system

Abstract

Provide a system. 【Solution means】 Data collection means, Preprocessing means, Means for training a machine learning model, Means for generating an advertising plan based on market trends, Means for receiving user feedback, Means for improving the advertising plan generated based on the user feedback, Means for determining the final advertisement and converting it into a distribution specification, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional product design process, it is difficult to quickly respond to customer needs and market changes, and there are problems that it takes a lot of time and labor to generate a design, receive and reflect customer feedback. Also, the means for evaluating and improving the validity of a design are limited, and it is difficult to lead to the creation of a new design.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for data collection, preprocessing, training a machine learning model, generating design proposals based on customer requirements, receiving user feedback, improving the design proposals generated based on the user feedback, and determining the final design and converting it into the specifications of an actual product. This system streamlines the entire design process and enables the rapid realization of sophisticated designs that meet customer requirements and market trends.

[0006] "Data collection means" refers to a device or process that has the function of collecting data from external sources in order to obtain market trend information and customer needs.

[0007] "Preprocessing means" refers to a device or process that has the function of normalizing collected data and removing unnecessary information to prepare it for analysis.

[0008] A "means for training a machine learning model" is a device or process that has the function of learning patterns using a machine learning algorithm with a given dataset.

[0009] "Means for generating design proposals" refers to a device or process that has the function of automatically proposing new designs based on customer requirements and market trends.

[0010] "Means of receiving user feedback" refers to a device or process that has an interface or function for collecting evaluations and opinions from users.

[0011] "Means for improving generated design proposals" refers to a device or process that has the function of improving existing designs based on feedback obtained from users.

[0012] "Means for determining the final design and converting it into the specifications of an actual product" refers to a device or process that has the function of converting the determined design into a format that can actually be manufactured, and moving on to the next stage of product development. [Brief explanation of the drawing]

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

[0014] Next, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] 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.

[0017] 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.

[0018] 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.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

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

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0034] This invention is a system that combines data collection, preprocessing, AI-based design generation, and the reception and improvement of user feedback. Specifically, the system is realized through the use of a server, terminals, and users, each playing their respective roles.

[0035] Server Role

[0036] The server first collects market trend data from external sources such as social media and news sites. This information is used to understand customer needs and the latest trends. The server normalizes and cleans this data and prepares it for use in training AI models. Furthermore, the server also has the ability to generate new product design proposals using the trained AI models.

[0037] Terminal role

[0038] The terminal presents the user with design proposals sent from the server. The user evaluates the displayed design proposals and provides feedback. The terminal is responsible for sending this feedback to the server. Furthermore, once the final design is decided, the terminal can output the design as a product specification document.

[0039] User roles

[0040] Users review the design proposals presented on their devices and provide feedback on their preferences and areas for improvement. This feedback serves as valuable information for the server to improve the design.

[0041] Specific example

[0042] For example, if a company wants to develop a new smartphone case design, the server collects relevant data from Twitter and feedback platforms. Based on this data, the AI ​​learns about color and material trends and generates various design proposals. The device displays these design proposals to the user, who selects their favorite design and provides feedback on color adjustments and material changes. The server then receives this feedback, refines the design, and provides a final version. Finally, the device converts the selected design specifications into digital data for transmission to the manufacturing department.

[0043] Thus, the proposed system combines human creativity with machine learning technology to provide highly efficient and user-friendly product designs.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects market trend data and user feedback from specified APIs. This data is filtered based on pre-specified keywords and topics.

[0047] Step 2:

[0048] The server analyzes the collected raw data, filters out unnecessary information, and normalizes it. This makes the data clean and consistent.

[0049] Step 3:

[0050] The server uses pre-processed data to train a machine learning model. The model learns the factors and trends that influence the design.

[0051] Step 4:

[0052] The server generates new design proposals using the trained model. These generated design proposals reflect the user's past preferences and market trends.

[0053] Step 5:

[0054] The server sends the generated design proposal to the terminal. The terminal displays the design on its user interface.

[0055] Step 6:

[0056] Users review the design proposal displayed on their device and provide feedback on the design through the interface. This feedback often concerns color, shape, and functionality.

[0057] Step 7:

[0058] The server receives feedback from users and improves the design proposals. The feedback is reflected in the model, and new design proposals are generated as needed.

[0059] Step 8:

[0060] The terminal converts the user's selected final design into product design specifications. These specifications are then prepared as digital data for implementation in the manufacturing department.

[0061] (Example 1)

[0062] 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."

[0063] Traditional product design processes have made it difficult to quickly generate designs that effectively reflect customer needs and market trends. Furthermore, the inability to quickly incorporate user feedback and improve designs sometimes led to problems with the final product's market suitability.

[0064] 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.

[0065] In this invention, the server includes means for collecting data from external sources, means for processing the collected data and preparing it in a format suitable for machine learning, and means for generating design proposals based on customer requirements using a trained generative AI model. This enables the rapid generation of design proposals that reflect customer needs and market trends, and immediate design improvements based on user feedback.

[0066] "Means for collecting data from external sources" refers to a device or method that has the function of automatically acquiring necessary data from various sources on the internet.

[0067] "Methods for processing collected data and preparing it in a format suitable for machine learning" refers to processing methods that convert acquired data into an analyzable format, correct incomplete data, and delete unnecessary data.

[0068] "A means of generating design proposals based on customer requirements using a trained generative AI model" refers to a technology that pre-trains a machine learning algorithm and uses that model to automatically generate new designs that meet user needs.

[0069] "Means of receiving user feedback" refers to interfaces and processes that record user opinions and requests within the system and reflect them in subsequent actions.

[0070] "Methods for improving design proposals" refer to methods for improving generated designs based on user feedback, and modifying them to be of higher quality and better meet user needs.

[0071] "Means of converting a final design into a product specification format" refers to a process or system for converting a completed design proposal into a format that is adaptable to the manufacturing process and can be used in actual product manufacturing.

[0072] "Acquiring market trend information using APIs as a means of information acquisition" refers to a technology that uses a specific application program interface to acquire market trend and consumer behavior data in real time.

[0073] "Applying natural language processing technology" means using technology that allows machines to understand and process human language to utilize language data for model training and design generation.

[0074] The following describes embodiments for carrying out the invention.

[0075] This invention is a system that highly automates data collection and processing, AI-powered design generation, and the collection and incorporation of user feedback. Specifically, it is operated by three parties—a server, a terminal, and a user—each playing a different role.

[0076] Server Role

[0077] The server plays a central role in collecting data from diverse sources. Specifically, the server uses scraping tools such as Python's BeautifulSoup and Selenium to collect information from social media and news sites. The server processes this data using machine learning libraries such as Pandas and NumPy, converting it into a format suitable for training AI models. Then, it uses the trained generative AI model to generate new design proposals based on customer requirements. Machine learning frameworks such as TENSORFLOW® and PyTorch are used to train the generative AI model. During generation, specific prompt statements are provided as input to create appropriate design proposals.

[0078] Terminal role

[0079] The terminal provides an interface that presents design proposals sent from the server to the user. Specifically, it utilizes front-end libraries such as React and Vue.js to build a user-friendly UI. Through this UI, the user evaluates the design proposals and provides feedback. The terminal then sends this feedback back to the server. This exchange enables a process of improving the design based on user requests.

[0080] User roles

[0081] Users review the design proposals displayed on their devices and evaluate whether each design matches their needs and preferences. They can provide specific feedback, such as "Make this color more vibrant" or "Change this material." This user feedback is then sent to the server and used to improve the designs.

[0082] Examples of specific cases and prompt statements

[0083] For example, when a company designs a new smartphone case, the server collects data from social media and feedback platforms, and an AI model generates design proposals based on that data. An example of a prompt used for generation is, "Generate smartphone case design proposals that reflect the latest color trends." In this way, the design cycle, including user feedback, is efficiently managed.

[0084] This system combines human creativity with machine learning technology to provide rapid and highly adaptable product designs.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The server collects data from external sources. Specifically, the server uses APIs from social media and news sites to obtain text and image data related to market trends. This data is used as input data to understand customer needs. The obtained data is stored in storage so that it can be reused in the next processing step.

[0088] Step 2:

[0089] The server preprocesses the collected data. Since the input data may contain missing values ​​or noise, the server cleans and normalizes the data using Pandas and NumPy. This data processing outputs a clean dataset suitable for training machine learning models.

[0090] Step 3:

[0091] The server generates design proposals using a generative AI model. Using a clean dataset as input, the AI ​​model, trained with TensorFlow or PyTorch, generates a variety of design proposals. Using the prompt "Generate design proposals that reflect the latest color trends," designs that meet user needs are output.

[0092] Step 4:

[0093] The device presents design proposals received from the server to the user. The device generates a UI using React or Vue.js, allowing the user to view various design proposals on the screen. The design proposals are displayed in a visually clear manner, enabling the user to intuitively select and evaluate them.

[0094] Step 5:

[0095] Users evaluate the presented design proposals and provide feedback. They input specific requests and suggestions for improvement in a format such as, "I'd like the colors in this design adjusted." User feedback is crucial information for improvements in the next step.

[0096] Step 6:

[0097] The device sends user feedback to the server. The feedback is sent to the server using HTTP communication and formatted for easy analysis. Once the data arrives at the server, it is ready for the next improvement step.

[0098] Step 7:

[0099] The server improves the design proposal based on user feedback. Using the feedback as input, an AI model is used to improve the design. The improved design proposal is generated as a new output, better meeting user needs.

[0100] Step 8:

[0101] Once the final design is decided, the terminal converts it into a product specification. The selected design is output as digital data in PDF or CAD format, ready to be sent to the manufacturing department. The terminal automates this conversion, enabling a rapid data flow.

[0102] (Application Example 1)

[0103] 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."

[0104] In today's advertising industry, creating effective advertising designs that quickly respond to consumer needs and market trends is crucial. However, traditional methods struggle to grasp market trends and incorporate consumer feedback, and these processes are time-consuming and resource-intensive.

[0105] 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.

[0106] In this invention, the server includes data collection means, preprocessing means, and means for training a machine learning model. This makes it possible to quickly grasp market trends and generate effective advertising designs that reflect consumer feedback.

[0107] "Data collection methods" refer to the function of acquiring trend data from external sources in order to understand market trends and consumer needs.

[0108] "Preprocessing means" refers to functions that normalize collected data and prepare it in a format suitable for training machine learning models.

[0109] "Methods for training machine learning models" refers to the function of training an AI model using collected and pre-processed data, thereby giving it the ability to generate new advertising ideas.

[0110] "Methods for generating advertising proposals" refers to a function that utilizes machine learning models to create appropriate advertising design proposals based on market trends and other factors.

[0111] "Means of receiving user feedback" refers to a function that collects consumer evaluations and suggestions for improvement regarding advertising proposals.

[0112] "Means for improving ad drafts" refers to a function that modifies generated ad drafts to make them more effective based on collected user feedback.

[0113] "Means of determining and converting advertisements into distribution specifications" refers to the function of finalizing the advertisement design and converting it into a format suitable for use and distribution.

[0114] This invention is a system that generates advertising designs that quickly respond to market trends in the advertising industry and effectively reflect consumer needs. The system mainly consists of three elements: a server, a terminal, and a user.

[0115] The server is responsible for collecting market trend data from external sources using APIs. The collected data is analyzed using libraries such as BeautifulSoup and Scrapy in the Python language, and normalized and cleansed using Pandas. Next, an AI model is trained on the data using machine learning libraries such as TensorFlow. This trained generative AI model has the function of generating advertising design proposals based on market trends.

[0116] The device provides the user with an interface through which the user can view multiple generated design proposals. The applications used are primarily developed with Flutter®, and users can select their preferred design on the interface and provide feedback on its evaluation and potential improvements.

[0117] User feedback is sent back to the server, which then uses it to refine the ad design. Ultimately, the most effective ad design is determined and converted into a distribution specification by the server.

[0118] For example, when a server generates an advertising design for a new beverage, the prompt would be, "Generate an advertising design proposal that emphasizes the modern and healthy image of the new beverage brand." This is expected to generate advertising designs that accurately capture market needs in a short amount of time.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server collects market trend data from external sources via APIs. The input to this data collection is market trend information provided by the API, and the output is raw market trend data. The server then uses analysis tools (such as BeautifulSoup or Scrapy) to extract the necessary information and format it into a dataset.

[0122] Step 2:

[0123] The server processes the formatted market trend data using the Pandas library. The input contains raw market trend data, and the output is normalized and cleaned data. The normalization process unifies the data format and removes unnecessary data.

[0124] Step 3:

[0125] The server trains a machine learning model using TensorFlow. The input for this step is pre-processed market trend data, and the output is a generative AI model. The machine learning model learns trends from the provided data and gains foundational knowledge to generate advertising designs.

