system

Abstract

We provide a system that allows for the preservation of traditional techniques and the creation of new, modern proposals. [Solution] A system comprising: a camera and sensor means for collecting technical data from craftsmen; a means for preprocessing the collected technical data and converting it into an analyzable format; a means for inputting the converted data into a generation AI to learn from it; a means for saving the learning results of the generation AI in a database; a data analysis AI means for collecting and analyzing trend data; a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI; a means for feeding back the generated proposals to craftsmen and collecting their evaluations; and a means for improving the models of the generation AI and data analysis AI based on the collected feedback.

Description

[Technical Field]

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

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

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

[0004] In modern times, traditional craftsmanship is in danger of disappearing due to a lack of successors and the difficulty of passing on skills. To solve this problem, there is a need to preserve skills that cannot be passed on using traditional methods in new ways, and to create new proposals that respond to modern trends. [Means for solving the problem]

[0005] The present invention provides a system that uses generative AI to learn artisan skills and stores the resulting technical data in a database. The system includes a means for collecting artisan technical data using cameras and sensors, preprocessing it, and converting it into an analyzable format. It also provides a means for using data analysis AI to collect and analyze trend data on the Internet, and combining it with the learned technical data to generate new proposals. Furthermore, the system provides a feedback loop in which the generated proposals are fed back to the artisans, and the system is improved based on their evaluation, thereby preserving traditional skills and generating new, modern proposals.

[0006] "Camera and sensor means" is a collective term for cameras and sensor devices installed to collect technical data of craftsmen.

[0007] "Generative AI" is an artificial intelligence system that learns from collected technical data of craftsmen and recognizes and generates technical patterns.

[0008] "Raw data" refers to artisan technical data that has been collected but has not yet been converted into an analyzable format.

[0009] "Preprocessing" refers to a series of processes, such as data cleansing and noise removal, that transform raw data into an analyzable format.

[0010] A "database" is an information storage device that stores the results of the technology learned by generative AI and manages them in a reusable form.

[0011] "Data analysis AI" is an artificial intelligence system used to collect and analyze trend data on the Internet.

[0012] "Trend data" refers to data that shows current market and consumer trends, and is mainly collected from online sources such as social media, fashion sites, and market reports.

[0013] "Feedback" is the process of collecting evaluations and opinions from craftsmen regarding new proposals that have been generated.

[0014] A "feedback loop" refers to a cyclical process in which the models of the system (generative AI and data analysis AI) are improved based on collected feedback, thereby improving the accuracy of the entire system. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] System Overview

[0037] The system of the present invention is composed of a camera and sensor means, generation AI, data analysis AI, database, and feedback loop, which allows for the collection, storage, and analysis of craftsmanship data, the generation of new proposals, and the transfer of skills.

[0038] Learning and preserving craftsmanship

[0039] Technical Data Collection

[0040] Subject: Server

[0041] The server installs cameras and sensor devices in the space where the craftsmen work. These devices monitor and record the craftsmen's movements and work environment in real time. The server saves the video and audio data collected from the cameras and sensor devices in cloud storage.

[0042] Specific examples

[0043] As a craftsman creates a tea bowl, the camera captures the craftsman's hand movements and the tools he uses in detail. The sensor device collects data such as the shape and temperature of the bowl. This allows even the finest techniques to be accurately recorded as digital data.

[0044] Generative AI learning

[0045] Technical Data Learning

[0046] Subject: Server

[0047] The server inputs the pre-processed data into a generative AI model, which learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[0048] Data analysis and new proposals

[0049] Trend data collection and analysis

[0050] Subject: Data Analysis AI

[0051] Data analysis AI collects the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc. It analyzes this data and identifies current market trends.

[0052] Specific examples

[0053] Data analysis AI analyzes popular online search terms and best-selling products to identify the most popular designs and color combinations, providing the raw materials for creating new proposals that are in line with the times.

[0054] Generate new suggestions and feedback

[0055] Generate a new proposal

[0056] Subject: Data Analysis AI

[0057] The data analysis AI combines the technical data learned by the generation AI with the analyzed trend data to generate new product and design proposals. These proposals are fed back to the craftsmen and used in their actual work.

[0058] Gathering feedback and improving the system

[0059] Subject: Server

[0060] The server presents the generated proposals to the craftsmen and collects their evaluations and opinions. Based on this feedback, the model of the entire system (generative AI and data analysis AI) is improved, thereby improving the quality of the generated proposals.

[0061] Specific examples

[0062] Craftsmen will prototype new tea bowl designs and report the production process and final evaluation to the server. The server will use this feedback to adjust the algorithms of the generative AI and data analysis AI, and reflect this in the next proposal.

[0063] conclusion

[0064] The system of this invention makes it possible to learn and preserve traditional artisan techniques as digital data and propose new products that match modern trends, thereby realizing the inheritance and evolution of artisan techniques.

[0065] The processing flow will be explained below.

[0066] Learning and preserving craftsmanship

[0067] Technical Data Collection

[0068] Subject: Server

[0069] 1. Step 1: Camera and Sensor Settings

[0070] The server places cameras and sensor devices in the craftsman's workshop and performs initial settings to enable accurate detection.

[0071] 2. Step 2: Start collecting data

[0072] The server collects data from cameras and sensor devices in real time and transfers it to cloud storage.

[0073] 3. Step 3: Preprocessing

[0074] The server removes noise from the collected video data, splits the video into frames, and normalizes and timestamps the sensor data.

[0075] Specific examples

[0076] 1. Step 1:

[0077] The server places the camera on the desk where the craftsman is working and adjusts it to the appropriate angle.

[0078] 2. Step 2:

[0079] The server begins to collect video footage of the craftsman shaping the tea bowl and shape data obtained by the sensor in real time.

[0080] 3. Step 3:

[0081] The server removes noise from the collected video data, splits it into frames, normalizes the sensor data, and organizes it as time-series data.

[0082] Generative AI learning

[0083] Technical Data Learning

[0084] Subject: Server

[0085] 1. Step 1: Data Entry

[0086] The server inputs the pre-processed technical data into the generative AI model.

[0087] 2. Step 2: Model training

[0088] The server begins learning the technical patterns using generative AI and trains iteratively.

[0089] 3. Step 3: Save the learning results

[0090] The server stores the results of the technical patterns learned by the generative AI in a database and manages them in a reusable form.

[0091] Specific examples

[0092] 1. Step 1:

[0093] The server inputs pre-processed video data of the craftsman shaping the tea bowl into the generation AI.

[0094] 2. Step 2:

[0095] The server repeatedly trains the generative AI with data to learn things like hand movements and the shape of the vessel.

[0096] 3. Step 3:

[0097] The server stores the learning results in a database and adds metadata (learning date and time, data size, etc.).

[0098] Data analysis and new proposals

[0099] Trend data collection and analysis

[0100] Subject: Data Analysis AI

[0101] 1. Step 1: Trend data collection

[0102] Data analysis AI collects trend data from social media, fashion sites, market reports, etc.

[0103] 2. Step 2: Trend analysis

[0104] Data analysis AI analyzes collected trend data, identifies major themes and styles, and performs clustering.

[0105] 3. Step 3: Generate new proposals

[0106] The data analysis AI generates new proposals based on the technical data learned by the generation AI and the results of trend analysis.

[0107] Specific examples

[0108] 1. Step 1:

[0109] Data analysis AI collects trend data on popular designs and colors on the Internet.

[0110] 2. Step 2:

[0111] Data analysis AI analyzes collected trend data and identifies the most popular designs and color combinations.

[0112] 3. Step 3:

[0113] The data analysis AI combines the technical data of the craftsmen learned by the generation AI to propose new tea bowl designs.

[0114] Generate new suggestions and feedback

[0115] Generating and Evaluating New Proposals

[0116] Subject: Server

[0117] 1. Step 1: Feedback on the proposal

[0118] The server presents the generated new proposals to the craftsmen and collects their evaluations and opinions.

[0119] 2. Step 2: Save the evaluation data

[0120] The server organizes the feedback data collected from the craftsmen and stores it in a database.

[0121] 3. Step 3: System Improvement

[0122] The server uses the collected feedback to improve the generative AI and data analysis AI models and reflect this in its next proposal.

[0123] Specific examples

[0124] 1. Step 1:

[0125] The server shows the new bowl design to the craftsman and encourages him to give feedback.

[0126] 2. Step 2:

[0127] The server organizes the craftsmen's feedback and stores it in a database.

[0128] 3. Step 3:

[0129] The server adjusts the algorithms of the generation AI and data analysis AI based on the collected feedback and reflects it in the next proposal.

[0130] Example 1

[0131] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0132] The inheritance of artisanal skills is extremely important in today's world, but because traditional techniques rely on oral transmission and direct instruction, they are difficult to pass on efficiently. It's also difficult to propose new ideas that are in line with market trends, putting many traditional techniques at risk of becoming outdated. Furthermore, when introducing new technologies, there is a lack of a system for systematically collecting feedback and improving models. To solve these problems, a system is needed that digitizes technology, links with trends, and utilizes feedback.

[0133] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0134] In this invention, the server includes a video device and a sensor device for collecting data on the work of engineers, a device for preprocessing the collected work data and converting it into an analyzable format, and a device for inputting the converted data into a generative model for learning. This enables the efficient inheritance of traditional techniques and the generation of new proposals in line with modern trends.

[0135] An "engineer" is someone who has specific skills or abilities and uses those skills to create products or services.

[0136] "Work data" refers to data that includes information on the actions, procedures, and tools used by engineers when they perform work.

[0137] "Video equipment" refers to equipment such as cameras that record the actions and work processes of technicians as visual data.

[0138] A "sensor device" is a device for acquiring environmental data and physical parameters such as temperature, pressure, and humidity in real time.

[0139] "Preprocessing" is the process of converting collected raw data into an analyzable format, removing noise, and converting the data.

[0140] A "generative model" is an artificial intelligence model that learns the actions and techniques of engineers based on collected data and generates new proposals.

[0141] "Data storage" refers to a storage device or system for permanently storing learned data and analysis results.

[0142] "Trend data" is data that shows market and consumer trends and is collected based on information on the Internet.

[0143] A "data analysis model" is an artificial intelligence model that analyzes collected trend data and extracts important patterns and market trends.

[0144] A "proposal" is a new product design or technical improvement plan generated based on the generative model and data analysis model.

[0145] "Evaluation" refers to information including feedback and opinions given by engineers regarding the proposal, as well as actual work results.

[0146] "Algorithm" refers to the computational methods and procedures used by generative models and data analysis models to generate new proposals.

[0147] System Overview

[0148] This invention is a system for digitizing and passing on engineers' skills, and is composed of a video device, a sensor device, a generative model, a data analysis model, data storage, and an evaluation feedback device. This system collects and analyzes engineers' work data, generates new proposals, and realizes technological evolution.

[0149] Hardware and Software Configuration

[0150] The system uses the following hardware and software:

[0151] Video equipment: High-resolution camera

[0152] Sensor devices: temperature sensors, pressure sensors, humidity sensors

[0153] Generative model: Deep learning model (e.g., TENSORFLOW (registered trademark), PyTorch)

[0154] Data analysis models: Natural language processing and data mining tools (e.g., Scikit-learn, NLTK)

[0155] Data storage: Cloud storage (e.g., Amazon S3, Google Cloud Storage)

[0156] Evaluation Feedback Instrument: A dedicated feedback collection application

[0157] Specific actions

[0158] The system works as follows: First, video and sensor devices collect data on the technician's work in real time. The video devices capture high-resolution images of the technician's hand movements and the tools they use, while the sensor devices collect environmental data such as temperature, humidity, and pressure. This data is sent to a server and stored in cloud storage.

[0159] The server then preprocesses the collected data, which includes noise removal, data shaping, and format conversion. The preprocessed data is then input into a generative model, which learns the technician's behavior patterns and techniques. The data learned by the generative model is then stored in data storage.

[0160] In parallel, the data analysis model collects and analyzes the latest trend data from the Internet, for example, from social media, fashion sites, and market reports. The analyzed trend data is then input into the generative model and used to generate new proposals.

[0161] Finally, the generated proposals are presented to engineers, whose evaluations are collected through a feedback collection application. This feedback is used to refine the generative model and data analysis model algorithms, thereby improving the accuracy of future proposals and technical improvements.

[0162] Specific examples

[0163] As a potter creates a tea bowl, a video device captures detailed footage of the potter's hand movements and the tools he uses, while a sensor device collects the temperature and humidity of the work surface. The preprocessed data is fed into a generative model, which learns how the potter moves his hands and uses the tools. At the same time, a data analysis model collects and analyzes the latest trends, and based on this information, new tea bowl design proposals are generated.

[0164] The craftsman is presented with a prompt: "Please prototype a newly proposed tea bowl design and report the production process and final evaluation to the server." Based on this feedback, the algorithms of the generative model and data analysis model are improved, and the accuracy of the next proposal is improved.

[0165] Prompt Sentence Examples

[0166] Here are some example prompts to input to the generative AI model:

[0167] "We provide a dataset to learn how artisans use their hands and tools to create tea bowls. You can then propose new designs for tea bowls based on this data."

[0168] This concludes the "Mode for carrying out the invention." This system digitizes the skills of engineers and generates new proposals that are in line with trends, thereby realizing the inheritance and evolution of technology.

[0169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0170] Step 1:

[0171] The server collects data in real time from video and sensor devices installed in the technician's workspace. The video devices capture high-resolution images of the technician's hand movements and the tools they use, while the sensor devices collect environmental data such as temperature, humidity, and pressure. The input data consists of video (video stream) and sensor information (numerical data), which the server stores in cloud storage. Specifically, the camera captures the movement, and the various sensors read the values ​​and send them to the server.

[0172] Step 2:

[0173] The server preprocesses the data stored in the cloud storage. Preprocessing includes noise removal, data shaping, and format conversion. For example, it removes unwanted noise from video data and synchronizes sensor data on the time axis. The input data is raw data, and the output data is preprocessed data. Specifically, the server applies a noise filtering algorithm to unify the different data formats.

[0174] Step 3:

[0175] The server inputs the preprocessed data into a generative AI model. The generative AI model uses this data to learn the technician's movements and work patterns. The input data is preprocessed technical data, and the output data is the learning results (a numerical model of the technical data). Specifically, the server runs the generative AI model (e.g., a deep learning network) and proceeds with learning based on the dataset.

[0176] Step 4:

[0177] Data analysis AI collects trend data from the internet. It automatically collects and analyzes the latest trend information from sources such as social media, fashion sites, and market reports. The input data is text and image data from the web, and the output data is the analysis results (trend information). Specifically, data analysis AI performs web scraping and analyzes the collected data using natural language processing (NLP) algorithms.

[0178] Step 5:

[0179] Data analysis AI combines the technical data learned by the generative AI model with collected trend data to generate new proposals. The input data is the learned technical data and analyzed trend data, and the output data is new proposals (product designs or technical improvement ideas). Specifically, data analysis AI combines these data sets to generate new designs and product concepts.

[0180] Step 6:

[0181] The server presents the generated proposal to the engineer and collects their evaluations and opinions. The input data is the new proposal, and the output data is the feedback from the engineer. The server receives the engineer's evaluations and opinions using a feedback collection application. Specifically, the server sends the generated proposal to the engineer's dedicated terminal, and the engineer enters feedback on it.

[0182] Step 7:

[0183] The server improves the algorithms of the generative AI model and data analysis AI based on the collected feedback. The input data is feedback from engineers, and the output data is the improved algorithm. Specifically, the server analyzes the feedback data and adjusts the parameters of the generative AI and data analysis model, thereby improving the accuracy of the next proposal.

[0184] (Application example 1)

[0185] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0186] Traditionally, the transmission of artisanal skills has relied on oral and practical training, making it difficult to transfer skills and requiring a great deal of time and effort. Furthermore, in order to quickly respond to modern market trends, it is essential to improve techniques and create new proposals, but this is not easy. Furthermore, because artisanal skills are highly advanced, they cannot be immediately understood even after watching a demonstration, and new techniques must be learned through trial and error. However, this process also presents a problem: it is not efficient.

[0187] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0188] In this invention, the server includes a camera and sensor means for collecting technical data from craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generation AI for learning, a means for storing the learning results of the generation AI in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI, a means for feeding back the generated proposals to the craftsmen and collecting their evaluations, a means for improving the models of the generation AI and the data analysis AI based on the collected feedback, a means for displaying the proposals to the craftsmen in real time via smart glasses, and a means for collecting feedback from the smart glasses and storing it in the cloud. This not only enables efficient skill transfer, but also enables the rapid generation of new proposals that reflect modern market trends and allows craftsmen to accept and improve the proposals in real time.

[0189] Definitions of important words

[0190] A "camera" is a device for recording images of objects or people.

[0191] A "sensor" is a device that measures physical motion or environmental data and collects that information in digital form.

[0192] "Preprocessing" is a data processing step to convert collected data into a format suitable for analysis and learning.

[0193] "Generative AI" is an artificial intelligence model that learns artisan techniques and trend data to generate new proposals.

[0194] A "database" is a digital storage device for systematically storing and managing collected technical data and the learning results of generative AI.

[0195] "Data Analysis AI" is an artificial intelligence model that collects and analyzes trend data to identify current market trends.

[0196] "Trend data" refers to data on the latest trends and market trends on the Internet.

[0197] "Feedback" refers to the evaluation and opinions of craftsmen regarding new proposals.

[0198] "Smart glasses" are wearable devices that display images and have functions such as cameras and sensors.

[0199] The "cloud" is a data storage and computing service provided over the internet.

[0200] MODE FOR CARRYING OUT THE INVENTION

[0201] System Overview

[0202] The system of this invention is composed of cameras and sensors, generative AI, data analysis AI, a database, smart glasses, cloud storage, and a feedback loop. This system not only collects and stores the craftsman's technical data, but also enables analysis and generation of new proposals using generative AI, and continuous improvement through feedback.

[0203] Learning and preserving craftsmanship

[0204] Technical Data Collection

[0205] The server installs cameras and sensor devices in the space where the artisan works. These devices monitor and record the artisan's movements and work environment in real time. For example, when an artisan creates pottery, the camera captures detailed images of the artisan's hand movements and the tools he uses, while the sensors collect data such as the shape and temperature of the vessel. The collected video and sensor data are stored in cloud storage.

[0206] Generative AI learning

[0207] Technical Data Learning

[0208] The server inputs the pre-processed technical data into the generative AI model, which then learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[0209] Data analysis and new proposals

[0210] Trend data collection and analysis

[0211] Data analysis AI collects the latest trend data from the internet, for example, automatically retrieving relevant information from social media, fashion sites, market reports, etc., to identify current market trends.

[0212] Generate a new proposal

[0213] The data analysis AI combines the technical data learned by the generation AI with the analyzed trend data to generate new product and design proposals. These proposals are fed back to artisans in real time via smart glasses. For example, a new jewelry design using traditional pearl-making techniques can be generated, and the artisan can then create it.

[0214] Gathering feedback and improving the system

[0215] Collecting feedback

[0216] The smart glasses collect feedback from artisans on new proposals and send the data to the cloud, where the server uses the feedback to improve its generative and data-analytical AI models.

[0217] System Improvements

[0218] The server adjusts the algorithms of the generation AI and data analysis AI based on the evaluations and opinions of the craftsmen and reflects them in the next proposal. This allows the system to continuously evolve and make higher quality proposals.

[0219] Specific example details

[0220] Imagine a traditional pearl craftsman wearing smart glasses. A camera in the glasses records his movements in real time and stores them in the cloud. AI then suggests new designs based on the latest jewelry trends, which the craftsman then prototypes. The entire process works seamlessly, with a feedback loop that allows the system to improve.

[0221] Prompt Sentence Examples

[0222] "Create contemporary jewelry designs using traditional pearling techniques, while also taking into account the latest fashion trends."

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Program processing flow

[0225] Step 1:

[0226] Technical data collection

[0227] The server uses cameras and sensors installed in the space where the craftsmen work to monitor and record the craftsmen's movements and working environment in real time.

[0228] Input: Video and environmental data from cameras and sensors

[0229] Data processing: Integrate and preprocess video data and sensor data

[0230] Output: Pre-processed technical data

[0231] Step 2:

[0232] Data Preprocessing

[0233] The server converts the collected technical data into an analyzable format: for example, video data is split into frames, and sensor data is converted into appropriate units.

[0234] Input: Preprocessed technical data

[0235] Data calculation: Preprocessing such as frame division, unit conversion, noise removal, etc.

[0236] Output: Data in a parsable format

[0237] Step 3:

[0238] Generative AI learning

[0239] The server inputs technical data in an analyzable format into the generation AI, allowing it to learn the movement patterns and techniques of the craftsmen.

[0240] Input: Data in a parsable format

[0241] Data Computation: Learning Processes with Generative AI Models

[0242] Output: Technical data as a result of learning

[0243] Step 4:

[0244] Saving to a database

[0245] The server stores the learning results of the generative AI in a database, allowing important technical information to be systematically stored.

[0246] Input: Generative AI learning results

[0247] Data calculation: saving to database

[0248] Output: Technical data in the database

[0249] Step 5:

[0250] Trend data collection and analysis

[0251] The server uses data analysis AI to collect and analyze the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc.

[0252] Input: Trending information on the internet

[0253] Data calculation: Trend data collection and analysis

[0254] Output: Analyzed trend data

[0255] Step 6:

[0256] Generate a new proposal

[0257] The server combines the technical data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new product and design proposals.

[0258] Input: Technical data, trend data

[0259] Data calculation: Proposal generation process

[0260] Output: New proposal

[0261] Step 7:

[0262] Feedback to smart glasses

[0263] The server displays the generated new suggestions to the craftsman in real time via smart glasses, and the craftsman works on the suggestions and provides feedback.

[0264] Input: New Proposal

[0265] Data calculation: Real-time display on smart glasses

[0266] Output: Craftsmanship and feedback

[0267] Step 8:

[0268] Collect feedback and store it in the cloud

[0269] Feedback collected from smart glasses is stored in cloud storage.

[0270] Input: Feedback from craftsmen

[0271] Data Computing: Feedback Collection and Cloud Storage Processing

[0272] Output: Feedback data on the cloud

[0273] Step 9:

[0274] System Improvements

[0275] The server uses the collected feedback to improve its generative and data analysis AI models, which will result in more accurate suggestions for the next time.

[0276] Input: Feedback data on the cloud

[0277] Data calculation: Model refinement process

[0278] Output: Improved generative AI and data analysis AI models

[0279] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0280] System Overview

[0281] This invention is a system for preserving and passing on artisanal techniques, and includes a camera and sensor means, generation AI, data analysis AI, database, feedback loop, and an emotion engine that recognizes the user's emotions. This allows for the artisan's emotional feedback on proposed new designs and techniques to be incorporated, resulting in more accurate suggestions and system improvements.

[0282] Learning and preserving craftsmanship

[0283] Technical Data Collection

[0284] Subject: Server

[0285] The server installs cameras and sensor devices in the space where the craftsmen work. These devices monitor and record the craftsmen's movements and working environment in real time, and the collected data is stored in cloud storage.

[0286] Specific examples

[0287] As a craftsman creates a tea bowl, the camera captures the craftsman's hand movements and the tools he uses in detail. The sensor device collects data such as the shape and temperature of the bowl. This allows even the finest techniques to be accurately recorded as digital data.

