System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting data related to the craft technique, a means for analyzing the collected craft technique data in a multi-faceted manner, a means for generating a new product proposal utilizing the craft technique based on the analysis result, a means for proposing an appropriate cooperation partner to the generated new product proposal, a means for displaying the proposal result on a user terminal, a means for collecting feedback from the user, and a means for improving the system based on the collected feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] It is important to pass on Japan's traditional craft techniques and modern artisanal skills to the next generation and maximize their value. However, converting these techniques into new products that meet modern market needs and finding appropriate collaboration partners is difficult, time-consuming, and costly. Therefore, appropriate methods are needed to efficiently utilize these techniques and maximize their value. Furthermore, it is also necessary to effectively collect user feedback and improve the accuracy of the system. [Means for solving the problem]

[0005] This invention is a system that includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas that utilize craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user's terminal, means for collecting feedback from users, and means for improving the system based on the collected feedback.This makes it possible to efficiently visualize the value of craft techniques and offer them to the market as new product value.Furthermore, by appropriately selecting collaboration partners and improving the system based on feedback, more accurate proposals can be made.

[0006] "Craftsmanship techniques" is a general term for manufacturing techniques and related knowledge based on traditional Japanese crafts and modern artisan techniques.

[0007] "Data collection means" refers to the processes and devices that capture and store information about craft techniques in a database.

[0008] "Means for multifaceted data analysis" refers to the processes and devices that evaluate collected craft technology data from various perspectives and extract value.

[0009] "Means for generating new product ideas" refers to the process and devices for creating new product ideas based on the analysis results.

[0010] The "means for proposing collaboration partners" refers to the process and device for selecting and proposing the most suitable collaborating companies or individuals for the generated new product ideas.

[0011] The "means for displaying proposal results" refers to a process and device for displaying new product proposals and partner candidates sent from the server on a user terminal.

[0012] "Means for collecting feedback" refers to the process and devices for receiving opinions and ratings from users and incorporating them into the system.

[0013] "Means for improving the system" refers to the processes and devices used to improve the system's functionality and accuracy based on collected feedback. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] As an embodiment of the present invention, the processing flow of the entire system will be explained in natural language below, along with the roles of each entity, namely, server, terminal, and user, and specific examples.

[0036] 1. Collection of technical data

[0037] The server collects data about craft techniques. Through an internal database or external API, the server obtains technical information, manufacturing processes, materials used, historical background, and information about the artisans involved.

[0038] Examples:

[0039] The server collects technical information about "ceramics" from various databases, including the ceramic manufacturing process, the types of clay and glazes used, and the history of famous artisans and their works.

[0040] 2. Data analysis and visualization

[0041] The server analyzes the collected technical data from multiple angles. It cleanses the data and extracts specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts to visualize the analysis results.

[0042] Examples:

[0043] The server analyzes the ceramics data and identifies their strengths as durability, aesthetic value, and rare manufacturing techniques, and then summarizes these characteristics in a radar chart.

[0044] 3. New product idea generation

[0045] The server generates new product ideas based on the analysis results, using an algorithm that takes into account market trends and consumer needs to propose new product ideas.

[0046] Examples:

[0047] The server generates design proposals for a new set of tableware using ceramic techniques, based on market data that reflects the desire for simple, contemporary designs.

[0048] 4. Matching collaboration partners

[0049] The server searches a database for potential partners best suited to a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[0050] Examples:

[0051] With the aim of mass-producing a new ceramic tableware set, the server compiles a list of optimal partners from a database of ceramic manufacturers and designers both in Japan and overseas.

[0052] 5. Presentation of proposed results

[0053] The terminal displays the new product ideas and partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[0054] Examples:

[0055] The device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[0056] 6. Feedback and Improvement

[0057] Users provide feedback to the system, and the server uses that feedback to improve the system's accuracy. Users input their opinions about proposed ideas and partners, and the server analyzes them to identify areas for improvement.

[0058] Examples:

[0059] Users can send feedback to the server, such as "I want more design variations." The server analyzes this feedback and improves the algorithm to generate more diverse design proposals next time.

[0060] This will enable us to maximize the use of traditional Japanese craftsmanship and modern artisan skills, create new product value, and find suitable collaboration partners.In addition, we will be able to continuously improve the system through feedback from users and make better proposals.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The server connects to an internal database or external API to collect information about the craft techniques, including the specific process of the technique, the materials used, historical background, and information about the artisans involved.

[0064] Specific operation:

[0065] The server accesses a database on "ceramics" and retrieves information on the manufacturing process, material characteristics, historical background, and related craftsmen.

[0066] Step 2:

[0067] The server cleanses the collected craft technology data, filling in missing values ​​and removing outliers.

[0068] Specific operation:

[0069] The server organizes the acquired ceramic data, detects incomplete data and outliers, and completes them.

[0070] Step 3:

[0071] The server analyzes the data from multiple angles and extracts the strengths, weaknesses, rarity, and points of differentiation of the craftsmanship from competitors.

[0072] Specific operation:

[0073] The server runs the ceramic data through machine learning algorithms to assess its durability, aesthetic value, rarity of manufacturing techniques, and other factors, identifying its strengths and weaknesses.

[0074] Step 4:

[0075] The server visualizes the analysis results and generates graphs and charts.

[0076] Specific operation:

[0077] The server displays the strengths and weaknesses of ceramics in the form of radar charts, heat maps, and other formats.

[0078] Step 5:

[0079] The server generates new product ideas taking into account market trends and consumer needs.

[0080] Specific operation:

[0081] The server analyzes market data and generates new product ideas, such as a "modern design ceramic tableware set."

[0082] Step 6:

[0083] The server selects and proposes the most suitable collaboration partner for the new product idea.

[0084] Specific operation:

[0085] The server searches a database of domestic and international ceramic manufacturers and designers and lists suitable partners to manufacture the new ceramic tableware set.

[0086] Step 7:

[0087] The terminal displays the new product proposals and collaboration partner candidates sent from the server to the user.

[0088] Specific operation:

[0089] The terminal displays a design proposal for a new ceramic tableware set and a list of recommended partners on a user interface.

[0090] Step 8:

[0091] The user inputs feedback about the proposed ideas and partners and sends it to the server.

[0092] Specific operation:

[0093] The user enters feedback on the device, such as "I would like more design variations," and presses the send button.

[0094] Step 9:

[0095] The server analyzes the received feedback and identifies improvements for the next implementation process.

[0096] Specific operation:

[0097] The server analyzes the text of user feedback and determines that the algorithm needs to be improved to increase design variation.

[0098] Step 10:

[0099] The server updates the system's algorithms and database based on the analysis results, improving the accuracy of the entire system.

[0100] Specific operation:

[0101] Based on the feedback, the server improves the machine learning algorithm and updates the model to generate diverse design proposals.

[0102] Example 1

[0103] 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."

[0104] In the conventional product development process for craftsmanship, data collection and analysis were time-consuming, making it difficult to efficiently generate new product ideas and propose appropriate collaboration partners. There was also a lack of mechanisms for appropriately incorporating user feedback and improving the system. This limited the speed and quality of product development.

[0105] 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.

[0106] In this invention, the server includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas utilizing craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for collecting user feedback, means for improving the system based on the collected feedback, means for acquiring data on craft techniques using an external API, means for visually visualizing the analysis results, and means for using a generative AI model when generating new product ideas. This makes it possible to efficiently generate new product ideas based on craft techniques and propose appropriate collaboration partners, and to continuously improve the system by utilizing user feedback.

[0107] "Craftsmanship" refers to crafts made using traditional methods and techniques, as well as related manufacturing processes, materials and designs.

[0108] "Means of collecting data" refers to devices and systems for obtaining information related to craft techniques from various databases and external APIs.

[0109] "Means for analyzing data from multiple perspectives" refers to techniques and methods for analyzing collected data from various perspectives and extracting specific information.

[0110] "Means for generating new product ideas" refers to devices and methods for devising new crafts and their applied products based on the results of the analysis.

[0111] "Means for proposing collaborative partners" refers to devices and systems for selecting and proposing the most suitable collaborating companies and craftsmen to realize new product ideas.

[0112] "Means for displaying the proposal results on the user terminal" refers to a device or system for visually showing the proposal contents sent from the server to the user.

[0113] "Means for collecting user feedback" refers to a device or system for obtaining opinions and ratings provided by users.

[0114] "Means for improving the system based on feedback" refers to techniques and methods for analyzing collected feedback and improving the performance and accuracy of the system.

[0115] "Means of obtaining data using external APIs" refers to programs and systems for obtaining information from external databases and services via the Internet.

[0116] "Visual visualization means" refers to devices and technologies for converting and displaying the results of data analysis in a visual format such as a graph or chart.

[0117] "Means for using generative AI models" refers to devices or programs that utilize models using artificial intelligence technology to generate new ideas and concepts.

[0118] An embodiment of the present invention relates to a system that efficiently generates ideas for new products based on craft techniques and proposes collaboration partners, and realizes continuous improvement of the system based on user feedback.

[0119] Technical data collection

[0120] The server collects data about craft techniques, using internal databases and external APIs to obtain technical information, manufacturing processes, materials used, historical background, and artisan information.

[0121] For example, the server collects technical information about "ceramics" from various databases, including the ceramic manufacturing process, the types of clay and glazes used, and the history of famous artisans and their works.

[0122] Data Analysis and Visualization

[0123] We analyze the technical data collected by the server from multiple angles, cleanse the data, extract specific strengths, weaknesses, rarity, and points of differentiation from competitors, and generate visual graphs and charts to visualize the analysis results.

[0124] As a specific example, the server analyzes data on ceramics, identifies its strengths as durability, aesthetic value, and rare manufacturing techniques, and summarizes these in a radar chart for each characteristic.

[0125] Generate new product ideas

[0126] The server generates new product ideas based on the analysis results, using algorithms that take into account market trends and consumer needs, and utilizing generative AI models to propose new product ideas.

[0127] As a concrete example, the server generates design proposals for a new set of tableware using ceramic techniques. Based on market data, the following prompt is used to reflect the desire for a simple, modern design:

[0128] "Please propose a new design for a ceramic tableware set, taking into consideration current market trends."

[0129] Matching collaboration partners

[0130] The server searches a database for the best candidates for collaboration partners for a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[0131] As a concrete example, the server considers mass production of a new ceramic tableware set and lists the most suitable partners from a database of ceramic manufacturers and designers both in Japan and overseas.

[0132] Presentation of proposed results

[0133] The terminal displays the new product ideas and partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[0134] For example, the device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[0135] Feedback and Improvements

[0136] Users provide feedback to the system, and the server uses that feedback to improve the system's accuracy. Users input their opinions about proposed ideas and partners, and the server analyzes them to identify areas for improvement.

[0137] As a concrete example, a user can send feedback to the server such as "I would like more design variations," and the server will analyze this and improve its algorithm to generate more diverse design proposals next time.

[0138] This system will enable the creation of new product value by maximizing the use of traditional Japanese craft techniques and modern artisanal skills, and will enable the efficient search for suitable collaboration partners. Furthermore, the system will be continuously improved through user feedback, enabling the creation of better proposals.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] A server collects data about craft skills.

[0142] Input: The server takes input from internal database queries and request parameters from external APIs.

[0143] Data processing: The server retrieves data from these sources and cleanses it by detecting duplicates and missing information.

[0144] Output: A clean set of craft data is produced.

[0145] Specific operation: The server sends an HTTP request to the specified API endpoint, receives technical information as a response, and issues a SELECT query to extract data from the internal database.

[0146] Step 2:

[0147] The technical data collected by the server is analyzed from multiple perspectives.

[0148] Input: The clean data collected in step 1.

[0149] Data processing: The server uses statistical analysis, text mining techniques, etc. to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors.

[0150] Output: Characteristic data as the analysis result and visualization data based on it are generated.

[0151] Specific operation: The server calls statistical functions to analyze the collected data and generates the results as radar charts and graphs.

[0152] Step 3:

[0153] The server generates new product ideas based on the analysis results.

[0154] Inputs: Analysis results generated in step 2. External data on market trends and consumer needs.

[0155] Data processing: The server uses the generative AI model to generate new product ideas.

[0156] Output: A prototype of the new product idea is generated.

[0157] Specific operation: The server inputs the prompt statement and analysis results into the generative AI model and obtains the output idea data.

[0158] Step 4:

[0159] The server searches for and evaluates potential collaboration partners related to the new product idea.

[0160] Input: Prototype of new product idea generated in step 3. Database of collaboration partners.

[0161] Data processing: Scoring potential partners based on suitability criteria and shortlisting the most suitable partners.

[0162] Output: A list of high-scoring partner candidates is generated.

[0163] What it does: The server queries internal and external partner databases and applies a rating algorithm to generate a score.

[0164] Step 5:

[0165] The terminal displays the new product ideas and partner candidates sent from the server to the user.

[0166] Input: Partner candidate list generated in step 4. Prototype of new product idea.

[0167] Data processing: Visually display information using a GUI.

[0168] Output: Display of design proposals and partner list.

[0169] Specific operation: The device applies the data obtained from the server to the GUI components and renders it on the screen.

[0170] Step 6:

[0171] The user provides feedback to the system.

[0172] Input: Ratings and opinions on new product ideas and potential partners.

[0173] Data processing: Collect feedback and send it to the server.

[0174] Output: Sending feedback data.

[0175] Specific behavior: A user enters their opinion into the feedback form and clicks the submit button, which sends an HTTP POST request to the server.

[0176] Step 7:

[0177] The server analyzes user feedback to improve the accuracy of the system.

[0178] Input: Feedback data collected in step 6.

[0179] Data processing: Analyzing feedback data to identify areas for improvement in algorithms and models.

[0180] Output: Improved algorithms and models.

[0181] Specific operation: The server analyzes the feedback data using natural language processing technology and adjusts and optimizes the generative AI model and related algorithms based on the insights gained.

[0182] (Application example 1)

[0183] 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."

[0184] Conventional methods of providing information about crafts make it difficult for customers to learn detailed technical information or the manufacturing background of crafts. Furthermore, developing new products and selecting appropriate collaboration partners are not easy, and there is a lack of mechanisms for incorporating user feedback into the system. Furthermore, the interactive information provided to customers in craft displays in physical stores is limited, creating a need for an improved customer experience.

[0185] 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.

[0186] In this invention, the server includes a means for collecting data on craft techniques, a means for multifaceted analysis of the collected craft technique data, and a means for generating new product ideas that utilize craft techniques based on the analysis results. This enables the provision of detailed technical information on crafts, the development of new products, and the selection of collaboration partners. Furthermore, by including a means for visually displaying craft information using augmented reality, the customer experience in physical stores can be improved.

[0187] "Craftsmanship" refers to the techniques used by artisans to create artistic products by hand using traditional methods and techniques.

[0188] "Data collection means" refers to the mechanism for obtaining necessary information from internal databases related to craft techniques and external APIs.

[0189] "Data analysis means" refers to a system for cleansing collected craft technology data and analyzing it from multiple perspectives.

[0190] "New product idea generation means" refers to a system for proposing new crafts and their designs based on analyzed data.

[0191] The "means for proposing collaboration partners" refers to a mechanism for proposing optimal manufacturing partners or collaborators for the new product ideas that have been generated.

[0192] "User terminal display means" refers to a mechanism for displaying the proposal results and related information on a device that is directly operated by the user.

[0193] "Feedback collection means" refers to a mechanism for collecting user opinions and requests into the system.

[0194] "System improvement measures" refer to mechanisms for improving the system's algorithms and functions based on collected feedback.

[0195] "Augmented reality display means" refers to a mechanism for visually displaying additional information about real-world artifacts via a smartphone or dedicated device.

[0196] As an embodiment of the present invention, a processing flow of a new craft product suggestion system will be described.

[0197] Overall system configuration

[0198] This system mainly consists of three entities: a server, a terminal, and a user. The server collects and analyzes data, generates suggestions, and analyzes feedback. The terminal provides information to the user and collects feedback. It also uses augmented reality (AR) to visually display information about real crafts.

[0199] Server Roles

[0200] 1. Collection of technical data

[0201] The server primarily collects data about craft techniques through internal databases and external APIs. This data includes information about the manufacturing process, materials, historical background, and the artisans involved. For example, it collects technical information about ceramics, including details about the manufacturing process, clays, and glazes used.

[0202] 2. Data analysis and visualization

[0203] The server then cleanses the collected data and performs a multifaceted analysis, extracting strengths, weaknesses, rarity, and points of differentiation from competitors, and presenting these in visual formats such as radar charts. This analysis identifies characteristics such as the durability, aesthetic value, and rare manufacturing techniques of ceramics, for example.

[0204] 3. New product idea generation

[0205] Based on the analysis results, the server generates new product ideas, taking into account market trends and consumer needs through an algorithm, suggesting new product ideas such as a tableware set with a simple, modern design.

[0206] 4. Matching collaboration partners

[0207] The server searches its database for the optimal partner for the new product idea and proposes it, using criteria such as technical capabilities and past performance as criteria. For example, it could create a list of optimal partners from ceramic manufacturers and designers both in Japan and overseas.

[0208] Device Role

[0209] 1. Displaying the proposed results

[0210] The terminal displays new product ideas and potential collaboration partners sent from the server in a visually easy-to-understand format to the user. For example, it displays a design idea for a new ceramic tableware set and a list of recommended partners.

[0211] 2. Augmented reality features

[0212] The device is equipped with an AR function, allowing users to visually display product information, manufacturing process, and artisan information by pointing the camera at an actual craft item.

[0213] User Roles

[0214] 1. Providing Feedback

[0215] Users can provide their opinions and requests regarding the displayed suggestions. For example, they can send feedback such as "I would like more design variations."

[0216] System Improvement

[0217] The server collects and analyzes user feedback to improve the system's algorithms and functions, and also incorporates the collected feedback into future proposals.

[0218] Hardware and software used

[0219] The system uses the following hardware and software:

[0220] Hardware: Server, smartphone (or tablet)

[0221] Software: Flask (web framework), SQLite (database), NLTK (text analysis)

[0222] Examples and prompts

[0223] (Example)

[0224] User example 1: A customer visiting a physical store wants to learn about the manufacturing techniques behind a new tea bowl. By pointing their smartphone camera at the bowl, AR will display background information about the manufacturing process and the craftsman.

[0225] User example 2: When a user enters their idea for tableware using a durable and rare glaze into the app, new product ideas and collaboration partners based on that idea are displayed.

[0226] (Example of a prompt)

[0227] "Generate new ceramic design ideas. The target audience is young people in their 20s who want simple, modern designs."

[0228] "Please suggest improvements to increase product variety based on the feedback below. Feedback: I would like more design variations."

[0229] The above is a detailed embodiment of the present invention. This system makes it possible to propose new products that utilize craft techniques, provide effective information, and improve customer experience.

[0230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0231] Step 1:

[0232] The server collects data about craft techniques. As input, it receives information from external APIs and internal databases. This data includes manufacturing processes, materials, historical background, artisan information, etc. The server retrieves this data and stores it in the internal database. The output is the collected raw data.

[0233] Step 2:

[0234] The data collected by the server is cleansed and analyzed from multiple perspectives. The input is the raw data collected in step 1. Data cleansing removes incomplete and duplicate data. The cleansed data is then analyzed using analytical algorithms to extract strengths, weaknesses, rarity, and points of differentiation from competitors. The output is a summary of the analysis results, and visualized data such as radar charts is also generated.

[0235] Step 3:

[0236] The server generates new product ideas based on the analysis results. The input is the analysis results obtained in step 2. A generative AI model is used to generate new product designs and concepts, taking into account market trends and consumer needs. Prompt statements are used to instruct the generative AI model. The output is details of the new product ideas.

[0237] Step 4:

[0238] The server proposes optimal collaboration partners for new product ideas generated by the server. The input is the new product idea generated in step 3. An algorithm that takes into account past performance and technical capabilities is used to search for optimal collaboration partners from a database. The output is a list of candidate collaboration partners.

[0239] Step 5:

[0240] The terminal visually displays the proposal results from the server to the user. The input is the new product idea and list of collaboration partners obtained in step 4. The information is displayed in a format that is easy for the user to understand. For example, a design proposal for a new ceramic tableware set and a list of recommended partners are displayed on the screen. The output is the displayed information.

[0241] Step 6:

[0242] The device displays information about the craft using augmented reality. The input is video data acquired when the user points the smartphone camera at the craft. The device displays detailed information about the craft obtained from the server as AR. For example, if the camera is pointed at an actual tea bowl, the manufacturing process and background information about the craftsman will be displayed on the screen. The output is information displayed using augmented reality.

[0243] Step 7:

[0244] The user enters feedback based on the information provided. The input is the user's opinion or request. For example, the user may send feedback such as "I would like more design variations." The output is the collected feedback data.

[0245] Step 8:

[0246] The server collects user feedback and improves the system. The input is the feedback data collected in step 7. The feedback is analyzed and used as data to improve the system's algorithms and functions, which can then be reflected in the next proposal. The output is improved system settings and algorithms.

[0247] 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.

[0248] As an embodiment of the present invention, the processing flow of the entire system that combines the emotion engine will be explained in natural language below. The roles of each entity, the server, terminal, and user, will be explained along with specific examples.

[0249] 1. Collection of technical data

[0250] The server collects data about craft techniques. Through an internal database or external API, the server obtains technical information, manufacturing processes, materials used, historical background, and information about the artisans involved.

[0251] Examples:

[0252] The server accesses a database on "ceramics" and retrieves information on the manufacturing process, material characteristics, historical background, and associated craftsmen.

[0253] 2. Data analysis and visualization

[0254] The server analyzes the collected technical data from multiple angles. It cleanses the data and extracts specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts to visualize the analysis results.

