The output is the initial design proposal, which is then sent to the terminal.

[0319] Step 4:

[0320] The terminal presents the received initial design proposal to the user. The user reviews it and inputs their feedback (e.g., "I want it to be smaller") into the terminal. This input is user feedback, and the output is the transmission of feedback data to the server.

[0321] Step 5:

[0322] The server readjusts the design proposal based on user feedback received through an integrated optimization mechanism. This process uses an adaptive learning algorithm to optimize the design while incorporating the feedback. The output is the revised design proposal, which then proceeds to verification using a simulation evaluation mechanism.

[0323] Step 6:

[0324] The server verifies the reliability and quality of the revised design proposal using simulation evaluation tools. It virtually checks whether the design meets the specified requirements using simulation tools from AWS or Google Cloud. The output is feedback data, including the final evaluation.

[0325] Step 7:

[0326] The server sends a final design proposal, incorporating the evaluation results, to the terminal for the user to view. The user can review the final design and repeat the process of submitting further adjustment requests as needed. The output of this step is the final design proposal, and the project is completed based on the user's decision.

[0327] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0328] This invention relates to a system for recognizing user emotions and incorporating feedback corresponding to those emotions into the product design optimization process. This system operates in an environment that includes a server, terminals, and users.

[0329] The server first receives the requirements for product design from the user via a terminal. The user can input detailed information about the product type, required functions, and design preferences. The terminal sends this information to the server. The server analyzes the received design requirements using natural language processing technology and generates initial design proposals using a generative model based on this analysis.

[0330] The generated design proposals are sent from the server to the user's device, where they can view the details and input their reactions and emotions as feedback. During this process, an emotion engine operates on the device, analyzing the user's facial expressions and voice to recognize their emotions. For example, various emotional states such as smiles, expressions of surprise, and expressions of disinterest are analyzed.

[0331] The server receives feedback and sentiment data transmitted from the terminal and adjusts the design proposal through an integrated optimization mechanism. The data obtained by the sentiment engine is used to adjust design elements that should be particularly emphasized in the optimization process. The server performs sentiment-based adaptive learning to improve the design.

[0332] As a concrete example, consider a scenario where a user is considering the design of a smartphone. The user inputs their preferences regarding a specific screen size and camera performance. The server generates and presents initial design proposals, but at this time, the device analyzes the user's facial expressions and communicates to the server, via an emotion engine, how satisfied the user is with the design or whether improvements are needed. For example, if the user shows interest, an instruction is sent to the server to emphasize that part of the design.

[0333] Through the above process, the present invention achieves optimization of product design that takes user emotions into account, enabling product development that is more closely aligned with user needs.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] The user inputs and submits specific design requirements for the product (such as product type, functions, and design preferences) via a terminal.

[0337] Step 2:

[0338] The terminal transfers the entered design requirements to the server. The data is written in natural language.

[0339] Step 3:

[0340] The server uses natural language processing technology to analyze the received requirements. As a result, it extracts the structured data necessary for product design.

[0341] Step 4:

[0342] Based on the analyzed data, the server generates an initial design proposal using a generative model. At this stage, it creates an integrated proposal that takes into account both the internal and external design.

[0343] Step 5:

[0344] The server sends the generated design proposal to the terminal and presents it to the user. The user then reviews the design proposal in detail on the terminal.

[0345] Step 6:

[0346] An emotion engine operates on the device to analyze the user's emotional state (facial expressions, voice, etc.). Emotional data is obtained when the user views the design proposal.

[0347] Step 7:

[0348] Users input their feedback on their device and send emotional data in response to it to the server. The feedback content and emotional state are treated together.

[0349] Step 8:

[0350] The server receives feedback and sentiment data to optimize the design proposal. It analyzes the sentiment data to identify design elements that should be particularly emphasized and areas for improvement.

[0351] Step 9:

[0352] The server will virtually prototype the improved design and verify its reliability and performance through simulation tests.

[0353] Step 10:

[0354] The server sends the final optimization results to the terminal. The user reviews the optimized design proposal on the terminal and makes a final approval.

[0355] (Example 2)

[0356] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0357] In traditional product design processes, it was difficult to take user emotions into account, making it challenging to efficiently deliver highly satisfying product designs. Furthermore, there was a lack of effective methods for incorporating user feedback into design optimization. This hindered product development that truly met user needs.

[0358] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0359] In this invention, the server includes language processing means for receiving and analyzing requests from users, modeling means for generating an initial design based on the analyzed requests, and emotion analysis means for recognizing the user's emotions during feedback. This makes it possible to optimize product design while taking user emotions into consideration.

[0360] "Language processing means" refers to methods for analyzing requests received from users and converting natural language into data that a computer can understand.

[0361] A "modeling tool" is a method or process for automatically generating an initial design based on analyzed requirements.

[0362] An "interface means" is a mechanism or medium for users to review the generated design and provide feedback.

[0363] "Emotion analysis methods" refer to the process of recognizing emotions during user feedback and determining the user's emotional state from their facial expressions and voice.

[0364] An "integrated optimization method" is a method for adjusting and optimizing a design based on collected feedback and sentiment data.

[0365] "Verification testing methods" refer to processes for evaluating optimized designs and confirming their effectiveness and practicality.

[0366] "Adaptive learning methods" are learning methods that use user feedback and sentiment data to continuously improve designs.

[0367] This invention relates to a system for optimizing product design to reflect user emotions. This system operates in an environment that includes servers, terminals, and users.

[0368] The server first receives the requirements for product design from the user via a terminal. The user can input the product type, required functions, and design preferences through the terminal. The terminal sends this information to the server as digital data. The server analyzes this data using natural language processing technology. Specifically, a language processing engine is used to convert the requirements received from the user into structured data. The analyzed information is then sent to a generative AI model, which operates based on this data.

[0369] This generative AI model generates initial designs based on prompt input. For example, if a user inputs "screen size 6.5 inches, camera performance 48MP, design preference simple and modern style" on their device, the server receives this prompt as input and generates suitable design proposals through the AI ​​model. These generated proposals are sent to the device and presented to the user.

[0370] On the device, an emotion engine operates in response to the design proposals presented to the user, and a function is implemented to recognize emotions by analyzing the user's facial expressions and voice. For example, if the user smiles in response to a design, the device sends this information to the server as emotion data.

[0371] The server receives feedback and sentiment data from the terminal and adjusts the design proposal via an integrated optimization mechanism. This information is used to determine which parts of the design should be improved. Then, an adaptive learning mechanism learns from this data and further optimizes the design.

[0372] In this way, this invention enables the optimization of product design that takes user emotions into account, and realizes the development of products that are tailored to the needs of users.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The user uses a terminal to input requirements regarding the product design. These requirements include the type of product, necessary functions, and design preferences. For example, they might enter specific requirements such as, "The screen size should be 6.5 inches, the camera performance 48MP, and a simple design is preferred."

[0376] Step 2:

[0377] The terminal sends the user's input request as digital data to the server. The input information is structured and transferred to the server. This allows the server to accurately receive the user's request and proceed with subsequent analysis.

[0378] Step 3:

[0379] The server analyzes the received data using natural language processing techniques. This process involves data processing that tokenizes, classifies, and extracts meaning from the input request. As a result, the analyzed request is output in a format that can be input into a generative AI model.

[0380] Step 4:

[0381] The server inputs the analyzed data into the generating AI model and generates an initial product design proposal. Based on the prompts, a design is generated according to the input requirements. In this process, design parameters are determined through data calculations, and a virtual design proposal is created.

[0382] Step 5:

[0383] The server sends the generated design proposal to the terminal. The terminal prepares to display this design proposal to the user and formats the data so that the user can visually confirm its contents.

[0384] Step 6:

[0385] The user reviews the design proposals presented on the device and provides feedback. The device collects the user's facial expressions and voice responses, which are then analyzed using an emotion engine. Specifically, facial expressions such as smiles and surprise are recorded as data and output as emotional states.