[0288] Generative AI learning

[0289] Technical Data Learning

[0290] Subject: Server

[0291] The server inputs the pre-processed data into a generative AI model, which learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[0292] Data analysis and new proposals

[0293] Trend data collection and analysis

[0294] Subject: Data Analysis AI

[0295] Data analysis AI collects the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc. It analyzes this data and identifies current market trends.

[0296] Specific examples

[0297] Data analysis AI analyzes popular online search terms and best-selling products to identify the most popular designs and color combinations, providing the raw materials for creating new proposals that are in line with the times.

[0298] Emotion engine combination and feedback

[0299] Generating and Evaluating New Proposals

[0300] Subject: Server

[0301] The server presents the new proposals generated by the generation AI and data analysis AI to the craftsman. The emotion engine analyzes the craftsman's emotions in real time after receiving the proposal and includes the analysis data in feedback. This allows the craftsman's emotional reaction to the proposal to be reflected in the system and used in the next proposal.

[0302] Gathering feedback and improving the system

[0303] Subject: Server

[0304] The server organizes the feedback data collected from the craftsmen and stores it in a database. Based on the collected feedback, the generation AI and data analysis AI models are improved to improve the accuracy of the next proposal.

[0305] Specific examples

[0306] A craftsman creates a prototype of a newly proposed tea bowl design and reports the production process and final evaluation to the server. The emotion engine analyzes the craftsman's emotions, such as happiness, surprise, or confusion, in real time when they see the proposal, and includes this data in feedback. The server uses this feedback to adjust the algorithms of the generation AI and data analysis AI, and reflects the results in the next proposal.

[0307] Emotion Engine Details

[0308] Emotion data collection and analysis

[0309] Subject: Server

[0310] The server collects the craftsman's facial expressions and tone of voice through devices such as cameras and microphones, and the emotion engine analyzes the data to recognize emotions, making it easier to collect not only technical feedback but also emotional feedback.

[0311] Specific examples

[0312] While the craftsman is reviewing the proposal, a camera captures his / her facial expressions and a microphone records his / her tone of voice. The emotion engine analyzes this data to identify the craftsman's emotions and transmits the data to a server, providing a comprehensive view of the craftsman's technical and emotional responses.

[0313] conclusion

[0314] The system of this invention can learn and store traditional artisan techniques as digital data, generate new proposals that match modern trends, and comprehensively incorporate the user's emotional feedback. This will enable the inheritance and evolution of artisan techniques, as well as advanced proposals that match the user's preferences and emotions.

[0315] The processing flow will be explained below.

[0316] Learning and preserving craftsmanship

[0317] Technical Data Collection

[0318] Subject: Server

[0319] Step 1:

[0320] The server installs cameras and sensor devices in the craftsman's workshop, positioned to optimally record the craftsman's movements.

[0321] Step 2:

[0322] The server collects video and sensor data from cameras and sensor devices in real time and stores it in cloud storage.

[0323] Step 3:

[0324] The server removes noise from the collected video data and divides it into frames. The sensor data is normalized and organized as time-series data.

[0325] Specific examples

[0326] Step 1:

[0327] The server places a camera on the desk where the craftsman is working and adjusts it to the optimal angle.

[0328] Step 2:

[0329] The server begins to collect video footage of the craftsman shaping the tea bowl and shape data obtained by the sensor in real time.

[0330] Step 3:

[0331] The server denoises the collected video data, divides it into frames, and normalizes the sensor data to create time-series data.

[0332] Generative AI learning

[0333] Technical Data Learning

[0334] Subject: Server

[0335] Step 1:

[0336] The server inputs pre-processed technical data into the generative AI model.

[0337] Step 2:

[0338] The server begins learning the craftsmanship of generative AI and trains iteratively.

[0339] Step 3:

[0340] The server stores the results learned by the generative AI in a database and manages them in a reusable format.

[0341] Specific examples

[0342] Step 1:

[0343] The server inputs preprocessed video data of the craftsman shaping the tea bowl into the generation AI.

[0344] Step 2:

[0345] The server uses generative AI to repeatedly train itself on data to learn things like hand movements and the shape of the vessel.

[0346] Step 3:

[0347] The server stores the learning results in a database and adds metadata (learning date and time, data size, etc.).

[0348] Data analysis and new proposals

[0349] Trend data collection and analysis

[0350] Subject: Data Analysis AI

[0351] Step 1:

[0352] Data analysis AI collects trend data from social media, fashion sites, market reports, etc.

[0353] Step 2:

[0354] Data analysis AI analyzes collected trend data, identifies major themes and styles, and performs clustering.

[0355] Step 3:

[0356] The data analysis AI generates new proposals based on the technical data learned by the generation AI and the results of trend analysis.

[0357] Specific examples

[0358] Step 1:

[0359] Data analysis AI collects the latest tea utensil design and color trends from the internet.

[0360] Step 2:

[0361] Data analysis AI analyzes collected trend data to identify popular designs and color combinations.

[0362] Step 3:

[0363] The data analysis AI combines the technical data of the craftsmen learned by the generation AI to propose new tea bowl designs.

[0364] Emotion engine combination and feedback

[0365] Generating and Evaluating New Proposals

[0366] Subject: Server

[0367] Step 1:

[0368] The server presents new proposals to the craftsman and simultaneously collects the craftsman's emotional data through cameras and microphones.

[0369] Step 2:

[0370] The emotion engine analyzes collected facial expression data and voice tone to recognize the emotions of the craftsman.

[0371] Step 3:

[0372] The server records the craftsman's emotional response to the proposal as analytical data and stores this data as feedback.

[0373] Specific examples

[0374] Step 1:

[0375] The server shows the new tea bowl design to the craftsman and collects the craftsman's emotional responses (facial expressions, tone of voice) in real time using a camera and microphone.

[0376] Step 2:

[0377] The emotion engine analyzes the craftsman's smile, exclamation of surprise, etc. to identify his / her emotions.

[0378] Step 3:

[0379] The server stores the analyzed emotion data as feedback data for the proposal and uses it to generate the next proposal.

[0380] Gathering feedback and improving the system

[0381] Subject: Server

[0382] Step 1:

[0383] The server organizes the collected feedback data and stores it in a database.

[0384] Step 2:

[0385] The server improves the generative AI and data analysis AI models based on the collected feedback.

[0386] Step 3:

[0387] The server uses the improved model to generate the next proposal, improving the accuracy of the system.

[0388] Specific examples

[0389] Step 1:

[0390] The server organizes the feedback data and emotion data from the craftsmen and stores them in a database.

[0391] Step 2:

[0392] The server adjusts the algorithms of the generative AI and data analysis AI based on the collected feedback and improves the model.

[0393] Step 3:

[0394] The server will propose the next bowl design based on the improved model, improving its accuracy.

[0395] Example 2

[0396] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0397] Preserving and passing on traditional craftsmanship is becoming increasingly difficult as technology becomes more advanced. Furthermore, adapting to modern market trends requires new proposals that take into account not only the craftsman's skills but also the latest market trends. Furthermore, to improve the accuracy of proposals, it is necessary to incorporate not only the craftsman's technical feedback but also their emotional reactions. However, it was difficult to achieve these comprehensively with conventional systems.

[0398] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a camera and sensor device means for collecting technical data of craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generative AI model for learning, a means for saving the learning results of the generative AI model in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generative AI model and the trend data analyzed by the data analysis AI means, a means for feeding back the generated proposals to the craftsmen and analyzing the craftsmen's emotions in real time using an emotion engine, and a means for improving the generative AI model and the model of the data analysis AI means based on the collected feedback. This makes it possible to realize an advanced feedback system that precisely preserves the craftsmen's skills, generates new technical proposals that respond to modern trends, and further reflects the craftsmen's emotional reactions.

[0399] A "camera" is a device that records the craftsman's actions and working environment as video data.

[0400] A "sensor device" is a device that measures physical information (such as temperature and shape) in a craftsman's working environment and collects it as data.

[0401] "Preprocessing" is the process of removing noise from collected technical data and converting it into an analyzable form.

[0402] A "generative AI model" is an artificial intelligence model that learns preprocessed technical data and analyzes and stores the movement patterns and techniques of craftsmen.

[0403] A "database" is a data storage system for systematically storing the learning results of a generative AI model.

[0404] "Data Analysis AI Method" is an artificial intelligence system that collects and analyzes trend data on the Internet to identify current market trends.

[0405] The "emotion engine" is a system that analyzes the facial expressions and tone of voice of craftsmen and recognizes their emotions in real time.

[0406] "Feedback" is the process of collecting artisans' technical and emotional reactions to new proposals.

[0407] "Model refinement" is the process of adjusting the algorithms of generative AI models and data analysis AI methods based on collected feedback data.

[0408] "New proposals" are proposals for new technologies and designs that are generated by combining data analyzed by generative AI models and data analysis AI means.

[0409] MODE FOR CARRYING OUT THE INVENTION

[0410] System Overview

[0411] The system aims to preserve and pass on artisanal techniques and is a comprehensive system that includes cameras and sensor devices, generative AI models, data analysis AI methods, databases, and an emotion engine. This system enables more accurate proposals and system improvements, including the emotional feedback of artisans on new designs and technical proposals.

[0412] Hardware and software used

[0413] Hardware

[0414] Camera: Used to record the craftsman's movements and working environment as video data.

[0415] Sensor device: Used to measure and collect data such as changes in shape and temperature during work.

[0416] Cloud storage: Used to store collected data.

[0417] software

[0418] Generative AI model: Learns from artisan technical data and uses it to generate new suggestions.

[0419] Data analysis AI means: Used to analyze trend data on the Internet.

[0420] Emotion engine: Used to analyze the emotions of craftsmen in real time.

[0421] Database: Used to store the learning results and feedback data of the generative AI model.

[0422] System processing flow

[0423] 1. Data collection: The server installs cameras and sensor devices in the space where the craftsman works, which monitors and records the craftsman's movements and working environment in real time. This information is stored in cloud storage.

[0424] Example: A craftsman creating a tea bowl is filmed with a camera, and a sensor device records the shape and temperature of the bowl.

[0425] 2. Data Preprocessing: The server cleanses the collected data and converts it into a format that the generative AI model can understand, removing noise and making the data analyzable.

[0426] Example: Cutting unnecessary scenes from captured footage and removing outliers in temperature data.

[0427] 3. Learning by generative AI: The server inputs the preprocessed data into a generative AI model, which learns the movement patterns and techniques of the craftsman. The learning results are stored in a database.

[0428] Example: AI learns how a craftsman moves his hands and uses tools.

[0429] 4. Trend data collection and analysis: Data analysis AI tools collect and analyze the latest trend data from the Internet, thereby understanding current market trends.

[0430] Example: Identify popular designs and color combinations based on data collected from social media and fashion sites.

[0431] 5. Generate new proposals: The server combines the data from the generative AI model and the data analysis AI method to generate new proposals, which are then fed back to the craftsman.

[0432] Example: The newly generated tea bowl design is displayed on the craftsman's device.

[0433] 6. Emotion engine analysis: Analyze the emotions of the craftsmen who receive the proposal in real time and collect their feedback. Analyze facial expressions and tone of voice through cameras and microphones.

[0434] Example: The emotion engine analyzes the happiness and surprise of a craftsman when he sees a new design.

[0435] 7. Feedback collection and system improvement: The server will improve the generative AI model and data analysis AI means based on the collected feedback data and reflect this in the next proposal.

[0436] Example: A craftsman prototypes a new tea bowl design and reports his or her impressions to the server. This data is used to retrain the AI ​​model.

[0437] Prompt Sentence Examples

[0438] "Describe a system for analyzing video data of the traditional tea bowl making process and generating new design proposals that take into account current trends. Also, explain how you incorporate the artisan's emotional response to the proposals."

[0439] This system can learn and store traditional artisan techniques as digital data, generate new proposals that match modern trends, and comprehensively incorporate the user's emotional feedback. This allows for the preservation and evolution of artisan techniques, and enables advanced proposals that match the user's preferences and emotions.

[0440] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0441] Step 1:

[0442] Installation of cameras and sensor devices

[0443] Subject: Server

[0444] Description:

[0445] The server installs cameras and sensor devices in the space where the craftsman works, setting the cameras at the appropriate positions and angles and placing the sensors at the appropriate work locations.

[0446] input:

[0447] Camera and sensor devices.

[0448] output:

[0449] You are now ready to record the craftsman's movements and working environment.

[0450] Specific behavior:

[0451] The server remotely adjusts the focus and angle of the camera via the network, and places sensor devices around the work object.

[0452] Step 2:

[0453] Data collection

[0454] Subject: Server

[0455] Description:

[0456] The server collects real-time data on the worker's movements and working environment through cameras and sensor devices, and this data is stored in cloud storage.

[0457] input:

[0458] Craftsman behavior and working environment.

[0459] output:

[0460] Video data and environmental data are stored in cloud storage.

[0461] Specific behavior:

[0462] As the craftsman shapes the tea bowl, the camera captures his or her hand movements, and the sensor device measures the shape and temperature and sends the data to a server.

[0463] Step 3:

[0464] Data Preprocessing

[0465] Subject: Server

[0466] Description:

[0467] The server cleanses the collected data and converts it into an analyzable format, which involves removing noise and converting the data format.

[0468] input:

[0469] Collected video and environmental data.

[0470] output:

[0471] Cleansed, parseable data.

[0472] Specific behavior:

[0473] The server denoises the collected images, cuts out unnecessary parts, removes outliers from the sensor data, and converts them into standard formats (e.g., CSV or PNG).

[0474] Step 4:

[0475] Generative AI learning

[0476] Subject: Server

[0477] Description:

[0478] The server inputs the preprocessed data into a generative AI model to learn the craftsman's technical patterns, and the learning results are stored in a database.

[0479] input:

[0480] Preprocessed data.

[0481] output:

[0482] Technical data learned by generative AI models.

[0483] Specific behavior:

[0484] The server inputs preprocessed video and sensor data into a generative AI model, which then learns the patterns of the craftsman's hand movements and techniques. The learning results are stored in a database.

[0485] Step 5:

[0486] Trend data collection and analysis

[0487] Subject: Data Analysis AI

[0488] Description:

[0489] Data analysis AI collects the latest trend data from the internet and analyzes it, and the analysis results are used to generate new proposals.

[0490] input:

[0491] Trending data on the internet.

[0492] output:

[0493] Analyzed trend data.

[0494] Specific behavior:

[0495] Data analysis AI searches the web using specific keywords (for example, "handmade tea bowl trends") and analyzes the collected data to identify popular designs and color combinations.

[0496] Step 6:

[0497] Generate a new proposal

[0498] Subject: Server

[0499] Description:

[0500] The server combines the generative AI model with the data generated by the data analysis AI to generate new suggestions, which are then fed back to the craftsman.

[0501] input:

[0502] Generative AI model learning results and analyzed trend data.

[0503] output:

[0504] New technology proposal.

[0505] Specific behavior:

[0506] The server combines the technical data obtained from the generation AI model with the trend information obtained from the data analysis AI to generate a new tea bowl design and send it to the craftsman's device.

[0507] Step 7:

[0508] Emotion Engine Analysis

[0509] Subject: Server

[0510] Description:

[0511] The server uses an emotion engine to analyze the craftsman's emotions in real time, identifying the craftsman's emotions based on data obtained through cameras and microphones.

[0512] input:

[0513] Real-time data from cameras and microphones.

[0514] output:

[0515] Analyzed emotion data.

[0516] Specific behavior:

[0517] As the craftsman reviews the design of a new tea bowl, a camera captures his facial expressions and a microphone records his tone of voice. The server uses an emotion engine to analyze this data and identify the craftsman's emotions.

[0518] Step 8:

[0519] Gathering feedback and improving the system

[0520] Subject: Server

[0521] Description:

[0522] The server uses the collected feedback to improve the generative AI model and data analysis AI, which will improve the accuracy of the next proposal.

[0523] input:

[0524] Technical and emotional feedback data from artisans.

[0525] output:

[0526] Improved generative AI models and data analysis AI.

[0527] Specific behavior:

[0528] The craftsman prototypes the new tea bowl design and reports his / her opinions and impressions to the server, which then retrains the generative AI model and data analysis AI method based on the collected feedback data and reflects it in the next proposal.

[0529] (Application example 2)

[0530] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0531] Conventional autonomous vehicles have been unable to fully utilize the driver's emotional state and real-time environmental information to improve driving comfort and safety, and lack the means to effectively collect and analyze this information and make improvements based on system feedback.

[0532] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0533] In this invention, the server includes a camera and sensor means for collecting technical data from craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generation AI for learning, a means for storing the learning results of the generation AI in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI, a means for feeding back the generated proposals to craftsmen and collecting their evaluations, a means for improving the models of the generation AI and the data analysis AI based on the collected feedback, a means for optimizing driving patterns and routes to improve the comfort and safety of the other-type vehicle while driving, a means for controlling driving based on the optimized driving patterns and routes, an emotion engine for analyzing the emotional state of the driver, and a means for collecting feedback and improving the system based on the emotional state analyzed by the emotion engine. This makes it possible to effectively utilize the real-time environment and the driver's emotional state while driving, thereby improving comfort and safety.

[0534] "Camera and sensor means" refers to devices that photograph and measure the driver's condition and driving environment in real time.

[0535] "Means of preprocessing and converting into an analyzable format" refers to the process of converting collected data into a format that can be analyzed by AI.

[0536] "Means of inputting data into a generative AI and having it learn" refers to the process of inputting preprocessed data into a generative AI model and having it learn.

[0537] "Means for saving in a database" refers to a database system for recording and saving learning results.

[0538] "Data analysis AI means for collecting and analyzing trend data" is an artificial intelligence system for collecting and analyzing trend information on the Internet.

[0539] The "means of generating new proposals" is the process of combining the data learned by the generation AI with the trend data analyzed by the data analysis AI to create new proposals.

[0540] "Feedback and evaluation collection measures" are the processes of presenting new proposals to drivers and collecting their reactions and evaluations.

[0541] "Means to improve generative and analytical AI models" refers to the process of improving AI models based on collected feedback to improve the accuracy of future recommendations.

[0542] "Means for optimizing driving patterns and routes" refers to the process of calculating optimal driving patterns and routes to improve the comfort and safety of the vehicle while driving.

[0543] "Means for controlling driving" refers to a system that controls the vehicle based on optimized driving patterns and routes.

[0544] The "emotion engine for analyzing the driver's emotional state" is a system that uses cameras and microphones to analyze the driver's facial expressions and tone of voice to recognize their emotions.

[0545] "Means for collecting feedback and improving the system" refers to the process of collecting feedback based on the driver's emotional state and improving the overall system based on that feedback.

[0546] This invention provides a system that collects, analyzes, and feeds back various data to improve the comfort and safety of automobiles while driving. Specific methods and processes for realizing this system are described below.

[0547] System Configuration

[0548] The system consists of the following main components:

[0549] 1. Camera and sensor means:

[0550] This is a device that captures and measures the driver's condition and driving environment in real time. Specifically, it includes cameras and microphones installed inside the vehicle and various sensors that monitor the external environment.

[0551] 2. Data preprocessing methods:

[0552] This software preprocesses the collected data and converts it into an analyzable format, for example by dividing the collected video data into an appropriate number of frames, removing noise, and normalizing it.

[0553] 3. Generative AI Model:

[0554] This is an artificial intelligence model that inputs the preprocessed data and performs learning, thereby learning data related to the driver's behavioral patterns and driving environment.

[0555] 4. Database:

[0556] This is a database system for recording and storing the learning results of the generation AI. This system stores environmental data during driving, the driver's emotional state, traffic information, etc.

[0557] 5. Data analysis AI methods:

[0558] This is an AI system for collecting and analyzing trend data, such as traffic information, weather data, and social media trend information from the Internet.

[0559] 6. New proposal generation methods:

[0560] This is the process of combining the data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new suggestions, which will then suggest optimal driving patterns and routes for the driver.

[0561] 7. Feedback and evaluation collection methods:

[0562] New suggestions are presented to drivers and their reactions and evaluations are collected, for example, by presenting the suggestions via an in-car display or smartphone.

[0563] 8. Model refinement methods:

[0564] This is the process of improving the generative AI and data analysis AI models based on the collected feedback, which will improve the accuracy of the next proposal.

[0565] 9. Driving pattern and route optimization measures:

[0566] It is an AI system that calculates optimal driving patterns and routes to improve vehicle comfort and safety while driving.

[0567] 10. Travel control means:

[0568] This is a system for controlling vehicles based on optimized driving patterns and routes. Autonomous driving systems and actuators are used for actual vehicle control.

[0569] 11. Emotion Engine:

[0570] This system uses cameras and microphones to analyze the driver's facial expressions and tone of voice to recognize their emotions, and is used to grasp the driver's fatigue and state of tension in real time.

[0571] 12. Feedback collection and system improvement methods:

[0572] It is a process of collecting feedback based on the driver's emotional state and using that to improve the overall system.

[0573] Specific examples

[0574] For example, when a driver is driving on the highway, the emotion engine analyzes the driver's facial expressions to detect signs of fatigue. This data is analyzed by a generative AI model and used to optimize a safe driving route. The optimal route is calculated and displayed on the vehicle's display. Driver feedback is also collected and reflected in future recommendations.

[0575] Prompt Sentence Examples

[0576] Below are some example prompts that can be input to the generative AI model in this system:

[0577] "What facial expressions do drivers have while driving that make you feel safer? And vice versa?"

[0578] The above configuration makes it possible to effectively improve comfort and safety during driving.

[0579] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0580] Step 1:

[0581] The server monitors the driver's condition and driving environment in real time using cameras and sensors installed in the vehicle.

[0582] Input: Video data from cameras and sensors and environmental data

[0583] Data processing: Video data is divided into frames, and noise is removed and normalized.

[0584] Output: Preprocessed data (video frames and environmental data)

[0585] Step 2:

[0586] The server inputs the preprocessed data into a generative AI model, which learns about the driver's behavioral patterns and driving environment.

[0587] Input: Preprocessed data (video frames and environmental data)

[0588] Data Computation: Learning with Generative AI Models

[0589] Output: Learning result data (driving patterns and environmental recognition data)

[0590] Step 3:

[0591] The server stores the learning result data in a database.

[0592] Input: Learning result data obtained from the generative AI model

[0593] Data processing: Converting data into a format that can be saved in a database

[0594] Output: Learning result data stored in a database

[0595] Step 4:

[0596] The server collects relevant information from the internet using data analysis AI means to collect and analyze trend data.

[0597] Input: Internet traffic information, weather data, social media trend information

[0598] Data calculation: Analyze collected data and extract important trend information

[0599] Output: Analyzed trend data

[0600] Step 5:

[0601] The server combines the technical data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new proposals.

[0602] Input: Training result data and trend data

[0603] Data arithmetic: Combining data to generate new suggestions

[0604] Output: New proposed data (optimal driving patterns and routes)

[0605] Step 6:

[0606] The terminal provides feedback on new proposals to the driver and collects their evaluations.

[0607] Input: New proposal data

[0608] Specific operation: Displaying suggestions on the in-car display or smartphone

[0609] Output: Driver feedback data

[0610] Step 7:

[0611] The server refines its generative AI and data analysis AI models based on the collected feedback.