[0255] Examples:

[0256] The server then applies machine learning algorithms to the ceramic data, assessing its durability, aesthetic value, and the rarity of its manufacturing techniques, to identify its strengths and weaknesses, which are then compiled into a radar chart for each characteristic.

[0257] 3. New product idea generation

[0258] The server generates new product ideas based on the analysis results, using an algorithm that takes into account market trends and consumer needs to propose new product ideas.

[0259] Examples:

[0260] The server generates design proposals for a new set of tableware using ceramic techniques, based on market data that reflects the desire for simple, contemporary designs.

[0261] 4. Matching collaboration partners

[0262] The server searches a database for potential partners best suited to a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[0263] Examples:

[0264] With the aim of mass-producing a new ceramic tableware set, the server compiles a list of optimal partners from a database of domestic and international ceramic manufacturers and designers.

[0265] 5. Presentation of proposed results

[0266] The terminal displays the new product ideas and collaboration partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[0267] Examples:

[0268] The device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[0269] 6. Emotion Recognition by Emotion Engine

[0270] The device recognizes the user's emotion using the emotion engine when the user inputs feedback, and transmits not only the user's feedback but also the emotion information to the server.

[0271] Examples:

[0272] The device analyzes the user's facial expressions and voice to recognize emotions such as "happiness" or "dissatisfaction." When the user gives feedback such as "I'm impressed" about the design of a new tableware set, that emotion is also analyzed.

[0273] 7. Collecting feedback and sentiment data

[0274] The server receives and analyzes the feedback and emotional data sent from the device, thereby understanding the user's true reaction and utilizing it for future suggestions.

[0275] Examples:

[0276] The server analyzes feedback such as "I want more design variations" and feelings of "dissatisfaction" and reflects this in the next new product proposal.

[0277] 8. Continuous improvement of the system

[0278] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[0279] Examples:

[0280] The server implements new algorithms based on data from the emotion engine and makes adjustments to generate better emotion-based product suggestions.

[0281] In this way, by combining an emotion recognition engine, it is possible to make the most of traditional Japanese craft techniques and modern artisan skills to create new product value, as well as to realize a system that makes even more accurate suggestions based on feedback based on the user's emotions.

[0282] The processing flow will be explained below.

[0283] Step 1:

[0284] The server connects to an internal database and external APIs to collect information about craft techniques, including technical information, manufacturing processes, materials used, historical background, and artisan information.

[0285] Specific operation:

[0286] The server retrieves information from a ceramics database about the manufacturing process, the types of clay and glazes used, historical background, and artisans.

[0287] Step 2:

[0288] The server pre-processes the collected craft data, cleansing it, filling in missing values, and removing outliers.

[0289] Specific operation:

[0290] The server cleanses the acquired ceramic data, identifying and completing incomplete data and outliers.

[0291] Step 3:

[0292] The server analyzes the data from multiple angles and applies machine learning algorithms to extract the strengths, weaknesses, and rarity of the craftsmanship, as well as points of differentiation from competitors.

[0293] Specific operation:

[0294] The server analyzes the ceramics' data, assessing their durability, aesthetic value, and the rarity of their manufacturing techniques, and identifies their strengths and weaknesses.

[0295] Step 4:

[0296] The server visualizes the analysis results, generating graphs and charts based on the extracted features and summarizing them in a visually easy-to-understand format.

[0297] Specific operation:

[0298] The server displays the strengths and weaknesses of ceramics in the form of radar charts, heat maps, and other formats.

[0299] Step 5:

[0300] The server generates new product ideas taking into account market trends and consumer needs. Using an algorithm, the server combines collected data with market needs to propose new product ideas.

[0301] Specific operation:

[0302] The server analyzes market data and generates a new product idea: a "modern design ceramic tableware set."

[0303] Step 6:

[0304] The server searches a database for the most suitable partner for a new product idea and proposes it. Suitability is evaluated based on technical capabilities and past performance.

[0305] Specific operation:

[0306] The server searches a database of domestic and international ceramic manufacturers and designers, and lists suitable partners for mass production of new ceramic tableware sets.

[0307] Step 7:

[0308] The terminal displays the new product ideas and collaboration partner candidates sent from the server to the user, and displays the received data in a visually easy-to-understand format.

[0309] Specific operation:

[0310] The terminal displays a design proposal for a new ceramic tableware set and a list of recommended partners on a user interface.

[0311] Step 8:

[0312] The device uses an emotion engine to recognize the user's emotions when the user inputs feedback, analyzes the user's facial expressions and voice, and transmits the emotional information to the server.

[0313] Specific operation:

[0314] When a user inputs feedback such as "I'm happy" about a new ceramic design, the device analyzes the user's facial expression and intonation of the voice to recognize the emotion of "joy."

[0315] Step 9:

[0316] The server receives and analyzes the feedback and emotion data sent from the device, and evaluates new product ideas based on the user's emotions and feedback.

[0317] Specific operation:

[0318] The server analyzes the feedback such as "great design" and the emotion data such as "delight" to ensure that the new design is well-received.

[0319] Step 10:

[0320] The server improves the system based on feedback and emotional data, refining the algorithm and making adjustments to improve the accuracy of the next suggestion.

[0321] Specific operation:

[0322] The server updates the machine learning algorithm based on the feedback, including the emotional data, and makes adjustments to generate more emotionally sensitive product suggestions next time.

[0323] The above is the specific processing flow of the entire system that combines the emotion engine. This will realize a system that makes the most of traditional Japanese craftsmanship and modern artisan skills to create new product value and makes highly accurate, integrated proposals based on user emotional feedback.

[0324] Example 2

[0325] 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."

[0326] Traditional craft data collection and analysis systems lack sufficient accuracy and flexibility in generating new product ideas and recommending optimal collaboration partners. They also lack effective methods for properly collecting user feedback and incorporating it into future proposals. Furthermore, feedback analysis does not take user emotions into account, making it difficult to understand users' authentic reactions and continuously improve the system.

[0327] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0328] In this invention, the server includes means for collecting information on craft techniques, means for analyzing the collected craft technique information from various angles, means for generating new product ideas that utilize craft techniques based on the analysis results, means for proposing optimal collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for collecting user feedback, means for improving the system based on the collected feedback and emotional data, and means for recognizing user emotions using an emotion recognition engine. This enables multifaceted analysis of the collected data, generation of new product ideas and proposals for optimal collaboration partners, and analysis of user feedback including emotional data, thereby realizing continuous improvement of the system.

[0329] "Craftsmanship information" includes technical information about the craft, the manufacturing process, materials used, historical background, and information about the artisans involved.

[0330] "Collection means" refers to the means for collecting information via various databases and external APIs.

[0331] "Means for analyzing from multiple angles" refers to technical means for analyzing collected information from multiple angles and extracting its strengths, weaknesses, rarity, and points of differentiation from competitors.

[0332] "Means for generating new product ideas" means techniques for generating new product designs and concepts, taking into account market trends and consumer needs.

[0333] The "means of proposing the most suitable collaboration partner" is a technology that searches a database for and proposes the most suitable collaboration partner candidate for a new product proposal based on technical capabilities and past performance.

[0334] The "means for displaying the proposal results on the user terminal" refers to a technical means for displaying the generated new product proposals and collaboration partner candidates on the user terminal.

[0335] "Means for collecting feedback from users" refers to means for collecting opinions and evaluations from users.

[0336] "Means for improving the system based on feedback and emotional data" refers to technical means for analyzing feedback and emotional data from users and improving the system algorithms and design proposals based on this.

[0337] An "emotion recognition engine" is a technology for recognizing a user's emotions, analyzing emotions such as joy, sadness, and anger from facial expressions and voice.

[0338] As an embodiment of the present invention, the processing flow of the entire system is shown below. This system mainly involves collaboration between the server, terminals, and users, and uses various technologies to propose new products and collect feedback.

[0339] 1. Collection of technical data

[0340] The server collects information about craft techniques. It connects to an internal database (e.g., MongoDB) and also retrieves technical information, manufacturing processes, materials used, historical background, and related artisan information from external sources through a RESTful API.

[0341] Example: A server accesses a database about "ceramics" and retrieves information about the manufacturing process, material properties, historical background, and associated artisans.

[0342] 2. Data analysis and visualization

[0343] The server analyzes the collected information from multiple angles using Python and R. It cleanses the data and uses machine learning algorithms such as k-means clustering to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts using Matplotlib and Plotly to visualize the analysis results.

[0344] Example: A server runs data on ceramics through a machine learning algorithm to evaluate its durability, aesthetic value, rarity of manufacturing techniques, etc., and identify its strengths and weaknesses. These are then compiled into a radar chart for each characteristic.

[0345] 3. New product idea generation

[0346] The server uses a generative AI model (e.g., OpenAI® GPT-4®) to generate new product ideas. The server uses algorithms based on market trends and consumer needs to propose new product ideas.

[0347] Example: A server prompts a generative AI model with the prompt "Generate ideas for a new ceramic tableware set with a modern design" and receives the generated ideas.

[0348] 4. Matching collaboration partners

[0349] The server searches a database (e.g., MySQL (registered trademark)) for the best partner candidates for a new product idea and makes suggestions. Suitability is evaluated based on factors such as technical capabilities and past performance.

[0350] Example: Using an SQL query to find relevant partners in a database, calculate a reputation score and shortlist the best partners.

[0351] 5. Presentation of proposed results

[0352] The device displays new product ideas and potential collaboration partners sent from the server to the user. JavaScript (registered trademark) and HTML5 are used to display the data in a visually easy-to-understand manner.

[0353] Example: Using React.js on the front end, we display the design of new product ideas and a list of partners. Once the user selects a partner, details of the partner candidate are also displayed in a popup.

[0354] 6. Emotion Recognition by Emotion Engine

[0355] When the user inputs feedback, the device uses an emotion engine (e.g., Microsoft® Azure® Emotion API) to recognize the user's emotions, and then transmits not only the user's feedback but also the emotional information to the server.

[0356] Example: When filling out a form, a webcam captures the user's facial expression, and the image data is sent to the Emotion API to recognize emotions. The resulting emotional data, such as "happiness" or "sadness," is then displayed.

[0357] 7. Collecting feedback and sentiment data

[0358] The server receives the feedback and emotion data sent from the device and analyzes it using Python's Pandas, which allows the server to understand the user's true reaction and use it to improve the next experience.

[0359] Example: The server combines the received feedback "I like the new design" with the emotion data "joy" and performs detailed analysis using a text analysis tool.

[0360] 8. Continuous improvement of the system

[0361] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[0362] Example: Using the results of a sentiment analysis engine, we can update the training dataset for a machine learning model and improve the algorithm that generates new design ideas.

[0363] In this way, by combining the emotion recognition engine, we have created a system that can make highly accurate new product proposals through the collection and analysis of craft technology data, the generation of new product ideas, the proposal of collaboration partners, and the collection and analysis of feedback. This system can reflect user feedback based on their emotions and make continuously improved new product proposals.

[0364] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0365] The flow of this system's program processing

[0366] Step 1:

[0367] The server collects information about craft techniques, connecting to an internal database (e.g., MongoDB) and also retrieving technical information, manufacturing processes, materials used, historical background, and related artisan information from external sources through a RESTful API.

[0368] Input: Database configuration information, external API endpoint

[0369] Output: List of collected crafting and technical information

[0370] What it does: Reads the configuration file "config.json", gets the database URL and authentication information, connects to it using a MongoDB client, sends a GET request to an external API endpoint, and retrieves the returned JSON data.

[0371] Step 2:

[0372] The server cleanses the collected information, completing missing data values ​​and detecting and correcting inconsistencies.

[0373] Input: List of collected craft technical information

[0374] Output: A list of cleansed craft information

[0375] Specific operation: Using Python's Pandas library, the data is read into a DataFrame and cleansed, such as filling in missing values ​​with the mean value.

[0376] Step 3:

[0377] The server then performs multifaceted analysis of the cleansed data, using machine learning algorithms such as k-means clustering to extract the strengths, weaknesses, and rarity of the technology, as well as points of differentiation from competitors.

[0378] Input: Cleansed list of craft information

[0379] Output: A list of analysis results (strengths, weaknesses, rarity, points of differentiation from competitors)

[0380] What it does: Uses the Scikit-learn library to perform k-means clustering to divide the data into clusters, calculates the center value within each cluster, and identifies strengths and weaknesses.

[0381] Step 4:

[0382] The server visualizes the analysis results, generating graphs and charts using Matplotlib and Plotly.

[0383] Input: List of analysis results (strengths, weaknesses, rarity, points of differentiation from competitors)

[0384] Output: Visualized graphs and charts

[0385] What it does: Create a radar chart using Matplotlib to visually display the strengths and weaknesses of each technology.

[0386] Step 5:

[0387] The server uses generative AI models (e.g., OpenAI GPT-4) to generate new product ideas, using algorithms based on market trends and consumer needs.

[0388] Input: Prompt statement (e.g., "Generate ideas for a new ceramic tableware set with a modern design"), analysis results

[0389] Output: List of new product ideas

[0390] Specific operation: Provide a prompt to the generative AI model and receive the generated ideas.

[0391] Step 6:

[0392] The server searches a database (e.g., MySQL) for the best partner candidates for the new product idea and proposes them. They are evaluated based on their technical capabilities and past performance.

[0393] Input: List of new product ideas, partner database

[0394] Output: A list of suitable collaboration partners

[0395] What it does: Uses an SQL query to find relevant partners in the database, calculates a rating score and lists the best partners.

[0396] Step 7:

[0397] The device displays new product ideas and potential collaboration partners sent from the server to the user, using JavaScript and HTML5 to present the data in a visually easy-to-understand manner.

[0398] Input: List of new product ideas, list of suitable collaboration partners

[0399] Output: New product ideas and potential collaboration partners displayed to the user

[0400] Specific operation: Using React.js on the front end, we display the design of new product ideas and a list of partners. Details of the partner candidates selected by the user are also displayed in a popup.

[0401] Step 8:

[0402] When the user inputs feedback, the device uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion, and then sends the user's feedback and emotional information to the server.

[0403] Input: Feedback text, user facial expressions and voice data

[0404] Output: Recognized emotion data, feedback sentence

[0405] Specific operation: When filling out a form, the system captures the user's facial expression with a webcam, sends the image data to the Emotion API, and recognizes their emotions. The resulting emotional data, such as "happiness" or "sadness," is then displayed.

[0406] Step 9:

[0407] The server receives and analyzes the feedback and emotion data sent from the device. It uses Python's Pandas to analyze the data and understand the user's true reaction.

[0408] Input: Feedback sentence, emotion data

[0409] Output: Report of analysis results

[0410] Specific operation: The server combines the received feedback "I like the new design" with the emotion data "joy" and performs detailed analysis using text analysis tools.

[0411] Step 10:

[0412] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[0413] Input: Analysis results report

[0414] Output: Improved algorithm, list of new design alternatives

[0415] What it does: Based on the results of the sentiment analysis engine, it updates the training dataset for the machine learning model and improves the algorithm that generates new design ideas.

[0416] The above steps work together to create a system that proposes new products based on craft techniques and performs feedback analysis.

[0417] (Application example 2)

[0418] 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."

[0419] In the traditional craft technology data collection, analysis, and product creation process, it is common to have a function for collecting user feedback, but there is a problem in that it is difficult to accurately recognize user emotions and improve the system based on that emotional data. This makes it difficult to understand users' true reactions and make more accurate product suggestions.

[0420] 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.

[0421] In this invention, the server includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas utilizing craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for recognizing user emotions, means for collecting feedback and emotional data from users, and means for improving the system based on the collected feedback and emotional data. This enables more accurate product suggestions by accurately understanding the user's emotional state and reflecting emotional feedback.

[0422] "Craftsmanship" refers to the art of producing fine and practical items using traditional or modern techniques.

[0423] "Means for collecting data" refers to the methods and devices used to obtain specific data and store it in the database.

[0424] "Means for multifaceted analysis" refers to methods and devices for analyzing collected data from multiple perspectives to gain a comprehensive understanding.

[0425] "Means for generating new product ideas" refers to methods or devices for generating ideas for new products or services based on collected and analyzed data.

[0426] The "means for proposing collaboration partners" refers to a method or device for selecting and proposing appropriate collaborators or companies based on the generated new product ideas.

[0427] "Means for displaying on a user terminal" refers to a method or apparatus for displaying information on a user's device (e.g., smartphone, tablet, or PC).

[0428] "Means for recognizing emotions" refers to a method or device for detecting and analyzing a user's emotions.

[0429] "Means for collecting feedback and emotional data" refers to a method or device for capturing a user's opinions and emotional state and storing them in a database.

[0430] "Means for improving the system" refers to methods and devices for improving the system's functionality and performance based on collected feedback and sentiment data.

[0431] The system of the present invention is constructed with the participation of a server, a terminal, and a user.

[0432] 1. Data Collection Module

[0433] The server has the function of collecting data on craft techniques. The data is obtained through internal databases and external APIs. For example, it accesses a database on "ceramics" to obtain information on the manufacturing process, material properties, historical background, and related craftspeople.

[0434] 2. Data Analysis and Visualization Module

[0435] The server runs algorithms to analyze the collected data from multiple angles. The collected data is cleansed to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors. The analysis results are then displayed visually as graphs and charts. For example, data on ceramics can be run through a machine learning algorithm to evaluate durability, aesthetic value, and the rarity of manufacturing techniques, and the results can be summarized in a radar chart.

[0436] 3. New product idea generation module

[0437] The server generates new product ideas using an algorithm that takes into account market trends and consumer needs. For example, the server may generate a design proposal for a new tableware set using ceramic techniques, reflecting market data that indicates a demand for simple, modern designs.

[0438] 4. Collaboration Partner Matching Module

[0439] The server searches its database for the best possible partner for a new product idea and suggests them. For example, if a new ceramic tableware set is being mass-produced, the server will compile a list of ceramic manufacturers and designers both in Japan and overseas.

[0440] 5. Proposal result display module

[0441] The terminal has a function to display new product ideas and potential collaboration partners sent from the server to the user. For example, the terminal displays a design idea for a new ceramic tableware set and a list of recommended partners, allowing the user to consider collaboration with an appropriate partner.

[0442] 6. Emotion Recognition Module

[0443] The device uses an emotion engine to recognize the user's emotions when the user inputs feedback. For example, it uses a smartphone camera to analyze the user's facial expressions and voice and recognizes emotional states such as "happiness" or "dissatisfaction."

[0444] 7. Feedback and Emotion Data Collection Module

[0445] The server collects the feedback and emotion data sent from the device and stores it in a database. For example, when a user gives feedback such as "I'm impressed" about the design of a new tableware set, the emotion is also analyzed and sent to the server.

[0446] 8. System Improvement Module

[0447] The server improves the system based on the collected feedback and emotional data. Based on the results of emotion recognition and feedback analysis, the server aims to improve the algorithm and diversify design proposals. For example, the server could analyze feedback such as "We want more design variations" and the emotion of "dissatisfaction" and reflect this in the next new product proposal.

[0448] Examples:

[0449] For example, when a user of the "Traditional Crafts Virtual Market" is looking at the design of a new ceramic tableware set, the app can analyze the user's facial expression with a camera and detect "joy." If the user provides feedback on a design, such as "it's very beautiful," that emotional data is sent to the server. The server analyzes this data and reflects it in generating the next design proposal.

[0450] Example prompt sentence:

[0451] "Use the following feedback and emotion data to train an algorithm to generate new ceramic design ideas. Feedback: 'So beautiful' Emotion: 'Joy'"

[0452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0453] Step 1:

[0454] A server collects data about the craft.

[0455] Input: Internal database or external API

[0456] Data processing: Through internal databases and external APIs, we obtain technical information, manufacturing processes, materials used, historical background, and information on related craftspeople.

[0457] Output: Collected database

[0458] Specific operation: The server accesses a database related to "ceramics," obtains various information, and stores it in the database.

[0459] Step 2:

[0460] The server analyzes the collected technical data from multiple perspectives.

[0461] Input: Collected database

[0462] Data calculation: Data is cleansed to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors.

[0463] Output: Analysis results

[0464] How it works: The server runs the ceramic data through machine learning algorithms (such as TENSORFLOW (registered trademark) or PyTorch) to evaluate durability, aesthetic value, rarity of manufacturing techniques, etc., and compiles the ceramics' strengths and weaknesses into a radar chart.

[0465] Step 3:

[0466] The server generates new product ideas based on the analysis results.

[0467] Input: Analysis results

[0468] Data calculations: Using algorithms that take into account market trends and consumer needs, new product ideas are proposed.

[0469] Output: New product idea

[0470] What it does: The server uses market data to generate design ideas for a new ceramic dinnerware set, reflecting the desire for simple, contemporary designs.

[0471] Step 4:

[0472] The server searches a database for potential collaboration partners that are best suited to the new product idea and makes suggestions.

[0473] Input: New product idea

[0474] Data calculation: Evaluate the suitability of collaboration partners based on their technical capabilities and past performance.

[0475] Output: List of partners

[0476] Specific operation: The server compiles a list of suitable partner candidates from a database of domestic and international ceramic manufacturers and designers.

[0477] Step 5:

[0478] The terminal displays the new product proposals and collaboration partner candidates sent from the server to the user.

[0479] Input: New product ideas, potential partners

[0480] Output: Data displayed on the user's terminal

[0481] Specific operation: The device displays design proposals for a new ceramic tableware set and a list of recommended partners, which the user can review to consider partner collaboration.

[0482] Step 6:

[0483] The terminal recognizes the user's emotions using an emotion engine when the user inputs feedback.