[0126] Step 4:

[0127] The user receives ad design proposals sent from the server via a Flutter app on their device. The input is the generated ad design proposal, which the user evaluates. The output is the user's feedback, including the evaluation information.

[0128] Step 5:

[0129] The server improves the ad design based on feedback received from the terminal. The input is user feedback, and the output is the improved ad design proposal. The server analyzes the content of the feedback, incorporates it into the generating AI model, and adjusts the ad proposal.

[0130] Step 6:

[0131] Finally, the server finalizes the optimized ad draft and converts it into a distributable format. The input for this step is the improved ad design draft, and the output is the final ad design usable on the advertising medium. The server converts this into a digital format and prepares it for distribution.

[0132] 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.

[0133] This invention is a system that optimizes designs by taking user emotions into account, in addition to data collection, preprocessing, and AI model-based design proposal generation, by incorporating an emotion engine. This system aims to provide more personalized designs by analyzing the emotional state of users, particularly when receiving feedback.

[0134] Server Role

[0135] The server collects market trend information via information source APIs, performs data cleansing and normalization, and trains machine learning models on the collected data to generate design proposals that reflect customer requirements. Furthermore, the server utilizes an emotion engine to analyze the emotions contained in user feedback and uses this information to improve the design process.

[0136] Functions of the Emotion Engine

[0137] The emotion engine performs natural language processing on comments and feedback entered by users through their devices, and extracts emotional indicators from them. These indicators reflect user preferences and frustrations and are used to evaluate and improve design proposals.

[0138] Terminal role

[0139] The device presents design proposals sent from the server to the user and receives feedback from the user. The device sends this feedback to the server in real time, including sentiment data analyzed by the sentiment engine.

[0140] User roles

[0141] Users review the design proposals presented on their devices and provide feedback, frankly recording their feelings and opinions. The interaction is designed with the intention that this feedback will lead to better design improvements.

[0142] Specific example

[0143] For example, when designing a new furniture set, if a user provides feedback such as "This color is unsettling," the emotion engine analyzes "anxiety" as an emotional metric. The server incorporates this data into its model and generates design proposals with more calming color schemes. The terminal then presents the improved design to the user and obtains further feedback.

[0144] Thus, the present invention builds a feedback cycle that incorporates user emotions and achieves advanced design optimization to enhance user satisfaction.

[0145] The following describes the processing flow.

[0146] Step 1:

[0147] The server collects market trend data via information source APIs. This data is used to understand consumer opinions and trends related to products.

[0148] Step 2:

[0149] The server normalizes the collected data and performs data cleansing to remove noise. This prepares the data for analysis.

[0150] Step 3:

[0151] The server trains a machine learning model using clean data. This model is responsible for learning trends and patterns that influence the design.

[0152] Step 4:

[0153] The server uses the trained model to generate design proposals based on customer requirements. These design proposals will reflect historical trend data.

[0154] Step 5:

[0155] The terminal displays design proposals sent from the server on its user interface. The user reviews these and forms their first impression.

[0156] Step 6:

[0157] Users provide specific comments as feedback on the design proposals displayed on their devices. This feedback may include comments on particular colors or shapes.

[0158] Step 7:

[0159] The device sends user feedback to the server. Simultaneously, it also includes data for sentiment analysis by the emotion engine.

[0160] Step 8:

[0161] The server uses an emotion engine to analyze user feedback and extract emotion metrics. These emotion metrics, in the form of "satisfied" or "dissatisfied," are used to improve the design.

[0162] Step 9:

[0163] The server improves the design proposal based on the analyzed sentiment data. The improved design becomes personalized, reflecting the user's emotional state.

[0164] Step 10:

[0165] The device receives a new design proposal from the server again and presents it to the user. The user reviews this new proposal and provides further evaluation and feedback.

[0166] Through this processing flow, the system quickly generates design proposals that take user emotions and feedback into account, aiming to improve user satisfaction.

[0167] (Example 2)

[0168] 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".

[0169] To meet the diverse needs of today's consumers, it is crucial to quickly generate designs that reflect the emotions and preferences of individual customers and to continuously improve them. However, traditional design processes struggle to adequately reflect user opinions and lack mechanisms for efficiently analyzing collected feedback and incorporating it into designs. This raises concerns about declining consumer satisfaction and reduced competitiveness in the market.

[0170] 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.

[0171] In this invention, the server includes means for collecting information, means for preprocessing the data, and means for training the data using machine learning algorithms. This makes it possible to process user feedback through sentiment analysis, quickly propose more personalized designs, and enable a continuous improvement cycle.

[0172] "Means of collecting information" refers to protocols and interfaces for obtaining market trends and customer demands.

[0173] "Methods for preprocessing data" refers to the process of converting collected data into an analyzable format and handling missing or outlier values.

[0174] "Methods for training data using machine learning algorithms" refers to the process of generating a machine learning model using training data and optimizing the model so that it can perform pattern recognition and prediction.

[0175] "Methods for proposing designs" refers to the process of considering customer needs and presenting unique product designs and service plans using generative AI models.

[0176] "Means of receiving feedback from users" refers to the process of collecting opinions and impressions from end users and inputting that information into the system in an analyzable format.

[0177] "Methods for processing and improving design through sentiment analysis" refers to the process of analyzing emotional information contained in user feedback and reflecting the results in improving designs and proposals.

[0178] "Methods for finalizing the design and converting it into the specifications of an actual product" refers to the process of translating the finalized design proposal into detailed specifications and proposing it as a production-ready technical document.

[0179] This invention is a system for providing personalized designs to individual users. The server collects market trend information using an information gathering protocol. This makes it possible to provide designs that are always based on the latest market needs. The data is preprocessed using the Python Pandas library to impute missing values ​​and remove outliers.

[0180] Subsequently, the server uses machine learning algorithms to train a model for design generation. Frameworks such as TensorFlow and PyTorch are commonly used for this process. The generated model then produces design proposals based on user feedback, enabling suggestions tailored to customer needs.

[0181] The terminal presents design proposals sent from the server to the user and collects feedback from the user. The user then inputs specific comments via the terminal, providing their opinions to the system. This enables continuous design improvement based on feedback.

[0182] A sentiment engine is used for sentiment analysis. It analyzes comments included in user feedback and extracts sentiment indicators using natural language processing techniques. These indicators are directly used to improve the design, resulting in a more satisfying design.

[0183] As a concrete example, when considering the design of a new furniture set, if a user provides feedback such as "This color is unsettling," the emotion engine analyzes "anxiety" as an emotional indicator. Based on this analysis, the server adjusts the model and regenerates design proposals with calmer color schemes, which are then presented to the user.

[0184] An example of a prompt for a generative AI model is, "If the user prefers a calm design, please suggest suitable color schemes and styles."

[0185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0186] Step 1:

[0187] The server acquires market trend information using an information gathering protocol. As input, it sends data acquisition requests to the information source API and receives market data in JSON format from the API. Based on this data, the server performs data cleansing, such as imputing missing values ​​and removing outliers, using the Python Pandas library. The output is a dataset prepared in an analyzable format.

[0188] Step 2:

[0189] The server trains a machine learning model using pre-processed data. The input to this process is the previously processed dataset. The server uses frameworks such as TensorFlow and PyTorch to train a machine learning model for generating design proposals. The output is a trained model capable of meeting customer needs.

[0190] Step 3:

[0191] The server uses a trained generative AI model to generate design proposals based on customer needs. It takes the model obtained in the previous step and requirements extracted from user feedback as input. Prompts are used to specify generation conditions, such as "If the user prefers a calm design, suggest suitable color schemes and styles." The output is an optimized design proposal.

[0192] Step 4:

[0193] The terminal presents the user with design proposals provided by the server. The input for this process is the design proposals received from the server. The terminal outputs the design proposals visually through the user interface.

[0194] Step 5:

[0195] Users review the presented design proposals and input feedback into their devices. This feedback includes free-form comments and opinions on the designs. The user's feedback is sent to the server in real time via the device.

[0196] Step 6:

[0197] The server performs sentiment analysis on the user feedback it receives. It takes the feedback text data as input and analyzes the text using natural language processing techniques. Using an emotion engine, it extracts the user's sentiment indicators, and the output is a dataset containing sentiment information.

[0198] Step 7:

[0199] The server refines the design proposal based on the data obtained from sentiment analysis. This process uses the acquired sentiment data as input to adjust the design elements. Finally, the improved design proposal is generated and presented to the user again through the terminal.

[0200] (Application Example 2)

[0201] 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".

[0202] Providing personalized designs that appropriately incorporate user emotions and feedback in advertising and product design has traditionally been a challenging task. In particular, there is a need to analyze user emotions in real time and immediately optimize designs based on that analysis. This necessitates establishing an effective feedback cycle to enhance user satisfaction.

[0203] 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.

[0204] In this invention, the server includes data acquisition means, data formatting means, and means for training a learning model. This makes it possible to analyze user feedback and emotions collected via information terminals and optimize design proposals in real time based on them.

[0205] A "data acquisition method" is a mechanism for collecting data from information sources and using it to generate and optimize design proposals.

[0206] "Data formatting means" refers to a function that performs the process of processing and normalizing collected data into an analyzable format.

[0207] "Methods for training a learning model" refers to the process of training a model using a machine learning algorithm and generating design proposals based on user requirements.

[0208] "Means for generating design proposals based on user requirements" refers to a process that automatically proposes designs according to the user's requests and specifications.

[0209] "Means for receiving user feedback" refers to an interface for collecting feedback and opinions from users via information terminals.

[0210] "Means of improving a design proposal" refers to algorithms or methods for modifying an existing design proposal into a more optimal form based on the feedback received.

[0211] "Methods for determining the final design and converting it into product specifications" refers to a set of procedures for finalizing an improved design proposal as a concrete product specification and applying it to the actual product.

[0212] An "emotion analysis tool" is a technological mechanism that analyzes user feedback, identifies the emotions contained within it, and reflects these findings in design improvements.

[0213] "A means of presenting information on information terminals in real time and promoting re-evaluation" refers to a system that immediately displays the improved design on the user's terminal and conducts a cyclical evaluation by soliciting further feedback.

[0214] The system for implementing this invention comprises multiple means, including data acquisition, data formatting, training of a learning model, sentiment analysis, and optimization of design proposals. These means are intended to provide personalized content based on user feedback, particularly in the fields of advertising and product design.

[0215] The server first retrieves data from the information source. During this process, it uses the information source interface to collect relevant data such as market trend information. The collected data is then formatted and converted into a parseable format using libraries such as Python's NumPy and Pandas.

[0216] Next, the collected and formatted data is used to train a learning model on the server. This training utilizes natural language processing techniques to extract useful information from the collected feedback and generate design proposals based on user requirements.

[0217] The collected feedback includes eye-tracking data and audio feedback, and sentiment indicators are extracted using sentiment analysis tools such as TensorFlow. For example, if a user sees an advertisement through smart glasses and responds with "This doesn't put me in a good mood this morning," the sentiment engine analyzes this as "low energy." Based on this information, the server optimizes the design proposal and creates new ad designs and messages using a generative AI model.

[0218] The optimized design is immediately delivered to information terminals, and additional feedback from users is encouraged, enabling a continuous evaluation cycle. In this process, the AI ​​model is instructed using a prompt message such as, "User sentiment: Low energy. Product name: Coffee machine. Please suggest the best advertising message and design."

[0219] This system enables real-time design optimization that takes user emotions into account, thereby enhancing the appeal of advertisements and products.

[0220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0221] Step 1:

[0222] The server retrieves market trend information from data sources through an information source interface. The input is the data source, and the output is raw market trend data. This data forms the basis for subsequent design proposal generation.

[0223] Step 2:

[0224] The server uses Python's NumPy and Pandas to format the acquired market trend data. The input is unformatted market trend data, and the output is data normalized into a parseable format. Specifically, it cleans up irregular data and arranges it into a consistent format.

[0225] Step 3:

[0226] The server trains a learning model based on the formatted data. The input is normalized data, and the output is a trained model that generates design proposals based on user requirements. Specifically, it uses natural language processing techniques to extract useful patterns from the data.

[0227] Step 4:

[0228] The device receives feedback from the user. Input consists of user eye-tracking data and voice comments, while output is unanalyzed feedback data sent to the server via the device. This feedback is sent to the server in real time.

[0229] Step 5:

[0230] The server extracts sentiment indicators from feedback data using sentiment analysis methods such as TensorFlow. The input is unanalyzed feedback data, and the output is analyzed data including sentiment indicators. Specifically, it identifies the user's emotions from voice comments using natural language processing.

[0231] Step 6:

[0232] The server optimizes design proposals using a generative AI model based on sentiment indicators. The inputs are sentiment indicators and a trained model, while the output is the optimized design proposal. Specifically, it provides the generative AI model with prompts suggesting new designs or messages, and retrieves appropriate results.