[0386] Step 7:

[0387] The device sends analyzed sentiment data and user feedback to the server. All collected information is transferred to the server as feedback data and sentiment data. This data is used for further analysis and design adjustments.

[0388] Step 8:

[0389] The server compares the received feedback with sentiment data and adjusts the design. An integrated optimization mechanism performs data calculations that reflect user sentiment and feedback, optimizing the new design proposal. The final output is an improved design.

[0390] Step 9:

[0391] The server performs adaptive learning and continuously analyzes data to improve the design. Based on the accumulated feedback, it learns more effective design strategies and incorporates them into future design proposal generation.

[0392] (Application Example 2)

[0393] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0394] The present invention aims to provide a system that can offer product suggestions that better match user preferences by incorporating user emotional feedback into product design. Furthermore, it aims to improve the accuracy of suggestions by analyzing user emotions in real time and immediately reflecting them in the design.

[0395] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0396] In this invention, the server includes a natural language processing means for receiving and analyzing design requirements from the user, a design generation means for generating initial design proposals based on the analysis results, and an emotion analysis means for analyzing the user's emotions and using them for feedback. This enables the optimization of designs based on the user's emotions and the suggestion of products that match their preferences.

[0397] "Natural language processing means" refers to technologies for analyzing design requirements received from users, where a computer understands human language and analyzes its meaning.

[0398] "Design generation means" refers to algorithms or models that automatically generate initial design proposals based on analyzed requirements.

[0399] "User information terminal means" refers to devices or systems that provide an interface for users to review designs and input feedback.

[0400] "Integrated optimization means" refers to the entire process of improving and optimizing design proposals based on the feedback received.

[0401] "Emotional analysis means" refers to technology for analyzing a user's emotions, and is a function that recognizes emotional states through facial expressions and voice.

[0402] "Product suggestion method" refers to a function that proposes appropriate product designs based on user feedback and sentiment data.

[0403] A "smart device" refers to any device that processes information interactively, such as a terminal that can detect and analyze a user's emotions in real time.

[0404] "Adaptive learning methods" are technologies that sequentially learn from user feedback and use that feedback to improve the overall design functions of the system.

[0405] This system enables a product design optimization process that leverages user sentiment analysis. Its main components include a server, smart devices (e.g., smart glasses), and a user interface.

[0406] First, the server receives design requirements from the user and analyzes them using natural language processing. This includes the elements the user wants in the design and their preferred specifications. Then, using a design generation system, it generates initial design proposals based on the received requirements. The generated proposals are presented to the user via a smart device.

[0407] Users can react to presented designs via their smart devices, and simultaneously, an emotion analysis system operates to collect emotional data from the user's facial expressions and voice. The emotional data collected in real time by the smart device is sent to a server and used by an integrated optimization system to optimize the design proposal. This process is then passed on to a product recommendation system, which provides optimal product recommendations based on the user's preferences.

[0408] As a concrete example, when a user wearing a smart device while shopping smiles upon seeing the design of a displayed product, that emotion is analyzed, and the server then suggests designs that are even closer to the user's preferences.

[0409] Example of a prompt

[0410] "The user is observing casual bags. They are showing a positive expression. Suggest the following design: casual, bright colors, and plenty of storage."

[0411] This system enables highly accurate product design proposals that take user emotions into account, which is expected to improve the user experience.

[0412] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0413] Step 1:

[0414] The server receives design requirements for product design from the user. This input includes the type of product, its functions, and design preferences. The server uses natural language processing to analyze these design requirements and translate the user's needs into specific design parameters. This process generates requirements data for input into a generative AI model.

[0415] Step 2:

[0416] Based on the analyzed requirements data, the server generates initial design proposals using a design generation mechanism. This generation process utilizes a generation AI model to create appropriate design proposals based on the requirements. These design proposals are then ready to be sent to the user via the user interface.

[0417] Step 3:

[0418] The user reviews the design proposals presented via their device. During this process, if a smart device is worn, the user's facial expressions and speech are captured in real time. This input data is used to identify the user's emotions through emotion analysis, and emotion data related to interest, satisfaction, etc., is generated.

[0419] Step 4:

[0420] The server integrates emotional data and feedback received from the terminal. An integration and optimization mechanism analyzes this data and adjusts and optimizes the design proposal. Specifically, design elements are emphasized or improved in response to positive or negative user reactions. This step yields an improved design proposal.

[0421] Step 5:

[0422] Based on the improved design proposals, specific product suggestions are generated for the user through a product suggestion system. These suggestions select the most suitable product based on the user's individual preferences. This further personalizes the user experience, leading to greater satisfaction.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0424] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0429] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0431] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0433] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0434] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0435] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0436] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0437] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0438] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0439] This invention relates to a system for efficiently designing products that combine functionality and aesthetics by integrating internal and external design in product development. This system operates in an environment that includes servers, terminals, and users.

[0440] The server first receives product design requirements from the user via a terminal. The user can input detailed information about the functions and design features required for the product. The server then uses natural language processing technology to analyze the received design requirements. Based on this analysis, the server generates an initial design proposal that considers both internal and external design. This generation process involves searching through a vast amount of existing design data using machine learning and generative models.

[0441] The generated design proposal is sent to the user's device, where the user can review it in detail. The user then provides feedback on the design proposal via their device. This feedback can include specific functional improvements or changes to design preferences.

[0442] The server receives user feedback and initiates an integrated optimization process. Through this integrated optimization process, the server incorporates the feedback and readjusts the design proposal. During this process, the server creates virtual prototypes of the design and uses simulations to verify the reliability and quality of the design proposal.

[0443] As a concrete example, consider a smartwatch design project. The user desires a stylish design with specific health management functions, which they specify on their device. The server generates an initial smartwatch design proposal based on this and presents it to the user. Subsequently, based on the user's feedback, the design's colors, shapes, and function placement are re-evaluated, and the server generates an optimized final design proposal. Through this process, a smartwatch that combines the user's desired functions and style is designed.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The user uses a terminal to input the design requirements for the product. These requirements include the type of product, necessary functions, and design preferences.

[0447] Step 2:

[0448] The terminal sends user input data to the server. The transmitted data includes requirements information written in natural language.

[0449] Step 3:

[0450] The server uses natural language processing techniques to analyze the received data. This extracts key requirements and specific design conditions, which are then processed as structured data.

[0451] Step 4:

[0452] Based on the analysis results, the server generates initial design proposals using a generative model. This process includes algorithms that reference information from a large number of existing databases and select the design best suited to the analyzed requirements.

[0453] Step 5:

[0454] The server sends the generated design proposal to the terminal. The terminal displays the received design proposal to the user, who then reviews the details.

[0455] Step 6:

[0456] Users input feedback on the design proposal via their device. This feedback includes specific comments on areas for design improvement and desired additional features.

[0457] Step 7:

[0458] The device sends user feedback to the server. The server receives the feedback and uses it to further refine the design.

[0459] Step 8:

[0460] Based on feedback, the server refines its design using integrated optimization techniques. Necessary modifications are made to achieve a balance between internal and external design.

[0461] Step 9:

[0462] The server will create virtual prototypes of the improved design proposals and verify their reliability and performance through simulations.

[0463] Step 10:

[0464] The server sends the final, refined design to the terminal for user review. The design approved by the user becomes the final product design.

[0465] (Example 1)

[0466] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0467] The present invention aims to accurately understand user requirements during the product design process, generate design proposals that efficiently and effectively meet those requirements, and provide an optimal design that incorporates user feedback. This aims to achieve a rapid design process while balancing functionality and aesthetics in product development.

[0468] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0469] In this invention, the server includes language processing means for receiving and analyzing requirements from a user, generation means for generating design proposals based on the analyzed requirements, and interface means for presenting the generated design proposals and receiving feedback. This makes it possible to generate and optimize design proposals that accurately reflect the user's requirements.

[0470] A "user" is the entity that provides the design requirements for a product and gives feedback on the design proposal.

[0471] "Requirements" refer to information that includes specific preferences regarding the functions and design that users expect from a product.