[0484] Input: User's facial expression data, voice data

[0485] Data calculation: Using an emotion recognition library (e.g., OpenCV or Affectiva), analyze the user's facial expressions and voice to determine their emotional state.

[0486] Output: User emotion data

[0487] Specific operation: The smartphone camera is used to capture the user's facial expressions and analyze their emotional state, such as "happiness" or "dissatisfaction."

[0488] Step 7:

[0489] The server collects and analyzes the feedback and emotion data sent from the terminals.

[0490] Input: User feedback, emotional data

[0491] Data calculation: Analyze the feedback content and emotional data and use it for the next proposal.

[0492] Output: Analysis results

[0493] Specific operation: The server analyzes feedback such as "I would like more design variations" and "dissatisfaction" feelings, and reflects this in the next new product proposal.

[0494] Step 8:

[0495] The server improves the system based on feedback including emotional data.

[0496] Input: Analysis results

[0497] Data calculation: Improve the algorithm based on emotion recognition results and feedback analysis results.

[0498] Output: Updated system

[0499] What it does: The server implements a new algorithm and makes adjustments to generate better product suggestions based on emotions.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] [Second embodiment]

[0504] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0505] 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.

[0506] 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).

[0507] 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.

[0508] 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.

[0509] 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).

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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.

[0514] 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.

[0515] 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."

[0516] As an embodiment of the present invention, the processing flow of the entire system will be explained in natural language below, along with the roles of each entity, namely, server, terminal, and user, and specific examples.

[0517] 1. Collection of technical data

[0518] The server collects data about craft techniques. Through an internal database or external API, the server obtains technical information, manufacturing processes, materials used, historical background, and information about the artisans involved.

[0519] Examples:

[0520] The server collects technical information about "ceramics" from various databases, including the ceramic manufacturing process, the types of clay and glazes used, and the history of famous artisans and their works.

[0521] 2. Data analysis and visualization

[0522] The server analyzes the collected technical data from multiple angles. It cleanses the data and extracts specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts to visualize the analysis results.

[0523] Examples:

[0524] The server analyzes the ceramics data and identifies their strengths as durability, aesthetic value, and rare manufacturing techniques, and then summarizes these characteristics in a radar chart.

[0525] 3. New product idea generation

[0526] The server generates new product ideas based on the analysis results, using an algorithm that takes into account market trends and consumer needs to propose new product ideas.

[0527] Examples:

[0528] The server generates design proposals for a new set of tableware using ceramic techniques, based on market data that reflects the desire for simple, contemporary designs.

[0529] 4. Matching collaboration partners

[0530] The server searches a database for potential partners best suited to a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[0531] Examples:

[0532] With the aim of mass-producing a new ceramic tableware set, the server compiles a list of optimal partners from a database of ceramic manufacturers and designers both in Japan and overseas.

[0533] 5. Presentation of proposed results

[0534] The terminal displays the new product ideas and partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[0535] Examples:

[0536] The device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[0537] 6. Feedback and Improvement

[0538] Users provide feedback to the system, and the server uses that feedback to improve the system's accuracy. Users input their opinions about proposed ideas and partners, and the server analyzes them to identify areas for improvement.

[0539] Examples:

[0540] Users can send feedback to the server, such as "I want more design variations." The server analyzes this feedback and improves the algorithm to generate more diverse design proposals next time.

[0541] This will enable us to maximize the use of traditional Japanese craftsmanship and modern artisan skills, create new product value, and find suitable collaboration partners.In addition, we will be able to continuously improve the system through feedback from users and make better proposals.

[0542] The processing flow will be explained below.

[0543] Step 1:

[0544] The server connects to an internal database or external API to collect information about the craft techniques, including the specific process of the technique, the materials used, historical background, and information about the artisans involved.

[0545] Specific operation:

[0546] The server accesses a database on "ceramics" and retrieves information on the manufacturing process, material characteristics, historical background, and related craftsmen.

[0547] Step 2:

[0548] The server cleanses the collected craft technology data, filling in missing values ​​and removing outliers.

[0549] Specific operation:

[0550] The server organizes the acquired ceramic data, detects incomplete data and outliers, and completes them.

[0551] Step 3:

[0552] The server analyzes the data from multiple angles and extracts the strengths, weaknesses, rarity, and points of differentiation of the craftsmanship from competitors.

[0553] Specific operation:

[0554] The server runs the ceramic data through machine learning algorithms to assess its durability, aesthetic value, rarity of manufacturing techniques, and other factors, identifying its strengths and weaknesses.

[0555] Step 4:

[0556] The server visualizes the analysis results and generates graphs and charts.

[0557] Specific operation:

[0558] The server displays the strengths and weaknesses of ceramics in the form of radar charts, heat maps, and other formats.

[0559] Step 5:

[0560] The server generates new product ideas taking into account market trends and consumer needs.

[0561] Specific operation:

[0562] The server analyzes market data and generates new product ideas, such as a "modern design ceramic tableware set."

[0563] Step 6:

[0564] The server selects and proposes the most suitable collaboration partner for the new product idea.

[0565] Specific operation:

[0566] The server searches a database of domestic and international ceramic manufacturers and designers and lists suitable partners to manufacture the new ceramic tableware set.

[0567] Step 7:

[0568] The terminal displays the new product proposals and collaboration partner candidates sent from the server to the user.

[0569] Specific operation:

[0570] The terminal displays a design proposal for a new ceramic tableware set and a list of recommended partners on a user interface.

[0571] Step 8:

[0572] The user inputs feedback about the proposed ideas and partners and sends it to the server.

[0573] Specific operation:

[0574] The user enters feedback on the device, such as "I would like more design variations," and presses the send button.

[0575] Step 9:

[0576] The server analyzes the received feedback and identifies improvements for the next implementation process.

[0577] Specific operation:

[0578] The server analyzes the text of user feedback and determines that the algorithm needs to be improved to increase design variation.

[0579] Step 10:

[0580] The server updates the system's algorithms and database based on the analysis results, improving the accuracy of the entire system.

[0581] Specific operation:

[0582] Based on the feedback, the server improves the machine learning algorithm and updates the model to generate diverse design proposals.

[0583] Example 1

[0584] 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."

[0585] In the conventional product development process for craftsmanship, data collection and analysis were time-consuming, making it difficult to efficiently generate new product ideas and propose appropriate collaboration partners. There was also a lack of mechanisms for appropriately incorporating user feedback and improving the system. This limited the speed and quality of product development.

[0586] 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.

[0587] In this invention, the server includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas utilizing craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for collecting user feedback, means for improving the system based on the collected feedback, means for acquiring data on craft techniques using an external API, means for visually visualizing the analysis results, and means for using a generative AI model when generating new product ideas. This makes it possible to efficiently generate new product ideas based on craft techniques and propose appropriate collaboration partners, and to continuously improve the system by utilizing user feedback.

[0588] "Craftsmanship" refers to crafts made using traditional methods and techniques, as well as related manufacturing processes, materials and designs.

[0589] "Means of collecting data" refers to devices and systems for obtaining information related to craft techniques from various databases and external APIs.

[0590] "Means for analyzing data from multiple perspectives" refers to techniques and methods for analyzing collected data from various perspectives and extracting specific information.

[0591] "Means for generating new product ideas" refers to devices and methods for devising new crafts and their applied products based on the results of the analysis.

[0592] "Means for proposing collaborative partners" refers to devices and systems for selecting and proposing the most suitable collaborating companies and craftsmen to realize new product ideas.

[0593] "Means for displaying the proposal results on the user terminal" refers to a device or system for visually showing the proposal contents sent from the server to the user.

[0594] "Means for collecting user feedback" refers to a device or system for obtaining opinions and ratings provided by users.

[0595] "Means for improving the system based on feedback" refers to techniques and methods for analyzing collected feedback and improving the performance and accuracy of the system.

[0596] "Means of obtaining data using external APIs" refers to programs and systems for obtaining information from external databases and services via the Internet.

[0597] "Visual visualization means" refers to devices and technologies for converting and displaying the results of data analysis in a visual format such as a graph or chart.

[0598] "Means for using generative AI models" refers to devices or programs that utilize models using artificial intelligence technology to generate new ideas and concepts.

[0599] An embodiment of the present invention relates to a system that efficiently generates ideas for new products based on craft techniques and proposes collaboration partners, and realizes continuous improvement of the system based on user feedback.

[0600] Technical data collection

[0601] The server collects data about craft techniques, using internal databases and external APIs to obtain technical information, manufacturing processes, materials used, historical background, and artisan information.

[0602] For example, the server collects technical information about "ceramics" from various databases, including the ceramic manufacturing process, the types of clay and glazes used, and the history of famous artisans and their works.

[0603] Data Analysis and Visualization

[0604] We analyze the technical data collected by the server from multiple angles, cleanse the data, extract specific strengths, weaknesses, rarity, and points of differentiation from competitors, and generate visual graphs and charts to visualize the analysis results.

[0605] As a specific example, the server analyzes data on ceramics, identifies its strengths as durability, aesthetic value, and rare manufacturing techniques, and summarizes these in a radar chart for each characteristic.

[0606] Generate new product ideas

[0607] The server generates new product ideas based on the analysis results, using algorithms that take into account market trends and consumer needs, and utilizing generative AI models to propose new product ideas.

[0608] As a concrete example, the server generates design proposals for a new set of tableware using ceramic techniques. Based on market data, the following prompt is used to reflect the desire for a simple, modern design:

[0609] "Please propose a new design for a ceramic tableware set, taking into consideration current market trends."

[0610] Matching collaboration partners

[0611] The server searches a database for the best candidates for collaboration partners for a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[0612] As a concrete example, the server considers mass production of a new ceramic tableware set and lists the most suitable partners from a database of ceramic manufacturers and designers both in Japan and overseas.

[0613] Presentation of proposed results

[0614] The terminal displays the new product ideas and partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[0615] For example, the device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[0616] Feedback and Improvements

[0617] Users provide feedback to the system, and the server uses that feedback to improve the system's accuracy. Users input their opinions about proposed ideas and partners, and the server analyzes them to identify areas for improvement.

[0618] As a concrete example, a user can send feedback to the server such as "I would like more design variations," and the server will analyze this and improve its algorithm to generate more diverse design proposals next time.

[0619] This system will enable the creation of new product value by maximizing the use of traditional Japanese craft techniques and modern artisanal skills, and will enable the efficient search for suitable collaboration partners. Furthermore, the system will be continuously improved through user feedback, enabling the creation of better proposals.

[0620] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0621] Step 1:

[0622] A server collects data about craft skills.

[0623] Input: The server takes input from internal database queries and request parameters from external APIs.

[0624] Data processing: The server retrieves data from these sources and cleanses it by detecting duplicates and missing information.

[0625] Output: A clean set of craft data is produced.

[0626] Specific operation: The server sends an HTTP request to the specified API endpoint, receives technical information as a response, and issues a SELECT query to extract data from the internal database.

[0627] Step 2:

[0628] The technical data collected by the server is analyzed from multiple perspectives.

[0629] Input: The clean data collected in step 1.

[0630] Data processing: The server uses statistical analysis, text mining techniques, etc. to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors.

[0631] Output: Characteristic data as the analysis result and visualization data based on it are generated.

[0632] Specific operation: The server calls statistical functions to analyze the collected data and generates the results as radar charts and graphs.

[0633] Step 3:

[0634] The server generates new product ideas based on the analysis results.

[0635] Inputs: Analysis results generated in step 2. External data on market trends and consumer needs.

[0636] Data processing: The server uses the generative AI model to generate new product ideas.

[0637] Output: A prototype of the new product idea is generated.

[0638] Specific operation: The server inputs the prompt statement and analysis results into the generative AI model and obtains the output idea data.

[0639] Step 4:

[0640] The server searches for and evaluates potential collaboration partners related to the new product idea.

[0641] Input: Prototype of new product idea generated in step 3. Database of collaboration partners.

[0642] Data processing: Scoring potential partners based on suitability criteria and shortlisting the most suitable partners.

[0643] Output: A list of high-scoring partner candidates is generated.

[0644] What it does: The server queries internal and external partner databases and applies a rating algorithm to generate a score.

[0645] Step 5:

[0646] The terminal displays the new product ideas and partner candidates sent from the server to the user.

[0647] Input: Partner candidate list generated in step 4. Prototype of new product idea.

[0648] Data processing: Visually display information using a GUI.

[0649] Output: Display of design proposals and partner list.

[0650] Specific operation: The device applies the data obtained from the server to the GUI components and renders it on the screen.

[0651] Step 6:

[0652] The user provides feedback to the system.

[0653] Input: Ratings and opinions on new product ideas and potential partners.

[0654] Data processing: Collect feedback and send it to the server.

[0655] Output: Sending feedback data.

[0656] Specific behavior: A user enters their opinion into the feedback form and clicks the submit button, which sends an HTTP POST request to the server.

[0657] Step 7:

[0658] The server analyzes user feedback to improve the accuracy of the system.

[0659] Input: Feedback data collected in step 6.

[0660] Data processing: Analyzing feedback data to identify areas for improvement in algorithms and models.

[0661] Output: Improved algorithms and models.

[0662] Specific operation: The server analyzes the feedback data using natural language processing technology and adjusts and optimizes the generative AI model and related algorithms based on the insights gained.

[0663] (Application example 1)

[0664] 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."

[0665] Conventional methods of providing information about crafts make it difficult for customers to learn detailed technical information or the manufacturing background of crafts. Furthermore, developing new products and selecting appropriate collaboration partners are not easy, and there is a lack of mechanisms for incorporating user feedback into the system. Furthermore, the interactive information provided to customers in craft displays in physical stores is limited, creating a need for an improved customer experience.

[0666] 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.

[0667] In this invention, the server includes a means for collecting data on craft techniques, a means for multifaceted analysis of the collected craft technique data, and a means for generating new product ideas that utilize craft techniques based on the analysis results. This enables the provision of detailed technical information on crafts, the development of new products, and the selection of collaboration partners. Furthermore, by including a means for visually displaying craft information using augmented reality, the customer experience in physical stores can be improved.

[0668] "Craftsmanship" refers to the techniques used by artisans to create artistic products by hand using traditional methods and techniques.

[0669] "Data collection means" refers to the mechanism for obtaining necessary information from internal databases related to craft techniques and external APIs.

[0670] "Data analysis means" refers to a system for cleansing collected craft technology data and analyzing it from multiple perspectives.

[0671] "New product idea generation means" refers to a system for proposing new crafts and their designs based on analyzed data.

[0672] The "means for proposing collaboration partners" refers to a mechanism for proposing optimal manufacturing partners or collaborators for the new product ideas that have been generated.

[0673] "User terminal display means" refers to a mechanism for displaying the proposal results and related information on a device that is directly operated by the user.

[0674] "Feedback collection means" refers to a mechanism for collecting user opinions and requests into the system.

[0675] "System improvement measures" refer to mechanisms for improving the system's algorithms and functions based on collected feedback.

[0676] "Augmented reality display means" refers to a mechanism for visually displaying additional information about real-world artifacts via a smartphone or dedicated device.

[0677] As an embodiment of the present invention, a processing flow of a new craft product suggestion system will be described.

[0678] Overall system configuration

[0679] This system mainly consists of three entities: a server, a terminal, and a user. The server collects and analyzes data, generates suggestions, and analyzes feedback. The terminal provides information to the user and collects feedback. It also uses augmented reality (AR) to visually display information about real crafts.

[0680] Server Roles

[0681] 1. Collection of technical data

[0682] The server primarily collects data about craft techniques through internal databases and external APIs. This data includes information about the manufacturing process, materials, historical background, and the artisans involved. For example, it collects technical information about ceramics, including details about the manufacturing process, clays, and glazes used.

[0683] 2. Data analysis and visualization

[0684] The server then cleanses the collected data and performs a multifaceted analysis, extracting strengths, weaknesses, rarity, and points of differentiation from competitors, and presenting these in visual formats such as radar charts. This analysis identifies characteristics such as the durability, aesthetic value, and rare manufacturing techniques of ceramics, for example.

[0685] 3. New product idea generation

[0686] Based on the analysis results, the server generates new product ideas, taking into account market trends and consumer needs through an algorithm, suggesting new product ideas such as a tableware set with a simple, modern design.

[0687] 4. Matching collaboration partners

[0688] The server searches its database for the optimal partner for the new product idea and proposes it, using criteria such as technical capabilities and past performance as criteria. For example, it could create a list of optimal partners from ceramic manufacturers and designers both in Japan and overseas.

[0689] Device Role

[0690] 1. Displaying the proposed results

[0691] The terminal displays new product ideas and potential collaboration partners sent from the server in a visually easy-to-understand format to the user. For example, it displays a design idea for a new ceramic tableware set and a list of recommended partners.

[0692] 2. Augmented reality features

[0693] The device is equipped with an AR function, allowing users to visually display product information, manufacturing process, and artisan information by pointing the camera at an actual craft item.

[0694] User Roles

[0695] 1. Providing Feedback

[0696] Users can provide their opinions and requests regarding the displayed suggestions. For example, they can send feedback such as "I would like more design variations."

[0697] System Improvement

[0698] The server collects and analyzes user feedback to improve the system's algorithms and functions, and also incorporates the collected feedback into future proposals.

[0699] Hardware and software used

[0700] The system uses the following hardware and software:

[0701] Hardware: Server, smartphone (or tablet)

[0702] Software: Flask (web framework), SQLite (database), NLTK (text analysis)

[0703] Examples and prompts

[0704] (Example)

[0705] User example 1: A customer visiting a physical store wants to learn about the manufacturing techniques behind a new tea bowl. By pointing their smartphone camera at the bowl, AR will display background information about the manufacturing process and the craftsman.

[0706] User example 2: When a user enters their idea for tableware using a durable and rare glaze into the app, new product ideas and collaboration partners based on that idea are displayed.

[0707] (Example of a prompt)

[0708] "Generate new ceramic design ideas. The target audience is young people in their 20s who want simple, modern designs."

[0709] "Please suggest improvements to increase product variety based on the feedback below. Feedback: I would like more design variations."

[0710] The above is a detailed embodiment of the present invention. This system makes it possible to propose new products that utilize craft techniques, provide effective information, and improve customer experience.

[0711] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0712] Step 1:

[0713] The server collects data about craft techniques. As input, it receives information from external APIs and internal databases. This data includes manufacturing processes, materials, historical background, artisan information, etc. The server retrieves this data and stores it in the internal database. The output is the collected raw data.

[0714] Step 2:

[0715] The data collected by the server is cleansed and analyzed from multiple perspectives. The input is the raw data collected in step 1. Data cleansing removes incomplete and duplicate data. The cleansed data is then analyzed using analytical algorithms to extract strengths, weaknesses, rarity, and points of differentiation from competitors. The output is a summary of the analysis results, and visualized data such as radar charts is also generated.

[0716] Step 3:

[0717] The server generates new product ideas based on the analysis results. The input is the analysis results obtained in step 2. A generative AI model is used to generate new product designs and concepts, taking into account market trends and consumer needs. Prompt statements are used to instruct the generative AI model. The output is details of the new product ideas.

[0718] Step 4:

[0719] The server proposes optimal collaboration partners for new product ideas generated by the server. The input is the new product idea generated in step 3. An algorithm that takes into account past performance and technical capabilities is used to search for optimal collaboration partners from a database. The output is a list of candidate collaboration partners.

[0720] Step 5:

[0721] The terminal visually displays the proposal results from the server to the user. The input is the new product idea and list of collaboration partners obtained in step 4. The information is displayed in a format that is easy for the user to understand. For example, a design proposal for a new ceramic tableware set and a list of recommended partners are displayed on the screen. The output is the displayed information.

[0722] Step 6:

[0723] The device displays information about the craft using augmented reality. The input is video data acquired when the user points the smartphone camera at the craft. The device displays detailed information about the craft obtained from the server as AR. For example, if the camera is pointed at an actual tea bowl, the manufacturing process and background information about the craftsman will be displayed on the screen. The output is information displayed using augmented reality.

[0724] Step 7:

[0725] The user enters feedback based on the information provided. The input is the user's opinion or request. For example, the user may send feedback such as "I would like more design variations." The output is the collected feedback data.

[0726] Step 8:

[0727] The server collects user feedback and improves the system. The input is the feedback data collected in step 7. The feedback is analyzed and used as data to improve the system's algorithms and functions, which can then be reflected in the next proposal. The output is improved system settings and algorithms.

[0728] 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.

[0729] As an embodiment of the present invention, the processing flow of the entire system that combines the emotion engine will be explained in natural language below. The roles of each entity, the server, terminal, and user, will be explained along with specific examples.

[0730] 1. Collection of technical data

[0731] The server collects data about craft techniques. Through an internal database or external API, the server obtains technical information, manufacturing processes, materials used, historical background, and information about the artisans involved.

[0732] Examples:

[0733] The server accesses a database on "ceramics" and retrieves information on the manufacturing process, material characteristics, historical background, and associated craftsmen.

[0734] 2. Data analysis and visualization

[0735] The server analyzes the collected technical data from multiple angles. It cleanses the data and extracts specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts to visualize the analysis results.

[0736] Examples:

[0737] The server then applies machine learning algorithms to the ceramic data, assessing its durability, aesthetic value, and the rarity of its manufacturing techniques, to identify its strengths and weaknesses, which are then compiled into a radar chart for each characteristic.

[0738] 3. New product idea generation

[0739] The server generates new product ideas based on the analysis results, using an algorithm that takes into account market trends and consumer needs to propose new product ideas.

[0740] Examples:

[0741] The server generates design proposals for a new set of tableware using ceramic techniques, based on market data that reflects the desire for simple, contemporary designs.