[0612] Input: Driver feedback data

[0613] Data calculation: Analyze feedback data and adjust AI models

[0614] Output: Improved generative AI and data analysis AI models

[0615] Step 8:

[0616] The server uses the improved AI model to optimize the vehicle's driving patterns and routes while in operation.

[0617] Input: Improved generative AI and data analysis AI models

[0618] Data calculation: Calculates optimal driving patterns and routes

[0619] Output: Optimized driving patterns and route data

[0620] Step 9:

[0621] The terminal controls the vehicle based on the optimized driving pattern and route.

[0622] Input: Optimized driving pattern and route data

[0623] Specific operation: Controlling the driving route using an autonomous driving system and actuators

[0624] Output: Control data for the vehicle during operation

[0625] Step 10:

[0626] The server collects and analyzes data from cameras and microphones using an emotion engine to analyze the driver's emotional state.

[0627] Input: Camera video and audio data

[0628] Data processing: Emotional state analysis (facial expression recognition and voice tone analysis)

[0629] Output: Driver's emotional state data

[0630] Step 11:

[0631] The server collects feedback based on the emotional state analyzed by the emotion engine and improves the system.

[0632] Input: Driver's emotional state data

[0633] Data calculation: Analyze emotional state data and improve the entire system

[0634] Output: Improved system feedback data

[0635] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0636] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0637] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0638] [Second embodiment]

[0639] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0640] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0641] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0642] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0643] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0644] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0645] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0646] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0647] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0648] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0649] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0650] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0651] System Overview

[0652] The system of the present invention is composed of a camera and sensor means, generation AI, data analysis AI, database, and feedback loop, which allows for the collection, storage, and analysis of craftsmanship data, the generation of new proposals, and the transfer of skills.

[0653] Learning and preserving craftsmanship

[0654] Technical Data Collection

[0655] Subject: Server

[0656] The server installs cameras and sensor devices in the space where the craftsmen work. These devices monitor and record the craftsmen's movements and work environment in real time. The server saves the video and audio data collected from the cameras and sensor devices in cloud storage.

[0657] Specific examples

[0658] As a craftsman creates a tea bowl, the camera captures the craftsman's hand movements and the tools he uses in detail. The sensor device collects data such as the shape and temperature of the bowl. This allows even the finest techniques to be accurately recorded as digital data.

[0659] Generative AI learning

[0660] Technical Data Learning

[0661] Subject: Server

[0662] The server inputs the pre-processed data into a generative AI model, which learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[0663] Data analysis and new proposals

[0664] Trend data collection and analysis

[0665] Subject: Data Analysis AI

[0666] Data analysis AI collects the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc. It analyzes this data and identifies current market trends.

[0667] Specific examples

[0668] Data analysis AI analyzes popular online search terms and best-selling products to identify the most popular designs and color combinations, providing the raw materials for creating new proposals that are in line with the times.

[0669] Generate new suggestions and feedback

[0670] Generate a new proposal

[0671] Subject: Data Analysis AI

[0672] The data analysis AI combines the technical data learned by the generation AI with the analyzed trend data to generate new product and design proposals. These proposals are fed back to the craftsmen and used in their actual work.

[0673] Gathering feedback and improving the system

[0674] Subject: Server

[0675] The server presents the generated proposals to the craftsmen and collects their evaluations and opinions. Based on this feedback, the model of the entire system (generative AI and data analysis AI) is improved, thereby improving the quality of the generated proposals.

[0676] Specific examples

[0677] Craftsmen will prototype new tea bowl designs and report the production process and final evaluation to the server. The server will use this feedback to adjust the algorithms of the generative AI and data analysis AI, and reflect this in the next proposal.

[0678] conclusion

[0679] The system of this invention makes it possible to learn and preserve traditional artisan techniques as digital data and propose new products that match modern trends, thereby realizing the inheritance and evolution of artisan techniques.

[0680] The processing flow will be explained below.

[0681] Learning and preserving craftsmanship

[0682] Technical Data Collection

[0683] Subject: Server

[0684] 1. Step 1: Camera and Sensor Settings

[0685] The server places cameras and sensor devices in the craftsman's workshop and performs initial settings to enable accurate detection.

[0686] 2. Step 2: Start collecting data

[0687] The server collects data from cameras and sensor devices in real time and transfers it to cloud storage.

[0688] 3. Step 3: Preprocessing

[0689] The server removes noise from the collected video data, splits the video into frames, and normalizes and timestamps the sensor data.

[0690] Specific examples

[0691] 1. Step 1:

[0692] The server places the camera on the desk where the craftsman is working and adjusts it to the appropriate angle.

[0693] 2. Step 2:

[0694] The server begins to collect video footage of the craftsman shaping the tea bowl and shape data obtained by the sensor in real time.

[0695] 3. Step 3:

[0696] The server removes noise from the collected video data, splits it into frames, normalizes the sensor data, and organizes it as time-series data.

[0697] Generative AI learning

[0698] Technical Data Learning

[0699] Subject: Server

[0700] 1. Step 1: Data Entry

[0701] The server inputs the pre-processed technical data into the generative AI model.

[0702] 2. Step 2: Model training

[0703] The server begins learning the technical patterns using generative AI and trains iteratively.

[0704] 3. Step 3: Save the learning results

[0705] The server stores the results of the technical patterns learned by the generative AI in a database and manages them in a reusable form.

[0706] Specific examples

[0707] 1. Step 1:

[0708] The server inputs pre-processed video data of the craftsman shaping the tea bowl into the generation AI.

[0709] 2. Step 2:

[0710] The server repeatedly trains the generative AI with data to learn things like hand movements and the shape of the vessel.

[0711] 3. Step 3:

[0712] The server stores the learning results in a database and adds metadata (learning date and time, data size, etc.).

[0713] Data analysis and new proposals

[0714] Trend data collection and analysis

[0715] Subject: Data Analysis AI

[0716] 1. Step 1: Trend data collection

[0717] Data analysis AI collects trend data from social media, fashion sites, market reports, etc.

[0718] 2. Step 2: Trend analysis

[0719] Data analysis AI analyzes collected trend data, identifies major themes and styles, and performs clustering.

[0720] 3. Step 3: Generate new proposals

[0721] The data analysis AI generates new proposals based on the technical data learned by the generation AI and the results of trend analysis.

[0722] Specific examples

[0723] 1. Step 1:

[0724] Data analysis AI collects trend data on popular designs and colors on the Internet.

[0725] 2. Step 2:

[0726] Data analysis AI analyzes collected trend data and identifies the most popular designs and color combinations.

[0727] 3. Step 3:

[0728] The data analysis AI combines the technical data of the craftsmen learned by the generation AI to propose new tea bowl designs.

[0729] Generate new suggestions and feedback

[0730] Generating and Evaluating New Proposals

[0731] Subject: Server

[0732] 1. Step 1: Feedback on the proposal

[0733] The server presents the generated new proposals to the craftsmen and collects their evaluations and opinions.

[0734] 2. Step 2: Save the evaluation data

[0735] The server organizes the feedback data collected from the craftsmen and stores it in a database.

[0736] 3. Step 3: System Improvement

[0737] The server uses the collected feedback to improve the generative AI and data analysis AI models and reflect this in its next proposal.

[0738] Specific examples

[0739] 1. Step 1:

[0740] The server shows the new bowl design to the craftsman and encourages him to give feedback.

[0741] 2. Step 2:

[0742] The server organizes the craftsmen's feedback and stores it in a database.

[0743] 3. Step 3:

[0744] The server adjusts the algorithms of the generation AI and data analysis AI based on the collected feedback and reflects it in the next proposal.

[0745] Example 1

[0746] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0747] The inheritance of artisanal skills is extremely important in today's world, but because traditional techniques rely on oral transmission and direct instruction, they are difficult to pass on efficiently. It's also difficult to propose new ideas that are in line with market trends, putting many traditional techniques at risk of becoming outdated. Furthermore, when introducing new technologies, there is a lack of a system for systematically collecting feedback and improving models. To solve these problems, a system is needed that digitizes technology, links with trends, and utilizes feedback.

[0748] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0749] In this invention, the server includes a video device and a sensor device for collecting data on the work of engineers, a device for preprocessing the collected work data and converting it into an analyzable format, and a device for inputting the converted data into a generative model for learning. This enables the efficient inheritance of traditional techniques and the generation of new proposals in line with modern trends.

[0750] An "engineer" is someone who has specific skills or abilities and uses those skills to create products or services.

[0751] "Work data" refers to data that includes information on the actions, procedures, and tools used by engineers when they perform work.

[0752] "Video equipment" refers to equipment such as cameras that record the actions and work processes of technicians as visual data.

[0753] A "sensor device" is a device for acquiring environmental data and physical parameters such as temperature, pressure, and humidity in real time.

[0754] "Preprocessing" is the process of converting collected raw data into an analyzable format, removing noise, and converting the data.

[0755] A "generative model" is an artificial intelligence model that learns the actions and techniques of engineers based on collected data and generates new proposals.

[0756] "Data storage" refers to a storage device or system for permanently storing learned data and analysis results.

[0757] "Trend data" is data that shows market and consumer trends and is collected based on information on the Internet.

[0758] A "data analysis model" is an artificial intelligence model that analyzes collected trend data and extracts important patterns and market trends.

[0759] A "proposal" is a new product design or technical improvement plan generated based on the generative model and data analysis model.

[0760] "Evaluation" refers to information including feedback and opinions given by engineers regarding the proposal, as well as actual work results.

[0761] "Algorithm" refers to the computational methods and procedures used by generative models and data analysis models to generate new proposals.

[0762] System Overview

[0763] This invention is a system for digitizing and passing on engineers' skills, and is composed of a video device, a sensor device, a generative model, a data analysis model, data storage, and an evaluation feedback device. This system collects and analyzes engineers' work data, generates new proposals, and realizes technological evolution.

[0764] Hardware and Software Configuration

[0765] The system uses the following hardware and software:

[0766] Video equipment: High-resolution camera

[0767] Sensor devices: temperature sensors, pressure sensors, humidity sensors

[0768] Generative models: Deep learning models (e.g., TensorFlow, PyTorch)

[0769] Data analysis models: Natural language processing and data mining tools (e.g., Scikit-learn, NLTK)

[0770] Data storage: Cloud storage (e.g., Amazon S3, Google Cloud Storage)

[0771] Evaluation Feedback Instrument: A dedicated feedback collection application

[0772] Specific actions

[0773] The system works as follows: First, video and sensor devices collect data on the technician's work in real time. The video devices capture high-resolution images of the technician's hand movements and the tools they use, while the sensor devices collect environmental data such as temperature, humidity, and pressure. This data is sent to a server and stored in cloud storage.

[0774] The server then preprocesses the collected data, which includes noise removal, data shaping, and format conversion. The preprocessed data is then input into a generative model, which learns the technician's behavior patterns and techniques. The data learned by the generative model is then stored in data storage.

[0775] In parallel, the data analysis model collects and analyzes the latest trend data from the Internet, for example, from social media, fashion sites, and market reports. The analyzed trend data is then input into the generative model and used to generate new proposals.

[0776] Finally, the generated proposals are presented to engineers, whose evaluations are collected through a feedback collection application. This feedback is used to refine the generative model and data analysis model algorithms, thereby improving the accuracy of future proposals and technical improvements.

[0777] Specific examples

[0778] As a potter creates a tea bowl, a video device captures detailed footage of the potter's hand movements and the tools he uses, while a sensor device collects the temperature and humidity of the work surface. The preprocessed data is fed into a generative model, which learns how the potter moves his hands and uses the tools. At the same time, a data analysis model collects and analyzes the latest trends, and based on this information, new tea bowl design proposals are generated.

[0779] The craftsman is presented with a prompt: "Please prototype a newly proposed tea bowl design and report the production process and final evaluation to the server." Based on this feedback, the algorithms of the generative model and data analysis model are improved, and the accuracy of the next proposal is improved.

[0780] Prompt Sentence Examples

[0781] Here are some example prompts to input to the generative AI model:

[0782] "We provide a dataset to learn how artisans use their hands and tools to create tea bowls. You can then propose new designs for tea bowls based on this data."

[0783] This concludes the "Mode for carrying out the invention." This system digitizes the skills of engineers and generates new proposals that are in line with trends, thereby realizing the inheritance and evolution of technology.

[0784] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0785] Step 1:

[0786] The server collects data in real time from video and sensor devices installed in the technician's workspace. The video devices capture high-resolution images of the technician's hand movements and the tools they use, while the sensor devices collect environmental data such as temperature, humidity, and pressure. The input data consists of video (video stream) and sensor information (numerical data), which the server stores in cloud storage. Specifically, the camera captures the movement, and the various sensors read the values ​​and send them to the server.

[0787] Step 2:

[0788] The server preprocesses the data stored in the cloud storage. Preprocessing includes noise removal, data shaping, and format conversion. For example, it removes unwanted noise from video data and synchronizes sensor data on the time axis. The input data is raw data, and the output data is preprocessed data. Specifically, the server applies a noise filtering algorithm to unify the different data formats.

[0789] Step 3:

[0790] The server inputs the preprocessed data into a generative AI model. The generative AI model uses this data to learn the technician's movements and work patterns. The input data is preprocessed technical data, and the output data is the learning results (a numerical model of the technical data). Specifically, the server runs the generative AI model (e.g., a deep learning network) and proceeds with learning based on the dataset.

[0791] Step 4:

[0792] Data analysis AI collects trend data from the internet. It automatically collects and analyzes the latest trend information from sources such as social media, fashion sites, and market reports. The input data is text and image data from the web, and the output data is the analysis results (trend information). Specifically, data analysis AI performs web scraping and analyzes the collected data using natural language processing (NLP) algorithms.

[0793] Step 5:

[0794] Data analysis AI combines the technical data learned by the generative AI model with collected trend data to generate new proposals. The input data is the learned technical data and analyzed trend data, and the output data is new proposals (product designs or technical improvement ideas). Specifically, data analysis AI combines these data sets to generate new designs and product concepts.

[0795] Step 6:

[0796] The server presents the generated proposal to the engineer and collects their evaluations and opinions. The input data is the new proposal, and the output data is the feedback from the engineer. The server receives the engineer's evaluations and opinions using a feedback collection application. Specifically, the server sends the generated proposal to the engineer's dedicated terminal, and the engineer enters feedback on it.

[0797] Step 7:

[0798] The server improves the algorithms of the generative AI model and data analysis AI based on the collected feedback. The input data is feedback from engineers, and the output data is the improved algorithm. Specifically, the server analyzes the feedback data and adjusts the parameters of the generative AI and data analysis model, thereby improving the accuracy of the next proposal.

[0799] (Application example 1)

[0800] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0801] Traditionally, the transmission of artisanal skills has relied on oral and practical training, making it difficult to transfer skills and requiring a great deal of time and effort. Furthermore, in order to quickly respond to modern market trends, it is essential to improve techniques and create new proposals, but this is not easy. Furthermore, because artisanal skills are highly advanced, they cannot be immediately understood even after watching a demonstration, and new techniques must be learned through trial and error. However, this process also presents a problem: it is not efficient.

[0802] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0803] In this invention, the server includes a camera and sensor means for collecting technical data from craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generation AI for learning, a means for storing the learning results of the generation AI in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI, a means for feeding back the generated proposals to the craftsmen and collecting their evaluations, a means for improving the models of the generation AI and the data analysis AI based on the collected feedback, a means for displaying the proposals to the craftsmen in real time via smart glasses, and a means for collecting feedback from the smart glasses and storing it in the cloud. This not only enables efficient skill transfer, but also enables the rapid generation of new proposals that reflect modern market trends and allows craftsmen to accept and improve the proposals in real time.

[0804] Definitions of important words

[0805] A "camera" is a device for recording images of objects or people.

[0806] A "sensor" is a device that measures physical motion or environmental data and collects that information in digital form.

[0807] "Preprocessing" is a data processing step to convert collected data into a format suitable for analysis and learning.

[0808] "Generative AI" is an artificial intelligence model that learns artisan techniques and trend data to generate new proposals.

[0809] A "database" is a digital storage device for systematically storing and managing collected technical data and the learning results of generative AI.

[0810] "Data Analysis AI" is an artificial intelligence model that collects and analyzes trend data to identify current market trends.

[0811] "Trend data" refers to data on the latest trends and market trends on the Internet.

[0812] "Feedback" refers to the evaluation and opinions of craftsmen regarding new proposals.

[0813] "Smart glasses" are wearable devices that display images and have functions such as cameras and sensors.

[0814] The "cloud" is a data storage and computing service provided over the internet.

[0815] MODE FOR CARRYING OUT THE INVENTION

[0816] System Overview

[0817] The system of this invention is composed of cameras and sensors, generative AI, data analysis AI, a database, smart glasses, cloud storage, and a feedback loop. This system not only collects and stores the craftsman's technical data, but also enables analysis and generation of new proposals using generative AI, and continuous improvement through feedback.

[0818] Learning and preserving craftsmanship

[0819] Technical Data Collection

[0820] The server installs cameras and sensor devices in the space where the artisan works. These devices monitor and record the artisan's movements and work environment in real time. For example, when an artisan creates pottery, the camera captures detailed images of the artisan's hand movements and the tools he uses, while the sensors collect data such as the shape and temperature of the vessel. The collected video and sensor data are stored in cloud storage.

[0821] Generative AI learning

[0822] Technical Data Learning

[0823] The server inputs the pre-processed technical data into the generative AI model, which then learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[0824] Data analysis and new proposals

[0825] Trend data collection and analysis

[0826] Data analysis AI collects the latest trend data from the internet, for example, automatically retrieving relevant information from social media, fashion sites, market reports, etc., to identify current market trends.

[0827] Generate a new proposal

[0828] The data analysis AI combines the technical data learned by the generation AI with the analyzed trend data to generate new product and design proposals. These proposals are fed back to artisans in real time via smart glasses. For example, a new jewelry design using traditional pearl-making techniques can be generated, and the artisan can then create it.

[0829] Gathering feedback and improving the system

[0830] Collecting feedback

[0831] The smart glasses collect feedback from artisans on new proposals and send the data to the cloud, where the server uses the feedback to improve its generative and data-analytical AI models.

[0832] System Improvements

[0833] The server adjusts the algorithms of the generation AI and data analysis AI based on the evaluations and opinions of the craftsmen and reflects them in the next proposal. This allows the system to continuously evolve and make higher quality proposals.

[0834] Specific example details

[0835] Imagine a traditional pearl craftsman wearing smart glasses. A camera in the glasses records his movements in real time and stores them in the cloud. AI then suggests new designs based on the latest jewelry trends, which the craftsman then prototypes. The entire process works seamlessly, with a feedback loop that allows the system to improve.

[0836] Prompt Sentence Examples

[0837] "Create contemporary jewelry designs using traditional pearling techniques, while also taking into account the latest fashion trends."

[0838] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0839] Program processing flow

[0840] Step 1:

[0841] Technical data collection

[0842] The server uses cameras and sensors installed in the space where the craftsmen work to monitor and record the craftsmen's movements and working environment in real time.

[0843] Input: Video and environmental data from cameras and sensors

[0844] Data processing: Integrate and preprocess video data and sensor data

[0845] Output: Pre-processed technical data

[0846] Step 2:

[0847] Data Preprocessing

[0848] The server converts the collected technical data into an analyzable format: for example, video data is split into frames, and sensor data is converted into appropriate units.

[0849] Input: Preprocessed technical data

[0850] Data calculation: Preprocessing such as frame division, unit conversion, noise removal, etc.

[0851] Output: Data in a parsable format

[0852] Step 3:

[0853] Generative AI learning

[0854] The server inputs technical data in an analyzable format into the generation AI, allowing it to learn the movement patterns and techniques of the craftsmen.

[0855] Input: Data in a parsable format

[0856] Data Computation: Learning Processes with Generative AI Models

[0857] Output: Technical data as a result of learning

[0858] Step 4:

[0859] Saving to a database

[0860] The server stores the learning results of the generative AI in a database, allowing important technical information to be systematically stored.

[0861] Input: Generative AI learning results

[0862] Data calculation: saving to database

[0863] Output: Technical data in the database

[0864] Step 5:

[0865] Trend data collection and analysis

[0866] The server uses data analysis AI to collect and analyze the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc.

[0867] Input: Trending information on the internet

[0868] Data calculation: Trend data collection and analysis

[0869] Output: Analyzed trend data

[0870] Step 6:

[0871] Generate a new proposal

[0872] The server combines the technical data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new product and design proposals.

[0873] Input: Technical data, trend data

[0874] Data calculation: Proposal generation process

[0875] Output: New proposal

[0876] Step 7:

[0877] Feedback to smart glasses

[0878] The server displays the generated new suggestions to the craftsman in real time via smart glasses, and the craftsman works on the suggestions and provides feedback.

[0879] Input: New Proposal

[0880] Data calculation: Real-time display on smart glasses

[0881] Output: Craftsmanship and feedback

[0882] Step 8:

[0883] Collect feedback and store it in the cloud

[0884] Feedback collected from smart glasses is stored in cloud storage.

[0885] Input: Feedback from craftsmen

[0886] Data Computing: Feedback Collection and Cloud Storage Processing

[0887] Output: Feedback data on the cloud

[0888] Step 9:

[0889] System Improvements

[0890] The server uses the collected feedback to improve its generative and data analysis AI models, which will result in more accurate suggestions for the next time.

[0891] Input: Feedback data on the cloud

[0892] Data calculation: Model refinement process

[0893] Output: Improved generative AI and data analysis AI models

[0894] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0895] System Overview

[0896] This invention is a system for preserving and passing on artisanal techniques, and includes a camera and sensor means, generation AI, data analysis AI, database, feedback loop, and an emotion engine that recognizes the user's emotions. This allows for the artisan's emotional feedback on proposed new designs and techniques to be incorporated, resulting in more accurate suggestions and system improvements.

[0897] Learning and preserving craftsmanship

[0898] Technical Data Collection

[0899] Subject: Server

[0900] The server installs cameras and sensor devices in the space where the craftsmen work. These devices monitor and record the craftsmen's movements and working environment in real time, and the collected data is stored in cloud storage.

[0901] Specific examples

[0902] As a craftsman creates a tea bowl, the camera captures the craftsman's hand movements and the tools he uses in detail. The sensor device collects data such as the shape and temperature of the bowl. This allows even the finest techniques to be accurately recorded as digital data.

[0903] Generative AI learning

[0904] Technical Data Learning

[0905] Subject: Server

[0906] The server inputs the pre-processed data into a generative AI model, which learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[0907] Data analysis and new proposals

[0908] Trend data collection and analysis

[0909] Subject: Data Analysis AI

[0910] Data analysis AI collects the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc. It analyzes this data and identifies current market trends.

[0911] Specific examples

[0912] Data analysis AI analyzes popular online search terms and best-selling products to identify the most popular designs and color combinations, providing the raw materials for creating new proposals that are in line with the times.

[0913] Emotion engine combination and feedback

[0914] Generating and Evaluating New Proposals

[0915] Subject: Server

[0916] The server presents the new proposals generated by the generation AI and data analysis AI to the craftsman. The emotion engine analyzes the craftsman's emotions in real time after receiving the proposal and includes the analysis data in feedback. This allows the craftsman's emotional reaction to the proposal to be reflected in the system and used in the next proposal.