[0472] "Language processing means" refers to techniques used to analyze requirements received from users, and includes natural language processing.

[0473] "Generation means" refers to the technology used to create an initial design proposal based on the analyzed requirements, and includes generative AI models.

[0474] An "interface means" is a system function that presents the generated design proposal to the user and receives feedback.

[0475] "Optimization methods" refer to the process of improving design proposals based on user feedback to arrive at the optimal design.

[0476] "Testing methods" refer to techniques used to verify the reliability and quality of an optimized design.

[0477] This invention can be implemented as a system in the product development process that efficiently analyzes user design requirements and generates and proposes optimized design options. This system operates in an environment that includes servers, terminals, and users.

[0478] The server first receives product design requirements from the user via a terminal. The user uses the terminal to input detailed information about the functions and design features required for the product. In this process, the terminal functions as a means of transferring the design requirements entered by the user to the server.

[0479] The server analyzes the received design requirements using natural language processing techniques through language processing tools. This analysis extracts the user's requirements as structured data. Natural language processing (NLP) libraries may be used for this. Based on the information extracted through this analysis, the server creates design proposals using generation tools. It utilizes generative AI models and machine learning frameworks (e.g., TensorFlow and PyTorch) to generate designs that meet the requirements from a vast design database.

[0480] The generated design proposal is sent to the terminal via an interface and reviewed by the user. At this stage, the user can submit feedback on the design proposal through the terminal.

[0481] Upon receiving this feedback, the server improves the design proposal using optimization techniques. Specifically, the design proposal is adjusted based on the feedback, and the reliability and quality of the design are verified through simulation using testing methods.

[0482] As a concrete example, let's consider a smartwatch design project. The user desires a stylish design that includes specific health management functions, and specifies this on their device. The server generates an initial smartwatch design proposal based on this and presents it to the user. Subsequently, based on the user's feedback, the design's colors, shapes, and function placement are re-evaluated, and the server generates an optimized final design proposal.

[0483] An example of a prompt message is: "Generate design proposals for a smartwatch with new health management features. The designs should have modern and stylish elements."

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] The user inputs product design requirements through a terminal. The input is in the form of a detailed description of the specific functions (e.g., health management functions) and design features (e.g., a stylish appearance) desired for the product. The terminal plays the role of preparing the initial data of these requirements, which will then be sent to the server. At this stage, the input represents the user's requirements, and the output is the transmission of data to the server.

[0487] Step 2:

[0488] The server receives requirements data sent from the terminal and performs natural language processing using language processing tools. Specifically, it uses natural language processing (NLP) techniques to convert the received text data into structured data. This allows each element of the requirements to be analyzed, and the information necessary for the internal and external design of the product is extracted. The input for this step is the user's requirements data, and the output is structured data as a result of the analysis.

[0489] Step 3:

[0490] The server generates initial design proposals using a generation method based on the analyzed structured data. Here, a generative AI model is utilized, and a machine learning framework (e.g., TensorFlow or PyTorch) is used to create design proposals that meet the requirements from a vast amount of existing design data. In this step, structured data is used as input, and the output is the generated design proposal.

[0491] Step 4:

[0492] The server sends the generated design proposal to the terminal for the user to review. The user can then review the presented design proposal in detail on the terminal. After reviewing, the user provides feedback. This feedback may include suggestions for feature improvements or requests for design changes. In this step, the input is a request for review of the generated design proposal, and the output is the user's feedback.

[0493] Step 5:

[0494] The server readjusts the design proposal using optimization techniques based on feedback received from the user. While analyzing the feedback and making necessary design changes, the server utilizes virtual prototyping and simulation technologies to verify the reliability and quality of the design. An optimized design proposal is then obtained. The input for this step is user feedback, and the output is the optimized design proposal.

[0495] Step 6:

[0496] The server sends the optimized final design to the terminal for final confirmation. The user reviews the final design on the terminal and requests further adjustments if necessary. In this final step, the input is the presentation of the optimized design, and the output is final confirmation or provision of further feedback.

[0497] (Application Example 1)

[0498] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0499] In modern product development, efficiently designing and proposing customized products that meet diverse user needs is challenging. Traditional systems require cumbersome adjustments between internal and external design, and efficient means of incorporating feedback sequentially are limited. Furthermore, there is a growing demand for immediate and flexible proposals using smart devices.

[0500] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0501] In this invention, the server includes a natural language processing means for receiving design specifications from a user and analyzing the specifications, a generative modeling means for generating an initial design proposal based on the analyzed specifications, and an adaptive presentation means for customizing and proposing the design proposal according to the user's requirements. This enables the efficient design and proposal of customized products that meet the diverse needs of users.

[0502] "Design specifications" refer to a set of detailed requirements regarding the internal structure and external design of a product, based on user requirements.

[0503] "Natural language processing means" refers to technologies that analyze language data provided by users and extract meaning to understand design specifications.

[0504] "Generative model means" refers to algorithms and processes for automatically generating initial product designs based on analyzed design specifications.

[0505] "User interaction means" refers to an interface that allows users to review generated design proposals and provide opinions and feedback.

[0506] An "integrated optimization method" is an integrated process for generating the optimal product design by adjusting the design based on feedback from users.

[0507] A "simulation evaluation method" is a technique for conducting virtual tests to evaluate the reliability and functionality of an optimized design.

[0508] "Adaptive presentation means" refers to a technology that customizes design proposals according to the user's specific requirements and dynamically presents the proposed content.

[0509] A "generative model" is a predictive model and algorithm used to create new design proposals based on a large amount of past design data.

[0510] This embodiment of the invention is a system for rapidly designing customized products that reflect the diverse requirements of users. The server receives product design specifications from the user via a terminal and analyzes these specifications using natural language processing. This makes it possible to understand the user's requirements in detail.

[0511] Based on the analyzed results, the server generates initial design proposals using a generative model. The generative model employs machine learning frameworks such as TensorFlow and PyTorch, and utilizes a prediction algorithm trained on large-scale design data. These design proposals are presented to the user via user interaction, allowing the user to review them and provide feedback through their terminal.

[0512] Upon receiving feedback, the server modifies and optimizes the design proposal using integrated optimization tools and verifies the reliability of the design using simulation evaluation tools. For example, it virtually tests whether the design proposal meets the required functions and conforms to safety standards. Simulation tools from Google Cloud and AWS are often used for evaluation at this stage.

[0513] For example, if a user enters "I want a red, rounded soap dispenser" into an online shopping site, the server analyzes this request and generates appropriate design proposals. The server then presents these proposals to the user, and if the user provides feedback such as "I want it to be smaller," the design is adjusted again and an optimized proposal is presented. This process allows users to freely choose a customized product.

[0514] Examples of prompts for the generating AI model include specific requirements such as, "Choose an exterior design for the dispenser. Consider red color, a rounded form, and improved storage capacity."

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The user uses a terminal to input product design specifications (e.g., "I want a red, rounded soap dispenser"). The terminal sends this input data to the server. At this stage, the input is the user's request, and the output is the data transfer to the server.

[0518] Step 2:

[0519] The server analyzes the user's design specifications received using natural language processing. This process uses the Google Cloud Natural Language API to analyze the input text data and extract key intents and elements. The output is structured data, which is then passed on to the next generation step.

[0520] Step 3:

[0521] The server generates initial design proposals using a generative model based on the analyzed structured data. Here, a generative AI model using TensorFlow is employed, and a prediction algorithm operates based on existing design data. The output is the initial design proposal, which is then sent to the terminal.

[0522] Step 4:

[0523] The terminal presents the received initial design proposal to the user. The user reviews it and inputs their feedback (e.g., "I want it to be smaller") into the terminal. This input is user feedback, and the output is the transmission of feedback data to the server.

[0524] Step 5:

[0525] The server readjusts the design proposal based on user feedback received through an integrated optimization mechanism. This process uses an adaptive learning algorithm to optimize the design while incorporating the feedback. The output is the revised design proposal, which then proceeds to verification using a simulation evaluation mechanism.