[0233] Step 7:

[0234] The device presents optimized design proposals to the user in real time and encourages further feedback. The input is the optimized design proposal, and the output is newly acquired user reactions and comments. The user then reviews this and makes their next evaluation.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] [Second Embodiment]

[0239] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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).

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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".

[0251] This invention is a system that combines data collection, preprocessing, AI-based design generation, and the reception and improvement of user feedback. Specifically, the system is realized through the use of a server, terminals, and users, each playing their respective roles.

[0252] Server Role

[0253] The server first collects market trend data from external sources such as social media and news sites. This information is used to understand customer needs and the latest trends. The server normalizes and cleans this data and prepares it for use in training AI models. Furthermore, the server also has the ability to generate new product design proposals using the trained AI models.

[0254] Terminal role

[0255] The terminal presents the user with design proposals sent from the server. The user evaluates the displayed design proposals and provides feedback. The terminal is responsible for sending this feedback to the server. Furthermore, once the final design is decided, the terminal can output the design as a product specification document.

[0256] User roles

[0257] Users review the design proposals presented on their devices and provide feedback on their preferences and areas for improvement. This feedback serves as valuable information for the server to improve the design.

[0258] Specific example

[0259] For example, if a company wants to develop a new smartphone case design, the server collects relevant data from Twitter and feedback platforms. Based on this data, the AI ​​learns about color and material trends and generates various design proposals. The device displays these design proposals to the user, who selects their favorite design and provides feedback on color adjustments and material changes. The server then receives this feedback, refines the design, and provides a final version. Finally, the device converts the selected design specifications into digital data for transmission to the manufacturing department.

[0260] Thus, the proposed system combines human creativity with machine learning technology to provide highly efficient and user-friendly product designs.

[0261] The following describes the processing flow.

[0262] Step 1:

[0263] The server collects market trend data and user feedback from specified APIs. This data is filtered based on pre-specified keywords and topics.

[0264] Step 2:

[0265] The server analyzes the collected raw data, filters out unnecessary information, and normalizes it. This makes the data clean and consistent.

[0266] Step 3:

[0267] The server uses pre-processed data to train a machine learning model. The model learns the factors and trends that influence the design.

[0268] Step 4:

[0269] The server generates new design proposals using the trained model. These generated design proposals reflect the user's past preferences and market trends.

[0270] Step 5:

[0271] The server sends the generated design proposal to the terminal. The terminal displays the design on its user interface.

[0272] Step 6:

[0273] Users review the design proposal displayed on their device and provide feedback on the design through the interface. This feedback often concerns color, shape, and functionality.

[0274] Step 7:

[0275] The server receives feedback from users and improves the design proposals. The feedback is reflected in the model, and new design proposals are generated as needed.

[0276] Step 8:

[0277] The terminal converts the user's selected final design into product design specifications. These specifications are then prepared as digital data for implementation in the manufacturing department.

[0278] (Example 1)

[0279] 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."

[0280] Traditional product design processes have made it difficult to quickly generate designs that effectively reflect customer needs and market trends. Furthermore, the inability to quickly incorporate user feedback and improve designs sometimes led to problems with the final product's market suitability.

[0281] 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.

[0282] In this invention, the server includes means for collecting data from external sources, means for processing the collected data and preparing it in a format suitable for machine learning, and means for generating design proposals based on customer requirements using a trained generative AI model. This enables the rapid generation of design proposals that reflect customer needs and market trends, and immediate design improvements based on user feedback.

[0283] The "means for collecting data from external information sources" refers to a device or method having a function of automatically acquiring necessary data from various information sources on the Internet.

[0284] The "means for processing the collected data and arranging it in a form suitable for machine learning" refers to a processing method for converting the acquired data into an analyzable form and performing correction of incomplete data and deletion of unnecessary data.

[0285] The "means for generating a design proposal based on customer requirements using a trained generative AI model" refers to a technology that pre-learns a machine learning algorithm and automatically generates a new design according to user needs using that model.

[0286] The "means for receiving feedback from users" refers to an interface or process for recording opinions and desires provided by users in the system and reflecting them in the next action.

[0287] The "means for improving the design proposal" refers to a method for improving the generated design based on user feedback and correcting it to be of higher quality and meeting the needs.

[0288] The "means for converting the final design into the specification format of the product" refers to a process or system for converting the completed design proposal into a form adaptable to the manufacturing process so that it can be used in actual product manufacturing.

[0289] "In the information acquisition means, acquiring market trend information using an API" refers to a technology for acquiring real-time market trend and consumer trend data using a specific application program interface.

[0290] "Applying natural language processing technology" refers to a method of using technology for machines to understand and process human language to utilize language data in model training and design generation.

[0291] The following describes embodiments for carrying out the invention.

[0292] This invention is a system that highly automates data collection and processing, AI-powered design generation, and the collection and incorporation of user feedback. Specifically, it is operated by having three parties—a server, a terminal, and a user—each play different roles.

[0293] Server Role

[0294] The server plays a central role in collecting data from diverse sources. Specifically, the server uses scraping tools such as Python's BeautifulSoup and Selenium to collect information from social media and news sites. The server processes this data using machine learning libraries such as Pandas and NumPy, converting it into a format suitable for training AI models. Then, it uses the trained generative AI model to generate new design proposals based on customer requirements. Machine learning frameworks such as TensorFlow and PyTorch are used to train the generative AI model. During generation, specific prompt statements are provided as input to create appropriate design proposals.

[0295] Terminal role

[0296] The terminal provides an interface that presents design proposals sent from the server to the user. Specifically, it utilizes front-end libraries such as React and Vue.js to build a user-friendly UI. Through this UI, the user evaluates the design proposals and provides feedback. The terminal then sends this feedback back to the server. This exchange enables a process of improving the design based on user requests.

[0297] User roles

[0298] Users review the design proposals displayed on their devices and evaluate whether each design matches their needs and preferences. They can provide specific feedback, such as "Make this color more vibrant" or "Change this material." This user feedback is then sent to the server and used to improve the designs.

[0299] Examples of specific cases and prompt statements

[0300] For example, when a company designs a new smartphone case, the server collects data from social media and feedback platforms, and an AI model generates design proposals based on that data. An example of a prompt used for generation is, "Generate smartphone case design proposals that reflect the latest color trends." In this way, the design cycle, including user feedback, is efficiently managed.

[0301] This system combines human creativity with machine learning technology to provide rapid and highly adaptable product designs.

[0302] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0303] Step 1:

[0304] The server collects data from external sources. Specifically, the server uses APIs from social media and news sites to obtain text and image data related to market trends. This data is used as input data to understand customer needs. The obtained data is stored in storage so that it can be reused in the next processing step.

[0305] Step 2:

[0306] The server preprocesses the collected data. Since the input data may contain missing values or noise, the server uses Pandas and NumPy to clean and normalize the data. This data processing outputs a clean dataset suitable for training a machine learning model.

[0307] Step 3:

[0308] The server uses a generative AI model to generate design proposals. Using the clean dataset as input, an AI model trained with TensorFlow or PyTorch generates various design proposals. Using the prompt sentence "Please generate a design proposal that reflects the latest color trends", a design that meets the user's needs is output.

[0309] Step 4:

[0310] The terminal presents the design proposals received from the server to the user. The terminal generates a UI using React or Vue.js, and the user can view various design proposals on the screen. The design proposals are displayed visually and clearly, enabling the user to make intuitive selections and evaluations.

[0311] Step 5:

[0312] The user evaluates the presented design proposals and inputs feedback. The user inputs specific requirements and areas for improvement, for example, in the form of "I want to adjust the color of this design", into the terminal. The user's feedback is important information for improvement in the next step.

[0313] Step 6:

[0314] The terminal sends the user's feedback to the server. The feedback is sent to the server using HTTP communication and is arranged in a format that can be easily analyzed. After the data arrives at the server, preparations are made for the next improvement step.

[0315] Step 7:

[0316] The server improves the design proposal based on user feedback. Using the feedback as input, an AI model is used to improve the design. The improved design proposal is generated as a new output, better meeting user needs.

[0317] Step 8:

[0318] Once the final design is decided, the terminal converts it into a product specification. The selected design is output as digital data in PDF or CAD format, ready to be sent to the manufacturing department. The terminal automates this conversion, enabling a rapid data flow.

[0319] (Application Example 1)

[0320] 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."

[0321] In today's advertising industry, creating effective advertising designs that quickly respond to consumer needs and market trends is crucial. However, traditional methods struggle to grasp market trends and incorporate consumer feedback, and these processes are time-consuming and resource-intensive.

[0322] 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.

[0323] In this invention, the server includes data collection means, preprocessing means, and means for training a machine learning model. This makes it possible to quickly grasp market trends and generate effective advertising designs that reflect consumer feedback.

[0324] "Data collection methods" refer to the function of acquiring trend data from external sources in order to understand market trends and consumer needs.

[0325] "Preprocessing means" refers to functions that normalize collected data and prepare it in a format suitable for training machine learning models.

[0326] "Methods for training machine learning models" refer to functions that enable AI models to learn using collected and pre-processed data, thereby giving them the ability to generate new advertising ideas.

[0327] "Methods for generating advertising proposals" refers to a function that utilizes machine learning models to create appropriate advertising design proposals based on market trends and other factors.

[0328] "Means of receiving user feedback" refers to a function that collects consumer evaluations and suggestions for improvement regarding advertising proposals.

[0329] "Means for improving ad drafts" refers to a function that modifies generated ad drafts to make them more effective based on collected user feedback.

[0330] "Means of determining and converting advertisements into distribution specifications" refers to the function of finalizing the advertisement design and converting it into a format suitable for use and distribution.

[0331] This invention is a system that generates advertising designs that quickly respond to market trends in the advertising industry and effectively reflect consumer needs. The system mainly consists of three elements: a server, a terminal, and a user.

[0332] The server is responsible for collecting market trend data from external sources using APIs. The collected data is analyzed using libraries such as BeautifulSoup and Scrapy in the Python language, and normalized and cleansed using Pandas. Next, an AI model is trained on the data using machine learning libraries such as TensorFlow. This trained generative AI model has the function of generating advertising design proposals based on market trends.

[0333] The device provides the user with an interface through which the user can view multiple generated design proposals. The application primarily uses Flutter, allowing the user to select their preferred design on the interface and provide feedback on its evaluation and potential improvements.

[0334] User feedback is sent back to the server, which then uses it to refine the ad design. Ultimately, the most effective ad design is determined and converted by the server into a distribution specification.

[0335] For example, when a server generates an advertising design for a new beverage, the prompt would be, "Generate an advertising design proposal that emphasizes the modern and healthy image of the new beverage brand." This is expected to generate advertising designs that accurately capture market needs in a short amount of time.

[0336] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0337] Step 1:

[0338] The server collects market trend data from external sources via APIs. The input to this data collection is market trend information provided by the API, and the output is raw market trend data. The server then uses analysis tools (such as BeautifulSoup or Scrapy) to extract the necessary information and format it into a dataset.

[0339] Step 2:

[0340] The server processes the formatted market trend data using the Pandas library. The input contains raw market trend data, and the output is normalized and cleaned data. The normalization process unifies the data format and removes unnecessary data.

[0341] Step 3:

[0342] The server trains a machine learning model using TensorFlow. The input for this step is pre-processed market trend data, and the output is a generative AI model. The machine learning model learns trends from the provided data and gains foundational knowledge to generate advertising designs.

[0343] Step 4:

[0344] The user receives ad design proposals sent from the server via a Flutter app on their device. The input is the generated ad design proposal, which the user evaluates. The output is the user's feedback, including the evaluation information.

[0345] Step 5:

[0346] The server improves the ad design based on feedback received from the terminal. The input is user feedback, and the output is the improved ad design proposal. The server analyzes the content of the feedback, incorporates it into the generating AI model, and adjusts the ad proposal.

[0347] Step 6:

[0348] Finally, the server finalizes the optimized ad draft and converts it into a distributable format. The input for this step is the improved ad design draft, and the output is the final ad design usable on the advertising medium. The server converts this into a digital format and prepares it for distribution.

[0349] 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.

[0350] This invention is a system that optimizes designs by taking user emotions into account, in addition to data collection, preprocessing, and AI model-based design proposal generation, by incorporating an emotion engine. This system aims to provide more personalized designs by analyzing the emotional state of users, particularly when receiving feedback.

[0351] Server Role

[0352] The server collects market trend information via information source APIs, performs data cleansing and normalization, and trains machine learning models on the collected data to generate design proposals that reflect customer requirements. Furthermore, the server utilizes an emotion engine to analyze the emotions contained in user feedback and uses this information to improve the design process.

[0353] Functions of the Emotion Engine

[0354] The emotion engine performs natural language processing on comments and feedback entered by users through their devices, and extracts emotional indicators from them. These indicators reflect user preferences and frustrations and are used to evaluate and improve design proposals.