[0742] 4. Matching collaboration partners

[0743] The server searches a database for potential partners best suited to a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[0744] Examples:

[0745] With the aim of mass-producing a new ceramic tableware set, the server compiles a list of optimal partners from a database of domestic and international ceramic manufacturers and designers.

[0746] 5. Presentation of proposed results

[0747] The terminal displays the new product ideas and collaboration partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[0748] Examples:

[0749] The device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[0750] 6. Emotion Recognition by Emotion Engine

[0751] The device recognizes the user's emotion using the emotion engine when the user inputs feedback, and transmits not only the user's feedback but also the emotion information to the server.

[0752] Examples:

[0753] The device analyzes the user's facial expressions and voice to recognize emotions such as "happiness" or "dissatisfaction." When the user gives feedback such as "I'm impressed" about the design of a new tableware set, that emotion is also analyzed.

[0754] 7. Collecting feedback and sentiment data

[0755] The server receives and analyzes the feedback and emotional data sent from the device, thereby understanding the user's true reaction and utilizing it for future suggestions.

[0756] Examples:

[0757] The server analyzes feedback such as "I want more design variations" and feelings of "dissatisfaction" and reflects this in the next new product proposal.

[0758] 8. Continuous improvement of the system

[0759] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[0760] Examples:

[0761] The server implements new algorithms based on data from the emotion engine and makes adjustments to generate better emotion-based product suggestions.

[0762] In this way, by combining an emotion recognition engine, it is possible to make the most of traditional Japanese craft techniques and modern artisan skills to create new product value, as well as to realize a system that makes even more accurate suggestions based on feedback based on the user's emotions.

[0763] The processing flow will be explained below.

[0764] Step 1:

[0765] The server connects to an internal database and external APIs to collect information about craft techniques, including technical information, manufacturing processes, materials used, historical background, and artisan information.

[0766] Specific operation:

[0767] The server retrieves information from a ceramics database about the manufacturing process, the types of clay and glazes used, historical background, and artisans.

[0768] Step 2:

[0769] The server pre-processes the collected craft data, cleansing it, filling in missing values, and removing outliers.

[0770] Specific operation:

[0771] The server cleanses the acquired ceramic data, identifying and completing incomplete data and outliers.

[0772] Step 3:

[0773] The server analyzes the data from multiple angles and applies machine learning algorithms to extract the strengths, weaknesses, and rarity of the craftsmanship, as well as points of differentiation from competitors.

[0774] Specific operation:

[0775] The server analyzes the ceramics' data, assessing their durability, aesthetic value, and the rarity of their manufacturing techniques, and identifies their strengths and weaknesses.

[0776] Step 4:

[0777] The server visualizes the analysis results, generating graphs and charts based on the extracted features and summarizing them in a visually easy-to-understand format.

[0778] Specific operation:

[0779] The server displays the strengths and weaknesses of ceramics in the form of radar charts, heat maps, and other formats.

[0780] Step 5:

[0781] The server generates new product ideas taking into account market trends and consumer needs. Using an algorithm, the server combines collected data with market needs to propose new product ideas.

[0782] Specific operation:

[0783] The server analyzes market data and generates a new product idea: a "modern design ceramic tableware set."

[0784] Step 6:

[0785] The server searches a database for the most suitable partner for a new product idea and proposes it. Suitability is evaluated based on technical capabilities and past performance.

[0786] Specific operation:

[0787] The server searches a database of domestic and international ceramic manufacturers and designers, and lists suitable partners for mass production of new ceramic tableware sets.

[0788] Step 7:

[0789] The terminal displays the new product ideas and collaboration partner candidates sent from the server to the user, and displays the received data in a visually easy-to-understand format.

[0790] Specific operation:

[0791] The terminal displays a design proposal for a new ceramic tableware set and a list of recommended partners on a user interface.

[0792] Step 8:

[0793] The device uses an emotion engine to recognize the user's emotions when the user inputs feedback, analyzes the user's facial expressions and voice, and transmits the emotional information to the server.

[0794] Specific operation:

[0795] When a user inputs feedback such as "I'm happy" about a new ceramic design, the device analyzes the user's facial expression and intonation of the voice to recognize the emotion of "joy."

[0796] Step 9:

[0797] The server receives and analyzes the feedback and emotion data sent from the device, and evaluates new product ideas based on the user's emotions and feedback.

[0798] Specific operation:

[0799] The server analyzes the feedback such as "great design" and the emotion data such as "delight" to ensure that the new design is well-received.

[0800] Step 10:

[0801] The server improves the system based on feedback and emotional data, refining the algorithm and making adjustments to improve the accuracy of the next suggestion.

[0802] Specific operation:

[0803] The server updates the machine learning algorithm based on the feedback, including the emotional data, and makes adjustments to generate more emotionally sensitive product suggestions next time.

[0804] The above is the specific processing flow of the entire system that combines the emotion engine. This will realize a system that makes the most of traditional Japanese craftsmanship and modern artisan skills to create new product value and makes highly accurate, integrated proposals based on user emotional feedback.

[0805] Example 2

[0806] 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."

[0807] Traditional craft data collection and analysis systems lack sufficient accuracy and flexibility in generating new product ideas and recommending optimal collaboration partners. They also lack effective methods for properly collecting user feedback and incorporating it into future proposals. Furthermore, feedback analysis does not take user emotions into account, making it difficult to understand users' authentic reactions and continuously improve the system.

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

[0809] In this invention, the server includes means for collecting information on craft techniques, means for analyzing the collected craft technique information from various angles, means for generating new product ideas that utilize craft techniques based on the analysis results, means for proposing optimal collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for collecting user feedback, means for improving the system based on the collected feedback and emotional data, and means for recognizing user emotions using an emotion recognition engine. This enables multifaceted analysis of the collected data, generation of new product ideas and proposals for optimal collaboration partners, and analysis of user feedback including emotional data, thereby realizing continuous improvement of the system.

[0810] "Craftsmanship information" includes technical information about the craft, the manufacturing process, materials used, historical background, and information about the artisans involved.

[0811] "Collection means" refers to the means for collecting information via various databases and external APIs.

[0812] "Means for analyzing from multiple angles" refers to technical means for analyzing collected information from multiple angles and extracting its strengths, weaknesses, rarity, and points of differentiation from competitors.

[0813] "Means for generating new product ideas" means techniques for generating new product designs and concepts, taking into account market trends and consumer needs.

[0814] The "means of proposing the most suitable collaboration partner" is a technology that searches a database for and proposes the most suitable collaboration partner candidate for a new product proposal based on technical capabilities and past performance.

[0815] The "means for displaying the proposal results on the user terminal" refers to a technical means for displaying the generated new product proposals and collaboration partner candidates on the user terminal.

[0816] "Means for collecting feedback from users" refers to means for collecting opinions and evaluations from users.

[0817] "Means for improving the system based on feedback and emotional data" refers to technical means for analyzing feedback and emotional data from users and improving the system algorithms and design proposals based on this.

[0818] An "emotion recognition engine" is a technology for recognizing a user's emotions, analyzing emotions such as joy, sadness, and anger from facial expressions and voice.

[0819] As an embodiment of the present invention, the processing flow of the entire system is shown below. This system mainly involves collaboration between the server, terminals, and users, and uses various technologies to propose new products and collect feedback.

[0820] 1. Collection of technical data

[0821] The server collects information about craft techniques. It connects to an internal database (e.g., MongoDB) and also retrieves technical information, manufacturing processes, materials used, historical background, and related artisan information from external sources through a RESTful API.

[0822] Example: A server accesses a database about "ceramics" and retrieves information about the manufacturing process, material properties, historical background, and associated artisans.

[0823] 2. Data analysis and visualization

[0824] The server analyzes the collected information from multiple angles using Python and R. It cleanses the data and uses machine learning algorithms such as k-means clustering to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts using Matplotlib and Plotly to visualize the analysis results.

[0825] Example: A server runs data on ceramics through a machine learning algorithm to evaluate its durability, aesthetic value, rarity of manufacturing techniques, etc., and identify its strengths and weaknesses. These are then compiled into a radar chart for each characteristic.

[0826] 3. New product idea generation

[0827] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate new product ideas. The server uses algorithms based on market trends and consumer needs to propose new product ideas.

[0828] Example: A server prompts a generative AI model with the prompt "Generate ideas for a new ceramic tableware set with a modern design" and receives the generated ideas.

[0829] 4. Matching collaboration partners

[0830] The server searches a database (e.g., MySQL) for the best partner candidates for a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[0831] Example: Using an SQL query to find relevant partners in a database, calculate a reputation score and shortlist the best partners.

[0832] 5. Presentation of proposed results

[0833] The device displays new product ideas and potential collaboration partners sent from the server to the user, using JavaScript and HTML5 to present the data in a visually easy-to-understand manner.

[0834] Example: Using React.js on the front end, we display the design of new product ideas and a list of partners. Once the user selects a partner, details of the partner candidate are also displayed in a popup.

[0835] 6. Emotion Recognition by Emotion Engine

[0836] When the user inputs feedback, the device uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion, and then sends the user's feedback and emotional information to the server.

[0837] Example: When filling out a form, a webcam captures the user's facial expression, and the image data is sent to the Emotion API to recognize emotions. The resulting emotional data, such as "happiness" or "sadness," is then displayed.

[0838] 7. Collecting feedback and sentiment data

[0839] The server receives the feedback and emotion data sent from the device and analyzes it using Python's Pandas, which allows the server to understand the user's true reaction and use it to improve the next experience.

[0840] Example: The server combines the received feedback "I like the new design" with the emotion data "joy" and performs detailed analysis using a text analysis tool.

[0841] 8. Continuous improvement of the system

[0842] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[0843] Example: Using the results of a sentiment analysis engine, we can update the training dataset for a machine learning model and improve the algorithm that generates new design ideas.

[0844] In this way, by combining the emotion recognition engine, we have created a system that can make highly accurate new product proposals through the collection and analysis of craft technology data, the generation of new product ideas, the proposal of collaboration partners, and the collection and analysis of feedback. This system can reflect user feedback based on their emotions and make continuously improved new product proposals.

[0845] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0846] The flow of this system's program processing

[0847] Step 1:

[0848] The server collects information about craft techniques, connecting to an internal database (e.g., MongoDB) and also retrieving technical information, manufacturing processes, materials used, historical background, and related artisan information from external sources through a RESTful API.

[0849] Input: Database configuration information, external API endpoint

[0850] Output: List of collected crafting and technical information

[0851] What it does: Reads the configuration file "config.json", gets the database URL and authentication information, connects to it using a MongoDB client, sends a GET request to an external API endpoint, and retrieves the returned JSON data.

[0852] Step 2:

[0853] The server cleanses the collected information, completing missing data values ​​and detecting and correcting inconsistencies.

[0854] Input: List of collected craft technical information

[0855] Output: A list of cleansed craft information

[0856] Specific operation: Using Python's Pandas library, the data is read into a DataFrame and cleansed, such as filling in missing values ​​with the mean value.

[0857] Step 3:

[0858] The server then performs multifaceted analysis of the cleansed data, using machine learning algorithms such as k-means clustering to extract the strengths, weaknesses, and rarity of the technology, as well as points of differentiation from competitors.

[0859] Input: Cleansed list of craft information

[0860] Output: A list of analysis results (strengths, weaknesses, rarity, points of differentiation from competitors)

[0861] What it does: Uses the Scikit-learn library to perform k-means clustering to divide the data into clusters, calculates the center value within each cluster, and identifies strengths and weaknesses.

[0862] Step 4:

[0863] The server visualizes the analysis results, generating graphs and charts using Matplotlib and Plotly.

[0864] Input: List of analysis results (strengths, weaknesses, rarity, points of differentiation from competitors)

[0865] Output: Visualized graphs and charts

[0866] What it does: Create a radar chart using Matplotlib to visually display the strengths and weaknesses of each technology.

[0867] Step 5:

[0868] The server uses generative AI models (e.g., OpenAI GPT-4) to generate new product ideas, using algorithms based on market trends and consumer needs.

[0869] Input: Prompt statement (e.g., "Generate ideas for a new ceramic tableware set with a modern design"), analysis results

[0870] Output: List of new product ideas

[0871] Specific operation: Provide a prompt to the generative AI model and receive the generated ideas.

[0872] Step 6:

[0873] The server searches a database (e.g., MySQL) for the best partner candidates for the new product idea and proposes them. They are evaluated based on their technical capabilities and past performance.

[0874] Input: List of new product ideas, partner database

[0875] Output: A list of suitable collaboration partners

[0876] What it does: Uses an SQL query to find relevant partners in the database, calculates a rating score and lists the best partners.

[0877] Step 7:

[0878] The device displays new product ideas and potential collaboration partners sent from the server to the user, using JavaScript and HTML5 to present the data in a visually easy-to-understand manner.

[0879] Input: List of new product ideas, list of suitable collaboration partners

[0880] Output: New product ideas and potential collaboration partners displayed to the user

[0881] Specific operation: Using React.js on the front end, we display the design of new product ideas and a list of partners. Details of the partner candidates selected by the user are also displayed in a popup.

[0882] Step 8:

[0883] When the user inputs feedback, the device uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion, and then sends the user's feedback and emotional information to the server.

[0884] Input: Feedback text, user facial expressions and voice data

[0885] Output: Recognized emotion data, feedback sentence

[0886] Specific operation: When filling out a form, the system captures the user's facial expression with a webcam, sends the image data to the Emotion API, and recognizes their emotions. The resulting emotional data, such as "happiness" or "sadness," is then displayed.

[0887] Step 9:

[0888] The server receives and analyzes the feedback and emotion data sent from the device. It uses Python's Pandas to analyze the data and understand the user's true reaction.

[0889] Input: Feedback sentence, emotion data

[0890] Output: Report of analysis results

[0891] Specific operation: The server combines the received feedback "I like the new design" with the emotion data "joy" and performs detailed analysis using text analysis tools.

[0892] Step 10:

[0893] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[0894] Input: Analysis results report

[0895] Output: Improved algorithm, list of new design alternatives

[0896] What it does: Based on the results of the sentiment analysis engine, it updates the training dataset for the machine learning model and improves the algorithm that generates new design ideas.

[0897] The above steps work together to create a system that proposes new products based on craft techniques and performs feedback analysis.

[0898] (Application example 2)

[0899] 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."

[0900] In the traditional craft technology data collection, analysis, and product creation process, it is common to have a function for collecting user feedback, but there is a problem in that it is difficult to accurately recognize user emotions and improve the system based on that emotional data. This makes it difficult to understand users' true reactions and make more accurate product suggestions.

[0901] 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.

[0902] In this invention, the server includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas utilizing craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for recognizing user emotions, means for collecting feedback and emotional data from users, and means for improving the system based on the collected feedback and emotional data. This enables more accurate product suggestions by accurately understanding the user's emotional state and reflecting emotional feedback.

[0903] "Craftsmanship" refers to the art of producing fine and practical items using traditional or modern techniques.

[0904] "Means for collecting data" refers to the methods and devices used to obtain specific data and store it in the database.

[0905] "Means for multifaceted analysis" refers to methods and devices for analyzing collected data from multiple perspectives to gain a comprehensive understanding.

[0906] "Means for generating new product ideas" refers to methods or devices for generating ideas for new products or services based on collected and analyzed data.

[0907] The "means for proposing collaboration partners" refers to a method or device for selecting and proposing appropriate collaborators or companies based on the generated new product ideas.

[0908] "Means for displaying on a user terminal" refers to a method or apparatus for displaying information on a user's device (e.g., smartphone, tablet, or PC).

[0909] "Means for recognizing emotions" refers to a method or device for detecting and analyzing a user's emotions.

[0910] "Means for collecting feedback and emotional data" refers to a method or device for capturing a user's opinions and emotional state and storing them in a database.

[0911] "Means for improving the system" refers to methods and devices for improving the system's functionality and performance based on collected feedback and sentiment data.

[0912] The system of the present invention is constructed with the participation of a server, a terminal, and a user.

[0913] 1. Data Collection Module

[0914] The server has the function of collecting data on craft techniques. The data is obtained through internal databases and external APIs. For example, it accesses a database on "ceramics" to obtain information on the manufacturing process, material properties, historical background, and related craftspeople.

[0915] 2. Data Analysis and Visualization Module

[0916] The server runs algorithms to analyze the collected data from multiple angles. The collected data is cleansed to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors. The analysis results are then displayed visually as graphs and charts. For example, data on ceramics can be run through a machine learning algorithm to evaluate durability, aesthetic value, and the rarity of manufacturing techniques, and the results can be summarized in a radar chart.

[0917] 3. New product idea generation module

[0918] The server generates new product ideas using an algorithm that takes into account market trends and consumer needs. For example, the server may generate a design proposal for a new tableware set using ceramic techniques, reflecting market data that indicates a demand for simple, modern designs.

[0919] 4. Collaboration Partner Matching Module

[0920] The server searches its database for the best possible partner for a new product idea and suggests them. For example, if a new ceramic tableware set is being mass-produced, the server will compile a list of ceramic manufacturers and designers both in Japan and overseas.

[0921] 5. Proposal result display module

[0922] The terminal has a function to display new product ideas and potential collaboration partners sent from the server to the user. For example, the terminal displays a design idea for a new ceramic tableware set and a list of recommended partners, allowing the user to consider collaboration with an appropriate partner.

[0923] 6. Emotion Recognition Module

[0924] The device uses an emotion engine to recognize the user's emotions when the user inputs feedback. For example, it uses a smartphone camera to analyze the user's facial expressions and voice and recognizes emotional states such as "happiness" or "dissatisfaction."

[0925] 7. Feedback and Emotion Data Collection Module

[0926] The server collects the feedback and emotion data sent from the device and stores it in a database. For example, when a user gives feedback such as "I'm impressed" about the design of a new tableware set, the emotion is also analyzed and sent to the server.

[0927] 8. System Improvement Module

[0928] The server improves the system based on the collected feedback and emotional data. Based on the results of emotion recognition and feedback analysis, the server aims to improve the algorithm and diversify design proposals. For example, the server could analyze feedback such as "We want more design variations" and the emotion of "dissatisfaction" and reflect this in the next new product proposal.

[0929] Examples:

[0930] For example, when a user of the "Traditional Crafts Virtual Market" is looking at the design of a new ceramic tableware set, the app can analyze the user's facial expression with a camera and detect "joy." If the user provides feedback on a design, such as "it's very beautiful," that emotional data is sent to the server. The server analyzes this data and reflects it in generating the next design proposal.

[0931] Example prompt sentence:

[0932] "Use the following feedback and emotion data to train an algorithm to generate new ceramic design ideas. Feedback: 'So beautiful' Emotion: 'Joy'"

[0933] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0934] Step 1:

[0935] A server collects data about the craft.

[0936] Input: Internal database or external API

[0937] Data processing: Through internal databases and external APIs, we obtain technical information, manufacturing processes, materials used, historical background, and information on related craftspeople.

[0938] Output: Collected database

[0939] Specific operation: The server accesses a database related to "ceramics," obtains various information, and stores it in the database.

[0940] Step 2:

[0941] The server analyzes the collected technical data from multiple perspectives.

[0942] Input: Collected database

[0943] Data calculation: Data is cleansed to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors.

[0944] Output: Analysis results

[0945] How it works: The server runs the ceramic data through machine learning algorithms (such as TensorFlow or PyTorch) to evaluate the durability, aesthetic value, and rarity of the manufacturing technology, and then summarizes the ceramics' strengths and weaknesses in a radar chart.

[0946] Step 3:

[0947] The server generates new product ideas based on the analysis results.

[0948] Input: Analysis results

[0949] Data calculations: Using algorithms that take into account market trends and consumer needs, new product ideas are proposed.

[0950] Output: New product idea

[0951] What it does: The server uses market data to generate design ideas for a new ceramic dinnerware set, reflecting the desire for simple, contemporary designs.

[0952] Step 4:

[0953] The server searches a database for potential collaboration partners that are best suited to the new product idea and makes suggestions.

[0954] Input: New product idea

[0955] Data calculation: Evaluate the suitability of collaboration partners based on their technical capabilities and past performance.

[0956] Output: List of partners

[0957] Specific operation: The server compiles a list of suitable partner candidates from a database of domestic and international ceramic manufacturers and designers.

[0958] Step 5:

[0959] The terminal displays the new product proposals and collaboration partner candidates sent from the server to the user.

[0960] Input: New product ideas, potential partners

[0961] Output: Data displayed on the user's terminal

[0962] Specific operation: The device displays design proposals for a new ceramic tableware set and a list of recommended partners, which the user can review to consider partner collaboration.

[0963] Step 6:

[0964] The terminal recognizes the user's emotions using an emotion engine when the user inputs feedback.

[0965] Input: User's facial expression data, voice data

[0966] Data calculation: Using an emotion recognition library (e.g., OpenCV or Affectiva), analyze the user's facial expressions and voice to determine their emotional state.

[0967] Output: User emotion data

[0968] Specific operation: The smartphone camera is used to capture the user's facial expressions and analyze their emotional state, such as "happiness" or "dissatisfaction."

[0969] Step 7:

[0970] The server collects and analyzes the feedback and emotion data sent from the terminals.

[0971] Input: User feedback, emotional data

[0972] Data calculation: Analyze the feedback content and emotional data and use it for the next proposal.

[0973] Output: Analysis results

[0974] Specific operation: The server analyzes feedback such as "I would like more design variations" and "dissatisfaction" feelings, and reflects this in the next new product proposal.

[0975] Step 8:

[0976] The server improves the system based on feedback including emotional data.

[0977] Input: Analysis results

[0978] Data calculation: Improve the algorithm based on emotion recognition results and feedback analysis results.

[0979] Output: Updated system

[0980] What it does: The server implements a new algorithm and makes adjustments to generate better product suggestions based on emotions.