[0526] Step 6:

[0527] The server verifies the reliability and quality of the revised design proposal using simulation evaluation tools. It virtually checks whether the design meets the specified requirements using simulation tools from AWS or Google Cloud. The output is feedback data, including the final evaluation.

[0528] Step 7:

[0529] The server sends a final design proposal, incorporating the evaluation results, to the terminal for the user to view. The user can review the final design and repeat the process of submitting further adjustment requests as needed. The output of this step is the final design proposal, and the project is completed based on the user's decision.

[0530] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0531] This invention relates to a system for recognizing user emotions and incorporating feedback corresponding to those emotions into the product design optimization process. This system operates in an environment that includes a server, terminals, and users.

[0532] The server first receives the requirements for product design from the user via a terminal. The user can input detailed information about the product type, required functions, and design preferences. The terminal sends this information to the server. The server analyzes the received design requirements using natural language processing technology and generates initial design proposals using a generative model based on this analysis.

[0533] The generated design proposals are sent from the server to the user's device, where they can view the details and input their reactions and emotions as feedback. During this process, an emotion engine operates on the device, analyzing the user's facial expressions and voice to recognize their emotions. For example, various emotional states such as smiles, expressions of surprise, and expressions of disinterest are analyzed.

[0534] The server receives feedback and sentiment data transmitted from the terminal and adjusts the design proposal through an integrated optimization mechanism. The data obtained by the sentiment engine is used to adjust design elements that should be particularly emphasized in the optimization process. The server performs sentiment-based adaptive learning to improve the design.

[0535] As a concrete example, consider a scenario where a user is considering the design of a smartphone. The user inputs their preferences regarding a specific screen size and camera performance. The server generates and presents initial design proposals, but at this time, the device analyzes the user's facial expressions and communicates to the server, via an emotion engine, how satisfied the user is with the design or whether improvements are needed. For example, if the user shows interest, an instruction is sent to the server to emphasize that part of the design.

[0536] Through the above process, the present invention achieves optimization of product design that takes user emotions into account, enabling product development that is more closely aligned with user needs.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The user inputs and submits specific design requirements for the product (such as product type, functions, and design preferences) via a terminal.

[0540] Step 2:

[0541] The terminal transfers the entered design requirements to the server. The data is written in natural language.

[0542] Step 3:

[0543] The server uses natural language processing technology to analyze the received requirements. As a result, it extracts the structured data necessary for product design.

[0544] Step 4:

[0545] Based on the analyzed data, the server generates an initial design proposal using a generative model. At this stage, it creates an integrated proposal that takes into account both the internal and external design.

[0546] Step 5:

[0547] The server sends the generated design proposal to the terminal and presents it to the user. The user then reviews the design proposal in detail on the terminal.

[0548] Step 6:

[0549] An emotion engine operates on the device to analyze the user's emotional state (facial expressions, voice, etc.). Emotional data is obtained when the user views the design proposal.

[0550] Step 7:

[0551] Users input their feedback on their device and send emotional data in response to it to the server. The feedback content and emotional state are treated together.

[0552] Step 8:

[0553] The server receives feedback and sentiment data to optimize the design proposal. It analyzes the sentiment data to identify design elements that should be particularly emphasized and areas for improvement.

[0554] Step 9:

[0555] The server will virtually prototype the improved design and verify its reliability and performance through simulation tests.

[0556] Step 10:

[0557] The server sends the final optimization results to the terminal. The user reviews the optimized design proposal on the terminal and makes a final approval.

[0558] (Example 2)

[0559] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0560] In traditional product design processes, it was difficult to take user emotions into account, making it challenging to efficiently deliver highly satisfying product designs. Furthermore, there was a lack of effective methods for incorporating user feedback into design optimization. This hindered product development that truly met user needs.

[0561] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0562] In this invention, the server includes language processing means for receiving and analyzing requests from users, modeling means for generating an initial design based on the analyzed requests, and emotion analysis means for recognizing the user's emotions during feedback. This makes it possible to optimize product design while taking user emotions into consideration.

[0563] "Language processing means" refers to methods for analyzing requests received from users and converting natural language into data that a computer can understand.

[0564] A "modeling tool" is a method or process for automatically generating an initial design based on analyzed requirements.

[0565] An "interface means" is a mechanism or medium for users to review the generated design and provide feedback.

[0566] "Emotion analysis methods" refer to the process of recognizing emotions during user feedback and determining the user's emotional state from their facial expressions and voice.

[0567] An "integrated optimization method" is a method for adjusting and optimizing a design based on collected feedback and sentiment data.

[0568] "Verification testing methods" refer to processes for evaluating optimized designs and confirming their effectiveness and practicality.

[0569] "Adaptive learning methods" are learning methods that use user feedback and sentiment data to continuously improve designs.

[0570] This invention relates to a system for optimizing product design to reflect user emotions. This system operates in an environment that includes servers, terminals, and users.

[0571] The server first receives the requirements for product design from the user via a terminal. The user can input the product type, required functions, and design preferences through the terminal. The terminal sends this information to the server as digital data. The server analyzes this data using natural language processing technology. Specifically, a language processing engine is used to convert the requirements received from the user into structured data. The analyzed information is then sent to a generative AI model, which operates based on this data.

[0572] This generative AI model generates initial designs based on prompt input. For example, if a user inputs "screen size 6.5 inches, camera performance 48MP, design preference simple and modern style" on their device, the server receives this prompt as input and generates suitable design proposals through the AI ​​model. These generated proposals are sent to the device and presented to the user.

[0573] On the device, an emotion engine operates in response to the design proposals presented to the user, and a function is implemented to recognize emotions by analyzing the user's facial expressions and voice. For example, if the user smiles in response to a design, the device sends this information to the server as emotion data.

[0574] The server receives feedback and sentiment data from the terminal and adjusts the design proposal via an integrated optimization mechanism. This information is used to determine which parts of the design should be improved. Then, an adaptive learning mechanism learns from this data and further optimizes the design.

[0575] In this way, this invention enables the optimization of product design that takes user emotions into account, and realizes the development of products that are tailored to the needs of users.

[0576] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0577] Step 1:

[0578] The user uses a terminal to input requirements regarding the product design. These requirements include the type of product, necessary functions, and design preferences. For example, they might enter specific requirements such as, "The screen size should be 6.5 inches, the camera performance 48MP, and a simple design is preferred."

[0579] Step 2:

[0580] The terminal sends the user's input request as digital data to the server. The input information is structured and transferred to the server. This allows the server to accurately receive the user's request and proceed with subsequent analysis.

[0581] Step 3:

[0582] The server analyzes the received data using natural language processing techniques. This process involves data processing that tokenizes, classifies, and extracts meaning from the input request. As a result, the analyzed request is output in a format that can be input into a generative AI model.

[0583] Step 4:

[0584] The server inputs the analyzed data into the generating AI model and generates an initial product design proposal. Based on the prompts, a design is generated according to the input requirements. In this process, design parameters are determined through data calculations, and a virtual design proposal is created.

[0585] Step 5:

[0586] The server sends the generated design proposal to the terminal. The terminal prepares to display this design proposal to the user and formats the data so that the user can visually confirm its contents.

[0587] Step 6:

[0588] The user reviews the design proposals presented on the device and provides feedback. The device collects the user's facial expressions and voice responses, which are then analyzed using an emotion engine. Specifically, facial expressions such as smiles and surprise are recorded as data and output as emotional states.

[0589] Step 7:

[0590] The device sends analyzed sentiment data and user feedback to the server. All collected information is transferred to the server as feedback data and sentiment data. This data is used for further analysis and design adjustments.

[0591] Step 8:

[0592] The server compares the received feedback with sentiment data and adjusts the design. An integrated optimization mechanism performs data calculations that reflect user sentiment and feedback, optimizing the new design proposal. The final output is an improved design.

[0593] Step 9:

[0594] The server performs adaptive learning and continuously analyzes data to improve the design. Based on the accumulated feedback, it learns more effective design strategies and incorporates them into future design proposal generation.