[0355] Terminal role

[0356] The device presents design proposals sent from the server to the user and receives feedback from the user. The device sends this feedback to the server in real time, including sentiment data analyzed by the sentiment engine.

[0357] User roles

[0358] Users review the design proposals presented on their devices and provide feedback, frankly recording their feelings and opinions. The interaction is designed with the intention that this feedback will lead to better design improvements.

[0359] Specific example

[0360] For example, when designing a new furniture set, if a user provides feedback such as "This color is unsettling," the emotion engine analyzes "anxiety" as an emotional metric. The server incorporates this data into its model and generates design proposals with more calming color schemes. The terminal then presents the improved design to the user and obtains further feedback.

[0361] Thus, the present invention builds a feedback cycle that incorporates user emotions and achieves advanced design optimization to enhance user satisfaction.

[0362] The following describes the processing flow.

[0363] Step 1:

[0364] The server collects market trend data via information source APIs. This data is used to understand consumer opinions and trends related to products.

[0365] Step 2:

[0366] The server normalizes the collected data and performs data cleansing to remove noise. This prepares the data for analysis.

[0367] Step 3:

[0368] The server trains a machine learning model using clean data. This model is responsible for learning trends and patterns that influence the design.

[0369] Step 4:

[0370] The server uses the trained model to generate design proposals based on customer requirements. These design proposals will reflect historical trend data.

[0371] Step 5:

[0372] The terminal displays design proposals sent from the server on its user interface. The user reviews these and forms their first impression.

[0373] Step 6:

[0374] Users provide specific comments as feedback on the design proposals displayed on their devices. This feedback may include comments on particular colors or shapes.

[0375] Step 7:

[0376] The device sends user feedback to the server. Simultaneously, it also includes data for sentiment analysis by the emotion engine.

[0377] Step 8:

[0378] The server uses an emotion engine to analyze user feedback and extract emotion metrics. These emotion metrics, in the form of "satisfied" or "dissatisfied," are used to improve the design.

[0379] Step 9:

[0380] The server improves the design proposal based on the analyzed sentiment data. The improved design becomes personalized, reflecting the user's emotional state.

[0381] Step 10:

[0382] The device receives a new design proposal from the server again and presents it to the user. The user reviews this new proposal and provides further evaluation and feedback.

[0383] Through this processing flow, the system quickly generates design proposals that take user emotions and feedback into account, aiming to improve user satisfaction.

[0384] (Example 2)

[0385] 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".

[0386] To meet the diverse needs of today's consumers, it is crucial to quickly generate designs that reflect the emotions and preferences of individual customers and to continuously improve them. However, traditional design processes struggle to adequately reflect user opinions and lack mechanisms for efficiently analyzing collected feedback and incorporating it into designs. This raises concerns about declining consumer satisfaction and reduced competitiveness in the market.

[0387] 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.

[0388] In this invention, the server includes means for collecting information, means for preprocessing the data, and means for training the data using machine learning algorithms. This makes it possible to process user feedback through sentiment analysis, quickly propose more personalized designs, and enable a continuous improvement cycle.

[0389] "Means of collecting information" refers to protocols and interfaces for obtaining market trends and customer demands.

[0390] "Methods for preprocessing data" refers to the process of converting collected data into an analyzable format and handling missing or outlier values.

[0391] "Methods for training data using machine learning algorithms" refers to the process of generating a machine learning model using training data and optimizing the model so that it can perform pattern recognition and prediction.

[0392] "Methods for proposing designs" refers to the process of considering customer needs and presenting unique product designs and service plans using generative AI models.

[0393] "Means of receiving feedback from users" refers to the process of collecting opinions and impressions from end users and inputting that information into the system in an analyzable format.

[0394] "Methods for processing and improving design through sentiment analysis" refers to the process of analyzing emotional information contained in user feedback and reflecting the results in improving designs and proposals.

[0395] "Methods for finalizing the design and converting it into the specifications of an actual product" refers to the process of translating the finalized design proposal into detailed specifications and proposing it as a production-ready technical document.

[0396] This invention is a system for providing personalized designs to individual users. The server collects market trend information using an information gathering protocol. This makes it possible to provide designs that are always based on the latest market needs. The data is preprocessed using the Python Pandas library to impute missing values ​​and remove outliers.

[0397] Subsequently, the server uses machine learning algorithms to train a model for design generation. Frameworks such as TensorFlow and PyTorch are commonly used for this process. The generated model then produces design proposals based on user feedback, enabling suggestions tailored to customer needs.

[0398] The terminal presents design proposals sent from the server to the user and collects feedback from the user. The user then inputs specific comments via the terminal, providing their opinions to the system. This enables continuous design improvement based on feedback.

[0399] A sentiment engine is used for sentiment analysis. It analyzes comments included in user feedback and extracts sentiment indicators using natural language processing techniques. These indicators are directly used to improve the design, resulting in a more satisfying design.

[0400] As a concrete example, when considering the design of a new furniture set, if a user provides feedback such as "This color is unsettling," the emotion engine analyzes "anxiety" as an emotional indicator. Based on this analysis, the server adjusts the model and regenerates design proposals with calmer color schemes, which are then presented to the user.

[0401] An example of a prompt for a generative AI model is, "If the user prefers a calm design, please suggest suitable color schemes and styles."

[0402] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0403] Step 1:

[0404] The server acquires market trend information using an information gathering protocol. As input, it sends data acquisition requests to the information source API and receives market data in JSON format from the API. Based on this data, the server performs data cleansing, such as imputing missing values ​​and removing outliers, using the Python Pandas library. The output is a dataset prepared in an analyzable format.

[0405] Step 2:

[0406] The server trains a machine learning model using pre-processed data. The input to this process is the previously processed dataset. The server uses frameworks such as TensorFlow and PyTorch to train a machine learning model for generating design proposals. The output is a trained model capable of meeting customer needs.

[0407] Step 3:

[0408] The server uses a trained generative AI model to generate design proposals based on customer needs. It takes the model obtained in the previous step and requirements extracted from user feedback as input. Prompts are used to specify generation conditions, such as "If the user prefers a calm design, suggest suitable color schemes and styles." The output is an optimized design proposal.

[0409] Step 4:

[0410] The terminal presents the user with design proposals provided by the server. The input for this process is the design proposals received from the server. The terminal outputs the design proposals visually through the user interface.

[0411] Step 5:

[0412] Users review the presented design proposals and input feedback into their devices. This feedback includes free-form comments and opinions on the designs. The user's feedback is sent to the server in real time via the device.

[0413] Step 6:

[0414] The server performs sentiment analysis on the user feedback it receives. It takes the feedback text data as input and analyzes the text using natural language processing techniques. Using an emotion engine, it extracts the user's sentiment indicators, and the output is a dataset containing sentiment information.

[0415] Step 7:

[0416] The server refines the design proposal based on the data obtained from sentiment analysis. This process uses the acquired sentiment data as input to adjust the design elements. Finally, the improved design proposal is generated and presented to the user again through the terminal.

[0417] (Application Example 2)

[0418] 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."

[0419] Providing personalized designs that appropriately incorporate user emotions and feedback in advertising and product design has traditionally been a challenging task. In particular, there is a need to analyze user emotions in real time and immediately optimize designs based on that analysis. This necessitates establishing an effective feedback cycle to enhance user satisfaction.

[0420] 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.

[0421] In this invention, the server includes data acquisition means, data formatting means, and means for training a learning model. This makes it possible to analyze user feedback and emotions collected via information terminals and optimize design proposals in real time based on them.

[0422] A "data acquisition method" is a mechanism for collecting data from information sources and using it to generate and optimize design proposals.

[0423] "Data formatting means" refers to a function that performs the process of processing and normalizing collected data into an analyzable format.

[0424] "Methods for training a learning model" refers to the process of training a model using a machine learning algorithm and generating design proposals based on user requirements.

[0425] "Means for generating design proposals based on user requirements" refers to a process that automatically proposes designs according to the user's requests and specifications.

[0426] "Means for receiving user feedback" refers to an interface for collecting feedback and opinions from users via information terminals.

[0427] "Means for improving a design proposal" refers to algorithms or methods for modifying an existing design proposal into a more optimal form based on the feedback received.

[0428] "Means of determining the final design and converting it into product specifications" refers to a set of procedures for finalizing an improved design proposal as a concrete product specification and applying it to the actual product.

[0429] An "emotion analysis tool" is a technological mechanism that analyzes user feedback, identifies the emotions contained within it, and reflects these findings in design improvements.

[0430] "A means of presenting information on information terminals in real time and promoting re-evaluation" refers to a system that immediately displays the improved design on the user's terminal and conducts a cyclical evaluation by soliciting further feedback.

[0431] The system for implementing this invention comprises multiple means, including data acquisition, data formatting, training of a learning model, sentiment analysis, and optimization of design proposals. These means are intended to provide personalized content based on user feedback, particularly in the fields of advertising and product design.

[0432] The server first retrieves data from the information source. During this process, it uses the information source interface to collect relevant data such as market trend information. The collected data is then formatted and converted into a parseable format using libraries such as Python's NumPy and Pandas.

[0433] Next, the collected and formatted data is used to train a learning model on the server. This training utilizes natural language processing techniques to extract useful information from the collected feedback and generate design proposals based on user requirements.

[0434] The collected feedback includes eye-tracking data and audio feedback, and sentiment indicators are extracted using sentiment analysis tools such as TensorFlow. For example, if a user sees an advertisement through smart glasses and responds with "This doesn't put me in a good mood this morning," the sentiment engine analyzes this as "low energy." Based on this information, the server optimizes the design proposal and creates new ad designs and messages using a generative AI model.

[0435] The optimized design is immediately delivered to information terminals, and additional feedback from users is encouraged, enabling a continuous evaluation cycle. In this process, the AI ​​model is instructed using a prompt message such as, "User sentiment: Low energy. Product name: Coffee machine. Please suggest the best advertising message and design."

[0436] This system enables real-time design optimization that takes user emotions into account, thereby enhancing the appeal of advertisements and products.

[0437] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0438] Step 1:

[0439] The server retrieves market trend information from data sources through an information source interface. The input is the data source, and the output is raw market trend data. This data forms the basis for subsequent design proposal generation.

[0440] Step 2:

[0441] The server uses Python's NumPy and Pandas to format the acquired market trend data. The input is unformatted market trend data, and the output is data normalized into a parseable format. Specifically, it cleans up irregular data and arranges it into a consistent format.

[0442] Step 3:

[0443] The server trains a learning model based on the formatted data. The input is normalized data, and the output is a trained model that generates design proposals based on user requirements. Specifically, it uses natural language processing techniques to extract useful patterns from the data.

[0444] Step 4:

[0445] The device receives feedback from the user. Input consists of user eye-tracking data and voice comments, while output is unanalyzed feedback data sent to the server via the device. This feedback is sent to the server in real time.

[0446] Step 5:

[0447] The server extracts sentiment indicators from feedback data using sentiment analysis methods such as TensorFlow. The input is unanalyzed feedback data, and the output is analyzed data including sentiment indicators. Specifically, it identifies the user's emotions from voice comments using natural language processing.

[0448] Step 6:

[0449] The server optimizes design proposals using a generative AI model based on sentiment indicators. The inputs are sentiment indicators and a trained model, while the output is the optimized design proposal. Specifically, it provides the generative AI model with prompts suggesting new designs or messages, and retrieves appropriate results.

[0450] Step 7:

[0451] The device presents optimized design proposals to the user in real time and encourages further feedback. The input is the optimized design proposal, and the output is newly acquired user reactions and comments. The user then reviews this and makes their next evaluation.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] [Third Embodiment]

[0456] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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".

[0468] This invention is a system that combines data collection, preprocessing, AI-based design generation, and the reception and improvement of user feedback. Specifically, the system is realized through the use of a server, terminals, and users, each playing their respective roles.

[0469] Server Role

[0470] The server first collects market trend data from external sources such as social media and news sites. This information is used to understand customer needs and the latest trends. The server normalizes and cleans this data and prepares it for use in training AI models. Furthermore, the server also has the ability to generate new product design proposals using the trained AI models.

[0471] Terminal role

[0472] The terminal presents the user with design proposals sent from the server. The user evaluates the displayed design proposals and provides feedback. The terminal is responsible for sending this feedback to the server. Furthermore, once the final design is decided, the terminal can output the design as a product specification document.

[0473] User roles

[0474] Users review the design proposals presented on their devices and provide feedback on their preferences and areas for improvement. This feedback serves as valuable information for the server to improve the design.

[0475] Specific example

[0476] For example, if a company wants to develop a new smartphone case design, the server collects relevant data from Twitter and feedback platforms. Based on this data, the AI ​​learns about color and material trends and generates various design proposals. The device displays these design proposals to the user, who selects their favorite design and provides feedback on color adjustments and material changes. The server then receives this feedback, refines the design, and provides a final version. Finally, the device converts the selected design specifications into digital data for transmission to the manufacturing department.