[0917] Gathering feedback and improving the system

[0918] Subject: Server

[0919] The server organizes the feedback data collected from the craftsmen and stores it in a database. Based on the collected feedback, the generation AI and data analysis AI models are improved to improve the accuracy of the next proposal.

[0920] Specific examples

[0921] A craftsman creates a prototype of a newly proposed tea bowl design and reports the production process and final evaluation to the server. The emotion engine analyzes the craftsman's emotions, such as happiness, surprise, or confusion, in real time when they see the proposal, and includes this data in feedback. The server uses this feedback to adjust the algorithms of the generation AI and data analysis AI, and reflects the results in the next proposal.

[0922] Emotion Engine Details

[0923] Emotion data collection and analysis

[0924] Subject: Server

[0925] The server collects the craftsman's facial expressions and tone of voice through devices such as cameras and microphones, and the emotion engine analyzes the data to recognize emotions, making it easier to collect not only technical feedback but also emotional feedback.

[0926] Specific examples

[0927] While the craftsman is reviewing the proposal, a camera captures his / her facial expressions and a microphone records his / her tone of voice. The emotion engine analyzes this data to identify the craftsman's emotions and transmits the data to a server, providing a comprehensive view of the craftsman's technical and emotional responses.

[0928] conclusion

[0929] The system of this invention can learn and store traditional artisan techniques as digital data, generate new proposals that match modern trends, and comprehensively incorporate the user's emotional feedback. This will enable the inheritance and evolution of artisan techniques, as well as advanced proposals that match the user's preferences and emotions.

[0930] The processing flow will be explained below.

[0931] Learning and preserving craftsmanship

[0932] Technical Data Collection

[0933] Subject: Server

[0934] Step 1:

[0935] The server installs cameras and sensor devices in the craftsman's workshop, positioned to optimally record the craftsman's movements.

[0936] Step 2:

[0937] The server collects video and sensor data from cameras and sensor devices in real time and stores it in cloud storage.

[0938] Step 3:

[0939] The server removes noise from the collected video data and divides it into frames. The sensor data is normalized and organized as time-series data.

[0940] Specific examples

[0941] Step 1:

[0942] The server places a camera on the desk where the craftsman is working and adjusts it to the optimal angle.

[0943] Step 2:

[0944] The server begins to collect video footage of the craftsman shaping the tea bowl and shape data obtained by the sensor in real time.

[0945] Step 3:

[0946] The server denoises the collected video data, divides it into frames, and normalizes the sensor data to create time-series data.

[0947] Generative AI learning

[0948] Technical Data Learning

[0949] Subject: Server

[0950] Step 1:

[0951] The server inputs pre-processed technical data into the generative AI model.

[0952] Step 2:

[0953] The server begins learning the craftsmanship of generative AI and trains iteratively.

[0954] Step 3:

[0955] The server stores the results learned by the generative AI in a database and manages them in a reusable format.

[0956] Specific examples

[0957] Step 1:

[0958] The server inputs preprocessed video data of the craftsman shaping the tea bowl into the generation AI.

[0959] Step 2:

[0960] The server uses generative AI to repeatedly train itself on data to learn things like hand movements and the shape of the vessel.

[0961] Step 3:

[0962] The server stores the learning results in a database and adds metadata (learning date and time, data size, etc.).

[0963] Data analysis and new proposals

[0964] Trend data collection and analysis

[0965] Subject: Data Analysis AI

[0966] Step 1:

[0967] Data analysis AI collects trend data from social media, fashion sites, market reports, etc.

[0968] Step 2:

[0969] Data analysis AI analyzes collected trend data, identifies major themes and styles, and performs clustering.

[0970] Step 3:

[0971] The data analysis AI generates new proposals based on the technical data learned by the generation AI and the results of trend analysis.

[0972] Specific examples

[0973] Step 1:

[0974] Data analysis AI collects the latest tea utensil design and color trends from the internet.

[0975] Step 2:

[0976] Data analysis AI analyzes collected trend data to identify popular designs and color combinations.

[0977] Step 3:

[0978] The data analysis AI combines the technical data of the craftsmen learned by the generation AI to propose new tea bowl designs.

[0979] Emotion engine combination and feedback

[0980] Generating and Evaluating New Proposals

[0981] Subject: Server

[0982] Step 1:

[0983] The server presents new proposals to the craftsman and simultaneously collects the craftsman's emotional data through cameras and microphones.

[0984] Step 2:

[0985] The emotion engine analyzes collected facial expression data and voice tone to recognize the emotions of the craftsman.

[0986] Step 3:

[0987] The server records the craftsman's emotional response to the proposal as analytical data and stores this data as feedback.

[0988] Specific examples

[0989] Step 1:

[0990] The server shows the new tea bowl design to the craftsman and collects the craftsman's emotional responses (facial expressions, tone of voice) in real time using a camera and microphone.

[0991] Step 2:

[0992] The emotion engine analyzes the craftsman's smile, exclamation of surprise, etc. to identify his / her emotions.

[0993] Step 3:

[0994] The server stores the analyzed emotion data as feedback data for the proposal and uses it to generate the next proposal.

[0995] Gathering feedback and improving the system

[0996] Subject: Server

[0997] Step 1:

[0998] The server organizes the collected feedback data and stores it in a database.

[0999] Step 2:

[1000] The server improves the generative AI and data analysis AI models based on the collected feedback.

[1001] Step 3:

[1002] The server uses the improved model to generate the next proposal, improving the accuracy of the system.

[1003] Specific examples

[1004] Step 1:

[1005] The server organizes the feedback data and emotion data from the craftsmen and stores them in a database.

[1006] Step 2:

[1007] The server adjusts the algorithms of the generative AI and data analysis AI based on the collected feedback and improves the model.

[1008] Step 3:

[1009] The server will propose the next bowl design based on the improved model, improving its accuracy.

[1010] Example 2

[1011] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1012] Preserving and passing on traditional craftsmanship is becoming increasingly difficult as technology becomes more advanced. Furthermore, adapting to modern market trends requires new proposals that take into account not only the craftsman's skills but also the latest market trends. Furthermore, to improve the accuracy of proposals, it is necessary to incorporate not only the craftsman's technical feedback but also their emotional reactions. However, it was difficult to achieve these comprehensively with conventional systems.

[1013] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a camera and sensor device means for collecting technical data of craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generative AI model for learning, a means for saving the learning results of the generative AI model in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generative AI model and the trend data analyzed by the data analysis AI means, a means for feeding back the generated proposals to the craftsmen and analyzing the craftsmen's emotions in real time using an emotion engine, and a means for improving the generative AI model and the model of the data analysis AI means based on the collected feedback. This makes it possible to realize an advanced feedback system that precisely preserves the craftsmen's skills, generates new technical proposals that respond to modern trends, and further reflects the craftsmen's emotional reactions.

[1014] A "camera" is a device that records the craftsman's actions and working environment as video data.

[1015] A "sensor device" is a device that measures physical information (such as temperature and shape) in a craftsman's working environment and collects it as data.

[1016] "Preprocessing" is the process of removing noise from collected technical data and converting it into an analyzable form.

[1017] A "generative AI model" is an artificial intelligence model that learns preprocessed technical data and analyzes and stores the movement patterns and techniques of craftsmen.

[1018] A "database" is a data storage system for systematically storing the learning results of a generative AI model.

[1019] "Data Analysis AI Method" is an artificial intelligence system that collects and analyzes trend data on the Internet to identify current market trends.

[1020] The "emotion engine" is a system that analyzes the facial expressions and tone of voice of craftsmen and recognizes their emotions in real time.

[1021] "Feedback" is the process of collecting artisans' technical and emotional reactions to new proposals.

[1022] "Model refinement" is the process of adjusting the algorithms of generative AI models and data analysis AI methods based on collected feedback data.

[1023] "New proposals" are proposals for new technologies and designs that are generated by combining data analyzed by generative AI models and data analysis AI means.

[1024] MODE FOR CARRYING OUT THE INVENTION

[1025] System Overview

[1026] The system aims to preserve and pass on artisanal techniques and is a comprehensive system that includes cameras and sensor devices, generative AI models, data analysis AI methods, databases, and an emotion engine. This system enables more accurate proposals and system improvements, including the emotional feedback of artisans on new designs and technical proposals.

[1027] Hardware and software used

[1028] Hardware

[1029] Camera: Used to record the craftsman's movements and working environment as video data.

[1030] Sensor device: Used to measure and collect data such as changes in shape and temperature during work.

[1031] Cloud storage: Used to store collected data.

[1032] software

[1033] Generative AI model: Learns from artisan technical data and uses it to generate new suggestions.

[1034] Data analysis AI means: Used to analyze trend data on the Internet.

[1035] Emotion engine: Used to analyze the emotions of craftsmen in real time.

[1036] Database: Used to store the learning results and feedback data of the generative AI model.

[1037] System processing flow

[1038] 1. Data collection: The server installs cameras and sensor devices in the space where the craftsman works, which monitors and records the craftsman's movements and working environment in real time. This information is stored in cloud storage.

[1039] Example: A craftsman creating a tea bowl is filmed with a camera, and a sensor device records the shape and temperature of the bowl.

[1040] 2. Data Preprocessing: The server cleanses the collected data and converts it into a format that the generative AI model can understand, removing noise and making the data analyzable.

[1041] Example: Cutting unnecessary scenes from captured footage and removing outliers in temperature data.

[1042] 3. Learning by generative AI: The server inputs the preprocessed data into a generative AI model, which learns the movement patterns and techniques of the craftsman. The learning results are stored in a database.

[1043] Example: AI learns how a craftsman moves his hands and uses tools.

[1044] 4. Trend data collection and analysis: Data analysis AI tools collect and analyze the latest trend data from the Internet, thereby understanding current market trends.

[1045] Example: Identify popular designs and color combinations based on data collected from social media and fashion sites.

[1046] 5. Generate new proposals: The server combines the data from the generative AI model and the data analysis AI method to generate new proposals, which are then fed back to the craftsman.

[1047] Example: The newly generated tea bowl design is displayed on the craftsman's device.

[1048] 6. Emotion engine analysis: Analyze the emotions of the craftsmen who receive the proposal in real time and collect their feedback. Analyze facial expressions and tone of voice through cameras and microphones.

[1049] Example: The emotion engine analyzes the happiness and surprise of a craftsman when he sees a new design.

[1050] 7. Feedback collection and system improvement: The server will improve the generative AI model and data analysis AI means based on the collected feedback data and reflect this in the next proposal.

[1051] Example: A craftsman prototypes a new tea bowl design and reports his or her impressions to the server. This data is used to retrain the AI ​​model.

[1052] Prompt Sentence Examples

[1053] "Describe a system for analyzing video data of the traditional tea bowl making process and generating new design proposals that take into account current trends. Also, explain how you incorporate the artisan's emotional response to the proposals."

[1054] This system can learn and store traditional artisan techniques as digital data, generate new proposals that match modern trends, and comprehensively incorporate the user's emotional feedback. This allows for the preservation and evolution of artisan techniques, and enables advanced proposals that match the user's preferences and emotions.

[1055] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1056] Step 1:

[1057] Installation of cameras and sensor devices

[1058] Subject: Server

[1059] Description:

[1060] The server installs cameras and sensor devices in the space where the craftsman works, setting the cameras at the appropriate positions and angles and placing the sensors at the appropriate work locations.

[1061] input:

[1062] Camera and sensor devices.

[1063] output:

[1064] You are now ready to record the craftsman's movements and working environment.

[1065] Specific behavior:

[1066] The server remotely adjusts the focus and angle of the camera via the network, and places sensor devices around the work object.

[1067] Step 2:

[1068] Data collection

[1069] Subject: Server

[1070] Description:

[1071] The server collects real-time data on the worker's movements and working environment through cameras and sensor devices, and this data is stored in cloud storage.

[1072] input:

[1073] Craftsman behavior and working environment.

[1074] output:

[1075] Video data and environmental data are stored in cloud storage.

[1076] Specific behavior:

[1077] As the craftsman shapes the tea bowl, the camera captures his or her hand movements, and the sensor device measures the shape and temperature and sends the data to a server.

[1078] Step 3:

[1079] Data Preprocessing

[1080] Subject: Server

[1081] Description:

[1082] The server cleanses the collected data and converts it into an analyzable format, which involves removing noise and converting the data format.

[1083] input:

[1084] Collected video and environmental data.

[1085] output:

[1086] Cleansed, parseable data.

[1087] Specific behavior:

[1088] The server denoises the collected images, cuts out unnecessary parts, removes outliers from the sensor data, and converts them into standard formats (e.g., CSV or PNG).

[1089] Step 4:

[1090] Generative AI learning

[1091] Subject: Server

[1092] Description:

[1093] The server inputs the preprocessed data into a generative AI model to learn the craftsman's technical patterns, and the learning results are stored in a database.

[1094] input:

[1095] Preprocessed data.

[1096] output:

[1097] Technical data learned by generative AI models.

[1098] Specific behavior:

[1099] The server inputs preprocessed video and sensor data into a generative AI model, which then learns the patterns of the craftsman's hand movements and techniques. The learning results are stored in a database.

[1100] Step 5:

[1101] Trend data collection and analysis

[1102] Subject: Data Analysis AI

[1103] Description:

[1104] Data analysis AI collects the latest trend data from the internet and analyzes it, and the analysis results are used to generate new proposals.

[1105] input:

[1106] Trending data on the internet.

[1107] output:

[1108] Analyzed trend data.

[1109] Specific behavior:

[1110] Data analysis AI searches the web using specific keywords (for example, "handmade tea bowl trends") and analyzes the collected data to identify popular designs and color combinations.

[1111] Step 6:

[1112] Generate a new proposal

[1113] Subject: Server

[1114] Description:

[1115] The server combines the generative AI model with the data generated by the data analysis AI to generate new suggestions, which are then fed back to the craftsman.

[1116] input:

[1117] Generative AI model learning results and analyzed trend data.

[1118] output:

[1119] New technology proposal.

[1120] Specific behavior:

[1121] The server combines the technical data obtained from the generation AI model with the trend information obtained from the data analysis AI to generate a new tea bowl design and send it to the craftsman's device.

[1122] Step 7:

[1123] Emotion Engine Analysis

[1124] Subject: Server

[1125] Description:

[1126] The server uses an emotion engine to analyze the craftsman's emotions in real time, identifying the craftsman's emotions based on data obtained through cameras and microphones.

[1127] input:

[1128] Real-time data from cameras and microphones.

[1129] output:

[1130] Analyzed emotion data.

[1131] Specific behavior:

[1132] As the craftsman reviews the design of a new tea bowl, a camera captures his facial expressions and a microphone records his tone of voice. The server uses an emotion engine to analyze this data and identify the craftsman's emotions.

[1133] Step 8:

[1134] Gathering feedback and improving the system

[1135] Subject: Server

[1136] Description:

[1137] The server uses the collected feedback to improve the generative AI model and data analysis AI, which will improve the accuracy of the next proposal.

[1138] input:

[1139] Technical and emotional feedback data from artisans.

[1140] output:

[1141] Improved generative AI models and data analysis AI.

[1142] Specific behavior:

[1143] The craftsman prototypes the new tea bowl design and reports his / her opinions and impressions to the server, which then retrains the generative AI model and data analysis AI method based on the collected feedback data and reflects it in the next proposal.

[1144] (Application example 2)

[1145] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1146] Conventional autonomous vehicles have been unable to fully utilize the driver's emotional state and real-time environmental information to improve driving comfort and safety, and lack the means to effectively collect and analyze this information and make improvements based on system feedback.

[1147] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1148] In this invention, the server includes a camera and sensor means for collecting technical data from craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generation AI for learning, a means for storing the learning results of the generation AI in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI, a means for feeding back the generated proposals to craftsmen and collecting their evaluations, a means for improving the models of the generation AI and the data analysis AI based on the collected feedback, a means for optimizing driving patterns and routes to improve the comfort and safety of the other-type vehicle while driving, a means for controlling driving based on the optimized driving patterns and routes, an emotion engine for analyzing the emotional state of the driver, and a means for collecting feedback and improving the system based on the emotional state analyzed by the emotion engine. This makes it possible to effectively utilize the real-time environment and the driver's emotional state while driving, thereby improving comfort and safety.

[1149] "Camera and sensor means" refers to devices that photograph and measure the driver's condition and driving environment in real time.

[1150] "Means of preprocessing and converting into an analyzable format" refers to the process of converting collected data into a format that can be analyzed by AI.

[1151] "Means of inputting data into a generative AI and having it learn" refers to the process of inputting preprocessed data into a generative AI model and having it learn.

[1152] "Means for saving in a database" refers to a database system for recording and saving learning results.

[1153] "Data analysis AI means for collecting and analyzing trend data" is an artificial intelligence system for collecting and analyzing trend information on the Internet.

[1154] The "means of generating new proposals" is the process of combining the data learned by the generation AI with the trend data analyzed by the data analysis AI to create new proposals.

[1155] "Feedback and evaluation collection measures" are the processes of presenting new proposals to drivers and collecting their reactions and evaluations.

[1156] "Means to improve generative and analytical AI models" refers to the process of improving AI models based on collected feedback to improve the accuracy of future recommendations.

[1157] "Means for optimizing driving patterns and routes" refers to the process of calculating optimal driving patterns and routes to improve the comfort and safety of the vehicle while driving.

[1158] "Means for controlling driving" refers to a system that controls the vehicle based on optimized driving patterns and routes.

[1159] The "emotion engine for analyzing the driver's emotional state" is a system that uses cameras and microphones to analyze the driver's facial expressions and tone of voice to recognize their emotions.

[1160] "Means for collecting feedback and improving the system" refers to the process of collecting feedback based on the driver's emotional state and improving the overall system based on that feedback.

[1161] This invention provides a system that collects, analyzes, and feeds back various data to improve the comfort and safety of automobiles while driving. Specific methods and processes for realizing this system are described below.

[1162] System Configuration

[1163] The system consists of the following main components:

[1164] 1. Camera and sensor means:

[1165] This is a device that captures and measures the driver's condition and driving environment in real time. Specifically, it includes cameras and microphones installed inside the vehicle and various sensors that monitor the external environment.

[1166] 2. Data preprocessing methods:

[1167] This software preprocesses the collected data and converts it into an analyzable format, for example by dividing the collected video data into an appropriate number of frames, removing noise, and normalizing it.

[1168] 3. Generative AI Model:

[1169] This is an artificial intelligence model that inputs the preprocessed data and performs learning, thereby learning data related to the driver's behavioral patterns and driving environment.

[1170] 4. Database:

[1171] This is a database system for recording and storing the learning results of the generation AI. This system stores environmental data during driving, the driver's emotional state, traffic information, etc.

[1172] 5. Data analysis AI methods:

[1173] This is an AI system for collecting and analyzing trend data, such as traffic information, weather data, and social media trend information from the Internet.

[1174] 6. New proposal generation methods:

[1175] This is the process of combining the data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new suggestions, which will then suggest optimal driving patterns and routes for the driver.

[1176] 7. Feedback and evaluation collection methods:

[1177] New suggestions are presented to drivers and their reactions and evaluations are collected, for example, by presenting the suggestions via an in-car display or smartphone.

[1178] 8. Model refinement methods:

[1179] This is the process of improving the generative AI and data analysis AI models based on the collected feedback, which will improve the accuracy of the next proposal.

[1180] 9. Driving pattern and route optimization measures:

[1181] It is an AI system that calculates optimal driving patterns and routes to improve vehicle comfort and safety while driving.

[1182] 10. Travel control means:

[1183] This is a system for controlling vehicles based on optimized driving patterns and routes. Autonomous driving systems and actuators are used for actual vehicle control.

[1184] 11. Emotion Engine:

[1185] This system uses cameras and microphones to analyze the driver's facial expressions and tone of voice to recognize their emotions, and is used to grasp the driver's fatigue and state of tension in real time.

[1186] 12. Feedback collection and system improvement methods:

[1187] It is a process of collecting feedback based on the driver's emotional state and using that to improve the overall system.

[1188] Specific examples

[1189] For example, when a driver is driving on the highway, the emotion engine analyzes the driver's facial expressions to detect signs of fatigue. This data is analyzed by a generative AI model and used to optimize a safe driving route. The optimal route is calculated and displayed on the vehicle's display. Driver feedback is also collected and reflected in future recommendations.

[1190] Prompt Sentence Examples

[1191] Below are some example prompts that can be input to the generative AI model in this system:

[1192] "What facial expressions do drivers have while driving that make you feel safer? And vice versa?"

[1193] The above configuration makes it possible to effectively improve comfort and safety during driving.

[1194] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1195] Step 1:

[1196] The server monitors the driver's condition and driving environment in real time using cameras and sensors installed in the vehicle.

[1197] Input: Video data from cameras and sensors and environmental data

[1198] Data processing: Video data is divided into frames, and noise is removed and normalized.

[1199] Output: Preprocessed data (video frames and environmental data)

[1200] Step 2:

[1201] The server inputs the preprocessed data into a generative AI model, which learns about the driver's behavioral patterns and driving environment.

[1202] Input: Preprocessed data (video frames and environmental data)

[1203] Data Computation: Learning with Generative AI Models

[1204] Output: Learning result data (driving patterns and environmental recognition data)

[1205] Step 3:

[1206] The server stores the learning result data in a database.

[1207] Input: Learning result data obtained from the generative AI model

[1208] Data processing: Converting data into a format that can be saved in a database

[1209] Output: Learning result data stored in a database

[1210] Step 4:

[1211] The server collects relevant information from the internet using data analysis AI means to collect and analyze trend data.

[1212] Input: Internet traffic information, weather data, social media trend information

[1213] Data calculation: Analyze collected data and extract important trend information

[1214] Output: Analyzed trend data

[1215] Step 5:

[1216] The server combines the technical data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new proposals.

[1217] Input: Training result data and trend data

[1218] Data arithmetic: Combining data to generate new suggestions

[1219] Output: New proposed data (optimal driving patterns and routes)

[1220] Step 6:

[1221] The terminal provides feedback on new proposals to the driver and collects their evaluations.

[1222] Input: New proposal data

[1223] Specific operation: Displaying suggestions on the in-car display or smartphone

[1224] Output: Driver feedback data

[1225] Step 7:

[1226] The server refines its generative AI and data analysis AI models based on the collected feedback.

[1227] Input: Driver feedback data

[1228] Data calculation: Analyze feedback data and adjust AI models

[1229] Output: Improved generative AI and data analysis AI models

[1230] Step 8:

[1231] The server uses the improved AI model to optimize the vehicle's driving patterns and routes while in operation.

[1232] Input: Improved generative AI and data analysis AI models

[1233] Data calculation: Calculates optimal driving patterns and routes

[1234] Output: Optimized driving patterns and route data

[1235] Step 9:

[1236] The terminal controls the vehicle based on the optimized driving pattern and route.

[1237] Input: Optimized driving pattern and route data

[1238] Specific operation: Controlling the driving route using an autonomous driving system and actuators

[1239] Output: Control data for the vehicle during operation

[1240] Step 10:

[1241] The server collects and analyzes data from cameras and microphones using an emotion engine to analyze the driver's emotional state.