[0981] 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.

[0982] 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.

[0983] 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.

[0984] [Third embodiment]

[0985] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0986] 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.

[0987] 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).

[0988] 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.

[0989] 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.

[0990] 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).

[0991] 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.

[0992] 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.

[0993] 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.

[0994] 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.

[0995] 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.

[0996] 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."

[0997] As an embodiment of the present invention, the processing flow of the entire system will be explained in natural language below, along with the roles of each entity, namely, server, terminal, and user, and specific examples.

[0998] 1. Collection of technical data

[0999] The server collects data about craft techniques. Through an internal database or external API, the server obtains technical information, manufacturing processes, materials used, historical background, and information about the artisans involved.

[1000] Examples:

[1001] The server collects technical information about "ceramics" from various databases, including the ceramic manufacturing process, the types of clay and glazes used, and the history of famous artisans and their works.

[1002] 2. Data analysis and visualization

[1003] The server analyzes the collected technical data from multiple angles. It cleanses the data and extracts specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts to visualize the analysis results.

[1004] Examples:

[1005] The server analyzes the ceramics data and identifies their strengths as durability, aesthetic value, and rare manufacturing techniques, and then summarizes these characteristics in a radar chart.

[1006] 3. New product idea generation

[1007] The server generates new product ideas based on the analysis results, using an algorithm that takes into account market trends and consumer needs to propose new product ideas.

[1008] Examples:

[1009] The server generates design proposals for a new set of tableware using ceramic techniques, based on market data that reflects the desire for simple, contemporary designs.

[1010] 4. Matching collaboration partners

[1011] The server searches a database for potential partners best suited to a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[1012] Examples:

[1013] With the aim of mass-producing a new ceramic tableware set, the server compiles a list of optimal partners from a database of ceramic manufacturers and designers both in Japan and overseas.

[1014] 5. Presentation of proposed results

[1015] The terminal displays the new product ideas and partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[1016] Examples:

[1017] The device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[1018] 6. Feedback and Improvement

[1019] Users provide feedback to the system, and the server uses that feedback to improve the system's accuracy. Users input their opinions about proposed ideas and partners, and the server analyzes them to identify areas for improvement.

[1020] Examples:

[1021] Users can send feedback to the server, such as "I want more design variations." The server analyzes this feedback and improves the algorithm to generate more diverse design proposals next time.

[1022] This will enable us to maximize the use of traditional Japanese craftsmanship and modern artisan skills, create new product value, and find suitable collaboration partners.In addition, we will be able to continuously improve the system through feedback from users and make better proposals.

[1023] The processing flow will be explained below.

[1024] Step 1:

[1025] The server connects to an internal database or external API to collect information about the craft techniques, including the specific process of the technique, the materials used, historical background, and information about the artisans involved.

[1026] Specific operation:

[1027] The server accesses a database on "ceramics" and retrieves information on the manufacturing process, material characteristics, historical background, and related craftsmen.

[1028] Step 2:

[1029] The server cleanses the collected craft technology data, filling in missing values ​​and removing outliers.

[1030] Specific operation:

[1031] The server organizes the acquired ceramic data, detects incomplete data and outliers, and completes them.

[1032] Step 3:

[1033] The server analyzes the data from multiple angles and extracts the strengths, weaknesses, rarity, and points of differentiation of the craftsmanship from competitors.

[1034] Specific operation:

[1035] The server runs the ceramic data through machine learning algorithms to assess its durability, aesthetic value, rarity of manufacturing techniques, and other factors, identifying its strengths and weaknesses.

[1036] Step 4:

[1037] The server visualizes the analysis results and generates graphs and charts.

[1038] Specific operation:

[1039] The server displays the strengths and weaknesses of ceramics in the form of radar charts, heat maps, and other formats.

[1040] Step 5:

[1041] The server generates new product ideas taking into account market trends and consumer needs.

[1042] Specific operation:

[1043] The server analyzes market data and generates new product ideas, such as a "modern design ceramic tableware set."

[1044] Step 6:

[1045] The server selects and proposes the most suitable collaboration partner for the new product idea.

[1046] Specific operation:

[1047] The server searches a database of domestic and international ceramic manufacturers and designers and lists suitable partners to manufacture the new ceramic tableware set.

[1048] Step 7:

[1049] The terminal displays the new product proposals and collaboration partner candidates sent from the server to the user.

[1050] Specific operation:

[1051] The terminal displays a design proposal for a new ceramic tableware set and a list of recommended partners on a user interface.

[1052] Step 8:

[1053] The user inputs feedback about the proposed ideas and partners and sends it to the server.

[1054] Specific operation:

[1055] The user enters feedback on the device, such as "I would like more design variations," and presses the send button.

[1056] Step 9:

[1057] The server analyzes the received feedback and identifies improvements for the next implementation process.

[1058] Specific operation:

[1059] The server analyzes the text of user feedback and determines that the algorithm needs to be improved to increase design variation.

[1060] Step 10:

[1061] The server updates the system's algorithms and database based on the analysis results, improving the accuracy of the entire system.

[1062] Specific operation:

[1063] Based on the feedback, the server improves the machine learning algorithm and updates the model to generate diverse design proposals.

[1064] Example 1

[1065] 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."

[1066] In the conventional product development process for craftsmanship, data collection and analysis were time-consuming, making it difficult to efficiently generate new product ideas and propose appropriate collaboration partners. There was also a lack of mechanisms for appropriately incorporating user feedback and improving the system. This limited the speed and quality of product development.

[1067] 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.

[1068] In this invention, the server includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas utilizing craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for collecting user feedback, means for improving the system based on the collected feedback, means for acquiring data on craft techniques using an external API, means for visually visualizing the analysis results, and means for using a generative AI model when generating new product ideas. This makes it possible to efficiently generate new product ideas based on craft techniques and propose appropriate collaboration partners, and to continuously improve the system by utilizing user feedback.

[1069] "Craftsmanship" refers to crafts made using traditional methods and techniques, as well as related manufacturing processes, materials and designs.

[1070] "Means of collecting data" refers to devices and systems for obtaining information related to craft techniques from various databases and external APIs.

[1071] "Means for analyzing data from multiple perspectives" refers to techniques and methods for analyzing collected data from various perspectives and extracting specific information.

[1072] "Means for generating new product ideas" refers to devices and methods for devising new crafts and their applied products based on the results of the analysis.

[1073] "Means for proposing collaborative partners" refers to devices and systems for selecting and proposing the most suitable collaborating companies and craftsmen to realize new product ideas.

[1074] "Means for displaying the proposal results on the user terminal" refers to a device or system for visually showing the proposal contents sent from the server to the user.

[1075] "Means for collecting user feedback" refers to a device or system for obtaining opinions and ratings provided by users.

[1076] "Means for improving the system based on feedback" refers to techniques and methods for analyzing collected feedback and improving the performance and accuracy of the system.

[1077] "Means of obtaining data using external APIs" refers to programs and systems for obtaining information from external databases and services via the Internet.

[1078] "Visual visualization means" refers to devices and technologies for converting and displaying the results of data analysis in a visual format such as a graph or chart.

[1079] "Means for using generative AI models" refers to devices or programs that utilize models using artificial intelligence technology to generate new ideas and concepts.

[1080] An embodiment of the present invention relates to a system that efficiently generates ideas for new products based on craft techniques and proposes collaboration partners, and realizes continuous improvement of the system based on user feedback.

[1081] Technical data collection

[1082] The server collects data about craft techniques, using internal databases and external APIs to obtain technical information, manufacturing processes, materials used, historical background, and artisan information.

[1083] For example, the server collects technical information about "ceramics" from various databases, including the ceramic manufacturing process, the types of clay and glazes used, and the history of famous artisans and their works.

[1084] Data Analysis and Visualization

[1085] We analyze the technical data collected by the server from multiple angles, cleanse the data, extract specific strengths, weaknesses, rarity, and points of differentiation from competitors, and generate visual graphs and charts to visualize the analysis results.

[1086] As a specific example, the server analyzes data on ceramics, identifies its strengths as durability, aesthetic value, and rare manufacturing techniques, and summarizes these in a radar chart for each characteristic.

[1087] Generate new product ideas

[1088] The server generates new product ideas based on the analysis results, using algorithms that take into account market trends and consumer needs, and utilizing generative AI models to propose new product ideas.

[1089] As a concrete example, the server generates design proposals for a new set of tableware using ceramic techniques. Based on market data, the following prompt is used to reflect the desire for a simple, modern design:

[1090] "Please propose a new design for a ceramic tableware set, taking into consideration current market trends."

[1091] Matching collaboration partners

[1092] The server searches a database for the best candidates for collaboration partners for a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[1093] As a concrete example, the server considers mass production of a new ceramic tableware set and lists the most suitable partners from a database of ceramic manufacturers and designers both in Japan and overseas.

[1094] Presentation of proposed results

[1095] The terminal displays the new product ideas and partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[1096] For example, the device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[1097] Feedback and Improvements

[1098] Users provide feedback to the system, and the server uses that feedback to improve the system's accuracy. Users input their opinions about proposed ideas and partners, and the server analyzes them to identify areas for improvement.

[1099] As a concrete example, a user can send feedback to the server such as "I would like more design variations," and the server will analyze this and improve its algorithm to generate more diverse design proposals next time.

[1100] This system will enable the creation of new product value by maximizing the use of traditional Japanese craft techniques and modern artisanal skills, and will enable the efficient search for suitable collaboration partners. Furthermore, the system will be continuously improved through user feedback, enabling the creation of better proposals.

[1101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1102] Step 1:

[1103] A server collects data about craft skills.

[1104] Input: The server takes input from internal database queries and request parameters from external APIs.

[1105] Data processing: The server retrieves data from these sources and cleanses it by detecting duplicates and missing information.

[1106] Output: A clean set of craft data is produced.

[1107] Specific operation: The server sends an HTTP request to the specified API endpoint, receives technical information as a response, and issues a SELECT query to extract data from the internal database.

[1108] Step 2:

[1109] The technical data collected by the server is analyzed from multiple perspectives.

[1110] Input: The clean data collected in step 1.

[1111] Data processing: The server uses statistical analysis, text mining techniques, etc. to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors.

[1112] Output: Characteristic data as the analysis result and visualization data based on it are generated.

[1113] Specific operation: The server calls statistical functions to analyze the collected data and generates the results as radar charts and graphs.

[1114] Step 3:

[1115] The server generates new product ideas based on the analysis results.

[1116] Inputs: Analysis results generated in step 2. External data on market trends and consumer needs.

[1117] Data processing: The server uses the generative AI model to generate new product ideas.

[1118] Output: A prototype of the new product idea is generated.

[1119] Specific operation: The server inputs the prompt statement and analysis results into the generative AI model and obtains the output idea data.

[1120] Step 4:

[1121] The server searches for and evaluates potential collaboration partners related to the new product idea.

[1122] Input: Prototype of new product idea generated in step 3. Database of collaboration partners.

[1123] Data processing: Scoring potential partners based on suitability criteria and shortlisting the most suitable partners.

[1124] Output: A list of high-scoring partner candidates is generated.

[1125] What it does: The server queries internal and external partner databases and applies a rating algorithm to generate a score.

[1126] Step 5:

[1127] The terminal displays the new product ideas and partner candidates sent from the server to the user.

[1128] Input: Partner candidate list generated in step 4. Prototype of new product idea.

[1129] Data processing: Visually display information using a GUI.

[1130] Output: Display of design proposals and partner list.

[1131] Specific operation: The device applies the data obtained from the server to the GUI components and renders it on the screen.

[1132] Step 6:

[1133] The user provides feedback to the system.

[1134] Input: Ratings and opinions on new product ideas and potential partners.

[1135] Data processing: Collect feedback and send it to the server.

[1136] Output: Sending feedback data.

[1137] Specific behavior: A user enters their opinion into the feedback form and clicks the submit button, which sends an HTTP POST request to the server.

[1138] Step 7:

[1139] The server analyzes user feedback to improve the accuracy of the system.

[1140] Input: Feedback data collected in step 6.

[1141] Data processing: Analyzing feedback data to identify areas for improvement in algorithms and models.

[1142] Output: Improved algorithms and models.

[1143] Specific operation: The server analyzes the feedback data using natural language processing technology and adjusts and optimizes the generative AI model and related algorithms based on the insights gained.

[1144] (Application example 1)

[1145] 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."

[1146] Conventional methods of providing information about crafts make it difficult for customers to learn detailed technical information or the manufacturing background of crafts. Furthermore, developing new products and selecting appropriate collaboration partners are not easy, and there is a lack of mechanisms for incorporating user feedback into the system. Furthermore, the interactive information provided to customers in craft displays in physical stores is limited, creating a need for an improved customer experience.

[1147] 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.

[1148] In this invention, the server includes a means for collecting data on craft techniques, a means for multifaceted analysis of the collected craft technique data, and a means for generating new product ideas that utilize craft techniques based on the analysis results. This enables the provision of detailed technical information on crafts, the development of new products, and the selection of collaboration partners. Furthermore, by including a means for visually displaying craft information using augmented reality, the customer experience in physical stores can be improved.

[1149] "Craftsmanship" refers to the techniques used by artisans to create artistic products by hand using traditional methods and techniques.

[1150] "Data collection means" refers to the mechanism for obtaining necessary information from internal databases related to craft techniques and external APIs.

[1151] "Data analysis means" refers to a system for cleansing collected craft technology data and analyzing it from multiple perspectives.

[1152] "New product idea generation means" refers to a system for proposing new crafts and their designs based on analyzed data.

[1153] The "means for proposing collaboration partners" refers to a mechanism for proposing optimal manufacturing partners or collaborators for the new product ideas that have been generated.

[1154] "User terminal display means" refers to a mechanism for displaying the proposal results and related information on a device that is directly operated by the user.

[1155] "Feedback collection means" refers to a mechanism for collecting user opinions and requests into the system.

[1156] "System improvement measures" refer to mechanisms for improving the system's algorithms and functions based on collected feedback.

[1157] "Augmented reality display means" refers to a mechanism for visually displaying additional information about real-world artifacts via a smartphone or dedicated device.

[1158] As an embodiment of the present invention, a processing flow of a new craft product suggestion system will be described.

[1159] Overall system configuration

[1160] This system mainly consists of three entities: a server, a terminal, and a user. The server collects and analyzes data, generates suggestions, and analyzes feedback. The terminal provides information to the user and collects feedback. It also uses augmented reality (AR) to visually display information about real crafts.

[1161] Server Roles

[1162] 1. Collection of technical data

[1163] The server primarily collects data about craft techniques through internal databases and external APIs. This data includes information about the manufacturing process, materials, historical background, and the artisans involved. For example, it collects technical information about ceramics, including details about the manufacturing process, clays, and glazes used.

[1164] 2. Data analysis and visualization

[1165] The server then cleanses the collected data and performs a multifaceted analysis, extracting strengths, weaknesses, rarity, and points of differentiation from competitors, and presenting these in visual formats such as radar charts. This analysis identifies characteristics such as the durability, aesthetic value, and rare manufacturing techniques of ceramics, for example.

[1166] 3. New product idea generation

[1167] Based on the analysis results, the server generates new product ideas, taking into account market trends and consumer needs through an algorithm, suggesting new product ideas such as a tableware set with a simple, modern design.

[1168] 4. Matching collaboration partners

[1169] The server searches its database for the optimal partner for the new product idea and proposes it, using criteria such as technical capabilities and past performance as criteria. For example, it could create a list of optimal partners from ceramic manufacturers and designers both in Japan and overseas.

[1170] Device Role

[1171] 1. Displaying the proposed results

[1172] The terminal displays new product ideas and potential collaboration partners sent from the server in a visually easy-to-understand format to the user. For example, it displays a design idea for a new ceramic tableware set and a list of recommended partners.

[1173] 2. Augmented reality features

[1174] The device is equipped with an AR function, allowing users to visually display product information, manufacturing process, and artisan information by pointing the camera at an actual craft item.

[1175] User Roles

[1176] 1. Providing Feedback

[1177] Users can provide their opinions and requests regarding the displayed suggestions. For example, they can send feedback such as "I would like more design variations."

[1178] System Improvement

[1179] The server collects and analyzes user feedback to improve the system's algorithms and functions, and also incorporates the collected feedback into future proposals.

[1180] Hardware and software used

[1181] The system uses the following hardware and software:

[1182] Hardware: Server, smartphone (or tablet)

[1183] Software: Flask (web framework), SQLite (database), NLTK (text analysis)

[1184] Examples and prompts

[1185] (Example)

[1186] User example 1: A customer visiting a physical store wants to learn about the manufacturing techniques behind a new tea bowl. By pointing their smartphone camera at the bowl, AR will display background information about the manufacturing process and the craftsman.

[1187] User example 2: When a user enters their idea for tableware using a durable and rare glaze into the app, new product ideas and collaboration partners based on that idea are displayed.

[1188] (Example of a prompt)

[1189] "Generate new ceramic design ideas. The target audience is young people in their 20s who want simple, modern designs."

[1190] "Please suggest improvements to increase product variety based on the feedback below. Feedback: I would like more design variations."

[1191] The above is a detailed embodiment of the present invention. This system makes it possible to propose new products that utilize craft techniques, provide effective information, and improve customer experience.

[1192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1193] Step 1:

[1194] The server collects data about craft techniques. As input, it receives information from external APIs and internal databases. This data includes manufacturing processes, materials, historical background, artisan information, etc. The server retrieves this data and stores it in the internal database. The output is the collected raw data.

[1195] Step 2:

[1196] The data collected by the server is cleansed and analyzed from multiple perspectives. The input is the raw data collected in step 1. Data cleansing removes incomplete and duplicate data. The cleansed data is then analyzed using analytical algorithms to extract strengths, weaknesses, rarity, and points of differentiation from competitors. The output is a summary of the analysis results, and visualized data such as radar charts is also generated.

[1197] Step 3:

[1198] The server generates new product ideas based on the analysis results. The input is the analysis results obtained in step 2. A generative AI model is used to generate new product designs and concepts, taking into account market trends and consumer needs. Prompt statements are used to instruct the generative AI model. The output is details of the new product ideas.

[1199] Step 4:

[1200] The server proposes optimal collaboration partners for new product ideas generated by the server. The input is the new product idea generated in step 3. An algorithm that takes into account past performance and technical capabilities is used to search for optimal collaboration partners from a database. The output is a list of candidate collaboration partners.

[1201] Step 5:

[1202] The terminal visually displays the proposal results from the server to the user. The input is the new product idea and list of collaboration partners obtained in step 4. The information is displayed in a format that is easy for the user to understand. For example, a design proposal for a new ceramic tableware set and a list of recommended partners are displayed on the screen. The output is the displayed information.

[1203] Step 6:

[1204] The device displays information about the craft using augmented reality. The input is video data acquired when the user points the smartphone camera at the craft. The device displays detailed information about the craft obtained from the server as AR. For example, if the camera is pointed at an actual tea bowl, the manufacturing process and background information about the craftsman will be displayed on the screen. The output is information displayed using augmented reality.

[1205] Step 7:

[1206] The user enters feedback based on the information provided. The input is the user's opinion or request. For example, the user may send feedback such as "I would like more design variations." The output is the collected feedback data.

[1207] Step 8:

[1208] The server collects user feedback and improves the system. The input is the feedback data collected in step 7. The feedback is analyzed and used as data to improve the system's algorithms and functions, which can then be reflected in the next proposal. The output is improved system settings and algorithms.

[1209] 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.

[1210] As an embodiment of the present invention, the processing flow of the entire system that combines the emotion engine will be explained in natural language below. The roles of each entity, the server, terminal, and user, will be explained along with specific examples.

[1211] 1. Collection of technical data

[1212] The server collects data about craft techniques. Through an internal database or external API, the server obtains technical information, manufacturing processes, materials used, historical background, and information about the artisans involved.

[1213] Examples:

[1214] The server accesses a database on "ceramics" and retrieves information on the manufacturing process, material characteristics, historical background, and associated craftsmen.

[1215] 2. Data analysis and visualization

[1216] The server analyzes the collected technical data from multiple angles. It cleanses the data and extracts specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts to visualize the analysis results.

[1217] Examples:

[1218] The server then applies machine learning algorithms to the ceramic data, assessing its durability, aesthetic value, and the rarity of its manufacturing techniques, to identify its strengths and weaknesses, which are then compiled into a radar chart for each characteristic.

[1219] 3. New product idea generation

[1220] The server generates new product ideas based on the analysis results, using an algorithm that takes into account market trends and consumer needs to propose new product ideas.

[1221] Examples:

[1222] The server generates design proposals for a new set of tableware using ceramic techniques, based on market data that reflects the desire for simple, contemporary designs.

[1223] 4. Matching collaboration partners

[1224] The server searches a database for potential partners best suited to a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[1225] Examples:

[1226] With the aim of mass-producing a new ceramic tableware set, the server compiles a list of optimal partners from a database of domestic and international ceramic manufacturers and designers.

[1227] 5. Presentation of proposed results

[1228] The terminal displays the new product ideas and collaboration partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[1229] Examples:

[1230] The device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[1231] 6. Emotion Recognition by Emotion Engine

[1232] The device recognizes the user's emotion using the emotion engine when the user inputs feedback, and transmits not only the user's feedback but also the emotion information to the server.

[1233] Examples:

[1234] The device analyzes the user's facial expressions and voice to recognize emotions such as "happiness" or "dissatisfaction." When the user gives feedback such as "I'm impressed" about the design of a new tableware set, that emotion is also analyzed.

[1235] 7. Collecting feedback and sentiment data

[1236] The server receives and analyzes the feedback and emotional data sent from the device, thereby understanding the user's true reaction and utilizing it for future suggestions.