[0477] Thus, the proposed system combines human creativity with machine learning technology to provide highly efficient and user-friendly product designs.

[0478] The following describes the processing flow.

[0479] Step 1:

[0480] The server collects market trend data and user feedback from specified APIs. This data is filtered based on pre-specified keywords and topics.

[0481] Step 2:

[0482] The server analyzes the collected raw data, filters out unnecessary information, and normalizes it. This makes the data clean and consistent.

[0483] Step 3:

[0484] The server uses pre-processed data to train a machine learning model. The model learns the factors and trends that influence the design.

[0485] Step 4:

[0486] The server generates new design proposals using the trained model. These generated design proposals reflect the user's past preferences and market trends.

[0487] Step 5:

[0488] The server sends the generated design proposal to the terminal. The terminal displays the design on its user interface.

[0489] Step 6:

[0490] Users review the design proposal displayed on their device and provide feedback on the design through the interface. This feedback often concerns color, shape, and functionality.

[0491] Step 7:

[0492] The server receives feedback from users and improves the design proposals. The feedback is reflected in the model, and new design proposals are generated as needed.

[0493] Step 8:

[0494] The terminal converts the user's selected final design into product design specifications. These specifications are then prepared as digital data for implementation in the manufacturing department.

[0495] (Example 1)

[0496] 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."

[0497] Traditional product design processes have made it difficult to quickly generate designs that effectively reflect customer needs and market trends. Furthermore, the inability to quickly incorporate user feedback and improve designs sometimes led to problems with the final product's market suitability.

[0498] 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.

[0499] In this invention, the server includes means for collecting data from external sources, means for processing the collected data and preparing it in a format suitable for machine learning, and means for generating design proposals based on customer requirements using a trained generative AI model. This enables the rapid generation of design proposals that reflect customer needs and market trends, and immediate design improvements based on user feedback.

[0500] "Means for collecting data from external sources" refers to a device or method that has the function of automatically acquiring necessary data from various sources on the internet.

[0501] "Methods for processing collected data and preparing it in a format suitable for machine learning" refers to processing methods that convert acquired data into an analyzable format, correct incomplete data, and delete unnecessary data.

[0502] "A means of generating design proposals based on customer requirements using a trained generative AI model" refers to a technology that pre-trains a machine learning algorithm and uses that model to automatically generate new designs that meet user needs.

[0503] "Means of receiving user feedback" refers to interfaces and processes that record user opinions and requests within the system and reflect them in subsequent actions.

[0504] "Methods for improving design proposals" refer to methods for improving generated designs based on user feedback, and modifying them to be of higher quality and better meet user needs.

[0505] "Means of converting a final design into a product specification format" refers to a process or system for converting a completed design proposal into a format that is adaptable to the manufacturing process and can be used in actual product manufacturing.

[0506] "Acquiring market trend information using APIs as a means of information acquisition" refers to a technology that uses a specific application program interface to acquire market trends and consumer behavior data in real time.

[0507] "Applying natural language processing technology" means using technology that allows machines to understand and process human language to utilize language data for model training and design generation.

[0508] The following describes embodiments for carrying out the invention.

[0509] This invention is a system that highly automates data collection and processing, AI-powered design generation, and the collection and incorporation of user feedback. Specifically, it is operated by having three parties—a server, a terminal, and a user—each play different roles.

[0510] Server Role

[0511] The server plays a central role in collecting data from diverse sources. Specifically, the server uses scraping tools such as Python's BeautifulSoup and Selenium to collect information from social media and news sites. The server processes this data using machine learning libraries such as Pandas and NumPy, converting it into a format suitable for training AI models. Then, it uses the trained generative AI model to generate new design proposals based on customer requirements. Machine learning frameworks such as TensorFlow and PyTorch are used to train the generative AI model. During generation, specific prompt statements are provided as input to create appropriate design proposals.

[0512] Terminal role

[0513] The terminal provides an interface that presents design proposals sent from the server to the user. Specifically, it utilizes front-end libraries such as React and Vue.js to build a user-friendly UI. Through this UI, the user evaluates the design proposals and provides feedback. The terminal then sends this feedback back to the server. This exchange enables a process of improving the design based on user requests.

[0514] User roles

[0515] Users review the design proposals displayed on their devices and evaluate whether each design matches their needs and preferences. They can provide specific feedback, such as "Make this color more vibrant" or "Change this material." This user feedback is then sent to the server and used to improve the designs.

[0516] Examples of specific cases and prompt statements

[0517] For example, when a company designs a new smartphone case, the server collects data from social media and feedback platforms, and an AI model generates design proposals based on that data. An example of a prompt used for generation is, "Generate smartphone case design proposals that reflect the latest color trends." In this way, the design cycle, including user feedback, is efficiently managed.

[0518] This system combines human creativity with machine learning technology to provide rapid and highly adaptable product designs.

[0519] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0520] Step 1:

[0521] The server collects data from external sources. Specifically, the server uses APIs from social media and news sites to obtain text and image data related to market trends. This data is used as input data to understand customer needs. The obtained data is stored in storage so that it can be reused in the next processing step.

[0522] Step 2:

[0523] The server preprocesses the collected data. Since the input data may contain missing values ​​or noise, the server cleans and normalizes the data using Pandas and NumPy. This data processing outputs a clean dataset suitable for training machine learning models.

[0524] Step 3:

[0525] The server generates design proposals using a generative AI model. Using a clean dataset as input, the AI ​​model, trained with TensorFlow or PyTorch, generates a variety of design proposals. Using the prompt "Generate design proposals that reflect the latest color trends," designs that meet user needs are output.

[0526] Step 4:

[0527] The device presents design proposals received from the server to the user. The device generates a UI using React or Vue.js, allowing the user to view various design proposals on the screen. The design proposals are displayed in a visually clear manner, enabling the user to intuitively select and evaluate them.

[0528] Step 5:

[0529] Users evaluate the presented design proposals and provide feedback. They input specific requests and suggestions for improvement in a format such as, "I'd like the colors in this design adjusted." User feedback is crucial information for improvements in the next step.

[0530] Step 6:

[0531] The device sends user feedback to the server. The feedback is sent to the server using HTTP communication and formatted for easy analysis. Once the data arrives at the server, it is ready for the next improvement step.

[0532] Step 7:

[0533] The server improves the design proposal based on user feedback. Using the feedback as input, an AI model is used to improve the design. The improved design proposal is generated as a new output, better meeting user needs.

[0534] Step 8:

[0535] Once the final design is decided, the terminal converts it into a product specification. The selected design is output as digital data in PDF or CAD format, ready to be sent to the manufacturing department. The terminal automates this conversion, enabling a rapid data flow.

[0536] (Application Example 1)

[0537] 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."

[0538] In today's advertising industry, creating effective advertising designs that quickly respond to consumer needs and market trends is crucial. However, traditional methods struggle to grasp market trends and incorporate consumer feedback, and these processes are time-consuming and resource-intensive.

[0539] 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.

[0540] In this invention, the server includes data collection means, preprocessing means, and means for training a machine learning model. This makes it possible to quickly grasp market trends and generate effective advertising designs that reflect consumer feedback.

[0541] "Data collection methods" refer to the function of acquiring trend data from external sources in order to understand market trends and consumer needs.

[0542] "Preprocessing means" refers to functions that normalize collected data and prepare it in a format suitable for training machine learning models.

[0543] "Methods for training machine learning models" refer to functions that enable AI models to learn using collected and pre-processed data, thereby giving them the ability to generate new advertising ideas.

[0544] "Methods for generating advertising proposals" refers to a function that utilizes machine learning models to create appropriate advertising design proposals based on market trends and other factors.

[0545] "Means of receiving user feedback" refers to a function that collects consumer evaluations and suggestions for improvement regarding advertising proposals.

[0546] "Means for improving ad drafts" refers to a function that modifies generated ad drafts to make them more effective based on collected user feedback.

[0547] "Means of determining and converting advertisements into distribution specifications" refers to the function of finalizing the advertisement design and converting it into a format suitable for use and distribution.

[0548] This invention is a system that generates advertising designs that quickly respond to market trends in the advertising industry and effectively reflect consumer needs. The system mainly consists of three elements: a server, a terminal, and a user.

[0549] The server is responsible for collecting market trend data from external sources using APIs. The collected data is analyzed using libraries such as BeautifulSoup and Scrapy in the Python language, and normalized and cleansed using Pandas. Next, an AI model is trained on the data using machine learning libraries such as TensorFlow. This trained generative AI model has the function of generating advertising design proposals based on market trends.

[0550] The device provides the user with an interface through which the user can view multiple generated design proposals. The application primarily uses Flutter, allowing the user to select their preferred design on the interface and provide feedback on its evaluation and potential improvements.

[0551] User feedback is sent back to the server, which then uses it to refine the ad design. Ultimately, the most effective ad design is determined and converted by the server into a distribution specification.

[0552] For example, when a server generates an advertising design for a new beverage, the prompt would be, "Generate an advertising design proposal that emphasizes the modern and healthy image of the new beverage brand." This is expected to generate advertising designs that accurately capture market needs in a short amount of time.

[0553] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0554] Step 1:

[0555] The server collects market trend data from external sources via APIs. The input to this data collection is market trend information provided by the API, and the output is raw market trend data. The server then uses analysis tools (such as BeautifulSoup or Scrapy) to extract the necessary information and format it into a dataset.

[0556] Step 2:

[0557] The server processes the formatted market trend data using the Pandas library. The input contains raw market trend data, and the output is normalized and cleaned data. The normalization process unifies the data format and removes unnecessary data.

[0558] Step 3:

[0559] The server trains a machine learning model using TensorFlow. The input for this step is pre-processed market trend data, and the output is a generative AI model. The machine learning model learns trends from the provided data and gains foundational knowledge to generate advertising designs.

[0560] Step 4:

[0561] The user receives ad design proposals sent from the server via a Flutter app on their device. The input is the generated ad design proposal, which the user evaluates. The output is the user's feedback, including the evaluation information.

[0562] Step 5:

[0563] The server improves the ad design based on feedback received from the terminal. The input is user feedback, and the output is the improved ad design proposal. The server analyzes the content of the feedback, incorporates it into the generating AI model, and adjusts the ad proposal.

[0564] Step 6:

[0565] Finally, the server finalizes the optimized ad draft and converts it into a distributable format. The input for this step is the improved ad design draft, and the output is the final ad design usable on the advertising medium. The server converts this into a digital format and prepares it for distribution.

[0566] 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.

[0567] This invention is a system that optimizes designs by taking user emotions into account, in addition to data collection, preprocessing, and AI model-based design proposal generation, by incorporating an emotion engine. This system aims to provide more personalized designs by analyzing the emotional state of users, particularly when receiving feedback.

[0568] Server Role

[0569] The server collects market trend information via information source APIs, performs data cleansing and normalization, and trains machine learning models on the collected data to generate design proposals that reflect customer requirements. Furthermore, the server utilizes an emotion engine to analyze the emotions contained in user feedback and uses this information to improve the design process.

[0570] Functions of the Emotion Engine

[0571] The emotion engine performs natural language processing on comments and feedback entered by users through their devices, and extracts emotional indicators from them. These indicators reflect user preferences and frustrations and are used to evaluate and improve design proposals.

[0572] Terminal role

[0573] The device presents design proposals sent from the server to the user and receives feedback from the user. The device sends this feedback to the server in real time, including sentiment data analyzed by the sentiment engine.

[0574] User roles

[0575] Users review the design proposals presented on their devices and provide feedback, frankly recording their feelings and opinions. The interaction is designed with the intention that this feedback will lead to better design improvements.

[0576] Specific example

[0577] For example, when designing a new furniture set, if a user provides feedback such as "This color is unsettling," the emotion engine analyzes "anxiety" as an emotional metric. The server incorporates this data into its model and generates design proposals with more calming color schemes. The terminal then presents the improved design to the user and obtains further feedback.

[0578] Thus, the present invention builds a feedback cycle that incorporates user emotions and achieves advanced design optimization to enhance user satisfaction.

[0579] The following describes the processing flow.

[0580] Step 1:

[0581] The server collects market trend data via information source APIs. This data is used to understand consumer opinions and trends related to products.

[0582] Step 2:

[0583] The server normalizes the collected data and performs data cleansing to remove noise. This prepares the data for analysis.

[0584] Step 3:

[0585] The server trains a machine learning model using clean data. This model is responsible for learning trends and patterns that influence the design.

[0586] Step 4:

[0587] The server uses the trained model to generate design proposals based on customer requirements. These design proposals will reflect historical trend data.

[0588] Step 5:

[0589] The terminal displays design proposals sent from the server on its user interface. The user reviews these and forms their first impression.