[1242] Input: Camera video and audio data

[1243] Data processing: Emotional state analysis (facial expression recognition and voice tone analysis)

[1244] Output: Driver's emotional state data

[1245] Step 11:

[1246] The server collects feedback based on the emotional state analyzed by the emotion engine and improves the system.

[1247] Input: Driver's emotional state data

[1248] Data calculation: Analyze emotional state data and improve the entire system

[1249] Output: Improved system feedback data

[1250] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1251] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1252] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1253] [Third embodiment]

[1254] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1255] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1256] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1257] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1258] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1259] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1260] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1261] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1262] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1263] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1264] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1265] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1266] System Overview

[1267] The system of the present invention is composed of a camera and sensor means, generation AI, data analysis AI, database, and feedback loop, which allows for the collection, storage, and analysis of craftsmanship data, the generation of new proposals, and the transfer of skills.

[1268] Learning and preserving craftsmanship

[1269] Technical Data Collection

[1270] Subject: Server

[1271] The server installs cameras and sensor devices in the space where the craftsmen work. These devices monitor and record the craftsmen's movements and work environment in real time. The server saves the video and audio data collected from the cameras and sensor devices in cloud storage.

[1272] Specific examples

[1273] As a craftsman creates a tea bowl, the camera captures the craftsman's hand movements and the tools he uses in detail. The sensor device collects data such as the shape and temperature of the bowl. This allows even the finest techniques to be accurately recorded as digital data.

[1274] Generative AI learning

[1275] Technical Data Learning

[1276] Subject: Server

[1277] The server inputs the pre-processed data into a generative AI model, which learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[1278] Data analysis and new proposals

[1279] Trend data collection and analysis

[1280] Subject: Data Analysis AI

[1281] Data analysis AI collects the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc. It analyzes this data and identifies current market trends.

[1282] Specific examples

[1283] Data analysis AI analyzes popular online search terms and best-selling products to identify the most popular designs and color combinations, providing the raw materials for creating new proposals that are in line with the times.

[1284] Generate new suggestions and feedback

[1285] Generate a new proposal

[1286] Subject: Data Analysis AI

[1287] The data analysis AI combines the technical data learned by the generation AI with the analyzed trend data to generate new product and design proposals. These proposals are fed back to the craftsmen and used in their actual work.

[1288] Gathering feedback and improving the system

[1289] Subject: Server

[1290] The server presents the generated proposals to the craftsmen and collects their evaluations and opinions. Based on this feedback, the model of the entire system (generative AI and data analysis AI) is improved, thereby improving the quality of the generated proposals.

[1291] Specific examples

[1292] Craftsmen will prototype new tea bowl designs and report the production process and final evaluation to the server. The server will use this feedback to adjust the algorithms of the generative AI and data analysis AI, and reflect this in the next proposal.

[1293] conclusion

[1294] The system of this invention makes it possible to learn and preserve traditional artisan techniques as digital data and propose new products that match modern trends, thereby realizing the inheritance and evolution of artisan techniques.

[1295] The processing flow will be explained below.

[1296] Learning and preserving craftsmanship

[1297] Technical Data Collection

[1298] Subject: Server

[1299] 1. Step 1: Camera and Sensor Settings

[1300] The server places cameras and sensor devices in the craftsman's workshop and performs initial settings to enable accurate detection.

[1301] 2. Step 2: Start collecting data

[1302] The server collects data from cameras and sensor devices in real time and transfers it to cloud storage.

[1303] 3. Step 3: Preprocessing

[1304] The server removes noise from the collected video data, splits the video into frames, and normalizes and timestamps the sensor data.

[1305] Specific examples

[1306] 1. Step 1:

[1307] The server places the camera on the desk where the craftsman is working and adjusts it to the appropriate angle.

[1308] 2. Step 2:

[1309] The server begins to collect video footage of the craftsman shaping the tea bowl and shape data obtained by the sensor in real time.

[1310] 3. Step 3:

[1311] The server removes noise from the collected video data, splits it into frames, normalizes the sensor data, and organizes it as time-series data.

[1312] Generative AI learning

[1313] Technical Data Learning

[1314] Subject: Server

[1315] 1. Step 1: Data Entry

[1316] The server inputs the pre-processed technical data into the generative AI model.

[1317] 2. Step 2: Model training

[1318] The server begins learning the technical patterns using generative AI and trains iteratively.

[1319] 3. Step 3: Save the learning results

[1320] The server stores the results of the technical patterns learned by the generative AI in a database and manages them in a reusable form.

[1321] Specific examples

[1322] 1. Step 1:

[1323] The server inputs pre-processed video data of the craftsman shaping the tea bowl into the generation AI.

[1324] 2. Step 2:

[1325] The server repeatedly trains the generative AI with data to learn things like hand movements and the shape of the vessel.

[1326] 3. Step 3:

[1327] The server stores the learning results in a database and adds metadata (learning date and time, data size, etc.).

[1328] Data analysis and new proposals

[1329] Trend data collection and analysis

[1330] Subject: Data Analysis AI

[1331] 1. Step 1: Trend data collection

[1332] Data analysis AI collects trend data from social media, fashion sites, market reports, etc.

[1333] 2. Step 2: Trend analysis

[1334] Data analysis AI analyzes collected trend data, identifies major themes and styles, and performs clustering.

[1335] 3. Step 3: Generate new proposals

[1336] The data analysis AI generates new proposals based on the technical data learned by the generation AI and the results of trend analysis.

[1337] Specific examples

[1338] 1. Step 1:

[1339] Data analysis AI collects trend data on popular designs and colors on the Internet.

[1340] 2. Step 2:

[1341] Data analysis AI analyzes collected trend data and identifies the most popular designs and color combinations.

[1342] 3. Step 3:

[1343] The data analysis AI combines the technical data of the craftsmen learned by the generation AI to propose new tea bowl designs.

[1344] Generate new suggestions and feedback

[1345] Generating and Evaluating New Proposals

[1346] Subject: Server

[1347] 1. Step 1: Feedback on the proposal

[1348] The server presents the generated new proposals to the craftsmen and collects their evaluations and opinions.

[1349] 2. Step 2: Save the evaluation data

[1350] The server organizes the feedback data collected from the craftsmen and stores it in a database.

[1351] 3. Step 3: System Improvement

[1352] The server uses the collected feedback to improve the generative AI and data analysis AI models and reflect this in its next proposal.

[1353] Specific examples

[1354] 1. Step 1:

[1355] The server shows the new bowl design to the craftsman and encourages him to give feedback.

[1356] 2. Step 2:

[1357] The server organizes the craftsmen's feedback and stores it in a database.

[1358] 3. Step 3:

[1359] The server adjusts the algorithms of the generation AI and data analysis AI based on the collected feedback and reflects it in the next proposal.

[1360] Example 1

[1361] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1362] The inheritance of artisanal skills is extremely important in today's world, but because traditional techniques rely on oral transmission and direct instruction, they are difficult to pass on efficiently. It's also difficult to propose new ideas that are in line with market trends, putting many traditional techniques at risk of becoming outdated. Furthermore, when introducing new technologies, there is a lack of a system for systematically collecting feedback and improving models. To solve these problems, a system is needed that digitizes technology, links with trends, and utilizes feedback.

[1363] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1364] In this invention, the server includes a video device and a sensor device for collecting data on the work of engineers, a device for preprocessing the collected work data and converting it into an analyzable format, and a device for inputting the converted data into a generative model for learning. This enables the efficient inheritance of traditional techniques and the generation of new proposals in line with modern trends.

[1365] An "engineer" is someone who has specific skills or abilities and uses those skills to create products or services.

[1366] "Work data" refers to data that includes information on the actions, procedures, and tools used by engineers when they perform work.

[1367] "Video equipment" refers to equipment such as cameras that record the actions and work processes of technicians as visual data.

[1368] A "sensor device" is a device for acquiring environmental data and physical parameters such as temperature, pressure, and humidity in real time.

[1369] "Preprocessing" is the process of converting collected raw data into an analyzable format, removing noise, and converting the data.

[1370] A "generative model" is an artificial intelligence model that learns the actions and techniques of engineers based on collected data and generates new proposals.

[1371] "Data storage" refers to a storage device or system for permanently storing learned data and analysis results.

[1372] "Trend data" is data that shows market and consumer trends and is collected based on information on the Internet.

[1373] A "data analysis model" is an artificial intelligence model that analyzes collected trend data and extracts important patterns and market trends.

[1374] A "proposal" is a new product design or technical improvement plan generated based on the generative model and data analysis model.

[1375] "Evaluation" refers to information including feedback and opinions given by engineers regarding the proposal, as well as actual work results.

[1376] "Algorithm" refers to the computational methods and procedures used by generative models and data analysis models to generate new proposals.

[1377] System Overview

[1378] This invention is a system for digitizing and passing on engineers' skills, and is composed of a video device, a sensor device, a generative model, a data analysis model, data storage, and an evaluation feedback device. This system collects and analyzes engineers' work data, generates new proposals, and realizes technological evolution.

[1379] Hardware and Software Configuration

[1380] The system uses the following hardware and software:

[1381] Video equipment: High-resolution camera

[1382] Sensor devices: temperature sensors, pressure sensors, humidity sensors

[1383] Generative models: Deep learning models (e.g., TensorFlow, PyTorch)

[1384] Data analysis models: Natural language processing and data mining tools (e.g., Scikit-learn, NLTK)

[1385] Data storage: Cloud storage (e.g., Amazon S3, Google Cloud Storage)

[1386] Evaluation Feedback Instrument: A dedicated feedback collection application

[1387] Specific actions

[1388] The system works as follows: First, video and sensor devices collect data on the technician's work in real time. The video devices capture high-resolution images of the technician's hand movements and the tools they use, while the sensor devices collect environmental data such as temperature, humidity, and pressure. This data is sent to a server and stored in cloud storage.

[1389] The server then preprocesses the collected data, which includes noise removal, data shaping, and format conversion. The preprocessed data is then input into a generative model, which learns the technician's behavior patterns and techniques. The data learned by the generative model is then stored in data storage.

[1390] In parallel, the data analysis model collects and analyzes the latest trend data from the Internet, for example, from social media, fashion sites, and market reports. The analyzed trend data is then input into the generative model and used to generate new proposals.

[1391] Finally, the generated proposals are presented to engineers, whose evaluations are collected through a feedback collection application. This feedback is used to refine the generative model and data analysis model algorithms, thereby improving the accuracy of future proposals and technical improvements.

[1392] Specific examples

[1393] As a potter creates a tea bowl, a video device captures detailed footage of the potter's hand movements and the tools he uses, while a sensor device collects the temperature and humidity of the work surface. The preprocessed data is fed into a generative model, which learns how the potter moves his hands and uses the tools. At the same time, a data analysis model collects and analyzes the latest trends, and based on this information, new tea bowl design proposals are generated.

[1394] The craftsman is presented with a prompt: "Please prototype a newly proposed tea bowl design and report the production process and final evaluation to the server." Based on this feedback, the algorithms of the generative model and data analysis model are improved, and the accuracy of the next proposal is improved.

[1395] Prompt Sentence Examples

[1396] Here are some example prompts to input to the generative AI model:

[1397] "We provide a dataset to learn how artisans use their hands and tools to create tea bowls. You can then propose new designs for tea bowls based on this data."

[1398] This concludes the "Mode for carrying out the invention." This system digitizes the skills of engineers and generates new proposals that are in line with trends, thereby realizing the inheritance and evolution of technology.

[1399] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1400] Step 1:

[1401] The server collects data in real time from video and sensor devices installed in the technician's workspace. The video devices capture high-resolution images of the technician's hand movements and the tools they use, while the sensor devices collect environmental data such as temperature, humidity, and pressure. The input data consists of video (video stream) and sensor information (numerical data), which the server stores in cloud storage. Specifically, the camera captures the movement, and the various sensors read the values ​​and send them to the server.

[1402] Step 2:

[1403] The server preprocesses the data stored in the cloud storage. Preprocessing includes noise removal, data shaping, and format conversion. For example, it removes unwanted noise from video data and synchronizes sensor data on the time axis. The input data is raw data, and the output data is preprocessed data. Specifically, the server applies a noise filtering algorithm to unify the different data formats.

[1404] Step 3:

[1405] The server inputs the preprocessed data into a generative AI model. The generative AI model uses this data to learn the technician's movements and work patterns. The input data is preprocessed technical data, and the output data is the learning results (a numerical model of the technical data). Specifically, the server runs the generative AI model (e.g., a deep learning network) and proceeds with learning based on the dataset.

[1406] Step 4:

[1407] Data analysis AI collects trend data from the internet. It automatically collects and analyzes the latest trend information from sources such as social media, fashion sites, and market reports. The input data is text and image data from the web, and the output data is the analysis results (trend information). Specifically, data analysis AI performs web scraping and analyzes the collected data using natural language processing (NLP) algorithms.

[1408] Step 5:

[1409] Data analysis AI combines the technical data learned by the generative AI model with collected trend data to generate new proposals. The input data is the learned technical data and analyzed trend data, and the output data is new proposals (product designs or technical improvement ideas). Specifically, data analysis AI combines these data sets to generate new designs and product concepts.

[1410] Step 6:

[1411] The server presents the generated proposal to the engineer and collects their evaluations and opinions. The input data is the new proposal, and the output data is the feedback from the engineer. The server receives the engineer's evaluations and opinions using a feedback collection application. Specifically, the server sends the generated proposal to the engineer's dedicated terminal, and the engineer enters feedback on it.

[1412] Step 7:

[1413] The server improves the algorithms of the generative AI model and data analysis AI based on the collected feedback. The input data is feedback from engineers, and the output data is the improved algorithm. Specifically, the server analyzes the feedback data and adjusts the parameters of the generative AI and data analysis model, thereby improving the accuracy of the next proposal.

[1414] (Application example 1)

[1415] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1416] Traditionally, the transmission of artisanal skills has relied on oral and practical training, making it difficult to transfer skills and requiring a great deal of time and effort. Furthermore, in order to quickly respond to modern market trends, it is essential to improve techniques and create new proposals, but this is not easy. Furthermore, because artisanal skills are highly advanced, they cannot be immediately understood even after watching a demonstration, and new techniques must be learned through trial and error. However, this process also presents a problem: it is not efficient.

[1417] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1418] In this invention, the server includes a camera and sensor means for collecting technical data from craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generation AI for learning, a means for storing the learning results of the generation AI in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI, a means for feeding back the generated proposals to the craftsmen and collecting their evaluations, a means for improving the models of the generation AI and the data analysis AI based on the collected feedback, a means for displaying the proposals to the craftsmen in real time via smart glasses, and a means for collecting feedback from the smart glasses and storing it in the cloud. This not only enables efficient skill transfer, but also enables the rapid generation of new proposals that reflect modern market trends and allows craftsmen to accept and improve the proposals in real time.

[1419] Definitions of important words

[1420] A "camera" is a device for recording images of objects or people.

[1421] A "sensor" is a device that measures physical motion or environmental data and collects that information in digital form.

[1422] "Preprocessing" is a data processing step to convert collected data into a format suitable for analysis and learning.

[1423] "Generative AI" is an artificial intelligence model that learns artisan techniques and trend data to generate new proposals.

[1424] A "database" is a digital storage device for systematically storing and managing collected technical data and the learning results of generative AI.

[1425] "Data Analysis AI" is an artificial intelligence model that collects and analyzes trend data to identify current market trends.

[1426] "Trend data" refers to data on the latest trends and market trends on the Internet.

[1427] "Feedback" refers to the evaluation and opinions of craftsmen regarding new proposals.

[1428] "Smart glasses" are wearable devices that display images and have functions such as cameras and sensors.

[1429] The "cloud" is a data storage and computing service provided over the internet.

[1430] MODE FOR CARRYING OUT THE INVENTION

[1431] System Overview

[1432] The system of this invention is composed of cameras and sensors, generative AI, data analysis AI, a database, smart glasses, cloud storage, and a feedback loop. This system not only collects and stores the craftsman's technical data, but also enables analysis and generation of new proposals using generative AI, and continuous improvement through feedback.

[1433] Learning and preserving craftsmanship

[1434] Technical Data Collection

[1435] The server installs cameras and sensor devices in the space where the artisan works. These devices monitor and record the artisan's movements and work environment in real time. For example, when an artisan creates pottery, the camera captures detailed images of the artisan's hand movements and the tools he uses, while the sensors collect data such as the shape and temperature of the vessel. The collected video and sensor data are stored in cloud storage.

[1436] Generative AI learning

[1437] Technical Data Learning

[1438] The server inputs the pre-processed technical data into the generative AI model, which then learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[1439] Data analysis and new proposals

[1440] Trend data collection and analysis

[1441] Data analysis AI collects the latest trend data from the internet, for example, automatically retrieving relevant information from social media, fashion sites, market reports, etc., to identify current market trends.

[1442] Generate a new proposal

[1443] The data analysis AI combines the technical data learned by the generation AI with the analyzed trend data to generate new product and design proposals. These proposals are fed back to artisans in real time via smart glasses. For example, a new jewelry design using traditional pearl-making techniques can be generated, and the artisan can then create it.

[1444] Gathering feedback and improving the system

[1445] Collecting feedback

[1446] The smart glasses collect feedback from artisans on new proposals and send the data to the cloud, where the server uses the feedback to improve its generative and data-analytical AI models.

[1447] System Improvements

[1448] The server adjusts the algorithms of the generation AI and data analysis AI based on the evaluations and opinions of the craftsmen and reflects them in the next proposal. This allows the system to continuously evolve and make higher quality proposals.

[1449] Specific example details

[1450] Imagine a traditional pearl craftsman wearing smart glasses. A camera in the glasses records his movements in real time and stores them in the cloud. AI then suggests new designs based on the latest jewelry trends, which the craftsman then prototypes. The entire process works seamlessly, with a feedback loop that allows the system to improve.

[1451] Prompt Sentence Examples

[1452] "Create contemporary jewelry designs using traditional pearling techniques, while also taking into account the latest fashion trends."

[1453] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1454] Program processing flow

[1455] Step 1:

[1456] Technical data collection

[1457] The server uses cameras and sensors installed in the space where the craftsmen work to monitor and record the craftsmen's movements and working environment in real time.

[1458] Input: Video and environmental data from cameras and sensors

[1459] Data processing: Integrate and preprocess video data and sensor data

[1460] Output: Pre-processed technical data

[1461] Step 2:

[1462] Data Preprocessing

[1463] The server converts the collected technical data into an analyzable format: for example, video data is split into frames, and sensor data is converted into appropriate units.

[1464] Input: Preprocessed technical data

[1465] Data calculation: Preprocessing such as frame division, unit conversion, noise removal, etc.

[1466] Output: Data in a parsable format

[1467] Step 3:

[1468] Generative AI learning

[1469] The server inputs technical data in an analyzable format into the generation AI, allowing it to learn the movement patterns and techniques of the craftsmen.

[1470] Input: Data in a parsable format

[1471] Data Computation: Learning Processes with Generative AI Models

[1472] Output: Technical data as a result of learning

[1473] Step 4:

[1474] Saving to a database

[1475] The server stores the learning results of the generative AI in a database, allowing important technical information to be systematically stored.

[1476] Input: Generative AI learning results

[1477] Data calculation: saving to database

[1478] Output: Technical data in the database

[1479] Step 5:

[1480] Trend data collection and analysis

[1481] The server uses data analysis AI to collect and analyze the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc.

[1482] Input: Trending information on the internet

[1483] Data calculation: Trend data collection and analysis

[1484] Output: Analyzed trend data

[1485] Step 6:

[1486] Generate a new proposal

[1487] The server combines the technical data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new product and design proposals.

[1488] Input: Technical data, trend data

[1489] Data calculation: Proposal generation process

[1490] Output: New proposal

[1491] Step 7:

[1492] Feedback to smart glasses

[1493] The server displays the generated new suggestions to the craftsman in real time via smart glasses, and the craftsman works on the suggestions and provides feedback.

[1494] Input: New Proposal

[1495] Data calculation: Real-time display on smart glasses

[1496] Output: Craftsmanship and feedback

[1497] Step 8:

[1498] Collect feedback and store it in the cloud

[1499] Feedback collected from smart glasses is stored in cloud storage.

[1500] Input: Feedback from craftsmen

[1501] Data Computing: Feedback Collection and Cloud Storage Processing

[1502] Output: Feedback data on the cloud

[1503] Step 9:

[1504] System Improvements

[1505] The server uses the collected feedback to improve its generative and data analysis AI models, which will result in more accurate suggestions for the next time.

[1506] Input: Feedback data on the cloud

[1507] Data calculation: Model refinement process

[1508] Output: Improved generative AI and data analysis AI models

[1509] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1510] System Overview

[1511] This invention is a system for preserving and passing on artisanal techniques, and includes a camera and sensor means, generation AI, data analysis AI, database, feedback loop, and an emotion engine that recognizes the user's emotions. This allows for the artisan's emotional feedback on proposed new designs and techniques to be incorporated, resulting in more accurate suggestions and system improvements.

[1512] Learning and preserving craftsmanship

[1513] Technical Data Collection

[1514] Subject: Server

[1515] The server installs cameras and sensor devices in the space where the craftsmen work. These devices monitor and record the craftsmen's movements and working environment in real time, and the collected data is stored in cloud storage.

[1516] Specific examples

[1517] As a craftsman creates a tea bowl, the camera captures the craftsman's hand movements and the tools he uses in detail. The sensor device collects data such as the shape and temperature of the bowl. This allows even the finest techniques to be accurately recorded as digital data.

[1518] Generative AI learning

[1519] Technical Data Learning

[1520] Subject: Server

[1521] The server inputs the pre-processed data into a generative AI model, which learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[1522] Data analysis and new proposals

[1523] Trend data collection and analysis

[1524] Subject: Data Analysis AI

[1525] Data analysis AI collects the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc. It analyzes this data and identifies current market trends.

[1526] Specific examples

[1527] Data analysis AI analyzes popular online search terms and best-selling products to identify the most popular designs and color combinations, providing the raw materials for creating new proposals that are in line with the times.

[1528] Emotion engine combination and feedback

[1529] Generating and Evaluating New Proposals

[1530] Subject: Server

[1531] The server presents the new proposals generated by the generation AI and data analysis AI to the craftsman. The emotion engine analyzes the craftsman's emotions in real time after receiving the proposal and includes the analysis data in feedback. This allows the craftsman's emotional reaction to the proposal to be reflected in the system and used in the next proposal.

[1532] Gathering feedback and improving the system

[1533] Subject: Server

[1534] The server organizes the feedback data collected from the craftsmen and stores it in a database. Based on the collected feedback, the generation AI and data analysis AI models are improved to improve the accuracy of the next proposal.

[1535] Specific examples

[1536] A craftsman creates a prototype of a newly proposed tea bowl design and reports the production process and final evaluation to the server. The emotion engine analyzes the craftsman's emotions, such as happiness, surprise, or confusion, in real time when they see the proposal, and includes this data in feedback. The server uses this feedback to adjust the algorithms of the generation AI and data analysis AI, and reflects the results in the next proposal.