[1237] Examples:

[1238] The server analyzes feedback such as "I want more design variations" and feelings of "dissatisfaction" and reflects this in the next new product proposal.

[1239] 8. Continuous improvement of the system

[1240] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[1241] Examples:

[1242] The server implements new algorithms based on data from the emotion engine and makes adjustments to generate better emotion-based product suggestions.

[1243] In this way, by combining an emotion recognition engine, it is possible to make the most of traditional Japanese craft techniques and modern artisan skills to create new product value, as well as to realize a system that makes even more accurate suggestions based on feedback based on the user's emotions.

[1244] The processing flow will be explained below.

[1245] Step 1:

[1246] The server connects to an internal database and external APIs to collect information about craft techniques, including technical information, manufacturing processes, materials used, historical background, and artisan information.

[1247] Specific operation:

[1248] The server retrieves information from a ceramics database about the manufacturing process, the types of clay and glazes used, historical background, and artisans.

[1249] Step 2:

[1250] The server pre-processes the collected craft data, cleansing it, filling in missing values, and removing outliers.

[1251] Specific operation:

[1252] The server cleanses the acquired ceramic data, identifying and completing incomplete data and outliers.

[1253] Step 3:

[1254] The server analyzes the data from multiple angles and applies machine learning algorithms to extract the strengths, weaknesses, and rarity of the craftsmanship, as well as points of differentiation from competitors.

[1255] Specific operation:

[1256] The server analyzes the ceramics' data, assessing their durability, aesthetic value, and the rarity of their manufacturing techniques, and identifies their strengths and weaknesses.

[1257] Step 4:

[1258] The server visualizes the analysis results, generating graphs and charts based on the extracted features and summarizing them in a visually easy-to-understand format.

[1259] Specific operation:

[1260] The server displays the strengths and weaknesses of ceramics in the form of radar charts, heat maps, and other formats.

[1261] Step 5:

[1262] The server generates new product ideas taking into account market trends and consumer needs. Using an algorithm, the server combines collected data with market needs to propose new product ideas.

[1263] Specific operation:

[1264] The server analyzes market data and generates a new product idea: a "modern design ceramic tableware set."

[1265] Step 6:

[1266] The server searches a database for the most suitable partner for a new product idea and proposes it. Suitability is evaluated based on technical capabilities and past performance.

[1267] Specific operation:

[1268] The server searches a database of domestic and international ceramic manufacturers and designers, and lists suitable partners for mass production of new ceramic tableware sets.

[1269] Step 7:

[1270] The terminal displays the new product ideas and collaboration partner candidates sent from the server to the user, and displays the received data in a visually easy-to-understand format.

[1271] Specific operation:

[1272] The terminal displays a design proposal for a new ceramic tableware set and a list of recommended partners on a user interface.

[1273] Step 8:

[1274] The device uses an emotion engine to recognize the user's emotions when the user inputs feedback, analyzes the user's facial expressions and voice, and transmits the emotional information to the server.

[1275] Specific operation:

[1276] When a user inputs feedback such as "I'm happy" about a new ceramic design, the device analyzes the user's facial expression and intonation of the voice to recognize the emotion of "joy."

[1277] Step 9:

[1278] The server receives and analyzes the feedback and emotion data sent from the device, and evaluates new product ideas based on the user's emotions and feedback.

[1279] Specific operation:

[1280] The server analyzes the feedback such as "great design" and the emotion data such as "delight" to ensure that the new design is well-received.

[1281] Step 10:

[1282] The server improves the system based on feedback and emotional data, refining the algorithm and making adjustments to improve the accuracy of the next suggestion.

[1283] Specific operation:

[1284] The server updates the machine learning algorithm based on the feedback, including the emotional data, and makes adjustments to generate more emotionally sensitive product suggestions next time.

[1285] The above is the specific processing flow of the entire system that combines the emotion engine. This will realize a system that makes the most of traditional Japanese craftsmanship and modern artisan skills to create new product value and makes highly accurate, integrated proposals based on user emotional feedback.

[1286] Example 2

[1287] 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."

[1288] Traditional craft data collection and analysis systems lack sufficient accuracy and flexibility in generating new product ideas and recommending optimal collaboration partners. They also lack effective methods for properly collecting user feedback and incorporating it into future proposals. Furthermore, feedback analysis does not take user emotions into account, making it difficult to understand users' authentic reactions and continuously improve the system.

[1289] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1290] In this invention, the server includes means for collecting information on craft techniques, means for analyzing the collected craft technique information from various angles, means for generating new product ideas that utilize craft techniques based on the analysis results, means for proposing optimal collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for collecting user feedback, means for improving the system based on the collected feedback and emotional data, and means for recognizing user emotions using an emotion recognition engine. This enables multifaceted analysis of the collected data, generation of new product ideas and proposals for optimal collaboration partners, and analysis of user feedback including emotional data, thereby realizing continuous improvement of the system.

[1291] "Craftsmanship information" includes technical information about the craft, the manufacturing process, materials used, historical background, and information about the artisans involved.

[1292] "Collection means" refers to the means for collecting information via various databases and external APIs.

[1293] "Means for analyzing from multiple angles" refers to technical means for analyzing collected information from multiple angles and extracting its strengths, weaknesses, rarity, and points of differentiation from competitors.

[1294] "Means for generating new product ideas" means techniques for generating new product designs and concepts, taking into account market trends and consumer needs.

[1295] The "means of proposing the most suitable collaboration partner" is a technology that searches a database for and proposes the most suitable collaboration partner candidate for a new product proposal based on technical capabilities and past performance.

[1296] The "means for displaying the proposal results on the user terminal" refers to a technical means for displaying the generated new product proposals and collaboration partner candidates on the user terminal.

[1297] "Means for collecting feedback from users" refers to means for collecting opinions and evaluations from users.

[1298] "Means for improving the system based on feedback and emotional data" refers to technical means for analyzing feedback and emotional data from users and improving the system algorithms and design proposals based on this.

[1299] An "emotion recognition engine" is a technology for recognizing a user's emotions, analyzing emotions such as joy, sadness, and anger from facial expressions and voice.

[1300] As an embodiment of the present invention, the processing flow of the entire system is shown below. This system mainly involves collaboration between the server, terminals, and users, and uses various technologies to propose new products and collect feedback.

[1301] 1. Collection of technical data

[1302] The server collects information about craft techniques. It connects to an internal database (e.g., MongoDB) and also retrieves technical information, manufacturing processes, materials used, historical background, and related artisan information from external sources through a RESTful API.

[1303] Example: A server accesses a database about "ceramics" and retrieves information about the manufacturing process, material properties, historical background, and associated artisans.

[1304] 2. Data analysis and visualization

[1305] The server analyzes the collected information from multiple angles using Python and R. It cleanses the data and uses machine learning algorithms such as k-means clustering to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts using Matplotlib and Plotly to visualize the analysis results.

[1306] Example: A server runs data on ceramics through a machine learning algorithm to evaluate its durability, aesthetic value, rarity of manufacturing techniques, etc., and identify its strengths and weaknesses. These are then compiled into a radar chart for each characteristic.

[1307] 3. New product idea generation

[1308] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate new product ideas. The server uses algorithms based on market trends and consumer needs to propose new product ideas.

[1309] Example: A server prompts a generative AI model with the prompt "Generate ideas for a new ceramic tableware set with a modern design" and receives the generated ideas.

[1310] 4. Matching collaboration partners

[1311] The server searches a database (e.g., MySQL) for the best partner candidates for a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[1312] Example: Using an SQL query to find relevant partners in a database, calculate a reputation score and shortlist the best partners.

[1313] 5. Presentation of proposed results

[1314] The device displays new product ideas and potential collaboration partners sent from the server to the user, using JavaScript and HTML5 to present the data in a visually easy-to-understand manner.

[1315] Example: Using React.js on the front end, we display the design of new product ideas and a list of partners. Once the user selects a partner, details of the partner candidate are also displayed in a popup.

[1316] 6. Emotion Recognition by Emotion Engine

[1317] When the user inputs feedback, the device uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion, and then sends the user's feedback and emotional information to the server.

[1318] Example: When filling out a form, a webcam captures the user's facial expression, and the image data is sent to the Emotion API to recognize emotions. The resulting emotional data, such as "happiness" or "sadness," is then displayed.

[1319] 7. Collecting feedback and sentiment data

[1320] The server receives the feedback and emotion data sent from the device and analyzes it using Python's Pandas, which allows the server to understand the user's true reaction and use it to improve the next experience.

[1321] Example: The server combines the received feedback "I like the new design" with the emotion data "joy" and performs detailed analysis using a text analysis tool.

[1322] 8. Continuous improvement of the system

[1323] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[1324] Example: Using the results of a sentiment analysis engine, we can update the training dataset for a machine learning model and improve the algorithm that generates new design ideas.

[1325] In this way, by combining the emotion recognition engine, we have created a system that can make highly accurate new product proposals through the collection and analysis of craft technology data, the generation of new product ideas, the proposal of collaboration partners, and the collection and analysis of feedback. This system can reflect user feedback based on their emotions and make continuously improved new product proposals.

[1326] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1327] The flow of this system's program processing

[1328] Step 1:

[1329] The server collects information about craft techniques, connecting to an internal database (e.g., MongoDB) and also retrieving technical information, manufacturing processes, materials used, historical background, and related artisan information from external sources through a RESTful API.

[1330] Input: Database configuration information, external API endpoint

[1331] Output: List of collected crafting and technical information

[1332] What it does: Reads the configuration file "config.json", gets the database URL and authentication information, connects to it using a MongoDB client, sends a GET request to an external API endpoint, and retrieves the returned JSON data.

[1333] Step 2:

[1334] The server cleanses the collected information, completing missing data values ​​and detecting and correcting inconsistencies.

[1335] Input: List of collected craft technical information

[1336] Output: A list of cleansed craft information

[1337] Specific operation: Using Python's Pandas library, the data is read into a DataFrame and cleansed, such as filling in missing values ​​with the mean value.

[1338] Step 3:

[1339] The server then performs multifaceted analysis of the cleansed data, using machine learning algorithms such as k-means clustering to extract the strengths, weaknesses, and rarity of the technology, as well as points of differentiation from competitors.

[1340] Input: Cleansed list of craft information

[1341] Output: A list of analysis results (strengths, weaknesses, rarity, points of differentiation from competitors)

[1342] What it does: Uses the Scikit-learn library to perform k-means clustering to divide the data into clusters, calculates the center value within each cluster, and identifies strengths and weaknesses.

[1343] Step 4:

[1344] The server visualizes the analysis results, generating graphs and charts using Matplotlib and Plotly.

[1345] Input: List of analysis results (strengths, weaknesses, rarity, points of differentiation from competitors)

[1346] Output: Visualized graphs and charts

[1347] What it does: Create a radar chart using Matplotlib to visually display the strengths and weaknesses of each technology.

[1348] Step 5:

[1349] The server uses generative AI models (e.g., OpenAI GPT-4) to generate new product ideas, using algorithms based on market trends and consumer needs.

[1350] Input: Prompt statement (e.g., "Generate ideas for a new ceramic tableware set with a modern design"), analysis results

[1351] Output: List of new product ideas

[1352] Specific operation: Provide a prompt to the generative AI model and receive the generated ideas.

[1353] Step 6:

[1354] The server searches a database (e.g., MySQL) for the best partner candidates for the new product idea and proposes them. They are evaluated based on their technical capabilities and past performance.

[1355] Input: List of new product ideas, partner database

[1356] Output: A list of suitable collaboration partners

[1357] What it does: Uses an SQL query to find relevant partners in the database, calculates a rating score and lists the best partners.

[1358] Step 7:

[1359] The device displays new product ideas and potential collaboration partners sent from the server to the user, using JavaScript and HTML5 to present the data in a visually easy-to-understand manner.

[1360] Input: List of new product ideas, list of suitable collaboration partners

[1361] Output: New product ideas and potential collaboration partners displayed to the user

[1362] Specific operation: Using React.js on the front end, we display the design of new product ideas and a list of partners. Details of the partner candidates selected by the user are also displayed in a popup.

[1363] Step 8:

[1364] When the user inputs feedback, the device uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion, and then sends the user's feedback and emotional information to the server.

[1365] Input: Feedback text, user facial expressions and voice data

[1366] Output: Recognized emotion data, feedback sentence

[1367] Specific operation: When filling out a form, the system captures the user's facial expression with a webcam, sends the image data to the Emotion API, and recognizes their emotions. The resulting emotional data, such as "happiness" or "sadness," is then displayed.

[1368] Step 9:

[1369] The server receives and analyzes the feedback and emotion data sent from the device. It uses Python's Pandas to analyze the data and understand the user's true reaction.

[1370] Input: Feedback sentence, emotion data

[1371] Output: Report of analysis results

[1372] Specific operation: The server combines the received feedback "I like the new design" with the emotion data "joy" and performs detailed analysis using text analysis tools.

[1373] Step 10:

[1374] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[1375] Input: Analysis results report

[1376] Output: Improved algorithm, list of new design alternatives

[1377] What it does: Based on the results of the sentiment analysis engine, it updates the training dataset for the machine learning model and improves the algorithm that generates new design ideas.

[1378] The above steps work together to create a system that proposes new products based on craft techniques and performs feedback analysis.

[1379] (Application example 2)

[1380] 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."

[1381] In the traditional craft technology data collection, analysis, and product creation process, it is common to have a function for collecting user feedback, but there is a problem in that it is difficult to accurately recognize user emotions and improve the system based on that emotional data. This makes it difficult to understand users' true reactions and make more accurate product suggestions.

[1382] 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.

[1383] In this invention, the server includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas utilizing craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for recognizing user emotions, means for collecting feedback and emotional data from users, and means for improving the system based on the collected feedback and emotional data. This enables more accurate product suggestions by accurately understanding the user's emotional state and reflecting emotional feedback.

[1384] "Craftsmanship" refers to the art of producing fine and practical items using traditional or modern techniques.

[1385] "Means for collecting data" refers to the methods and devices used to obtain specific data and store it in the database.

[1386] "Means for multifaceted analysis" refers to methods and devices for analyzing collected data from multiple perspectives to gain a comprehensive understanding.

[1387] "Means for generating new product ideas" refers to methods or devices for generating ideas for new products or services based on collected and analyzed data.

[1388] The "means for proposing collaboration partners" refers to a method or device for selecting and proposing appropriate collaborators or companies based on the generated new product ideas.

[1389] "Means for displaying on a user terminal" refers to a method or apparatus for displaying information on a user's device (e.g., smartphone, tablet, or PC).

[1390] "Means for recognizing emotions" refers to a method or device for detecting and analyzing a user's emotions.

[1391] "Means for collecting feedback and emotional data" refers to a method or device for capturing a user's opinions and emotional state and storing them in a database.

[1392] "Means for improving the system" refers to methods and devices for improving the system's functionality and performance based on collected feedback and sentiment data.

[1393] The system of the present invention is constructed with the participation of a server, a terminal, and a user.

[1394] 1. Data Collection Module

[1395] The server has the function of collecting data on craft techniques. The data is obtained through internal databases and external APIs. For example, it accesses a database on "ceramics" to obtain information on the manufacturing process, material properties, historical background, and related craftspeople.

[1396] 2. Data Analysis and Visualization Module

[1397] The server runs algorithms to analyze the collected data from multiple angles. The collected data is cleansed to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors. The analysis results are then displayed visually as graphs and charts. For example, data on ceramics can be run through a machine learning algorithm to evaluate durability, aesthetic value, and the rarity of manufacturing techniques, and the results can be summarized in a radar chart.

[1398] 3. New product idea generation module

[1399] The server generates new product ideas using an algorithm that takes into account market trends and consumer needs. For example, the server may generate a design proposal for a new tableware set using ceramic techniques, reflecting market data that indicates a demand for simple, modern designs.

[1400] 4. Collaboration Partner Matching Module

[1401] The server searches its database for the best possible partner for a new product idea and suggests them. For example, if a new ceramic tableware set is being mass-produced, the server will compile a list of ceramic manufacturers and designers both in Japan and overseas.

[1402] 5. Proposal result display module

[1403] The terminal has a function to display new product ideas and potential collaboration partners sent from the server to the user. For example, the terminal displays a design idea for a new ceramic tableware set and a list of recommended partners, allowing the user to consider collaboration with an appropriate partner.

[1404] 6. Emotion Recognition Module

[1405] The device uses an emotion engine to recognize the user's emotions when the user inputs feedback. For example, it uses a smartphone camera to analyze the user's facial expressions and voice and recognizes emotional states such as "happiness" or "dissatisfaction."

[1406] 7. Feedback and Emotion Data Collection Module

[1407] The server collects the feedback and emotion data sent from the device and stores it in a database. For example, when a user gives feedback such as "I'm impressed" about the design of a new tableware set, the emotion is also analyzed and sent to the server.

[1408] 8. System Improvement Module

[1409] The server improves the system based on the collected feedback and emotional data. Based on the results of emotion recognition and feedback analysis, the server aims to improve the algorithm and diversify design proposals. For example, the server could analyze feedback such as "We want more design variations" and the emotion of "dissatisfaction" and reflect this in the next new product proposal.

[1410] Examples:

[1411] For example, when a user of the "Traditional Crafts Virtual Market" is looking at the design of a new ceramic tableware set, the app can analyze the user's facial expression with a camera and detect "joy." If the user provides feedback on a design, such as "it's very beautiful," that emotional data is sent to the server. The server analyzes this data and reflects it in generating the next design proposal.

[1412] Example prompt sentence:

[1413] "Use the following feedback and emotion data to train an algorithm to generate new ceramic design ideas. Feedback: 'So beautiful' Emotion: 'Joy'"

[1414] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1415] Step 1:

[1416] A server collects data about the craft.

[1417] Input: Internal database or external API

[1418] Data processing: Through internal databases and external APIs, we obtain technical information, manufacturing processes, materials used, historical background, and information on related craftspeople.

[1419] Output: Collected database

[1420] Specific operation: The server accesses a database related to "ceramics," obtains various information, and stores it in the database.

[1421] Step 2:

[1422] The server analyzes the collected technical data from multiple perspectives.

[1423] Input: Collected database

[1424] Data calculation: Data is cleansed to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors.

[1425] Output: Analysis results

[1426] How it works: The server runs the ceramic data through machine learning algorithms (such as TensorFlow or PyTorch) to evaluate the durability, aesthetic value, and rarity of the manufacturing technology, and then summarizes the ceramics' strengths and weaknesses in a radar chart.

[1427] Step 3:

[1428] The server generates new product ideas based on the analysis results.

[1429] Input: Analysis results

[1430] Data calculations: Using algorithms that take into account market trends and consumer needs, new product ideas are proposed.

[1431] Output: New product idea

[1432] What it does: The server uses market data to generate design ideas for a new ceramic dinnerware set, reflecting the desire for simple, contemporary designs.

[1433] Step 4:

[1434] The server searches a database for potential collaboration partners that are best suited to the new product idea and makes suggestions.

[1435] Input: New product idea

[1436] Data calculation: Evaluate the suitability of collaboration partners based on their technical capabilities and past performance.

[1437] Output: List of partners

[1438] Specific operation: The server compiles a list of suitable partner candidates from a database of domestic and international ceramic manufacturers and designers.

[1439] Step 5:

[1440] The terminal displays the new product proposals and collaboration partner candidates sent from the server to the user.

[1441] Input: New product ideas, potential partners

[1442] Output: Data displayed on the user's terminal

[1443] Specific operation: The device displays design proposals for a new ceramic tableware set and a list of recommended partners, which the user can review to consider partner collaboration.

[1444] Step 6:

[1445] The terminal recognizes the user's emotions using an emotion engine when the user inputs feedback.

[1446] Input: User's facial expression data, voice data

[1447] Data calculation: Using an emotion recognition library (e.g., OpenCV or Affectiva), analyze the user's facial expressions and voice to determine their emotional state.

[1448] Output: User emotion data

[1449] Specific operation: The smartphone camera is used to capture the user's facial expressions and analyze their emotional state, such as "happiness" or "dissatisfaction."

[1450] Step 7:

[1451] The server collects and analyzes the feedback and emotion data sent from the terminals.

[1452] Input: User feedback, emotional data

[1453] Data calculation: Analyze the feedback content and emotional data and use it for the next proposal.

[1454] Output: Analysis results

[1455] Specific operation: The server analyzes feedback such as "I would like more design variations" and "dissatisfaction" feelings, and reflects this in the next new product proposal.

[1456] Step 8:

[1457] The server improves the system based on feedback including emotional data.

[1458] Input: Analysis results

[1459] Data calculation: Improve the algorithm based on emotion recognition results and feedback analysis results.

[1460] Output: Updated system

[1461] What it does: The server implements a new algorithm and makes adjustments to generate better product suggestions based on emotions.

[1462] 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.

[1463] 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.

[1464] 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.

[1465] [Fourth embodiment]

[1466] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1467] 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.

[1468] 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).

[1469] 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.

[1470] 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.

[1471] 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).

[1472] 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.

[1473] 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.

[1474] 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.

[1475] 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.

[1476] 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.

[1477] 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.

[1478] 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."

[1479] As an embodiment of the present invention, the processing flow of the entire system will be explained in natural language below, along with the roles of each entity, namely, server, terminal, and user, and specific examples.

[1480] 1. Collection of technical data

[1481] The server collects data about craft techniques. Through an internal database or external API, the server obtains technical information, manufacturing processes, materials used, historical background, and information about the artisans involved.

[1482] Examples:

[1483] The server collects technical information about "ceramics" from various databases, including the ceramic manufacturing process, the types of clay and glazes used, and the history of famous artisans and their works.