[0590] Step 6:

[0591] Users provide specific comments as feedback on the design proposals displayed on their devices. This feedback may include comments on particular colors or shapes.

[0592] Step 7:

[0593] The device sends user feedback to the server. Simultaneously, it also includes data for sentiment analysis by the emotion engine.

[0594] Step 8:

[0595] The server uses an emotion engine to analyze user feedback and extract emotion metrics. These emotion metrics, in the form of "satisfied" or "dissatisfied," are used to improve the design.

[0596] Step 9:

[0597] The server improves the design proposal based on the analyzed sentiment data. The improved design becomes personalized, reflecting the user's emotional state.

[0598] Step 10:

[0599] The device receives a new design proposal from the server again and presents it to the user. The user reviews this new proposal and provides further evaluation and feedback.

[0600] Through this processing flow, the system quickly generates design proposals that take user emotions and feedback into account, aiming to improve user satisfaction.

[0601] (Example 2)

[0602] 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."

[0603] To meet the diverse needs of today's consumers, it is crucial to quickly generate designs that reflect the emotions and preferences of individual customers and to continuously improve them. However, traditional design processes struggle to adequately reflect user opinions and lack mechanisms for efficiently analyzing collected feedback and incorporating it into designs. This raises concerns about declining consumer satisfaction and reduced competitiveness in the market.

[0604] 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.

[0605] In this invention, the server includes means for collecting information, means for preprocessing the data, and means for training the data using machine learning algorithms. This makes it possible to process user feedback through sentiment analysis, quickly propose more personalized designs, and enable a continuous improvement cycle.

[0606] "Means of collecting information" refers to protocols and interfaces for obtaining market trends and customer demands.

[0607] "Methods for preprocessing data" refers to the process of converting collected data into an analyzable format and handling missing or outlier values.

[0608] "Methods for training data using machine learning algorithms" refers to the process of generating a machine learning model using training data and optimizing the model so that it can perform pattern recognition and prediction.

[0609] "Methods for proposing designs" refers to the process of considering customer needs and presenting unique product designs and service plans using generative AI models.

[0610] "Means of receiving feedback from users" refers to the process of collecting opinions and impressions from end users and inputting that information into the system in an analyzable format.

[0611] "Methods for processing and improving design through sentiment analysis" refers to the process of analyzing emotional information contained in user feedback and reflecting the results in improving designs and proposals.

[0612] "Methods for finalizing the design and converting it into the specifications of an actual product" refers to the process of translating the finalized design proposal into detailed specifications and proposing it as a production-ready technical document.

[0613] This invention is a system for providing personalized designs to individual users. The server collects market trend information using an information gathering protocol. This makes it possible to provide designs that are always based on the latest market needs. The data is preprocessed using the Python Pandas library to impute missing values ​​and remove outliers.

[0614] Subsequently, the server uses machine learning algorithms to train a model for design generation. Frameworks such as TensorFlow and PyTorch are commonly used for this process. The generated model then produces design proposals based on user feedback, enabling suggestions tailored to customer needs.

[0615] The terminal presents design proposals sent from the server to the user and collects feedback from the user. The user then inputs specific comments via the terminal, providing their opinions to the system. This enables continuous design improvement based on feedback.

[0616] A sentiment engine is used for sentiment analysis. It analyzes comments included in user feedback and extracts sentiment indicators using natural language processing techniques. These indicators are directly used to improve the design, resulting in a more satisfying design.

[0617] As a concrete example, when considering the design of a new furniture set, if a user provides feedback such as "This color is unsettling," the emotion engine analyzes "anxiety" as an emotional indicator. Based on this analysis, the server adjusts the model and regenerates design proposals with calmer color schemes, which are then presented to the user.

[0618] An example of a prompt for a generative AI model is, "If the user prefers a calm design, please suggest suitable color schemes and styles."

[0619] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0620] Step 1:

[0621] The server acquires market trend information using an information gathering protocol. As input, it sends data acquisition requests to the information source API and receives market data in JSON format from the API. Based on this data, the server performs data cleansing, such as imputing missing values ​​and removing outliers, using the Python Pandas library. The output is a dataset prepared in an analyzable format.

[0622] Step 2:

[0623] The server trains a machine learning model using pre-processed data. The input to this process is the previously processed dataset. The server uses frameworks such as TensorFlow and PyTorch to train a machine learning model for generating design proposals. The output is a trained model capable of meeting customer needs.

[0624] Step 3:

[0625] The server uses a trained generative AI model to generate design proposals based on customer needs. It takes the model obtained in the previous step and requirements extracted from user feedback as input. Prompts are used to specify generation conditions, such as "If the user prefers a calm design, suggest suitable color schemes and styles." The output is an optimized design proposal.

[0626] Step 4:

[0627] The terminal presents the user with design proposals provided by the server. The input for this process is the design proposals received from the server. The terminal outputs the design proposals visually through the user interface.

[0628] Step 5:

[0629] Users review the presented design proposals and input feedback into their devices. This feedback includes free-form comments and opinions on the designs. The user's feedback is sent to the server in real time via the device.

[0630] Step 6:

[0631] The server performs sentiment analysis on the user feedback it receives. It takes the feedback text data as input and analyzes the text using natural language processing techniques. Using an emotion engine, it extracts the user's sentiment indicators, and the output is a dataset containing sentiment information.

[0632] Step 7:

[0633] The server refines the design proposal based on the data obtained from sentiment analysis. This process uses the acquired sentiment data as input to adjust the design elements. Finally, the improved design proposal is generated and presented to the user again through the terminal.

[0634] (Application Example 2)

[0635] 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."

[0636] Providing personalized designs that appropriately incorporate user emotions and feedback in advertising and product design has traditionally been a challenging task. In particular, there is a need to analyze user emotions in real time and immediately optimize designs based on that analysis. This necessitates establishing an effective feedback cycle to enhance user satisfaction.

[0637] 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.

[0638] In this invention, the server includes data acquisition means, data formatting means, and means for training a learning model. This makes it possible to analyze user feedback and emotions collected via information terminals and optimize design proposals in real time based on them.

[0639] A "data acquisition method" is a mechanism for collecting data from information sources and using it to generate and optimize design proposals.

[0640] "Data formatting means" refers to a function that performs the process of processing and normalizing collected data into an analyzable format.

[0641] "Methods for training a learning model" refers to the process of training a model using a machine learning algorithm and generating design proposals based on user requirements.

[0642] "Means for generating design proposals based on user requirements" refers to a process that automatically proposes designs according to the user's requests and specifications.

[0643] "Means for receiving user feedback" refers to an interface for collecting feedback and opinions from users via information terminals.

[0644] "Means for improving a design proposal" refers to algorithms or methods for modifying an existing design proposal into a more optimal form based on the feedback received.

[0645] "Means of determining the final design and converting it into product specifications" refers to a set of procedures for finalizing an improved design proposal as a concrete product specification and applying it to the actual product.

[0646] An "emotion analysis tool" is a technological mechanism that analyzes user feedback, identifies the emotions contained within it, and reflects these findings in design improvements.

[0647] "A means of presenting information on information terminals in real time and promoting re-evaluation" refers to a system that immediately displays the improved design on the user's terminal and conducts a cyclical evaluation by soliciting further feedback.

[0648] The system for implementing this invention comprises multiple means, including data acquisition, data formatting, training of a learning model, sentiment analysis, and optimization of design proposals. These means are intended to provide personalized content based on user feedback, particularly in the fields of advertising and product design.

[0649] The server first retrieves data from the information source. During this process, it uses the information source interface to collect relevant data such as market trend information. The collected data is then formatted and converted into a parseable format using libraries such as Python's NumPy and Pandas.

[0650] Next, the collected and formatted data is used to train a learning model on the server. This training utilizes natural language processing techniques to extract useful information from the collected feedback and generate design proposals based on user requirements.

[0651] The collected feedback includes eye-tracking data and audio feedback, and sentiment indicators are extracted using sentiment analysis tools such as TensorFlow. For example, if a user sees an advertisement through smart glasses and responds with "This doesn't put me in a good mood this morning," the sentiment engine analyzes this as "low energy." Based on this information, the server optimizes the design proposal and creates new ad designs and messages using a generative AI model.

[0652] The optimized design is immediately delivered to information terminals, and additional feedback from users is encouraged, enabling a continuous evaluation cycle. In this process, the AI ​​model is instructed using a prompt message such as, "User sentiment: Low energy. Product name: Coffee machine. Please suggest the best advertising message and design."

[0653] This system enables real-time design optimization that takes user emotions into account, thereby enhancing the appeal of advertisements and products.

[0654] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0655] Step 1:

[0656] The server retrieves market trend information from data sources through an information source interface. The input is the data source, and the output is raw market trend data. This data forms the basis for subsequent design proposal generation.

[0657] Step 2:

[0658] The server uses Python's NumPy and Pandas to format the acquired market trend data. The input is unformatted market trend data, and the output is data normalized into a parseable format. Specifically, it cleans up irregular data and arranges it into a consistent format.

[0659] Step 3:

[0660] The server trains a learning model based on the formatted data. The input is normalized data, and the output is a trained model that generates design proposals based on user requirements. Specifically, it uses natural language processing techniques to extract useful patterns from the data.

[0661] Step 4:

[0662] The device receives feedback from the user. Input consists of user eye-tracking data and voice comments, while output is unanalyzed feedback data sent to the server via the device. This feedback is sent to the server in real time.

[0663] Step 5:

[0664] The server extracts sentiment indicators from feedback data using sentiment analysis methods such as TensorFlow. The input is unanalyzed feedback data, and the output is analyzed data including sentiment indicators. Specifically, it identifies the user's emotions from voice comments using natural language processing.

[0665] Step 6:

[0666] The server optimizes design proposals using a generative AI model based on sentiment indicators. The inputs are sentiment indicators and a trained model, while the output is the optimized design proposal. Specifically, it provides the generative AI model with prompts suggesting new designs or messages, and retrieves appropriate results.

[0667] Step 7:

[0668] The device presents optimized design proposals to the user in real time and encourages further feedback. The input is the optimized design proposal, and the output is newly acquired user reactions and comments. The user then reviews this and makes their next evaluation.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] [Fourth Embodiment]

[0673] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0674] 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.

[0675] 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).

[0676] 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.

[0677] 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.

[0678] 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).

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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.

[0685] 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".

[0686] This invention is a system that combines data collection, preprocessing, AI-based design generation, and the reception and improvement of user feedback. Specifically, the system is realized through the use of a server, terminals, and users, each playing their respective roles.

[0687] Server Role

[0688] The server first collects market trend data from external sources such as social media and news sites. This information is used to understand customer needs and the latest trends. The server normalizes and cleans this data and prepares it for use in training AI models. Furthermore, the server also has the ability to generate new product design proposals using the trained AI models.

[0689] Terminal role

[0690] The terminal presents the user with design proposals sent from the server. The user evaluates the displayed design proposals and provides feedback. The terminal is responsible for sending this feedback to the server. Furthermore, once the final design is decided, the terminal can output the design as a product specification document.

[0691] User roles

[0692] Users review the design proposals presented on their devices and provide feedback on their preferences and areas for improvement. This feedback serves as valuable information for the server to improve the design.

[0693] Specific example

[0694] For example, if a company wants to develop a new smartphone case design, the server collects relevant data from Twitter and feedback platforms. Based on this data, the AI ​​learns about color and material trends and generates various design proposals. The device displays these design proposals to the user, who selects their favorite design and provides feedback on color adjustments and material changes. The server then receives this feedback, refines the design, and provides a final version. Finally, the device converts the selected design specifications into digital data for transmission to the manufacturing department.

[0695] Thus, the proposed system combines human creativity with machine learning technology to provide highly efficient and user-friendly product designs.

[0696] The following describes the processing flow.

[0697] Step 1:

[0698] The server collects market trend data and user feedback from specified APIs. This data is filtered based on pre-specified keywords and topics.

[0699] Step 2:

[0700] The server analyzes the collected raw data, filters out unnecessary information, and normalizes it. This makes the data clean and consistent.

[0701] Step 3:

[0702] The server uses pre-processed data to train a machine learning model. The model learns the factors and trends that influence the design.

[0703] Step 4:

[0704] The server generates new design proposals using the trained model. These generated design proposals reflect the user's past preferences and market trends.

[0705] Step 5:

[0706] The server sends the generated design proposal to the terminal. The terminal displays the design on its user interface.

[0707] Step 6:

[0708] Users review the design proposal displayed on their device and provide feedback on the design through the interface. This feedback often concerns color, shape, and functionality.

[0709] Step 7:

[0710] The server receives feedback from users and improves the design proposals. The feedback is reflected in the model, and new design proposals are generated as needed.

[0711] Step 8:

[0712] The terminal converts the user's selected final design into product design specifications. These specifications are then prepared as digital data for implementation in the manufacturing department.