[1537] Emotion Engine Details

[1538] Emotion data collection and analysis

[1539] Subject: Server

[1540] The server collects the craftsman's facial expressions and tone of voice through devices such as cameras and microphones, and the emotion engine analyzes the data to recognize emotions, making it easier to collect not only technical feedback but also emotional feedback.

[1541] Specific examples

[1542] While the craftsman is reviewing the proposal, a camera captures his / her facial expressions and a microphone records his / her tone of voice. The emotion engine analyzes this data to identify the craftsman's emotions and transmits the data to a server, providing a comprehensive view of the craftsman's technical and emotional responses.

[1543] conclusion

[1544] The system of this invention can learn and store traditional artisan techniques as digital data, generate new proposals that match modern trends, and comprehensively incorporate the user's emotional feedback. This will enable the inheritance and evolution of artisan techniques, as well as advanced proposals that match the user's preferences and emotions.

[1545] The processing flow will be explained below.

[1546] Learning and preserving craftsmanship

[1547] Technical Data Collection

[1548] Subject: Server

[1549] Step 1:

[1550] The server installs cameras and sensor devices in the craftsman's workshop, positioned to optimally record the craftsman's movements.

[1551] Step 2:

[1552] The server collects video and sensor data from cameras and sensor devices in real time and stores it in cloud storage.

[1553] Step 3:

[1554] The server removes noise from the collected video data and divides it into frames. The sensor data is normalized and organized as time-series data.

[1555] Specific examples

[1556] Step 1:

[1557] The server places a camera on the desk where the craftsman is working and adjusts it to the optimal angle.

[1558] Step 2:

[1559] The server begins to collect video footage of the craftsman shaping the tea bowl and shape data obtained by the sensor in real time.

[1560] Step 3:

[1561] The server denoises the collected video data, divides it into frames, and normalizes the sensor data to create time-series data.

[1562] Generative AI learning

[1563] Technical Data Learning

[1564] Subject: Server

[1565] Step 1:

[1566] The server inputs pre-processed technical data into the generative AI model.

[1567] Step 2:

[1568] The server begins learning the craftsmanship of generative AI and trains iteratively.

[1569] Step 3:

[1570] The server stores the results learned by the generative AI in a database and manages them in a reusable format.

[1571] Specific examples

[1572] Step 1:

[1573] The server inputs preprocessed video data of the craftsman shaping the tea bowl into the generation AI.

[1574] Step 2:

[1575] The server uses generative AI to repeatedly train itself on data to learn things like hand movements and the shape of the vessel.

[1576] Step 3:

[1577] The server stores the learning results in a database and adds metadata (learning date and time, data size, etc.).

[1578] Data analysis and new proposals

[1579] Trend data collection and analysis

[1580] Subject: Data Analysis AI

[1581] Step 1:

[1582] Data analysis AI collects trend data from social media, fashion sites, market reports, etc.

[1583] Step 2:

[1584] Data analysis AI analyzes collected trend data, identifies major themes and styles, and performs clustering.

[1585] Step 3:

[1586] The data analysis AI generates new proposals based on the technical data learned by the generation AI and the results of trend analysis.

[1587] Specific examples

[1588] Step 1:

[1589] Data analysis AI collects the latest tea utensil design and color trends from the internet.

[1590] Step 2:

[1591] Data analysis AI analyzes collected trend data to identify popular designs and color combinations.

[1592] Step 3:

[1593] The data analysis AI combines the technical data of the craftsmen learned by the generation AI to propose new tea bowl designs.

[1594] Emotion engine combination and feedback

[1595] Generating and Evaluating New Proposals

[1596] Subject: Server

[1597] Step 1:

[1598] The server presents new proposals to the craftsman and simultaneously collects the craftsman's emotional data through cameras and microphones.

[1599] Step 2:

[1600] The emotion engine analyzes collected facial expression data and voice tone to recognize the emotions of the craftsman.

[1601] Step 3:

[1602] The server records the craftsman's emotional response to the proposal as analytical data and stores this data as feedback.

[1603] Specific examples

[1604] Step 1:

[1605] The server shows the new tea bowl design to the craftsman and collects the craftsman's emotional responses (facial expressions, tone of voice) in real time using a camera and microphone.

[1606] Step 2:

[1607] The emotion engine analyzes the craftsman's smile, exclamation of surprise, etc. to identify his / her emotions.

[1608] Step 3:

[1609] The server stores the analyzed emotion data as feedback data for the proposal and uses it to generate the next proposal.

[1610] Gathering feedback and improving the system

[1611] Subject: Server

[1612] Step 1:

[1613] The server organizes the collected feedback data and stores it in a database.

[1614] Step 2:

[1615] The server improves the generative AI and data analysis AI models based on the collected feedback.

[1616] Step 3:

[1617] The server uses the improved model to generate the next proposal, improving the accuracy of the system.

[1618] Specific examples

[1619] Step 1:

[1620] The server organizes the feedback data and emotion data from the craftsmen and stores them in a database.

[1621] Step 2:

[1622] The server adjusts the algorithms of the generative AI and data analysis AI based on the collected feedback and improves the model.

[1623] Step 3:

[1624] The server will propose the next bowl design based on the improved model, improving its accuracy.

[1625] Example 2

[1626] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1627] Preserving and passing on traditional craftsmanship is becoming increasingly difficult as technology becomes more advanced. Furthermore, adapting to modern market trends requires new proposals that take into account not only the craftsman's skills but also the latest market trends. Furthermore, to improve the accuracy of proposals, it is necessary to incorporate not only the craftsman's technical feedback but also their emotional reactions. However, it was difficult to achieve these comprehensively with conventional systems.

[1628] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a camera and sensor device means for collecting technical data of craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generative AI model for learning, a means for saving the learning results of the generative AI model in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generative AI model and the trend data analyzed by the data analysis AI means, a means for feeding back the generated proposals to the craftsmen and analyzing the craftsmen's emotions in real time using an emotion engine, and a means for improving the generative AI model and the model of the data analysis AI means based on the collected feedback. This makes it possible to realize an advanced feedback system that precisely preserves the craftsmen's skills, generates new technical proposals that respond to modern trends, and further reflects the craftsmen's emotional reactions.

[1629] A "camera" is a device that records the craftsman's actions and working environment as video data.

[1630] A "sensor device" is a device that measures physical information (such as temperature and shape) in a craftsman's working environment and collects it as data.

[1631] "Preprocessing" is the process of removing noise from collected technical data and converting it into an analyzable form.

[1632] A "generative AI model" is an artificial intelligence model that learns preprocessed technical data and analyzes and stores the movement patterns and techniques of craftsmen.

[1633] A "database" is a data storage system for systematically storing the learning results of a generative AI model.

[1634] "Data Analysis AI Method" is an artificial intelligence system that collects and analyzes trend data on the Internet to identify current market trends.

[1635] The "emotion engine" is a system that analyzes the facial expressions and tone of voice of craftsmen and recognizes their emotions in real time.

[1636] "Feedback" is the process of collecting artisans' technical and emotional reactions to new proposals.

[1637] "Model refinement" is the process of adjusting the algorithms of generative AI models and data analysis AI methods based on collected feedback data.

[1638] "New proposals" are proposals for new technologies and designs that are generated by combining data analyzed by generative AI models and data analysis AI means.

[1639] MODE FOR CARRYING OUT THE INVENTION

[1640] System Overview

[1641] The system aims to preserve and pass on artisanal techniques and is a comprehensive system that includes cameras and sensor devices, generative AI models, data analysis AI methods, databases, and an emotion engine. This system enables more accurate proposals and system improvements, including the emotional feedback of artisans on new designs and technical proposals.

[1642] Hardware and software used

[1643] Hardware

[1644] Camera: Used to record the craftsman's movements and working environment as video data.

[1645] Sensor device: Used to measure and collect data such as changes in shape and temperature during work.

[1646] Cloud storage: Used to store collected data.

[1647] software

[1648] Generative AI model: Learns from artisan technical data and uses it to generate new suggestions.

[1649] Data analysis AI means: Used to analyze trend data on the Internet.

[1650] Emotion engine: Used to analyze the emotions of craftsmen in real time.

[1651] Database: Used to store the learning results and feedback data of the generative AI model.

[1652] System processing flow

[1653] 1. Data collection: The server installs cameras and sensor devices in the space where the craftsman works, which monitors and records the craftsman's movements and working environment in real time. This information is stored in cloud storage.

[1654] Example: A craftsman creating a tea bowl is filmed with a camera, and a sensor device records the shape and temperature of the bowl.

[1655] 2. Data Preprocessing: The server cleanses the collected data and converts it into a format that the generative AI model can understand, removing noise and making the data analyzable.

[1656] Example: Cutting unnecessary scenes from captured footage and removing outliers in temperature data.

[1657] 3. Learning by generative AI: The server inputs the preprocessed data into a generative AI model, which learns the movement patterns and techniques of the craftsman. The learning results are stored in a database.

[1658] Example: AI learns how a craftsman moves his hands and uses tools.

[1659] 4. Trend data collection and analysis: Data analysis AI tools collect and analyze the latest trend data from the Internet, thereby understanding current market trends.

[1660] Example: Identify popular designs and color combinations based on data collected from social media and fashion sites.

[1661] 5. Generate new proposals: The server combines the data from the generative AI model and the data analysis AI method to generate new proposals, which are then fed back to the craftsman.

[1662] Example: The newly generated tea bowl design is displayed on the craftsman's device.

[1663] 6. Emotion engine analysis: Analyze the emotions of the craftsmen who receive the proposal in real time and collect their feedback. Analyze facial expressions and tone of voice through cameras and microphones.

[1664] Example: The emotion engine analyzes the happiness and surprise of a craftsman when he sees a new design.

[1665] 7. Feedback collection and system improvement: The server will improve the generative AI model and data analysis AI means based on the collected feedback data and reflect this in the next proposal.

[1666] Example: A craftsman prototypes a new tea bowl design and reports his or her impressions to the server. This data is used to retrain the AI ​​model.

[1667] Prompt Sentence Examples

[1668] "Describe a system for analyzing video data of the traditional tea bowl making process and generating new design proposals that take into account current trends. Also, explain how you incorporate the artisan's emotional response to the proposals."

[1669] This system can learn and store traditional artisan techniques as digital data, generate new proposals that match modern trends, and comprehensively incorporate the user's emotional feedback. This allows for the preservation and evolution of artisan techniques, and enables advanced proposals that match the user's preferences and emotions.

[1670] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1671] Step 1:

[1672] Installation of cameras and sensor devices

[1673] Subject: Server

[1674] Description:

[1675] The server installs cameras and sensor devices in the space where the craftsman works, setting the cameras at the appropriate positions and angles and placing the sensors at the appropriate work locations.

[1676] input:

[1677] Camera and sensor devices.

[1678] output:

[1679] You are now ready to record the craftsman's movements and working environment.

[1680] Specific behavior:

[1681] The server remotely adjusts the focus and angle of the camera via the network, and places sensor devices around the work object.

[1682] Step 2:

[1683] Data collection

[1684] Subject: Server

[1685] Description:

[1686] The server collects real-time data on the worker's movements and working environment through cameras and sensor devices, and this data is stored in cloud storage.

[1687] input:

[1688] Craftsman behavior and working environment.

[1689] output:

[1690] Video data and environmental data are stored in cloud storage.

[1691] Specific behavior:

[1692] As the craftsman shapes the tea bowl, the camera captures his or her hand movements, and the sensor device measures the shape and temperature and sends the data to a server.

[1693] Step 3:

[1694] Data Preprocessing

[1695] Subject: Server

[1696] Description:

[1697] The server cleanses the collected data and converts it into an analyzable format, which involves removing noise and converting the data format.

[1698] input:

[1699] Collected video and environmental data.

[1700] output:

[1701] Cleansed, parseable data.

[1702] Specific behavior:

[1703] The server denoises the collected images, cuts out unnecessary parts, removes outliers from the sensor data, and converts them into standard formats (e.g., CSV or PNG).

[1704] Step 4:

[1705] Generative AI learning

[1706] Subject: Server

[1707] Description:

[1708] The server inputs the preprocessed data into a generative AI model to learn the craftsman's technical patterns, and the learning results are stored in a database.

[1709] input:

[1710] Preprocessed data.

[1711] output:

[1712] Technical data learned by generative AI models.

[1713] Specific behavior:

[1714] The server inputs preprocessed video and sensor data into a generative AI model, which then learns the patterns of the craftsman's hand movements and techniques. The learning results are stored in a database.

[1715] Step 5:

[1716] Trend data collection and analysis

[1717] Subject: Data Analysis AI

[1718] Description:

[1719] Data analysis AI collects the latest trend data from the internet and analyzes it, and the analysis results are used to generate new proposals.

[1720] input:

[1721] Trending data on the internet.

[1722] output:

[1723] Analyzed trend data.

[1724] Specific behavior:

[1725] Data analysis AI searches the web using specific keywords (for example, "handmade tea bowl trends") and analyzes the collected data to identify popular designs and color combinations.

[1726] Step 6:

[1727] Generate a new proposal

[1728] Subject: Server

[1729] Description:

[1730] The server combines the generative AI model with the data generated by the data analysis AI to generate new suggestions, which are then fed back to the craftsman.

[1731] input:

[1732] Generative AI model learning results and analyzed trend data.

[1733] output:

[1734] New technology proposal.

[1735] Specific behavior:

[1736] The server combines the technical data obtained from the generation AI model with the trend information obtained from the data analysis AI to generate a new tea bowl design and send it to the craftsman's device.

[1737] Step 7:

[1738] Emotion Engine Analysis

[1739] Subject: Server

[1740] Description:

[1741] The server uses an emotion engine to analyze the craftsman's emotions in real time, identifying the craftsman's emotions based on data obtained through cameras and microphones.

[1742] input:

[1743] Real-time data from cameras and microphones.

[1744] output:

[1745] Analyzed emotion data.

[1746] Specific behavior:

[1747] As the craftsman reviews the design of a new tea bowl, a camera captures his facial expressions and a microphone records his tone of voice. The server uses an emotion engine to analyze this data and identify the craftsman's emotions.

[1748] Step 8:

[1749] Gathering feedback and improving the system

[1750] Subject: Server

[1751] Description:

[1752] The server uses the collected feedback to improve the generative AI model and data analysis AI, which will improve the accuracy of the next proposal.

[1753] input:

[1754] Technical and emotional feedback data from artisans.

[1755] output:

[1756] Improved generative AI models and data analysis AI.

[1757] Specific behavior:

[1758] The craftsman prototypes the new tea bowl design and reports his / her opinions and impressions to the server, which then retrains the generative AI model and data analysis AI method based on the collected feedback data and reflects it in the next proposal.

[1759] (Application example 2)

[1760] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1761] Conventional autonomous vehicles have been unable to fully utilize the driver's emotional state and real-time environmental information to improve driving comfort and safety, and lack the means to effectively collect and analyze this information and make improvements based on system feedback.

[1762] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1763] In this invention, the server includes a camera and sensor means for collecting technical data from craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generation AI for learning, a means for storing the learning results of the generation AI in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI, a means for feeding back the generated proposals to craftsmen and collecting their evaluations, a means for improving the models of the generation AI and the data analysis AI based on the collected feedback, a means for optimizing driving patterns and routes to improve the comfort and safety of the other-type vehicle while driving, a means for controlling driving based on the optimized driving patterns and routes, an emotion engine for analyzing the emotional state of the driver, and a means for collecting feedback and improving the system based on the emotional state analyzed by the emotion engine. This makes it possible to effectively utilize the real-time environment and the driver's emotional state while driving, thereby improving comfort and safety.

[1764] "Camera and sensor means" refers to devices that photograph and measure the driver's condition and driving environment in real time.

[1765] "Means of preprocessing and converting into an analyzable format" refers to the process of converting collected data into a format that can be analyzed by AI.

[1766] "Means of inputting data into a generative AI and having it learn" refers to the process of inputting preprocessed data into a generative AI model and having it learn.

[1767] "Means for saving in a database" refers to a database system for recording and saving learning results.

[1768] "Data analysis AI means for collecting and analyzing trend data" is an artificial intelligence system for collecting and analyzing trend information on the Internet.

[1769] The "means of generating new proposals" is the process of combining the data learned by the generation AI with the trend data analyzed by the data analysis AI to create new proposals.

[1770] "Feedback and evaluation collection measures" are the processes of presenting new proposals to drivers and collecting their reactions and evaluations.

[1771] "Means to improve generative and analytical AI models" refers to the process of improving AI models based on collected feedback to improve the accuracy of future recommendations.

[1772] "Means for optimizing driving patterns and routes" refers to the process of calculating optimal driving patterns and routes to improve the comfort and safety of the vehicle while driving.

[1773] "Means for controlling driving" refers to a system that controls the vehicle based on optimized driving patterns and routes.

[1774] The "emotion engine for analyzing the driver's emotional state" is a system that uses cameras and microphones to analyze the driver's facial expressions and tone of voice to recognize their emotions.

[1775] "Means for collecting feedback and improving the system" refers to the process of collecting feedback based on the driver's emotional state and improving the overall system based on that feedback.

[1776] This invention provides a system that collects, analyzes, and feeds back various data to improve the comfort and safety of automobiles while driving. Specific methods and processes for realizing this system are described below.

[1777] System Configuration

[1778] The system consists of the following main components:

[1779] 1. Camera and sensor means:

[1780] This is a device that captures and measures the driver's condition and driving environment in real time. Specifically, it includes cameras and microphones installed inside the vehicle and various sensors that monitor the external environment.

[1781] 2. Data preprocessing methods:

[1782] This software preprocesses the collected data and converts it into an analyzable format, for example by dividing the collected video data into an appropriate number of frames, removing noise, and normalizing it.

[1783] 3. Generative AI Model:

[1784] This is an artificial intelligence model that inputs the preprocessed data and performs learning, thereby learning data related to the driver's behavioral patterns and driving environment.

[1785] 4. Database:

[1786] This is a database system for recording and storing the learning results of the generation AI. This system stores environmental data during driving, the driver's emotional state, traffic information, etc.

[1787] 5. Data analysis AI methods:

[1788] This is an AI system for collecting and analyzing trend data, such as traffic information, weather data, and social media trend information from the Internet.

[1789] 6. New proposal generation methods:

[1790] This is the process of combining the data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new suggestions, which will then suggest optimal driving patterns and routes for the driver.

[1791] 7. Feedback and evaluation collection methods:

[1792] New suggestions are presented to drivers and their reactions and evaluations are collected, for example, by presenting the suggestions via an in-car display or smartphone.

[1793] 8. Model refinement methods:

[1794] This is the process of improving the generative AI and data analysis AI models based on the collected feedback, which will improve the accuracy of the next proposal.

[1795] 9. Driving pattern and route optimization measures:

[1796] It is an AI system that calculates optimal driving patterns and routes to improve vehicle comfort and safety while driving.

[1797] 10. Travel control means:

[1798] This is a system for controlling vehicles based on optimized driving patterns and routes. Autonomous driving systems and actuators are used for actual vehicle control.

[1799] 11. Emotion Engine:

[1800] This system uses cameras and microphones to analyze the driver's facial expressions and tone of voice to recognize their emotions, and is used to grasp the driver's fatigue and state of tension in real time.

[1801] 12. Feedback collection and system improvement methods:

[1802] It is a process of collecting feedback based on the driver's emotional state and using that to improve the overall system.

[1803] Specific examples

[1804] For example, when a driver is driving on the highway, the emotion engine analyzes the driver's facial expressions to detect signs of fatigue. This data is analyzed by a generative AI model and used to optimize a safe driving route. The optimal route is calculated and displayed on the vehicle's display. Driver feedback is also collected and reflected in future recommendations.

[1805] Prompt Sentence Examples

[1806] Below are some example prompts that can be input to the generative AI model in this system:

[1807] "What facial expressions do drivers have while driving that make you feel safer? And vice versa?"

[1808] The above configuration makes it possible to effectively improve comfort and safety during driving.

[1809] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1810] Step 1:

[1811] The server monitors the driver's condition and driving environment in real time using cameras and sensors installed in the vehicle.

[1812] Input: Video data from cameras and sensors and environmental data

[1813] Data processing: Video data is divided into frames, and noise is removed and normalized.

[1814] Output: Preprocessed data (video frames and environmental data)

[1815] Step 2:

[1816] The server inputs the preprocessed data into a generative AI model, which learns about the driver's behavioral patterns and driving environment.

[1817] Input: Preprocessed data (video frames and environmental data)

[1818] Data Computation: Learning with Generative AI Models

[1819] Output: Learning result data (driving patterns and environmental recognition data)

[1820] Step 3:

[1821] The server stores the learning result data in a database.

[1822] Input: Learning result data obtained from the generative AI model

[1823] Data processing: Converting data into a format that can be saved in a database

[1824] Output: Learning result data stored in a database

[1825] Step 4:

[1826] The server collects relevant information from the internet using data analysis AI means to collect and analyze trend data.

[1827] Input: Internet traffic information, weather data, social media trend information

[1828] Data calculation: Analyze collected data and extract important trend information

[1829] Output: Analyzed trend data

[1830] Step 5:

[1831] The server combines the technical data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new proposals.

[1832] Input: Training result data and trend data

[1833] Data arithmetic: Combining data to generate new suggestions

[1834] Output: New proposed data (optimal driving patterns and routes)

[1835] Step 6:

[1836] The terminal provides feedback on new proposals to the driver and collects their evaluations.

[1837] Input: New proposal data

[1838] Specific operation: Displaying suggestions on the in-car display or smartphone

[1839] Output: Driver feedback data

[1840] Step 7:

[1841] The server refines its generative AI and data analysis AI models based on the collected feedback.

[1842] Input: Driver feedback data

[1843] Data calculation: Analyze feedback data and adjust AI models

[1844] Output: Improved generative AI and data analysis AI models

[1845] Step 8:

[1846] The server uses the improved AI model to optimize the vehicle's driving patterns and routes while in operation.

[1847] Input: Improved generative AI and data analysis AI models

[1848] Data calculation: Calculates optimal driving patterns and routes

[1849] Output: Optimized driving patterns and route data

[1850] Step 9:

[1851] The terminal controls the vehicle based on the optimized driving pattern and route.

[1852] Input: Optimized driving pattern and route data

[1853] Specific operation: Controlling the driving route using an autonomous driving system and actuators

[1854] Output: Control data for the vehicle during operation

[1855] Step 10:

[1856] The server collects and analyzes data from cameras and microphones using an emotion engine to analyze the driver's emotional state.

[1857] Input: Camera video and audio data

[1858] Data processing: Emotional state analysis (facial expression recognition and voice tone analysis)

[1859] Output: Driver's emotional state data

[1860] Step 11:

[1861] The server collects feedback based on the emotional state analyzed by the emotion engine and improves the system.

[1862] Input: Driver's emotional state data

[1863] Data calculation: Analyze emotional state data and improve the entire system

[1864] Output: Improved system feedback data

[1865] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1866] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1867] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1868] [Fourth embodiment]

[1869] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1870] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1871] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1872] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1873] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1874] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1875] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1876] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1877] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1878] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1879] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1880] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1881] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1882] System Overview

[1883] The system of the present invention is composed of a camera and sensor means, generation AI, data analysis AI, database, and feedback loop, which allows for the collection, storage, and analysis of craftsmanship data, the generation of new proposals, and the transfer of skills.