[1484] 2. Data analysis and visualization

[1485] The server analyzes the collected technical data from multiple angles. It cleanses the data and extracts specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts to visualize the analysis results.

[1486] Examples:

[1487] The server analyzes the ceramics data and identifies their strengths as durability, aesthetic value, and rare manufacturing techniques, and then summarizes these characteristics in a radar chart.

[1488] 3. New product idea generation

[1489] The server generates new product ideas based on the analysis results, using an algorithm that takes into account market trends and consumer needs to propose new product ideas.

[1490] Examples:

[1491] The server generates design proposals for a new set of tableware using ceramic techniques, based on market data that reflects the desire for simple, contemporary designs.

[1492] 4. Matching collaboration partners

[1493] The server searches a database for potential partners best suited to a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[1494] Examples:

[1495] With the aim of mass-producing a new ceramic tableware set, the server compiles a list of optimal partners from a database of ceramic manufacturers and designers both in Japan and overseas.

[1496] 5. Presentation of proposed results

[1497] The terminal displays the new product ideas and partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[1498] Examples:

[1499] The device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[1500] 6. Feedback and Improvement

[1501] Users provide feedback to the system, and the server uses that feedback to improve the system's accuracy. Users input their opinions about proposed ideas and partners, and the server analyzes them to identify areas for improvement.

[1502] Examples:

[1503] Users can send feedback to the server, such as "I want more design variations." The server analyzes this feedback and improves the algorithm to generate more diverse design proposals next time.

[1504] This will enable us to maximize the use of traditional Japanese craftsmanship and modern artisan skills, create new product value, and find suitable collaboration partners.In addition, we will be able to continuously improve the system through feedback from users and make better proposals.

[1505] The processing flow will be explained below.

[1506] Step 1:

[1507] The server connects to an internal database or external API to collect information about the craft techniques, including the specific process of the technique, the materials used, historical background, and information about the artisans involved.

[1508] Specific operation:

[1509] The server accesses a database on "ceramics" and retrieves information on the manufacturing process, material characteristics, historical background, and related craftsmen.

[1510] Step 2:

[1511] The server cleanses the collected craft technology data, filling in missing values ​​and removing outliers.

[1512] Specific operation:

[1513] The server organizes the acquired ceramic data, detects incomplete data and outliers, and completes them.

[1514] Step 3:

[1515] The server analyzes the data from multiple angles and extracts the strengths, weaknesses, rarity, and points of differentiation of the craftsmanship from competitors.

[1516] Specific operation:

[1517] The server runs the ceramic data through machine learning algorithms to assess its durability, aesthetic value, rarity of manufacturing techniques, and other factors, identifying its strengths and weaknesses.

[1518] Step 4:

[1519] The server visualizes the analysis results and generates graphs and charts.

[1520] Specific operation:

[1521] The server displays the strengths and weaknesses of ceramics in the form of radar charts, heat maps, and other formats.

[1522] Step 5:

[1523] The server generates new product ideas taking into account market trends and consumer needs.

[1524] Specific operation:

[1525] The server analyzes market data and generates new product ideas, such as a "modern design ceramic tableware set."

[1526] Step 6:

[1527] The server selects and proposes the most suitable collaboration partner for the new product idea.

[1528] Specific operation:

[1529] The server searches a database of domestic and international ceramic manufacturers and designers and lists suitable partners to manufacture the new ceramic tableware set.

[1530] Step 7:

[1531] The terminal displays the new product proposals and collaboration partner candidates sent from the server to the user.

[1532] Specific operation:

[1533] The terminal displays a design proposal for a new ceramic tableware set and a list of recommended partners on a user interface.

[1534] Step 8:

[1535] The user inputs feedback about the proposed ideas and partners and sends it to the server.

[1536] Specific operation:

[1537] The user enters feedback on the device, such as "I would like more design variations," and presses the send button.

[1538] Step 9:

[1539] The server analyzes the received feedback and identifies improvements for the next implementation process.

[1540] Specific operation:

[1541] The server analyzes the text of user feedback and determines that the algorithm needs to be improved to increase design variation.

[1542] Step 10:

[1543] The server updates the system's algorithms and database based on the analysis results, improving the accuracy of the entire system.

[1544] Specific operation:

[1545] Based on the feedback, the server improves the machine learning algorithm and updates the model to generate diverse design proposals.

[1546] Example 1

[1547] 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."

[1548] In the conventional product development process for craftsmanship, data collection and analysis were time-consuming, making it difficult to efficiently generate new product ideas and propose appropriate collaboration partners. There was also a lack of mechanisms for appropriately incorporating user feedback and improving the system. This limited the speed and quality of product development.

[1549] 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.

[1550] In this invention, the server includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas utilizing craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for collecting user feedback, means for improving the system based on the collected feedback, means for acquiring data on craft techniques using an external API, means for visually visualizing the analysis results, and means for using a generative AI model when generating new product ideas. This makes it possible to efficiently generate new product ideas based on craft techniques and propose appropriate collaboration partners, and to continuously improve the system by utilizing user feedback.

[1551] "Craftsmanship" refers to crafts made using traditional methods and techniques, as well as related manufacturing processes, materials and designs.

[1552] "Means of collecting data" refers to devices and systems for obtaining information related to craft techniques from various databases and external APIs.

[1553] "Means for analyzing data from multiple perspectives" refers to techniques and methods for analyzing collected data from various perspectives and extracting specific information.

[1554] "Means for generating new product ideas" refers to devices and methods for devising new crafts and their applied products based on the results of the analysis.

[1555] "Means for proposing collaborative partners" refers to devices and systems for selecting and proposing the most suitable collaborating companies and craftsmen to realize new product ideas.

[1556] "Means for displaying the proposal results on the user terminal" refers to a device or system for visually showing the proposal contents sent from the server to the user.

[1557] "Means for collecting user feedback" refers to a device or system for obtaining opinions and ratings provided by users.

[1558] "Means for improving the system based on feedback" refers to techniques and methods for analyzing collected feedback and improving the performance and accuracy of the system.

[1559] "Means of obtaining data using external APIs" refers to programs and systems for obtaining information from external databases and services via the Internet.

[1560] "Visual visualization means" refers to devices and technologies for converting and displaying the results of data analysis in a visual format such as a graph or chart.

[1561] "Means for using generative AI models" refers to devices or programs that utilize models using artificial intelligence technology to generate new ideas and concepts.

[1562] An embodiment of the present invention relates to a system that efficiently generates ideas for new products based on craft techniques and proposes collaboration partners, and realizes continuous improvement of the system based on user feedback.

[1563] Technical data collection

[1564] The server collects data about craft techniques, using internal databases and external APIs to obtain technical information, manufacturing processes, materials used, historical background, and artisan information.

[1565] For example, the server collects technical information about "ceramics" from various databases, including the ceramic manufacturing process, the types of clay and glazes used, and the history of famous artisans and their works.

[1566] Data Analysis and Visualization

[1567] We analyze the technical data collected by the server from multiple angles, cleanse the data, extract specific strengths, weaknesses, rarity, and points of differentiation from competitors, and generate visual graphs and charts to visualize the analysis results.

[1568] As a specific example, the server analyzes data on ceramics, identifies its strengths as durability, aesthetic value, and rare manufacturing techniques, and summarizes these in a radar chart for each characteristic.

[1569] Generate new product ideas

[1570] The server generates new product ideas based on the analysis results, using algorithms that take into account market trends and consumer needs, and utilizing generative AI models to propose new product ideas.

[1571] As a concrete example, the server generates design proposals for a new set of tableware using ceramic techniques. Based on market data, the following prompt is used to reflect the desire for a simple, modern design:

[1572] "Please propose a new design for a ceramic tableware set, taking into consideration current market trends."

[1573] Matching collaboration partners

[1574] The server searches a database for the best candidates for collaboration partners for a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[1575] As a concrete example, the server considers mass production of a new ceramic tableware set and lists the most suitable partners from a database of ceramic manufacturers and designers both in Japan and overseas.

[1576] Presentation of proposed results

[1577] The terminal displays the new product ideas and partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[1578] For example, the device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[1579] Feedback and Improvements

[1580] Users provide feedback to the system, and the server uses that feedback to improve the system's accuracy. Users input their opinions about proposed ideas and partners, and the server analyzes them to identify areas for improvement.

[1581] As a concrete example, a user can send feedback to the server such as "I would like more design variations," and the server will analyze this and improve its algorithm to generate more diverse design proposals next time.

[1582] This system will enable the creation of new product value by maximizing the use of traditional Japanese craft techniques and modern artisanal skills, and will enable the efficient search for suitable collaboration partners. Furthermore, the system will be continuously improved through user feedback, enabling the creation of better proposals.

[1583] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1584] Step 1:

[1585] A server collects data about craft skills.

[1586] Input: The server takes input from internal database queries and request parameters from external APIs.

[1587] Data processing: The server retrieves data from these sources and cleanses it by detecting duplicates and missing information.

[1588] Output: A clean set of craft data is produced.

[1589] Specific operation: The server sends an HTTP request to the specified API endpoint, receives technical information as a response, and issues a SELECT query to extract data from the internal database.

[1590] Step 2:

[1591] The technical data collected by the server is analyzed from multiple perspectives.

[1592] Input: The clean data collected in step 1.

[1593] Data processing: The server uses statistical analysis, text mining techniques, etc. to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors.

[1594] Output: Characteristic data as the analysis result and visualization data based on it are generated.

[1595] Specific operation: The server calls statistical functions to analyze the collected data and generates the results as radar charts and graphs.

[1596] Step 3:

[1597] The server generates new product ideas based on the analysis results.

[1598] Inputs: Analysis results generated in step 2. External data on market trends and consumer needs.

[1599] Data processing: The server uses the generative AI model to generate new product ideas.

[1600] Output: A prototype of the new product idea is generated.

[1601] Specific operation: The server inputs the prompt statement and analysis results into the generative AI model and obtains the output idea data.

[1602] Step 4:

[1603] The server searches for and evaluates potential collaboration partners related to the new product idea.

[1604] Input: Prototype of new product idea generated in step 3. Database of collaboration partners.

[1605] Data processing: Scoring potential partners based on suitability criteria and shortlisting the most suitable partners.

[1606] Output: A list of high-scoring partner candidates is generated.

[1607] What it does: The server queries internal and external partner databases and applies a rating algorithm to generate a score.

[1608] Step 5:

[1609] The terminal displays the new product ideas and partner candidates sent from the server to the user.

[1610] Input: Partner candidate list generated in step 4. Prototype of new product idea.

[1611] Data processing: Visually display information using a GUI.

[1612] Output: Display of design proposals and partner list.

[1613] Specific operation: The device applies the data obtained from the server to the GUI components and renders it on the screen.

[1614] Step 6:

[1615] The user provides feedback to the system.

[1616] Input: Ratings and opinions on new product ideas and potential partners.

[1617] Data processing: Collect feedback and send it to the server.

[1618] Output: Sending feedback data.

[1619] Specific behavior: A user enters their opinion into the feedback form and clicks the submit button, which sends an HTTP POST request to the server.

[1620] Step 7:

[1621] The server analyzes user feedback to improve the accuracy of the system.

[1622] Input: Feedback data collected in step 6.

[1623] Data processing: Analyzing feedback data to identify areas for improvement in algorithms and models.

[1624] Output: Improved algorithms and models.

[1625] Specific operation: The server analyzes the feedback data using natural language processing technology and adjusts and optimizes the generative AI model and related algorithms based on the insights gained.

[1626] (Application example 1)

[1627] 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."

[1628] Conventional methods of providing information about crafts make it difficult for customers to learn detailed technical information or the manufacturing background of crafts. Furthermore, developing new products and selecting appropriate collaboration partners are not easy, and there is a lack of mechanisms for incorporating user feedback into the system. Furthermore, the interactive information provided to customers in craft displays in physical stores is limited, creating a need for an improved customer experience.

[1629] 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.

[1630] In this invention, the server includes a means for collecting data on craft techniques, a means for multifaceted analysis of the collected craft technique data, and a means for generating new product ideas that utilize craft techniques based on the analysis results. This enables the provision of detailed technical information on crafts, the development of new products, and the selection of collaboration partners. Furthermore, by including a means for visually displaying craft information using augmented reality, the customer experience in physical stores can be improved.

[1631] "Craftsmanship" refers to the techniques used by artisans to create artistic products by hand using traditional methods and techniques.

[1632] "Data collection means" refers to the mechanism for obtaining necessary information from internal databases related to craft techniques and external APIs.

[1633] "Data analysis means" refers to a system for cleansing collected craft technology data and analyzing it from multiple perspectives.

[1634] "New product idea generation means" refers to a system for proposing new crafts and their designs based on analyzed data.

[1635] The "means for proposing collaboration partners" refers to a mechanism for proposing optimal manufacturing partners or collaborators for the new product ideas that have been generated.

[1636] "User terminal display means" refers to a mechanism for displaying the proposal results and related information on a device that is directly operated by the user.

[1637] "Feedback collection means" refers to a mechanism for collecting user opinions and requests into the system.

[1638] "System improvement measures" refer to mechanisms for improving the system's algorithms and functions based on collected feedback.

[1639] "Augmented reality display means" refers to a mechanism for visually displaying additional information about real-world artifacts via a smartphone or dedicated device.

[1640] As an embodiment of the present invention, a processing flow of a new craft product suggestion system will be described.

[1641] Overall system configuration

[1642] This system mainly consists of three entities: a server, a terminal, and a user. The server collects and analyzes data, generates suggestions, and analyzes feedback. The terminal provides information to the user and collects feedback. It also uses augmented reality (AR) to visually display information about real crafts.

[1643] Server Roles

[1644] 1. Collection of technical data

[1645] The server primarily collects data about craft techniques through internal databases and external APIs. This data includes information about the manufacturing process, materials, historical background, and the artisans involved. For example, it collects technical information about ceramics, including details about the manufacturing process, clays, and glazes used.

[1646] 2. Data analysis and visualization

[1647] The server then cleanses the collected data and performs a multifaceted analysis, extracting strengths, weaknesses, rarity, and points of differentiation from competitors, and presenting these in visual formats such as radar charts. This analysis identifies characteristics such as the durability, aesthetic value, and rare manufacturing techniques of ceramics, for example.

[1648] 3. New product idea generation

[1649] Based on the analysis results, the server generates new product ideas, taking into account market trends and consumer needs through an algorithm, suggesting new product ideas such as a tableware set with a simple, modern design.

[1650] 4. Matching collaboration partners

[1651] The server searches its database for the optimal partner for the new product idea and proposes it, using criteria such as technical capabilities and past performance as criteria. For example, it could create a list of optimal partners from ceramic manufacturers and designers both in Japan and overseas.

[1652] Device Role

[1653] 1. Displaying the proposed results

[1654] The terminal displays new product ideas and potential collaboration partners sent from the server in a visually easy-to-understand format to the user. For example, it displays a design idea for a new ceramic tableware set and a list of recommended partners.

[1655] 2. Augmented reality features

[1656] The device is equipped with an AR function, allowing users to visually display product information, manufacturing process, and artisan information by pointing the camera at an actual craft item.

[1657] User Roles

[1658] 1. Providing Feedback

[1659] Users can provide their opinions and requests regarding the displayed suggestions. For example, they can send feedback such as "I would like more design variations."

[1660] System Improvement

[1661] The server collects and analyzes user feedback to improve the system's algorithms and functions, and also incorporates the collected feedback into future proposals.

[1662] Hardware and software used

[1663] The system uses the following hardware and software:

[1664] Hardware: Server, smartphone (or tablet)

[1665] Software: Flask (web framework), SQLite (database), NLTK (text analysis)

[1666] Examples and prompts

[1667] (Example)

[1668] User example 1: A customer visiting a physical store wants to learn about the manufacturing techniques behind a new tea bowl. By pointing their smartphone camera at the bowl, AR will display background information about the manufacturing process and the craftsman.

[1669] User example 2: When a user enters their idea for tableware using a durable and rare glaze into the app, new product ideas and collaboration partners based on that idea are displayed.

[1670] (Example of a prompt)

[1671] "Generate new ceramic design ideas. The target audience is young people in their 20s who want simple, modern designs."

[1672] "Please suggest improvements to increase product variety based on the feedback below. Feedback: I would like more design variations."

[1673] The above is a detailed embodiment of the present invention. This system makes it possible to propose new products that utilize craft techniques, provide effective information, and improve customer experience.

[1674] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1675] Step 1:

[1676] The server collects data about craft techniques. As input, it receives information from external APIs and internal databases. This data includes manufacturing processes, materials, historical background, artisan information, etc. The server retrieves this data and stores it in the internal database. The output is the collected raw data.

[1677] Step 2:

[1678] The data collected by the server is cleansed and analyzed from multiple perspectives. The input is the raw data collected in step 1. Data cleansing removes incomplete and duplicate data. The cleansed data is then analyzed using analytical algorithms to extract strengths, weaknesses, rarity, and points of differentiation from competitors. The output is a summary of the analysis results, and visualized data such as radar charts is also generated.

[1679] Step 3:

[1680] The server generates new product ideas based on the analysis results. The input is the analysis results obtained in step 2. A generative AI model is used to generate new product designs and concepts, taking into account market trends and consumer needs. Prompt statements are used to instruct the generative AI model. The output is details of the new product ideas.

[1681] Step 4:

[1682] The server proposes optimal collaboration partners for new product ideas generated by the server. The input is the new product idea generated in step 3. An algorithm that takes into account past performance and technical capabilities is used to search for optimal collaboration partners from a database. The output is a list of candidate collaboration partners.

[1683] Step 5:

[1684] The terminal visually displays the proposal results from the server to the user. The input is the new product idea and list of collaboration partners obtained in step 4. The information is displayed in a format that is easy for the user to understand. For example, a design proposal for a new ceramic tableware set and a list of recommended partners are displayed on the screen. The output is the displayed information.

[1685] Step 6:

[1686] The device displays information about the craft using augmented reality. The input is video data acquired when the user points the smartphone camera at the craft. The device displays detailed information about the craft obtained from the server as AR. For example, if the camera is pointed at an actual tea bowl, the manufacturing process and background information about the craftsman will be displayed on the screen. The output is information displayed using augmented reality.

[1687] Step 7:

[1688] The user enters feedback based on the information provided. The input is the user's opinion or request. For example, the user may send feedback such as "I would like more design variations." The output is the collected feedback data.

[1689] Step 8:

[1690] The server collects user feedback and improves the system. The input is the feedback data collected in step 7. The feedback is analyzed and used as data to improve the system's algorithms and functions, which can then be reflected in the next proposal. The output is improved system settings and algorithms.

[1691] 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.

[1692] As an embodiment of the present invention, the processing flow of the entire system that combines the emotion engine will be explained in natural language below. The roles of each entity, the server, terminal, and user, will be explained along with specific examples.

[1693] 1. Collection of technical data

[1694] The server collects data about craft techniques. Through an internal database or external API, the server obtains technical information, manufacturing processes, materials used, historical background, and information about the artisans involved.

[1695] Examples:

[1696] The server accesses a database on "ceramics" and retrieves information on the manufacturing process, material characteristics, historical background, and associated craftsmen.

[1697] 2. Data analysis and visualization

[1698] The server analyzes the collected technical data from multiple angles. It cleanses the data and extracts specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts to visualize the analysis results.

[1699] Examples:

[1700] The server then applies machine learning algorithms to the ceramic data, assessing its durability, aesthetic value, and the rarity of its manufacturing techniques, to identify its strengths and weaknesses, which are then compiled into a radar chart for each characteristic.

[1701] 3. New product idea generation

[1702] The server generates new product ideas based on the analysis results, using an algorithm that takes into account market trends and consumer needs to propose new product ideas.

[1703] Examples:

[1704] The server generates design proposals for a new set of tableware using ceramic techniques, based on market data that reflects the desire for simple, contemporary designs.

[1705] 4. Matching collaboration partners

[1706] The server searches a database for potential partners best suited to a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[1707] Examples:

[1708] With the aim of mass-producing a new ceramic tableware set, the server compiles a list of optimal partners from a database of domestic and international ceramic manufacturers and designers.

[1709] 5. Presentation of proposed results

[1710] The terminal displays the new product ideas and collaboration partner candidates sent from the server to the user. The terminal presents the received data to the user in a visually easy-to-understand format.

[1711] Examples:

[1712] The device displays design ideas for a new ceramic tableware set and a list of recommended partners, allowing users to consider partner collaboration.

[1713] 6. Emotion Recognition by Emotion Engine

[1714] The device recognizes the user's emotion using the emotion engine when the user inputs feedback, and transmits not only the user's feedback but also the emotion information to the server.

[1715] Examples:

[1716] The device analyzes the user's facial expressions and voice to recognize emotions such as "happiness" or "dissatisfaction." When the user gives feedback such as "I'm impressed" about the design of a new tableware set, that emotion is also analyzed.

[1717] 7. Collecting feedback and sentiment data

[1718] The server receives and analyzes the feedback and emotional data sent from the device, thereby understanding the user's true reaction and utilizing it for future suggestions.

[1719] Examples:

[1720] The server analyzes feedback such as "I want more design variations" and feelings of "dissatisfaction" and reflects this in the next new product proposal.

[1721] 8. Continuous improvement of the system

[1722] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[1723] Examples:

[1724] The server implements new algorithms based on data from the emotion engine and makes adjustments to generate better emotion-based product suggestions.

[1725] In this way, by combining an emotion recognition engine, it is possible to make the most of traditional Japanese craft techniques and modern artisan skills to create new product value, as well as to realize a system that makes even more accurate suggestions based on feedback based on the user's emotions.

[1726] The processing flow will be explained below.