[0595] (Application Example 2)

[0596] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0597] The present invention aims to provide a system that can offer product suggestions that better match user preferences by incorporating user emotional feedback into product design. Furthermore, it aims to improve the accuracy of suggestions by analyzing user emotions in real time and immediately reflecting them in the design.

[0598] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0599] In this invention, the server includes a natural language processing means for receiving and analyzing design requirements from the user, a design generation means for generating initial design proposals based on the analysis results, and an emotion analysis means for analyzing the user's emotions and using them for feedback. This enables the optimization of designs based on the user's emotions and the suggestion of products that match their preferences.

[0600] "Natural language processing means" refers to technologies for analyzing design requirements received from users, where a computer understands human language and analyzes its meaning.

[0601] "Design generation means" refers to algorithms or models that automatically generate initial design proposals based on analyzed requirements.

[0602] "User information terminal means" refers to devices or systems that provide an interface for users to review designs and input feedback.

[0603] "Integrated optimization means" refers to the entire process of improving and optimizing design proposals based on the feedback received.

[0604] "Emotional analysis means" refers to technology for analyzing a user's emotions, and is a function that recognizes emotional states through facial expressions and voice.

[0605] "Product suggestion method" refers to a function that proposes appropriate product designs based on user feedback and sentiment data.

[0606] A "smart device" refers to any device that processes information interactively, such as a terminal that can detect and analyze a user's emotions in real time.

[0607] "Adaptive learning methods" are technologies that sequentially learn from user feedback and use that feedback to improve the overall design functions of the system.

[0608] This system enables a product design optimization process that leverages user sentiment analysis. Its main components include a server, smart devices (e.g., smart glasses), and a user interface.

[0609] First, the server receives design requirements from the user and analyzes them using natural language processing. This includes the elements the user wants in the design and their preferred specifications. Then, using a design generation system, it generates initial design proposals based on the received requirements. The generated proposals are presented to the user via a smart device.

[0610] Users can react to presented designs via their smart devices, and simultaneously, an emotion analysis system operates to collect emotional data from the user's facial expressions and voice. The emotional data collected in real time by the smart device is sent to a server and used by an integrated optimization system to optimize the design proposal. This process is then passed on to a product recommendation system, which provides optimal product recommendations based on the user's preferences.

[0611] As a concrete example, when a user wearing a smart device while shopping smiles upon seeing the design of a displayed product, that emotion is analyzed, and the server then suggests designs that are even closer to the user's preferences.

[0612] Example of a prompt

[0613] "The user is observing casual bags. They are showing a positive expression. Suggest the following design: casual, bright colors, and plenty of storage."

[0614] This system enables highly accurate product design proposals that take user emotions into account, which is expected to improve the user experience.

[0615] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0616] Step 1:

[0617] The server receives design requirements for product design from the user. This input includes the type of product, its functions, and design preferences. The server uses natural language processing to analyze these design requirements and translate the user's needs into specific design parameters. This process generates requirements data for input into a generative AI model.

[0618] Step 2:

[0619] Based on the analyzed requirements data, the server generates initial design proposals using a design generation mechanism. This generation process utilizes a generation AI model to create appropriate design proposals based on the requirements. These design proposals are then ready to be sent to the user via the user interface.

[0620] Step 3:

[0621] The user reviews the design proposals presented via their device. During this process, if a smart device is worn, the user's facial expressions and speech are captured in real time. This input data is used to identify the user's emotions through emotion analysis, and emotion data related to interest, satisfaction, etc., is generated.

[0622] Step 4:

[0623] The server integrates emotional data and feedback received from the terminal. An integration and optimization mechanism analyzes this data and adjusts and optimizes the design proposal. Specifically, design elements are emphasized or improved in response to positive or negative user reactions. This step yields an improved design proposal.

[0624] Step 5:

[0625] Based on the improved design proposals, specific product suggestions are generated for the user through a product suggestion system. These suggestions select the most suitable product based on the user's individual preferences. This further personalizes the user experience, leading to greater satisfaction.

[0626] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0627] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0628] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0632] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0633] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0634] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0635] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0636] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0637] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0638] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0639] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0640] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0641] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0642] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] This invention relates to a system for efficiently designing products that combine functionality and aesthetics by integrating internal and external design in product development. This system operates in an environment that includes servers, terminals, and users.

[0644] The server first receives product design requirements from the user via a terminal. The user can input detailed information about the functions and design features required for the product. The server then uses natural language processing technology to analyze the received design requirements. Based on this analysis, the server generates an initial design proposal that considers both internal and external design. This generation process involves searching through a vast amount of existing design data using machine learning and generative models.

[0645] The generated design proposal is sent to the user's device, where the user can review it in detail. The user then provides feedback on the design proposal via their device. This feedback can include specific functional improvements or changes to design preferences.

[0646] The server receives user feedback and initiates an integrated optimization process. Through this integrated optimization process, the server incorporates the feedback and readjusts the design proposal. During this process, the server creates virtual prototypes of the design and uses simulations to verify the reliability and quality of the design proposal.

[0647] As a concrete example, consider a smartwatch design project. The user desires a stylish design with specific health management functions, which they specify on their device. The server generates an initial smartwatch design proposal based on this and presents it to the user. Subsequently, based on the user's feedback, the design's colors, shapes, and function placement are re-evaluated, and the server generates an optimized final design proposal. Through this process, a smartwatch that combines the user's desired functions and style is designed.

[0648] The following describes the processing flow.

[0649] Step 1:

[0650] The user uses a terminal to input the design requirements for the product. These requirements include the type of product, necessary functions, and design preferences.

[0651] Step 2:

[0652] The terminal sends user input data to the server. The transmitted data includes requirements information written in natural language.

[0653] Step 3:

[0654] The server uses natural language processing techniques to analyze the received data. This extracts key requirements and specific design conditions, which are then processed as structured data.

[0655] Step 4:

[0656] Based on the analysis results, the server generates initial design proposals using a generative model. This process includes algorithms that reference information from a large number of existing databases and select the design best suited to the analyzed requirements.

[0657] Step 5:

[0658] The server sends the generated design proposal to the terminal. The terminal displays the received design proposal to the user, who then reviews the details.

[0659] Step 6:

[0660] Users input feedback on the design proposal via their device. This feedback includes specific comments on areas for design improvement and desired additional features.

[0661] Step 7:

[0662] The device sends user feedback to the server. The server receives the feedback and uses it to further refine the design.

[0663] Step 8:

[0664] Based on feedback, the server refines its design using integrated optimization techniques. Necessary modifications are made to achieve a balance between internal and external design.

[0665] Step 9:

[0666] The server will create virtual prototypes of the improved design proposals and verify their reliability and performance through simulations.

[0667] Step 10:

[0668] The server sends the final, refined design to the terminal for user review. The design approved by the user becomes the final product design.

[0669] (Example 1)

[0670] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0671] The present invention aims to accurately understand user requirements during the product design process, generate design proposals that efficiently and effectively meet those requirements, and provide an optimal design that incorporates user feedback. This aims to achieve a rapid design process while balancing functionality and aesthetics in product development.

[0672] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0673] In this invention, the server includes language processing means for receiving and analyzing requirements from a user, generation means for generating design proposals based on the analyzed requirements, and interface means for presenting the generated design proposals and receiving feedback. This makes it possible to generate and optimize design proposals that accurately reflect the user's requirements.

[0674] A "user" is the entity that provides the design requirements for a product and gives feedback on the design proposal.

[0675] "Requirements" refer to information that includes specific preferences regarding the functions and design that users expect from a product.

[0676] "Language processing means" refers to techniques used to analyze requirements received from users, and includes natural language processing.

[0677] "Generation means" refers to the technology used to create an initial design proposal based on the analyzed requirements, and includes generative AI models.

[0678] An "interface means" is a system function that presents the generated design proposal to the user and receives feedback.

[0679] "Optimization methods" refer to the process of improving design proposals based on user feedback to arrive at the optimal design.

[0680] "Testing methods" refer to techniques used to verify the reliability and quality of an optimized design.