[1884] Learning and preserving craftsmanship

[1885] Technical Data Collection

[1886] Subject: Server

[1887] The server installs cameras and sensor devices in the space where the craftsmen work. These devices monitor and record the craftsmen's movements and work environment in real time. The server saves the video and audio data collected from the cameras and sensor devices in cloud storage.

[1888] Specific examples

[1889] As a craftsman creates a tea bowl, the camera captures the craftsman's hand movements and the tools he uses in detail. The sensor device collects data such as the shape and temperature of the bowl. This allows even the finest techniques to be accurately recorded as digital data.

[1890] Generative AI learning

[1891] Technical Data Learning

[1892] Subject: Server

[1893] The server inputs the pre-processed data into a generative AI model, which learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[1894] Data analysis and new proposals

[1895] Trend data collection and analysis

[1896] Subject: Data Analysis AI

[1897] Data analysis AI collects the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc. It analyzes this data and identifies current market trends.

[1898] Specific examples

[1899] Data analysis AI analyzes popular online search terms and best-selling products to identify the most popular designs and color combinations, providing the raw materials for creating new proposals that are in line with the times.

[1900] Generate new suggestions and feedback

[1901] Generate a new proposal

[1902] Subject: Data Analysis AI

[1903] The data analysis AI combines the technical data learned by the generation AI with the analyzed trend data to generate new product and design proposals. These proposals are fed back to the craftsmen and used in their actual work.

[1904] Gathering feedback and improving the system

[1905] Subject: Server

[1906] The server presents the generated proposals to the craftsmen and collects their evaluations and opinions. Based on this feedback, the model of the entire system (generative AI and data analysis AI) is improved, thereby improving the quality of the generated proposals.

[1907] Specific examples

[1908] Craftsmen will prototype new tea bowl designs and report the production process and final evaluation to the server. The server will use this feedback to adjust the algorithms of the generative AI and data analysis AI, and reflect this in the next proposal.

[1909] conclusion

[1910] The system of this invention makes it possible to learn and preserve traditional artisan techniques as digital data and propose new products that match modern trends, thereby realizing the inheritance and evolution of artisan techniques.

[1911] The processing flow will be explained below.

[1912] Learning and preserving craftsmanship

[1913] Technical Data Collection

[1914] Subject: Server

[1915] 1. Step 1: Camera and Sensor Settings

[1916] The server places cameras and sensor devices in the craftsman's workshop and performs initial settings to enable accurate detection.

[1917] 2. Step 2: Start collecting data

[1918] The server collects data from cameras and sensor devices in real time and transfers it to cloud storage.

[1919] 3. Step 3: Preprocessing

[1920] The server removes noise from the collected video data, splits the video into frames, and normalizes and timestamps the sensor data.

[1921] Specific examples

[1922] 1. Step 1:

[1923] The server places the camera on the desk where the craftsman is working and adjusts it to the appropriate angle.

[1924] 2. Step 2:

[1925] The server begins to collect video footage of the craftsman shaping the tea bowl and shape data obtained by the sensor in real time.

[1926] 3. Step 3:

[1927] The server removes noise from the collected video data, splits it into frames, normalizes the sensor data, and organizes it as time-series data.

[1928] Generative AI learning

[1929] Technical Data Learning

[1930] Subject: Server

[1931] 1. Step 1: Data Entry

[1932] The server inputs the pre-processed technical data into the generative AI model.

[1933] 2. Step 2: Model training

[1934] The server begins learning the technical patterns using generative AI and trains iteratively.

[1935] 3. Step 3: Save the learning results

[1936] The server stores the results of the technical patterns learned by the generative AI in a database and manages them in a reusable form.

[1937] Specific examples

[1938] 1. Step 1:

[1939] The server inputs pre-processed video data of the craftsman shaping the tea bowl into the generation AI.

[1940] 2. Step 2:

[1941] The server repeatedly trains the generative AI with data to learn things like hand movements and the shape of the vessel.

[1942] 3. Step 3:

[1943] The server stores the learning results in a database and adds metadata (learning date and time, data size, etc.).

[1944] Data analysis and new proposals

[1945] Trend data collection and analysis

[1946] Subject: Data Analysis AI

[1947] 1. Step 1: Trend data collection

[1948] Data analysis AI collects trend data from social media, fashion sites, market reports, etc.

[1949] 2. Step 2: Trend analysis

[1950] Data analysis AI analyzes collected trend data, identifies major themes and styles, and performs clustering.

[1951] 3. Step 3: Generate new proposals

[1952] The data analysis AI generates new proposals based on the technical data learned by the generation AI and the results of trend analysis.

[1953] Specific examples

[1954] 1. Step 1:

[1955] Data analysis AI collects trend data on popular designs and colors on the Internet.

[1956] 2. Step 2:

[1957] Data analysis AI analyzes collected trend data and identifies the most popular designs and color combinations.

[1958] 3. Step 3:

[1959] The data analysis AI combines the technical data of the craftsmen learned by the generation AI to propose new tea bowl designs.

[1960] Generate new suggestions and feedback

[1961] Generating and Evaluating New Proposals

[1962] Subject: Server

[1963] 1. Step 1: Feedback on the proposal

[1964] The server presents the generated new proposals to the craftsmen and collects their evaluations and opinions.

[1965] 2. Step 2: Save the evaluation data

[1966] The server organizes the feedback data collected from the craftsmen and stores it in a database.

[1967] 3. Step 3: System Improvement

[1968] The server uses the collected feedback to improve the generative AI and data analysis AI models and reflect this in its next proposal.

[1969] Specific examples

[1970] 1. Step 1:

[1971] The server shows the new bowl design to the craftsman and encourages him to give feedback.

[1972] 2. Step 2:

[1973] The server organizes the craftsmen's feedback and stores it in a database.

[1974] 3. Step 3:

[1975] The server adjusts the algorithms of the generation AI and data analysis AI based on the collected feedback and reflects it in the next proposal.

[1976] Example 1

[1977] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1978] The inheritance of artisanal skills is extremely important in today's world, but because traditional techniques rely on oral transmission and direct instruction, they are difficult to pass on efficiently. It's also difficult to propose new ideas that are in line with market trends, putting many traditional techniques at risk of becoming outdated. Furthermore, when introducing new technologies, there is a lack of a system for systematically collecting feedback and improving models. To solve these problems, a system is needed that digitizes technology, links with trends, and utilizes feedback.

[1979] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1980] In this invention, the server includes a video device and a sensor device for collecting data on the work of engineers, a device for preprocessing the collected work data and converting it into an analyzable format, and a device for inputting the converted data into a generative model for learning. This enables the efficient inheritance of traditional techniques and the generation of new proposals in line with modern trends.

[1981] An "engineer" is someone who has specific skills or abilities and uses those skills to create products or services.

[1982] "Work data" refers to data that includes information on the actions, procedures, and tools used by engineers when they perform work.

[1983] "Video equipment" refers to equipment such as cameras that record the actions and work processes of technicians as visual data.

[1984] A "sensor device" is a device for acquiring environmental data and physical parameters such as temperature, pressure, and humidity in real time.

[1985] "Preprocessing" is the process of converting collected raw data into an analyzable format, removing noise, and converting the data.

[1986] A "generative model" is an artificial intelligence model that learns the actions and techniques of engineers based on collected data and generates new proposals.

[1987] "Data storage" refers to a storage device or system for permanently storing learned data and analysis results.

[1988] "Trend data" is data that shows market and consumer trends and is collected based on information on the Internet.

[1989] A "data analysis model" is an artificial intelligence model that analyzes collected trend data and extracts important patterns and market trends.

[1990] A "proposal" is a new product design or technical improvement plan generated based on the generative model and data analysis model.

[1991] "Evaluation" refers to information including feedback and opinions given by engineers regarding the proposal, as well as actual work results.

[1992] "Algorithm" refers to the computational methods and procedures used by generative models and data analysis models to generate new proposals.

[1993] System Overview

[1994] This invention is a system for digitizing and passing on engineers' skills, and is composed of a video device, a sensor device, a generative model, a data analysis model, data storage, and an evaluation feedback device. This system collects and analyzes engineers' work data, generates new proposals, and realizes technological evolution.

[1995] Hardware and Software Configuration

[1996] The system uses the following hardware and software:

[1997] Video equipment: High-resolution camera

[1998] Sensor devices: temperature sensors, pressure sensors, humidity sensors

[1999] Generative models: Deep learning models (e.g., TensorFlow, PyTorch)

[2000] Data analysis models: Natural language processing and data mining tools (e.g., Scikit-learn, NLTK)

[2001] Data storage: Cloud storage (e.g., Amazon S3, Google Cloud Storage)

[2002] Evaluation Feedback Instrument: A dedicated feedback collection application

[2003] Specific actions

[2004] The system works as follows: First, video and sensor devices collect data on the technician's work in real time. The video devices capture high-resolution images of the technician's hand movements and the tools they use, while the sensor devices collect environmental data such as temperature, humidity, and pressure. This data is sent to a server and stored in cloud storage.

[2005] The server then preprocesses the collected data, which includes noise removal, data shaping, and format conversion. The preprocessed data is then input into a generative model, which learns the technician's behavior patterns and techniques. The data learned by the generative model is then stored in data storage.

[2006] In parallel, the data analysis model collects and analyzes the latest trend data from the Internet, for example, from social media, fashion sites, and market reports. The analyzed trend data is then input into the generative model and used to generate new proposals.

[2007] Finally, the generated proposals are presented to engineers, whose evaluations are collected through a feedback collection application. This feedback is used to refine the generative model and data analysis model algorithms, thereby improving the accuracy of future proposals and technical improvements.

[2008] Specific examples

[2009] As a potter creates a tea bowl, a video device captures detailed footage of the potter's hand movements and the tools he uses, while a sensor device collects the temperature and humidity of the work surface. The preprocessed data is fed into a generative model, which learns how the potter moves his hands and uses the tools. At the same time, a data analysis model collects and analyzes the latest trends, and based on this information, new tea bowl design proposals are generated.

[2010] The craftsman is presented with a prompt: "Please prototype a newly proposed tea bowl design and report the production process and final evaluation to the server." Based on this feedback, the algorithms of the generative model and data analysis model are improved, and the accuracy of the next proposal is improved.

[2011] Prompt Sentence Examples

[2012] Here are some example prompts to input to the generative AI model:

[2013] "We provide a dataset to learn how artisans use their hands and tools to create tea bowls. You can then propose new designs for tea bowls based on this data."

[2014] This concludes the "Mode for carrying out the invention." This system digitizes the skills of engineers and generates new proposals that are in line with trends, thereby realizing the inheritance and evolution of technology.

[2015] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2016] Step 1:

[2017] The server collects data in real time from video and sensor devices installed in the technician's workspace. The video devices capture high-resolution images of the technician's hand movements and the tools they use, while the sensor devices collect environmental data such as temperature, humidity, and pressure. The input data consists of video (video stream) and sensor information (numerical data), which the server stores in cloud storage. Specifically, the camera captures the movement, and the various sensors read the values ​​and send them to the server.

[2018] Step 2:

[2019] The server preprocesses the data stored in the cloud storage. Preprocessing includes noise removal, data shaping, and format conversion. For example, it removes unwanted noise from video data and synchronizes sensor data on the time axis. The input data is raw data, and the output data is preprocessed data. Specifically, the server applies a noise filtering algorithm to unify the different data formats.

[2020] Step 3:

[2021] The server inputs the preprocessed data into a generative AI model. The generative AI model uses this data to learn the technician's movements and work patterns. The input data is preprocessed technical data, and the output data is the learning results (a numerical model of the technical data). Specifically, the server runs the generative AI model (e.g., a deep learning network) and proceeds with learning based on the dataset.

[2022] Step 4:

[2023] Data analysis AI collects trend data from the internet. It automatically collects and analyzes the latest trend information from sources such as social media, fashion sites, and market reports. The input data is text and image data from the web, and the output data is the analysis results (trend information). Specifically, data analysis AI performs web scraping and analyzes the collected data using natural language processing (NLP) algorithms.

[2024] Step 5:

[2025] Data analysis AI combines the technical data learned by the generative AI model with collected trend data to generate new proposals. The input data is the learned technical data and analyzed trend data, and the output data is new proposals (product designs or technical improvement ideas). Specifically, data analysis AI combines these data sets to generate new designs and product concepts.

[2026] Step 6:

[2027] The server presents the generated proposal to the engineer and collects their evaluations and opinions. The input data is the new proposal, and the output data is the feedback from the engineer. The server receives the engineer's evaluations and opinions using a feedback collection application. Specifically, the server sends the generated proposal to the engineer's dedicated terminal, and the engineer enters feedback on it.

[2028] Step 7:

[2029] The server improves the algorithms of the generative AI model and data analysis AI based on the collected feedback. The input data is feedback from engineers, and the output data is the improved algorithm. Specifically, the server analyzes the feedback data and adjusts the parameters of the generative AI and data analysis model, thereby improving the accuracy of the next proposal.

[2030] (Application example 1)

[2031] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2032] Traditionally, the transmission of artisanal skills has relied on oral and practical training, making it difficult to transfer skills and requiring a great deal of time and effort. Furthermore, in order to quickly respond to modern market trends, it is essential to improve techniques and create new proposals, but this is not easy. Furthermore, because artisanal skills are highly advanced, they cannot be immediately understood even after watching a demonstration, and new techniques must be learned through trial and error. However, this process also presents a problem: it is not efficient.

[2033] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2034] In this invention, the server includes a camera and sensor means for collecting technical data from craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generation AI for learning, a means for storing the learning results of the generation AI in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI, a means for feeding back the generated proposals to the craftsmen and collecting their evaluations, a means for improving the models of the generation AI and the data analysis AI based on the collected feedback, a means for displaying the proposals to the craftsmen in real time via smart glasses, and a means for collecting feedback from the smart glasses and storing it in the cloud. This not only enables efficient skill transfer, but also enables the rapid generation of new proposals that reflect modern market trends and allows craftsmen to accept and improve the proposals in real time.

[2035] Definitions of important words

[2036] A "camera" is a device for recording images of objects or people.

[2037] A "sensor" is a device that measures physical motion or environmental data and collects that information in digital form.

[2038] "Preprocessing" is a data processing step to convert collected data into a format suitable for analysis and learning.

[2039] "Generative AI" is an artificial intelligence model that learns artisan techniques and trend data to generate new proposals.

[2040] A "database" is a digital storage device for systematically storing and managing collected technical data and the learning results of generative AI.

[2041] "Data Analysis AI" is an artificial intelligence model that collects and analyzes trend data to identify current market trends.

[2042] "Trend data" refers to data on the latest trends and market trends on the Internet.

[2043] "Feedback" refers to the evaluation and opinions of craftsmen regarding new proposals.

[2044] "Smart glasses" are wearable devices that display images and have functions such as cameras and sensors.

[2045] The "cloud" is a data storage and computing service provided over the internet.

[2046] MODE FOR CARRYING OUT THE INVENTION

[2047] System Overview

[2048] The system of this invention is composed of cameras and sensors, generative AI, data analysis AI, a database, smart glasses, cloud storage, and a feedback loop. This system not only collects and stores the craftsman's technical data, but also enables analysis and generation of new proposals using generative AI, and continuous improvement through feedback.

[2049] Learning and preserving craftsmanship

[2050] Technical Data Collection

[2051] The server installs cameras and sensor devices in the space where the artisan works. These devices monitor and record the artisan's movements and work environment in real time. For example, when an artisan creates pottery, the camera captures detailed images of the artisan's hand movements and the tools he uses, while the sensors collect data such as the shape and temperature of the vessel. The collected video and sensor data are stored in cloud storage.

[2052] Generative AI learning

[2053] Technical Data Learning

[2054] The server inputs the pre-processed technical data into the generative AI model, which then learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[2055] Data analysis and new proposals

[2056] Trend data collection and analysis

[2057] Data analysis AI collects the latest trend data from the internet, for example, automatically retrieving relevant information from social media, fashion sites, market reports, etc., to identify current market trends.

[2058] Generate a new proposal

[2059] The data analysis AI combines the technical data learned by the generation AI with the analyzed trend data to generate new product and design proposals. These proposals are fed back to artisans in real time via smart glasses. For example, a new jewelry design using traditional pearl-making techniques can be generated, and the artisan can then create it.

[2060] Gathering feedback and improving the system

[2061] Collecting feedback

[2062] The smart glasses collect feedback from artisans on new proposals and send the data to the cloud, where the server uses the feedback to improve its generative and data-analytical AI models.

[2063] System Improvements

[2064] The server adjusts the algorithms of the generation AI and data analysis AI based on the evaluations and opinions of the craftsmen and reflects them in the next proposal. This allows the system to continuously evolve and make higher quality proposals.

[2065] Specific example details

[2066] Imagine a traditional pearl craftsman wearing smart glasses. A camera in the glasses records his movements in real time and stores them in the cloud. AI then suggests new designs based on the latest jewelry trends, which the craftsman then prototypes. The entire process works seamlessly, with a feedback loop that allows the system to improve.

[2067] Prompt Sentence Examples

[2068] "Create contemporary jewelry designs using traditional pearling techniques, while also taking into account the latest fashion trends."

[2069] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2070] Program processing flow

[2071] Step 1:

[2072] Technical data collection

[2073] The server uses cameras and sensors installed in the space where the craftsmen work to monitor and record the craftsmen's movements and working environment in real time.

[2074] Input: Video and environmental data from cameras and sensors

[2075] Data processing: Integrate and preprocess video data and sensor data

[2076] Output: Pre-processed technical data

[2077] Step 2:

[2078] Data Preprocessing

[2079] The server converts the collected technical data into an analyzable format: for example, video data is split into frames, and sensor data is converted into appropriate units.

[2080] Input: Preprocessed technical data

[2081] Data calculation: Preprocessing such as frame division, unit conversion, noise removal, etc.

[2082] Output: Data in a parsable format

[2083] Step 3:

[2084] Generative AI learning

[2085] The server inputs technical data in an analyzable format into the generation AI, allowing it to learn the movement patterns and techniques of the craftsmen.

[2086] Input: Data in a parsable format

[2087] Data Computation: Learning Processes with Generative AI Models

[2088] Output: Technical data as a result of learning

[2089] Step 4:

[2090] Saving to a database

[2091] The server stores the learning results of the generative AI in a database, allowing important technical information to be systematically stored.

[2092] Input: Generative AI learning results

[2093] Data calculation: saving to database

[2094] Output: Technical data in the database

[2095] Step 5:

[2096] Trend data collection and analysis

[2097] The server uses data analysis AI to collect and analyze the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc.

[2098] Input: Trending information on the internet

[2099] Data calculation: Trend data collection and analysis

[2100] Output: Analyzed trend data

[2101] Step 6:

[2102] Generate a new proposal

[2103] The server combines the technical data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new product and design proposals.

[2104] Input: Technical data, trend data

[2105] Data calculation: Proposal generation process

[2106] Output: New proposal

[2107] Step 7:

[2108] Feedback to smart glasses

[2109] The server displays the generated new suggestions to the craftsman in real time via smart glasses, and the craftsman works on the suggestions and provides feedback.

[2110] Input: New Proposal

[2111] Data calculation: Real-time display on smart glasses

[2112] Output: Craftsmanship and feedback

[2113] Step 8:

[2114] Collect feedback and store it in the cloud

[2115] Feedback collected from smart glasses is stored in cloud storage.

[2116] Input: Feedback from craftsmen

[2117] Data Computing: Feedback Collection and Cloud Storage Processing

[2118] Output: Feedback data on the cloud

[2119] Step 9:

[2120] System Improvements

[2121] The server uses the collected feedback to improve its generative and data analysis AI models, which will result in more accurate suggestions for the next time.

[2122] Input: Feedback data on the cloud

[2123] Data calculation: Model refinement process

[2124] Output: Improved generative AI and data analysis AI models

[2125] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2126] System Overview

[2127] This invention is a system for preserving and passing on artisanal techniques, and includes a camera and sensor means, generation AI, data analysis AI, database, feedback loop, and an emotion engine that recognizes the user's emotions. This allows for the artisan's emotional feedback on proposed new designs and techniques to be incorporated, resulting in more accurate suggestions and system improvements.

[2128] Learning and preserving craftsmanship

[2129] Technical Data Collection

[2130] Subject: Server

[2131] The server installs cameras and sensor devices in the space where the craftsmen work. These devices monitor and record the craftsmen's movements and working environment in real time, and the collected data is stored in cloud storage.

[2132] Specific examples

[2133] As a craftsman creates a tea bowl, the camera captures the craftsman's hand movements and the tools he uses in detail. The sensor device collects data such as the shape and temperature of the bowl. This allows even the finest techniques to be accurately recorded as digital data.

[2134] Generative AI learning

[2135] Technical Data Learning

[2136] Subject: Server

[2137] The server inputs the pre-processed data into a generative AI model, which learns the craftsman's movement patterns and techniques and stores the results in a database, allowing important technical information to be systematically collected and stored for future use.

[2138] Data analysis and new proposals

[2139] Trend data collection and analysis

[2140] Subject: Data Analysis AI

[2141] Data analysis AI collects the latest trend data from the internet, automatically retrieving relevant information from social media, fashion sites, market reports, etc. It analyzes this data and identifies current market trends.

[2142] Specific examples

[2143] Data analysis AI analyzes popular online search terms and best-selling products to identify the most popular designs and color combinations, providing the raw materials for creating new proposals that are in line with the times.

[2144] Emotion engine combination and feedback

[2145] Generating and Evaluating New Proposals

[2146] Subject: Server

[2147] The server presents the new proposals generated by the generation AI and data analysis AI to the craftsman. The emotion engine analyzes the craftsman's emotions in real time after receiving the proposal and includes the analysis data in feedback. This allows the craftsman's emotional reaction to the proposal to be reflected in the system and used in the next proposal.

[2148] Gathering feedback and improving the system

[2149] Subject: Server

[2150] The server organizes the feedback data collected from the craftsmen and stores it in a database. Based on the collected feedback, the generation AI and data analysis AI models are improved to improve the accuracy of the next proposal.

[2151] Specific examples

[2152] A craftsman creates a prototype of a newly proposed tea bowl design and reports the production process and final evaluation to the server. The emotion engine analyzes the craftsman's emotions, such as happiness, surprise, or confusion, in real time when they see the proposal, and includes this data in feedback. The server uses this feedback to adjust the algorithms of the generation AI and data analysis AI, and reflects the results in the next proposal.

[2153] Emotion Engine Details

[2154] Emotion data collection and analysis

[2155] Subject: Server

[2156] The server collects the craftsman's facial expressions and tone of voice through devices such as cameras and microphones, and the emotion engine analyzes the data to recognize emotions, making it easier to collect not only technical feedback but also emotional feedback.

[2157] Specific examples

[2158] While the craftsman is reviewing the proposal, a camera captures his / her facial expressions and a microphone records his / her tone of voice. The emotion engine analyzes this data to identify the craftsman's emotions and transmits the data to a server, providing a comprehensive view of the craftsman's technical and emotional responses.

[2159] conclusion

[2160] The system of this invention can learn and store traditional artisan techniques as digital data, generate new proposals that match modern trends, and comprehensively incorporate the user's emotional feedback. This will enable the inheritance and evolution of artisan techniques, as well as advanced proposals that match the user's preferences and emotions.