[1727] Step 1:

[1728] The server connects to an internal database and external APIs to collect information about craft techniques, including technical information, manufacturing processes, materials used, historical background, and artisan information.

[1729] Specific operation:

[1730] The server retrieves information from a ceramics database about the manufacturing process, the types of clay and glazes used, historical background, and artisans.

[1731] Step 2:

[1732] The server pre-processes the collected craft data, cleansing it, filling in missing values, and removing outliers.

[1733] Specific operation:

[1734] The server cleanses the acquired ceramic data, identifying and completing incomplete data and outliers.

[1735] Step 3:

[1736] The server analyzes the data from multiple angles and applies machine learning algorithms to extract the strengths, weaknesses, and rarity of the craftsmanship, as well as points of differentiation from competitors.

[1737] Specific operation:

[1738] The server analyzes the ceramics' data, assessing their durability, aesthetic value, and the rarity of their manufacturing techniques, and identifies their strengths and weaknesses.

[1739] Step 4:

[1740] The server visualizes the analysis results, generating graphs and charts based on the extracted features and summarizing them in a visually easy-to-understand format.

[1741] Specific operation:

[1742] The server displays the strengths and weaknesses of ceramics in the form of radar charts, heat maps, and other formats.

[1743] Step 5:

[1744] The server generates new product ideas taking into account market trends and consumer needs. Using an algorithm, the server combines collected data with market needs to propose new product ideas.

[1745] Specific operation:

[1746] The server analyzes market data and generates a new product idea: a "modern design ceramic tableware set."

[1747] Step 6:

[1748] The server searches a database for the most suitable partner for a new product idea and proposes it. Suitability is evaluated based on technical capabilities and past performance.

[1749] Specific operation:

[1750] The server searches a database of domestic and international ceramic manufacturers and designers, and lists suitable partners for mass production of new ceramic tableware sets.

[1751] Step 7:

[1752] The terminal displays the new product ideas and collaboration partner candidates sent from the server to the user, and displays the received data in a visually easy-to-understand format.

[1753] Specific operation:

[1754] The terminal displays a design proposal for a new ceramic tableware set and a list of recommended partners on a user interface.

[1755] Step 8:

[1756] The device uses an emotion engine to recognize the user's emotions when the user inputs feedback, analyzes the user's facial expressions and voice, and transmits the emotional information to the server.

[1757] Specific operation:

[1758] When a user inputs feedback such as "I'm happy" about a new ceramic design, the device analyzes the user's facial expression and intonation of the voice to recognize the emotion of "joy."

[1759] Step 9:

[1760] The server receives and analyzes the feedback and emotion data sent from the device, and evaluates new product ideas based on the user's emotions and feedback.

[1761] Specific operation:

[1762] The server analyzes the feedback such as "great design" and the emotion data such as "delight" to ensure that the new design is well-received.

[1763] Step 10:

[1764] The server improves the system based on feedback and emotional data, refining the algorithm and making adjustments to improve the accuracy of the next suggestion.

[1765] Specific operation:

[1766] The server updates the machine learning algorithm based on the feedback, including the emotional data, and makes adjustments to generate more emotionally sensitive product suggestions next time.

[1767] The above is the specific processing flow of the entire system that combines the emotion engine. This will realize a system that makes the most of traditional Japanese craftsmanship and modern artisan skills to create new product value and makes highly accurate, integrated proposals based on user emotional feedback.

[1768] Example 2

[1769] 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."

[1770] Traditional craft data collection and analysis systems lack sufficient accuracy and flexibility in generating new product ideas and recommending optimal collaboration partners. They also lack effective methods for properly collecting user feedback and incorporating it into future proposals. Furthermore, feedback analysis does not take user emotions into account, making it difficult to understand users' authentic reactions and continuously improve the system.

[1771] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1772] In this invention, the server includes means for collecting information on craft techniques, means for analyzing the collected craft technique information from various angles, means for generating new product ideas that utilize craft techniques based on the analysis results, means for proposing optimal collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for collecting user feedback, means for improving the system based on the collected feedback and emotional data, and means for recognizing user emotions using an emotion recognition engine. This enables multifaceted analysis of the collected data, generation of new product ideas and proposals for optimal collaboration partners, and analysis of user feedback including emotional data, thereby realizing continuous improvement of the system.

[1773] "Craftsmanship information" includes technical information about the craft, the manufacturing process, materials used, historical background, and information about the artisans involved.

[1774] "Collection means" refers to the means for collecting information via various databases and external APIs.

[1775] "Means for analyzing from multiple angles" refers to technical means for analyzing collected information from multiple angles and extracting its strengths, weaknesses, rarity, and points of differentiation from competitors.

[1776] "Means for generating new product ideas" means techniques for generating new product designs and concepts, taking into account market trends and consumer needs.

[1777] The "means of proposing the most suitable collaboration partner" is a technology that searches a database for and proposes the most suitable collaboration partner candidate for a new product proposal based on technical capabilities and past performance.

[1778] The "means for displaying the proposal results on the user terminal" refers to a technical means for displaying the generated new product proposals and collaboration partner candidates on the user terminal.

[1779] "Means for collecting feedback from users" refers to means for collecting opinions and evaluations from users.

[1780] "Means for improving the system based on feedback and emotional data" refers to technical means for analyzing feedback and emotional data from users and improving the system algorithms and design proposals based on this.

[1781] An "emotion recognition engine" is a technology for recognizing a user's emotions, analyzing emotions such as joy, sadness, and anger from facial expressions and voice.

[1782] As an embodiment of the present invention, the processing flow of the entire system is shown below. This system mainly involves collaboration between the server, terminals, and users, and uses various technologies to propose new products and collect feedback.

[1783] 1. Collection of technical data

[1784] The server collects information about craft techniques. It connects to an internal database (e.g., MongoDB) and also retrieves technical information, manufacturing processes, materials used, historical background, and related artisan information from external sources through a RESTful API.

[1785] Example: A server accesses a database about "ceramics" and retrieves information about the manufacturing process, material properties, historical background, and associated artisans.

[1786] 2. Data analysis and visualization

[1787] The server analyzes the collected information from multiple angles using Python and R. It cleanses the data and uses machine learning algorithms such as k-means clustering to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors. Based on this, it generates visual graphs and charts using Matplotlib and Plotly to visualize the analysis results.

[1788] Example: A server runs data on ceramics through a machine learning algorithm to evaluate its durability, aesthetic value, rarity of manufacturing techniques, etc., and identify its strengths and weaknesses. These are then compiled into a radar chart for each characteristic.

[1789] 3. New product idea generation

[1790] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate new product ideas. The server uses algorithms based on market trends and consumer needs to propose new product ideas.

[1791] Example: A server prompts a generative AI model with the prompt "Generate ideas for a new ceramic tableware set with a modern design" and receives the generated ideas.

[1792] 4. Matching collaboration partners

[1793] The server searches a database (e.g., MySQL) for the best partner candidates for a new product idea and proposes them. Suitability is evaluated based on factors such as technical capabilities and past performance.

[1794] Example: Using an SQL query to find relevant partners in a database, calculate a reputation score and shortlist the best partners.

[1795] 5. Presentation of proposed results

[1796] The device displays new product ideas and potential collaboration partners sent from the server to the user, using JavaScript and HTML5 to present the data in a visually easy-to-understand manner.

[1797] Example: Using React.js on the front end, we display the design of new product ideas and a list of partners. Once the user selects a partner, details of the partner candidate are also displayed in a popup.

[1798] 6. Emotion Recognition by Emotion Engine

[1799] When the user inputs feedback, the device uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion, and then sends the user's feedback and emotional information to the server.

[1800] Example: When filling out a form, a webcam captures the user's facial expression, and the image data is sent to the Emotion API to recognize emotions. The resulting emotional data, such as "happiness" or "sadness," is then displayed.

[1801] 7. Collecting feedback and sentiment data

[1802] The server receives the feedback and emotion data sent from the device and analyzes it using Python's Pandas, which allows the server to understand the user's true reaction and use it to improve the next experience.

[1803] Example: The server combines the received feedback "I like the new design" with the emotion data "joy" and performs detailed analysis using a text analysis tool.

[1804] 8. Continuous improvement of the system

[1805] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[1806] Example: Using the results of a sentiment analysis engine, we can update the training dataset for a machine learning model and improve the algorithm that generates new design ideas.

[1807] In this way, by combining the emotion recognition engine, we have created a system that can make highly accurate new product proposals through the collection and analysis of craft technology data, the generation of new product ideas, the proposal of collaboration partners, and the collection and analysis of feedback. This system can reflect user feedback based on their emotions and make continuously improved new product proposals.

[1808] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1809] The flow of this system's program processing

[1810] Step 1:

[1811] The server collects information about craft techniques, connecting to an internal database (e.g., MongoDB) and also retrieving technical information, manufacturing processes, materials used, historical background, and related artisan information from external sources through a RESTful API.

[1812] Input: Database configuration information, external API endpoint

[1813] Output: List of collected crafting and technical information

[1814] What it does: Reads the configuration file "config.json", gets the database URL and authentication information, connects to it using a MongoDB client, sends a GET request to an external API endpoint, and retrieves the returned JSON data.

[1815] Step 2:

[1816] The server cleanses the collected information, completing missing data values ​​and detecting and correcting inconsistencies.

[1817] Input: List of collected craft technical information

[1818] Output: A list of cleansed craft information

[1819] Specific operation: Using Python's Pandas library, the data is read into a DataFrame and cleansed, such as filling in missing values ​​with the mean value.

[1820] Step 3:

[1821] The server then performs multifaceted analysis of the cleansed data, using machine learning algorithms such as k-means clustering to extract the strengths, weaknesses, and rarity of the technology, as well as points of differentiation from competitors.

[1822] Input: Cleansed list of craft information

[1823] Output: A list of analysis results (strengths, weaknesses, rarity, points of differentiation from competitors)

[1824] What it does: Uses the Scikit-learn library to perform k-means clustering to divide the data into clusters, calculates the center value within each cluster, and identifies strengths and weaknesses.

[1825] Step 4:

[1826] The server visualizes the analysis results, generating graphs and charts using Matplotlib and Plotly.

[1827] Input: List of analysis results (strengths, weaknesses, rarity, points of differentiation from competitors)

[1828] Output: Visualized graphs and charts

[1829] What it does: Create a radar chart using Matplotlib to visually display the strengths and weaknesses of each technology.

[1830] Step 5:

[1831] The server uses generative AI models (e.g., OpenAI GPT-4) to generate new product ideas, using algorithms based on market trends and consumer needs.

[1832] Input: Prompt statement (e.g., "Generate ideas for a new ceramic tableware set with a modern design"), analysis results

[1833] Output: List of new product ideas

[1834] Specific operation: Provide a prompt to the generative AI model and receive the generated ideas.

[1835] Step 6:

[1836] The server searches a database (e.g., MySQL) for the best partner candidates for the new product idea and proposes them. They are evaluated based on their technical capabilities and past performance.

[1837] Input: List of new product ideas, partner database

[1838] Output: A list of suitable collaboration partners

[1839] What it does: Uses an SQL query to find relevant partners in the database, calculates a rating score and lists the best partners.

[1840] Step 7:

[1841] The device displays new product ideas and potential collaboration partners sent from the server to the user, using JavaScript and HTML5 to present the data in a visually easy-to-understand manner.

[1842] Input: List of new product ideas, list of suitable collaboration partners

[1843] Output: New product ideas and potential collaboration partners displayed to the user

[1844] Specific operation: Using React.js on the front end, we display the design of new product ideas and a list of partners. Details of the partner candidates selected by the user are also displayed in a popup.

[1845] Step 8:

[1846] When the user inputs feedback, the device uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotion, and then sends the user's feedback and emotional information to the server.

[1847] Input: Feedback text, user facial expressions and voice data

[1848] Output: Recognized emotion data, feedback sentence

[1849] Specific operation: When filling out a form, the system captures the user's facial expression with a webcam, sends the image data to the Emotion API, and recognizes their emotions. The resulting emotional data, such as "happiness" or "sadness," is then displayed.

[1850] Step 9:

[1851] The server receives and analyzes the feedback and emotion data sent from the device. It uses Python's Pandas to analyze the data and understand the user's true reaction.

[1852] Input: Feedback sentence, emotion data

[1853] Output: Report of analysis results

[1854] Specific operation: The server combines the received feedback "I like the new design" with the emotion data "joy" and performs detailed analysis using text analysis tools.

[1855] Step 10:

[1856] The server improves the system based on feedback, including emotional data. Based on the emotion recognition results and feedback analysis results, the system aims to improve the algorithm and diversify design proposals.

[1857] Input: Analysis results report

[1858] Output: Improved algorithm, list of new design alternatives

[1859] What it does: Based on the results of the sentiment analysis engine, it updates the training dataset for the machine learning model and improves the algorithm that generates new design ideas.

[1860] The above steps work together to create a system that proposes new products based on craft techniques and performs feedback analysis.

[1861] (Application example 2)

[1862] 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."

[1863] In the traditional craft technology data collection, analysis, and product creation process, it is common to have a function for collecting user feedback, but there is a problem in that it is difficult to accurately recognize user emotions and improve the system based on that emotional data. This makes it difficult to understand users' true reactions and make more accurate product suggestions.

[1864] 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.

[1865] In this invention, the server includes means for collecting data on craft techniques, means for multifaceted analysis of the collected craft technique data, means for generating new product ideas utilizing craft techniques based on the analysis results, means for proposing appropriate collaboration partners for the generated new product ideas, means for displaying the proposal results on a user terminal, means for recognizing user emotions, means for collecting feedback and emotional data from users, and means for improving the system based on the collected feedback and emotional data. This enables more accurate product suggestions by accurately understanding the user's emotional state and reflecting emotional feedback.

[1866] "Craftsmanship" refers to the art of producing fine and practical items using traditional or modern techniques.

[1867] "Means for collecting data" refers to the methods and devices used to obtain specific data and store it in the database.

[1868] "Means for multifaceted analysis" refers to methods and devices for analyzing collected data from multiple perspectives to gain a comprehensive understanding.

[1869] "Means for generating new product ideas" refers to methods or devices for generating ideas for new products or services based on collected and analyzed data.

[1870] The "means for proposing collaboration partners" refers to a method or device for selecting and proposing appropriate collaborators or companies based on the generated new product ideas.

[1871] "Means for displaying on a user terminal" refers to a method or apparatus for displaying information on a user's device (e.g., smartphone, tablet, or PC).

[1872] "Means for recognizing emotions" refers to a method or device for detecting and analyzing a user's emotions.

[1873] "Means for collecting feedback and emotional data" refers to a method or device for capturing a user's opinions and emotional state and storing them in a database.

[1874] "Means for improving the system" refers to methods and devices for improving the system's functionality and performance based on collected feedback and sentiment data.

[1875] The system of the present invention is constructed with the participation of a server, a terminal, and a user.

[1876] 1. Data Collection Module

[1877] The server has the function of collecting data on craft techniques. The data is obtained through internal databases and external APIs. For example, it accesses a database on "ceramics" to obtain information on the manufacturing process, material properties, historical background, and related craftspeople.

[1878] 2. Data Analysis and Visualization Module

[1879] The server runs algorithms to analyze the collected data from multiple angles. The collected data is cleansed to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors. The analysis results are then displayed visually as graphs and charts. For example, data on ceramics can be run through a machine learning algorithm to evaluate durability, aesthetic value, and the rarity of manufacturing techniques, and the results can be summarized in a radar chart.

[1880] 3. New product idea generation module

[1881] The server generates new product ideas using an algorithm that takes into account market trends and consumer needs. For example, the server may generate a design proposal for a new tableware set using ceramic techniques, reflecting market data that indicates a demand for simple, modern designs.

[1882] 4. Collaboration Partner Matching Module

[1883] The server searches its database for the best possible partner for a new product idea and suggests them. For example, if a new ceramic tableware set is being mass-produced, the server will compile a list of ceramic manufacturers and designers both in Japan and overseas.

[1884] 5. Proposal result display module

[1885] The terminal has a function to display new product ideas and potential collaboration partners sent from the server to the user. For example, the terminal displays a design idea for a new ceramic tableware set and a list of recommended partners, allowing the user to consider collaboration with an appropriate partner.

[1886] 6. Emotion Recognition Module

[1887] The device uses an emotion engine to recognize the user's emotions when the user inputs feedback. For example, it uses a smartphone camera to analyze the user's facial expressions and voice and recognizes emotional states such as "happiness" or "dissatisfaction."

[1888] 7. Feedback and Emotion Data Collection Module

[1889] The server collects the feedback and emotion data sent from the device and stores it in a database. For example, when a user gives feedback such as "I'm impressed" about the design of a new tableware set, the emotion is also analyzed and sent to the server.

[1890] 8. System Improvement Module

[1891] The server improves the system based on the collected feedback and emotional data. Based on the results of emotion recognition and feedback analysis, the server aims to improve the algorithm and diversify design proposals. For example, the server could analyze feedback such as "We want more design variations" and the emotion of "dissatisfaction" and reflect this in the next new product proposal.

[1892] Examples:

[1893] For example, when a user of the "Traditional Crafts Virtual Market" is looking at the design of a new ceramic tableware set, the app can analyze the user's facial expression with a camera and detect "joy." If the user provides feedback on a design, such as "it's very beautiful," that emotional data is sent to the server. The server analyzes this data and reflects it in generating the next design proposal.

[1894] Example prompt sentence:

[1895] "Use the following feedback and emotion data to train an algorithm to generate new ceramic design ideas. Feedback: 'So beautiful' Emotion: 'Joy'"

[1896] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1897] Step 1:

[1898] A server collects data about the craft.

[1899] Input: Internal database or external API

[1900] Data processing: Through internal databases and external APIs, we obtain technical information, manufacturing processes, materials used, historical background, and information on related craftspeople.

[1901] Output: Collected database

[1902] Specific operation: The server accesses a database related to "ceramics," obtains various information, and stores it in the database.

[1903] Step 2:

[1904] The server analyzes the collected technical data from multiple perspectives.

[1905] Input: Collected database

[1906] Data calculation: Data is cleansed to extract specific strengths, weaknesses, rarity, and points of differentiation from competitors.

[1907] Output: Analysis results

[1908] How it works: The server runs the ceramic data through machine learning algorithms (such as TensorFlow or PyTorch) to evaluate the durability, aesthetic value, and rarity of the manufacturing technology, and then summarizes the ceramics' strengths and weaknesses in a radar chart.

[1909] Step 3:

[1910] The server generates new product ideas based on the analysis results.

[1911] Input: Analysis results

[1912] Data calculations: Using algorithms that take into account market trends and consumer needs, new product ideas are proposed.

[1913] Output: New product idea

[1914] What it does: The server uses market data to generate design ideas for a new ceramic dinnerware set, reflecting the desire for simple, contemporary designs.

[1915] Step 4:

[1916] The server searches a database for potential collaboration partners that are best suited to the new product idea and makes suggestions.

[1917] Input: New product idea

[1918] Data calculation: Evaluate the suitability of collaboration partners based on their technical capabilities and past performance.

[1919] Output: List of partners

[1920] Specific operation: The server compiles a list of suitable partner candidates from a database of domestic and international ceramic manufacturers and designers.

[1921] Step 5:

[1922] The terminal displays the new product proposals and collaboration partner candidates sent from the server to the user.

[1923] Input: New product ideas, potential partners

[1924] Output: Data displayed on the user's terminal

[1925] Specific operation: The device displays design proposals for a new ceramic tableware set and a list of recommended partners, which the user can review to consider partner collaboration.

[1926] Step 6:

[1927] The terminal recognizes the user's emotions using an emotion engine when the user inputs feedback.

[1928] Input: User's facial expression data, voice data

[1929] Data calculation: Using an emotion recognition library (e.g., OpenCV or Affectiva), analyze the user's facial expressions and voice to determine their emotional state.

[1930] Output: User emotion data

[1931] Specific operation: The smartphone camera is used to capture the user's facial expressions and analyze their emotional state, such as "happiness" or "dissatisfaction."

[1932] Step 7:

[1933] The server collects and analyzes the feedback and emotion data sent from the terminals.

[1934] Input: User feedback, emotional data

[1935] Data calculation: Analyze the feedback content and emotional data and use it for the next proposal.

[1936] Output: Analysis results

[1937] Specific operation: The server analyzes feedback such as "I would like more design variations" and "dissatisfaction" feelings, and reflects this in the next new product proposal.

[1938] Step 8:

[1939] The server improves the system based on feedback including emotional data.

[1940] Input: Analysis results

[1941] Data calculation: Improve the algorithm based on emotion recognition results and feedback analysis results.

[1942] Output: Updated system

[1943] What it does: The server implements a new algorithm and makes adjustments to generate better product suggestions based on emotions.

[1944] 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.

[1945] 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.

[1946] 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.

[1947] 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.

[1948] 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.

[1949] 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.

[1950] 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).

[1951] 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.

[1952] 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."

[1953] 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.

[1954] 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).

[1955] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1956] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1957] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1958] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1959] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1960] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1961] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an ent...

Claims

1. a means of collecting data on craft skills; A means of analyzing collected craft technology data from multiple angles, A means of generating new product ideas that utilize craft techniques based on the analysis results; A means for proposing appropriate collaboration partners for the generated new product ideas; means for displaying the proposal results on a user terminal; a means for collecting feedback from users; a means of improving the system based on the feedback collected; A system including:

2. The system according to claim 1, further comprising means for analyzing the craft technology data and visualizing its strengths, weaknesses, rarity, and points of differentiation from competitors.

3. The system according to claim 1 , further comprising means for displaying new product ideas and suitable collaboration partner candidates on a user terminal.

Images