[0681] This invention can be implemented as a system in the product development process that efficiently analyzes user design requirements and generates and proposes optimized design options. This system operates in an environment that includes servers, terminals, and users.

[0682] The server first receives product design requirements from the user via a terminal. The user uses the terminal to input detailed information about the functions and design features required for the product. In this process, the terminal functions as a means of transferring the design requirements entered by the user to the server.

[0683] The server analyzes the received design requirements using natural language processing techniques through language processing tools. This analysis extracts the user's requirements as structured data. Natural language processing (NLP) libraries may be used for this. Based on the information extracted through this analysis, the server creates design proposals using generation tools. It utilizes generative AI models and machine learning frameworks (e.g., TensorFlow and PyTorch) to generate designs that meet the requirements from a vast design database.

[0684] The generated design proposal is sent to the terminal via an interface and reviewed by the user. At this stage, the user can submit feedback on the design proposal through the terminal.

[0685] Upon receiving this feedback, the server improves the design proposal using optimization techniques. Specifically, the design proposal is adjusted based on the feedback, and the reliability and quality of the design are verified through simulation using testing methods.

[0686] As a concrete example, let's consider a smartwatch design project. The user desires a stylish design that includes specific health management functions, and specifies this on their device. The server generates an initial smartwatch design proposal based on this and presents it to the user. Subsequently, based on the user's feedback, the design's colors, shapes, and function placement are re-evaluated, and the server generates an optimized final design proposal.

[0687] An example of a prompt message is: "Generate design proposals for a smartwatch with new health management features. The designs should have modern and stylish elements."

[0688] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0689] Step 1:

[0690] The user inputs product design requirements through a terminal. The input is in the form of a detailed description of the specific functions (e.g., health management functions) and design features (e.g., a stylish appearance) desired for the product. The terminal plays the role of preparing the initial data of these requirements, which will then be sent to the server. At this stage, the input represents the user's requirements, and the output is the transmission of data to the server.

[0691] Step 2:

[0692] The server receives requirements data sent from the terminal and performs natural language processing using language processing tools. Specifically, it uses natural language processing (NLP) techniques to convert the received text data into structured data. This allows each element of the requirements to be analyzed, and the information necessary for the internal and external design of the product is extracted. The input for this step is the user's requirements data, and the output is structured data as a result of the analysis.

[0693] Step 3:

[0694] The server generates initial design proposals using a generation method based on the analyzed structured data. Here, a generative AI model is utilized, and a machine learning framework (e.g., TensorFlow or PyTorch) is used to create design proposals that meet the requirements from a vast amount of existing design data. In this step, structured data is used as input, and the output is the generated design proposal.

[0695] Step 4:

[0696] The server sends the generated design proposal to the terminal for the user to review. The user can then review the presented design proposal in detail on the terminal. After reviewing, the user provides feedback. This feedback may include suggestions for feature improvements or requests for design changes. In this step, the input is a request for review of the generated design proposal, and the output is the user's feedback.

[0697] Step 5:

[0698] The server readjusts the design proposal using optimization techniques based on feedback received from the user. While analyzing the feedback and making necessary design changes, the server utilizes virtual prototyping and simulation technologies to verify the reliability and quality of the design. An optimized design proposal is then obtained. The input for this step is user feedback, and the output is the optimized design proposal.

[0699] Step 6:

[0700] The server sends the optimized final design to the terminal for final confirmation. The user reviews the final design on the terminal and requests further adjustments if necessary. In this final step, the input is the presentation of the optimized design, and the output is final confirmation or provision of further feedback.

[0701] (Application Example 1)

[0702] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] In modern product development, efficiently designing and proposing customized products that meet diverse user needs is challenging. Traditional systems require cumbersome adjustments between internal and external design, and efficient means of incorporating feedback sequentially are limited. Furthermore, there is a growing demand for immediate and flexible proposals using smart devices.

[0704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0705] In this invention, the server includes a natural language processing means for receiving design specifications from a user and analyzing the specifications, a generative modeling means for generating an initial design proposal based on the analyzed specifications, and an adaptive presentation means for customizing and proposing the design proposal according to the user's requirements. This enables the efficient design and proposal of customized products that meet the diverse needs of users.

[0706] "Design specifications" refer to a set of detailed requirements regarding the internal structure and external design of a product, based on user requirements.

[0707] "Natural language processing means" refers to technologies that analyze language data provided by users and extract meaning to understand design specifications.

[0708] "Generative model means" refers to algorithms and processes for automatically generating initial product designs based on analyzed design specifications.

[0709] "User interaction means" refers to an interface that allows users to review generated design proposals and provide opinions and feedback.

[0710] An "integrated optimization method" is an integrated process for generating the optimal product design by adjusting the design based on feedback from users.

[0711] A "simulation evaluation method" is a technique for conducting virtual tests to evaluate the reliability and functionality of an optimized design.

[0712] "Adaptive presentation means" refers to a technology that customizes design proposals according to the user's specific requirements and dynamically presents the proposed content.

[0713] A "generative model" is a predictive model and algorithm used to create new design proposals based on a large amount of past design data.

[0714] This embodiment of the invention is a system for rapidly designing customized products that reflect the diverse requirements of users. The server receives product design specifications from the user via a terminal and analyzes these specifications using natural language processing. This makes it possible to understand the user's requirements in detail.

[0715] Based on the analyzed results, the server generates initial design proposals using a generative model. The generative model employs machine learning frameworks such as TensorFlow and PyTorch, and utilizes a prediction algorithm trained on large-scale design data. These design proposals are presented to the user via user interaction, allowing the user to review them and provide feedback through their terminal.

[0716] Upon receiving feedback, the server modifies and optimizes the design proposal using integrated optimization tools and verifies the reliability of the design using simulation evaluation tools. For example, it virtually tests whether the design proposal meets the required functions and conforms to safety standards. Simulation tools from Google Cloud and AWS are often used for evaluation at this stage.

[0717] For example, if a user enters "I want a red, rounded soap dispenser" into an online shopping site, the server analyzes this request and generates appropriate design proposals. The server then presents these proposals to the user, and if the user provides feedback such as "I want it to be smaller," the design is adjusted again and an optimized proposal is presented. This process allows users to freely choose a customized product.

[0718] Examples of prompts for the generating AI model include specific requirements such as, "Choose an exterior design for the dispenser. Consider red color, a rounded form, and improved storage capacity."

[0719] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0720] Step 1:

[0721] The user uses a terminal to input product design specifications (e.g., "I want a red, rounded soap dispenser"). The terminal sends this input data to the server. At this stage, the input is the user's request, and the output is the data transfer to the server.

[0722] Step 2:

[0723] The server analyzes the user's design specifications received using natural language processing. This process uses the Google Cloud Natural Language API to analyze the input text data and extract key intents and elements. The output is structured data, which is then passed on to the next generation step.

[0724] Step 3:

[0725] The server generates initial design proposals using a generative model based on the analyzed structured data. Here, a generative AI model using TensorFlow is employed, and a prediction algorithm operates based on existing design data. The output is the initial design proposal, which is then sent to the terminal.

[0726] Step 4:

[0727] The terminal presents the received initial design proposal to the user. The user reviews it and inputs their feedback (e.g., "I want it to be smaller") into the terminal. This input is user feedback, and the output is the transmission of feedback data to the server.

[0728] Step 5:

[0729] The server readjusts the design proposal based on user feedback received through an integrated optimization mechanism. This process uses an adaptive learning algorithm to optimize the design while incorporating the feedback. The output is the revised design proposal, which then proceeds to verification using a simulation evaluation mechanism.

[0730] Step 6:

[0731] The server verifies the reliability and quality of the revised design proposal using simulation evaluation tools. It virtually checks whether the design meets the specified requirements using simulation tools from AWS or Google Cloud. The output is feedback data, including the final evaluation.

[0732] Step 7:

[0733] The server sends a final design proposal, incorporating the evaluation results, to the terminal for the user to view. The user can review the final design and repeat the process of submitting further adjustment requests as needed. The output of this step is the final design proposal, and the project is completed based on the user's decision.