[0713] (Example 1)

[0714] 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".

[0715] Traditional product design processes have made it difficult to quickly generate designs that effectively reflect customer needs and market trends. Furthermore, the inability to quickly incorporate user feedback and improve designs sometimes led to problems with the final product's market suitability.

[0716] 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.

[0717] In this invention, the server includes means for collecting data from external sources, means for processing the collected data and preparing it in a format suitable for machine learning, and means for generating design proposals based on customer requirements using a trained generative AI model. This enables the rapid generation of design proposals that reflect customer needs and market trends, and immediate design improvements based on user feedback.

[0718] "Means for collecting data from external sources" refers to a device or method that has the function of automatically acquiring necessary data from various sources on the internet.

[0719] "Methods for processing collected data and preparing it in a format suitable for machine learning" refers to processing methods that convert acquired data into an analyzable format, correct incomplete data, and delete unnecessary data.

[0720] "A means of generating design proposals based on customer requirements using a trained generative AI model" refers to a technology that pre-trains a machine learning algorithm and uses that model to automatically generate new designs that meet user needs.

[0721] "Means of receiving user feedback" refers to interfaces and processes that record user opinions and requests within the system and reflect them in subsequent actions.

[0722] "Methods for improving design proposals" refer to methods for improving generated designs based on user feedback, and modifying them to be of higher quality and better meet user needs.

[0723] "Means of converting a final design into a product specification format" refers to a process or system for converting a completed design proposal into a format that is adaptable to the manufacturing process and can be used in actual product manufacturing.

[0724] "Acquiring market trend information using APIs as a means of information acquisition" refers to a technology that uses a specific application program interface to acquire market trends and consumer behavior data in real time.

[0725] "Applying natural language processing technology" means using technology that allows machines to understand and process human language to utilize language data for model training and design generation.

[0726] The following describes embodiments for carrying out the invention.

[0727] This invention is a system that highly automates data collection and processing, AI-powered design generation, and the collection and incorporation of user feedback. Specifically, it is operated by having three parties—a server, a terminal, and a user—each play different roles.

[0728] Server Role

[0729] The server plays a central role in collecting data from diverse sources. Specifically, the server uses scraping tools such as Python's BeautifulSoup and Selenium to collect information from social media and news sites. The server processes this data using machine learning libraries such as Pandas and NumPy, converting it into a format suitable for training AI models. Then, it uses the trained generative AI model to generate new design proposals based on customer requirements. Machine learning frameworks such as TensorFlow and PyTorch are used to train the generative AI model. During generation, specific prompt statements are provided as input to create appropriate design proposals.

[0730] Terminal role

[0731] The terminal provides an interface that presents design proposals sent from the server to the user. Specifically, it utilizes front-end libraries such as React and Vue.js to build a user-friendly UI. Through this UI, the user evaluates the design proposals and provides feedback. The terminal then sends this feedback back to the server. This exchange enables a process of improving the design based on user requests.

[0732] User roles

[0733] Users review the design proposals displayed on their devices and evaluate whether each design matches their needs and preferences. They can provide specific feedback, such as "Make this color more vibrant" or "Change this material." This user feedback is then sent to the server and used to improve the designs.

[0734] Examples of specific cases and prompt statements

[0735] For example, when a company designs a new smartphone case, the server collects data from social media and feedback platforms, and an AI model generates design proposals based on that data. An example of a prompt used for generation is, "Generate smartphone case design proposals that reflect the latest color trends." In this way, the design cycle, including user feedback, is efficiently managed.

[0736] This system combines human creativity with machine learning technology to provide rapid and highly adaptable product designs.

[0737] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0738] Step 1:

[0739] The server collects data from external sources. Specifically, the server uses APIs from social media and news sites to obtain text and image data related to market trends. This data is used as input data to understand customer needs. The obtained data is stored in storage so that it can be reused in the next processing step.

[0740] Step 2:

[0741] The server preprocesses the collected data. Since the input data may contain missing values ​​or noise, the server cleans and normalizes the data using Pandas and NumPy. This data processing outputs a clean dataset suitable for training machine learning models.

[0742] Step 3:

[0743] The server generates design proposals using a generative AI model. Using a clean dataset as input, the AI ​​model, trained with TensorFlow or PyTorch, generates a variety of design proposals. Using the prompt "Generate design proposals that reflect the latest color trends," designs that meet user needs are output.

[0744] Step 4:

[0745] The device presents design proposals received from the server to the user. The device generates a UI using React or Vue.js, allowing the user to view various design proposals on the screen. The design proposals are displayed in a visually clear manner, enabling the user to intuitively select and evaluate them.

[0746] Step 5:

[0747] Users evaluate the presented design proposals and provide feedback. They input specific requests and suggestions for improvement in a format such as, "I'd like the colors in this design adjusted." User feedback is crucial information for improvements in the next step.

[0748] Step 6:

[0749] The device sends user feedback to the server. The feedback is sent to the server using HTTP communication and formatted for easy analysis. Once the data arrives at the server, it is ready for the next improvement step.

[0750] Step 7:

[0751] The server improves the design proposal based on user feedback. Using the feedback as input, an AI model is used to improve the design. The improved design proposal is generated as a new output, better meeting user needs.

[0752] Step 8:

[0753] Once the final design is decided, the terminal converts it into a product specification. The selected design is output as digital data in PDF or CAD format, ready to be sent to the manufacturing department. The terminal automates this conversion, enabling a rapid data flow.

[0754] (Application Example 1)

[0755] 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".

[0756] In today's advertising industry, creating effective advertising designs that quickly respond to consumer needs and market trends is crucial. However, traditional methods struggle to grasp market trends and incorporate consumer feedback, and these processes are time-consuming and resource-intensive.

[0757] 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.

[0758] In this invention, the server includes data collection means, preprocessing means, and means for training a machine learning model. This makes it possible to quickly grasp market trends and generate effective advertising designs that reflect consumer feedback.

[0759] "Data collection methods" refer to the function of acquiring trend data from external sources in order to understand market trends and consumer needs.

[0760] "Preprocessing means" refers to functions that normalize collected data and prepare it in a format suitable for training machine learning models.

[0761] "Methods for training machine learning models" refer to functions that enable AI models to learn using collected and pre-processed data, thereby giving them the ability to generate new advertising ideas.

[0762] "Methods for generating advertising proposals" refers to a function that utilizes machine learning models to create appropriate advertising design proposals based on market trends and other factors.

[0763] "Means of receiving user feedback" refers to a function that collects consumer evaluations and suggestions for improvement regarding advertising proposals.

[0764] "Means for improving ad drafts" refers to a function that modifies generated ad drafts to make them more effective based on collected user feedback.

[0765] "Means of determining and converting advertisements into distribution specifications" refers to the function of finalizing the advertisement design and converting it into a format suitable for use and distribution.

[0766] This invention is a system that generates advertising designs that quickly respond to market trends in the advertising industry and effectively reflect consumer needs. The system mainly consists of three elements: a server, a terminal, and a user.

[0767] The server is responsible for collecting market trend data from external sources using APIs. The collected data is analyzed using libraries such as BeautifulSoup and Scrapy in the Python language, and normalized and cleansed using Pandas. Next, an AI model is trained on the data using machine learning libraries such as TensorFlow. This trained generative AI model has the function of generating advertising design proposals based on market trends.

[0768] The device provides the user with an interface through which the user can view multiple generated design proposals. The application primarily uses Flutter, allowing the user to select their preferred design on the interface and provide feedback on its evaluation and potential improvements.

[0769] User feedback is sent back to the server, which then uses it to refine the ad design. Ultimately, the most effective ad design is determined and converted by the server into a distribution specification.

[0770] For example, when a server generates an advertising design for a new beverage, the prompt would be, "Generate an advertising design proposal that emphasizes the modern and healthy image of the new beverage brand." This is expected to generate advertising designs that accurately capture market needs in a short amount of time.

[0771] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0772] Step 1:

[0773] The server collects market trend data from external sources via APIs. The input to this data collection is market trend information provided by the API, and the output is raw market trend data. The server then uses analysis tools (such as BeautifulSoup or Scrapy) to extract the necessary information and format it into a dataset.

[0774] Step 2:

[0775] The server processes the formatted market trend data using the Pandas library. The input contains raw market trend data, and the output is normalized and cleaned data. The normalization process unifies the data format and removes unnecessary data.

[0776] Step 3:

[0777] The server trains a machine learning model using TensorFlow. The input for this step is pre-processed market trend data, and the output is a generative AI model. The machine learning model learns trends from the provided data and gains foundational knowledge to generate advertising designs.

[0778] Step 4:

[0779] The user receives ad design proposals sent from the server via a Flutter app on their device. The input is the generated ad design proposal, which the user evaluates. The output is the user's feedback, including the evaluation information.

[0780] Step 5:

[0781] The server improves the ad design based on feedback received from the terminal. The input is user feedback, and the output is the improved ad design proposal. The server analyzes the content of the feedback, incorporates it into the generating AI model, and adjusts the ad proposal.

[0782] Step 6:

[0783] Finally, the server finalizes the optimized ad draft and converts it into a distributable format. The input for this step is the improved ad design draft, and the output is the final ad design usable on the advertising medium. The server converts this into a digital format and prepares it for distribution.

[0784] 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.

[0785] This invention is a system that optimizes designs by taking user emotions into account, in addition to data collection, preprocessing, and AI model-based design proposal generation, by incorporating an emotion engine. This system aims to provide more personalized designs by analyzing the emotional state of users, particularly when receiving feedback.

[0786] Server Role

[0787] The server collects market trend information via information source APIs, performs data cleansing and normalization, and trains machine learning models on the collected data to generate design proposals that reflect customer requirements. Furthermore, the server utilizes an emotion engine to analyze the emotions contained in user feedback and uses this information to improve the design process.

[0788] Functions of the Emotion Engine

[0789] The emotion engine performs natural language processing on comments and feedback entered by users through their devices, and extracts emotional indicators from them. These indicators reflect user preferences and frustrations and are used to evaluate and improve design proposals.

[0790] Terminal role

[0791] The device presents design proposals sent from the server to the user and receives feedback from the user. The device sends this feedback to the server in real time, including sentiment data analyzed by the sentiment engine.

[0792] User roles

[0793] Users review the design proposals presented on their devices and provide feedback, frankly recording their feelings and opinions. The interaction is designed with the intention that this feedback will lead to better design improvements.

[0794] Specific example

[0795] For example, when designing a new furniture set, if a user provides feedback such as "This color is unsettling," the emotion engine analyzes "anxiety" as an emotional metric. The server incorporates this data into its model and generates design proposals with more calming color schemes. The terminal then presents the improved design to the user and obtains further feedback.

[0796] Thus, the present invention builds a feedback cycle that incorporates user emotions and achieves advanced design optimization to enhance user satisfaction.

[0797] The following describes the processing flow.

[0798] Step 1:

[0799] The server collects market trend data via information source APIs. This data is used to understand consumer opinions and trends related to products.

[0800] Step 2:

[0801] The server normalizes the collected data and performs data cleansing to remove noise. This prepares the data for analysis.

[0802] Step 3:

[0803] The server trains a machine learning model using clean data. This model is responsible for learning trends and patterns that influence the design.

[0804] Step 4:

[0805] The server uses the trained model to generate design proposals based on customer requirements. These design proposals will reflect historical trend data.

[0806] Step 5:

[0807] The terminal displays design proposals sent from the server on its user interface. The user reviews these and forms their first impression.

[0808] Step 6:

[0809] Users provide specific comments as feedback on the design proposals displayed on their devices. This feedback may include comments on particular colors or shapes.

[0810] Step 7:

[0811] The device sends user feedback to the server. Simultaneously, it also includes data for sentiment analysis by the emotion engine.

[0812] Step 8:

[0813] The server uses an emotion engine to analyze user feedback and extract emotion metrics. These emotion metrics, in the form of "satisfied" or "dissatisfied," are used to improve the design.

[0814] Step 9:

[0815] The server improves the design proposal based on the analyzed sentiment data. The improved design becomes personalized, reflecting the user's emotional state.

[0816] Step 10:

[0817] The device receives a new design proposal from the server again and presents it to the user. The user reviews this new proposal and provides further evaluation and feedback.

[0818] Through this processing flow, the system quickly generates design proposals that take user emotions and feedback into account, aiming to improve user satisfaction.

[0819] (Example 2)

[0820] 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".

[0821] To meet the diverse needs of today's consumers, it is crucial to quickly generate designs that reflect the emotions and preferences of individual customers and to continuously improve them. However, traditional design processes struggle to adequately reflect user opinions and lack mechanisms for efficiently analyzing collected feedback and incorporating it into designs. This raises concerns about declining consumer satisfaction and reduced competitiveness in the market.

[0822] 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.