[2161] The processing flow will be explained below.

[2162] Learning and preserving craftsmanship

[2163] Technical Data Collection

[2164] Subject: Server

[2165] Step 1:

[2166] The server installs cameras and sensor devices in the craftsman's workshop, positioned to optimally record the craftsman's movements.

[2167] Step 2:

[2168] The server collects video and sensor data from cameras and sensor devices in real time and stores it in cloud storage.

[2169] Step 3:

[2170] The server removes noise from the collected video data and divides it into frames. The sensor data is normalized and organized as time-series data.

[2171] Specific examples

[2172] Step 1:

[2173] The server places a camera on the desk where the craftsman is working and adjusts it to the optimal angle.

[2174] Step 2:

[2175] The server begins to collect video footage of the craftsman shaping the tea bowl and shape data obtained by the sensor in real time.

[2176] Step 3:

[2177] The server denoises the collected video data, divides it into frames, and normalizes the sensor data to create time-series data.

[2178] Generative AI learning

[2179] Technical Data Learning

[2180] Subject: Server

[2181] Step 1:

[2182] The server inputs pre-processed technical data into the generative AI model.

[2183] Step 2:

[2184] The server begins learning the craftsmanship of generative AI and trains iteratively.

[2185] Step 3:

[2186] The server stores the results learned by the generative AI in a database and manages them in a reusable format.

[2187] Specific examples

[2188] Step 1:

[2189] The server inputs preprocessed video data of the craftsman shaping the tea bowl into the generation AI.

[2190] Step 2:

[2191] The server uses generative AI to repeatedly train itself on data to learn things like hand movements and the shape of the vessel.

[2192] Step 3:

[2193] The server stores the learning results in a database and adds metadata (learning date and time, data size, etc.).

[2194] Data analysis and new proposals

[2195] Trend data collection and analysis

[2196] Subject: Data Analysis AI

[2197] Step 1:

[2198] Data analysis AI collects trend data from social media, fashion sites, market reports, etc.

[2199] Step 2:

[2200] Data analysis AI analyzes collected trend data, identifies major themes and styles, and performs clustering.

[2201] Step 3:

[2202] The data analysis AI generates new proposals based on the technical data learned by the generation AI and the results of trend analysis.

[2203] Specific examples

[2204] Step 1:

[2205] Data analysis AI collects the latest tea utensil design and color trends from the internet.

[2206] Step 2:

[2207] Data analysis AI analyzes collected trend data to identify popular designs and color combinations.

[2208] Step 3:

[2209] The data analysis AI combines the technical data of the craftsmen learned by the generation AI to propose new tea bowl designs.

[2210] Emotion engine combination and feedback

[2211] Generating and Evaluating New Proposals

[2212] Subject: Server

[2213] Step 1:

[2214] The server presents new proposals to the craftsman and simultaneously collects the craftsman's emotional data through cameras and microphones.

[2215] Step 2:

[2216] The emotion engine analyzes collected facial expression data and voice tone to recognize the emotions of the craftsman.

[2217] Step 3:

[2218] The server records the craftsman's emotional response to the proposal as analytical data and stores this data as feedback.

[2219] Specific examples

[2220] Step 1:

[2221] The server shows the new tea bowl design to the craftsman and collects the craftsman's emotional responses (facial expressions, tone of voice) in real time using a camera and microphone.

[2222] Step 2:

[2223] The emotion engine analyzes the craftsman's smile, exclamation of surprise, etc. to identify his / her emotions.

[2224] Step 3:

[2225] The server stores the analyzed emotion data as feedback data for the proposal and uses it to generate the next proposal.

[2226] Gathering feedback and improving the system

[2227] Subject: Server

[2228] Step 1:

[2229] The server organizes the collected feedback data and stores it in a database.

[2230] Step 2:

[2231] The server improves the generative AI and data analysis AI models based on the collected feedback.

[2232] Step 3:

[2233] The server uses the improved model to generate the next proposal, improving the accuracy of the system.

[2234] Specific examples

[2235] Step 1:

[2236] The server organizes the feedback data and emotion data from the craftsmen and stores them in a database.

[2237] Step 2:

[2238] The server adjusts the algorithms of the generative AI and data analysis AI based on the collected feedback and improves the model.

[2239] Step 3:

[2240] The server will propose the next bowl design based on the improved model, improving its accuracy.

[2241] Example 2

[2242] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2243] Preserving and passing on traditional craftsmanship is becoming increasingly difficult as technology becomes more advanced. Furthermore, adapting to modern market trends requires new proposals that take into account not only the craftsman's skills but also the latest market trends. Furthermore, to improve the accuracy of proposals, it is necessary to incorporate not only the craftsman's technical feedback but also their emotional reactions. However, it was difficult to achieve these comprehensively with conventional systems.

[2244] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a camera and sensor device means for collecting technical data of craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generative AI model for learning, a means for saving the learning results of the generative AI model in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generative AI model and the trend data analyzed by the data analysis AI means, a means for feeding back the generated proposals to the craftsmen and analyzing the craftsmen's emotions in real time using an emotion engine, and a means for improving the generative AI model and the model of the data analysis AI means based on the collected feedback. This makes it possible to realize an advanced feedback system that precisely preserves the craftsmen's skills, generates new technical proposals that respond to modern trends, and further reflects the craftsmen's emotional reactions.

[2245] A "camera" is a device that records the craftsman's actions and working environment as video data.

[2246] A "sensor device" is a device that measures physical information (such as temperature and shape) in a craftsman's working environment and collects it as data.

[2247] "Preprocessing" is the process of removing noise from collected technical data and converting it into an analyzable form.

[2248] A "generative AI model" is an artificial intelligence model that learns preprocessed technical data and analyzes and stores the movement patterns and techniques of craftsmen.

[2249] A "database" is a data storage system for systematically storing the learning results of a generative AI model.

[2250] "Data Analysis AI Method" is an artificial intelligence system that collects and analyzes trend data on the Internet to identify current market trends.

[2251] The "emotion engine" is a system that analyzes the facial expressions and tone of voice of craftsmen and recognizes their emotions in real time.

[2252] "Feedback" is the process of collecting artisans' technical and emotional reactions to new proposals.

[2253] "Model refinement" is the process of adjusting the algorithms of generative AI models and data analysis AI methods based on collected feedback data.

[2254] "New proposals" are proposals for new technologies and designs that are generated by combining data analyzed by generative AI models and data analysis AI means.

[2255] MODE FOR CARRYING OUT THE INVENTION

[2256] System Overview

[2257] The system aims to preserve and pass on artisanal techniques and is a comprehensive system that includes cameras and sensor devices, generative AI models, data analysis AI methods, databases, and an emotion engine. This system enables more accurate proposals and system improvements, including the emotional feedback of artisans on new designs and technical proposals.

[2258] Hardware and software used

[2259] Hardware

[2260] Camera: Used to record the craftsman's movements and working environment as video data.

[2261] Sensor device: Used to measure and collect data such as changes in shape and temperature during work.

[2262] Cloud storage: Used to store collected data.

[2263] software

[2264] Generative AI model: Learns from artisan technical data and uses it to generate new suggestions.

[2265] Data analysis AI means: Used to analyze trend data on the Internet.

[2266] Emotion engine: Used to analyze the emotions of craftsmen in real time.

[2267] Database: Used to store the learning results and feedback data of the generative AI model.

[2268] System processing flow

[2269] 1. Data collection: The server installs cameras and sensor devices in the space where the craftsman works, which monitors and records the craftsman's movements and working environment in real time. This information is stored in cloud storage.

[2270] Example: A craftsman creating a tea bowl is filmed with a camera, and a sensor device records the shape and temperature of the bowl.

[2271] 2. Data Preprocessing: The server cleanses the collected data and converts it into a format that the generative AI model can understand, removing noise and making the data analyzable.

[2272] Example: Cutting unnecessary scenes from captured footage and removing outliers in temperature data.

[2273] 3. Learning by generative AI: The server inputs the preprocessed data into a generative AI model, which learns the movement patterns and techniques of the craftsman. The learning results are stored in a database.

[2274] Example: AI learns how a craftsman moves his hands and uses tools.

[2275] 4. Trend data collection and analysis: Data analysis AI tools collect and analyze the latest trend data from the Internet, thereby understanding current market trends.

[2276] Example: Identify popular designs and color combinations based on data collected from social media and fashion sites.

[2277] 5. Generate new proposals: The server combines the data from the generative AI model and the data analysis AI method to generate new proposals, which are then fed back to the craftsman.

[2278] Example: The newly generated tea bowl design is displayed on the craftsman's device.

[2279] 6. Emotion engine analysis: Analyze the emotions of the craftsmen who receive the proposal in real time and collect their feedback. Analyze facial expressions and tone of voice through cameras and microphones.

[2280] Example: The emotion engine analyzes the happiness and surprise of a craftsman when he sees a new design.

[2281] 7. Feedback collection and system improvement: The server will improve the generative AI model and data analysis AI means based on the collected feedback data and reflect this in the next proposal.

[2282] Example: A craftsman prototypes a new tea bowl design and reports his or her impressions to the server. This data is used to retrain the AI ​​model.

[2283] Prompt Sentence Examples

[2284] "Describe a system for analyzing video data of the traditional tea bowl making process and generating new design proposals that take into account current trends. Also, explain how you incorporate the artisan's emotional response to the proposals."

[2285] This system can learn and store traditional artisan techniques as digital data, generate new proposals that match modern trends, and comprehensively incorporate the user's emotional feedback. This allows for the preservation and evolution of artisan techniques, and enables advanced proposals that match the user's preferences and emotions.

[2286] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2287] Step 1:

[2288] Installation of cameras and sensor devices

[2289] Subject: Server

[2290] Description:

[2291] The server installs cameras and sensor devices in the space where the craftsman works, setting the cameras at the appropriate positions and angles and placing the sensors at the appropriate work locations.

[2292] input:

[2293] Camera and sensor devices.

[2294] output:

[2295] You are now ready to record the craftsman's movements and working environment.

[2296] Specific behavior:

[2297] The server remotely adjusts the focus and angle of the camera via the network, and places sensor devices around the work object.

[2298] Step 2:

[2299] Data collection

[2300] Subject: Server

[2301] Description:

[2302] The server collects real-time data on the worker's movements and working environment through cameras and sensor devices, and this data is stored in cloud storage.

[2303] input:

[2304] Craftsman behavior and working environment.

[2305] output:

[2306] Video data and environmental data are stored in cloud storage.

[2307] Specific behavior:

[2308] As the craftsman shapes the tea bowl, the camera captures his or her hand movements, and the sensor device measures the shape and temperature and sends the data to a server.

[2309] Step 3:

[2310] Data Preprocessing

[2311] Subject: Server

[2312] Description:

[2313] The server cleanses the collected data and converts it into an analyzable format, which involves removing noise and converting the data format.

[2314] input:

[2315] Collected video and environmental data.

[2316] output:

[2317] Cleansed, parseable data.

[2318] Specific behavior:

[2319] The server denoises the collected images, cuts out unnecessary parts, removes outliers from the sensor data, and converts them into standard formats (e.g., CSV or PNG).

[2320] Step 4:

[2321] Generative AI learning

[2322] Subject: Server

[2323] Description:

[2324] The server inputs the preprocessed data into a generative AI model to learn the craftsman's technical patterns, and the learning results are stored in a database.

[2325] input:

[2326] Preprocessed data.

[2327] output:

[2328] Technical data learned by generative AI models.

[2329] Specific behavior:

[2330] The server inputs preprocessed video and sensor data into a generative AI model, which then learns the patterns of the craftsman's hand movements and techniques. The learning results are stored in a database.

[2331] Step 5:

[2332] Trend data collection and analysis

[2333] Subject: Data Analysis AI

[2334] Description:

[2335] Data analysis AI collects the latest trend data from the internet and analyzes it, and the analysis results are used to generate new proposals.

[2336] input:

[2337] Trending data on the internet.

[2338] output:

[2339] Analyzed trend data.

[2340] Specific behavior:

[2341] Data analysis AI searches the web using specific keywords (for example, "handmade tea bowl trends") and analyzes the collected data to identify popular designs and color combinations.

[2342] Step 6:

[2343] Generate a new proposal

[2344] Subject: Server

[2345] Description:

[2346] The server combines the generative AI model with the data generated by the data analysis AI to generate new suggestions, which are then fed back to the craftsman.

[2347] input:

[2348] Generative AI model learning results and analyzed trend data.

[2349] output:

[2350] New technology proposal.

[2351] Specific behavior:

[2352] The server combines the technical data obtained from the generation AI model with the trend information obtained from the data analysis AI to generate a new tea bowl design and send it to the craftsman's device.

[2353] Step 7:

[2354] Emotion Engine Analysis

[2355] Subject: Server

[2356] Description:

[2357] The server uses an emotion engine to analyze the craftsman's emotions in real time, identifying the craftsman's emotions based on data obtained through cameras and microphones.

[2358] input:

[2359] Real-time data from cameras and microphones.

[2360] output:

[2361] Analyzed emotion data.

[2362] Specific behavior:

[2363] As the craftsman reviews the design of a new tea bowl, a camera captures his facial expressions and a microphone records his tone of voice. The server uses an emotion engine to analyze this data and identify the craftsman's emotions.

[2364] Step 8:

[2365] Gathering feedback and improving the system

[2366] Subject: Server

[2367] Description:

[2368] The server uses the collected feedback to improve the generative AI model and data analysis AI, which will improve the accuracy of the next proposal.

[2369] input:

[2370] Technical and emotional feedback data from artisans.

[2371] output:

[2372] Improved generative AI models and data analysis AI.

[2373] Specific behavior:

[2374] The craftsman prototypes the new tea bowl design and reports his / her opinions and impressions to the server, which then retrains the generative AI model and data analysis AI method based on the collected feedback data and reflects it in the next proposal.

[2375] (Application example 2)

[2376] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2377] Conventional autonomous vehicles have been unable to fully utilize the driver's emotional state and real-time environmental information to improve driving comfort and safety, and lack the means to effectively collect and analyze this information and make improvements based on system feedback.

[2378] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2379] In this invention, the server includes a camera and sensor means for collecting technical data from craftsmen, a means for preprocessing the collected technical data and converting it into an analyzable format, a means for inputting the converted data into a generation AI for learning, a means for storing the learning results of the generation AI in a database, a data analysis AI means for collecting and analyzing trend data, a means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI, a means for feeding back the generated proposals to craftsmen and collecting their evaluations, a means for improving the models of the generation AI and the data analysis AI based on the collected feedback, a means for optimizing driving patterns and routes to improve the comfort and safety of the other-type vehicle while driving, a means for controlling driving based on the optimized driving patterns and routes, an emotion engine for analyzing the emotional state of the driver, and a means for collecting feedback and improving the system based on the emotional state analyzed by the emotion engine. This makes it possible to effectively utilize the real-time environment and the driver's emotional state while driving, thereby improving comfort and safety.

[2380] "Camera and sensor means" refers to devices that photograph and measure the driver's condition and driving environment in real time.

[2381] "Means of preprocessing and converting into an analyzable format" refers to the process of converting collected data into a format that can be analyzed by AI.

[2382] "Means of inputting data into a generative AI and having it learn" refers to the process of inputting preprocessed data into a generative AI model and having it learn.

[2383] "Means for saving in a database" refers to a database system for recording and saving learning results.

[2384] "Data analysis AI means for collecting and analyzing trend data" is an artificial intelligence system for collecting and analyzing trend information on the Internet.

[2385] The "means of generating new proposals" is the process of combining the data learned by the generation AI with the trend data analyzed by the data analysis AI to create new proposals.

[2386] "Feedback and evaluation collection measures" are the processes of presenting new proposals to drivers and collecting their reactions and evaluations.

[2387] "Means to improve generative and analytical AI models" refers to the process of improving AI models based on collected feedback to improve the accuracy of future recommendations.

[2388] "Means for optimizing driving patterns and routes" refers to the process of calculating optimal driving patterns and routes to improve the comfort and safety of the vehicle while driving.

[2389] "Means for controlling driving" refers to a system that controls the vehicle based on optimized driving patterns and routes.

[2390] The "emotion engine for analyzing the driver's emotional state" is a system that uses cameras and microphones to analyze the driver's facial expressions and tone of voice to recognize their emotions.

[2391] "Means for collecting feedback and improving the system" refers to the process of collecting feedback based on the driver's emotional state and improving the overall system based on that feedback.

[2392] This invention provides a system that collects, analyzes, and feeds back various data to improve the comfort and safety of automobiles while driving. Specific methods and processes for realizing this system are described below.

[2393] System Configuration

[2394] The system consists of the following main components:

[2395] 1. Camera and sensor means:

[2396] This is a device that captures and measures the driver's condition and driving environment in real time. Specifically, it includes cameras and microphones installed inside the vehicle and various sensors that monitor the external environment.

[2397] 2. Data preprocessing methods:

[2398] This software preprocesses the collected data and converts it into an analyzable format, for example by dividing the collected video data into an appropriate number of frames, removing noise, and normalizing it.

[2399] 3. Generative AI Model:

[2400] This is an artificial intelligence model that inputs the preprocessed data and performs learning, thereby learning data related to the driver's behavioral patterns and driving environment.

[2401] 4. Database:

[2402] This is a database system for recording and storing the learning results of the generation AI. This system stores environmental data during driving, the driver's emotional state, traffic information, etc.

[2403] 5. Data analysis AI methods:

[2404] This is an AI system for collecting and analyzing trend data, such as traffic information, weather data, and social media trend information from the Internet.

[2405] 6. New proposal generation methods:

[2406] This is the process of combining the data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new suggestions, which will then suggest optimal driving patterns and routes for the driver.

[2407] 7. Feedback and evaluation collection methods:

[2408] New suggestions are presented to drivers and their reactions and evaluations are collected, for example, by presenting the suggestions via an in-car display or smartphone.

[2409] 8. Model refinement methods:

[2410] This is the process of improving the generative AI and data analysis AI models based on the collected feedback, which will improve the accuracy of the next proposal.

[2411] 9. Driving pattern and route optimization measures:

[2412] It is an AI system that calculates optimal driving patterns and routes to improve vehicle comfort and safety while driving.

[2413] 10. Travel control means:

[2414] This is a system for controlling vehicles based on optimized driving patterns and routes. Autonomous driving systems and actuators are used for actual vehicle control.

[2415] 11. Emotion Engine:

[2416] This system uses cameras and microphones to analyze the driver's facial expressions and tone of voice to recognize their emotions, and is used to grasp the driver's fatigue and state of tension in real time.

[2417] 12. Feedback collection and system improvement methods:

[2418] It is a process of collecting feedback based on the driver's emotional state and using that to improve the overall system.

[2419] Specific examples

[2420] For example, when a driver is driving on the highway, the emotion engine analyzes the driver's facial expressions to detect signs of fatigue. This data is analyzed by a generative AI model and used to optimize a safe driving route. The optimal route is calculated and displayed on the vehicle's display. Driver feedback is also collected and reflected in future recommendations.

[2421] Prompt Sentence Examples

[2422] Below are some example prompts that can be input to the generative AI model in this system:

[2423] "What facial expressions do drivers have while driving that make you feel safer? And vice versa?"

[2424] The above configuration makes it possible to effectively improve comfort and safety during driving.

[2425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2426] Step 1:

[2427] The server monitors the driver's condition and driving environment in real time using cameras and sensors installed in the vehicle.

[2428] Input: Video data from cameras and sensors and environmental data

[2429] Data processing: Video data is divided into frames, and noise is removed and normalized.

[2430] Output: Preprocessed data (video frames and environmental data)

[2431] Step 2:

[2432] The server inputs the preprocessed data into a generative AI model, which learns about the driver's behavioral patterns and driving environment.

[2433] Input: Preprocessed data (video frames and environmental data)

[2434] Data Computation: Learning with Generative AI Models

[2435] Output: Learning result data (driving patterns and environmental recognition data)

[2436] Step 3:

[2437] The server stores the learning result data in a database.

[2438] Input: Learning result data obtained from the generative AI model

[2439] Data processing: Converting data into a format that can be saved in a database

[2440] Output: Learning result data stored in a database

[2441] Step 4:

[2442] The server collects relevant information from the internet using data analysis AI means to collect and analyze trend data.

[2443] Input: Internet traffic information, weather data, social media trend information

[2444] Data calculation: Analyze collected data and extract important trend information

[2445] Output: Analyzed trend data

[2446] Step 5:

[2447] The server combines the technical data learned by the generation AI with the trend data analyzed by the data analysis AI to generate new proposals.

[2448] Input: Training result data and trend data

[2449] Data arithmetic: Combining data to generate new suggestions

[2450] Output: New proposed data (optimal driving patterns and routes)

[2451] Step 6:

[2452] The terminal provides feedback on new proposals to the driver and collects their evaluations.

[2453] Input: New proposal data

[2454] Specific operation: Displaying suggestions on the in-car display or smartphone

[2455] Output: Driver feedback data

[2456] Step 7:

[2457] The server refines its generative AI and data analysis AI models based on the collected feedback.

[2458] Input: Driver feedback data

[2459] Data calculation: Analyze feedback data and adjust AI models

[2460] Output: Improved generative AI and data analysis AI models

[2461] Step 8:

[2462] The server uses the improved AI model to optimize the vehicle's driving patterns and routes while in operation.

[2463] Input: Improved generative AI and data analysis AI models

[2464] Data calculation: Calculates optimal driving patterns and routes

[2465] Output: Optimized driving patterns and route data

[2466] Step 9:

[2467] The terminal controls the vehicle based on the optimized driving pattern and route.

[2468] Input: Optimized driving pattern and route data

[2469] Specific operation: Controlling the driving route using an autonomous driving system and actuators

[2470] Output: Control data for the vehicle during operation

[2471] Step 10:

[2472] The server collects and analyzes data from cameras and microphones using an emotion engine to analyze the driver's emotional state.

[2473] Input: Camera video and audio data

[2474] Data processing: Emotional state analysis (facial expression recognition and voice tone analysis)

[2475] Output: Driver's emotional state data

[2476] Step 11:

[2477] The server collects feedback based on the emotional state analyzed by the emotion engine and improves the system.

[2478] Input: Driver's emotional state data

[2479] Data calculation: Analyze emotional state data and improve the entire system

[2480] Output: Improved system feedback data

[2481] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2482] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2483] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2484] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2485] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2486] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2487] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2488] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2489] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2490] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2491] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2492] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the prese...

Claims

1. camera and sensor means for collecting craftsmanship data; means for pre-processing the collected technical data into an analyzable format; A means for inputting the converted data into a generation AI to make it learn; A means for storing the learning results of the generation AI in a database; Data analysis AI tools for collecting and analyzing trend data, A means for generating new proposals by combining the technical data learned by the generation AI and the trend data analyzed by the data analysis AI; A means for feeding back the generated suggestions to craftsmen and collecting their evaluations; means for improving the generative AI and data analysis AI models based on the collected feedback; A system including:

2. The system of claim 1 , which uses generative AI and data analytical AI to generate new suggestions.

3. 2. The system according to claim 1, wherein the system is improved through learning, analysis, and feedback of craftsman's technical data and trend data.

Images