[0734] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0735] This invention relates to a system for recognizing user emotions and incorporating feedback corresponding to those emotions into the product design optimization process. This system operates in an environment that includes a server, terminals, and users.

[0736] The server first receives the requirements for product design from the user via a terminal. The user can input detailed information about the product type, required functions, and design preferences. The terminal sends this information to the server. The server analyzes the received design requirements using natural language processing technology and generates initial design proposals using a generative model based on this analysis.

[0737] The generated design proposals are sent from the server to the user's device, where they can view the details and input their reactions and emotions as feedback. During this process, an emotion engine operates on the device, analyzing the user's facial expressions and voice to recognize their emotions. For example, various emotional states such as smiles, expressions of surprise, and expressions of disinterest are analyzed.

[0738] The server receives feedback and sentiment data transmitted from the terminal and adjusts the design proposal through an integrated optimization mechanism. The data obtained by the sentiment engine is used to adjust design elements that should be particularly emphasized in the optimization process. The server performs sentiment-based adaptive learning to improve the design.

[0739] As a concrete example, consider a scenario where a user is considering the design of a smartphone. The user inputs their preferences regarding a specific screen size and camera performance. The server generates and presents initial design proposals, but at this time, the device analyzes the user's facial expressions and communicates to the server, via an emotion engine, how satisfied the user is with the design or whether improvements are needed. For example, if the user shows interest, an instruction is sent to the server to emphasize that part of the design.

[0740] Through the above process, the present invention achieves optimization of product design that takes user emotions into account, enabling product development that is more closely aligned with user needs.

[0741] The following describes the processing flow.

[0742] Step 1:

[0743] The user inputs and submits specific design requirements for the product (such as product type, functions, and design preferences) via a terminal.

[0744] Step 2:

[0745] The terminal transfers the entered design requirements to the server. The data is written in natural language.

[0746] Step 3:

[0747] The server uses natural language processing technology to analyze the received requirements. As a result, it extracts the structured data necessary for product design.

[0748] Step 4:

[0749] Based on the analyzed data, the server generates an initial design proposal using a generative model. At this stage, it creates an integrated proposal that takes into account both the internal and external design.

[0750] Step 5:

[0751] The server sends the generated design proposal to the terminal and presents it to the user. The user then reviews the design proposal in detail on the terminal.

[0752] Step 6:

[0753] An emotion engine operates on the device to analyze the user's emotional state (facial expressions, voice, etc.). Emotional data is obtained when the user views the design proposal.

[0754] Step 7:

[0755] Users input their feedback on their device and send emotional data in response to it to the server. The feedback content and emotional state are treated together.

[0756] Step 8:

[0757] The server receives feedback and sentiment data to optimize the design proposal. It analyzes the sentiment data to identify design elements that should be particularly emphasized and areas for improvement.

[0758] Step 9:

[0759] The server will virtually prototype the improved design and verify its reliability and performance through simulation tests.

[0760] Step 10:

[0761] The server sends the final optimization results to the terminal. The user reviews the optimized design proposal on the terminal and makes a final approval.

[0762] (Example 2)

[0763] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0764] In traditional product design processes, it was difficult to take user emotions into account, making it challenging to efficiently deliver highly satisfying product designs. Furthermore, there was a lack of effective methods for incorporating user feedback into design optimization. This hindered product development that truly met user needs.

[0765] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0766] In this invention, the server includes language processing means for receiving and analyzing requests from users, modeling means for generating an initial design based on the analyzed requests, and emotion analysis means for recognizing the user's emotions during feedback. This makes it possible to optimize product design while taking user emotions into consideration.

[0767] "Language processing means" refers to methods for analyzing requests received from users and converting natural language into data that a computer can understand.

[0768] A "modeling tool" is a method or process for automatically generating an initial design based on analyzed requirements.

[0769] An "interface means" is a mechanism or medium for users to review the generated design and provide feedback.

[0770] "Emotion analysis methods" refer to the process of recognizing emotions during user feedback and determining the user's emotional state from their facial expressions and voice.

[0771] An "integrated optimization method" is a method for adjusting and optimizing a design based on collected feedback and sentiment data.

[0772] "Verification testing methods" refer to processes for evaluating optimized designs and confirming their effectiveness and practicality.

[0773] "Adaptive learning methods" are learning methods that use user feedback and sentiment data to continuously improve designs.

[0774] This invention relates to a system for optimizing product design to reflect user emotions. This system operates in an environment that includes servers, terminals, and users.

[0775] The server first receives the requirements for product design from the user via a terminal. The user can input the product type, required functions, and design preferences through the terminal. The terminal sends this information to the server as digital data. The server analyzes this data using natural language processing technology. Specifically, a language processing engine is used to convert the requirements received from the user into structured data. The analyzed information is then sent to a generative AI model, which operates based on this data.

[0776] This generative AI model generates initial designs based on prompt input. For example, if a user inputs "screen size 6.5 inches, camera performance 48MP, design preference simple and modern style" on their device, the server receives this prompt as input and generates suitable design proposals through the AI ​​model. These generated proposals are sent to the device and presented to the user.

[0777] On the device, an emotion engine operates in response to the design proposals presented to the user, and a function is implemented to recognize emotions by analyzing the user's facial expressions and voice. For example, if the user smiles in response to a design, the device sends this information to the server as emotion data.

[0778] The server receives feedback and sentiment data from the terminal and adjusts the design proposal via an integrated optimization mechanism. This information is used to determine which parts of the design should be improved. Then, an adaptive learning mechanism learns from this data and further optimizes the design.

[0779] In this way, this invention enables the optimization of product design that takes user emotions into account, and realizes the development of products that are tailored to the needs of users.

[0780] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0781] Step 1:

[0782] The user uses a terminal to input requirements regarding the product design. These requirements include the type of product, necessary functions, and design preferences. For example, they might enter specific requirements such as, "The screen size should be 6.5 inches, the camera performance 48MP, and a simple design is preferred."

[0783] Step 2:

[0784] The terminal sends the user's input request as digital data to the server. The input information is structured and transferred to the server. This allows the server to accurately receive the user's request and proceed with subsequent analysis.

[0785] Step 3:

[0786] The server analyzes the received data using natural language processing techniques. This process involves data processing that tokenizes, classifies, and extracts meaning from the input request. As a result, the analyzed request is output in a format that can be input into a generative AI model.

[0787] Step 4:

[0788] The server inputs the analyzed data into the generating AI model and generates an initial product design proposal. Based on the prompts, a design is generated according to the input requirements. In this process, design parameters are determined through data calculations, and a virtual design proposal is created.

[0789] Step 5:

[0790] The server sends the generated design proposal to the terminal. The terminal prepares to display this design proposal to the user and formats the data so that the user can visually confirm its contents.

[0791] Step 6:

[0792] The user reviews the design proposals presented on the device and provides feedback. The device collects the user's facial expressions and voice responses, which are then analyzed using an emotion engine. Specifically, facial expressions such as smiles and surprise are recorded as data and output as emotional states.

[0793] Step 7:

[0794] The device sends analyzed sentiment data and user feedback to the server. All collected information is transferred to the server as feedback data and sentiment data. This data is used for further analysis and design adjustments.

[0795] Step 8:

[0796] The server compares the received feedback with sentiment data and adjusts the design. An integrated optimization mechanism performs data calculations that reflect user sentiment and feedback, optimizing the new design proposal. The final output is an improved design.

[0797] Step 9:

[0798] The server performs adaptive learning and continuously analyzes data to improve the design. Based on the accumulated feedback, it learns more effective design strategies and incorporates them into future design proposal generation.

[0799] (Application Example 2)

[0800] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0801] The present invention aims to provide a system that can offer product suggestions that better match user preferences by incorporating user emotional feedback into product design. Furthermore, it aims to improve the accuracy of suggestions by analyzing user emotions in real time and immediately reflecting them in the design.