[0823] In this invention, the server includes means for collecting information, means for preprocessing the data, and means for training the data using machine learning algorithms. This makes it possible to process user feedback through sentiment analysis, quickly propose more personalized designs, and enable a continuous improvement cycle.

[0824] "Means of collecting information" refers to protocols and interfaces for obtaining market trends and customer demands.

[0825] "Methods for preprocessing data" refers to the process of converting collected data into an analyzable format and handling missing or outlier values.

[0826] "Methods for training data using machine learning algorithms" refers to the process of generating a machine learning model using training data and optimizing the model so that it can perform pattern recognition and prediction.

[0827] "Methods for proposing designs" refers to the process of considering customer needs and presenting unique product designs and service plans using generative AI models.

[0828] "Means of receiving feedback from users" refers to the process of collecting opinions and impressions from end users and inputting that information into the system in an analyzable format.

[0829] "Methods for processing and improving design through sentiment analysis" refers to the process of analyzing emotional information contained in user feedback and reflecting the results in improving designs and proposals.

[0830] "Methods for finalizing the design and converting it into the specifications of an actual product" refers to the process of translating the finalized design proposal into detailed specifications and proposing it as a production-ready technical document.

[0831] This invention is a system for providing personalized designs to individual users. The server collects market trend information using an information gathering protocol. This makes it possible to provide designs that are always based on the latest market needs. The data is preprocessed using the Python Pandas library to impute missing values ​​and remove outliers.

[0832] Subsequently, the server uses machine learning algorithms to train a model for design generation. Frameworks such as TensorFlow and PyTorch are commonly used for this process. The generated model then produces design proposals based on user feedback, enabling suggestions tailored to customer needs.

[0833] The terminal presents design proposals sent from the server to the user and collects feedback from the user. The user then inputs specific comments via the terminal, providing their opinions to the system. This enables continuous design improvement based on feedback.

[0834] A sentiment engine is used for sentiment analysis. It analyzes comments included in user feedback and extracts sentiment indicators using natural language processing techniques. These indicators are directly used to improve the design, resulting in a more satisfying design.

[0835] As a concrete example, when considering the design of a new furniture set, if a user provides feedback such as "This color is unsettling," the emotion engine analyzes "anxiety" as an emotional indicator. Based on this analysis, the server adjusts the model and regenerates design proposals with calmer color schemes, which are then presented to the user.

[0836] An example of a prompt for a generative AI model is, "If the user prefers a calm design, please suggest suitable color schemes and styles."

[0837] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0838] Step 1:

[0839] The server acquires market trend information using an information gathering protocol. As input, it sends data acquisition requests to the information source API and receives market data in JSON format from the API. Based on this data, the server performs data cleansing, such as imputing missing values ​​and removing outliers, using the Python Pandas library. The output is a dataset prepared in an analyzable format.

[0840] Step 2:

[0841] The server trains a machine learning model using pre-processed data. The input to this process is the previously processed dataset. The server uses frameworks such as TensorFlow and PyTorch to train a machine learning model for generating design proposals. The output is a trained model capable of meeting customer needs.

[0842] Step 3:

[0843] The server uses a trained generative AI model to generate design proposals based on customer needs. It takes the model obtained in the previous step and requirements extracted from user feedback as input. Prompts are used to specify generation conditions, such as "If the user prefers a calm design, suggest suitable color schemes and styles." The output is an optimized design proposal.

[0844] Step 4:

[0845] The terminal presents the user with design proposals provided by the server. The input for this process is the design proposals received from the server. The terminal outputs the design proposals visually through the user interface.

[0846] Step 5:

[0847] Users review the presented design proposals and input feedback into their devices. This feedback includes free-form comments and opinions on the designs. The user's feedback is sent to the server in real time via the device.

[0848] Step 6:

[0849] The server performs sentiment analysis on the user feedback it receives. It takes the feedback text data as input and analyzes the text using natural language processing techniques. Using an emotion engine, it extracts the user's sentiment indicators, and the output is a dataset containing sentiment information.

[0850] Step 7:

[0851] The server refines the design proposal based on the data obtained from sentiment analysis. This process uses the acquired sentiment data as input to adjust the design elements. Finally, the improved design proposal is generated and presented to the user again through the terminal.

[0852] (Application Example 2)

[0853] 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".

[0854] Providing personalized designs that appropriately incorporate user emotions and feedback in advertising and product design has traditionally been a challenging task. In particular, there is a need to analyze user emotions in real time and immediately optimize designs based on that analysis. This necessitates establishing an effective feedback cycle to enhance user satisfaction.

[0855] 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.

[0856] In this invention, the server includes data acquisition means, data formatting means, and means for training a learning model. This makes it possible to analyze user feedback and emotions collected via information terminals and optimize design proposals in real time based on them.

[0857] A "data acquisition method" is a mechanism for collecting data from information sources and using it to generate and optimize design proposals.

[0858] "Data formatting means" refers to a function that performs the process of processing and normalizing collected data into an analyzable format.

[0859] "Methods for training a learning model" refers to the process of training a model using a machine learning algorithm and generating design proposals based on user requirements.

[0860] "Means for generating design proposals based on user requirements" refers to a process that automatically proposes designs according to the user's requests and specifications.

[0861] "Means for receiving user feedback" refers to an interface for collecting feedback and opinions from users via information terminals.

[0862] "Means for improving a design proposal" refers to algorithms or methods for modifying an existing design proposal into a more optimal form based on the feedback received.

[0863] "Means of determining the final design and converting it into product specifications" refers to a set of procedures for finalizing an improved design proposal as a concrete product specification and applying it to the actual product.

[0864] An "emotion analysis tool" is a technological mechanism that analyzes user feedback, identifies the emotions contained within it, and reflects these findings in design improvements.

[0865] "A means of presenting information on information terminals in real time and promoting re-evaluation" refers to a system that immediately displays the improved design on the user's terminal and conducts a cyclical evaluation by soliciting further feedback.

[0866] The system for implementing this invention comprises multiple means, including data acquisition, data formatting, training of a learning model, sentiment analysis, and optimization of design proposals. These means are intended to provide personalized content based on user feedback, particularly in the fields of advertising and product design.

[0867] The server first retrieves data from the information source. During this process, it uses the information source interface to collect relevant data such as market trend information. The collected data is then formatted and converted into a parseable format using libraries such as Python's NumPy and Pandas.

[0868] Next, the collected and formatted data is used to train a learning model on the server. This training utilizes natural language processing techniques to extract useful information from the collected feedback and generate design proposals based on user requirements.

[0869] The collected feedback includes eye-tracking data and audio feedback, and sentiment indicators are extracted using sentiment analysis tools such as TensorFlow. For example, if a user sees an advertisement through smart glasses and responds with "This doesn't put me in a good mood this morning," the sentiment engine analyzes this as "low energy." Based on this information, the server optimizes the design proposal and creates new ad designs and messages using a generative AI model.

[0870] The optimized design is immediately delivered to information terminals, and additional feedback from users is encouraged, enabling a continuous evaluation cycle. In this process, the AI ​​model is instructed using a prompt message such as, "User sentiment: Low energy. Product name: Coffee machine. Please suggest the best advertising message and design."

[0871] This system enables real-time design optimization that takes user emotions into account, thereby enhancing the appeal of advertisements and products.

[0872] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0873] Step 1:

[0874] The server retrieves market trend information from data sources through an information source interface. The input is the data source, and the output is raw market trend data. This data forms the basis for subsequent design proposal generation.

[0875] Step 2:

[0876] The server uses Python's NumPy and Pandas to format the acquired market trend data. The input is unformatted market trend data, and the output is data normalized into a parseable format. Specifically, it cleans up irregular data and arranges it into a consistent format.

[0877] Step 3:

[0878] The server trains a learning model based on the formatted data. The input is normalized data, and the output is a trained model that generates design proposals based on user requirements. Specifically, it uses natural language processing techniques to extract useful patterns from the data.

[0879] Step 4:

[0880] The device receives feedback from the user. Input consists of user eye-tracking data and voice comments, while output is unanalyzed feedback data sent to the server via the device. This feedback is sent to the server in real time.

[0881] Step 5:

[0882] The server extracts sentiment indicators from feedback data using sentiment analysis methods such as TensorFlow. The input is unanalyzed feedback data, and the output is analyzed data including sentiment indicators. Specifically, it identifies the user's emotions from voice comments using natural language processing.

[0883] Step 6:

[0884] The server optimizes design proposals using a generative AI model based on sentiment indicators. The inputs are sentiment indicators and a trained model, while the output is the optimized design proposal. Specifically, it provides the generative AI model with prompts suggesting new designs or messages, and retrieves appropriate results.

[0885] Step 7:

[0886] The device presents optimized design proposals to the user in real time and encourages further feedback. The input is the optimized design proposal, and the output is newly acquired user reactions and comments. The user then reviews this and makes their next evaluation.

[0887] 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.

[0888] 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.

[0889] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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."

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] The following is further disclosed regarding the embodiments described above.

[0909] (Claim 1)

[0910] Data collection means,

[0911] Pre-treatment means,

[0912] Methods for training machine learning models,

[0913] A means of generating design proposals based on customer requirements,

[0914] Means of receiving user feedback,

[0915] A means for improving the design proposal generated based on the aforementioned user feedback,

[0916] A means of determining the final design and translating it into the specifications of the actual product,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, characterized in that the data collection means acquires market trend information using an information source API.

[0920] (Claim 3)

[0921] The system according to claim 1, characterized in that the means for training the machine learning model uses natural language processing technology.

[0922] "Example 1"

[0923] (Claim 1)

[0924] Means of collecting data from external sources,

[0925] A means of processing the collected data and preparing it in a format suitable for machine learning,

[0926] A means of generating design proposals based on customer requirements using a trained generative AI model,

[0927] A means of receiving user feedback on the presented design,

[0928] A means for improving the design proposal generated based on the feedback,

[0929] A means of converting the final design into a product specification format,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, characterized in that it acquires market trend information using an API as a means of acquiring information.

[0933] (Claim 3)

[0934] The system according to claim 1, characterized in that natural language processing technology is applied as a means for training a machine learning model.

[0935] "Application Example 1"

[0936] (Claim 1)

[0937] Data collection means,

[0938] Pre-treatment means,

[0939] Methods for training machine learning models,

[0940] A means of generating advertising proposals based on market trends,

[0941] Means of receiving user feedback,

[0942] A means for improving the advertising proposal generated based on the aforementioned user feedback,

[0943] A means of determining the final advertisement and converting it to a distribution format,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, characterized in that the data collection means acquires trend data from an external information source.

[0947] (Claim 3)

[0948] The system according to claim 1, characterized in that the means for training the machine learning model uses generative AI model technology.

[0949] "Example 2 of combining an emotion engine"

[0950] (Claim 1)

[0951] Means of collecting information,

[0952] Means for preprocessing data,

[0953] Methods for training data using machine learning algorithms,

[0954] A means of proposing a design based on customer needs,

[0955] Means of receiving feedback from users,

[0956] A means for processing the aforementioned feedback through sentiment analysis and improving the design,

[0957] A means of finalizing the design and converting it into the specifications of the actual product,

[0958] A system that includes this.

[0959] (Claim 2)

[0960] The system according to claim 1, characterized in that the means for collecting the aforementioned information acquires market trends using a data acquisition protocol.

[0961] (Claim 3)

[0962] The system according to claim 1, characterized in that the means for training the machine learning algorithm uses natural language processing techniques.

[0963] "Application example 2 when combining with an emotional engine"

[0964] (Claim 1)

[0965] Data acquisition method,

[0966] Data formatting methods,

[0967] Means for training a learning model,

[0968] A means for generating design proposals based on user requirements,

[0969] Means of receiving user feedback,

[0970] A means of improving the design proposal generated based on the aforementioned user feedback,

[0971] A means of determining the final design and converting it into product specifications,

[0972] A method for extracting user emotional indicators using emotion analysis techniques and utilizing them to optimize design proposals,

[0973] A means of presenting the improved design on an information terminal in real time to facilitate re-evaluation,

[0974] A system that includes this.

[0975] (Claim 2)

[0976] The system according to claim 1, characterized in that the data acquisition means acquires market trend information using an information source interface.

[0977] (Claim 3)

[0978] The system according to claim 1, characterized in that the means for training the learning model utilizes natural language processing technology. [Explanation of Symbols]

[0979] 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. Data collection means, Pre-treatment means, Methods for training machine learning models, A means of generating advertising proposals based on market trends, Means of receiving user feedback, A means for improving the advertising proposal generated based on the aforementioned user feedback, A means of determining the final advertisement and converting it to a distribution format, A system that includes this.

2. The system according to claim 1, characterized in that the data collection means acquires trend data from an external information source.

3. The system according to claim 1, characterized in that the means for training the machine learning model uses generative AI model technology.

Images