[0802] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0803] In this invention, the server includes a natural language processing means for receiving and analyzing design requirements from the user, a design generation means for generating initial design proposals based on the analysis results, and an emotion analysis means for analyzing the user's emotions and using them for feedback. This enables the optimization of designs based on the user's emotions and the suggestion of products that match their preferences.

[0804] "Natural language processing means" refers to technologies for analyzing design requirements received from users, where a computer understands human language and analyzes its meaning.

[0805] "Design generation means" refers to algorithms or models that automatically generate initial design proposals based on analyzed requirements.

[0806] "User information terminal means" refers to devices or systems that provide an interface for users to review designs and input feedback.

[0807] "Integrated optimization means" refers to the entire process of improving and optimizing design proposals based on the feedback received.

[0808] "Emotional analysis means" refers to technology for analyzing a user's emotions, and is a function that recognizes emotional states through facial expressions and voice.

[0809] "Product suggestion method" refers to a function that proposes appropriate product designs based on user feedback and sentiment data.

[0810] A "smart device" refers to any device that processes information interactively, such as a terminal that can detect and analyze a user's emotions in real time.

[0811] "Adaptive learning methods" are technologies that sequentially learn from user feedback and use that feedback to improve the overall design functions of the system.

[0812] This system enables a product design optimization process that leverages user sentiment analysis. Its main components include a server, smart devices (e.g., smart glasses), and a user interface.

[0813] First, the server receives design requirements from the user and analyzes them using natural language processing. This includes the elements the user wants in the design and their preferred specifications. Then, using a design generation system, it generates initial design proposals based on the received requirements. The generated proposals are presented to the user via a smart device.

[0814] Users can react to presented designs via their smart devices, and simultaneously, an emotion analysis system operates to collect emotional data from the user's facial expressions and voice. The emotional data collected in real time by the smart device is sent to a server and used by an integrated optimization system to optimize the design proposal. This process is then passed on to a product recommendation system, which provides optimal product recommendations based on the user's preferences.

[0815] As a concrete example, when a user wearing a smart device while shopping smiles upon seeing the design of a displayed product, that emotion is analyzed, and the server then suggests designs that are even closer to the user's preferences.

[0816] Example of a prompt

[0817] "The user is observing casual bags. They are showing a positive expression. Suggest the following design: casual, bright colors, and plenty of storage."

[0818] This system enables highly accurate product design proposals that take user emotions into account, which is expected to improve the user experience.

[0819] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0820] Step 1:

[0821] The server receives design requirements for product design from the user. This input includes the type of product, its functions, and design preferences. The server uses natural language processing to analyze these design requirements and translate the user's needs into specific design parameters. This process generates requirements data for input into a generative AI model.

[0822] Step 2:

[0823] Based on the analyzed requirements data, the server generates initial design proposals using a design generation mechanism. This generation process utilizes a generation AI model to create appropriate design proposals based on the requirements. These design proposals are then ready to be sent to the user via the user interface.

[0824] Step 3:

[0825] The user reviews the design proposals presented via their device. During this process, if a smart device is worn, the user's facial expressions and speech are captured in real time. This input data is used to identify the user's emotions through emotion analysis, and emotion data related to interest, satisfaction, etc., is generated.

[0826] Step 4:

[0827] The server integrates emotional data and feedback received from the terminal. An integration and optimization mechanism analyzes this data and adjusts and optimizes the design proposal. Specifically, design elements are emphasized or improved in response to positive or negative user reactions. This step yields an improved design proposal.

[0828] Step 5:

[0829] Based on the improved design proposals, specific product suggestions are generated for the user through a product suggestion system. These suggestions select the most suitable product based on the user's individual preferences. This further personalizes the user experience, leading to greater satisfaction.

[0830] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0831] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0832] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0833] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0834] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0835] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0836] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0837] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0838] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0839] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0840] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0841] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0842] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0843] 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.

[0844] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0845] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0846] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0847] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0848] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0849] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0850] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0851] The following is further disclosed regarding the embodiments described above.

[0852] (Claim 1)

[0853] A natural language processing system for receiving design requirements from users and analyzing those requirements,

[0854] A generative model means for generating an initial design proposal based on the analyzed requirements,

[0855] A user interface for reviewing the generated design proposal and receiving feedback,

[0856] An integrated optimization method for optimizing design proposals based on feedback,

[0857] A simulation testing method for evaluating the optimized design,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, comprising means for simultaneously considering internal design and exterior design in the generation of design proposals.

[0861] (Claim 3)

[0862] The system according to claim 1, further comprising an adaptive learning means for sequentially learning user feedback and reflecting it in optimizing design proposals.

[0863] "Example 1"

[0864] (Claim 1)

[0865] A language processing means for receiving requirements from users and analyzing those requirements,

[0866] A generation means for generating design proposals based on analyzed requirements,

[0867] An interface for presenting generated design proposals and receiving feedback,

[0868] Optimization methods for optimizing the design proposal based on feedback,

[0869] Means of testing to verify the optimized design,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, comprising means for simultaneously considering structural and surface design when generating a design proposal.

[0873] (Claim 3)

[0874] The system according to claim 1, comprising an adaptive learning means for sequentially learning opinions and reflecting them in optimizing the design proposal.

[0875] "Application Example 1"

[0876] (Claim 1)

[0877] A natural language processing system for receiving design specifications from users and analyzing those specifications,

[0878] A generation model means for generating an initial design proposal based on the analyzed specifications,

[0879] User interaction methods for reviewing the generated design proposal and receiving feedback,

[0880] An integrated optimization method for optimizing the design proposal based on feedback,

[0881] A simulation evaluation method for evaluating an optimized design,

[0882] A means of providing an adaptive presentation for customizing and proposing design options according to the user's requirements,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, comprising means for simultaneously considering internal design points and external design points and for adjusting and generating design proposals according to the user's customization requirements.

[0886] (Claim 3)

[0887] The system according to claim 1, further comprising an adaptive learning means for sequentially learning user feedback and reflecting it in the optimization process of design proposals, and further comprising a means for displaying proposal content based on a generative model relating to customized product proposals.

[0888] "Example 2 of combining an emotion engine"

[0889] (Claim 1)

[0890] A language processing means for receiving requests from users and analyzing those requests,

[0891] A modeling means for generating an initial design based on the analyzed requirements,

[0892] An interface for reviewing the generated design and receiving feedback,

[0893] A means of sentiment analysis to recognize the user's emotions when providing feedback,

[0894] An integrated optimization method for optimizing design based on feedback and emotional data,

[0895] Verification test means for evaluating optimized designs,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, comprising means for simultaneously considering internal design and external design in the generation of the design.

[0899] (Claim 3)

[0900] The system according to claim 1, comprising an adaptive learning means for sequentially learning user feedback and emotional data and reflecting it in optimizing the design.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] A natural language processing system for receiving design requirements from users and analyzing those requirements,

[0904] A design generation means that generates an initial design proposal based on the analyzed requirements,

[0905] A user information terminal means for reviewing the generated design proposal and receiving feedback,

[0906] An integrated optimization method for optimizing design proposals based on feedback,

[0907] An emotion analysis tool used to analyze the user's emotions and provide feedback,

[0908] A product proposal method that suggests designs based on feedback and emotional data,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, comprising means for analyzing emotions in real time using a smart device and making product suggestions based on user preferences.

[0912] (Claim 3)

[0913] The system according to claim 1, comprising adaptive learning means for sequentially learning user feedback and reflecting it in optimizing design proposals and product proposals. [Explanation of Symbols]

[0914] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A natural language processing system for receiving design requirements from users and analyzing those requirements, A generative model means for generating an initial design proposal based on the analyzed requirements, A user interface for reviewing the generated design proposal and receiving feedback, An integrated optimization method for optimizing design proposals based on feedback, A simulation testing method for evaluating the optimized design, A system that includes this.

2. The system according to claim 1, comprising means for simultaneously considering internal design and external design in the generation of design proposals.

3. The system according to claim 1, further comprising an adaptive learning means for sequentially learning user feedback and reflecting it in optimizing design proposals.

Images